Methylkit Results Analysis
Aaron Kovacs & Mark Ziemann
2021-10-16
Read in RDS files and display methylkit CpG and tile results pre-annotations
library(GenomicFeatures)## Loading required package: BiocGenerics## Loading required package: parallel##
## Attaching package: 'BiocGenerics'## The following objects are masked from 'package:parallel':
##
## clusterApply, clusterApplyLB, clusterCall, clusterEvalQ,
## clusterExport, clusterMap, parApply, parCapply, parLapply,
## parLapplyLB, parRapply, parSapply, parSapplyLB## The following objects are masked from 'package:stats':
##
## IQR, mad, sd, var, xtabs## The following objects are masked from 'package:base':
##
## anyDuplicated, append, as.data.frame, basename, cbind, colnames,
## dirname, do.call, duplicated, eval, evalq, Filter, Find, get, grep,
## grepl, intersect, is.unsorted, lapply, Map, mapply, match, mget,
## order, paste, pmax, pmax.int, pmin, pmin.int, Position, rank,
## rbind, Reduce, rownames, sapply, setdiff, sort, table, tapply,
## union, unique, unsplit, which.max, which.min## Loading required package: S4Vectors## Loading required package: stats4##
## Attaching package: 'S4Vectors'## The following objects are masked from 'package:base':
##
## expand.grid, I, unname## Loading required package: IRanges## Loading required package: GenomeInfoDb## Loading required package: GenomicRanges## Loading required package: AnnotationDbi## Loading required package: Biobase## Welcome to Bioconductor
##
## Vignettes contain introductory material; view with
## 'browseVignettes()'. To cite Bioconductor, see
## 'citation("Biobase")', and for packages 'citation("pkgname")'.library(BiocManager)
library(RCircos)
library(dplyr)##
## Attaching package: 'dplyr'## The following object is masked from 'package:AnnotationDbi':
##
## select## The following object is masked from 'package:Biobase':
##
## combine## The following objects are masked from 'package:GenomicRanges':
##
## intersect, setdiff, union## The following object is masked from 'package:GenomeInfoDb':
##
## intersect## The following objects are masked from 'package:IRanges':
##
## collapse, desc, intersect, setdiff, slice, union## The following objects are masked from 'package:S4Vectors':
##
## first, intersect, rename, setdiff, setequal, union## The following objects are masked from 'package:BiocGenerics':
##
## combine, intersect, setdiff, union## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(data.table)##
## Attaching package: 'data.table'## The following objects are masked from 'package:dplyr':
##
## between, first, last## The following object is masked from 'package:GenomicRanges':
##
## shift## The following object is masked from 'package:IRanges':
##
## shift## The following objects are masked from 'package:S4Vectors':
##
## first, secondlibrary(GenomicRanges)
methylkitCvG <- readRDS("/mnt/data/aaron/projects/guppy-methylation/CvG_mydiff.rds")
methylkitCvL <- readRDS("/mnt/data/aaron/projects/guppy-methylation/CvL_mydiff.rds")
methylkitGvL <- readRDS("/mnt/data/aaron/projects/guppy-methylation/GvL_mydiff.rds")
methylkitTilesCvG <- readRDS("/mnt/data/aaron/projects/guppy-methylation/CvG_tiles_mydiff.rds")
methylkitTilesCvL <- readRDS("/mnt/data/aaron/projects/guppy-methylation/CvL_tiles_mydiff.rds")
methylkitTilesGvL <- readRDS("/mnt/data/aaron/projects/guppy-methylation/GvL_tiles_mydiff.rds")
class(methylkitCvG)## [1] "methylDiff"
## attr(,"package")
## [1] "methylKit"head(methylkitCvG)## Loading required package: methylKit##
## Attaching package: 'methylKit'## The following object is masked from 'package:dplyr':
##
## select## The following object is masked from 'package:AnnotationDbi':
##
## select## chr start end strand pvalue qvalue meth.diff
## 1 KK215283.1 652 652 + 0.7481443 0.9891325 -2.8205128
## 2 KK215283.1 772 772 + 0.9363417 0.9891325 0.5875441
## 3 KK215283.1 773 773 + 0.6880001 0.9891325 -4.3548387
## 4 KK215283.1 775 775 + 0.4375961 0.9475893 7.8502415
## 5 KK215283.1 776 776 + 0.7661416 0.9891325 3.3724340
## 6 KK215283.1 846 846 + 0.9663473 0.9891325 -0.4597701methylkitCvGGR <- as(methylkitCvG,"GRanges")
head(methylkitCvGGR)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | pvalue qvalue meth.diff
## <Rle> <IRanges> <Rle> | <numeric> <numeric> <numeric>
## [1] KK215283.1 652 + | 0.748144 0.989133 -2.820513
## [2] KK215283.1 772 + | 0.936342 0.989133 0.587544
## [3] KK215283.1 773 + | 0.688000 0.989133 -4.354839
## [4] KK215283.1 775 + | 0.437596 0.947589 7.850242
## [5] KK215283.1 776 + | 0.766142 0.989133 3.372434
## [6] KK215283.1 846 + | 0.966347 0.989133 -0.459770
## -------
## seqinfo: 2455 sequences from an unspecified genome; no seqlengthsmethylkitCvGdf <- getData(methylkitCvG)
methylkitCvGdf <- methylkitCvGdf[order(methylkitCvGdf[,6]), ]
head(methylkitCvGdf,25)## chr start end strand pvalue qvalue
## 14011068 LG4 1847635 1847635 + 1.510121e-15 2.819262e-08
## 14011071 LG4 1847677 1847677 + 6.272684e-15 5.855272e-08
## 14011018 LG4 1846766 1846766 + 9.610321e-15 5.980539e-08
## 14011020 LG4 1846768 1846768 + 1.055213e-13 4.924975e-07
## 14011073 LG4 1847679 1847679 + 3.361816e-13 1.046036e-06
## 14011075 LG4 1847691 1847691 + 3.317211e-13 1.046036e-06
## 14011017 LG4 1846756 1846756 + 6.059313e-13 1.616029e-06
## 14011016 LG4 1846735 1846735 + 8.313745e-13 1.940128e-06
## 14011077 LG4 1847697 1847697 + 1.443677e-12 2.994685e-06
## 14011014 LG4 1846719 1846719 + 4.063471e-12 7.586140e-06
## 8691557 LG19 4233614 4233614 + 2.875857e-08 4.880882e-02
## 3610880 LG12 13448520 13448520 + 5.349979e-08 8.323281e-02
## 5207011 LG14 17323571 17323571 + 6.150734e-08 8.832981e-02
## 6685875 LG16 15182433 15182433 + 7.754818e-08 9.651705e-02
## 12677287 LG23 2943357 2943357 + 7.286739e-08 9.651705e-02
## 2825536 LG11 12136925 12136925 + 8.300126e-08 9.684750e-02
## 517357 KK215326.1 149266 149266 + 9.226900e-08 1.013283e-01
## 1048158 LG1 9567732 9567732 + 1.691159e-07 1.529661e-01
## 3766083 LG12 19761580 19761580 + 1.831455e-07 1.529661e-01
## 5777147 LG15 10776288 10776288 + 2.048384e-07 1.529661e-01
## 9937952 LG2 21695053 21695053 + 1.907840e-07 1.529661e-01
## 11092016 LG20 21573163 21573163 + 1.890608e-07 1.529661e-01
## 11395170 LG21 6285858 6285858 + 1.993305e-07 1.529661e-01
## 12626591 LG23 1238768 1238768 + 1.673776e-07 1.529661e-01
## 17849024 LG8 22188358 22188358 + 1.904135e-07 1.529661e-01
## meth.diff
## 14011068 69.49153
## 14011071 71.81818
## 14011018 73.61963
## 14011020 67.64706
## 14011073 69.15584
## 14011075 65.26210
## 14011017 62.43094
## 14011016 59.77654
## 14011077 65.58559
## 14011014 60.12658
## 8691557 60.09818
## 3610880 -61.90476
## 5207011 50.00000
## 6685875 -55.77342
## 12677287 59.44056
## 2825536 -67.14976
## 517357 61.82839
## 1048158 61.79894
## 3766083 65.14286
## 5777147 -48.68586
## 9937952 50.54720
## 11092016 59.31174
## 11395170 61.08059
## 12626591 59.25926
## 17849024 -64.28571rm(methylkitCvGdf)
rm(methylkitCvG)
methylkitCvLGR <- as(methylkitCvL,"GRanges")
head(methylkitCvLGR)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | pvalue qvalue meth.diff
## <Rle> <IRanges> <Rle> | <numeric> <numeric> <numeric>
## [1] KK215283.1 652 + | 0.603885 0.986634 3.939394
## [2] KK215283.1 772 + | 0.936342 0.986634 0.587544
## [3] KK215283.1 775 + | 0.410994 0.932767 8.225617
## [4] KK215283.1 846 + | 1.000000 0.986634 0.000000
## [5] KK215283.1 1662 + | 0.627224 0.986634 5.882353
## [6] KK215283.1 1693 + | 0.443300 0.946530 -11.578947
## -------
## seqinfo: 2441 sequences from an unspecified genome; no seqlengthsmethylkitCvLdf <- getData(methylkitCvL)
methylkitCvLdf <- methylkitCvLdf[order(methylkitCvLdf[,6]), ]
head(methylkitCvLdf,25)## chr start end strand pvalue qvalue meth.diff
## 7721640 LG17 28853681 28853681 + 1.798548e-10 0.003278925 -56.81818
## 8503892 LG19 4233614 4233614 + 8.650817e-10 0.007885634 65.96774
## 11916736 LG22 9603310 9603310 + 4.190343e-08 0.254646567 73.91304
## 231578 KK215289.1 44015 44015 + 1.152627e-07 0.420269993 48.78205
## 11130041 LG21 5357179 5357179 + 1.035762e-07 0.420269993 -50.00000
## 325243 KK215296.1 299902 299902 + 1.744510e-07 0.454344073 52.17391
## 8778728 LG19 15379719 15379719 + 1.573263e-07 0.454344073 -62.66667
## 6104680 LG15 28566314 28566314 + 2.404266e-07 0.459360945 57.14286
## 8987858 LG19 22845041 22845041 + 2.966095e-07 0.459360945 -50.23847
## 10246492 LG2 44850219 44850219 + 2.568048e-07 0.459360945 -59.52381
## 11230076 LG21 9433707 9433707 + 3.023610e-07 0.459360945 56.72269
## 14527798 LG5 1744620 1744620 + 2.175832e-07 0.459360945 -67.03297
## 8175112 LG18 14883427 14883427 + 3.366633e-07 0.472130294 -57.67974
## 3791209 LG12 24547758 24547758 + 3.809787e-07 0.496114701 64.53804
## 1368825 LG1 23778631 23778631 + 9.371466e-07 0.504339931 48.00000
## 1828348 LG10 6617961 6617961 + 1.000341e-06 0.504339931 61.17085
## 3002781 LG11 21115605 21115605 + 1.117066e-06 0.504339931 -66.66667
## 4293316 LG13 19073588 19073588 + 8.732201e-07 0.504339931 -58.21429
## 4377666 LG13 22916688 22916688 + 8.333341e-07 0.504339931 53.57143
## 5730121 LG15 13613929 13613929 + 6.050107e-07 0.504339931 -64.09938
## 6125647 LG15 29368498 29368498 + 7.646502e-07 0.504339931 -61.81818
## 6125649 LG15 29368505 29368505 + 5.045099e-07 0.504339931 -60.83333
## 7225939 LG17 6718269 6718269 + 4.912646e-07 0.504339931 64.47368
## 7748138 LG17 29983389 29983389 + 1.176367e-06 0.504339931 -50.39216
## 8250593 LG18 17381026 17381026 + 6.090395e-07 0.504339931 56.25000rm(methylkitCvLdf)
rm(methylkitCvL)
methylkitGvLGR <- as(methylkitGvL,"GRanges")
methylkitGvLdf <- getData(methylkitGvL)
methylkitGvLdf <- methylkitGvLdf[order(methylkitGvLdf[,6]), ]
head(methylkitGvLdf,25)## chr start end strand pvalue qvalue
## 15775362 LG4 1846766 1846766 + 5.358976e-19 1.121417e-11
## 15775428 LG4 1847697 1847697 + 4.085825e-16 4.274991e-09
## 15775425 LG4 1847679 1847679 + 1.170641e-15 6.124197e-09
## 15775427 LG4 1847691 1847691 + 1.160716e-15 6.124197e-09
## 15775423 LG4 1847677 1847677 + 2.302746e-15 9.637436e-09
## 15775363 LG4 1846768 1846768 + 7.446573e-12 2.597112e-05
## 15775361 LG4 1846756 1846756 + 1.483015e-11 4.433360e-05
## 15775419 LG4 1847635 1847635 + 5.926712e-11 1.550277e-04
## 15775358 LG4 1846719 1846719 + 1.834129e-10 4.264546e-04
## 15775360 LG4 1846735 1846735 + 7.537840e-10 1.577366e-03
## 13288679 LG21 20288461 20288461 + 1.359249e-08 2.585782e-02
## 13652786 LG22 8050874 8050874 + 1.705089e-08 2.973386e-02
## 14854930 LG3 2944320 2944320 + 4.672240e-08 7.520856e-02
## 8247430 LG17 4774357 4774357 + 5.842523e-08 8.732888e-02
## 734635 KK215575.1 1095 1095 + 6.462642e-08 9.015801e-02
## 16211675 LG4 17759254 17759254 + 9.387446e-08 1.227759e-01
## 18961734 LG7 15331208 15331208 + 1.269597e-07 1.562796e-01
## 8796778 LG17 25482375 25482375 + 1.597860e-07 1.795140e-01
## 12196059 LG20 12234657 12234657 + 1.629921e-07 1.795140e-01
## 4238691 LG12 19502054 19502054 + 1.880141e-07 1.925755e-01
## 9601845 LG18 21480291 21480291 + 2.024595e-07 1.925755e-01
## 16746238 LG5 2856738 2856738 + 1.999029e-07 1.925755e-01
## 6767945 LG15 19894012 19894012 + 2.367951e-07 2.154420e-01
## 15775364 LG4 1846769 1846769 + 3.273650e-07 2.740171e-01
## 20537503 LG9 9539135 9539135 + 3.187294e-07 2.740171e-01
## meth.diff
## 15775362 -69.27181
## 15775428 -68.91892
## 15775425 -69.78610
## 15775427 -68.38710
## 15775423 -71.92571
## 15775363 -56.01915
## 15775361 -52.01427
## 15775419 -56.33363
## 15775358 -51.03567
## 15775360 -48.66543
## 13288679 45.71429
## 13652786 50.00000
## 14854930 51.85185
## 8247430 59.65157
## 734635 -44.18605
## 16211675 -57.26654
## 18961734 -60.60606
## 8796778 -75.00000
## 12196059 -53.75000
## 4238691 48.00000
## 9601845 -56.17647
## 16746238 -53.47826
## 6767945 49.62963
## 15775364 -37.09677
## 20537503 -36.17021rm(methylkitGvLdf)
rm(methylkitGvL)
methylkitTilesCvGGR <- as(methylkitTilesCvG,"GRanges")
methylkitTilesCvGdf <- getData(methylkitTilesCvG)
methylkitTilesCvGdf <- methylkitTilesCvGdf[order(methylkitTilesCvGdf[,6]), ]
head(methylkitTilesCvGdf,25)## chr start end strand pvalue qvalue
## 452727 LG4 1847001 1848000 * 9.714622e-131 4.885614e-125
## 452726 LG4 1846001 1847000 * 1.196917e-89 3.009727e-84
## 277432 LG19 1188001 1189000 * 1.774652e-81 2.974987e-76
## 17240 KK215608.1 11001 12000 * 1.425147e-63 1.791814e-58
## 139886 LG13 18161001 18162000 * 3.721408e-59 3.743092e-54
## 373358 LG21 14273001 14274000 * 6.434827e-53 5.393601e-48
## 29769 LG1 9073001 9074000 * 3.550053e-47 2.550528e-42
## 361837 LG21 1055001 1056000 * 2.372031e-46 1.491158e-41
## 37257 LG1 17897001 17898000 * 1.654721e-42 9.246461e-38
## 6554 KK215291.1 217001 218000 * 1.040687e-37 5.233756e-33
## 276276 LG18 21720001 21721000 * 1.092368e-36 4.994240e-32
## 285193 LG19 10333001 10334000 * 1.033326e-35 4.330611e-31
## 374935 LG21 15969001 15970000 * 1.447251e-35 5.598784e-31
## 395397 LG22 14521001 14522000 * 7.000381e-34 2.514704e-29
## 603932 LG9 23623001 23624000 * 8.468147e-34 2.839163e-29
## 565560 LG8 6639001 6640000 * 1.585600e-33 4.983872e-29
## 17241 KK215608.1 12001 13000 * 2.987925e-33 8.839221e-29
## 452496 LG4 1567001 1568000 * 1.046181e-32 2.922992e-28
## 305547 LG2 5617001 5618000 * 1.142720e-32 3.024681e-28
## 389251 LG22 7737001 7738000 * 3.135507e-31 7.884441e-27
## 599781 LG9 18984001 18985000 * 9.747297e-31 2.334308e-26
## 389475 LG22 7968001 7969000 * 2.947477e-29 6.737845e-25
## 140733 LG13 19073001 19074000 * 3.615032e-29 7.904557e-25
## 480557 LG5 2971001 2972000 * 5.312984e-29 1.113321e-24
## 53954 LG10 3130001 3131000 * 5.768525e-29 1.148219e-24
## meth.diff
## 452727 19.239478
## 452726 19.897694
## 277432 -22.272263
## 17240 10.634437
## 139886 20.536203
## 373358 17.569509
## 29769 14.606176
## 361837 14.585360
## 37257 -6.231157
## 6554 16.920822
## 276276 -15.394290
## 285193 16.787633
## 374935 -19.473167
## 395397 -31.913947
## 603932 14.478395
## 565560 -15.836400
## 17241 6.442482
## 452496 20.588230
## 305547 17.923089
## 389251 -17.677399
## 599781 14.578461
## 389475 -10.022580
## 140733 -16.694135
## 480557 13.827373
## 53954 18.592203#calculate number of deferentially methylated tiles
nrow(subset(methylkitTilesCvGdf,qvalue<0.05))## [1] 56912#positive direction
nrow(subset(methylkitTilesCvGdf,qvalue<0.05&meth.diff>0))## [1] 16999#negative direction
nrow(subset(methylkitTilesCvGdf,qvalue<0.05&meth.diff<0))## [1] 39913#rm(methylkitTilesCvGdf)
#rm(methylkitTilesCvG)
methylkitTilesCvLGR <- as(methylkitTilesCvL,"GRanges")
methylkitTilesCvLdf <- getData(methylkitTilesCvL)
methylkitTilesCvLdf <- methylkitTilesCvLdf[order(methylkitTilesCvLdf[,6]), ]
head(methylkitTilesCvLdf,25)## chr start end strand pvalue qvalue meth.diff
## 204228 LG16 509001 510000 * 3.213330e-96 1.635845e-90 -25.98584
## 361025 LG21 1055001 1056000 * 8.837088e-72 2.249397e-66 19.69921
## 276792 LG19 1188001 1189000 * 1.236241e-66 2.097822e-61 -20.54554
## 284545 LG19 10333001 10334000 * 5.976181e-65 7.605902e-60 22.88567
## 602637 LG9 23623001 23624000 * 3.595176e-58 3.660472e-53 20.83910
## 372516 LG21 14273001 14274000 * 1.515368e-52 1.285742e-47 18.42160
## 317691 LG2 20995001 20996000 * 4.065070e-48 2.956357e-43 -20.26683
## 14178 KK215350.1 22001 23000 * 1.997522e-45 1.271126e-40 24.99745
## 1189 KK215283.1 1376001 1377000 * 2.043225e-44 1.155741e-39 13.08783
## 547708 LG7 18259001 18260000 * 8.559718e-41 4.357590e-36 23.29152
## 102354 LG11 28461001 28462000 * 1.078697e-40 4.992221e-36 -13.62358
## 360619 LG21 538001 539000 * 5.735034e-40 2.432998e-35 -13.78305
## 156361 LG14 4148001 4149000 * 8.688214e-40 3.402312e-35 -21.04322
## 6529 KK215291.1 217001 218000 * 7.723858e-36 2.808621e-31 17.39731
## 276005 LG19 235001 236000 * 1.756644e-35 5.961827e-31 -12.55592
## 302270 LG2 2675001 2676000 * 1.337412e-34 4.255320e-30 -15.95202
## 142943 LG13 22016001 22017000 * 4.175001e-34 1.250243e-29 18.63147
## 388596 LG22 7968001 7969000 * 8.395748e-34 2.374509e-29 -10.86215
## 233292 LG17 1251001 1252000 * 9.366903e-34 2.509744e-29 -14.83773
## 156493 LG14 4298001 4299000 * 6.837021e-32 1.740299e-27 -22.56870
## 101490 LG11 27368001 27369000 * 1.892756e-31 4.588411e-27 13.36592
## 299678 LG19 28150001 28151000 * 4.631708e-31 1.071779e-26 -19.74654
## 448719 LG3 33585001 33586000 * 1.756511e-30 3.887855e-26 -15.20759
## 186417 LG15 10977001 10978000 * 1.506553e-29 3.195656e-25 -11.29762
## 294811 LG19 22292001 22293000 * 2.784744e-29 5.670641e-25 -21.32461nrow(subset(methylkitTilesCvLdf,qvalue<0.05))## [1] 49686nrow(subset(methylkitTilesCvLdf,qvalue<0.05&meth.diff>0))## [1] 19497nrow(subset(methylkitTilesCvLdf,qvalue<0.05&meth.diff<0))## [1] 30189#rm(methylkitTilesCvLdf)
#rm(methylkitTilesCvL)
methylkitTilesGvLGR <- as(methylkitTilesGvL,"GRanges")
methylkitTilesGvLdf <- getData(methylkitTilesGvL)
methylkitTilesGvLdf <- methylkitTilesGvLdf[order(methylkitTilesGvLdf[,6]), ]
head(methylkitTilesGvLdf,25)## chr start end strand pvalue qvalue
## 464144 LG4 1847001 1848000 * 7.503577e-141 3.921253e-135
## 464143 LG4 1846001 1847000 * 8.017760e-104 2.094979e-98
## 1205 KK215283.1 1376001 1377000 * 1.012781e-55 1.764212e-50
## 210188 LG16 509001 510000 * 1.433189e-54 1.872407e-49
## 143822 LG13 18161001 18162000 * 1.900156e-51 1.985985e-46
## 370715 LG21 538001 539000 * 5.180641e-40 4.512205e-35
## 283555 LG18 21720001 21721000 * 2.190222e-39 1.635109e-34
## 161199 LG14 4148001 4149000 * 2.644311e-35 1.727345e-30
## 242088 LG17 3558001 3559000 * 8.543377e-35 4.960707e-30
## 38534 LG1 17897001 17898000 * 2.744822e-33 1.434401e-28
## 332793 LG2 28494001 28495000 * 8.791832e-33 4.176796e-28
## 492680 LG5 2971001 2972000 * 5.782685e-32 2.518285e-27
## 938 KK215283.1 1067001 1068000 * 5.241053e-31 2.106841e-26
## 242914 LG17 4434001 4435000 * 7.173123e-31 2.677545e-26
## 145630 LG13 20091001 20092000 * 5.663990e-30 1.973276e-25
## 105339 LG11 28230001 28231000 * 9.311900e-30 3.041409e-25
## 541902 LG6 26062001 26063000 * 1.188011e-28 3.651978e-24
## 105522 LG11 28461001 28462000 * 1.453293e-28 4.079260e-24
## 362538 LG20 17269001 17270000 * 1.483127e-28 4.079260e-24
## 109157 LG12 3809001 3810000 * 8.326373e-28 2.175617e-23
## 143399 LG13 17708001 17709000 * 9.099195e-28 2.264333e-23
## 362539 LG20 17270001 17271000 * 1.628812e-27 3.869055e-23
## 326588 LG2 20995001 20996000 * 4.298768e-27 9.360290e-23
## 597999 LG8 27880001 27881000 * 4.180084e-27 9.360290e-23
## 356752 LG20 10934001 10935000 * 4.555249e-27 9.522011e-23
## meth.diff
## 464144 -19.016257
## 464143 -19.309795
## 1205 13.265035
## 210188 -17.403727
## 143822 -17.695603
## 370715 -12.608880
## 283555 14.869760
## 161199 -17.151052
## 242088 19.287516
## 38534 4.758557
## 332793 16.745778
## 492680 -13.468644
## 938 -12.749512
## 242914 -15.590322
## 145630 19.439454
## 105339 7.937271
## 541902 15.554887
## 105522 -10.520805
## 362538 15.944613
## 109157 1.780137
## 143399 15.489531
## 362539 9.619173
## 326588 -13.793773
## 597999 -11.484597
## 356752 -19.403691nrow(subset(methylkitTilesGvLdf,qvalue<0.05))## [1] 51790nrow(subset(methylkitTilesGvLdf,qvalue<0.05&meth.diff>0))## [1] 31399nrow(subset(methylkitTilesGvLdf,qvalue<0.05&meth.diff<0))## [1] 20391#rm(methylkitTilesGvLdf)
#rm(methylkitTilesGvL)gtf <- rtracklayer::import("/mnt/data/aaron/projects/guppy-methylation/Poecilia_reticulata.Guppy_female_1.0_MT.103.gtf")
head(gtf)## GRanges object with 6 ranges and 21 metadata columns:
## seqnames ranges strand | source type score phase
## <Rle> <IRanges> <Rle> | <factor> <factor> <numeric> <integer>
## [1] LG2 813-1286 - | ensembl gene NA <NA>
## [2] LG2 813-1286 - | ensembl transcript NA <NA>
## [3] LG2 813-1286 - | ensembl exon NA <NA>
## [4] LG2 816-1286 - | ensembl CDS NA 0
## [5] LG2 1284-1286 - | ensembl start_codon NA 0
## [6] LG2 813-815 - | ensembl stop_codon NA 0
## gene_id gene_version gene_source gene_biotype
## <character> <character> <character> <character>
## [1] ENSPREG00000006268 1 ensembl protein_coding
## [2] ENSPREG00000006268 1 ensembl protein_coding
## [3] ENSPREG00000006268 1 ensembl protein_coding
## [4] ENSPREG00000006268 1 ensembl protein_coding
## [5] ENSPREG00000006268 1 ensembl protein_coding
## [6] ENSPREG00000006268 1 ensembl protein_coding
## transcript_id transcript_version transcript_source
## <character> <character> <character>
## [1] <NA> <NA> <NA>
## [2] ENSPRET00000009285 1 ensembl
## [3] ENSPRET00000009285 1 ensembl
## [4] ENSPRET00000009285 1 ensembl
## [5] ENSPRET00000009285 1 ensembl
## [6] ENSPRET00000009285 1 ensembl
## transcript_biotype exon_number exon_id exon_version
## <character> <character> <character> <character>
## [1] <NA> <NA> <NA> <NA>
## [2] protein_coding <NA> <NA> <NA>
## [3] protein_coding 1 ENSPREE00000064246 1
## [4] protein_coding 1 <NA> <NA>
## [5] protein_coding 1 <NA> <NA>
## [6] protein_coding 1 <NA> <NA>
## protein_id protein_version gene_name transcript_name
## <character> <character> <character> <character>
## [1] <NA> <NA> <NA> <NA>
## [2] <NA> <NA> <NA> <NA>
## [3] <NA> <NA> <NA> <NA>
## [4] ENSPREP00000009175 1 <NA> <NA>
## [5] <NA> <NA> <NA> <NA>
## [6] <NA> <NA> <NA> <NA>
## projection_parent_gene projection_parent_transcript
## <character> <character>
## [1] <NA> <NA>
## [2] <NA> <NA>
## [3] <NA> <NA>
## [4] <NA> <NA>
## [5] <NA> <NA>
## [6] <NA> <NA>
## -------
## seqinfo: 463 sequences from an unspecified genome; no seqlengthsmy_genes <- gtf[gtf$type == "gene"]
head(my_genes)## GRanges object with 6 ranges and 21 metadata columns:
## seqnames ranges strand | source type score phase
## <Rle> <IRanges> <Rle> | <factor> <factor> <numeric> <integer>
## [1] LG2 813-1286 - | ensembl gene NA <NA>
## [2] LG2 18959-21569 - | ensembl gene NA <NA>
## [3] LG2 30025-35085 + | ensembl gene NA <NA>
## [4] LG2 306358-537092 + | ensembl gene NA <NA>
## [5] LG2 621822-632265 + | ensembl gene NA <NA>
## [6] LG2 627410-629578 - | ensembl gene NA <NA>
## gene_id gene_version gene_source gene_biotype transcript_id
## <character> <character> <character> <character> <character>
## [1] ENSPREG00000006268 1 ensembl protein_coding <NA>
## [2] ENSPREG00000006273 1 ensembl protein_coding <NA>
## [3] ENSPREG00000006291 1 ensembl protein_coding <NA>
## [4] ENSPREG00000006354 1 ensembl protein_coding <NA>
## [5] ENSPREG00000006412 1 ensembl protein_coding <NA>
## [6] ENSPREG00000006451 1 ensembl protein_coding <NA>
## transcript_version transcript_source transcript_biotype exon_number
## <character> <character> <character> <character>
## [1] <NA> <NA> <NA> <NA>
## [2] <NA> <NA> <NA> <NA>
## [3] <NA> <NA> <NA> <NA>
## [4] <NA> <NA> <NA> <NA>
## [5] <NA> <NA> <NA> <NA>
## [6] <NA> <NA> <NA> <NA>
## exon_id exon_version protein_id protein_version gene_name
## <character> <character> <character> <character> <character>
## [1] <NA> <NA> <NA> <NA> <NA>
## [2] <NA> <NA> <NA> <NA> <NA>
## [3] <NA> <NA> <NA> <NA> arl13b
## [4] <NA> <NA> <NA> <NA> zgc:152904
## [5] <NA> <NA> <NA> <NA> gart
## [6] <NA> <NA> <NA> <NA> n6amt1
## transcript_name projection_parent_gene projection_parent_transcript
## <character> <character> <character>
## [1] <NA> <NA> <NA>
## [2] <NA> <NA> <NA>
## [3] <NA> <NA> <NA>
## [4] <NA> <NA> <NA>
## [5] <NA> <NA> <NA>
## [6] <NA> <NA> <NA>
## -------
## seqinfo: 463 sequences from an unspecified genome; no seqlengthsmcols(my_genes) <- mcols(my_genes)[c(5,8,18)]
head(my_genes)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | gene_id gene_biotype
## <Rle> <IRanges> <Rle> | <character> <character>
## [1] LG2 813-1286 - | ENSPREG00000006268 protein_coding
## [2] LG2 18959-21569 - | ENSPREG00000006273 protein_coding
## [3] LG2 30025-35085 + | ENSPREG00000006291 protein_coding
## [4] LG2 306358-537092 + | ENSPREG00000006354 protein_coding
## [5] LG2 621822-632265 + | ENSPREG00000006412 protein_coding
## [6] LG2 627410-629578 - | ENSPREG00000006451 protein_coding
## gene_name
## <character>
## [1] <NA>
## [2] <NA>
## [3] arl13b
## [4] zgc:152904
## [5] gart
## [6] n6amt1
## -------
## seqinfo: 463 sequences from an unspecified genome; no seqlengthsgff <- rtracklayer::import("/mnt/data/aaron/projects/guppy-methylation/Poecilia_reticulata.Guppy_female_1.0_MT.dna_sm.toplevel_out.gff")
head(gff)## GRanges object with 6 ranges and 5 metadata columns:
## seqnames ranges strand | source type score
## <Rle> <IRanges> <Rle> | <factor> <factor> <numeric>
## [1] LG1 6715-6924 + | cpgplot sequence_feature NA
## [2] LG1 8186-8489 + | cpgplot sequence_feature NA
## [3] LG1 12358-12761 + | cpgplot sequence_feature NA
## [4] LG1 29724-30103 + | cpgplot sequence_feature NA
## [5] LG1 45593-45901 + | cpgplot sequence_feature NA
## [6] LG1 50080-50390 + | cpgplot sequence_feature NA
## phase ID
## <integer> <character>
## [1] <NA> LG1.1
## [2] <NA> LG1.2
## [3] <NA> LG1.3
## [4] <NA> LG1.4
## [5] <NA> LG1.5
## [6] <NA> LG1.6
## -------
## seqinfo: 646 sequences from an unspecified genome; no seqlengthsmy_CpGislands <- gff[gff$type == "sequence_feature"]
head(my_CpGislands)## GRanges object with 6 ranges and 5 metadata columns:
## seqnames ranges strand | source type score
## <Rle> <IRanges> <Rle> | <factor> <factor> <numeric>
## [1] LG1 6715-6924 + | cpgplot sequence_feature NA
## [2] LG1 8186-8489 + | cpgplot sequence_feature NA
## [3] LG1 12358-12761 + | cpgplot sequence_feature NA
## [4] LG1 29724-30103 + | cpgplot sequence_feature NA
## [5] LG1 45593-45901 + | cpgplot sequence_feature NA
## [6] LG1 50080-50390 + | cpgplot sequence_feature NA
## phase ID
## <integer> <character>
## [1] <NA> LG1.1
## [2] <NA> LG1.2
## [3] <NA> LG1.3
## [4] <NA> LG1.4
## [5] <NA> LG1.5
## [6] <NA> LG1.6
## -------
## seqinfo: 646 sequences from an unspecified genome; no seqlengthsmcols(my_CpGislands) <- mcols(my_CpGislands)[c(1,5)]
head(my_CpGislands)## GRanges object with 6 ranges and 2 metadata columns:
## seqnames ranges strand | source ID
## <Rle> <IRanges> <Rle> | <factor> <character>
## [1] LG1 6715-6924 + | cpgplot LG1.1
## [2] LG1 8186-8489 + | cpgplot LG1.2
## [3] LG1 12358-12761 + | cpgplot LG1.3
## [4] LG1 29724-30103 + | cpgplot LG1.4
## [5] LG1 45593-45901 + | cpgplot LG1.5
## [6] LG1 50080-50390 + | cpgplot LG1.6
## -------
## seqinfo: 646 sequences from an unspecified genome; no seqlengthsmy_Promotersdf <- read.table("/mnt/data/aaron/projects/guppy-methylation/Poecilia_reticulata.Guppy_female_1.0_MT.103_tss.bed",header = FALSE,stringsAsFactors=FALSE)
head(my_Promotersdf)## V1 V2 V3 V4 V5 V6 V7
## 1 LG2 28525 31526 + ENSPREG00000006291 ENSPRET00000009322 arl13b
## 2 LG2 304858 307859 + ENSPREG00000006354 ENSPRET00000009453 zgc:152904
## 3 LG2 446170 449171 + ENSPREG00000006354 ENSPRET00000009478 zgc:152904
## 4 LG2 446848 449849 + ENSPREG00000006354 ENSPRET00000009478 zgc:152904
## 5 LG2 620322 623323 + ENSPREG00000006412 ENSPRET00000009554 gart
## 6 LG2 620942 623943 + ENSPREG00000006412 ENSPRET00000009572 gartmy_Promoters <- makeGRangesFromDataFrame(my_Promotersdf,
keep.extra.columns=TRUE,
ignore.strand=FALSE,
seqinfo=NULL,
seqnames.field=c("V1"),
start.field="V2",
end.field=c("V3"),
strand.field="V4",
starts.in.df.are.0based=FALSE)
head(my_Promoters)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | V5 V6
## <Rle> <IRanges> <Rle> | <character> <character>
## [1] LG2 28525-31526 + | ENSPREG00000006291 ENSPRET00000009322
## [2] LG2 304858-307859 + | ENSPREG00000006354 ENSPRET00000009453
## [3] LG2 446170-449171 + | ENSPREG00000006354 ENSPRET00000009478
## [4] LG2 446848-449849 + | ENSPREG00000006354 ENSPRET00000009478
## [5] LG2 620322-623323 + | ENSPREG00000006412 ENSPRET00000009554
## [6] LG2 620942-623943 + | ENSPREG00000006412 ENSPRET00000009572
## V7
## <character>
## [1] arl13b
## [2] zgc:152904
## [3] zgc:152904
## [4] zgc:152904
## [5] gart
## [6] gart
## -------
## seqinfo: 452 sequences from an unspecified genome; no seqlengthsMethylkit CpG results annotated to genes
ol1 <- findOverlaps(methylkitCvGGR,my_genes)## Warning in .Seqinfo.mergexy(x, y): Each of the 2 combined objects has sequence levels not in the other:
## - in 'x': KK215332.1, KK215339.1, KK215341.1, KK215351.1, KK215360.1, KK215378.1, KK215383.1, KK215387.1, KK215388.1, KK215391.1, KK215393.1, KK215395.1, KK215396.1, KK215397.1, KK215400.1, KK215401.1, KK215402.1, KK215403.1, KK215405.1, KK215406.1, KK215407.1, KK215408.1, KK215411.1, KK215412.1, KK215414.1, KK215415.1, KK215418.1, KK215419.1, KK215420.1, KK215421.1, KK215424.1, KK215425.1, KK215427.1, KK215429.1, KK215430.1, KK215432.1, KK215433.1, KK215435.1, KK215439.1, KK215440.1, KK215441.1, KK215443.1, KK215444.1, KK215446.1, KK215448.1, KK215451.1, KK215453.1, KK215454.1, KK215455.1, KK215456.1, KK215459.1, KK215462.1, KK215463.1, KK215465.1, KK215466.1, KK215467.1, KK215472.1, KK215474.1, KK215475.1, KK215479.1, KK215480.1, KK215482.1, KK215484.1, KK215485.1, KK215486.1, KK215488.1, KK215489.1, KK215490.1, KK215491.1, KK215492.1, KK215494.1, KK215496.1, KK215497.1, KK215498.1, KK215501.1, KK215502.1, KK215503.1, KK215504.1, KK215506.1, KK215507.1, KK215508.1, KK215511.1, KK215512.1, KK215513.1, KK215514.1, KK215515.1, KK215516.1, KK215517.1, KK215518.1, KK215519.1, KK215521.1, KK215523.1, KK215524.1, KK215525.1, KK215526.1, KK215528.1, KK215529.1, KK215530.1, KK215531.1, KK215533.1, KK215538.1, KK215540.1, KK215541.1, KK215543.1, KK215544.1, KK215545.1, KK215546.1, KK215547.1, KK215548.1, KK215549.1, KK215551.1, KK215553.1, KK215554.1, KK215556.1, KK215558.1, KK215559.1, KK215560.1, KK215561.1, KK215562.1, KK215564.1, KK215567.1, KK215568.1, KK215573.1, KK215574.1, KK215577.1, KK215578.1, KK215579.1, KK215581.1, KK215582.1, KK215583.1, KK215584.1, KK215585.1, KK215586.1, KK215587.1, KK215588.1, KK215589.1, KK215590.1, KK215594.1, KK215595.1, KK215597.1, KK215598.1, KK215601.1, KK215602.1, KK215603.1, KK215605.1, KK215606.1, KK215608.1, KK215615.1, KK215616.1, KK215620.1, KK215621.1, KK215622.1, KK215624.1, KK215625.1, KK215626.1, KK215627.1, KK215628.1, KK215629.1, KK215630.1, KK215632.1, KK215633.1, KK215634.1, KK215635.1, KK215636.1, KK215637.1, KK215638.1, KK215639.1, KK215641.1, KK215642.1, KK215644.1, KK215645.1, KK215646.1, KK215647.1, KK215649.1, KK215652.1, KK215654.1, KK215655.1, KK215657.1, KK215658.1, KK215661.1, KK215662.1, KK215663.1, KK215664.1, KK215665.1, KK215668.1, KK215669.1, KK215670.1, KK215671.1, KK215672.1, KK215673.1, KK215675.1, KK215677.1, KK215678.1, KK215683.1, KK215684.1, KK215688.1, KK215689.1, KK215692.1, KK215694.1, KK215695.1, KK215699.1, KK215700.1, KK215701.1, KK215703.1, KK215704.1, KK215705.1, KK215706.1, KK215707.1, KK215709.1, KK215710.1, KK215711.1, KK215712.1, KK215715.1, KK215718.1, KK215719.1, KK215720.1, KK215721.1, KK215722.1, KK215723.1, KK215724.1, KK215726.1, KK215727.1, KK215728.1, KK215733.1, KK215734.1, KK215736.1, KK215737.1, KK215738.1, KK215739.1, KK215740.1, KK215741.1, KK215742.1, KK215743.1, KK215745.1, KK215748.1, KK215750.1, KK215752.1, KK215753.1, KK215754.1, KK215755.1, KK215756.1, KK215757.1, KK215758.1, KK215759.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215766.1, KK215767.1, KK215768.1, KK215769.1, KK215770.1, KK215771.1, KK215772.1, KK215774.1, KK215775.1, KK215776.1, KK215777.1, KK215778.1, KK215779.1, KK215780.1, KK215782.1, KK215783.1, KK215785.1, KK215786.1, KK215788.1, KK215789.1, KK215792.1, KK215794.1, KK215795.1, KK215796.1, KK215797.1, KK215798.1, KK215802.1, KK215804.1, KK215805.1, KK215807.1, KK215810.1, KK215812.1, KK215814.1, KK215815.1, KK215816.1, KK215818.1, KK215819.1, KK215821.1, KK215825.1, KK215827.1, KK215832.1, KK215834.1, KK215836.1, KK215837.1, KK215838.1, KK215839.1, KK215840.1, KK215841.1, KK215842.1, KK215843.1, KK215846.1, KK215847.1, KK215848.1, KK215849.1, KK215851.1, KK215852.1, KK215854.1, KK215857.1, KK215858.1, KK215859.1, KK215860.1, KK215861.1, KK215863.1, KK215864.1, KK215865.1, KK215867.1, KK215869.1, KK215870.1, KK215872.1, KK215873.1, KK215874.1, KK215875.1, KK215877.1, KK215878.1, KK215880.1, KK215881.1, KK215882.1, KK215884.1, KK215885.1, KK215886.1, KK215890.1, KK215891.1, KK215892.1, KK215893.1, KK215894.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215902.1, KK215903.1, KK215905.1, KK215907.1, KK215908.1, KK215909.1, KK215910.1, KK215911.1, KK215913.1, KK215914.1, KK215915.1, KK215917.1, KK215918.1, KK215920.1, KK215921.1, KK215922.1, KK215923.1, KK215924.1, KK215927.1, KK215928.1, KK215929.1, KK215933.1, KK215934.1, KK215935.1, KK215937.1, KK215938.1, KK215940.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215946.1, KK215949.1, KK215951.1, KK215952.1, KK215953.1, KK215956.1, KK215957.1, KK215958.1, KK215960.1, KK215962.1, KK215963.1, KK215965.1, KK215967.1, KK215969.1, KK215970.1, KK215971.1, KK215972.1, KK215973.1, KK215974.1, KK215975.1, KK215976.1, KK215977.1, KK215978.1, KK215979.1, KK215982.1, KK215983.1, KK215984.1, KK215985.1, KK215986.1, KK215987.1, KK215989.1, KK215990.1, KK215993.1, KK215994.1, KK215995.1, KK215996.1, KK215997.1, KK215999.1, KK216000.1, KK216001.1, KK216005.1, KK216006.1, KK216007.1, KK216008.1, KK216009.1, KK216011.1, KK216012.1, KK216015.1, KK216016.1, KK216017.1, KK216018.1, KK216021.1, KK216022.1, KK216023.1, KK216024.1, KK216025.1, KK216026.1, KK216027.1, KK216028.1, KK216029.1, KK216030.1, KK216032.1, KK216033.1, KK216034.1, KK216035.1, KK216036.1, KK216037.1, KK216038.1, KK216039.1, KK216040.1, KK216041.1, KK216042.1, KK216043.1, KK216044.1, KK216047.1, KK216048.1, KK216049.1, KK216050.1, KK216053.1, KK216055.1, KK216056.1, KK216058.1, KK216059.1, KK216062.1, KK216063.1, KK216064.1, KK216065.1, KK216066.1, KK216067.1, KK216068.1, KK216069.1, KK216070.1, KK216071.1, KK216072.1, KK216074.1, KK216075.1, KK216076.1, KK216077.1, KK216078.1, KK216079.1, KK216080.1, KK216082.1, KK216083.1, KK216084.1, KK216085.1, KK216086.1, KK216087.1, KK216089.1, KK216091.1, KK216093.1, KK216094.1, KK216095.1, KK216096.1, KK216097.1, KK216098.1, KK216099.1, KK216102.1, KK216103.1, KK216106.1, KK216109.1, KK216110.1, KK216111.1, KK216112.1, KK216113.1, KK216114.1, KK216115.1, KK216117.1, KK216118.1, KK216120.1, KK216122.1, KK216124.1, KK216125.1, KK216126.1, KK216127.1, KK216128.1, KK216131.1, KK216133.1, KK216134.1, KK216135.1, KK216137.1, KK216138.1, KK216140.1, KK216141.1, KK216142.1, KK216143.1, KK216144.1, KK216145.1, KK216146.1, KK216150.1, KK216151.1, KK216152.1, KK216154.1, KK216155.1, KK216157.1, KK216158.1, KK216159.1, KK216160.1, KK216162.1, KK216163.1, KK216164.1, KK216165.1, KK216166.1, KK216168.1, KK216169.1, KK216171.1, KK216172.1, KK216173.1, KK216174.1, KK216175.1, KK216176.1, KK216177.1, KK216178.1, KK216180.1, KK216181.1, KK216182.1, KK216184.1, KK216186.1, KK216190.1, KK216192.1, KK216193.1, KK216194.1, KK216195.1, KK216196.1, KK216197.1, KK216198.1, KK216200.1, KK216201.1, KK216202.1, KK216203.1, KK216205.1, KK216206.1, KK216208.1, KK216212.1, KK216213.1, KK216214.1, KK216215.1, KK216217.1, KK216218.1, KK216219.1, KK216221.1, KK216222.1, KK216224.1, KK216225.1, KK216226.1, KK216227.1, KK216229.1, KK216231.1, KK216232.1, KK216234.1, KK216235.1, KK216236.1, KK216237.1, KK216238.1, KK216240.1, KK216241.1, KK216242.1, KK216243.1, KK216244.1, KK216245.1, KK216248.1, KK216251.1, KK216252.1, KK216253.1, KK216254.1, KK216256.1, KK216258.1, KK216259.1, KK216260.1, KK216261.1, KK216262.1, KK216263.1, KK216264.1, KK216265.1, KK216266.1, KK216267.1, KK216269.1, KK216270.1, KK216271.1, KK216272.1, KK216273.1, KK216274.1, KK216275.1, KK216276.1, KK216278.1, KK216280.1, KK216281.1, KK216282.1, KK216283.1, KK216284.1, KK216285.1, KK216287.1, KK216288.1, KK216289.1, KK216290.1, KK216291.1, KK216292.1, KK216293.1, KK216295.1, KK216296.1, KK216297.1, KK216298.1, KK216299.1, KK216302.1, KK216303.1, KK216304.1, KK216306.1, KK216307.1, KK216308.1, KK216310.1, KK216311.1, KK216313.1, KK216315.1, KK216316.1, KK216317.1, KK216318.1, KK216319.1, KK216320.1, KK216321.1, KK216322.1, KK216323.1, KK216324.1, KK216325.1, KK216326.1, KK216327.1, KK216328.1, KK216329.1, KK216330.1, KK216331.1, KK216333.1, KK216334.1, KK216335.1, KK216336.1, KK216337.1, KK216338.1, KK216340.1, KK216341.1, KK216342.1, KK216343.1, KK216344.1, KK216345.1, KK216346.1, KK216347.1, KK216349.1, KK216351.1, KK216353.1, KK216354.1, KK216356.1, KK216359.ol1## Hits object with 5433218 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 25189 21953
## [2] 25190 21953
## [3] 25191 21953
## [4] 25192 21953
## [5] 25193 21953
## ... ... ...
## [5433214] 18867318 3357
## [5433215] 18867319 3357
## [5433216] 18867320 3357
## [5433217] 18867321 3357
## [5433218] 18867322 3357
## -------
## queryLength: 18874229 / subjectLength: 23254CvGgenes <- methylkitCvGGR[queryHits(ol1)]
mygenesol1 <- my_genes[subjectHits(ol1)]
head(CvGgenes)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | pvalue qvalue meth.diff
## <Rle> <IRanges> <Rle> | <numeric> <numeric> <numeric>
## [1] KK215283.1 634828 + | 0.846745 0.989133 1.58207
## [2] KK215283.1 634829 + | 0.149563 0.855539 -12.59259
## [3] KK215283.1 634833 + | 0.512963 0.973400 5.49096
## [4] KK215283.1 634877 + | 0.390452 0.930005 6.91057
## [5] KK215283.1 634878 + | 0.566729 0.988077 5.81818
## [6] KK215283.1 634882 + | 0.710529 0.989133 2.74390
## -------
## seqinfo: 2455 sequences from an unspecified genome; no seqlengthsmygenesol1## GRanges object with 5433218 ranges and 3 metadata columns:
## seqnames ranges strand | gene_id
## <Rle> <IRanges> <Rle> | <character>
## [1] KK215283.1 634721-638733 + | ENSPREG00000018045
## [2] KK215283.1 634721-638733 + | ENSPREG00000018045
## [3] KK215283.1 634721-638733 + | ENSPREG00000018045
## [4] KK215283.1 634721-638733 + | ENSPREG00000018045
## [5] KK215283.1 634721-638733 + | ENSPREG00000018045
## ... ... ... ... . ...
## [5433214] LG9 34074214-34108653 + | ENSPREG00000019083
## [5433215] LG9 34074214-34108653 + | ENSPREG00000019083
## [5433216] LG9 34074214-34108653 + | ENSPREG00000019083
## [5433217] LG9 34074214-34108653 + | ENSPREG00000019083
## [5433218] LG9 34074214-34108653 + | ENSPREG00000019083
## gene_biotype gene_name
## <character> <character>
## [1] protein_coding <NA>
## [2] protein_coding <NA>
## [3] protein_coding <NA>
## [4] protein_coding <NA>
## [5] protein_coding <NA>
## ... ... ...
## [5433214] protein_coding adamtsl2
## [5433215] protein_coding adamtsl2
## [5433216] protein_coding adamtsl2
## [5433217] protein_coding adamtsl2
## [5433218] protein_coding adamtsl2
## -------
## seqinfo: 463 sequences from an unspecified genome; no seqlengthsCvGgenesdf <- as.data.frame(CvGgenes,row.names = 1:nrow(as.data.frame(ranges(CvGgenes))))
str(CvGgenesdf)## 'data.frame': 5433218 obs. of 8 variables:
## $ seqnames : Factor w/ 2455 levels "KK215283.1","KK215284.1",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ start : int 634828 634829 634833 634877 634878 634882 634883 635036 635037 635039 ...
## $ end : int 634828 634829 634833 634877 634878 634882 634883 635036 635037 635039 ...
## $ width : int 1 1 1 1 1 1 1 1 1 1 ...
## $ strand : Factor w/ 3 levels "+","-","*": 1 1 1 1 1 1 1 1 1 1 ...
## $ pvalue : num 0.847 0.15 0.513 0.39 0.567 ...
## $ qvalue : num 0.989 0.856 0.973 0.93 0.988 ...
## $ meth.diff: num 1.58 -12.59 5.49 6.91 5.82 ...mygenesoldf1 <- as.data.frame(mygenesol1,row.names = 1:nrow(as.data.frame(ranges(mygenesol1))))
head(mygenesoldf1)## seqnames start end width strand gene_id gene_biotype
## 1 KK215283.1 634721 638733 4013 + ENSPREG00000018045 protein_coding
## 2 KK215283.1 634721 638733 4013 + ENSPREG00000018045 protein_coding
## 3 KK215283.1 634721 638733 4013 + ENSPREG00000018045 protein_coding
## 4 KK215283.1 634721 638733 4013 + ENSPREG00000018045 protein_coding
## 5 KK215283.1 634721 638733 4013 + ENSPREG00000018045 protein_coding
## 6 KK215283.1 634721 638733 4013 + ENSPREG00000018045 protein_coding
## gene_name
## 1 <NA>
## 2 <NA>
## 3 <NA>
## 4 <NA>
## 5 <NA>
## 6 <NA>CvGgenesdf <- cbind(CvGgenesdf,mygenesoldf1[c("gene_id","gene_biotype","gene_name")])
CvGgenesdf$seqnames <- as.character(CvGgenesdf$seqnames)
head(CvGgenesdf)## seqnames start end width strand pvalue qvalue meth.diff
## 1 KK215283.1 634828 634828 1 + 0.8467448 0.9891325 1.582070
## 2 KK215283.1 634829 634829 1 + 0.1495634 0.8555389 -12.592593
## 3 KK215283.1 634833 634833 1 + 0.5129634 0.9734001 5.490956
## 4 KK215283.1 634877 634877 1 + 0.3904517 0.9300051 6.910569
## 5 KK215283.1 634878 634878 1 + 0.5667291 0.9880772 5.818182
## 6 KK215283.1 634882 634882 1 + 0.7105289 0.9891325 2.743902
## gene_id gene_biotype gene_name
## 1 ENSPREG00000018045 protein_coding <NA>
## 2 ENSPREG00000018045 protein_coding <NA>
## 3 ENSPREG00000018045 protein_coding <NA>
## 4 ENSPREG00000018045 protein_coding <NA>
## 5 ENSPREG00000018045 protein_coding <NA>
## 6 ENSPREG00000018045 protein_coding <NA>CvGgeneschrdf <- CvGgenesdf[grep("LG",CvGgenesdf$seqnames),]
head(CvGgeneschrdf)## seqnames start end width strand pvalue qvalue meth.diff
## 205529 LG1 370928 370928 1 + 0.2444591 0.8893400 -14.101382
## 205530 LG1 370929 370929 1 + 0.3441769 0.9147317 10.863095
## 205531 LG1 370994 370994 1 + 1.0000000 0.9891325 0.000000
## 205532 LG1 371191 371191 1 + 0.4583006 0.9550554 -6.321839
## 205533 LG1 371192 371192 1 + 0.8701164 0.9891325 -1.382488
## 205534 LG1 371227 371227 1 + 0.6651526 0.9891325 3.118908
## gene_id gene_biotype gene_name
## 205529 ENSPREG00000000039 protein_coding <NA>
## 205530 ENSPREG00000000039 protein_coding <NA>
## 205531 ENSPREG00000000039 protein_coding <NA>
## 205532 ENSPREG00000000039 protein_coding <NA>
## 205533 ENSPREG00000000039 protein_coding <NA>
## 205534 ENSPREG00000000039 protein_coding <NA>CvGgeneschrdf <- CvGgeneschrdf[order(CvGgeneschrdf[,7]), ]
head(CvGgeneschrdf,10)## seqnames start end width strand pvalue qvalue
## 2512233 LG19 4233614 4233614 1 + 2.875857e-08 0.04880882
## 1495966 LG14 17323571 17323571 1 + 6.150734e-08 0.08832981
## 1913935 LG16 15182433 15182433 1 + 7.754818e-08 0.09651705
## 3646593 LG23 2943357 2943357 1 + 7.286739e-08 0.09651705
## 2870927 LG2 21695053 21695053 1 + 1.907840e-07 0.15296608
## 3176259 LG20 21573163 21573163 1 + 1.890608e-07 0.15296608
## 2349025 LG18 5261516 5261516 1 + 2.531751e-07 0.15642075
## 3944752 LG3 26875023 26875023 1 + 2.499710e-07 0.15642075
## 2480021 LG19 1199207 1199207 1 + 2.917105e-07 0.17018678
## 778072 LG11 10567447 10567447 1 + 4.698010e-07 0.23111492
## meth.diff gene_id gene_biotype gene_name
## 2512233 60.09818 ENSPREG00000021117 protein_coding tspan9a
## 1495966 50.00000 ENSPREG00000008650 protein_coding spns3
## 1913935 -55.77342 ENSPREG00000016960 protein_coding she
## 3646593 59.44056 ENSPREG00000023036 protein_coding anks1b
## 2870927 50.54720 ENSPREG00000015713 protein_coding cntnap5a
## 3176259 59.31174 ENSPREG00000005440 protein_coding puf60a
## 2349025 53.50000 ENSPREG00000004980 protein_coding sorcs2
## 3944752 51.76768 ENSPREG00000009047 protein_coding RASGRF1
## 2480021 -59.05316 ENSPREG00000017528 protein_coding SHANK1
## 778072 -55.55556 ENSPREG00000001422 protein_coding <NA>rm(CvGgenesdf)
rm(CvGgenes)ol1 <- findOverlaps(methylkitCvLGR,my_genes)## Warning in .Seqinfo.mergexy(x, y): Each of the 2 combined objects has sequence levels not in the other:
## - in 'x': KK215332.1, KK215339.1, KK215341.1, KK215351.1, KK215360.1, KK215378.1, KK215383.1, KK215387.1, KK215388.1, KK215391.1, KK215393.1, KK215395.1, KK215396.1, KK215397.1, KK215400.1, KK215401.1, KK215402.1, KK215403.1, KK215405.1, KK215406.1, KK215407.1, KK215408.1, KK215411.1, KK215412.1, KK215414.1, KK215415.1, KK215418.1, KK215419.1, KK215420.1, KK215421.1, KK215424.1, KK215425.1, KK215427.1, KK215429.1, KK215430.1, KK215432.1, KK215433.1, KK215435.1, KK215439.1, KK215440.1, KK215441.1, KK215443.1, KK215444.1, KK215446.1, KK215448.1, KK215451.1, KK215453.1, KK215454.1, KK215455.1, KK215456.1, KK215459.1, KK215462.1, KK215463.1, KK215465.1, KK215466.1, KK215467.1, KK215472.1, KK215474.1, KK215475.1, KK215479.1, KK215480.1, KK215482.1, KK215484.1, KK215485.1, KK215486.1, KK215488.1, KK215489.1, KK215490.1, KK215491.1, KK215492.1, KK215494.1, KK215496.1, KK215497.1, KK215498.1, KK215501.1, KK215502.1, KK215503.1, KK215504.1, KK215506.1, KK215507.1, KK215508.1, KK215511.1, KK215512.1, KK215513.1, KK215514.1, KK215515.1, KK215516.1, KK215517.1, KK215518.1, KK215519.1, KK215521.1, KK215523.1, KK215524.1, KK215525.1, KK215526.1, KK215528.1, KK215529.1, KK215530.1, KK215531.1, KK215533.1, KK215538.1, KK215540.1, KK215541.1, KK215543.1, KK215544.1, KK215545.1, KK215546.1, KK215547.1, KK215548.1, KK215549.1, KK215551.1, KK215553.1, KK215554.1, KK215556.1, KK215558.1, KK215559.1, KK215560.1, KK215561.1, KK215562.1, KK215564.1, KK215567.1, KK215568.1, KK215573.1, KK215574.1, KK215577.1, KK215578.1, KK215579.1, KK215581.1, KK215582.1, KK215583.1, KK215584.1, KK215585.1, KK215586.1, KK215587.1, KK215588.1, KK215589.1, KK215590.1, KK215594.1, KK215595.1, KK215597.1, KK215598.1, KK215601.1, KK215602.1, KK215603.1, KK215605.1, KK215606.1, KK215608.1, KK215615.1, KK215616.1, KK215620.1, KK215621.1, KK215622.1, KK215624.1, KK215625.1, KK215626.1, KK215627.1, KK215628.1, KK215629.1, KK215630.1, KK215632.1, KK215633.1, KK215634.1, KK215635.1, KK215636.1, KK215637.1, KK215638.1, KK215639.1, KK215641.1, KK215642.1, KK215644.1, KK215645.1, KK215646.1, KK215647.1, KK215649.1, KK215652.1, KK215654.1, KK215655.1, KK215657.1, KK215658.1, KK215661.1, KK215662.1, KK215663.1, KK215664.1, KK215665.1, KK215668.1, KK215669.1, KK215670.1, KK215671.1, KK215672.1, KK215673.1, KK215675.1, KK215677.1, KK215678.1, KK215683.1, KK215684.1, KK215688.1, KK215689.1, KK215692.1, KK215694.1, KK215695.1, KK215699.1, KK215700.1, KK215701.1, KK215703.1, KK215704.1, KK215705.1, KK215706.1, KK215707.1, KK215709.1, KK215710.1, KK215711.1, KK215712.1, KK215715.1, KK215718.1, KK215719.1, KK215720.1, KK215721.1, KK215722.1, KK215723.1, KK215724.1, KK215726.1, KK215727.1, KK215728.1, KK215733.1, KK215734.1, KK215736.1, KK215737.1, KK215738.1, KK215739.1, KK215740.1, KK215741.1, KK215742.1, KK215743.1, KK215745.1, KK215748.1, KK215750.1, KK215752.1, KK215753.1, KK215754.1, KK215755.1, KK215756.1, KK215757.1, KK215758.1, KK215759.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215766.1, KK215767.1, KK215768.1, KK215769.1, KK215770.1, KK215771.1, KK215772.1, KK215774.1, KK215775.1, KK215776.1, KK215777.1, KK215778.1, KK215779.1, KK215780.1, KK215782.1, KK215783.1, KK215785.1, KK215786.1, KK215788.1, KK215789.1, KK215792.1, KK215794.1, KK215795.1, KK215796.1, KK215797.1, KK215798.1, KK215802.1, KK215804.1, KK215805.1, KK215807.1, KK215810.1, KK215812.1, KK215814.1, KK215815.1, KK215816.1, KK215818.1, KK215819.1, KK215821.1, KK215825.1, KK215827.1, KK215832.1, KK215834.1, KK215836.1, KK215837.1, KK215838.1, KK215839.1, KK215840.1, KK215841.1, KK215842.1, KK215843.1, KK215846.1, KK215847.1, KK215848.1, KK215849.1, KK215851.1, KK215852.1, KK215854.1, KK215857.1, KK215858.1, KK215859.1, KK215860.1, KK215861.1, KK215863.1, KK215864.1, KK215865.1, KK215867.1, KK215869.1, KK215870.1, KK215872.1, KK215873.1, KK215875.1, KK215877.1, KK215878.1, KK215880.1, KK215881.1, KK215882.1, KK215884.1, KK215885.1, KK215886.1, KK215890.1, KK215891.1, KK215892.1, KK215893.1, KK215894.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215902.1, KK215903.1, KK215905.1, KK215907.1, KK215908.1, KK215909.1, KK215910.1, KK215911.1, KK215913.1, KK215914.1, KK215915.1, KK215917.1, KK215918.1, KK215920.1, KK215921.1, KK215922.1, KK215923.1, KK215924.1, KK215927.1, KK215928.1, KK215929.1, KK215930.1, KK215933.1, KK215934.1, KK215935.1, KK215937.1, KK215938.1, KK215940.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215946.1, KK215949.1, KK215951.1, KK215952.1, KK215953.1, KK215956.1, KK215957.1, KK215958.1, KK215960.1, KK215962.1, KK215963.1, KK215965.1, KK215967.1, KK215969.1, KK215970.1, KK215971.1, KK215972.1, KK215973.1, KK215974.1, KK215975.1, KK215976.1, KK215977.1, KK215978.1, KK215979.1, KK215982.1, KK215983.1, KK215984.1, KK215985.1, KK215986.1, KK215987.1, KK215989.1, KK215990.1, KK215993.1, KK215994.1, KK215995.1, KK215996.1, KK215997.1, KK215999.1, KK216000.1, KK216001.1, KK216005.1, KK216006.1, KK216007.1, KK216008.1, KK216009.1, KK216011.1, KK216012.1, KK216015.1, KK216016.1, KK216017.1, KK216018.1, KK216021.1, KK216022.1, KK216023.1, KK216024.1, KK216025.1, KK216026.1, KK216027.1, KK216028.1, KK216029.1, KK216030.1, KK216032.1, KK216033.1, KK216034.1, KK216035.1, KK216036.1, KK216037.1, KK216038.1, KK216039.1, KK216040.1, KK216041.1, KK216042.1, KK216043.1, KK216044.1, KK216047.1, KK216048.1, KK216049.1, KK216050.1, KK216053.1, KK216055.1, KK216056.1, KK216058.1, KK216059.1, KK216062.1, KK216063.1, KK216064.1, KK216065.1, KK216066.1, KK216067.1, KK216068.1, KK216069.1, KK216070.1, KK216071.1, KK216072.1, KK216073.1, KK216074.1, KK216075.1, KK216076.1, KK216077.1, KK216078.1, KK216079.1, KK216080.1, KK216082.1, KK216083.1, KK216084.1, KK216085.1, KK216086.1, KK216087.1, KK216089.1, KK216091.1, KK216093.1, KK216094.1, KK216095.1, KK216096.1, KK216097.1, KK216098.1, KK216099.1, KK216102.1, KK216103.1, KK216106.1, KK216109.1, KK216110.1, KK216111.1, KK216112.1, KK216113.1, KK216114.1, KK216115.1, KK216117.1, KK216118.1, KK216120.1, KK216122.1, KK216124.1, KK216125.1, KK216126.1, KK216127.1, KK216128.1, KK216131.1, KK216133.1, KK216134.1, KK216135.1, KK216137.1, KK216138.1, KK216140.1, KK216141.1, KK216142.1, KK216143.1, KK216144.1, KK216145.1, KK216146.1, KK216150.1, KK216151.1, KK216152.1, KK216154.1, KK216155.1, KK216157.1, KK216158.1, KK216159.1, KK216160.1, KK216162.1, KK216163.1, KK216164.1, KK216165.1, KK216166.1, KK216168.1, KK216169.1, KK216171.1, KK216172.1, KK216173.1, KK216174.1, KK216175.1, KK216176.1, KK216177.1, KK216178.1, KK216180.1, KK216181.1, KK216182.1, KK216184.1, KK216186.1, KK216190.1, KK216192.1, KK216193.1, KK216194.1, KK216195.1, KK216196.1, KK216197.1, KK216198.1, KK216200.1, KK216201.1, KK216202.1, KK216203.1, KK216205.1, KK216206.1, KK216208.1, KK216212.1, KK216213.1, KK216214.1, KK216215.1, KK216217.1, KK216218.1, KK216219.1, KK216221.1, KK216222.1, KK216224.1, KK216225.1, KK216226.1, KK216227.1, KK216229.1, KK216231.1, KK216232.1, KK216234.1, KK216235.1, KK216236.1, KK216237.1, KK216238.1, KK216240.1, KK216241.1, KK216242.1, KK216243.1, KK216244.1, KK216245.1, KK216248.1, KK216251.1, KK216252.1, KK216253.1, KK216254.1, KK216256.1, KK216258.1, KK216259.1, KK216260.1, KK216261.1, KK216262.1, KK216263.1, KK216264.1, KK216265.1, KK216266.1, KK216267.1, KK216269.1, KK216270.1, KK216271.1, KK216272.1, KK216273.1, KK216274.1, KK216275.1, KK216276.1, KK216278.1, KK216280.1, KK216281.1, KK216282.1, KK216283.1, KK216284.1, KK216285.1, KK216287.1, KK216288.1, KK216289.1, KK216290.1, KK216291.1, KK216292.1, KK216293.1, KK216295.1, KK216296.1, KK216297.1, KK216298.1, KK216299.1, KK216302.1, KK216303.1, KK216304.1, KK216306.1, KK216307.1, KK216308.1, KK216310.1, KK216311.1, KK216313.1, KK216315.1, KK216316.1, KK216317.1, KK216318.1, KK216319.1, KK216320.1, KK216321.1, KK216322.1, KK216323.1, KK216324.1, KK216325.1, KK216326.1, KK216327.1, KK216328.1, KK216329.1, KK216330.1, KK216331.1, KK216333.1, KK216334.1, KK216335.1, KK216336.1, KK216337.1, KK216338.1, KK216340.1, KK216341.1, KK216342.1, KK216343.1, KK216344.1, KK216345.1, KK216346.1, KK216347.1, KK216349.1, KK216351.1, KK216353.1, KK216354.1, KK216356.ol1## Hits object with 5324171 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 24596 21953
## [2] 24597 21953
## [3] 24598 21953
## [4] 24599 21953
## [5] 24600 21953
## ... ... ...
## [5324167] 18471054 3357
## [5324168] 18471055 3357
## [5324169] 18471056 3357
## [5324170] 18471057 3357
## [5324171] 18471058 3357
## -------
## queryLength: 18477943 / subjectLength: 23254CvLgenes <- methylkitCvLGR[queryHits(ol1)]
mygenesol1 <- my_genes[subjectHits(ol1)]
head(CvLgenes)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | pvalue qvalue meth.diff
## <Rle> <IRanges> <Rle> | <numeric> <numeric> <numeric>
## [1] KK215283.1 634828 + | 0.246992 0.879298 8.52391
## [2] KK215283.1 634829 + | 0.430606 0.941929 -6.10611
## [3] KK215283.1 634833 + | 0.657484 0.986634 -4.23977
## [4] KK215283.1 634834 + | 0.855708 0.986634 1.92308
## [5] KK215283.1 634877 + | 0.959279 0.986634 -0.47619
## [6] KK215283.1 634878 + | 0.340879 0.901546 9.71429
## -------
## seqinfo: 2441 sequences from an unspecified genome; no seqlengthsmygenesol1## GRanges object with 5324171 ranges and 3 metadata columns:
## seqnames ranges strand | gene_id
## <Rle> <IRanges> <Rle> | <character>
## [1] KK215283.1 634721-638733 + | ENSPREG00000018045
## [2] KK215283.1 634721-638733 + | ENSPREG00000018045
## [3] KK215283.1 634721-638733 + | ENSPREG00000018045
## [4] KK215283.1 634721-638733 + | ENSPREG00000018045
## [5] KK215283.1 634721-638733 + | ENSPREG00000018045
## ... ... ... ... . ...
## [5324167] LG9 34074214-34108653 + | ENSPREG00000019083
## [5324168] LG9 34074214-34108653 + | ENSPREG00000019083
## [5324169] LG9 34074214-34108653 + | ENSPREG00000019083
## [5324170] LG9 34074214-34108653 + | ENSPREG00000019083
## [5324171] LG9 34074214-34108653 + | ENSPREG00000019083
## gene_biotype gene_name
## <character> <character>
## [1] protein_coding <NA>
## [2] protein_coding <NA>
## [3] protein_coding <NA>
## [4] protein_coding <NA>
## [5] protein_coding <NA>
## ... ... ...
## [5324167] protein_coding adamtsl2
## [5324168] protein_coding adamtsl2
## [5324169] protein_coding adamtsl2
## [5324170] protein_coding adamtsl2
## [5324171] protein_coding adamtsl2
## -------
## seqinfo: 463 sequences from an unspecified genome; no seqlengthsCvLgenesdf <- as.data.frame(CvLgenes,row.names = 1:nrow(as.data.frame(ranges(CvLgenes))))
str(CvLgenesdf)## 'data.frame': 5324171 obs. of 8 variables:
## $ seqnames : Factor w/ 2441 levels "KK215283.1","KK215284.1",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ start : int 634828 634829 634833 634834 634877 634878 634882 634883 635036 635037 ...
## $ end : int 634828 634829 634833 634834 634877 634878 634882 634883 635036 635037 ...
## $ width : int 1 1 1 1 1 1 1 1 1 1 ...
## $ strand : Factor w/ 3 levels "+","-","*": 1 1 1 1 1 1 1 1 1 1 ...
## $ pvalue : num 0.247 0.431 0.657 0.856 0.959 ...
## $ qvalue : num 0.879 0.942 0.987 0.987 0.987 ...
## $ meth.diff: num 8.524 -6.106 -4.24 1.923 -0.476 ...mygenesoldf1 <- as.data.frame(mygenesol1,row.names = 1:nrow(as.data.frame(ranges(mygenesol1))))
head(mygenesoldf1)## seqnames start end width strand gene_id gene_biotype
## 1 KK215283.1 634721 638733 4013 + ENSPREG00000018045 protein_coding
## 2 KK215283.1 634721 638733 4013 + ENSPREG00000018045 protein_coding
## 3 KK215283.1 634721 638733 4013 + ENSPREG00000018045 protein_coding
## 4 KK215283.1 634721 638733 4013 + ENSPREG00000018045 protein_coding
## 5 KK215283.1 634721 638733 4013 + ENSPREG00000018045 protein_coding
## 6 KK215283.1 634721 638733 4013 + ENSPREG00000018045 protein_coding
## gene_name
## 1 <NA>
## 2 <NA>
## 3 <NA>
## 4 <NA>
## 5 <NA>
## 6 <NA>CvLgenesdf <- cbind(CvLgenesdf,mygenesoldf1[c("gene_id","gene_biotype","gene_name")])
CvLgenesdf$seqnames <- as.character(CvLgenesdf$seqnames)
head(CvLgenesdf)## seqnames start end width strand pvalue qvalue meth.diff
## 1 KK215283.1 634828 634828 1 + 0.2469920 0.8792980 8.5239085
## 2 KK215283.1 634829 634829 1 + 0.4306059 0.9419291 -6.1061061
## 3 KK215283.1 634833 634833 1 + 0.6574838 0.9866335 -4.2397661
## 4 KK215283.1 634834 634834 1 + 0.8557075 0.9866335 1.9230769
## 5 KK215283.1 634877 634877 1 + 0.9592788 0.9866335 -0.4761905
## 6 KK215283.1 634878 634878 1 + 0.3408788 0.9015464 9.7142857
## gene_id gene_biotype gene_name
## 1 ENSPREG00000018045 protein_coding <NA>
## 2 ENSPREG00000018045 protein_coding <NA>
## 3 ENSPREG00000018045 protein_coding <NA>
## 4 ENSPREG00000018045 protein_coding <NA>
## 5 ENSPREG00000018045 protein_coding <NA>
## 6 ENSPREG00000018045 protein_coding <NA>CvLgeneschrdf <- CvLgenesdf[grep("LG",CvLgenesdf$seqnames),]
head(CvLgeneschrdf)## seqnames start end width strand pvalue qvalue meth.diff
## 201026 LG1 370928 370928 1 + 0.4088249 0.9312908 -10.151803
## 201027 LG1 370929 370929 1 + 0.6597244 0.9866335 5.098684
## 201028 LG1 370994 370994 1 + 0.8585480 0.9866335 2.116935
## 201029 LG1 371191 371191 1 + 0.4124990 0.9332077 -7.512315
## 201030 LG1 371192 371192 1 + 0.5951440 0.9866335 -4.743833
## 201031 LG1 371227 371227 1 + 0.2710360 0.8814624 6.954887
## gene_id gene_biotype gene_name
## 201026 ENSPREG00000000039 protein_coding <NA>
## 201027 ENSPREG00000000039 protein_coding <NA>
## 201028 ENSPREG00000000039 protein_coding <NA>
## 201029 ENSPREG00000000039 protein_coding <NA>
## 201030 ENSPREG00000000039 protein_coding <NA>
## 201031 ENSPREG00000000039 protein_coding <NA>CvLgeneschrdf <- CvLgeneschrdf[order(CvLgeneschrdf[,7]), ]
head(CvLgeneschrdf,10)## seqnames start end width strand pvalue qvalue
## 2460944 LG19 4233614 4233614 1 + 8.650817e-10 0.007885634
## 2538498 LG19 15379719 15379719 1 + 1.573263e-07 0.454344073
## 1233468 LG13 22916688 22916688 1 + 8.333341e-07 0.504339931
## 2562745 LG19 18314781 18314781 1 + 1.251644e-06 0.504339931
## 2633973 LG19 26560884 26560884 1 + 1.229688e-06 0.504339931
## 2649322 LG2 377092 377092 1 + 9.436707e-07 0.504339931
## 2651466 LG2 449260 449260 1 + 1.316960e-06 0.504339931
## 2658131 LG2 1285106 1285106 1 + 1.298464e-06 0.504339931
## 2977079 LG2 45245104 45245104 1 + 4.418371e-07 0.504339931
## 3470539 LG22 14100551 14100551 1 + 1.287505e-06 0.504339931
## meth.diff gene_id gene_biotype gene_name
## 2460944 65.96774 ENSPREG00000021117 protein_coding tspan9a
## 2538498 -62.66667 ENSPREG00000009677 protein_coding SDK2
## 1233468 53.57143 ENSPREG00000006939 protein_coding LSAMP
## 2562745 50.00000 ENSPREG00000014274 protein_coding cep131
## 2633973 -72.30769 ENSPREG00000001715 protein_coding atad1b
## 2649322 41.37931 ENSPREG00000006354 protein_coding zgc:152904
## 2651466 -62.37037 ENSPREG00000006354 protein_coding zgc:152904
## 2658131 71.70868 ENSPREG00000007421 protein_coding trim25l
## 2977079 -40.00000 ENSPREG00000020747 protein_coding col5a2a
## 3470539 -35.48387 ENSPREG00000003116 protein_coding maco1brm(CvLgenes)
rm(CvLgenesdf)ol1 <- findOverlaps(methylkitGvLGR,my_genes)## Warning in .Seqinfo.mergexy(x, y): Each of the 2 combined objects has sequence levels not in the other:
## - in 'x': KK215332.1, KK215339.1, KK215341.1, KK215351.1, KK215360.1, KK215378.1, KK215383.1, KK215387.1, KK215388.1, KK215391.1, KK215393.1, KK215395.1, KK215396.1, KK215397.1, KK215400.1, KK215401.1, KK215402.1, KK215403.1, KK215405.1, KK215406.1, KK215407.1, KK215408.1, KK215411.1, KK215412.1, KK215414.1, KK215415.1, KK215418.1, KK215419.1, KK215420.1, KK215421.1, KK215424.1, KK215425.1, KK215427.1, KK215429.1, KK215430.1, KK215432.1, KK215433.1, KK215435.1, KK215439.1, KK215440.1, KK215441.1, KK215443.1, KK215444.1, KK215446.1, KK215448.1, KK215451.1, KK215453.1, KK215454.1, KK215455.1, KK215456.1, KK215459.1, KK215462.1, KK215463.1, KK215465.1, KK215466.1, KK215467.1, KK215472.1, KK215474.1, KK215475.1, KK215479.1, KK215480.1, KK215482.1, KK215484.1, KK215485.1, KK215486.1, KK215488.1, KK215489.1, KK215490.1, KK215491.1, KK215492.1, KK215494.1, KK215496.1, KK215497.1, KK215498.1, KK215501.1, KK215502.1, KK215503.1, KK215504.1, KK215506.1, KK215507.1, KK215508.1, KK215511.1, KK215512.1, KK215513.1, KK215514.1, KK215515.1, KK215516.1, KK215517.1, KK215518.1, KK215519.1, KK215521.1, KK215523.1, KK215524.1, KK215525.1, KK215526.1, KK215528.1, KK215529.1, KK215530.1, KK215531.1, KK215533.1, KK215538.1, KK215540.1, KK215541.1, KK215543.1, KK215544.1, KK215545.1, KK215546.1, KK215547.1, KK215548.1, KK215549.1, KK215551.1, KK215553.1, KK215554.1, KK215556.1, KK215558.1, KK215559.1, KK215560.1, KK215561.1, KK215562.1, KK215564.1, KK215567.1, KK215568.1, KK215573.1, KK215574.1, KK215577.1, KK215578.1, KK215579.1, KK215581.1, KK215582.1, KK215583.1, KK215584.1, KK215585.1, KK215586.1, KK215587.1, KK215588.1, KK215589.1, KK215590.1, KK215594.1, KK215595.1, KK215597.1, KK215598.1, KK215601.1, KK215602.1, KK215603.1, KK215605.1, KK215606.1, KK215608.1, KK215615.1, KK215616.1, KK215620.1, KK215621.1, KK215622.1, KK215624.1, KK215625.1, KK215626.1, KK215627.1, KK215628.1, KK215629.1, KK215630.1, KK215632.1, KK215633.1, KK215634.1, KK215635.1, KK215636.1, KK215637.1, KK215638.1, KK215639.1, KK215641.1, KK215642.1, KK215644.1, KK215645.1, KK215646.1, KK215647.1, KK215649.1, KK215652.1, KK215654.1, KK215655.1, KK215657.1, KK215658.1, KK215661.1, KK215662.1, KK215663.1, KK215664.1, KK215665.1, KK215668.1, KK215669.1, KK215670.1, KK215671.1, KK215672.1, KK215673.1, KK215675.1, KK215677.1, KK215678.1, KK215683.1, KK215684.1, KK215688.1, KK215689.1, KK215692.1, KK215694.1, KK215695.1, KK215699.1, KK215700.1, KK215701.1, KK215703.1, KK215704.1, KK215705.1, KK215706.1, KK215707.1, KK215709.1, KK215710.1, KK215711.1, KK215712.1, KK215715.1, KK215718.1, KK215719.1, KK215720.1, KK215721.1, KK215722.1, KK215723.1, KK215724.1, KK215726.1, KK215727.1, KK215728.1, KK215733.1, KK215734.1, KK215736.1, KK215737.1, KK215738.1, KK215739.1, KK215740.1, KK215741.1, KK215742.1, KK215743.1, KK215745.1, KK215748.1, KK215750.1, KK215752.1, KK215753.1, KK215754.1, KK215755.1, KK215756.1, KK215757.1, KK215758.1, KK215759.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215766.1, KK215767.1, KK215768.1, KK215769.1, KK215770.1, KK215771.1, KK215772.1, KK215774.1, KK215775.1, KK215776.1, KK215777.1, KK215778.1, KK215779.1, KK215780.1, KK215782.1, KK215783.1, KK215785.1, KK215786.1, KK215788.1, KK215789.1, KK215792.1, KK215794.1, KK215795.1, KK215796.1, KK215797.1, KK215798.1, KK215802.1, KK215804.1, KK215805.1, KK215807.1, KK215810.1, KK215812.1, KK215814.1, KK215815.1, KK215816.1, KK215818.1, KK215819.1, KK215821.1, KK215822.1, KK215825.1, KK215827.1, KK215831.1, KK215832.1, KK215834.1, KK215836.1, KK215837.1, KK215838.1, KK215839.1, KK215840.1, KK215841.1, KK215842.1, KK215843.1, KK215846.1, KK215847.1, KK215848.1, KK215849.1, KK215851.1, KK215852.1, KK215854.1, KK215857.1, KK215858.1, KK215859.1, KK215860.1, KK215861.1, KK215863.1, KK215864.1, KK215865.1, KK215867.1, KK215869.1, KK215870.1, KK215872.1, KK215873.1, KK215874.1, KK215875.1, KK215877.1, KK215878.1, KK215880.1, KK215881.1, KK215882.1, KK215884.1, KK215885.1, KK215886.1, KK215890.1, KK215891.1, KK215892.1, KK215893.1, KK215894.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215902.1, KK215903.1, KK215905.1, KK215907.1, KK215908.1, KK215909.1, KK215910.1, KK215911.1, KK215913.1, KK215914.1, KK215915.1, KK215917.1, KK215918.1, KK215920.1, KK215921.1, KK215922.1, KK215923.1, KK215924.1, KK215927.1, KK215928.1, KK215929.1, KK215933.1, KK215934.1, KK215935.1, KK215937.1, KK215938.1, KK215940.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215946.1, KK215949.1, KK215951.1, KK215952.1, KK215953.1, KK215956.1, KK215957.1, KK215958.1, KK215960.1, KK215962.1, KK215963.1, KK215965.1, KK215967.1, KK215969.1, KK215970.1, KK215971.1, KK215972.1, KK215973.1, KK215974.1, KK215975.1, KK215976.1, KK215977.1, KK215978.1, KK215979.1, KK215982.1, KK215983.1, KK215984.1, KK215985.1, KK215986.1, KK215987.1, KK215989.1, KK215990.1, KK215993.1, KK215994.1, KK215995.1, KK215996.1, KK215997.1, KK215999.1, KK216000.1, KK216001.1, KK216005.1, KK216006.1, KK216007.1, KK216008.1, KK216009.1, KK216011.1, KK216012.1, KK216015.1, KK216016.1, KK216017.1, KK216018.1, KK216021.1, KK216022.1, KK216023.1, KK216024.1, KK216025.1, KK216026.1, KK216027.1, KK216028.1, KK216029.1, KK216030.1, KK216032.1, KK216033.1, KK216034.1, KK216035.1, KK216036.1, KK216037.1, KK216038.1, KK216039.1, KK216040.1, KK216041.1, KK216042.1, KK216043.1, KK216044.1, KK216047.1, KK216048.1, KK216049.1, KK216050.1, KK216053.1, KK216055.1, KK216056.1, KK216058.1, KK216059.1, KK216062.1, KK216063.1, KK216064.1, KK216065.1, KK216066.1, KK216067.1, KK216068.1, KK216069.1, KK216070.1, KK216071.1, KK216072.1, KK216074.1, KK216075.1, KK216076.1, KK216077.1, KK216078.1, KK216079.1, KK216080.1, KK216082.1, KK216083.1, KK216084.1, KK216085.1, KK216086.1, KK216087.1, KK216089.1, KK216091.1, KK216093.1, KK216094.1, KK216095.1, KK216096.1, KK216097.1, KK216098.1, KK216099.1, KK216102.1, KK216103.1, KK216106.1, KK216109.1, KK216110.1, KK216111.1, KK216112.1, KK216113.1, KK216114.1, KK216115.1, KK216117.1, KK216118.1, KK216120.1, KK216122.1, KK216124.1, KK216125.1, KK216126.1, KK216127.1, KK216128.1, KK216131.1, KK216133.1, KK216134.1, KK216135.1, KK216137.1, KK216138.1, KK216140.1, KK216141.1, KK216142.1, KK216143.1, KK216144.1, KK216145.1, KK216146.1, KK216150.1, KK216151.1, KK216152.1, KK216154.1, KK216155.1, KK216157.1, KK216158.1, KK216159.1, KK216160.1, KK216162.1, KK216163.1, KK216164.1, KK216165.1, KK216166.1, KK216168.1, KK216169.1, KK216171.1, KK216172.1, KK216173.1, KK216174.1, KK216175.1, KK216176.1, KK216177.1, KK216178.1, KK216180.1, KK216181.1, KK216182.1, KK216184.1, KK216186.1, KK216190.1, KK216192.1, KK216193.1, KK216194.1, KK216195.1, KK216196.1, KK216197.1, KK216198.1, KK216200.1, KK216201.1, KK216202.1, KK216203.1, KK216205.1, KK216206.1, KK216208.1, KK216212.1, KK216213.1, KK216214.1, KK216215.1, KK216217.1, KK216218.1, KK216219.1, KK216221.1, KK216222.1, KK216224.1, KK216225.1, KK216226.1, KK216227.1, KK216229.1, KK216231.1, KK216232.1, KK216234.1, KK216235.1, KK216236.1, KK216237.1, KK216238.1, KK216239.1, KK216240.1, KK216241.1, KK216242.1, KK216243.1, KK216244.1, KK216245.1, KK216248.1, KK216249.1, KK216251.1, KK216252.1, KK216253.1, KK216254.1, KK216256.1, KK216258.1, KK216259.1, KK216260.1, KK216261.1, KK216262.1, KK216263.1, KK216264.1, KK216265.1, KK216266.1, KK216267.1, KK216269.1, KK216270.1, KK216271.1, KK216272.1, KK216273.1, KK216274.1, KK216275.1, KK216276.1, KK216278.1, KK216280.1, KK216281.1, KK216282.1, KK216283.1, KK216284.1, KK216285.1, KK216287.1, KK216288.1, KK216289.1, KK216290.1, KK216291.1, KK216292.1, KK216293.1, KK216295.1, KK216296.1, KK216297.1, KK216298.1, KK216299.1, KK216301.1, KK216302.1, KK216303.1, KK216304.1, KK216306.1, KK216307.1, KK216308.1, KK216310.1, KK216311.1, KK216313.1, KK216315.1, KK216316.1, KK216317.1, KK216318.1, KK216319.1, KK216320.1, KK216321.1, KK216322.1, KK216323.1, KK216324.1, KK216325.1, KK216326.1, KK216327.1, KK216328.1, KK216329.1, KK216330.1, KK216331.1, KK216333.1, KK216334.1, KK216335.1, KK216336.1, KK216337.1, KK216338.1, KK216340.1, KK216341.1, KK216342.1, KK216343.1, KK216344.1, KK216345.1, KK216346.1, KK216347.1, KK216349.ol1## Hits object with 6103392 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 28361 21953
## [2] 28362 21953
## [3] 28363 21953
## [4] 28364 21953
## [5] 28365 21953
## ... ... ...
## [6103388] 21227486 3357
## [6103389] 21227487 3357
## [6103390] 21227488 3357
## [6103391] 21227489 3357
## [6103392] 21227490 3357
## -------
## queryLength: 21234500 / subjectLength: 23254GvLgenes <- methylkitGvLGR[queryHits(ol1)]
mygenesol1 <- my_genes[subjectHits(ol1)]
head(GvLgenes)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | pvalue qvalue meth.diff
## <Rle> <IRanges> <Rle> | <numeric> <numeric> <numeric>
## [1] KK215283.1 634819 + | 0.985566 0.985470 0.184275
## [2] KK215283.1 634828 + | 0.321343 0.911687 6.941839
## [3] KK215283.1 634829 + | 0.459876 0.959983 6.486486
## [4] KK215283.1 634833 + | 0.260271 0.898880 -9.730722
## [5] KK215283.1 634877 + | 0.342616 0.920027 -7.386760
## [6] KK215283.1 634878 + | 0.641144 0.985470 3.896104
## -------
## seqinfo: 2483 sequences from an unspecified genome; no seqlengthsmygenesol1## GRanges object with 6103392 ranges and 3 metadata columns:
## seqnames ranges strand | gene_id
## <Rle> <IRanges> <Rle> | <character>
## [1] KK215283.1 634721-638733 + | ENSPREG00000018045
## [2] KK215283.1 634721-638733 + | ENSPREG00000018045
## [3] KK215283.1 634721-638733 + | ENSPREG00000018045
## [4] KK215283.1 634721-638733 + | ENSPREG00000018045
## [5] KK215283.1 634721-638733 + | ENSPREG00000018045
## ... ... ... ... . ...
## [6103388] LG9 34074214-34108653 + | ENSPREG00000019083
## [6103389] LG9 34074214-34108653 + | ENSPREG00000019083
## [6103390] LG9 34074214-34108653 + | ENSPREG00000019083
## [6103391] LG9 34074214-34108653 + | ENSPREG00000019083
## [6103392] LG9 34074214-34108653 + | ENSPREG00000019083
## gene_biotype gene_name
## <character> <character>
## [1] protein_coding <NA>
## [2] protein_coding <NA>
## [3] protein_coding <NA>
## [4] protein_coding <NA>
## [5] protein_coding <NA>
## ... ... ...
## [6103388] protein_coding adamtsl2
## [6103389] protein_coding adamtsl2
## [6103390] protein_coding adamtsl2
## [6103391] protein_coding adamtsl2
## [6103392] protein_coding adamtsl2
## -------
## seqinfo: 463 sequences from an unspecified genome; no seqlengthsGvLgenesdf <- as.data.frame(GvLgenes,row.names = 1:nrow(as.data.frame(ranges(GvLgenes))))
str(GvLgenesdf)## 'data.frame': 6103392 obs. of 8 variables:
## $ seqnames : Factor w/ 2483 levels "KK215283.1","KK215284.1",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ start : int 634819 634828 634829 634833 634877 634878 634882 634883 635036 635037 ...
## $ end : int 634819 634828 634829 634833 634877 634878 634882 634883 635036 635037 ...
## $ width : int 1 1 1 1 1 1 1 1 1 1 ...
## $ strand : Factor w/ 3 levels "+","-","*": 1 1 1 1 1 1 1 1 1 1 ...
## $ pvalue : num 0.986 0.321 0.46 0.26 0.343 ...
## $ qvalue : num 0.985 0.912 0.96 0.899 0.92 ...
## $ meth.diff: num 0.184 6.942 6.486 -9.731 -7.387 ...mygenesoldf1 <- as.data.frame(mygenesol1,row.names = 1:nrow(as.data.frame(ranges(mygenesol1))))
head(mygenesoldf1)## seqnames start end width strand gene_id gene_biotype
## 1 KK215283.1 634721 638733 4013 + ENSPREG00000018045 protein_coding
## 2 KK215283.1 634721 638733 4013 + ENSPREG00000018045 protein_coding
## 3 KK215283.1 634721 638733 4013 + ENSPREG00000018045 protein_coding
## 4 KK215283.1 634721 638733 4013 + ENSPREG00000018045 protein_coding
## 5 KK215283.1 634721 638733 4013 + ENSPREG00000018045 protein_coding
## 6 KK215283.1 634721 638733 4013 + ENSPREG00000018045 protein_coding
## gene_name
## 1 <NA>
## 2 <NA>
## 3 <NA>
## 4 <NA>
## 5 <NA>
## 6 <NA>GvLgenesdf <- cbind(GvLgenesdf,mygenesoldf1[c("gene_id","gene_biotype","gene_name")])
GvLgenesdf$seqnames <- as.character(GvLgenesdf$seqnames)
head(GvLgenesdf)## seqnames start end width strand pvalue qvalue meth.diff
## 1 KK215283.1 634819 634819 1 + 0.9855660 0.9854701 0.1842752
## 2 KK215283.1 634828 634828 1 + 0.3213426 0.9116874 6.9418386
## 3 KK215283.1 634829 634829 1 + 0.4598763 0.9599828 6.4864865
## 4 KK215283.1 634833 634833 1 + 0.2602714 0.8988798 -9.7307222
## 5 KK215283.1 634877 634877 1 + 0.3426160 0.9200267 -7.3867596
## 6 KK215283.1 634878 634878 1 + 0.6411436 0.9854701 3.8961039
## gene_id gene_biotype gene_name
## 1 ENSPREG00000018045 protein_coding <NA>
## 2 ENSPREG00000018045 protein_coding <NA>
## 3 ENSPREG00000018045 protein_coding <NA>
## 4 ENSPREG00000018045 protein_coding <NA>
## 5 ENSPREG00000018045 protein_coding <NA>
## 6 ENSPREG00000018045 protein_coding <NA>GvLgeneschrdf <- GvLgenesdf[grep("LG",GvLgenesdf$seqnames),]
head(GvLgeneschrdf)## seqnames start end width strand pvalue qvalue meth.diff
## 234566 LG1 370928 370928 1 + 0.7329085 0.9854701 3.949580
## 234567 LG1 370929 370929 1 + 0.6022629 0.9854701 -5.764411
## 234568 LG1 370994 370994 1 + 0.8585480 0.9854701 2.116935
## 234569 LG1 370995 370995 1 + 0.2717842 0.9007027 -11.627907
## 234570 LG1 371191 371191 1 + 0.9004467 0.9854701 -1.190476
## 234571 LG1 371192 371192 1 + 0.7028533 0.9854701 -3.361345
## gene_id gene_biotype gene_name
## 234566 ENSPREG00000000039 protein_coding <NA>
## 234567 ENSPREG00000000039 protein_coding <NA>
## 234568 ENSPREG00000000039 protein_coding <NA>
## 234569 ENSPREG00000000039 protein_coding <NA>
## 234570 ENSPREG00000000039 protein_coding <NA>
## 234571 ENSPREG00000000039 protein_coding <NA>GvLgeneschrdf <- GvLgeneschrdf[order(GvLgeneschrdf[,7]), ]
head(GvLgeneschrdf,10)## seqnames start end width strand pvalue qvalue
## 2388420 LG17 4774357 4774357 1 + 5.842523e-08 0.08732888
## 1171364 LG12 19502054 19502054 1 + 1.880141e-07 0.19257549
## 4770087 LG5 2856738 2856738 1 + 1.999029e-07 0.19257549
## 5928120 LG9 9539135 9539135 1 + 3.187294e-07 0.27401711
## 4565343 LG4 9137302 9137302 1 + 3.796739e-07 0.28358728
## 2836779 LG19 5548608 5548608 1 + 4.744448e-07 0.32026502
## 2667805 LG18 7031638 7031638 1 + 5.288252e-07 0.33533869
## 4097377 LG23 2913467 2913467 1 + 7.356941e-07 0.35812320
## 6014511 LG9 21683027 21683027 1 + 7.530081e-07 0.35812320
## 3361805 LG2 37766339 37766339 1 + 8.053226e-07 0.36635111
## meth.diff gene_id gene_biotype gene_name
## 2388420 59.65157 ENSPREG00000004944 protein_coding LRP8
## 1171364 48.00000 ENSPREG00000016764 protein_coding TMEM38B
## 4770087 -53.47826 ENSPREG00000022796 protein_coding ip6k1
## 5928120 -36.17021 ENSPREG00000003163 protein_coding antxr2a
## 4565343 44.44444 ENSPREG00000009366 protein_coding TNS3
## 2836779 -49.04880 ENSPREG00000022122 protein_coding kcnh4b
## 2667805 -58.38207 ENSPREG00000008202 protein_coding <NA>
## 4097377 -49.89418 ENSPREG00000023036 protein_coding anks1b
## 6014511 -49.00585 ENSPREG00000021577 protein_coding EPX
## 3361805 -49.59083 ENSPREG00000014758 protein_coding ugt1a1rm(GvLgenes)
rm(GvLgenesdf)Methylkit tile results annotated to genes
ol1 <- findOverlaps(methylkitTilesCvGGR,my_genes)## Warning in .Seqinfo.mergexy(x, y): Each of the 2 combined objects has sequence levels not in the other:
## - in 'x': KK215332.1, KK215339.1, KK215341.1, KK215351.1, KK215360.1, KK215378.1, KK215383.1, KK215387.1, KK215391.1, KK215393.1, KK215395.1, KK215396.1, KK215400.1, KK215401.1, KK215402.1, KK215403.1, KK215405.1, KK215406.1, KK215407.1, KK215408.1, KK215411.1, KK215412.1, KK215414.1, KK215415.1, KK215418.1, KK215419.1, KK215420.1, KK215421.1, KK215424.1, KK215425.1, KK215427.1, KK215430.1, KK215432.1, KK215433.1, KK215435.1, KK215439.1, KK215440.1, KK215441.1, KK215443.1, KK215444.1, KK215446.1, KK215448.1, KK215451.1, KK215453.1, KK215454.1, KK215455.1, KK215456.1, KK215459.1, KK215462.1, KK215463.1, KK215465.1, KK215466.1, KK215467.1, KK215472.1, KK215474.1, KK215475.1, KK215479.1, KK215480.1, KK215482.1, KK215484.1, KK215485.1, KK215486.1, KK215488.1, KK215490.1, KK215491.1, KK215492.1, KK215494.1, KK215496.1, KK215497.1, KK215498.1, KK215501.1, KK215502.1, KK215503.1, KK215504.1, KK215506.1, KK215507.1, KK215508.1, KK215511.1, KK215512.1, KK215513.1, KK215514.1, KK215515.1, KK215516.1, KK215517.1, KK215518.1, KK215519.1, KK215521.1, KK215523.1, KK215524.1, KK215525.1, KK215526.1, KK215528.1, KK215529.1, KK215530.1, KK215531.1, KK215533.1, KK215538.1, KK215540.1, KK215541.1, KK215543.1, KK215544.1, KK215545.1, KK215546.1, KK215547.1, KK215548.1, KK215549.1, KK215551.1, KK215553.1, KK215554.1, KK215556.1, KK215558.1, KK215559.1, KK215560.1, KK215561.1, KK215562.1, KK215567.1, KK215568.1, KK215573.1, KK215574.1, KK215577.1, KK215578.1, KK215579.1, KK215581.1, KK215582.1, KK215583.1, KK215584.1, KK215585.1, KK215586.1, KK215587.1, KK215588.1, KK215589.1, KK215590.1, KK215594.1, KK215595.1, KK215597.1, KK215598.1, KK215601.1, KK215602.1, KK215603.1, KK215605.1, KK215606.1, KK215608.1, KK215615.1, KK215616.1, KK215620.1, KK215621.1, KK215622.1, KK215624.1, KK215625.1, KK215626.1, KK215627.1, KK215628.1, KK215629.1, KK215630.1, KK215632.1, KK215633.1, KK215634.1, KK215635.1, KK215636.1, KK215637.1, KK215638.1, KK215639.1, KK215641.1, KK215642.1, KK215644.1, KK215645.1, KK215646.1, KK215647.1, KK215649.1, KK215652.1, KK215654.1, KK215655.1, KK215657.1, KK215658.1, KK215661.1, KK215662.1, KK215663.1, KK215664.1, KK215665.1, KK215668.1, KK215669.1, KK215670.1, KK215671.1, KK215672.1, KK215673.1, KK215675.1, KK215677.1, KK215678.1, KK215683.1, KK215684.1, KK215688.1, KK215689.1, KK215692.1, KK215694.1, KK215695.1, KK215699.1, KK215700.1, KK215701.1, KK215703.1, KK215704.1, KK215705.1, KK215706.1, KK215707.1, KK215709.1, KK215710.1, KK215711.1, KK215712.1, KK215715.1, KK215718.1, KK215719.1, KK215720.1, KK215721.1, KK215722.1, KK215723.1, KK215724.1, KK215726.1, KK215727.1, KK215728.1, KK215733.1, KK215734.1, KK215736.1, KK215737.1, KK215738.1, KK215739.1, KK215740.1, KK215741.1, KK215742.1, KK215743.1, KK215745.1, KK215748.1, KK215750.1, KK215752.1, KK215753.1, KK215754.1, KK215755.1, KK215756.1, KK215757.1, KK215758.1, KK215759.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215767.1, KK215768.1, KK215769.1, KK215770.1, KK215771.1, KK215772.1, KK215774.1, KK215775.1, KK215776.1, KK215777.1, KK215778.1, KK215779.1, KK215780.1, KK215782.1, KK215783.1, KK215785.1, KK215786.1, KK215788.1, KK215789.1, KK215792.1, KK215794.1, KK215795.1, KK215796.1, KK215797.1, KK215798.1, KK215802.1, KK215804.1, KK215807.1, KK215810.1, KK215812.1, KK215814.1, KK215815.1, KK215816.1, KK215818.1, KK215819.1, KK215821.1, KK215825.1, KK215827.1, KK215832.1, KK215834.1, KK215836.1, KK215837.1, KK215838.1, KK215839.1, KK215840.1, KK215841.1, KK215842.1, KK215843.1, KK215846.1, KK215847.1, KK215848.1, KK215849.1, KK215851.1, KK215852.1, KK215854.1, KK215857.1, KK215858.1, KK215859.1, KK215860.1, KK215861.1, KK215863.1, KK215864.1, KK215865.1, KK215867.1, KK215869.1, KK215870.1, KK215872.1, KK215873.1, KK215875.1, KK215877.1, KK215878.1, KK215880.1, KK215881.1, KK215882.1, KK215884.1, KK215885.1, KK215886.1, KK215890.1, KK215891.1, KK215892.1, KK215893.1, KK215894.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215902.1, KK215903.1, KK215907.1, KK215908.1, KK215909.1, KK215910.1, KK215911.1, KK215913.1, KK215915.1, KK215917.1, KK215918.1, KK215920.1, KK215921.1, KK215922.1, KK215923.1, KK215924.1, KK215927.1, KK215928.1, KK215929.1, KK215933.1, KK215934.1, KK215935.1, KK215937.1, KK215938.1, KK215940.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215946.1, KK215949.1, KK215951.1, KK215952.1, KK215953.1, KK215956.1, KK215957.1, KK215960.1, KK215962.1, KK215963.1, KK215965.1, KK215967.1, KK215969.1, KK215970.1, KK215971.1, KK215972.1, KK215973.1, KK215974.1, KK215975.1, KK215976.1, KK215977.1, KK215978.1, KK215979.1, KK215982.1, KK215983.1, KK215984.1, KK215985.1, KK215987.1, KK215989.1, KK215990.1, KK215993.1, KK215994.1, KK215995.1, KK215996.1, KK215997.1, KK215999.1, KK216000.1, KK216001.1, KK216006.1, KK216007.1, KK216008.1, KK216009.1, KK216011.1, KK216012.1, KK216015.1, KK216017.1, KK216018.1, KK216021.1, KK216022.1, KK216023.1, KK216024.1, KK216025.1, KK216026.1, KK216027.1, KK216028.1, KK216029.1, KK216030.1, KK216032.1, KK216033.1, KK216034.1, KK216035.1, KK216036.1, KK216037.1, KK216038.1, KK216039.1, KK216040.1, KK216041.1, KK216042.1, KK216043.1, KK216044.1, KK216047.1, KK216048.1, KK216049.1, KK216050.1, KK216053.1, KK216055.1, KK216056.1, KK216058.1, KK216059.1, KK216062.1, KK216063.1, KK216064.1, KK216065.1, KK216066.1, KK216067.1, KK216068.1, KK216069.1, KK216070.1, KK216071.1, KK216072.1, KK216074.1, KK216075.1, KK216076.1, KK216077.1, KK216078.1, KK216079.1, KK216080.1, KK216082.1, KK216083.1, KK216084.1, KK216085.1, KK216086.1, KK216087.1, KK216089.1, KK216093.1, KK216094.1, KK216095.1, KK216096.1, KK216097.1, KK216098.1, KK216099.1, KK216102.1, KK216103.1, KK216106.1, KK216109.1, KK216111.1, KK216112.1, KK216113.1, KK216114.1, KK216115.1, KK216117.1, KK216118.1, KK216120.1, KK216122.1, KK216124.1, KK216125.1, KK216126.1, KK216128.1, KK216131.1, KK216133.1, KK216134.1, KK216135.1, KK216137.1, KK216138.1, KK216140.1, KK216141.1, KK216142.1, KK216143.1, KK216144.1, KK216145.1, KK216146.1, KK216150.1, KK216151.1, KK216152.1, KK216154.1, KK216155.1, KK216157.1, KK216158.1, KK216159.1, KK216160.1, KK216162.1, KK216163.1, KK216164.1, KK216165.1, KK216166.1, KK216168.1, KK216169.1, KK216171.1, KK216172.1, KK216173.1, KK216174.1, KK216175.1, KK216176.1, KK216177.1, KK216178.1, KK216180.1, KK216181.1, KK216182.1, KK216184.1, KK216186.1, KK216190.1, KK216192.1, KK216193.1, KK216194.1, KK216195.1, KK216197.1, KK216198.1, KK216200.1, KK216201.1, KK216202.1, KK216203.1, KK216205.1, KK216206.1, KK216208.1, KK216212.1, KK216213.1, KK216214.1, KK216215.1, KK216217.1, KK216219.1, KK216221.1, KK216222.1, KK216224.1, KK216225.1, KK216226.1, KK216227.1, KK216229.1, KK216231.1, KK216232.1, KK216234.1, KK216235.1, KK216236.1, KK216237.1, KK216238.1, KK216240.1, KK216241.1, KK216242.1, KK216244.1, KK216245.1, KK216248.1, KK216251.1, KK216252.1, KK216253.1, KK216254.1, KK216256.1, KK216258.1, KK216259.1, KK216260.1, KK216261.1, KK216262.1, KK216263.1, KK216264.1, KK216265.1, KK216266.1, KK216267.1, KK216269.1, KK216270.1, KK216272.1, KK216273.1, KK216275.1, KK216276.1, KK216278.1, KK216280.1, KK216281.1, KK216282.1, KK216283.1, KK216284.1, KK216285.1, KK216287.1, KK216288.1, KK216289.1, KK216290.1, KK216291.1, KK216293.1, KK216295.1, KK216296.1, KK216297.1, KK216299.1, KK216302.1, KK216303.1, KK216304.1, KK216306.1, KK216307.1, KK216308.1, KK216310.1, KK216311.1, KK216313.1, KK216315.1, KK216316.1, KK216317.1, KK216318.1, KK216319.1, KK216320.1, KK216321.1, KK216322.1, KK216323.1, KK216324.1, KK216325.1, KK216326.1, KK216328.1, KK216329.1, KK216330.1, KK216331.1, KK216333.1, KK216334.1, KK216337.1, KK216338.1, KK216341.1, KK216342.1, KK216343.1, KK216344.1, KK216345.1, KK216346.1, KK216347.1, KK216351.1, KK216353.1, KK216354.1, KK216356.1, KK216359.1, KK216360.1, KK216362.1, KK216363.1, KK216364.1, KK216365.1, KK216366.1, KK216368.1, KK216369.1, KK216370.1, KK216371.1, KK216372.1, KK216374.1, KK216375.1, KK216376.1, KK216377.1, KK216378.1, KK216379.1, KK216381.1, KK216382.1, KK216383.1, KK216384.1, KK216386.1, KK216387.1, KK216388.1, KK216389.1, KK216390.1, KK216391.1, KK216392.1, KK216393.ol1## Hits object with 350565 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 1 21951
## [2] 2 21951
## [3] 3 21951
## [4] 4 21951
## [5] 5 21951
## ... ... ...
## [350561] 612816 3358
## [350562] 612817 3358
## [350563] 612818 3358
## [350564] 612819 3358
## [350565] 612820 3358
## -------
## queryLength: 612876 / subjectLength: 23254CvGgenes <- methylkitTilesCvGGR[queryHits(ol1)]
mygenesol1 <- my_genes[subjectHits(ol1)]
head(CvGgenes)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | pvalue qvalue meth.diff
## <Rle> <IRanges> <Rle> | <numeric> <numeric> <numeric>
## [1] KK215283.1 1001-2000 * | 7.54969e-02 2.32106e-01 2.900534
## [2] KK215283.1 2001-3000 * | 1.08579e-02 7.48798e-02 -7.506131
## [3] KK215283.1 3001-4000 * | 6.10716e-01 6.72251e-01 0.755263
## [4] KK215283.1 4001-5000 * | 9.42330e-01 8.02695e-01 -0.122143
## [5] KK215283.1 5001-6000 * | 4.79208e-08 1.08141e-05 -3.417290
## [6] KK215283.1 6001-7000 * | 5.26550e-01 6.29430e-01 0.460160
## -------
## seqinfo: 2173 sequences from an unspecified genome; no seqlengthsmygenesol1## GRanges object with 350565 ranges and 3 metadata columns:
## seqnames ranges strand | gene_id
## <Rle> <IRanges> <Rle> | <character>
## [1] KK215283.1 21-50200 - | ENSPREG00000017956
## [2] KK215283.1 21-50200 - | ENSPREG00000017956
## [3] KK215283.1 21-50200 - | ENSPREG00000017956
## [4] KK215283.1 21-50200 - | ENSPREG00000017956
## [5] KK215283.1 21-50200 - | ENSPREG00000017956
## ... ... ... ... . ...
## [350561] LG9 34108009-34113251 - | ENSPREG00000019150
## [350562] LG9 34108009-34113251 - | ENSPREG00000019150
## [350563] LG9 34108009-34113251 - | ENSPREG00000019150
## [350564] LG9 34108009-34113251 - | ENSPREG00000019150
## [350565] LG9 34108009-34113251 - | ENSPREG00000019150
## gene_biotype gene_name
## <character> <character>
## [1] protein_coding usp6nl
## [2] protein_coding usp6nl
## [3] protein_coding usp6nl
## [4] protein_coding usp6nl
## [5] protein_coding usp6nl
## ... ... ...
## [350561] protein_coding FAM163B
## [350562] protein_coding FAM163B
## [350563] protein_coding FAM163B
## [350564] protein_coding FAM163B
## [350565] protein_coding FAM163B
## -------
## seqinfo: 463 sequences from an unspecified genome; no seqlengthsCvGgenesdf <- as.data.frame(CvGgenes,row.names = 1:nrow(as.data.frame(ranges(CvGgenes))))
str(CvGgenesdf)## 'data.frame': 350565 obs. of 8 variables:
## $ seqnames : Factor w/ 2173 levels "KK215283.1","KK215284.1",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ start : int 1001 2001 3001 4001 5001 6001 7001 8001 9001 10001 ...
## $ end : int 2000 3000 4000 5000 6000 7000 8000 9000 10000 11000 ...
## $ width : int 1000 1000 1000 1000 1000 1000 1000 1000 1000 1000 ...
## $ strand : Factor w/ 3 levels "+","-","*": 3 3 3 3 3 3 3 3 3 3 ...
## $ pvalue : num 7.55e-02 1.09e-02 6.11e-01 9.42e-01 4.79e-08 ...
## $ qvalue : num 2.32e-01 7.49e-02 6.72e-01 8.03e-01 1.08e-05 ...
## $ meth.diff: num 2.901 -7.506 0.755 -0.122 -3.417 ...mygenesoldf1 <- as.data.frame(mygenesol1,row.names = 1:nrow(as.data.frame(ranges(mygenesol1))))
head(mygenesoldf1)## seqnames start end width strand gene_id gene_biotype
## 1 KK215283.1 21 50200 50180 - ENSPREG00000017956 protein_coding
## 2 KK215283.1 21 50200 50180 - ENSPREG00000017956 protein_coding
## 3 KK215283.1 21 50200 50180 - ENSPREG00000017956 protein_coding
## 4 KK215283.1 21 50200 50180 - ENSPREG00000017956 protein_coding
## 5 KK215283.1 21 50200 50180 - ENSPREG00000017956 protein_coding
## 6 KK215283.1 21 50200 50180 - ENSPREG00000017956 protein_coding
## gene_name
## 1 usp6nl
## 2 usp6nl
## 3 usp6nl
## 4 usp6nl
## 5 usp6nl
## 6 usp6nlCvGgenesdf <- cbind(CvGgenesdf,mygenesoldf1[c("gene_id","gene_biotype","gene_name")])
CvGgenesdf$seqnames <- as.character(CvGgenesdf$seqnames)
head(CvGgenesdf)## seqnames start end width strand pvalue qvalue meth.diff
## 1 KK215283.1 1001 2000 1000 * 7.549694e-02 2.321064e-01 2.9005339
## 2 KK215283.1 2001 3000 1000 * 1.085788e-02 7.487981e-02 -7.5061315
## 3 KK215283.1 3001 4000 1000 * 6.107164e-01 6.722510e-01 0.7552625
## 4 KK215283.1 4001 5000 1000 * 9.423302e-01 8.026952e-01 -0.1221433
## 5 KK215283.1 5001 6000 1000 * 4.792084e-08 1.081407e-05 -3.4172905
## 6 KK215283.1 6001 7000 1000 * 5.265504e-01 6.294296e-01 0.4601605
## gene_id gene_biotype gene_name
## 1 ENSPREG00000017956 protein_coding usp6nl
## 2 ENSPREG00000017956 protein_coding usp6nl
## 3 ENSPREG00000017956 protein_coding usp6nl
## 4 ENSPREG00000017956 protein_coding usp6nl
## 5 ENSPREG00000017956 protein_coding usp6nl
## 6 ENSPREG00000017956 protein_coding usp6nlCvGgeneschrdf <- CvGgenesdf[grep("LG",CvGgenesdf$seqnames),]
head(CvGgeneschrdf)## seqnames start end width strand pvalue qvalue meth.diff
## 9882 LG1 370001 371000 1000 * 0.001067668 0.01709797 8.0374510
## 9883 LG1 371001 372000 1000 * 0.098296250 0.26851123 -4.0579934
## 9884 LG1 373001 374000 1000 * 0.387934041 0.54585170 2.1415440
## 9885 LG1 374001 375000 1000 * 0.359606981 0.52609411 -1.9335817
## 9886 LG1 375001 376000 1000 * 0.850561299 0.77177761 -0.2866242
## 9887 LG1 376001 377000 1000 * 0.015165361 0.09152602 -4.0334807
## gene_id gene_biotype gene_name
## 9882 ENSPREG00000000039 protein_coding <NA>
## 9883 ENSPREG00000000039 protein_coding <NA>
## 9884 ENSPREG00000000039 protein_coding <NA>
## 9885 ENSPREG00000000039 protein_coding <NA>
## 9886 ENSPREG00000000039 protein_coding <NA>
## 9887 ENSPREG00000000039 protein_coding <NA>CvGgeneschrdf <- CvGgeneschrdf[order(CvGgeneschrdf[,7]), ]
head(CvGgeneschrdf,10)## seqnames start end width strand pvalue qvalue
## 157446 LG19 1188001 1189000 1000 * 1.774652e-81 2.974987e-76
## 76291 LG13 18161001 18162000 1000 * 3.721408e-59 3.743092e-54
## 14405 LG1 9073001 9074000 1000 * 3.550053e-47 2.550528e-42
## 203997 LG21 1055001 1056000 1000 * 2.372031e-46 1.491158e-41
## 18677 LG1 17897001 17898000 1000 * 1.654721e-42 9.246461e-38
## 156721 LG18 21720001 21721000 1000 * 1.092368e-36 4.994240e-32
## 156722 LG18 21720001 21721000 1000 * 1.092368e-36 4.994240e-32
## 161865 LG19 10333001 10334000 1000 * 1.033326e-35 4.330611e-31
## 223201 LG22 14521001 14522000 1000 * 7.000381e-34 2.514704e-29
## 345235 LG9 23623001 23624000 1000 * 8.468147e-34 2.839163e-29
## meth.diff gene_id gene_biotype gene_name
## 157446 -22.272263 ENSPREG00000017528 protein_coding SHANK1
## 76291 20.536203 ENSPREG00000001265 protein_coding <NA>
## 14405 14.606176 ENSPREG00000000312 protein_coding slx4
## 203997 14.585360 ENSPREG00000013853 protein_coding hivep2a
## 18677 -6.231157 ENSPREG00000004582 protein_coding <NA>
## 156721 -15.394290 ENSPREG00000014753 protein_coding aimp1b
## 156722 -15.394290 ENSPREG00000014824 protein_coding <NA>
## 161865 16.787633 ENSPREG00000002350 protein_coding QRFPR
## 223201 -31.913947 ENSPREG00000003390 protein_coding <NA>
## 345235 14.478395 ENSPREG00000003004 protein_coding homer1bnrow(subset(CvGgeneschrdf,qvalue<0.05))## [1] 33648nrow(subset(CvGgeneschrdf,qvalue<0.05&meth.diff>0))## [1] 9745nrow(subset(CvGgeneschrdf,qvalue<0.05&meth.diff<0))## [1] 23903rm(CvGgenesdf)
rm(CvGgenes)ol1 <- findOverlaps(methylkitTilesCvLGR,my_genes)## Warning in .Seqinfo.mergexy(x, y): Each of the 2 combined objects has sequence levels not in the other:
## - in 'x': KK215332.1, KK215339.1, KK215341.1, KK215351.1, KK215360.1, KK215378.1, KK215383.1, KK215387.1, KK215391.1, KK215393.1, KK215395.1, KK215396.1, KK215400.1, KK215401.1, KK215402.1, KK215403.1, KK215405.1, KK215406.1, KK215407.1, KK215408.1, KK215411.1, KK215412.1, KK215414.1, KK215415.1, KK215418.1, KK215419.1, KK215420.1, KK215421.1, KK215424.1, KK215425.1, KK215427.1, KK215430.1, KK215432.1, KK215433.1, KK215435.1, KK215439.1, KK215440.1, KK215441.1, KK215443.1, KK215444.1, KK215446.1, KK215448.1, KK215451.1, KK215453.1, KK215454.1, KK215455.1, KK215456.1, KK215459.1, KK215462.1, KK215463.1, KK215465.1, KK215466.1, KK215467.1, KK215472.1, KK215474.1, KK215475.1, KK215479.1, KK215480.1, KK215482.1, KK215484.1, KK215485.1, KK215486.1, KK215488.1, KK215490.1, KK215491.1, KK215492.1, KK215494.1, KK215496.1, KK215497.1, KK215498.1, KK215501.1, KK215502.1, KK215503.1, KK215504.1, KK215506.1, KK215507.1, KK215508.1, KK215511.1, KK215512.1, KK215513.1, KK215514.1, KK215515.1, KK215516.1, KK215517.1, KK215518.1, KK215519.1, KK215521.1, KK215523.1, KK215524.1, KK215525.1, KK215526.1, KK215528.1, KK215529.1, KK215530.1, KK215531.1, KK215533.1, KK215538.1, KK215540.1, KK215541.1, KK215543.1, KK215544.1, KK215545.1, KK215546.1, KK215547.1, KK215548.1, KK215549.1, KK215551.1, KK215553.1, KK215554.1, KK215556.1, KK215558.1, KK215559.1, KK215560.1, KK215561.1, KK215562.1, KK215567.1, KK215568.1, KK215573.1, KK215574.1, KK215577.1, KK215578.1, KK215579.1, KK215581.1, KK215582.1, KK215583.1, KK215584.1, KK215585.1, KK215586.1, KK215587.1, KK215588.1, KK215589.1, KK215590.1, KK215594.1, KK215595.1, KK215597.1, KK215598.1, KK215601.1, KK215602.1, KK215603.1, KK215605.1, KK215606.1, KK215608.1, KK215615.1, KK215616.1, KK215620.1, KK215621.1, KK215622.1, KK215624.1, KK215625.1, KK215626.1, KK215627.1, KK215628.1, KK215629.1, KK215630.1, KK215632.1, KK215633.1, KK215634.1, KK215635.1, KK215636.1, KK215637.1, KK215638.1, KK215639.1, KK215641.1, KK215642.1, KK215644.1, KK215645.1, KK215646.1, KK215647.1, KK215649.1, KK215652.1, KK215654.1, KK215655.1, KK215657.1, KK215658.1, KK215661.1, KK215662.1, KK215663.1, KK215664.1, KK215665.1, KK215668.1, KK215669.1, KK215670.1, KK215671.1, KK215672.1, KK215673.1, KK215675.1, KK215677.1, KK215678.1, KK215683.1, KK215684.1, KK215688.1, KK215689.1, KK215692.1, KK215694.1, KK215695.1, KK215699.1, KK215700.1, KK215701.1, KK215703.1, KK215704.1, KK215705.1, KK215706.1, KK215707.1, KK215709.1, KK215710.1, KK215711.1, KK215712.1, KK215715.1, KK215718.1, KK215719.1, KK215720.1, KK215721.1, KK215722.1, KK215723.1, KK215724.1, KK215726.1, KK215727.1, KK215728.1, KK215733.1, KK215734.1, KK215736.1, KK215737.1, KK215738.1, KK215739.1, KK215740.1, KK215741.1, KK215742.1, KK215743.1, KK215745.1, KK215748.1, KK215750.1, KK215752.1, KK215753.1, KK215754.1, KK215755.1, KK215756.1, KK215757.1, KK215758.1, KK215759.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215767.1, KK215768.1, KK215769.1, KK215770.1, KK215771.1, KK215772.1, KK215774.1, KK215775.1, KK215776.1, KK215777.1, KK215778.1, KK215779.1, KK215780.1, KK215782.1, KK215783.1, KK215785.1, KK215786.1, KK215788.1, KK215789.1, KK215792.1, KK215794.1, KK215795.1, KK215796.1, KK215797.1, KK215798.1, KK215802.1, KK215804.1, KK215807.1, KK215810.1, KK215812.1, KK215814.1, KK215815.1, KK215816.1, KK215818.1, KK215819.1, KK215821.1, KK215825.1, KK215827.1, KK215832.1, KK215834.1, KK215836.1, KK215837.1, KK215838.1, KK215839.1, KK215840.1, KK215841.1, KK215842.1, KK215843.1, KK215846.1, KK215847.1, KK215848.1, KK215849.1, KK215851.1, KK215852.1, KK215854.1, KK215857.1, KK215858.1, KK215859.1, KK215860.1, KK215861.1, KK215863.1, KK215864.1, KK215865.1, KK215867.1, KK215869.1, KK215872.1, KK215873.1, KK215875.1, KK215877.1, KK215878.1, KK215880.1, KK215881.1, KK215882.1, KK215884.1, KK215885.1, KK215886.1, KK215890.1, KK215891.1, KK215892.1, KK215893.1, KK215894.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215902.1, KK215903.1, KK215907.1, KK215908.1, KK215909.1, KK215910.1, KK215911.1, KK215913.1, KK215915.1, KK215917.1, KK215918.1, KK215920.1, KK215921.1, KK215922.1, KK215923.1, KK215924.1, KK215927.1, KK215928.1, KK215929.1, KK215933.1, KK215934.1, KK215935.1, KK215937.1, KK215938.1, KK215940.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215946.1, KK215949.1, KK215951.1, KK215952.1, KK215953.1, KK215956.1, KK215957.1, KK215960.1, KK215962.1, KK215963.1, KK215965.1, KK215967.1, KK215969.1, KK215970.1, KK215971.1, KK215972.1, KK215973.1, KK215974.1, KK215975.1, KK215976.1, KK215977.1, KK215978.1, KK215979.1, KK215982.1, KK215983.1, KK215984.1, KK215985.1, KK215987.1, KK215989.1, KK215990.1, KK215993.1, KK215994.1, KK215995.1, KK215996.1, KK215997.1, KK215999.1, KK216000.1, KK216001.1, KK216006.1, KK216007.1, KK216008.1, KK216009.1, KK216011.1, KK216012.1, KK216015.1, KK216017.1, KK216018.1, KK216021.1, KK216022.1, KK216023.1, KK216024.1, KK216025.1, KK216026.1, KK216027.1, KK216028.1, KK216029.1, KK216030.1, KK216032.1, KK216033.1, KK216034.1, KK216035.1, KK216036.1, KK216037.1, KK216038.1, KK216039.1, KK216040.1, KK216041.1, KK216042.1, KK216043.1, KK216044.1, KK216047.1, KK216048.1, KK216049.1, KK216050.1, KK216053.1, KK216055.1, KK216056.1, KK216058.1, KK216059.1, KK216062.1, KK216063.1, KK216064.1, KK216065.1, KK216066.1, KK216067.1, KK216068.1, KK216069.1, KK216070.1, KK216071.1, KK216072.1, KK216074.1, KK216075.1, KK216076.1, KK216077.1, KK216078.1, KK216079.1, KK216080.1, KK216082.1, KK216083.1, KK216084.1, KK216085.1, KK216086.1, KK216087.1, KK216089.1, KK216093.1, KK216094.1, KK216095.1, KK216096.1, KK216097.1, KK216098.1, KK216099.1, KK216102.1, KK216103.1, KK216106.1, KK216109.1, KK216111.1, KK216112.1, KK216113.1, KK216114.1, KK216115.1, KK216117.1, KK216118.1, KK216120.1, KK216122.1, KK216124.1, KK216125.1, KK216126.1, KK216128.1, KK216131.1, KK216133.1, KK216134.1, KK216135.1, KK216137.1, KK216138.1, KK216140.1, KK216141.1, KK216142.1, KK216143.1, KK216144.1, KK216145.1, KK216146.1, KK216150.1, KK216151.1, KK216152.1, KK216154.1, KK216155.1, KK216157.1, KK216158.1, KK216159.1, KK216160.1, KK216162.1, KK216163.1, KK216164.1, KK216165.1, KK216166.1, KK216168.1, KK216169.1, KK216171.1, KK216172.1, KK216173.1, KK216174.1, KK216175.1, KK216176.1, KK216177.1, KK216178.1, KK216180.1, KK216181.1, KK216182.1, KK216184.1, KK216186.1, KK216190.1, KK216192.1, KK216193.1, KK216194.1, KK216195.1, KK216197.1, KK216198.1, KK216200.1, KK216201.1, KK216202.1, KK216203.1, KK216205.1, KK216206.1, KK216208.1, KK216212.1, KK216213.1, KK216214.1, KK216215.1, KK216217.1, KK216219.1, KK216221.1, KK216222.1, KK216224.1, KK216225.1, KK216226.1, KK216227.1, KK216229.1, KK216231.1, KK216232.1, KK216234.1, KK216235.1, KK216236.1, KK216237.1, KK216238.1, KK216240.1, KK216241.1, KK216242.1, KK216244.1, KK216245.1, KK216248.1, KK216251.1, KK216252.1, KK216253.1, KK216254.1, KK216256.1, KK216258.1, KK216259.1, KK216260.1, KK216261.1, KK216262.1, KK216263.1, KK216264.1, KK216265.1, KK216266.1, KK216267.1, KK216269.1, KK216270.1, KK216272.1, KK216273.1, KK216275.1, KK216276.1, KK216278.1, KK216280.1, KK216281.1, KK216282.1, KK216283.1, KK216284.1, KK216285.1, KK216287.1, KK216288.1, KK216289.1, KK216290.1, KK216291.1, KK216293.1, KK216295.1, KK216296.1, KK216297.1, KK216299.1, KK216302.1, KK216303.1, KK216304.1, KK216306.1, KK216307.1, KK216308.1, KK216310.1, KK216311.1, KK216313.1, KK216315.1, KK216316.1, KK216317.1, KK216318.1, KK216319.1, KK216320.1, KK216321.1, KK216322.1, KK216323.1, KK216324.1, KK216325.1, KK216326.1, KK216328.1, KK216329.1, KK216330.1, KK216331.1, KK216333.1, KK216334.1, KK216337.1, KK216338.1, KK216341.1, KK216342.1, KK216343.1, KK216344.1, KK216345.1, KK216346.1, KK216347.1, KK216351.1, KK216353.1, KK216354.1, KK216356.1, KK216359.1, KK216360.1, KK216362.1, KK216363.1, KK216364.1, KK216365.1, KK216366.1, KK216368.1, KK216369.1, KK216370.1, KK216371.1, KK216372.1, KK216374.1, KK216375.1, KK216376.1, KK216377.1, KK216379.1, KK216381.1, KK216382.1, KK216383.1, KK216384.1, KK216386.1, KK216387.1, KK216388.1, KK216389.1, KK216390.1, KK216391.1, KK216392.1, KK216393.1, KK216394.1, KK216396.ol1## Hits object with 349945 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 1 21951
## [2] 2 21951
## [3] 3 21951
## [4] 4 21951
## [5] 5 21951
## ... ... ...
## [349941] 611501 3358
## [349942] 611502 3358
## [349943] 611503 3358
## [349944] 611504 3358
## [349945] 611505 3358
## -------
## queryLength: 611561 / subjectLength: 23254CvLgenes <- methylkitTilesCvLGR[queryHits(ol1)]
mygenesol1 <- my_genes[subjectHits(ol1)]
head(CvLgenes)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | pvalue qvalue meth.diff
## <Rle> <IRanges> <Rle> | <numeric> <numeric> <numeric>
## [1] KK215283.1 1001-2000 * | 4.30647e-01 5.91581e-01 -1.461714
## [2] KK215283.1 2001-3000 * | 1.74928e-01 3.84578e-01 -3.979328
## [3] KK215283.1 3001-4000 * | 7.67264e-01 7.55458e-01 -0.461540
## [4] KK215283.1 4001-5000 * | 5.92167e-01 6.79646e-01 -0.933934
## [5] KK215283.1 5001-6000 * | 3.18914e-07 5.26265e-05 -3.373850
## [6] KK215283.1 6001-7000 * | 5.00608e-01 6.32279e-01 0.509671
## -------
## seqinfo: 2159 sequences from an unspecified genome; no seqlengthsmygenesol1## GRanges object with 349945 ranges and 3 metadata columns:
## seqnames ranges strand | gene_id
## <Rle> <IRanges> <Rle> | <character>
## [1] KK215283.1 21-50200 - | ENSPREG00000017956
## [2] KK215283.1 21-50200 - | ENSPREG00000017956
## [3] KK215283.1 21-50200 - | ENSPREG00000017956
## [4] KK215283.1 21-50200 - | ENSPREG00000017956
## [5] KK215283.1 21-50200 - | ENSPREG00000017956
## ... ... ... ... . ...
## [349941] LG9 34108009-34113251 - | ENSPREG00000019150
## [349942] LG9 34108009-34113251 - | ENSPREG00000019150
## [349943] LG9 34108009-34113251 - | ENSPREG00000019150
## [349944] LG9 34108009-34113251 - | ENSPREG00000019150
## [349945] LG9 34108009-34113251 - | ENSPREG00000019150
## gene_biotype gene_name
## <character> <character>
## [1] protein_coding usp6nl
## [2] protein_coding usp6nl
## [3] protein_coding usp6nl
## [4] protein_coding usp6nl
## [5] protein_coding usp6nl
## ... ... ...
## [349941] protein_coding FAM163B
## [349942] protein_coding FAM163B
## [349943] protein_coding FAM163B
## [349944] protein_coding FAM163B
## [349945] protein_coding FAM163B
## -------
## seqinfo: 463 sequences from an unspecified genome; no seqlengthsCvLgenesdf <- as.data.frame(CvLgenes,row.names = 1:nrow(as.data.frame(ranges(CvLgenes))))
str(CvLgenesdf)## 'data.frame': 349945 obs. of 8 variables:
## $ seqnames : Factor w/ 2159 levels "KK215283.1","KK215284.1",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ start : int 1001 2001 3001 4001 5001 6001 7001 8001 9001 10001 ...
## $ end : int 2000 3000 4000 5000 6000 7000 8000 9000 10000 11000 ...
## $ width : int 1000 1000 1000 1000 1000 1000 1000 1000 1000 1000 ...
## $ strand : Factor w/ 3 levels "+","-","*": 3 3 3 3 3 3 3 3 3 3 ...
## $ pvalue : num 4.31e-01 1.75e-01 7.67e-01 5.92e-01 3.19e-07 ...
## $ qvalue : num 5.92e-01 3.85e-01 7.55e-01 6.80e-01 5.26e-05 ...
## $ meth.diff: num -1.462 -3.979 -0.462 -0.934 -3.374 ...mygenesoldf1 <- as.data.frame(mygenesol1,row.names = 1:nrow(as.data.frame(ranges(mygenesol1))))
head(mygenesoldf1)## seqnames start end width strand gene_id gene_biotype
## 1 KK215283.1 21 50200 50180 - ENSPREG00000017956 protein_coding
## 2 KK215283.1 21 50200 50180 - ENSPREG00000017956 protein_coding
## 3 KK215283.1 21 50200 50180 - ENSPREG00000017956 protein_coding
## 4 KK215283.1 21 50200 50180 - ENSPREG00000017956 protein_coding
## 5 KK215283.1 21 50200 50180 - ENSPREG00000017956 protein_coding
## 6 KK215283.1 21 50200 50180 - ENSPREG00000017956 protein_coding
## gene_name
## 1 usp6nl
## 2 usp6nl
## 3 usp6nl
## 4 usp6nl
## 5 usp6nl
## 6 usp6nlCvLgenesdf <- cbind(CvLgenesdf,mygenesoldf1[c("gene_id","gene_biotype","gene_name")])
CvLgenesdf$seqnames <- as.character(CvLgenesdf$seqnames)
head(CvLgenesdf)## seqnames start end width strand pvalue qvalue meth.diff
## 1 KK215283.1 1001 2000 1000 * 4.306472e-01 5.915813e-01 -1.4617137
## 2 KK215283.1 2001 3000 1000 * 1.749284e-01 3.845782e-01 -3.9793282
## 3 KK215283.1 3001 4000 1000 * 7.672639e-01 7.554584e-01 -0.4615403
## 4 KK215283.1 4001 5000 1000 * 5.921675e-01 6.796464e-01 -0.9339341
## 5 KK215283.1 5001 6000 1000 * 3.189136e-07 5.262654e-05 -3.3738501
## 6 KK215283.1 6001 7000 1000 * 5.006083e-01 6.322791e-01 0.5096713
## gene_id gene_biotype gene_name
## 1 ENSPREG00000017956 protein_coding usp6nl
## 2 ENSPREG00000017956 protein_coding usp6nl
## 3 ENSPREG00000017956 protein_coding usp6nl
## 4 ENSPREG00000017956 protein_coding usp6nl
## 5 ENSPREG00000017956 protein_coding usp6nl
## 6 ENSPREG00000017956 protein_coding usp6nlCvLgeneschrdf <- CvLgenesdf[grep("LG",CvLgenesdf$seqnames),]
head(CvLgeneschrdf)## seqnames start end width strand pvalue qvalue meth.diff
## 9869 LG1 370001 371000 1000 * 0.1466453 0.3515362 3.7859305
## 9870 LG1 371001 372000 1000 * 0.9564776 0.8198574 0.1310079
## 9871 LG1 373001 374000 1000 * 0.8755416 0.7941430 0.4072183
## 9872 LG1 374001 375000 1000 * 0.6786091 0.7193430 -0.9156532
## 9873 LG1 375001 376000 1000 * 0.7407755 0.7449283 -0.5467398
## 9874 LG1 376001 377000 1000 * 0.7699869 0.7564810 0.4727832
## gene_id gene_biotype gene_name
## 9869 ENSPREG00000000039 protein_coding <NA>
## 9870 ENSPREG00000000039 protein_coding <NA>
## 9871 ENSPREG00000000039 protein_coding <NA>
## 9872 ENSPREG00000000039 protein_coding <NA>
## 9873 ENSPREG00000000039 protein_coding <NA>
## 9874 ENSPREG00000000039 protein_coding <NA>CvLgeneschrdf <- CvLgeneschrdf[order(CvLgeneschrdf[,7]), ]
head(CvLgeneschrdf,10)## seqnames start end width strand pvalue qvalue
## 113524 LG16 509001 510000 1000 * 3.213330e-96 1.635845e-90
## 203638 LG21 1055001 1056000 1000 * 8.837088e-72 2.249397e-66
## 157168 LG19 1188001 1189000 1000 * 1.236241e-66 2.097822e-61
## 161585 LG19 10333001 10334000 1000 * 5.976181e-65 7.605902e-60
## 344625 LG9 23623001 23624000 1000 * 3.595176e-58 3.660472e-53
## 180121 LG2 20995001 20996000 1000 * 4.065070e-48 2.956357e-43
## 311551 LG7 18259001 18260000 1000 * 8.559718e-41 4.357590e-36
## 54558 LG11 28461001 28462000 1000 * 1.078697e-40 4.992221e-36
## 203346 LG21 538001 539000 1000 * 5.735034e-40 2.432998e-35
## 203347 LG21 538001 539000 1000 * 5.735034e-40 2.432998e-35
## meth.diff gene_id gene_biotype gene_name
## 113524 -25.98584 ENSPREG00000014798 protein_coding <NA>
## 203638 19.69921 ENSPREG00000013853 protein_coding hivep2a
## 157168 -20.54554 ENSPREG00000017528 protein_coding SHANK1
## 161585 22.88567 ENSPREG00000002350 protein_coding QRFPR
## 344625 20.83910 ENSPREG00000003004 protein_coding homer1b
## 180121 -20.26683 ENSPREG00000014863 protein_coding ephx2
## 311551 23.29152 ENSPREG00000003617 protein_coding uts2a
## 54558 -13.62358 ENSPREG00000010167 protein_coding ncdn
## 203346 -13.78305 ENSPREG00000012615 protein_coding crnkl1
## 203347 -13.78305 ENSPREG00000012722 protein_coding <NA>nrow(subset(CvLgeneschrdf,qvalue<0.05))## [1] 29132nrow(subset(CvLgeneschrdf,qvalue<0.05&meth.diff>0))## [1] 11337nrow(subset(CvLgeneschrdf,qvalue<0.05&meth.diff<0))## [1] 17795rm(CvLgenes)
rm(CvLgenesdf)ol1 <- findOverlaps(methylkitTilesGvLGR,my_genes)## Warning in .Seqinfo.mergexy(x, y): Each of the 2 combined objects has sequence levels not in the other:
## - in 'x': KK215332.1, KK215339.1, KK215341.1, KK215351.1, KK215360.1, KK215378.1, KK215383.1, KK215387.1, KK215391.1, KK215393.1, KK215395.1, KK215396.1, KK215397.1, KK215400.1, KK215401.1, KK215402.1, KK215403.1, KK215405.1, KK215406.1, KK215407.1, KK215408.1, KK215411.1, KK215412.1, KK215414.1, KK215415.1, KK215418.1, KK215419.1, KK215420.1, KK215421.1, KK215424.1, KK215425.1, KK215427.1, KK215429.1, KK215430.1, KK215432.1, KK215433.1, KK215435.1, KK215439.1, KK215440.1, KK215441.1, KK215443.1, KK215444.1, KK215446.1, KK215448.1, KK215451.1, KK215453.1, KK215454.1, KK215455.1, KK215456.1, KK215459.1, KK215462.1, KK215463.1, KK215465.1, KK215466.1, KK215467.1, KK215472.1, KK215474.1, KK215475.1, KK215479.1, KK215480.1, KK215482.1, KK215484.1, KK215485.1, KK215486.1, KK215488.1, KK215490.1, KK215491.1, KK215492.1, KK215494.1, KK215496.1, KK215497.1, KK215498.1, KK215501.1, KK215502.1, KK215503.1, KK215504.1, KK215506.1, KK215507.1, KK215508.1, KK215511.1, KK215512.1, KK215513.1, KK215514.1, KK215515.1, KK215516.1, KK215517.1, KK215518.1, KK215519.1, KK215521.1, KK215523.1, KK215524.1, KK215525.1, KK215526.1, KK215528.1, KK215529.1, KK215530.1, KK215531.1, KK215533.1, KK215538.1, KK215540.1, KK215541.1, KK215543.1, KK215544.1, KK215545.1, KK215546.1, KK215547.1, KK215548.1, KK215549.1, KK215551.1, KK215553.1, KK215554.1, KK215556.1, KK215558.1, KK215559.1, KK215560.1, KK215561.1, KK215562.1, KK215567.1, KK215568.1, KK215573.1, KK215574.1, KK215577.1, KK215578.1, KK215579.1, KK215581.1, KK215582.1, KK215583.1, KK215584.1, KK215585.1, KK215586.1, KK215587.1, KK215588.1, KK215589.1, KK215590.1, KK215594.1, KK215595.1, KK215597.1, KK215598.1, KK215601.1, KK215602.1, KK215603.1, KK215605.1, KK215606.1, KK215608.1, KK215615.1, KK215616.1, KK215620.1, KK215621.1, KK215622.1, KK215624.1, KK215625.1, KK215626.1, KK215627.1, KK215628.1, KK215629.1, KK215630.1, KK215632.1, KK215633.1, KK215634.1, KK215635.1, KK215636.1, KK215637.1, KK215638.1, KK215639.1, KK215641.1, KK215642.1, KK215644.1, KK215645.1, KK215646.1, KK215647.1, KK215649.1, KK215652.1, KK215654.1, KK215655.1, KK215657.1, KK215658.1, KK215661.1, KK215662.1, KK215663.1, KK215664.1, KK215665.1, KK215668.1, KK215669.1, KK215670.1, KK215671.1, KK215672.1, KK215673.1, KK215675.1, KK215677.1, KK215678.1, KK215683.1, KK215684.1, KK215688.1, KK215689.1, KK215692.1, KK215694.1, KK215695.1, KK215699.1, KK215700.1, KK215701.1, KK215703.1, KK215704.1, KK215705.1, KK215706.1, KK215707.1, KK215709.1, KK215710.1, KK215711.1, KK215712.1, KK215715.1, KK215718.1, KK215719.1, KK215720.1, KK215721.1, KK215722.1, KK215723.1, KK215724.1, KK215726.1, KK215727.1, KK215728.1, KK215733.1, KK215734.1, KK215736.1, KK215737.1, KK215738.1, KK215739.1, KK215740.1, KK215741.1, KK215742.1, KK215743.1, KK215745.1, KK215748.1, KK215750.1, KK215752.1, KK215753.1, KK215754.1, KK215755.1, KK215756.1, KK215757.1, KK215758.1, KK215759.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215767.1, KK215768.1, KK215769.1, KK215770.1, KK215771.1, KK215772.1, KK215774.1, KK215775.1, KK215776.1, KK215777.1, KK215778.1, KK215779.1, KK215780.1, KK215782.1, KK215783.1, KK215785.1, KK215786.1, KK215788.1, KK215789.1, KK215792.1, KK215794.1, KK215795.1, KK215796.1, KK215797.1, KK215798.1, KK215802.1, KK215804.1, KK215805.1, KK215807.1, KK215810.1, KK215812.1, KK215814.1, KK215815.1, KK215816.1, KK215818.1, KK215819.1, KK215821.1, KK215825.1, KK215827.1, KK215832.1, KK215834.1, KK215836.1, KK215837.1, KK215838.1, KK215839.1, KK215840.1, KK215841.1, KK215842.1, KK215843.1, KK215846.1, KK215847.1, KK215848.1, KK215849.1, KK215851.1, KK215852.1, KK215854.1, KK215857.1, KK215858.1, KK215859.1, KK215860.1, KK215861.1, KK215863.1, KK215864.1, KK215865.1, KK215867.1, KK215869.1, KK215870.1, KK215872.1, KK215873.1, KK215875.1, KK215877.1, KK215878.1, KK215880.1, KK215881.1, KK215882.1, KK215884.1, KK215885.1, KK215886.1, KK215890.1, KK215891.1, KK215892.1, KK215893.1, KK215894.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215902.1, KK215903.1, KK215905.1, KK215907.1, KK215908.1, KK215909.1, KK215910.1, KK215911.1, KK215913.1, KK215915.1, KK215917.1, KK215918.1, KK215920.1, KK215921.1, KK215922.1, KK215923.1, KK215924.1, KK215927.1, KK215928.1, KK215929.1, KK215933.1, KK215934.1, KK215935.1, KK215937.1, KK215938.1, KK215940.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215946.1, KK215949.1, KK215951.1, KK215952.1, KK215953.1, KK215956.1, KK215957.1, KK215960.1, KK215962.1, KK215963.1, KK215965.1, KK215967.1, KK215969.1, KK215970.1, KK215971.1, KK215972.1, KK215973.1, KK215974.1, KK215975.1, KK215976.1, KK215977.1, KK215978.1, KK215979.1, KK215982.1, KK215983.1, KK215984.1, KK215985.1, KK215987.1, KK215989.1, KK215990.1, KK215993.1, KK215994.1, KK215995.1, KK215996.1, KK215997.1, KK215999.1, KK216000.1, KK216001.1, KK216005.1, KK216006.1, KK216007.1, KK216008.1, KK216009.1, KK216011.1, KK216012.1, KK216015.1, KK216017.1, KK216018.1, KK216021.1, KK216022.1, KK216023.1, KK216024.1, KK216025.1, KK216026.1, KK216027.1, KK216028.1, KK216029.1, KK216030.1, KK216032.1, KK216033.1, KK216034.1, KK216035.1, KK216036.1, KK216037.1, KK216038.1, KK216039.1, KK216040.1, KK216041.1, KK216042.1, KK216043.1, KK216044.1, KK216047.1, KK216048.1, KK216049.1, KK216050.1, KK216053.1, KK216055.1, KK216056.1, KK216058.1, KK216059.1, KK216062.1, KK216063.1, KK216064.1, KK216065.1, KK216066.1, KK216067.1, KK216068.1, KK216069.1, KK216070.1, KK216071.1, KK216072.1, KK216074.1, KK216075.1, KK216076.1, KK216077.1, KK216078.1, KK216079.1, KK216080.1, KK216082.1, KK216083.1, KK216084.1, KK216085.1, KK216086.1, KK216087.1, KK216089.1, KK216091.1, KK216093.1, KK216094.1, KK216095.1, KK216096.1, KK216097.1, KK216098.1, KK216099.1, KK216102.1, KK216103.1, KK216106.1, KK216109.1, KK216110.1, KK216111.1, KK216112.1, KK216113.1, KK216114.1, KK216115.1, KK216117.1, KK216118.1, KK216120.1, KK216122.1, KK216124.1, KK216125.1, KK216126.1, KK216128.1, KK216131.1, KK216133.1, KK216134.1, KK216135.1, KK216137.1, KK216138.1, KK216140.1, KK216141.1, KK216142.1, KK216143.1, KK216144.1, KK216145.1, KK216146.1, KK216150.1, KK216151.1, KK216152.1, KK216154.1, KK216155.1, KK216157.1, KK216158.1, KK216159.1, KK216160.1, KK216162.1, KK216163.1, KK216164.1, KK216165.1, KK216166.1, KK216168.1, KK216169.1, KK216171.1, KK216172.1, KK216173.1, KK216174.1, KK216175.1, KK216176.1, KK216177.1, KK216178.1, KK216180.1, KK216181.1, KK216182.1, KK216184.1, KK216186.1, KK216190.1, KK216192.1, KK216193.1, KK216194.1, KK216195.1, KK216197.1, KK216198.1, KK216200.1, KK216201.1, KK216202.1, KK216203.1, KK216205.1, KK216206.1, KK216208.1, KK216212.1, KK216213.1, KK216214.1, KK216215.1, KK216217.1, KK216218.1, KK216219.1, KK216221.1, KK216222.1, KK216224.1, KK216225.1, KK216226.1, KK216227.1, KK216229.1, KK216231.1, KK216232.1, KK216234.1, KK216235.1, KK216236.1, KK216237.1, KK216238.1, KK216239.1, KK216240.1, KK216241.1, KK216242.1, KK216244.1, KK216245.1, KK216248.1, KK216251.1, KK216252.1, KK216253.1, KK216254.1, KK216256.1, KK216258.1, KK216259.1, KK216260.1, KK216261.1, KK216262.1, KK216263.1, KK216264.1, KK216265.1, KK216266.1, KK216267.1, KK216269.1, KK216270.1, KK216271.1, KK216272.1, KK216273.1, KK216275.1, KK216276.1, KK216278.1, KK216280.1, KK216281.1, KK216282.1, KK216283.1, KK216284.1, KK216285.1, KK216287.1, KK216288.1, KK216289.1, KK216290.1, KK216291.1, KK216293.1, KK216295.1, KK216296.1, KK216297.1, KK216298.1, KK216299.1, KK216302.1, KK216303.1, KK216304.1, KK216306.1, KK216307.1, KK216308.1, KK216310.1, KK216311.1, KK216313.1, KK216315.1, KK216316.1, KK216317.1, KK216318.1, KK216319.1, KK216320.1, KK216321.1, KK216322.1, KK216323.1, KK216324.1, KK216325.1, KK216326.1, KK216327.1, KK216328.1, KK216329.1, KK216330.1, KK216331.1, KK216333.1, KK216334.1, KK216336.1, KK216337.1, KK216338.1, KK216340.1, KK216341.1, KK216342.1, KK216343.1, KK216344.1, KK216345.1, KK216346.1, KK216347.1, KK216349.1, KK216351.1, KK216353.1, KK216354.1, KK216356.1, KK216357.1, KK216359.1, KK216360.1, KK216362.1, KK216363.1, KK216364.1, KK216365.1, KK216366.1, KK216368.1, KK216369.1, KK216370.1, KK216371.1, KK216372.1, KK216374.1, KK216375.ol1## Hits object with 357714 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 1 21951
## [2] 2 21951
## [3] 3 21951
## [4] 4 21951
## [5] 5 21951
## ... ... ...
## [357710] 628122 3358
## [357711] 628123 3358
## [357712] 628124 3358
## [357713] 628125 3358
## [357714] 628126 3358
## -------
## queryLength: 628182 / subjectLength: 23254GvLgenes <- methylkitTilesGvLGR[queryHits(ol1)]
mygenesol1 <- my_genes[subjectHits(ol1)]
head(GvLgenes)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | pvalue qvalue meth.diff
## <Rle> <IRanges> <Rle> | <numeric> <numeric> <numeric>
## [1] KK215283.1 1001-2000 * | 0.00759549 0.0650142 -4.3622475
## [2] KK215283.1 2001-3000 * | 0.23017743 0.4379161 3.5268033
## [3] KK215283.1 3001-4000 * | 0.37746100 0.5551125 -1.2168028
## [4] KK215283.1 4001-5000 * | 0.59677981 0.6806876 -0.8117908
## [5] KK215283.1 5001-6000 * | 0.94558884 0.8157496 0.0434404
## [6] KK215283.1 6001-7000 * | 0.94231220 0.8147248 0.0495109
## -------
## seqinfo: 2259 sequences from an unspecified genome; no seqlengthsmygenesol1## GRanges object with 357714 ranges and 3 metadata columns:
## seqnames ranges strand | gene_id
## <Rle> <IRanges> <Rle> | <character>
## [1] KK215283.1 21-50200 - | ENSPREG00000017956
## [2] KK215283.1 21-50200 - | ENSPREG00000017956
## [3] KK215283.1 21-50200 - | ENSPREG00000017956
## [4] KK215283.1 21-50200 - | ENSPREG00000017956
## [5] KK215283.1 21-50200 - | ENSPREG00000017956
## ... ... ... ... . ...
## [357710] LG9 34108009-34113251 - | ENSPREG00000019150
## [357711] LG9 34108009-34113251 - | ENSPREG00000019150
## [357712] LG9 34108009-34113251 - | ENSPREG00000019150
## [357713] LG9 34108009-34113251 - | ENSPREG00000019150
## [357714] LG9 34108009-34113251 - | ENSPREG00000019150
## gene_biotype gene_name
## <character> <character>
## [1] protein_coding usp6nl
## [2] protein_coding usp6nl
## [3] protein_coding usp6nl
## [4] protein_coding usp6nl
## [5] protein_coding usp6nl
## ... ... ...
## [357710] protein_coding FAM163B
## [357711] protein_coding FAM163B
## [357712] protein_coding FAM163B
## [357713] protein_coding FAM163B
## [357714] protein_coding FAM163B
## -------
## seqinfo: 463 sequences from an unspecified genome; no seqlengthsGvLgenesdf <- as.data.frame(GvLgenes,row.names = 1:nrow(as.data.frame(ranges(GvLgenes))))
str(GvLgenesdf)## 'data.frame': 357714 obs. of 8 variables:
## $ seqnames : Factor w/ 2259 levels "KK215283.1","KK215284.1",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ start : int 1001 2001 3001 4001 5001 6001 7001 8001 9001 10001 ...
## $ end : int 2000 3000 4000 5000 6000 7000 8000 9000 10000 11000 ...
## $ width : int 1000 1000 1000 1000 1000 1000 1000 1000 1000 1000 ...
## $ strand : Factor w/ 3 levels "+","-","*": 3 3 3 3 3 3 3 3 3 3 ...
## $ pvalue : num 0.0076 0.2302 0.3775 0.5968 0.9456 ...
## $ qvalue : num 0.065 0.438 0.555 0.681 0.816 ...
## $ meth.diff: num -4.3622 3.5268 -1.2168 -0.8118 0.0434 ...mygenesoldf1 <- as.data.frame(mygenesol1,row.names = 1:nrow(as.data.frame(ranges(mygenesol1))))
head(mygenesoldf1)## seqnames start end width strand gene_id gene_biotype
## 1 KK215283.1 21 50200 50180 - ENSPREG00000017956 protein_coding
## 2 KK215283.1 21 50200 50180 - ENSPREG00000017956 protein_coding
## 3 KK215283.1 21 50200 50180 - ENSPREG00000017956 protein_coding
## 4 KK215283.1 21 50200 50180 - ENSPREG00000017956 protein_coding
## 5 KK215283.1 21 50200 50180 - ENSPREG00000017956 protein_coding
## 6 KK215283.1 21 50200 50180 - ENSPREG00000017956 protein_coding
## gene_name
## 1 usp6nl
## 2 usp6nl
## 3 usp6nl
## 4 usp6nl
## 5 usp6nl
## 6 usp6nlGvLgenesdf <- cbind(GvLgenesdf,mygenesoldf1[c("gene_id","gene_biotype","gene_name")])
GvLgenesdf$seqnames <- as.character(GvLgenesdf$seqnames)
head(GvLgenesdf)## seqnames start end width strand pvalue qvalue meth.diff
## 1 KK215283.1 1001 2000 1000 * 0.007595492 0.06501423 -4.36224753
## 2 KK215283.1 2001 3000 1000 * 0.230177435 0.43791612 3.52680331
## 3 KK215283.1 3001 4000 1000 * 0.377461001 0.55511254 -1.21680284
## 4 KK215283.1 4001 5000 1000 * 0.596779809 0.68068755 -0.81179079
## 5 KK215283.1 5001 6000 1000 * 0.945588842 0.81574958 0.04344040
## 6 KK215283.1 6001 7000 1000 * 0.942312199 0.81472483 0.04951088
## gene_id gene_biotype gene_name
## 1 ENSPREG00000017956 protein_coding usp6nl
## 2 ENSPREG00000017956 protein_coding usp6nl
## 3 ENSPREG00000017956 protein_coding usp6nl
## 4 ENSPREG00000017956 protein_coding usp6nl
## 5 ENSPREG00000017956 protein_coding usp6nl
## 6 ENSPREG00000017956 protein_coding usp6nlGvLgeneschrdf <- GvLgenesdf[grep("LG",GvLgenesdf$seqnames),]
head(GvLgeneschrdf)## seqnames start end width strand pvalue qvalue meth.diff
## 10182 LG1 370001 371000 1000 * 0.063382034 0.22393253 -4.2515205
## 10183 LG1 371001 372000 1000 * 0.074650463 0.24475605 4.1890014
## 10184 LG1 373001 374000 1000 * 0.446985660 0.60009081 -1.7343257
## 10185 LG1 374001 375000 1000 * 0.616494391 0.69026495 1.0179284
## 10186 LG1 375001 376000 1000 * 0.861829816 0.78866545 -0.2601156
## 10187 LG1 376001 377000 1000 * 0.004385174 0.04632726 4.5062639
## gene_id gene_biotype gene_name
## 10182 ENSPREG00000000039 protein_coding <NA>
## 10183 ENSPREG00000000039 protein_coding <NA>
## 10184 ENSPREG00000000039 protein_coding <NA>
## 10185 ENSPREG00000000039 protein_coding <NA>
## 10186 ENSPREG00000000039 protein_coding <NA>
## 10187 ENSPREG00000000039 protein_coding <NA>GvLgeneschrdf <- GvLgeneschrdf[order(GvLgeneschrdf[,7]), ]
head(GvLgeneschrdf,10)## seqnames start end width strand pvalue qvalue
## 116121 LG16 509001 510000 1000 * 1.433189e-54 1.872407e-49
## 77967 LG13 18161001 18162000 1000 * 1.900156e-51 1.985985e-46
## 207930 LG21 538001 539000 1000 * 5.180641e-40 4.512205e-35
## 207931 LG21 538001 539000 1000 * 5.180641e-40 4.512205e-35
## 160079 LG18 21720001 21721000 1000 * 2.190222e-39 1.635109e-34
## 160080 LG18 21720001 21721000 1000 * 2.190222e-39 1.635109e-34
## 88277 LG14 4148001 4149000 1000 * 2.644311e-35 1.727345e-30
## 88278 LG14 4148001 4149000 1000 * 2.644311e-35 1.727345e-30
## 135448 LG17 3558001 3559000 1000 * 8.543377e-35 4.960707e-30
## 19131 LG1 17897001 17898000 1000 * 2.744822e-33 1.434401e-28
## meth.diff gene_id gene_biotype gene_name
## 116121 -17.403727 ENSPREG00000014798 protein_coding <NA>
## 77967 -17.695603 ENSPREG00000001265 protein_coding <NA>
## 207930 -12.608880 ENSPREG00000012615 protein_coding crnkl1
## 207931 -12.608880 ENSPREG00000012722 protein_coding <NA>
## 160079 14.869760 ENSPREG00000014753 protein_coding aimp1b
## 160080 14.869760 ENSPREG00000014824 protein_coding <NA>
## 88277 -17.151052 ENSPREG00000009387 protein_coding <NA>
## 88278 -17.151052 ENSPREG00000009393 protein_coding zgc:112437
## 135448 19.287516 ENSPREG00000002699 protein_coding <NA>
## 19131 4.758557 ENSPREG00000004582 protein_coding <NA>nrow(subset(GvLgeneschrdf,qvalue<0.05))## [1] 30442nrow(subset(GvLgeneschrdf,qvalue<0.05&meth.diff>0))## [1] 18666nrow(subset(GvLgeneschrdf,qvalue<0.05&meth.diff<0))## [1] 11776rm(GvLgenes)
rm(GvLgenesdf)Methyl kit CpG results annotated to CpG islands
ol1 <- findOverlaps(methylkitCvGGR,my_CpGislands)## Warning in .Seqinfo.mergexy(x, y): Each of the 2 combined objects has sequence levels not in the other:
## - in 'x': KK215310.1, KK215354.1, KK215361.1, KK215370.1, KK215371.1, KK215372.1, KK215373.1, KK215378.1, KK215379.1, KK215380.1, KK215381.1, KK215382.1, KK215388.1, KK215392.1, KK215393.1, KK215396.1, KK215402.1, KK215403.1, KK215404.1, KK215405.1, KK215406.1, KK215412.1, KK215414.1, KK215417.1, KK215420.1, KK215421.1, KK215422.1, KK215423.1, KK215429.1, KK215430.1, KK215433.1, KK215435.1, KK215437.1, KK215438.1, KK215440.1, KK215442.1, KK215454.1, KK215456.1, KK215458.1, KK215461.1, KK215462.1, KK215463.1, KK215465.1, KK215466.1, KK215467.1, KK215468.1, KK215472.1, KK215474.1, KK215480.1, KK215482.1, KK215483.1, KK215484.1, KK215485.1, KK215486.1, KK215487.1, KK215489.1, KK215493.1, KK215494.1, KK215497.1, KK215498.1, KK215501.1, KK215503.1, KK215504.1, KK215506.1, KK215508.1, KK215512.1, KK215515.1, KK215519.1, KK215521.1, KK215522.1, KK215523.1, KK215524.1, KK215525.1, KK215526.1, KK215528.1, KK215531.1, KK215533.1, KK215534.1, KK215536.1, KK215538.1, KK215541.1, KK215544.1, KK215545.1, KK215546.1, KK215547.1, KK215548.1, KK215549.1, KK215551.1, KK215554.1, KK215556.1, KK215557.1, KK215559.1, KK215560.1, KK215562.1, KK215564.1, KK215565.1, KK215570.1, KK215572.1, KK215573.1, KK215574.1, KK215577.1, KK215579.1, KK215580.1, KK215582.1, KK215584.1, KK215585.1, KK215591.1, KK215592.1, KK215593.1, KK215595.1, KK215598.1, KK215609.1, KK215612.1, KK215613.1, KK215614.1, KK215615.1, KK215620.1, KK215621.1, KK215623.1, KK215625.1, KK215626.1, KK215634.1, KK215635.1, KK215636.1, KK215637.1, KK215638.1, KK215642.1, KK215643.1, KK215644.1, KK215645.1, KK215647.1, KK215649.1, KK215651.1, KK215652.1, KK215654.1, KK215656.1, KK215657.1, KK215661.1, KK215662.1, KK215663.1, KK215665.1, KK215666.1, KK215668.1, KK215671.1, KK215673.1, KK215675.1, KK215677.1, KK215681.1, KK215684.1, KK215687.1, KK215688.1, KK215689.1, KK215691.1, KK215692.1, KK215694.1, KK215695.1, KK215697.1, KK215698.1, KK215702.1, KK215703.1, KK215705.1, KK215707.1, KK215708.1, KK215710.1, KK215712.1, KK215715.1, KK215717.1, KK215720.1, KK215721.1, KK215723.1, KK215724.1, KK215727.1, KK215728.1, KK215730.1, KK215731.1, KK215732.1, KK215734.1, KK215735.1, KK215736.1, KK215738.1, KK215741.1, KK215742.1, KK215743.1, KK215748.1, KK215756.1, KK215757.1, KK215758.1, KK215760.1, KK215761.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215766.1, KK215767.1, KK215770.1, KK215772.1, KK215774.1, KK215775.1, KK215776.1, KK215777.1, KK215779.1, KK215780.1, KK215784.1, KK215785.1, KK215786.1, KK215787.1, KK215789.1, KK215790.1, KK215794.1, KK215795.1, KK215796.1, KK215798.1, KK215800.1, KK215802.1, KK215803.1, KK215804.1, KK215805.1, KK215808.1, KK215809.1, KK215810.1, KK215813.1, KK215814.1, KK215815.1, KK215816.1, KK215818.1, KK215819.1, KK215824.1, KK215825.1, KK215826.1, KK215827.1, KK215828.1, KK215829.1, KK215834.1, KK215838.1, KK215839.1, KK215840.1, KK215842.1, KK215843.1, KK215844.1, KK215846.1, KK215847.1, KK215849.1, KK215851.1, KK215852.1, KK215854.1, KK215855.1, KK215856.1, KK215857.1, KK215858.1, KK215859.1, KK215860.1, KK215861.1, KK215863.1, KK215864.1, KK215865.1, KK215866.1, KK215867.1, KK215869.1, KK215870.1, KK215871.1, KK215873.1, KK215874.1, KK215875.1, KK215878.1, KK215879.1, KK215880.1, KK215881.1, KK215884.1, KK215885.1, KK215886.1, KK215887.1, KK215888.1, KK215890.1, KK215891.1, KK215892.1, KK215893.1, KK215895.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215902.1, KK215903.1, KK215905.1, KK215906.1, KK215908.1, KK215909.1, KK215911.1, KK215914.1, KK215915.1, KK215916.1, KK215918.1, KK215919.1, KK215920.1, KK215921.1, KK215923.1, KK215924.1, KK215927.1, KK215928.1, KK215933.1, KK215934.1, KK215936.1, KK215940.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215947.1, KK215949.1, KK215950.1, KK215951.1, KK215952.1, KK215953.1, KK215956.1, KK215957.1, KK215958.1, KK215960.1, KK215961.1, KK215966.1, KK215968.1, KK215969.1, KK215970.1, KK215971.1, KK215972.1, KK215973.1, KK215975.1, KK215976.1, KK215978.1, KK215979.1, KK215981.1, KK215982.1, KK215983.1, KK215984.1, KK215985.1, KK215987.1, KK215993.1, KK215994.1, KK215997.1, KK216000.1, KK216001.1, KK216005.1, KK216006.1, KK216009.1, KK216011.1, KK216012.1, KK216014.1, KK216015.1, KK216016.1, KK216017.1, KK216018.1, KK216022.1, KK216024.1, KK216025.1, KK216026.1, KK216028.1, KK216029.1, KK216030.1, KK216032.1, KK216033.1, KK216034.1, KK216035.1, KK216037.1, KK216039.1, KK216040.1, KK216041.1, KK216042.1, KK216043.1, KK216044.1, KK216048.1, KK216049.1, KK216050.1, KK216051.1, KK216053.1, KK216055.1, KK216056.1, KK216059.1, KK216062.1, KK216063.1, KK216064.1, KK216065.1, KK216066.1, KK216068.1, KK216069.1, KK216072.1, KK216075.1, KK216076.1, KK216077.1, KK216078.1, KK216079.1, KK216080.1, KK216081.1, KK216082.1, KK216083.1, KK216084.1, KK216085.1, KK216086.1, KK216087.1, KK216089.1, KK216091.1, KK216092.1, KK216093.1, KK216097.1, KK216098.1, KK216100.1, KK216101.1, KK216106.1, KK216107.1, KK216108.1, KK216110.1, KK216112.1, KK216114.1, KK216116.1, KK216120.1, KK216121.1, KK216122.1, KK216124.1, KK216125.1, KK216126.1, KK216127.1, KK216128.1, KK216130.1, KK216131.1, KK216133.1, KK216134.1, KK216135.1, KK216136.1, KK216138.1, KK216140.1, KK216141.1, KK216142.1, KK216143.1, KK216144.1, KK216146.1, KK216147.1, KK216148.1, KK216151.1, KK216152.1, KK216154.1, KK216155.1, KK216157.1, KK216158.1, KK216159.1, KK216160.1, KK216161.1, KK216163.1, KK216164.1, KK216165.1, KK216166.1, KK216168.1, KK216169.1, KK216171.1, KK216174.1, KK216176.1, KK216178.1, KK216179.1, KK216181.1, KK216182.1, KK216184.1, KK216186.1, KK216190.1, KK216193.1, KK216194.1, KK216195.1, KK216196.1, KK216197.1, KK216198.1, KK216200.1, KK216201.1, KK216202.1, KK216205.1, KK216206.1, KK216207.1, KK216208.1, KK216210.1, KK216212.1, KK216214.1, KK216215.1, KK216218.1, KK216221.1, KK216222.1, KK216224.1, KK216225.1, KK216226.1, KK216227.1, KK216228.1, KK216230.1, KK216231.1, KK216232.1, KK216234.1, KK216237.1, KK216238.1, KK216240.1, KK216241.1, KK216242.1, KK216243.1, KK216244.1, KK216245.1, KK216248.1, KK216251.1, KK216252.1, KK216253.1, KK216254.1, KK216256.1, KK216258.1, KK216259.1, KK216260.1, KK216261.1, KK216262.1, KK216263.1, KK216264.1, KK216266.1, KK216267.1, KK216268.1, KK216269.1, KK216270.1, KK216271.1, KK216274.1, KK216276.1, KK216277.1, KK216278.1, KK216280.1, KK216281.1, KK216284.1, KK216287.1, KK216288.1, KK216289.1, KK216290.1, KK216291.1, KK216292.1, KK216294.1, KK216295.1, KK216296.1, KK216297.1, KK216298.1, KK216302.1, KK216304.1, KK216306.1, KK216307.1, KK216310.1, KK216311.1, KK216312.1, KK216313.1, KK216315.1, KK216317.1, KK216318.1, KK216319.1, KK216320.1, KK216321.1, KK216322.1, KK216324.1, KK216325.1, KK216327.1, KK216328.1, KK216329.1, KK216330.1, KK216332.1, KK216333.1, KK216335.1, KK216336.1, KK216337.1, KK216338.1, KK216340.1, KK216341.1, KK216342.1, KK216344.1, KK216345.1, KK216346.1, KK216347.1, KK216349.1, KK216351.1, KK216352.1, KK216354.1, KK216355.1, KK216356.1, KK216359.1, KK216360.1, KK216361.1, KK216362.1, KK216363.1, KK216366.1, KK216369.1, KK216370.1, KK216371.1, KK216372.1, KK216374.1, KK216375.1, KK216376.1, KK216377.1, KK216378.1, KK216379.1, KK216380.1, KK216381.1, KK216383.1, KK216384.1, KK216385.1, KK216387.1, KK216388.1, KK216389.1, KK216390.1, KK216391.1, KK216393.1, KK216394.1, KK216396.1, KK216397.1, KK216400.1, KK216402.1, KK216403.1, KK216404.1, KK216405.1, KK216406.1, KK216407.1, KK216408.1, KK216410.1, KK216412.1, KK216413.1, KK216414.1, KK216416.1, KK216417.1, KK216418.1, KK216419.1, KK216420.1, KK216421.1, KK216422.1, KK216423.1, KK216424.1, KK216425.1, KK216426.1, KK216427.1, KK216428.1, KK216429.1, KK216430.1, KK216431.1, KK216432.1, KK216433.1, KK216434.1, KK216437.1, KK216438.1, KK216439.1, KK216440.1, KK216441.1, KK216442.1, KK216443.1, KK216444.1, KK216445.1, KK216446.1, KK216451.1, KK216452.1, KK216453.1, KK216454.1, KK216455.1, KK216456.1, KK216457.1, KK216458.1, KK216459.1, KK216461.1, KK216462.1, KK216463.1, KK216464.1, KK216465.1, KK216466.1, KK216467.1, KK216468.1, KK216469.1, KK216471.1, KK216474.1, KK216476.1, KK216477.1, KK216479.1, KK216482.1, KK216483.1, KK216486.1, KK216488.1, KK216489.1, KK216491.1, KK216492.ol1## Hits object with 2111405 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 131 56232
## [2] 132 56232
## [3] 133 56232
## [4] 134 56232
## [5] 135 56232
## ... ... ...
## [2111401] 18867689 23734
## [2111402] 18867690 23734
## [2111403] 18867691 23734
## [2111404] 18867692 23734
## [2111405] 18867693 23734
## -------
## queryLength: 18874229 / subjectLength: 60897CvGCpGislands <- methylkitCvGGR[queryHits(ol1)]
my_CpGislandsol1 <- my_CpGislands[subjectHits(ol1)]
head(CvGCpGislands)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | pvalue qvalue meth.diff
## <Rle> <IRanges> <Rle> | <numeric> <numeric> <numeric>
## [1] KK215283.1 5846 + | 0.300265 0.905349 -7.575758
## [2] KK215283.1 5847 + | 0.858625 0.989133 -1.851852
## [3] KK215283.1 5876 + | 0.454743 0.953638 -3.297297
## [4] KK215283.1 5877 + | 0.903155 0.989133 0.717703
## [5] KK215283.1 5882 + | 0.726841 0.989133 -1.378930
## [6] KK215283.1 5883 + | 0.155296 0.858617 -6.818182
## -------
## seqinfo: 2455 sequences from an unspecified genome; no seqlengthsmy_CpGislandsol1## GRanges object with 2111405 ranges and 2 metadata columns:
## seqnames ranges strand | source ID
## <Rle> <IRanges> <Rle> | <factor> <character>
## [1] KK215283.1 5832-6408 + | cpgplot KK215283.1.1
## [2] KK215283.1 5832-6408 + | cpgplot KK215283.1.1
## [3] KK215283.1 5832-6408 + | cpgplot KK215283.1.1
## [4] KK215283.1 5832-6408 + | cpgplot KK215283.1.1
## [5] KK215283.1 5832-6408 + | cpgplot KK215283.1.1
## ... ... ... ... . ... ...
## [2111401] LG9 34115391-34115990 + | cpgplot LG9.2412
## [2111402] LG9 34115391-34115990 + | cpgplot LG9.2412
## [2111403] LG9 34115391-34115990 + | cpgplot LG9.2412
## [2111404] LG9 34115391-34115990 + | cpgplot LG9.2412
## [2111405] LG9 34115391-34115990 + | cpgplot LG9.2412
## -------
## seqinfo: 646 sequences from an unspecified genome; no seqlengthsCvGCpGislandsdf <- as.data.frame(CvGCpGislands,row.names = 1:nrow(as.data.frame(ranges(CvGCpGislands))))
str(CvGCpGislandsdf)## 'data.frame': 2111405 obs. of 8 variables:
## $ seqnames : Factor w/ 2455 levels "KK215283.1","KK215284.1",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ start : int 5846 5847 5876 5877 5882 5883 5886 5901 5902 5904 ...
## $ end : int 5846 5847 5876 5877 5882 5883 5886 5901 5902 5904 ...
## $ width : int 1 1 1 1 1 1 1 1 1 1 ...
## $ strand : Factor w/ 3 levels "+","-","*": 1 1 1 1 1 1 1 1 1 1 ...
## $ pvalue : num 0.3 0.859 0.455 0.903 0.727 ...
## $ qvalue : num 0.905 0.989 0.954 0.989 0.989 ...
## $ meth.diff: num -7.576 -1.852 -3.297 0.718 -1.379 ...my_CpGislandsol1 <- as.data.frame(my_CpGislandsol1,row.names = 1:nrow(as.data.frame(ranges(my_CpGislandsol1))))
head(my_CpGislandsol1)## seqnames start end width strand source ID
## 1 KK215283.1 5832 6408 577 + cpgplot KK215283.1.1
## 2 KK215283.1 5832 6408 577 + cpgplot KK215283.1.1
## 3 KK215283.1 5832 6408 577 + cpgplot KK215283.1.1
## 4 KK215283.1 5832 6408 577 + cpgplot KK215283.1.1
## 5 KK215283.1 5832 6408 577 + cpgplot KK215283.1.1
## 6 KK215283.1 5832 6408 577 + cpgplot KK215283.1.1CvGCpGislandsdf <- cbind(CvGCpGislandsdf,my_CpGislandsol1[c("source","ID")])
CvGCpGislandsdf$seqnames <- as.character(CvGCpGislandsdf$seqnames)
head(CvGCpGislandsdf)## seqnames start end width strand pvalue qvalue meth.diff source
## 1 KK215283.1 5846 5846 1 + 0.3002655 0.9053487 -7.5757576 cpgplot
## 2 KK215283.1 5847 5847 1 + 0.8586247 0.9891325 -1.8518519 cpgplot
## 3 KK215283.1 5876 5876 1 + 0.4547431 0.9536377 -3.2972973 cpgplot
## 4 KK215283.1 5877 5877 1 + 0.9031549 0.9891325 0.7177033 cpgplot
## 5 KK215283.1 5882 5882 1 + 0.7268405 0.9891325 -1.3789300 cpgplot
## 6 KK215283.1 5883 5883 1 + 0.1552960 0.8586169 -6.8181818 cpgplot
## ID
## 1 KK215283.1.1
## 2 KK215283.1.1
## 3 KK215283.1.1
## 4 KK215283.1.1
## 5 KK215283.1.1
## 6 KK215283.1.1CvGCpGislandschrdf <- CvGCpGislandsdf[grep("LG",CvGCpGislandsdf$seqnames),]
head(CvGCpGislandschrdf)## seqnames start end width strand pvalue qvalue meth.diff source
## 171636 LG1 6736 6736 1 + 0.3204352 0.9091110 -7.5431034 cpgplot
## 171637 LG1 6757 6757 1 + 0.9242475 0.9891325 -0.8658009 cpgplot
## 171638 LG1 6758 6758 1 + 0.2152146 0.8777053 -4.1666667 cpgplot
## 171639 LG1 6776 6776 1 + 0.3408059 0.9141787 -6.2962963 cpgplot
## 171640 LG1 6777 6777 1 + 0.3344027 0.9121060 -2.1739130 cpgplot
## 171641 LG1 6783 6783 1 + 0.4444853 0.9506901 -7.9365079 cpgplot
## ID
## 171636 LG1.1
## 171637 LG1.1
## 171638 LG1.1
## 171639 LG1.1
## 171640 LG1.1
## 171641 LG1.1CvGCpGislandschrdf <- CvGCpGislandschrdf[order(CvGCpGislandschrdf[,7]), ]
head(CvGCpGislandschrdf,10)## seqnames start end width strand pvalue qvalue
## 1935938 LG8 3016 3016 1 + 9.847154e-07 0.3315359
## 501251 LG12 22154748 22154748 1 + 2.338922e-06 0.5223176
## 2011669 LG8 24787634 24787634 1 + 2.348873e-06 0.5223176
## 506563 LG12 23380866 23380866 1 + 5.046249e-06 0.5888062
## 706700 LG15 12159253 12159253 1 + 4.200336e-06 0.5888062
## 1033764 LG19 3514677 3514677 1 + 4.373365e-06 0.5888062
## 1260276 LG20 4938545 4938545 1 + 5.009500e-06 0.5888062
## 1351977 LG21 3097219 3097219 1 + 4.113820e-06 0.5888062
## 1460659 LG22 19739496 19739496 1 + 3.509237e-06 0.5888062
## 1990828 LG8 18816750 18816750 1 + 5.023631e-06 0.5888062
## meth.diff source ID
## 1935938 33.85339 cpgplot LG8.3
## 501251 -40.54054 cpgplot LG12.1622
## 2011669 42.79337 cpgplot LG8.2148
## 506563 57.63547 cpgplot LG12.1762
## 706700 33.33333 cpgplot LG15.789
## 1033764 35.29412 cpgplot LG19.885
## 1260276 10.35520 cpgplot LG20.473
## 1351977 62.20238 cpgplot LG21.699
## 1460659 -50.59259 cpgplot LG22.1569
## 1990828 -28.98551 cpgplot LG8.1557rm(CvGCpGislands)
rm(CvGCpGislandsdf)ol1 <- findOverlaps(methylkitCvLGR,my_CpGislands)## Warning in .Seqinfo.mergexy(x, y): Each of the 2 combined objects has sequence levels not in the other:
## - in 'x': KK215310.1, KK215354.1, KK215361.1, KK215370.1, KK215371.1, KK215372.1, KK215373.1, KK215378.1, KK215379.1, KK215380.1, KK215381.1, KK215382.1, KK215388.1, KK215392.1, KK215393.1, KK215396.1, KK215402.1, KK215403.1, KK215404.1, KK215405.1, KK215406.1, KK215412.1, KK215414.1, KK215417.1, KK215420.1, KK215421.1, KK215422.1, KK215423.1, KK215429.1, KK215430.1, KK215433.1, KK215435.1, KK215437.1, KK215438.1, KK215440.1, KK215442.1, KK215454.1, KK215456.1, KK215458.1, KK215461.1, KK215462.1, KK215463.1, KK215465.1, KK215466.1, KK215467.1, KK215468.1, KK215472.1, KK215474.1, KK215480.1, KK215482.1, KK215483.1, KK215484.1, KK215485.1, KK215486.1, KK215487.1, KK215489.1, KK215493.1, KK215494.1, KK215497.1, KK215498.1, KK215501.1, KK215503.1, KK215504.1, KK215506.1, KK215508.1, KK215512.1, KK215515.1, KK215519.1, KK215521.1, KK215522.1, KK215523.1, KK215524.1, KK215525.1, KK215526.1, KK215528.1, KK215531.1, KK215533.1, KK215534.1, KK215536.1, KK215538.1, KK215541.1, KK215544.1, KK215545.1, KK215546.1, KK215547.1, KK215548.1, KK215549.1, KK215551.1, KK215554.1, KK215556.1, KK215557.1, KK215559.1, KK215560.1, KK215562.1, KK215564.1, KK215565.1, KK215570.1, KK215572.1, KK215573.1, KK215574.1, KK215577.1, KK215579.1, KK215580.1, KK215582.1, KK215584.1, KK215585.1, KK215591.1, KK215592.1, KK215593.1, KK215595.1, KK215598.1, KK215609.1, KK215612.1, KK215613.1, KK215614.1, KK215615.1, KK215620.1, KK215621.1, KK215623.1, KK215625.1, KK215626.1, KK215634.1, KK215635.1, KK215636.1, KK215637.1, KK215638.1, KK215642.1, KK215643.1, KK215644.1, KK215645.1, KK215647.1, KK215649.1, KK215651.1, KK215652.1, KK215654.1, KK215656.1, KK215657.1, KK215661.1, KK215662.1, KK215663.1, KK215665.1, KK215666.1, KK215668.1, KK215671.1, KK215673.1, KK215675.1, KK215677.1, KK215681.1, KK215684.1, KK215687.1, KK215688.1, KK215689.1, KK215691.1, KK215692.1, KK215694.1, KK215695.1, KK215697.1, KK215698.1, KK215703.1, KK215705.1, KK215707.1, KK215708.1, KK215710.1, KK215712.1, KK215715.1, KK215717.1, KK215720.1, KK215721.1, KK215723.1, KK215724.1, KK215727.1, KK215728.1, KK215730.1, KK215731.1, KK215732.1, KK215734.1, KK215735.1, KK215736.1, KK215738.1, KK215741.1, KK215742.1, KK215743.1, KK215748.1, KK215756.1, KK215757.1, KK215758.1, KK215760.1, KK215761.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215766.1, KK215767.1, KK215770.1, KK215772.1, KK215774.1, KK215775.1, KK215776.1, KK215777.1, KK215779.1, KK215780.1, KK215784.1, KK215785.1, KK215786.1, KK215787.1, KK215789.1, KK215790.1, KK215794.1, KK215795.1, KK215796.1, KK215798.1, KK215800.1, KK215802.1, KK215803.1, KK215804.1, KK215805.1, KK215808.1, KK215809.1, KK215810.1, KK215813.1, KK215814.1, KK215815.1, KK215816.1, KK215818.1, KK215819.1, KK215824.1, KK215825.1, KK215826.1, KK215827.1, KK215828.1, KK215829.1, KK215834.1, KK215838.1, KK215839.1, KK215840.1, KK215842.1, KK215843.1, KK215844.1, KK215846.1, KK215847.1, KK215849.1, KK215851.1, KK215852.1, KK215854.1, KK215855.1, KK215856.1, KK215857.1, KK215858.1, KK215859.1, KK215860.1, KK215861.1, KK215863.1, KK215864.1, KK215865.1, KK215866.1, KK215867.1, KK215869.1, KK215870.1, KK215871.1, KK215873.1, KK215875.1, KK215878.1, KK215879.1, KK215880.1, KK215881.1, KK215884.1, KK215885.1, KK215886.1, KK215887.1, KK215888.1, KK215890.1, KK215891.1, KK215892.1, KK215893.1, KK215895.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215902.1, KK215903.1, KK215905.1, KK215906.1, KK215908.1, KK215909.1, KK215911.1, KK215914.1, KK215915.1, KK215916.1, KK215918.1, KK215919.1, KK215920.1, KK215921.1, KK215923.1, KK215924.1, KK215927.1, KK215928.1, KK215930.1, KK215933.1, KK215934.1, KK215936.1, KK215940.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215947.1, KK215949.1, KK215950.1, KK215951.1, KK215952.1, KK215953.1, KK215956.1, KK215957.1, KK215958.1, KK215960.1, KK215961.1, KK215968.1, KK215969.1, KK215970.1, KK215971.1, KK215972.1, KK215973.1, KK215975.1, KK215976.1, KK215978.1, KK215979.1, KK215981.1, KK215982.1, KK215983.1, KK215984.1, KK215985.1, KK215987.1, KK215993.1, KK215994.1, KK215997.1, KK216000.1, KK216001.1, KK216005.1, KK216006.1, KK216009.1, KK216011.1, KK216012.1, KK216014.1, KK216015.1, KK216016.1, KK216017.1, KK216018.1, KK216022.1, KK216024.1, KK216025.1, KK216026.1, KK216028.1, KK216029.1, KK216030.1, KK216032.1, KK216033.1, KK216034.1, KK216035.1, KK216037.1, KK216039.1, KK216040.1, KK216041.1, KK216042.1, KK216043.1, KK216044.1, KK216048.1, KK216049.1, KK216050.1, KK216051.1, KK216053.1, KK216055.1, KK216056.1, KK216059.1, KK216062.1, KK216063.1, KK216064.1, KK216065.1, KK216066.1, KK216068.1, KK216069.1, KK216072.1, KK216073.1, KK216075.1, KK216076.1, KK216077.1, KK216078.1, KK216079.1, KK216080.1, KK216081.1, KK216082.1, KK216083.1, KK216084.1, KK216085.1, KK216086.1, KK216087.1, KK216089.1, KK216091.1, KK216092.1, KK216093.1, KK216097.1, KK216098.1, KK216100.1, KK216101.1, KK216106.1, KK216107.1, KK216108.1, KK216110.1, KK216112.1, KK216114.1, KK216116.1, KK216120.1, KK216121.1, KK216122.1, KK216124.1, KK216125.1, KK216126.1, KK216127.1, KK216128.1, KK216130.1, KK216131.1, KK216133.1, KK216134.1, KK216135.1, KK216136.1, KK216138.1, KK216140.1, KK216141.1, KK216142.1, KK216143.1, KK216144.1, KK216146.1, KK216147.1, KK216148.1, KK216151.1, KK216152.1, KK216154.1, KK216155.1, KK216157.1, KK216158.1, KK216159.1, KK216160.1, KK216161.1, KK216163.1, KK216164.1, KK216165.1, KK216166.1, KK216168.1, KK216169.1, KK216171.1, KK216174.1, KK216176.1, KK216178.1, KK216179.1, KK216181.1, KK216182.1, KK216184.1, KK216186.1, KK216190.1, KK216193.1, KK216194.1, KK216195.1, KK216196.1, KK216197.1, KK216198.1, KK216200.1, KK216201.1, KK216202.1, KK216205.1, KK216206.1, KK216207.1, KK216208.1, KK216210.1, KK216212.1, KK216214.1, KK216215.1, KK216218.1, KK216221.1, KK216222.1, KK216224.1, KK216225.1, KK216226.1, KK216227.1, KK216228.1, KK216230.1, KK216231.1, KK216232.1, KK216234.1, KK216237.1, KK216238.1, KK216240.1, KK216241.1, KK216242.1, KK216243.1, KK216244.1, KK216245.1, KK216248.1, KK216251.1, KK216252.1, KK216253.1, KK216254.1, KK216256.1, KK216258.1, KK216259.1, KK216260.1, KK216261.1, KK216262.1, KK216263.1, KK216264.1, KK216266.1, KK216267.1, KK216268.1, KK216269.1, KK216270.1, KK216271.1, KK216274.1, KK216276.1, KK216277.1, KK216278.1, KK216280.1, KK216281.1, KK216284.1, KK216287.1, KK216288.1, KK216289.1, KK216290.1, KK216291.1, KK216292.1, KK216294.1, KK216295.1, KK216296.1, KK216297.1, KK216298.1, KK216302.1, KK216304.1, KK216306.1, KK216307.1, KK216310.1, KK216311.1, KK216312.1, KK216313.1, KK216315.1, KK216317.1, KK216318.1, KK216319.1, KK216320.1, KK216321.1, KK216322.1, KK216324.1, KK216325.1, KK216327.1, KK216328.1, KK216329.1, KK216330.1, KK216332.1, KK216333.1, KK216335.1, KK216336.1, KK216337.1, KK216338.1, KK216340.1, KK216341.1, KK216342.1, KK216344.1, KK216345.1, KK216346.1, KK216347.1, KK216349.1, KK216351.1, KK216352.1, KK216354.1, KK216355.1, KK216356.1, KK216359.1, KK216360.1, KK216361.1, KK216362.1, KK216363.1, KK216366.1, KK216369.1, KK216370.1, KK216371.1, KK216372.1, KK216374.1, KK216375.1, KK216376.1, KK216377.1, KK216378.1, KK216379.1, KK216380.1, KK216381.1, KK216383.1, KK216384.1, KK216385.1, KK216387.1, KK216388.1, KK216389.1, KK216390.1, KK216391.1, KK216393.1, KK216394.1, KK216396.1, KK216397.1, KK216400.1, KK216402.1, KK216403.1, KK216404.1, KK216405.1, KK216406.1, KK216407.1, KK216408.1, KK216410.1, KK216412.1, KK216413.1, KK216414.1, KK216416.1, KK216417.1, KK216418.1, KK216419.1, KK216420.1, KK216421.1, KK216422.1, KK216423.1, KK216424.1, KK216425.1, KK216426.1, KK216427.1, KK216428.1, KK216429.1, KK216430.1, KK216431.1, KK216432.1, KK216433.1, KK216434.1, KK216437.1, KK216438.1, KK216439.1, KK216440.1, KK216441.1, KK216442.1, KK216443.1, KK216444.1, KK216445.1, KK216446.1, KK216451.1, KK216452.1, KK216453.1, KK216454.1, KK216455.1, KK216456.1, KK216457.1, KK216458.1, KK216459.1, KK216461.1, KK216462.1, KK216463.1, KK216464.1, KK216465.1, KK216466.1, KK216467.1, KK216468.1, KK216469.1, KK216471.1, KK216474.1, KK216476.1, KK216477.1, KK216479.1, KK216482.1, KK216483.1, KK216486.1, KK216488.1, KK216489.1, KK216491.1, KK216492.1, KK216493.ol1## Hits object with 2073792 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 130 56232
## [2] 131 56232
## [3] 132 56232
## [4] 133 56232
## [5] 134 56232
## ... ... ...
## [2073788] 18471419 23734
## [2073789] 18471420 23734
## [2073790] 18471421 23734
## [2073791] 18471422 23734
## [2073792] 18471423 23734
## -------
## queryLength: 18477943 / subjectLength: 60897CvLCpGislands <- methylkitCvLGR[queryHits(ol1)]
my_CpGislandsol1 <- my_CpGislands[subjectHits(ol1)]
head(CvLCpGislands)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | pvalue qvalue meth.diff
## <Rle> <IRanges> <Rle> | <numeric> <numeric> <numeric>
## [1] KK215283.1 5846 + | 0.503837 0.968265 3.68217
## [2] KK215283.1 5847 + | 0.360989 0.910326 8.97436
## [3] KK215283.1 5876 + | 0.613846 0.986634 -2.17535
## [4] KK215283.1 5877 + | 0.724999 0.986634 2.03735
## [5] KK215283.1 5882 + | 0.344035 0.902707 -4.61437
## [6] KK215283.1 5883 + | 0.180168 0.872551 -6.45161
## -------
## seqinfo: 2441 sequences from an unspecified genome; no seqlengthsmy_CpGislandsol1## GRanges object with 2073792 ranges and 2 metadata columns:
## seqnames ranges strand | source ID
## <Rle> <IRanges> <Rle> | <factor> <character>
## [1] KK215283.1 5832-6408 + | cpgplot KK215283.1.1
## [2] KK215283.1 5832-6408 + | cpgplot KK215283.1.1
## [3] KK215283.1 5832-6408 + | cpgplot KK215283.1.1
## [4] KK215283.1 5832-6408 + | cpgplot KK215283.1.1
## [5] KK215283.1 5832-6408 + | cpgplot KK215283.1.1
## ... ... ... ... . ... ...
## [2073788] LG9 34115391-34115990 + | cpgplot LG9.2412
## [2073789] LG9 34115391-34115990 + | cpgplot LG9.2412
## [2073790] LG9 34115391-34115990 + | cpgplot LG9.2412
## [2073791] LG9 34115391-34115990 + | cpgplot LG9.2412
## [2073792] LG9 34115391-34115990 + | cpgplot LG9.2412
## -------
## seqinfo: 646 sequences from an unspecified genome; no seqlengthsCvLCpGislandsdf <- as.data.frame(CvLCpGislands,row.names = 1:nrow(as.data.frame(ranges(CvLCpGislands))))
str(CvLCpGislandsdf)## 'data.frame': 2073792 obs. of 8 variables:
## $ seqnames : Factor w/ 2441 levels "KK215283.1","KK215284.1",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ start : int 5846 5847 5876 5877 5882 5883 5886 5901 5902 5904 ...
## $ end : int 5846 5847 5876 5877 5882 5883 5886 5901 5902 5904 ...
## $ width : int 1 1 1 1 1 1 1 1 1 1 ...
## $ strand : Factor w/ 3 levels "+","-","*": 1 1 1 1 1 1 1 1 1 1 ...
## $ pvalue : num 0.504 0.361 0.614 0.725 0.344 ...
## $ qvalue : num 0.968 0.91 0.987 0.987 0.903 ...
## $ meth.diff: num 3.68 8.97 -2.18 2.04 -4.61 ...my_CpGislandsol1 <- as.data.frame(my_CpGislandsol1,row.names = 1:nrow(as.data.frame(ranges(my_CpGislandsol1))))
head(my_CpGislandsol1)## seqnames start end width strand source ID
## 1 KK215283.1 5832 6408 577 + cpgplot KK215283.1.1
## 2 KK215283.1 5832 6408 577 + cpgplot KK215283.1.1
## 3 KK215283.1 5832 6408 577 + cpgplot KK215283.1.1
## 4 KK215283.1 5832 6408 577 + cpgplot KK215283.1.1
## 5 KK215283.1 5832 6408 577 + cpgplot KK215283.1.1
## 6 KK215283.1 5832 6408 577 + cpgplot KK215283.1.1CvLCpGislandsdf <- cbind(CvLCpGislandsdf,my_CpGislandsol1[c("source","ID")])
CvLCpGislandsdf$seqnames <- as.character(CvLCpGislandsdf$seqnames)
head(CvLCpGislandsdf)## seqnames start end width strand pvalue qvalue meth.diff source
## 1 KK215283.1 5846 5846 1 + 0.5038369 0.9682648 3.682171 cpgplot
## 2 KK215283.1 5847 5847 1 + 0.3609891 0.9103265 8.974359 cpgplot
## 3 KK215283.1 5876 5876 1 + 0.6138463 0.9866335 -2.175346 cpgplot
## 4 KK215283.1 5877 5877 1 + 0.7249991 0.9866335 2.037351 cpgplot
## 5 KK215283.1 5882 5882 1 + 0.3440347 0.9027074 -4.614370 cpgplot
## 6 KK215283.1 5883 5883 1 + 0.1801677 0.8725507 -6.451613 cpgplot
## ID
## 1 KK215283.1.1
## 2 KK215283.1.1
## 3 KK215283.1.1
## 4 KK215283.1.1
## 5 KK215283.1.1
## 6 KK215283.1.1CvLCpGislandschrdf <- CvLCpGislandsdf[grep("LG",CvLCpGislandsdf$seqnames),]
head(CvLCpGislandschrdf)## seqnames start end width strand pvalue qvalue meth.diff
## 168315 LG1 6736 6736 1 + 0.009204301 0.7614440 -23.479730
## 168316 LG1 6757 6757 1 + 0.681014072 0.9866335 -3.896104
## 168317 LG1 6758 6758 1 + 0.101258775 0.8151339 -8.333333
## 168318 LG1 6776 6776 1 + 0.459371588 0.9520953 -4.404404
## 168319 LG1 6777 6777 1 + 0.095849874 0.8071970 -7.142857
## 168320 LG1 6783 6783 1 + 0.476773286 0.9580070 -6.766917
## source ID
## 168315 cpgplot LG1.1
## 168316 cpgplot LG1.1
## 168317 cpgplot LG1.1
## 168318 cpgplot LG1.1
## 168319 cpgplot LG1.1
## 168320 cpgplot LG1.1CvLCpGislandschrdf <- CvLCpGislandschrdf[order(CvLCpGislandschrdf[,7]), ]
head(CvLCpGislandschrdf,10)## seqnames start end width strand pvalue qvalue
## 1083870 LG2 1285106 1285106 1 + 1.298464e-06 0.5043399
## 1347580 LG21 12440572 12440572 1 + 7.649774e-07 0.5043399
## 1527348 LG3 7025036 7025036 1 + 1.834685e-06 0.5368033
## 1444783 LG22 23476842 23476842 1 + 2.390014e-06 0.5639412
## 401764 LG11 21480469 21480469 1 + 3.047519e-06 0.5646001
## 2000053 LG9 3178904 3178904 1 + 2.976812e-06 0.5646001
## 2019776 LG9 9539135 9539135 1 + 2.597092e-06 0.5646001
## 522084 LG13 3641262 3641262 1 + 3.383354e-06 0.5846745
## 878197 LG17 15875454 15875454 1 + 3.299379e-06 0.5846745
## 1198615 LG2 42532225 42532225 1 + 3.990365e-06 0.5901297
## meth.diff source ID
## 1083870 71.70868 cpgplot LG2.108
## 1347580 -57.14286 cpgplot LG21.1332
## 1527348 48.14815 cpgplot LG3.451
## 1444783 56.59574 cpgplot LG22.1873
## 401764 -45.94595 cpgplot LG11.1672
## 2000053 -44.82759 cpgplot LG9.173
## 2019776 -42.10526 cpgplot LG9.777
## 522084 39.28571 cpgplot LG13.246
## 878197 48.17170 cpgplot LG17.1359
## 1198615 -50.00000 cpgplot LG2.3583rm(CvLCpGislands)
rm(CvLCpGislandsdf)ol1 <- findOverlaps(methylkitGvLGR,my_CpGislands)## Warning in .Seqinfo.mergexy(x, y): Each of the 2 combined objects has sequence levels not in the other:
## - in 'x': KK215310.1, KK215354.1, KK215361.1, KK215370.1, KK215371.1, KK215372.1, KK215373.1, KK215378.1, KK215379.1, KK215380.1, KK215381.1, KK215382.1, KK215388.1, KK215392.1, KK215393.1, KK215396.1, KK215402.1, KK215403.1, KK215404.1, KK215405.1, KK215406.1, KK215412.1, KK215414.1, KK215417.1, KK215420.1, KK215421.1, KK215422.1, KK215423.1, KK215429.1, KK215430.1, KK215433.1, KK215435.1, KK215437.1, KK215438.1, KK215440.1, KK215442.1, KK215454.1, KK215456.1, KK215458.1, KK215461.1, KK215462.1, KK215463.1, KK215465.1, KK215466.1, KK215467.1, KK215468.1, KK215472.1, KK215474.1, KK215480.1, KK215482.1, KK215483.1, KK215484.1, KK215485.1, KK215486.1, KK215487.1, KK215489.1, KK215493.1, KK215494.1, KK215497.1, KK215498.1, KK215501.1, KK215503.1, KK215504.1, KK215506.1, KK215508.1, KK215512.1, KK215515.1, KK215519.1, KK215521.1, KK215522.1, KK215523.1, KK215524.1, KK215525.1, KK215526.1, KK215528.1, KK215531.1, KK215533.1, KK215534.1, KK215536.1, KK215538.1, KK215541.1, KK215544.1, KK215545.1, KK215546.1, KK215547.1, KK215548.1, KK215549.1, KK215551.1, KK215554.1, KK215556.1, KK215557.1, KK215559.1, KK215560.1, KK215562.1, KK215564.1, KK215565.1, KK215570.1, KK215572.1, KK215573.1, KK215574.1, KK215577.1, KK215579.1, KK215580.1, KK215582.1, KK215584.1, KK215585.1, KK215591.1, KK215592.1, KK215593.1, KK215595.1, KK215598.1, KK215609.1, KK215612.1, KK215613.1, KK215614.1, KK215615.1, KK215620.1, KK215621.1, KK215623.1, KK215625.1, KK215626.1, KK215634.1, KK215635.1, KK215636.1, KK215637.1, KK215638.1, KK215642.1, KK215643.1, KK215644.1, KK215645.1, KK215647.1, KK215649.1, KK215651.1, KK215652.1, KK215654.1, KK215656.1, KK215657.1, KK215661.1, KK215662.1, KK215663.1, KK215665.1, KK215666.1, KK215668.1, KK215671.1, KK215673.1, KK215675.1, KK215677.1, KK215681.1, KK215684.1, KK215687.1, KK215688.1, KK215689.1, KK215691.1, KK215692.1, KK215694.1, KK215695.1, KK215697.1, KK215698.1, KK215703.1, KK215705.1, KK215707.1, KK215708.1, KK215710.1, KK215712.1, KK215715.1, KK215717.1, KK215720.1, KK215721.1, KK215723.1, KK215724.1, KK215727.1, KK215728.1, KK215730.1, KK215731.1, KK215732.1, KK215734.1, KK215735.1, KK215736.1, KK215738.1, KK215741.1, KK215742.1, KK215743.1, KK215748.1, KK215756.1, KK215757.1, KK215758.1, KK215760.1, KK215761.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215766.1, KK215767.1, KK215770.1, KK215772.1, KK215774.1, KK215775.1, KK215776.1, KK215777.1, KK215779.1, KK215780.1, KK215784.1, KK215785.1, KK215786.1, KK215787.1, KK215789.1, KK215790.1, KK215794.1, KK215795.1, KK215796.1, KK215798.1, KK215800.1, KK215802.1, KK215803.1, KK215804.1, KK215805.1, KK215808.1, KK215809.1, KK215810.1, KK215813.1, KK215814.1, KK215815.1, KK215816.1, KK215818.1, KK215819.1, KK215824.1, KK215825.1, KK215826.1, KK215827.1, KK215828.1, KK215829.1, KK215831.1, KK215834.1, KK215838.1, KK215839.1, KK215840.1, KK215842.1, KK215843.1, KK215844.1, KK215846.1, KK215847.1, KK215849.1, KK215851.1, KK215852.1, KK215854.1, KK215855.1, KK215856.1, KK215857.1, KK215858.1, KK215859.1, KK215860.1, KK215861.1, KK215863.1, KK215864.1, KK215865.1, KK215866.1, KK215867.1, KK215869.1, KK215870.1, KK215871.1, KK215873.1, KK215874.1, KK215875.1, KK215878.1, KK215879.1, KK215880.1, KK215881.1, KK215884.1, KK215885.1, KK215886.1, KK215887.1, KK215888.1, KK215890.1, KK215891.1, KK215892.1, KK215893.1, KK215895.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215902.1, KK215903.1, KK215905.1, KK215906.1, KK215908.1, KK215909.1, KK215911.1, KK215914.1, KK215915.1, KK215916.1, KK215918.1, KK215919.1, KK215920.1, KK215921.1, KK215923.1, KK215924.1, KK215927.1, KK215928.1, KK215933.1, KK215934.1, KK215936.1, KK215939.1, KK215940.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215947.1, KK215949.1, KK215950.1, KK215951.1, KK215952.1, KK215953.1, KK215956.1, KK215957.1, KK215958.1, KK215960.1, KK215961.1, KK215966.1, KK215968.1, KK215969.1, KK215970.1, KK215971.1, KK215972.1, KK215973.1, KK215975.1, KK215976.1, KK215978.1, KK215979.1, KK215981.1, KK215982.1, KK215983.1, KK215984.1, KK215985.1, KK215987.1, KK215993.1, KK215994.1, KK215997.1, KK216000.1, KK216001.1, KK216005.1, KK216006.1, KK216009.1, KK216011.1, KK216012.1, KK216014.1, KK216015.1, KK216016.1, KK216017.1, KK216018.1, KK216022.1, KK216024.1, KK216025.1, KK216026.1, KK216028.1, KK216029.1, KK216030.1, KK216032.1, KK216033.1, KK216034.1, KK216035.1, KK216037.1, KK216039.1, KK216040.1, KK216041.1, KK216042.1, KK216043.1, KK216044.1, KK216048.1, KK216049.1, KK216050.1, KK216051.1, KK216053.1, KK216055.1, KK216056.1, KK216059.1, KK216062.1, KK216063.1, KK216064.1, KK216065.1, KK216066.1, KK216068.1, KK216069.1, KK216072.1, KK216075.1, KK216076.1, KK216077.1, KK216078.1, KK216079.1, KK216080.1, KK216081.1, KK216082.1, KK216083.1, KK216084.1, KK216085.1, KK216086.1, KK216087.1, KK216089.1, KK216091.1, KK216092.1, KK216093.1, KK216097.1, KK216098.1, KK216100.1, KK216101.1, KK216106.1, KK216107.1, KK216108.1, KK216110.1, KK216112.1, KK216114.1, KK216116.1, KK216120.1, KK216121.1, KK216122.1, KK216124.1, KK216125.1, KK216126.1, KK216127.1, KK216128.1, KK216130.1, KK216131.1, KK216133.1, KK216134.1, KK216135.1, KK216136.1, KK216138.1, KK216140.1, KK216141.1, KK216142.1, KK216143.1, KK216144.1, KK216146.1, KK216147.1, KK216148.1, KK216151.1, KK216152.1, KK216154.1, KK216155.1, KK216157.1, KK216158.1, KK216159.1, KK216160.1, KK216161.1, KK216163.1, KK216164.1, KK216165.1, KK216166.1, KK216168.1, KK216169.1, KK216171.1, KK216174.1, KK216176.1, KK216178.1, KK216179.1, KK216181.1, KK216182.1, KK216184.1, KK216186.1, KK216190.1, KK216193.1, KK216194.1, KK216195.1, KK216196.1, KK216197.1, KK216198.1, KK216200.1, KK216201.1, KK216202.1, KK216205.1, KK216206.1, KK216207.1, KK216208.1, KK216210.1, KK216212.1, KK216214.1, KK216215.1, KK216218.1, KK216221.1, KK216222.1, KK216224.1, KK216225.1, KK216226.1, KK216227.1, KK216228.1, KK216230.1, KK216231.1, KK216232.1, KK216234.1, KK216237.1, KK216238.1, KK216239.1, KK216240.1, KK216241.1, KK216242.1, KK216243.1, KK216244.1, KK216245.1, KK216248.1, KK216249.1, KK216251.1, KK216252.1, KK216253.1, KK216254.1, KK216256.1, KK216258.1, KK216259.1, KK216260.1, KK216261.1, KK216262.1, KK216263.1, KK216264.1, KK216266.1, KK216267.1, KK216268.1, KK216269.1, KK216270.1, KK216271.1, KK216274.1, KK216276.1, KK216277.1, KK216278.1, KK216280.1, KK216281.1, KK216284.1, KK216287.1, KK216288.1, KK216289.1, KK216290.1, KK216291.1, KK216292.1, KK216294.1, KK216295.1, KK216296.1, KK216297.1, KK216298.1, KK216301.1, KK216302.1, KK216304.1, KK216306.1, KK216307.1, KK216310.1, KK216311.1, KK216312.1, KK216313.1, KK216315.1, KK216317.1, KK216318.1, KK216319.1, KK216320.1, KK216321.1, KK216322.1, KK216324.1, KK216325.1, KK216327.1, KK216328.1, KK216329.1, KK216330.1, KK216332.1, KK216333.1, KK216335.1, KK216336.1, KK216337.1, KK216338.1, KK216340.1, KK216341.1, KK216342.1, KK216344.1, KK216345.1, KK216346.1, KK216347.1, KK216349.1, KK216351.1, KK216352.1, KK216354.1, KK216355.1, KK216356.1, KK216359.1, KK216360.1, KK216361.1, KK216362.1, KK216363.1, KK216366.1, KK216369.1, KK216370.1, KK216371.1, KK216372.1, KK216374.1, KK216375.1, KK216376.1, KK216377.1, KK216378.1, KK216379.1, KK216380.1, KK216381.1, KK216383.1, KK216384.1, KK216385.1, KK216387.1, KK216388.1, KK216389.1, KK216390.1, KK216391.1, KK216393.1, KK216394.1, KK216396.1, KK216397.1, KK216398.1, KK216400.1, KK216402.1, KK216403.1, KK216404.1, KK216405.1, KK216406.1, KK216407.1, KK216408.1, KK216410.1, KK216412.1, KK216413.1, KK216414.1, KK216416.1, KK216417.1, KK216418.1, KK216419.1, KK216420.1, KK216421.1, KK216422.1, KK216423.1, KK216424.1, KK216425.1, KK216426.1, KK216427.1, KK216428.1, KK216429.1, KK216430.1, KK216431.1, KK216432.1, KK216433.1, KK216434.1, KK216437.1, KK216438.1, KK216439.1, KK216440.1, KK216441.1, KK216442.1, KK216443.1, KK216444.1, KK216445.1, KK216446.1, KK216451.1, KK216452.1, KK216453.1, KK216454.1, KK216455.1, KK216456.1, KK216457.1, KK216458.1, KK216459.1, KK216461.1, KK216462.1, KK216463.1, KK216464.1, KK216465.1, KK216466.1, KK216467.1, KK216468.1, KK216469.1, KK216470.1, KK216471.1, KK216474.1, KK216476.1, KK216477.1, KK216479.1, KK216482.ol1## Hits object with 2382668 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 170 56232
## [2] 171 56232
## [3] 172 56232
## [4] 173 56232
## [5] 174 56232
## ... ... ...
## [2382664] 21227900 23734
## [2382665] 21227901 23734
## [2382666] 21227902 23734
## [2382667] 21227903 23734
## [2382668] 21227904 23734
## -------
## queryLength: 21234500 / subjectLength: 60897GvLCpGislands <- methylkitGvLGR[queryHits(ol1)]
my_CpGislandsol1 <- my_CpGislands[subjectHits(ol1)]
head(GvLCpGislands)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | pvalue qvalue meth.diff
## <Rle> <IRanges> <Rle> | <numeric> <numeric> <numeric>
## [1] KK215283.1 5846 + | 0.0765973 0.816899 11.257928
## [2] KK215283.1 5847 + | 0.1819384 0.892630 10.826211
## [3] KK215283.1 5876 + | 0.8144955 0.985470 1.121951
## [4] KK215283.1 5877 + | 0.7714114 0.985470 1.319648
## [5] KK215283.1 5882 + | 0.5051816 0.972447 -3.235441
## [6] KK215283.1 5883 + | 0.9499525 0.985470 0.366569
## -------
## seqinfo: 2483 sequences from an unspecified genome; no seqlengthsmy_CpGislandsol1## GRanges object with 2382668 ranges and 2 metadata columns:
## seqnames ranges strand | source ID
## <Rle> <IRanges> <Rle> | <factor> <character>
## [1] KK215283.1 5832-6408 + | cpgplot KK215283.1.1
## [2] KK215283.1 5832-6408 + | cpgplot KK215283.1.1
## [3] KK215283.1 5832-6408 + | cpgplot KK215283.1.1
## [4] KK215283.1 5832-6408 + | cpgplot KK215283.1.1
## [5] KK215283.1 5832-6408 + | cpgplot KK215283.1.1
## ... ... ... ... . ... ...
## [2382664] LG9 34115391-34115990 + | cpgplot LG9.2412
## [2382665] LG9 34115391-34115990 + | cpgplot LG9.2412
## [2382666] LG9 34115391-34115990 + | cpgplot LG9.2412
## [2382667] LG9 34115391-34115990 + | cpgplot LG9.2412
## [2382668] LG9 34115391-34115990 + | cpgplot LG9.2412
## -------
## seqinfo: 646 sequences from an unspecified genome; no seqlengthsGvLCpGislandsdf <- as.data.frame(GvLCpGislands,row.names = 1:nrow(as.data.frame(ranges(GvLCpGislands))))
str(GvLCpGislandsdf)## 'data.frame': 2382668 obs. of 8 variables:
## $ seqnames : Factor w/ 2483 levels "KK215283.1","KK215284.1",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ start : int 5846 5847 5876 5877 5882 5883 5885 5886 5901 5902 ...
## $ end : int 5846 5847 5876 5877 5882 5883 5885 5886 5901 5902 ...
## $ width : int 1 1 1 1 1 1 1 1 1 1 ...
## $ strand : Factor w/ 3 levels "+","-","*": 1 1 1 1 1 1 1 1 1 1 ...
## $ pvalue : num 0.0766 0.1819 0.8145 0.7714 0.5052 ...
## $ qvalue : num 0.817 0.893 0.985 0.985 0.972 ...
## $ meth.diff: num 11.26 10.83 1.12 1.32 -3.24 ...my_CpGislandsol1 <- as.data.frame(my_CpGislandsol1,row.names = 1:nrow(as.data.frame(ranges(my_CpGislandsol1))))
head(my_CpGislandsol1)## seqnames start end width strand source ID
## 1 KK215283.1 5832 6408 577 + cpgplot KK215283.1.1
## 2 KK215283.1 5832 6408 577 + cpgplot KK215283.1.1
## 3 KK215283.1 5832 6408 577 + cpgplot KK215283.1.1
## 4 KK215283.1 5832 6408 577 + cpgplot KK215283.1.1
## 5 KK215283.1 5832 6408 577 + cpgplot KK215283.1.1
## 6 KK215283.1 5832 6408 577 + cpgplot KK215283.1.1GvLCpGislandsdf <- cbind(GvLCpGislandsdf,my_CpGislandsol1[c("source","ID")])
GvLCpGislandsdf$seqnames <- as.character(GvLCpGislandsdf$seqnames)
head(GvLCpGislandsdf)## seqnames start end width strand pvalue qvalue meth.diff source
## 1 KK215283.1 5846 5846 1 + 0.07659731 0.8168994 11.2579281 cpgplot
## 2 KK215283.1 5847 5847 1 + 0.18193835 0.8926296 10.8262108 cpgplot
## 3 KK215283.1 5876 5876 1 + 0.81449548 0.9854701 1.1219512 cpgplot
## 4 KK215283.1 5877 5877 1 + 0.77141136 0.9854701 1.3196481 cpgplot
## 5 KK215283.1 5882 5882 1 + 0.50518162 0.9724473 -3.2354405 cpgplot
## 6 KK215283.1 5883 5883 1 + 0.94995253 0.9854701 0.3665689 cpgplot
## ID
## 1 KK215283.1.1
## 2 KK215283.1.1
## 3 KK215283.1.1
## 4 KK215283.1.1
## 5 KK215283.1.1
## 6 KK215283.1.1GvLCpGislandschrdf <- GvLCpGislandsdf[grep("LG",GvLCpGislandsdf$seqnames),]
head(GvLCpGislandschrdf)## seqnames start end width strand pvalue qvalue meth.diff source
## 194463 LG1 6736 6736 1 + 0.1179387 0.8485210 -15.936626 cpgplot
## 194464 LG1 6737 6737 1 + 0.6656729 0.9854701 -1.893939 cpgplot
## 194465 LG1 6757 6757 1 + 0.7410367 0.9854701 -3.030303 cpgplot
## 194466 LG1 6758 6758 1 + 0.4791965 0.9652098 -4.166667 cpgplot
## 194467 LG1 6776 6776 1 + 0.7879148 0.9854701 1.891892 cpgplot
## 194468 LG1 6777 6777 1 + 0.3022617 0.9053345 -4.968944 cpgplot
## ID
## 194463 LG1.1
## 194464 LG1.1
## 194465 LG1.1
## 194466 LG1.1
## 194467 LG1.1
## 194468 LG1.1GvLCpGislandschrdf <- GvLCpGislandschrdf[order(GvLCpGislandschrdf[,7]), ]
head(GvLCpGislandschrdf,10)## seqnames start end width strand pvalue qvalue
## 1873013 LG4 17759254 17759254 1 + 9.387446e-08 0.1227759
## 2320910 LG9 9539135 9539135 1 + 3.187294e-07 0.2740171
## 220166 LG1 9068545 9068545 1 + 3.491864e-07 0.2810408
## 871440 LG16 764776 764776 1 + 1.271785e-06 0.3958443
## 2290735 LG8 27834942 27834942 1 + 1.471141e-06 0.3958443
## 1760559 LG3 8478518 8478518 1 + 1.998130e-06 0.4437762
## 1864824 LG4 15799437 15799437 1 + 2.367559e-06 0.4587357
## 1674788 LG23 580895 580895 1 + 2.756714e-06 0.4728434
## 1524625 LG21 2706960 2706960 1 + 2.798251e-06 0.4731783
## 220165 LG1 9068542 9068542 1 + 2.840631e-06 0.4755436
## meth.diff source ID
## 1873013 -57.26654 cpgplot LG4.1446
## 2320910 -36.17021 cpgplot LG9.777
## 220166 51.21156 cpgplot LG1.682
## 871440 -49.70964 cpgplot LG16.251
## 2290735 49.87212 cpgplot LG8.2592
## 1760559 36.84211 cpgplot LG3.559
## 1864824 -49.03382 cpgplot LG4.1227
## 1674788 41.93548 cpgplot LG23.132
## 1524625 30.18868 cpgplot LG21.651
## 220165 46.32258 cpgplot LG1.682rm(GvLCpGislands)
rm(GvLCpGislandsdf)Methylkit CpG results annotated to promoters
ol1 <- findOverlaps(methylkitCvGGR,my_Promoters)## Warning in .Seqinfo.mergexy(x, y): Each of the 2 combined objects has sequence levels not in the other:
## - in 'x': KK215332.1, KK215339.1, KK215341.1, KK215351.1, KK215360.1, KK215378.1, KK215383.1, KK215387.1, KK215388.1, KK215391.1, KK215393.1, KK215395.1, KK215396.1, KK215397.1, KK215400.1, KK215401.1, KK215402.1, KK215403.1, KK215405.1, KK215406.1, KK215407.1, KK215408.1, KK215411.1, KK215412.1, KK215414.1, KK215415.1, KK215418.1, KK215419.1, KK215420.1, KK215421.1, KK215424.1, KK215425.1, KK215427.1, KK215429.1, KK215430.1, KK215432.1, KK215433.1, KK215435.1, KK215439.1, KK215440.1, KK215441.1, KK215443.1, KK215444.1, KK215446.1, KK215448.1, KK215451.1, KK215453.1, KK215454.1, KK215455.1, KK215456.1, KK215459.1, KK215462.1, KK215463.1, KK215465.1, KK215466.1, KK215467.1, KK215472.1, KK215474.1, KK215475.1, KK215479.1, KK215480.1, KK215482.1, KK215484.1, KK215485.1, KK215486.1, KK215488.1, KK215489.1, KK215490.1, KK215491.1, KK215492.1, KK215494.1, KK215496.1, KK215497.1, KK215498.1, KK215501.1, KK215502.1, KK215503.1, KK215504.1, KK215506.1, KK215507.1, KK215508.1, KK215511.1, KK215512.1, KK215513.1, KK215514.1, KK215515.1, KK215516.1, KK215517.1, KK215518.1, KK215519.1, KK215521.1, KK215523.1, KK215524.1, KK215525.1, KK215526.1, KK215528.1, KK215529.1, KK215530.1, KK215531.1, KK215533.1, KK215538.1, KK215540.1, KK215541.1, KK215543.1, KK215544.1, KK215545.1, KK215546.1, KK215547.1, KK215548.1, KK215549.1, KK215551.1, KK215553.1, KK215554.1, KK215556.1, KK215558.1, KK215559.1, KK215560.1, KK215561.1, KK215562.1, KK215564.1, KK215567.1, KK215568.1, KK215573.1, KK215574.1, KK215577.1, KK215578.1, KK215579.1, KK215581.1, KK215582.1, KK215583.1, KK215584.1, KK215585.1, KK215586.1, KK215587.1, KK215588.1, KK215589.1, KK215590.1, KK215594.1, KK215595.1, KK215597.1, KK215598.1, KK215601.1, KK215602.1, KK215603.1, KK215605.1, KK215606.1, KK215608.1, KK215615.1, KK215616.1, KK215620.1, KK215621.1, KK215622.1, KK215624.1, KK215625.1, KK215626.1, KK215627.1, KK215628.1, KK215629.1, KK215630.1, KK215632.1, KK215633.1, KK215634.1, KK215635.1, KK215636.1, KK215637.1, KK215638.1, KK215639.1, KK215641.1, KK215642.1, KK215644.1, KK215645.1, KK215646.1, KK215647.1, KK215649.1, KK215652.1, KK215654.1, KK215655.1, KK215657.1, KK215658.1, KK215661.1, KK215662.1, KK215663.1, KK215664.1, KK215665.1, KK215668.1, KK215669.1, KK215670.1, KK215671.1, KK215672.1, KK215673.1, KK215675.1, KK215677.1, KK215678.1, KK215683.1, KK215684.1, KK215688.1, KK215689.1, KK215692.1, KK215694.1, KK215695.1, KK215699.1, KK215700.1, KK215701.1, KK215703.1, KK215704.1, KK215705.1, KK215706.1, KK215707.1, KK215709.1, KK215710.1, KK215711.1, KK215712.1, KK215715.1, KK215718.1, KK215719.1, KK215720.1, KK215721.1, KK215722.1, KK215723.1, KK215724.1, KK215726.1, KK215727.1, KK215728.1, KK215733.1, KK215734.1, KK215736.1, KK215737.1, KK215738.1, KK215739.1, KK215740.1, KK215741.1, KK215742.1, KK215743.1, KK215745.1, KK215748.1, KK215750.1, KK215752.1, KK215753.1, KK215754.1, KK215755.1, KK215756.1, KK215757.1, KK215758.1, KK215759.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215766.1, KK215767.1, KK215768.1, KK215769.1, KK215770.1, KK215771.1, KK215772.1, KK215774.1, KK215775.1, KK215776.1, KK215777.1, KK215778.1, KK215779.1, KK215780.1, KK215782.1, KK215783.1, KK215785.1, KK215786.1, KK215788.1, KK215789.1, KK215792.1, KK215794.1, KK215795.1, KK215796.1, KK215797.1, KK215798.1, KK215802.1, KK215804.1, KK215805.1, KK215807.1, KK215810.1, KK215812.1, KK215814.1, KK215815.1, KK215816.1, KK215818.1, KK215819.1, KK215821.1, KK215825.1, KK215827.1, KK215832.1, KK215834.1, KK215836.1, KK215837.1, KK215838.1, KK215839.1, KK215840.1, KK215841.1, KK215842.1, KK215843.1, KK215846.1, KK215847.1, KK215848.1, KK215849.1, KK215851.1, KK215852.1, KK215854.1, KK215857.1, KK215858.1, KK215859.1, KK215860.1, KK215861.1, KK215863.1, KK215864.1, KK215865.1, KK215866.1, KK215867.1, KK215869.1, KK215870.1, KK215872.1, KK215873.1, KK215874.1, KK215875.1, KK215877.1, KK215878.1, KK215880.1, KK215881.1, KK215882.1, KK215884.1, KK215885.1, KK215886.1, KK215890.1, KK215891.1, KK215892.1, KK215893.1, KK215894.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215902.1, KK215903.1, KK215905.1, KK215907.1, KK215908.1, KK215909.1, KK215910.1, KK215911.1, KK215913.1, KK215914.1, KK215915.1, KK215917.1, KK215918.1, KK215920.1, KK215921.1, KK215922.1, KK215923.1, KK215924.1, KK215927.1, KK215928.1, KK215929.1, KK215933.1, KK215934.1, KK215935.1, KK215937.1, KK215938.1, KK215940.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215946.1, KK215949.1, KK215951.1, KK215952.1, KK215953.1, KK215956.1, KK215957.1, KK215958.1, KK215960.1, KK215962.1, KK215963.1, KK215965.1, KK215967.1, KK215969.1, KK215970.1, KK215971.1, KK215972.1, KK215973.1, KK215974.1, KK215975.1, KK215976.1, KK215977.1, KK215978.1, KK215979.1, KK215982.1, KK215983.1, KK215984.1, KK215985.1, KK215986.1, KK215987.1, KK215989.1, KK215990.1, KK215993.1, KK215994.1, KK215995.1, KK215996.1, KK215997.1, KK215999.1, KK216000.1, KK216001.1, KK216005.1, KK216006.1, KK216007.1, KK216008.1, KK216009.1, KK216011.1, KK216012.1, KK216015.1, KK216016.1, KK216017.1, KK216018.1, KK216021.1, KK216022.1, KK216023.1, KK216024.1, KK216025.1, KK216026.1, KK216027.1, KK216028.1, KK216029.1, KK216030.1, KK216032.1, KK216033.1, KK216034.1, KK216035.1, KK216036.1, KK216037.1, KK216038.1, KK216039.1, KK216040.1, KK216041.1, KK216042.1, KK216043.1, KK216044.1, KK216047.1, KK216048.1, KK216049.1, KK216050.1, KK216053.1, KK216055.1, KK216056.1, KK216058.1, KK216059.1, KK216062.1, KK216063.1, KK216064.1, KK216065.1, KK216066.1, KK216067.1, KK216068.1, KK216069.1, KK216070.1, KK216071.1, KK216072.1, KK216074.1, KK216075.1, KK216076.1, KK216077.1, KK216078.1, KK216079.1, KK216080.1, KK216082.1, KK216083.1, KK216084.1, KK216085.1, KK216086.1, KK216087.1, KK216089.1, KK216091.1, KK216093.1, KK216094.1, KK216095.1, KK216096.1, KK216097.1, KK216098.1, KK216099.1, KK216102.1, KK216103.1, KK216106.1, KK216109.1, KK216110.1, KK216111.1, KK216112.1, KK216113.1, KK216114.1, KK216115.1, KK216117.1, KK216118.1, KK216120.1, KK216122.1, KK216124.1, KK216125.1, KK216126.1, KK216127.1, KK216128.1, KK216131.1, KK216133.1, KK216134.1, KK216135.1, KK216137.1, KK216138.1, KK216140.1, KK216141.1, KK216142.1, KK216143.1, KK216144.1, KK216145.1, KK216146.1, KK216150.1, KK216151.1, KK216152.1, KK216154.1, KK216155.1, KK216157.1, KK216158.1, KK216159.1, KK216160.1, KK216162.1, KK216163.1, KK216164.1, KK216165.1, KK216166.1, KK216168.1, KK216169.1, KK216171.1, KK216172.1, KK216173.1, KK216174.1, KK216175.1, KK216176.1, KK216177.1, KK216178.1, KK216180.1, KK216181.1, KK216182.1, KK216184.1, KK216186.1, KK216190.1, KK216192.1, KK216193.1, KK216194.1, KK216195.1, KK216196.1, KK216197.1, KK216198.1, KK216200.1, KK216201.1, KK216202.1, KK216203.1, KK216205.1, KK216206.1, KK216208.1, KK216212.1, KK216213.1, KK216214.1, KK216215.1, KK216217.1, KK216218.1, KK216219.1, KK216221.1, KK216222.1, KK216224.1, KK216225.1, KK216226.1, KK216227.1, KK216229.1, KK216231.1, KK216232.1, KK216234.1, KK216235.1, KK216236.1, KK216237.1, KK216238.1, KK216240.1, KK216241.1, KK216242.1, KK216243.1, KK216244.1, KK216245.1, KK216248.1, KK216251.1, KK216252.1, KK216253.1, KK216254.1, KK216256.1, KK216258.1, KK216259.1, KK216260.1, KK216261.1, KK216262.1, KK216263.1, KK216264.1, KK216265.1, KK216266.1, KK216267.1, KK216269.1, KK216270.1, KK216271.1, KK216272.1, KK216273.1, KK216274.1, KK216275.1, KK216276.1, KK216278.1, KK216280.1, KK216281.1, KK216282.1, KK216283.1, KK216284.1, KK216285.1, KK216287.1, KK216288.1, KK216289.1, KK216290.1, KK216291.1, KK216292.1, KK216293.1, KK216295.1, KK216296.1, KK216297.1, KK216298.1, KK216299.1, KK216302.1, KK216303.1, KK216304.1, KK216306.1, KK216307.1, KK216308.1, KK216310.1, KK216311.1, KK216313.1, KK216315.1, KK216316.1, KK216317.1, KK216318.1, KK216319.1, KK216320.1, KK216321.1, KK216322.1, KK216323.1, KK216324.1, KK216325.1, KK216326.1, KK216327.1, KK216328.1, KK216329.1, KK216330.1, KK216331.1, KK216333.1, KK216334.1, KK216335.1, KK216336.1, KK216337.1, KK216338.1, KK216340.1, KK216341.1, KK216342.1, KK216343.1, KK216344.1, KK216345.1, KK216346.1, KK216347.1, KK216349.1, KK216351.1, KK216353.1, KK216354.1, KK216356.ol1## Hits object with 1658172 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 25112 16047
## [2] 25113 16047
## [3] 25114 16047
## [4] 25115 16047
## [5] 25116 16047
## ... ... ...
## [1658168] 18866542 2480
## [1658169] 18866543 2479
## [1658170] 18866543 2480
## [1658171] 18866544 2479
## [1658172] 18866544 2480
## -------
## queryLength: 18874229 / subjectLength: 34314CvGpromoters <- methylkitCvGGR[queryHits(ol1)]
myPromotersol1 <- my_Promoters[subjectHits(ol1)]
head(CvGpromoters)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | pvalue qvalue meth.diff
## <Rle> <IRanges> <Rle> | <numeric> <numeric> <numeric>
## [1] KK215283.1 633237 + | 0.934442 0.989133 0.427350
## [2] KK215283.1 633238 + | 0.112748 0.834984 8.731382
## [3] KK215283.1 633265 + | 0.485604 0.964594 4.118404
## [4] KK215283.1 633266 + | 0.783154 0.989133 -1.593137
## [5] KK215283.1 633284 + | 0.270109 0.898802 5.544006
## [6] KK215283.1 633285 + | 0.856427 0.989133 -0.774194
## -------
## seqinfo: 2455 sequences from an unspecified genome; no seqlengthsmyPromotersol1## GRanges object with 1658172 ranges and 3 metadata columns:
## seqnames ranges strand | V5
## <Rle> <IRanges> <Rle> | <character>
## [1] KK215283.1 633221-636222 + | ENSPREG00000018045
## [2] KK215283.1 633221-636222 + | ENSPREG00000018045
## [3] KK215283.1 633221-636222 + | ENSPREG00000018045
## [4] KK215283.1 633221-636222 + | ENSPREG00000018045
## [5] KK215283.1 633221-636222 + | ENSPREG00000018045
## ... ... ... ... . ...
## [1658168] LG9 34072750-34075751 + | ENSPREG00000019083
## [1658169] LG9 34072714-34075715 + | ENSPREG00000019083
## [1658170] LG9 34072750-34075751 + | ENSPREG00000019083
## [1658171] LG9 34072714-34075715 + | ENSPREG00000019083
## [1658172] LG9 34072750-34075751 + | ENSPREG00000019083
## V6 V7
## <character> <character>
## [1] ENSPRET00000026955 uncharacterised
## [2] ENSPRET00000026955 uncharacterised
## [3] ENSPRET00000026955 uncharacterised
## [4] ENSPRET00000026955 uncharacterised
## [5] ENSPRET00000026955 uncharacterised
## ... ... ...
## [1658168] ENSPRET00000028582 adamtsl2
## [1658169] ENSPRET00000028533 adamtsl2
## [1658170] ENSPRET00000028582 adamtsl2
## [1658171] ENSPRET00000028533 adamtsl2
## [1658172] ENSPRET00000028582 adamtsl2
## -------
## seqinfo: 452 sequences from an unspecified genome; no seqlengthsCvGpromotersdf <- as.data.frame(CvGpromoters,row.names = 1:nrow(as.data.frame(ranges(CvGpromoters))))
str(CvGpromotersdf)## 'data.frame': 1658172 obs. of 8 variables:
## $ seqnames : Factor w/ 2455 levels "KK215283.1","KK215284.1",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ start : int 633237 633238 633265 633266 633284 633285 633309 633310 633320 633321 ...
## $ end : int 633237 633238 633265 633266 633284 633285 633309 633310 633320 633321 ...
## $ width : int 1 1 1 1 1 1 1 1 1 1 ...
## $ strand : Factor w/ 3 levels "+","-","*": 1 1 1 1 1 1 1 1 1 1 ...
## $ pvalue : num 0.934 0.113 0.486 0.783 0.27 ...
## $ qvalue : num 0.989 0.835 0.965 0.989 0.899 ...
## $ meth.diff: num 0.427 8.731 4.118 -1.593 5.544 ...myPromotersoldf1 <- as.data.frame(myPromotersol1,row.names = 1:nrow(as.data.frame(ranges(myPromotersol1))))
head(myPromotersoldf1)## seqnames start end width strand V5 V6
## 1 KK215283.1 633221 636222 3002 + ENSPREG00000018045 ENSPRET00000026955
## 2 KK215283.1 633221 636222 3002 + ENSPREG00000018045 ENSPRET00000026955
## 3 KK215283.1 633221 636222 3002 + ENSPREG00000018045 ENSPRET00000026955
## 4 KK215283.1 633221 636222 3002 + ENSPREG00000018045 ENSPRET00000026955
## 5 KK215283.1 633221 636222 3002 + ENSPREG00000018045 ENSPRET00000026955
## 6 KK215283.1 633221 636222 3002 + ENSPREG00000018045 ENSPRET00000026955
## V7
## 1 uncharacterised
## 2 uncharacterised
## 3 uncharacterised
## 4 uncharacterised
## 5 uncharacterised
## 6 uncharacterisedCvGpromotersdf <- cbind(CvGpromotersdf,myPromotersoldf1[c("V5","V6","V7")])
CvGpromotersdf$seqnames <- as.character(CvGpromotersdf$seqnames)
head(CvGpromotersdf)## seqnames start end width strand pvalue qvalue meth.diff
## 1 KK215283.1 633237 633237 1 + 0.9344420 0.9891325 0.4273504
## 2 KK215283.1 633238 633238 1 + 0.1127477 0.8349844 8.7313816
## 3 KK215283.1 633265 633265 1 + 0.4856043 0.9645942 4.1184041
## 4 KK215283.1 633266 633266 1 + 0.7831542 0.9891325 -1.5931373
## 5 KK215283.1 633284 633284 1 + 0.2701086 0.8988020 5.5440055
## 6 KK215283.1 633285 633285 1 + 0.8564265 0.9891325 -0.7741935
## V5 V6 V7
## 1 ENSPREG00000018045 ENSPRET00000026955 uncharacterised
## 2 ENSPREG00000018045 ENSPRET00000026955 uncharacterised
## 3 ENSPREG00000018045 ENSPRET00000026955 uncharacterised
## 4 ENSPREG00000018045 ENSPRET00000026955 uncharacterised
## 5 ENSPREG00000018045 ENSPRET00000026955 uncharacterised
## 6 ENSPREG00000018045 ENSPRET00000026955 uncharacterisedCvGpromoterschrdf <- CvGpromotersdf[grep("LG",CvGpromotersdf$seqnames),]
head(CvGpromoterschrdf)## seqnames start end width strand pvalue qvalue meth.diff
## 93877 LG1 369385 369385 1 + 0.0843110 0.8066566 18.873518
## 93878 LG1 369386 369386 1 + 0.6561446 0.9891325 -4.830054
## 93879 LG1 369399 369399 1 + 0.4224427 0.9422793 8.586957
## 93880 LG1 369400 369400 1 + 0.4244279 0.9430309 7.926829
## 93881 LG1 369413 369413 1 + 0.6150454 0.9891325 5.043860
## 93882 LG1 369414 369414 1 + 0.1803816 0.8652707 11.672474
## V5 V6 V7
## 93877 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 93878 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 93879 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 93880 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 93881 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 93882 ENSPREG00000000039 ENSPRET00000000039 uncharacterisedCvGpromoterschrdf <- CvGpromoterschrdf[order(CvGpromoterschrdf[,7]), ]
colnames(CvGpromoterschrdf) <- c("seqnames","start","end","width","strand","pvalue","qvalue","meth.diff","gene_id","V6","gene_name")
CvGpromoterschrdf <- CvGpromoterschrdf[which(rownames(CvGpromoterschrdf)%in%rownames(unique(CvGpromoterschrdf[,1:2]))),]
head(CvGpromoterschrdf,50)## seqnames start end width strand pvalue qvalue
## 1195612 LG4 1847635 1847635 1 + 1.510121e-15 2.819262e-08
## 1195618 LG4 1847677 1847677 1 + 6.272684e-15 5.855272e-08
## 1195545 LG4 1846766 1846766 1 + 9.610321e-15 5.980539e-08
## 1195547 LG4 1846768 1846768 1 + 1.055213e-13 4.924975e-07
## 1195622 LG4 1847679 1847679 1 + 3.361816e-13 1.046036e-06
## 1195626 LG4 1847691 1847691 1 + 3.317211e-13 1.046036e-06
## 1195544 LG4 1846756 1846756 1 + 6.059313e-13 1.616029e-06
## 1195543 LG4 1846735 1846735 1 + 8.313745e-13 1.940128e-06
## 1195630 LG4 1847697 1847697 1 + 1.443677e-12 2.994685e-06
## 1195541 LG4 1846719 1846719 1 + 4.063471e-12 7.586140e-06
## 485962 LG14 17323571 17323571 1 + 6.150734e-08 8.832981e-02
## 600941 LG16 15182433 15182433 1 + 7.754818e-08 9.651705e-02
## 962180 LG20 21573163 21573163 1 + 1.890608e-07 1.529661e-01
## 1195616 LG4 1847655 1847655 1 + 2.377406e-07 1.564207e-01
## 1195620 LG4 1847678 1847678 1 + 6.976986e-07 2.967143e-01
## 1195614 LG4 1847636 1847636 1 + 1.148523e-06 3.488688e-01
## 1583403 LG8 26880460 26880460 1 + 1.916161e-06 4.769736e-01
## 845194 LG2 11354568 11354568 1 + 2.320259e-06 5.223176e-01
## 136091 LG1 17853600 17853600 1 + 4.121108e-06 5.888062e-01
## 1195628 LG4 1847692 1847692 1 + 4.516855e-06 5.888062e-01
## 317056 LG12 3488095 3488095 1 + 6.690908e-06 6.342275e-01
## 1564448 LG8 20759106 20759106 1 + 7.206294e-06 6.408805e-01
## 368411 LG13 1532265 1532265 1 + 7.661041e-06 6.422231e-01
## 1238788 LG4 20706584 20706584 1 + 8.290472e-06 6.422231e-01
## 1435244 LG7 6992653 6992653 1 + 1.006727e-05 6.735709e-01
## 204446 LG10 14353882 14353882 1 + 1.054948e-05 6.814857e-01
## 1195632 LG4 1847698 1847698 1 + 1.107826e-05 6.917098e-01
## 688184 LG17 21982657 21982657 1 + 1.261074e-05 7.116205e-01
## 830537 LG2 5125770 5125770 1 + 1.221175e-05 7.116205e-01
## 432611 LG13 32841388 32841388 1 + 1.601680e-05 7.277638e-01
## 485974 LG14 17323597 17323597 1 + 2.028140e-05 7.277638e-01
## 755045 LG19 1222458 1222458 1 + 1.519734e-05 7.277638e-01
## 821107 LG2 1369466 1369466 1 + 1.967878e-05 7.277638e-01
## 844601 LG2 11010380 11010380 1 + 1.484600e-05 7.277638e-01
## 1437551 LG7 9986254 9986254 1 + 1.686997e-05 7.277638e-01
## 1542716 LG8 14731191 14731191 1 + 2.144140e-05 7.277638e-01
## 1545960 LG8 15544450 15544450 1 + 2.006623e-05 7.277638e-01
## 1637819 LG9 23793928 23793928 1 + 2.069270e-05 7.277638e-01
## 94045 LG1 696084 696084 1 + 1.727733e-03 7.545325e-01
## 94071 LG1 696637 696637 1 + 7.417733e-04 7.545325e-01
## 94346 LG1 752107 752107 1 + 1.436807e-02 7.545325e-01
## 94517 LG1 883237 883237 1 + 8.831533e-03 7.545325e-01
## 94628 LG1 1213760 1213760 1 + 7.077961e-05 7.545325e-01
## 94635 LG1 1214091 1214091 1 + 6.661627e-03 7.545325e-01
## 94792 LG1 1224456 1224456 1 + 1.214504e-02 7.545325e-01
## 94804 LG1 1224976 1224976 1 + 1.621581e-02 7.545325e-01
## 94849 LG1 1237438 1237438 1 + 1.709452e-02 7.545325e-01
## 94921 LG1 1239019 1239019 1 + 6.745152e-03 7.545325e-01
## 95028 LG1 1247140 1247140 1 + 8.664613e-03 7.545325e-01
## 95046 LG1 1247692 1247692 1 + 9.691319e-03 7.545325e-01
## meth.diff gene_id V6 gene_name
## 1195612 69.49153 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1195618 71.81818 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1195545 73.61963 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1195547 67.64706 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1195622 69.15584 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1195626 65.26210 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1195544 62.43094 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1195543 59.77654 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1195630 65.58559 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1195541 60.12658 ENSPREG00000021490 ENSPRET00000032090 nasp
## 485962 50.00000 ENSPREG00000008650 ENSPRET00000012952 spns3
## 600941 -55.77342 ENSPREG00000016960 ENSPRET00000025381 she
## 962180 59.31174 ENSPREG00000005440 ENSPRET00000008381 puf60a
## 1195616 44.59459 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1195620 39.28571 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1195614 40.54054 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1583403 -53.21477 ENSPREG00000011178 ENSPRET00000016682 mfsd11
## 845194 55.27728 ENSPREG00000018586 ENSPRET00000027774 uncharacterised
## 136091 -63.33938 ENSPREG00000004513 ENSPRET00000006633 tspan5b
## 1195628 35.29412 ENSPREG00000021490 ENSPRET00000032090 nasp
## 317056 -51.19048 ENSPREG00000017256 ENSPRET00000025812 uncharacterised
## 1564448 31.66667 ENSPREG00000013978 ENSPRET00000020876 dhrs7b
## 368411 -46.74487 ENSPREG00000008623 ENSPRET00000012828 p4ha3
## 1238788 57.30706 ENSPREG00000000806 ENSPRET00000001120 uncharacterised
## 1435244 40.47619 ENSPREG00000010927 ENSPRET00000016341 tti1
## 204446 45.71429 ENSPREG00000008747 ENSPRET00000013011 prss23
## 1195632 34.48276 ENSPREG00000021490 ENSPRET00000032090 nasp
## 688184 -38.00000 ENSPREG00000009730 ENSPRET00000014960 uncharacterised
## 830537 37.83784 ENSPREG00000011543 ENSPRET00000017240 PTK2B
## 432611 47.05882 ENSPREG00000021706 ENSPRET00000032408 DGKD
## 485974 41.09731 ENSPREG00000008650 ENSPRET00000012952 spns3
## 755045 42.72014 ENSPREG00000017574 ENSPRET00000026325 zgc:91999
## 821107 41.72043 ENSPREG00000007735 ENSPRET00000011469 uncharacterised
## 844601 34.28571 ENSPREG00000018377 ENSPRET00000027472 uncharacterised
## 1437551 28.57790 ENSPREG00000013504 ENSPRET00000020162 casp9
## 1542716 -49.44179 ENSPREG00000006743 ENSPRET00000010021 uncharacterised
## 1545960 -50.25862 ENSPREG00000008074 ENSPRET00000012013 kdm8
## 1637819 -30.18868 ENSPREG00000003558 ENSPRET00000005239 polk
## 94045 -22.22222 ENSPREG00000000042 ENSPRET00000000042 uncharacterised
## 94071 -23.25581 ENSPREG00000000042 ENSPRET00000000042 uncharacterised
## 94346 22.06439 ENSPREG00000000046 ENSPRET00000000047 foxk1
## 94517 -12.50000 ENSPREG00000000052 ENSPRET00000000055 uncharacterised
## 94628 -32.55814 ENSPREG00000000054 ENSPRET00000000059 uncharacterised
## 94635 35.00000 ENSPREG00000000054 ENSPRET00000000059 uncharacterised
## 94792 -15.51940 ENSPREG00000000055 ENSPRET00000000060 alkbh5
## 94804 -10.34483 ENSPREG00000000055 ENSPRET00000000060 alkbh5
## 94849 -10.00000 ENSPREG00000000056 ENSPRET00000000061 mief2
## 94921 16.66667 ENSPREG00000000056 ENSPRET00000000061 mief2
## 95028 16.66667 ENSPREG00000000057 ENSPRET00000000062 uncharacterised
## 95046 15.15152 ENSPREG00000000057 ENSPRET00000000062 uncharacterisedrm(CvGpromoters)
rm(CvGpromotersdf)ol1 <- findOverlaps(methylkitCvLGR,my_Promoters)## Warning in .Seqinfo.mergexy(x, y): Each of the 2 combined objects has sequence levels not in the other:
## - in 'x': KK215332.1, KK215339.1, KK215341.1, KK215351.1, KK215360.1, KK215378.1, KK215383.1, KK215387.1, KK215388.1, KK215391.1, KK215393.1, KK215395.1, KK215396.1, KK215397.1, KK215400.1, KK215401.1, KK215402.1, KK215403.1, KK215405.1, KK215406.1, KK215407.1, KK215408.1, KK215411.1, KK215412.1, KK215414.1, KK215415.1, KK215418.1, KK215419.1, KK215420.1, KK215421.1, KK215424.1, KK215425.1, KK215427.1, KK215429.1, KK215430.1, KK215432.1, KK215433.1, KK215435.1, KK215439.1, KK215440.1, KK215441.1, KK215443.1, KK215444.1, KK215446.1, KK215448.1, KK215451.1, KK215453.1, KK215454.1, KK215455.1, KK215456.1, KK215459.1, KK215462.1, KK215463.1, KK215465.1, KK215466.1, KK215467.1, KK215472.1, KK215474.1, KK215475.1, KK215479.1, KK215480.1, KK215482.1, KK215484.1, KK215485.1, KK215486.1, KK215488.1, KK215489.1, KK215490.1, KK215491.1, KK215492.1, KK215494.1, KK215496.1, KK215497.1, KK215498.1, KK215501.1, KK215502.1, KK215503.1, KK215504.1, KK215506.1, KK215507.1, KK215508.1, KK215511.1, KK215512.1, KK215513.1, KK215514.1, KK215515.1, KK215516.1, KK215517.1, KK215518.1, KK215519.1, KK215521.1, KK215523.1, KK215524.1, KK215525.1, KK215526.1, KK215528.1, KK215529.1, KK215530.1, KK215531.1, KK215533.1, KK215538.1, KK215540.1, KK215541.1, KK215543.1, KK215544.1, KK215545.1, KK215546.1, KK215547.1, KK215548.1, KK215549.1, KK215551.1, KK215553.1, KK215554.1, KK215556.1, KK215558.1, KK215559.1, KK215560.1, KK215561.1, KK215562.1, KK215564.1, KK215567.1, KK215568.1, KK215573.1, KK215574.1, KK215577.1, KK215578.1, KK215579.1, KK215581.1, KK215582.1, KK215583.1, KK215584.1, KK215585.1, KK215586.1, KK215587.1, KK215588.1, KK215589.1, KK215590.1, KK215594.1, KK215595.1, KK215597.1, KK215598.1, KK215601.1, KK215602.1, KK215603.1, KK215605.1, KK215606.1, KK215608.1, KK215615.1, KK215616.1, KK215620.1, KK215621.1, KK215622.1, KK215624.1, KK215625.1, KK215626.1, KK215627.1, KK215628.1, KK215629.1, KK215630.1, KK215632.1, KK215633.1, KK215634.1, KK215635.1, KK215636.1, KK215637.1, KK215638.1, KK215639.1, KK215641.1, KK215642.1, KK215644.1, KK215645.1, KK215646.1, KK215647.1, KK215649.1, KK215652.1, KK215654.1, KK215655.1, KK215657.1, KK215658.1, KK215661.1, KK215662.1, KK215663.1, KK215664.1, KK215665.1, KK215668.1, KK215669.1, KK215670.1, KK215671.1, KK215672.1, KK215673.1, KK215675.1, KK215677.1, KK215678.1, KK215683.1, KK215684.1, KK215688.1, KK215689.1, KK215692.1, KK215694.1, KK215695.1, KK215699.1, KK215700.1, KK215701.1, KK215703.1, KK215704.1, KK215705.1, KK215706.1, KK215707.1, KK215709.1, KK215710.1, KK215711.1, KK215712.1, KK215715.1, KK215718.1, KK215719.1, KK215720.1, KK215721.1, KK215722.1, KK215723.1, KK215724.1, KK215726.1, KK215727.1, KK215728.1, KK215733.1, KK215734.1, KK215736.1, KK215737.1, KK215738.1, KK215739.1, KK215740.1, KK215741.1, KK215742.1, KK215743.1, KK215745.1, KK215748.1, KK215750.1, KK215752.1, KK215753.1, KK215754.1, KK215755.1, KK215756.1, KK215757.1, KK215758.1, KK215759.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215766.1, KK215767.1, KK215768.1, KK215769.1, KK215770.1, KK215771.1, KK215772.1, KK215774.1, KK215775.1, KK215776.1, KK215777.1, KK215778.1, KK215779.1, KK215780.1, KK215782.1, KK215783.1, KK215785.1, KK215786.1, KK215788.1, KK215789.1, KK215792.1, KK215794.1, KK215795.1, KK215796.1, KK215797.1, KK215798.1, KK215802.1, KK215804.1, KK215805.1, KK215807.1, KK215810.1, KK215812.1, KK215814.1, KK215815.1, KK215816.1, KK215818.1, KK215819.1, KK215821.1, KK215825.1, KK215827.1, KK215832.1, KK215834.1, KK215836.1, KK215837.1, KK215838.1, KK215839.1, KK215840.1, KK215841.1, KK215842.1, KK215843.1, KK215846.1, KK215847.1, KK215848.1, KK215849.1, KK215851.1, KK215852.1, KK215854.1, KK215857.1, KK215858.1, KK215859.1, KK215860.1, KK215861.1, KK215863.1, KK215864.1, KK215865.1, KK215866.1, KK215867.1, KK215869.1, KK215870.1, KK215872.1, KK215873.1, KK215875.1, KK215877.1, KK215878.1, KK215880.1, KK215881.1, KK215882.1, KK215884.1, KK215885.1, KK215886.1, KK215890.1, KK215891.1, KK215892.1, KK215893.1, KK215894.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215902.1, KK215903.1, KK215905.1, KK215907.1, KK215908.1, KK215909.1, KK215910.1, KK215911.1, KK215913.1, KK215914.1, KK215915.1, KK215917.1, KK215918.1, KK215920.1, KK215921.1, KK215922.1, KK215923.1, KK215924.1, KK215927.1, KK215928.1, KK215929.1, KK215930.1, KK215933.1, KK215934.1, KK215935.1, KK215937.1, KK215938.1, KK215940.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215946.1, KK215949.1, KK215951.1, KK215952.1, KK215953.1, KK215956.1, KK215957.1, KK215958.1, KK215960.1, KK215962.1, KK215963.1, KK215965.1, KK215967.1, KK215969.1, KK215970.1, KK215971.1, KK215972.1, KK215973.1, KK215974.1, KK215975.1, KK215976.1, KK215977.1, KK215978.1, KK215979.1, KK215982.1, KK215983.1, KK215984.1, KK215985.1, KK215986.1, KK215987.1, KK215989.1, KK215990.1, KK215993.1, KK215994.1, KK215995.1, KK215996.1, KK215997.1, KK215999.1, KK216000.1, KK216001.1, KK216005.1, KK216006.1, KK216007.1, KK216008.1, KK216009.1, KK216011.1, KK216012.1, KK216015.1, KK216016.1, KK216017.1, KK216018.1, KK216021.1, KK216022.1, KK216023.1, KK216024.1, KK216025.1, KK216026.1, KK216027.1, KK216028.1, KK216029.1, KK216030.1, KK216032.1, KK216033.1, KK216034.1, KK216035.1, KK216036.1, KK216037.1, KK216038.1, KK216039.1, KK216040.1, KK216041.1, KK216042.1, KK216043.1, KK216044.1, KK216047.1, KK216048.1, KK216049.1, KK216050.1, KK216053.1, KK216055.1, KK216056.1, KK216058.1, KK216059.1, KK216062.1, KK216063.1, KK216064.1, KK216065.1, KK216066.1, KK216067.1, KK216068.1, KK216069.1, KK216070.1, KK216071.1, KK216072.1, KK216073.1, KK216074.1, KK216075.1, KK216076.1, KK216077.1, KK216078.1, KK216079.1, KK216080.1, KK216082.1, KK216083.1, KK216084.1, KK216085.1, KK216086.1, KK216087.1, KK216089.1, KK216091.1, KK216093.1, KK216094.1, KK216095.1, KK216096.1, KK216097.1, KK216098.1, KK216099.1, KK216102.1, KK216103.1, KK216106.1, KK216109.1, KK216110.1, KK216111.1, KK216112.1, KK216113.1, KK216114.1, KK216115.1, KK216117.1, KK216118.1, KK216120.1, KK216122.1, KK216124.1, KK216125.1, KK216126.1, KK216127.1, KK216128.1, KK216131.1, KK216133.1, KK216134.1, KK216135.1, KK216137.1, KK216138.1, KK216140.1, KK216141.1, KK216142.1, KK216143.1, KK216144.1, KK216145.1, KK216146.1, KK216150.1, KK216151.1, KK216152.1, KK216154.1, KK216155.1, KK216157.1, KK216158.1, KK216159.1, KK216160.1, KK216162.1, KK216163.1, KK216164.1, KK216165.1, KK216166.1, KK216168.1, KK216169.1, KK216171.1, KK216172.1, KK216173.1, KK216174.1, KK216175.1, KK216176.1, KK216177.1, KK216178.1, KK216180.1, KK216181.1, KK216182.1, KK216184.1, KK216186.1, KK216190.1, KK216192.1, KK216193.1, KK216194.1, KK216195.1, KK216196.1, KK216197.1, KK216198.1, KK216200.1, KK216201.1, KK216202.1, KK216203.1, KK216205.1, KK216206.1, KK216208.1, KK216212.1, KK216213.1, KK216214.1, KK216215.1, KK216217.1, KK216218.1, KK216219.1, KK216221.1, KK216222.1, KK216224.1, KK216225.1, KK216226.1, KK216227.1, KK216229.1, KK216231.1, KK216232.1, KK216234.1, KK216235.1, KK216236.1, KK216237.1, KK216238.1, KK216240.1, KK216241.1, KK216242.1, KK216243.1, KK216244.1, KK216245.1, KK216248.1, KK216251.1, KK216252.1, KK216253.1, KK216254.1, KK216256.1, KK216258.1, KK216259.1, KK216260.1, KK216261.1, KK216262.1, KK216263.1, KK216264.1, KK216265.1, KK216266.1, KK216267.1, KK216269.1, KK216270.1, KK216271.1, KK216272.1, KK216273.1, KK216274.1, KK216275.1, KK216276.1, KK216278.1, KK216280.1, KK216281.1, KK216282.1, KK216283.1, KK216284.1, KK216285.1, KK216287.1, KK216288.1, KK216289.1, KK216290.1, KK216291.1, KK216292.1, KK216293.1, KK216295.1, KK216296.1, KK216297.1, KK216298.1, KK216299.1, KK216302.1, KK216303.1, KK216304.1, KK216306.1, KK216307.1, KK216308.1, KK216310.1, KK216311.1, KK216313.1, KK216315.1, KK216316.1, KK216317.1, KK216318.1, KK216319.1, KK216320.1, KK216321.1, KK216322.1, KK216323.1, KK216324.1, KK216325.1, KK216326.1, KK216327.1, KK216328.1, KK216329.1, KK216330.1, KK216331.1, KK216333.1, KK216334.1, KK216335.1, KK216336.1, KK216337.1, KK216338.1, KK216340.1, KK216341.1, KK216342.1, KK216343.1, KK216344.1, KK216345.1, KK216346.1, KK216347.1, KK216349.1, KK216351.1, KK216353.1, KK216354.ol1## Hits object with 1631000 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 24522 16047
## [2] 24523 16047
## [3] 24524 16047
## [4] 24525 16047
## [5] 24526 16047
## ... ... ...
## [1630996] 18470300 2480
## [1630997] 18470301 2479
## [1630998] 18470301 2480
## [1630999] 18470302 2479
## [1631000] 18470302 2480
## -------
## queryLength: 18477943 / subjectLength: 34314CvLpromoters <- methylkitCvLGR[queryHits(ol1)]
myPromotersol1 <- my_Promoters[subjectHits(ol1)]
head(CvLpromoters)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | pvalue qvalue meth.diff
## <Rle> <IRanges> <Rle> | <numeric> <numeric> <numeric>
## [1] KK215283.1 633237 + | 0.622135 0.986634 2.43056
## [2] KK215283.1 633238 + | 0.330647 0.896332 6.56566
## [3] KK215283.1 633265 + | 0.507152 0.968974 3.96825
## [4] KK215283.1 633266 + | 0.310117 0.888074 -7.26351
## [5] KK215283.1 633284 + | 0.333664 0.898537 5.16693
## [6] KK215283.1 633285 + | 0.366374 0.913127 -5.10753
## -------
## seqinfo: 2441 sequences from an unspecified genome; no seqlengthsmyPromotersol1## GRanges object with 1631000 ranges and 3 metadata columns:
## seqnames ranges strand | V5
## <Rle> <IRanges> <Rle> | <character>
## [1] KK215283.1 633221-636222 + | ENSPREG00000018045
## [2] KK215283.1 633221-636222 + | ENSPREG00000018045
## [3] KK215283.1 633221-636222 + | ENSPREG00000018045
## [4] KK215283.1 633221-636222 + | ENSPREG00000018045
## [5] KK215283.1 633221-636222 + | ENSPREG00000018045
## ... ... ... ... . ...
## [1630996] LG9 34072750-34075751 + | ENSPREG00000019083
## [1630997] LG9 34072714-34075715 + | ENSPREG00000019083
## [1630998] LG9 34072750-34075751 + | ENSPREG00000019083
## [1630999] LG9 34072714-34075715 + | ENSPREG00000019083
## [1631000] LG9 34072750-34075751 + | ENSPREG00000019083
## V6 V7
## <character> <character>
## [1] ENSPRET00000026955 uncharacterised
## [2] ENSPRET00000026955 uncharacterised
## [3] ENSPRET00000026955 uncharacterised
## [4] ENSPRET00000026955 uncharacterised
## [5] ENSPRET00000026955 uncharacterised
## ... ... ...
## [1630996] ENSPRET00000028582 adamtsl2
## [1630997] ENSPRET00000028533 adamtsl2
## [1630998] ENSPRET00000028582 adamtsl2
## [1630999] ENSPRET00000028533 adamtsl2
## [1631000] ENSPRET00000028582 adamtsl2
## -------
## seqinfo: 452 sequences from an unspecified genome; no seqlengthsCvLpromotersdf <- as.data.frame(CvLpromoters,row.names = 1:nrow(as.data.frame(ranges(CvLpromoters))))
str(CvLpromotersdf)## 'data.frame': 1631000 obs. of 8 variables:
## $ seqnames : Factor w/ 2441 levels "KK215283.1","KK215284.1",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ start : int 633237 633238 633265 633266 633284 633285 633309 633310 633320 633321 ...
## $ end : int 633237 633238 633265 633266 633284 633285 633309 633310 633320 633321 ...
## $ width : int 1 1 1 1 1 1 1 1 1 1 ...
## $ strand : Factor w/ 3 levels "+","-","*": 1 1 1 1 1 1 1 1 1 1 ...
## $ pvalue : num 0.622 0.331 0.507 0.31 0.334 ...
## $ qvalue : num 0.987 0.896 0.969 0.888 0.899 ...
## $ meth.diff: num 2.43 6.57 3.97 -7.26 5.17 ...myPromotersoldf1 <- as.data.frame(myPromotersol1,row.names = 1:nrow(as.data.frame(ranges(myPromotersol1))))
head(myPromotersoldf1)## seqnames start end width strand V5 V6
## 1 KK215283.1 633221 636222 3002 + ENSPREG00000018045 ENSPRET00000026955
## 2 KK215283.1 633221 636222 3002 + ENSPREG00000018045 ENSPRET00000026955
## 3 KK215283.1 633221 636222 3002 + ENSPREG00000018045 ENSPRET00000026955
## 4 KK215283.1 633221 636222 3002 + ENSPREG00000018045 ENSPRET00000026955
## 5 KK215283.1 633221 636222 3002 + ENSPREG00000018045 ENSPRET00000026955
## 6 KK215283.1 633221 636222 3002 + ENSPREG00000018045 ENSPRET00000026955
## V7
## 1 uncharacterised
## 2 uncharacterised
## 3 uncharacterised
## 4 uncharacterised
## 5 uncharacterised
## 6 uncharacterisedCvLpromotersdf <- cbind(CvLpromotersdf,myPromotersoldf1[c("V5","V6","V7")])
CvLpromotersdf$seqnames <- as.character(CvLpromotersdf$seqnames)
head(CvLpromotersdf)## seqnames start end width strand pvalue qvalue meth.diff
## 1 KK215283.1 633237 633237 1 + 0.6221346 0.9866335 2.430556
## 2 KK215283.1 633238 633238 1 + 0.3306467 0.8963317 6.565657
## 3 KK215283.1 633265 633265 1 + 0.5071523 0.9689742 3.968254
## 4 KK215283.1 633266 633266 1 + 0.3101171 0.8880741 -7.263514
## 5 KK215283.1 633284 633284 1 + 0.3336643 0.8985366 5.166932
## 6 KK215283.1 633285 633285 1 + 0.3663740 0.9131273 -5.107527
## V5 V6 V7
## 1 ENSPREG00000018045 ENSPRET00000026955 uncharacterised
## 2 ENSPREG00000018045 ENSPRET00000026955 uncharacterised
## 3 ENSPREG00000018045 ENSPRET00000026955 uncharacterised
## 4 ENSPREG00000018045 ENSPRET00000026955 uncharacterised
## 5 ENSPREG00000018045 ENSPRET00000026955 uncharacterised
## 6 ENSPREG00000018045 ENSPRET00000026955 uncharacterisedCvLpromoterschrdf <- CvLpromotersdf[grep("LG",CvLpromotersdf$seqnames),]
head(CvLpromoterschrdf)## seqnames start end width strand pvalue qvalue meth.diff
## 92163 LG1 369385 369385 1 + 0.2025557 0.8774727 15.4277700
## 92164 LG1 369386 369386 1 + 0.7724517 0.9866335 -3.1135531
## 92165 LG1 369399 369399 1 + 0.9273233 0.9866335 1.0869565
## 92166 LG1 369400 369400 1 + 0.9500893 0.9866335 0.6756757
## 92167 LG1 369413 369413 1 + 0.5794793 0.9866335 5.6818182
## 92168 LG1 369414 369414 1 + 0.7232382 0.9866335 3.4798535
## V5 V6 V7
## 92163 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 92164 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 92165 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 92166 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 92167 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 92168 ENSPREG00000000039 ENSPRET00000000039 uncharacterisedCvLpromoterschrdf <- CvLpromoterschrdf[order(CvLpromoterschrdf[,7]), ]
colnames(CvLpromoterschrdf) <- c("seqnames","start","end","width","strand","pvalue","qvalue","meth.diff","gene_id","V6","gene_name")
head(CvLpromoterschrdf,50)## seqnames start end width strand pvalue qvalue
## 804720 LG2 449260 449260 1 + 1.316960e-06 0.5043399
## 910884 LG20 421215 421215 1 + 6.352613e-07 0.5043399
## 1371208 LG6 24055348 24055348 1 + 1.261452e-06 0.5043399
## 818069 LG2 5310879 5310879 1 + 2.756394e-06 0.5646001
## 1568297 LG9 3178904 3178904 1 + 2.976812e-06 0.5646001
## 543482 LG15 26659727 26659727 1 + 3.680161e-06 0.5846745
## 543483 LG15 26659727 26659727 1 + 3.680161e-06 0.5846745
## 705655 LG18 6177030 6177030 1 + 4.198931e-06 0.5901297
## 1448486 LG7 23175036 23175036 1 + 5.187829e-06 0.5901297
## 1448487 LG7 23175036 23175036 1 + 5.187829e-06 0.5901297
## 1451938 LG7 25501799 25501799 1 + 5.282784e-06 0.5901297
## 1568293 LG9 3178894 3178894 1 + 5.458773e-06 0.5923730
## 1447911 LG7 22753449 22753449 1 + 5.654246e-06 0.5976734
## 485163 LG14 20779298 20779298 1 + 5.849763e-06 0.6059476
## 485164 LG14 20779298 20779298 1 + 5.849763e-06 0.6059476
## 177771 LG10 2599446 2599446 1 + 6.004599e-06 0.6081644
## 649970 LG17 6520124 6520124 1 + 7.433117e-06 0.6542794
## 649971 LG17 6520124 6520124 1 + 7.433117e-06 0.6542794
## 260620 LG11 12149141 12149141 1 + 1.025767e-05 0.6938669
## 260621 LG11 12149141 12149141 1 + 1.025767e-05 0.6938669
## 354092 LG12 24573345 24573345 1 + 1.070998e-05 0.7011907
## 703584 LG18 5690164 5690164 1 + 1.138136e-05 0.7011907
## 703585 LG18 5690164 5690164 1 + 1.138136e-05 0.7011907
## 742423 LG19 1222458 1222458 1 + 1.090334e-05 0.7011907
## 133653 LG1 17853600 17853600 1 + 1.323290e-05 0.7234779
## 724039 LG18 15684050 15684050 1 + 1.387912e-05 0.7270967
## 367353 LG13 4420126 4420126 1 + 1.447854e-05 0.7352582
## 367354 LG13 4420126 4420126 1 + 1.447854e-05 0.7352582
## 742003 LG19 1060528 1060528 1 + 1.591650e-05 0.7472693
## 804494 LG2 305116 305116 1 + 1.561378e-05 0.7472693
## 157125 LG1 29004553 29004553 1 + 2.344182e-05 0.7473102
## 201087 LG10 14406455 14406455 1 + 2.763668e-05 0.7473102
## 265317 LG11 14183622 14183622 1 + 3.020689e-05 0.7473102
## 480813 LG14 18600272 18600272 1 + 1.872631e-05 0.7473102
## 480814 LG14 18600272 18600272 1 + 1.872631e-05 0.7473102
## 495122 LG15 119173 119173 1 + 2.160155e-05 0.7473102
## 495123 LG15 119173 119173 1 + 2.160155e-05 0.7473102
## 681516 LG17 24589266 24589266 1 + 2.049828e-05 0.7473102
## 681517 LG17 24589266 24589266 1 + 2.049828e-05 0.7473102
## 690050 LG17 29792771 29792771 1 + 1.757258e-05 0.7473102
## 742004 LG19 1060540 1060540 1 + 2.167355e-05 0.7473102
## 794040 LG19 22789191 22789191 1 + 2.389124e-05 0.7473102
## 815788 LG2 4760872 4760872 1 + 2.604043e-05 0.7473102
## 815789 LG2 4760872 4760872 1 + 2.604043e-05 0.7473102
## 826231 LG2 7555076 7555076 1 + 2.483979e-05 0.7473102
## 827721 LG2 9180454 9180454 1 + 2.363310e-05 0.7473102
## 837557 LG2 14484697 14484697 1 + 2.721522e-05 0.7473102
## 837558 LG2 14484697 14484697 1 + 2.721522e-05 0.7473102
## 1149116 LG3 20251003 20251003 1 + 2.545591e-05 0.7473102
## 1251898 LG5 1685836 1685836 1 + 2.087340e-05 0.7473102
## meth.diff gene_id V6 gene_name
## 804720 -62.37037 ENSPREG00000006354 ENSPRET00000009478 zgc:152904
## 910884 56.98925 ENSPREG00000005117 ENSPRET00000007531 uncharacterised
## 1371208 53.33333 ENSPREG00000008036 ENSPRET00000011957 kti12
## 818069 56.09244 ENSPREG00000012054 ENSPRET00000018003 uncharacterised
## 1568297 -44.82759 ENSPREG00000016442 ENSPRET00000024613 adora2aa
## 543482 -45.45455 ENSPREG00000009249 ENSPRET00000013903 ATE1
## 543483 -45.45455 ENSPREG00000009249 ENSPRET00000013936 ATE1
## 705655 43.33333 ENSPREG00000006766 ENSPRET00000010053 uncharacterised
## 1448486 45.00000 ENSPREG00000017615 ENSPRET00000026315 gid8b
## 1448487 45.00000 ENSPREG00000017615 ENSPRET00000026315 gid8b
## 1451938 -35.29412 ENSPREG00000019654 ENSPRET00000029385 uncharacterised
## 1568293 -43.33333 ENSPREG00000016442 ENSPRET00000024613 adora2aa
## 1447911 -51.98413 ENSPREG00000017242 ENSPRET00000025819 DCAF1
## 485163 57.89474 ENSPREG00000012582 ENSPRET00000018803 pknox2
## 485164 57.89474 ENSPREG00000012582 ENSPRET00000018803 pknox2
## 177771 -53.81773 ENSPREG00000020058 ENSPRET00000030011 ablim3
## 649970 -48.62605 ENSPREG00000007978 ENSPRET00000011850 rpap2
## 649971 -48.62605 ENSPREG00000007978 ENSPRET00000011850 rpap2
## 260620 42.85714 ENSPREG00000004250 ENSPRET00000006180 sla1a
## 260621 42.85714 ENSPREG00000004250 ENSPRET00000006180 sla1a
## 354092 -47.45098 ENSPREG00000000874 ENSPRET00000001187 lpar1
## 703584 50.00000 ENSPREG00000005936 ENSPRET00000008808 arhgap36
## 703585 50.00000 ENSPREG00000005936 ENSPRET00000008877 arhgap36
## 742423 43.99642 ENSPREG00000017574 ENSPRET00000026325 zgc:91999
## 133653 -60.35088 ENSPREG00000004513 ENSPRET00000006633 tspan5b
## 724039 44.00000 ENSPREG00000018440 ENSPRET00000028079 PTPRD
## 367353 -52.61628 ENSPREG00000011322 ENSPRET00000016995 uncharacterised
## 367354 -52.61628 ENSPREG00000011322 ENSPRET00000016995 uncharacterised
## 742003 -41.41414 ENSPREG00000017430 ENSPRET00000026071 luc7l
## 804494 -52.41313 ENSPREG00000006354 ENSPRET00000009453 zgc:152904
## 157125 -32.43243 ENSPREG00000022787 ENSPRET00000034002 rrp36
## 201087 -36.36364 ENSPREG00000008829 ENSPRET00000013128 fosl1a
## 265317 -41.66667 ENSPREG00000007449 ENSPRET00000011036 uncharacterised
## 480813 -31.42857 ENSPREG00000009863 ENSPRET00000014721 dgat2
## 480814 -31.42857 ENSPREG00000009863 ENSPRET00000014727 dgat2
## 495122 -45.83333 ENSPREG00000017948 ENSPRET00000026991 uncharacterised
## 495123 -45.83333 ENSPREG00000017948 ENSPRET00000027035 uncharacterised
## 681516 -49.45652 ENSPREG00000013588 ENSPRET00000020304 uncharacterised
## 681517 -49.45652 ENSPREG00000013588 ENSPRET00000020304 uncharacterised
## 690050 -40.63063 ENSPREG00000020395 ENSPRET00000030455 uncharacterised
## 742004 -39.46970 ENSPREG00000017430 ENSPRET00000026071 luc7l
## 794040 61.21212 ENSPREG00000020187 ENSPRET00000030154 itga3b
## 815788 43.90390 ENSPREG00000010838 ENSPRET00000016219 uncharacterised
## 815789 43.90390 ENSPREG00000010838 ENSPRET00000016219 uncharacterised
## 826231 49.03846 ENSPREG00000015607 ENSPRET00000023363 DPP10
## 827721 -39.13043 ENSPREG00000017043 ENSPRET00000025489 igfbp5a
## 837557 30.00000 ENSPREG00000003743 ENSPRET00000005551 uncharacterised
## 837558 30.00000 ENSPREG00000003743 ENSPRET00000005565 uncharacterised
## 1149116 -37.03704 ENSPREG00000001699 ENSPRET00000002394 calb2b
## 1251898 -29.62963 ENSPREG00000022485 ENSPRET00000033558 lsm3rm(CvLpromoters)
rm(CvLpromotersdf)ol1 <- findOverlaps(methylkitGvLGR,my_Promoters)## Warning in .Seqinfo.mergexy(x, y): Each of the 2 combined objects has sequence levels not in the other:
## - in 'x': KK215332.1, KK215339.1, KK215341.1, KK215351.1, KK215360.1, KK215378.1, KK215383.1, KK215387.1, KK215388.1, KK215391.1, KK215393.1, KK215395.1, KK215396.1, KK215397.1, KK215400.1, KK215401.1, KK215402.1, KK215403.1, KK215405.1, KK215406.1, KK215407.1, KK215408.1, KK215411.1, KK215412.1, KK215414.1, KK215415.1, KK215418.1, KK215419.1, KK215420.1, KK215421.1, KK215424.1, KK215425.1, KK215427.1, KK215429.1, KK215430.1, KK215432.1, KK215433.1, KK215435.1, KK215439.1, KK215440.1, KK215441.1, KK215443.1, KK215444.1, KK215446.1, KK215448.1, KK215451.1, KK215453.1, KK215454.1, KK215455.1, KK215456.1, KK215459.1, KK215462.1, KK215463.1, KK215465.1, KK215466.1, KK215467.1, KK215472.1, KK215474.1, KK215475.1, KK215479.1, KK215480.1, KK215482.1, KK215484.1, KK215485.1, KK215486.1, KK215488.1, KK215489.1, KK215490.1, KK215491.1, KK215492.1, KK215494.1, KK215496.1, KK215497.1, KK215498.1, KK215501.1, KK215502.1, KK215503.1, KK215504.1, KK215506.1, KK215507.1, KK215508.1, KK215511.1, KK215512.1, KK215513.1, KK215514.1, KK215515.1, KK215516.1, KK215517.1, KK215518.1, KK215519.1, KK215521.1, KK215523.1, KK215524.1, KK215525.1, KK215526.1, KK215528.1, KK215529.1, KK215530.1, KK215531.1, KK215533.1, KK215538.1, KK215540.1, KK215541.1, KK215543.1, KK215544.1, KK215545.1, KK215546.1, KK215547.1, KK215548.1, KK215549.1, KK215551.1, KK215553.1, KK215554.1, KK215556.1, KK215558.1, KK215559.1, KK215560.1, KK215561.1, KK215562.1, KK215564.1, KK215567.1, KK215568.1, KK215573.1, KK215574.1, KK215577.1, KK215578.1, KK215579.1, KK215581.1, KK215582.1, KK215583.1, KK215584.1, KK215585.1, KK215586.1, KK215587.1, KK215588.1, KK215589.1, KK215590.1, KK215594.1, KK215595.1, KK215597.1, KK215598.1, KK215601.1, KK215602.1, KK215603.1, KK215605.1, KK215606.1, KK215608.1, KK215615.1, KK215616.1, KK215620.1, KK215621.1, KK215622.1, KK215624.1, KK215625.1, KK215626.1, KK215627.1, KK215628.1, KK215629.1, KK215630.1, KK215632.1, KK215633.1, KK215634.1, KK215635.1, KK215636.1, KK215637.1, KK215638.1, KK215639.1, KK215641.1, KK215642.1, KK215644.1, KK215645.1, KK215646.1, KK215647.1, KK215649.1, KK215652.1, KK215654.1, KK215655.1, KK215657.1, KK215658.1, KK215661.1, KK215662.1, KK215663.1, KK215664.1, KK215665.1, KK215668.1, KK215669.1, KK215670.1, KK215671.1, KK215672.1, KK215673.1, KK215675.1, KK215677.1, KK215678.1, KK215683.1, KK215684.1, KK215688.1, KK215689.1, KK215692.1, KK215694.1, KK215695.1, KK215699.1, KK215700.1, KK215701.1, KK215703.1, KK215704.1, KK215705.1, KK215706.1, KK215707.1, KK215709.1, KK215710.1, KK215711.1, KK215712.1, KK215715.1, KK215718.1, KK215719.1, KK215720.1, KK215721.1, KK215722.1, KK215723.1, KK215724.1, KK215726.1, KK215727.1, KK215728.1, KK215733.1, KK215734.1, KK215736.1, KK215737.1, KK215738.1, KK215739.1, KK215740.1, KK215741.1, KK215742.1, KK215743.1, KK215745.1, KK215748.1, KK215750.1, KK215752.1, KK215753.1, KK215754.1, KK215755.1, KK215756.1, KK215757.1, KK215758.1, KK215759.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215766.1, KK215767.1, KK215768.1, KK215769.1, KK215770.1, KK215771.1, KK215772.1, KK215774.1, KK215775.1, KK215776.1, KK215777.1, KK215778.1, KK215779.1, KK215780.1, KK215782.1, KK215783.1, KK215785.1, KK215786.1, KK215788.1, KK215789.1, KK215792.1, KK215794.1, KK215795.1, KK215796.1, KK215797.1, KK215798.1, KK215802.1, KK215804.1, KK215805.1, KK215807.1, KK215810.1, KK215812.1, KK215814.1, KK215815.1, KK215816.1, KK215818.1, KK215819.1, KK215821.1, KK215822.1, KK215825.1, KK215827.1, KK215831.1, KK215832.1, KK215834.1, KK215836.1, KK215837.1, KK215838.1, KK215839.1, KK215840.1, KK215841.1, KK215842.1, KK215843.1, KK215846.1, KK215847.1, KK215848.1, KK215849.1, KK215851.1, KK215852.1, KK215854.1, KK215857.1, KK215858.1, KK215859.1, KK215860.1, KK215861.1, KK215863.1, KK215864.1, KK215865.1, KK215866.1, KK215867.1, KK215869.1, KK215870.1, KK215872.1, KK215873.1, KK215874.1, KK215875.1, KK215877.1, KK215878.1, KK215880.1, KK215881.1, KK215882.1, KK215884.1, KK215885.1, KK215886.1, KK215890.1, KK215891.1, KK215892.1, KK215893.1, KK215894.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215902.1, KK215903.1, KK215905.1, KK215907.1, KK215908.1, KK215909.1, KK215910.1, KK215911.1, KK215913.1, KK215914.1, KK215915.1, KK215917.1, KK215918.1, KK215920.1, KK215921.1, KK215922.1, KK215923.1, KK215924.1, KK215927.1, KK215928.1, KK215929.1, KK215933.1, KK215934.1, KK215935.1, KK215937.1, KK215938.1, KK215940.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215946.1, KK215949.1, KK215951.1, KK215952.1, KK215953.1, KK215956.1, KK215957.1, KK215958.1, KK215960.1, KK215962.1, KK215963.1, KK215965.1, KK215967.1, KK215969.1, KK215970.1, KK215971.1, KK215972.1, KK215973.1, KK215974.1, KK215975.1, KK215976.1, KK215977.1, KK215978.1, KK215979.1, KK215982.1, KK215983.1, KK215984.1, KK215985.1, KK215986.1, KK215987.1, KK215989.1, KK215990.1, KK215993.1, KK215994.1, KK215995.1, KK215996.1, KK215997.1, KK215999.1, KK216000.1, KK216001.1, KK216005.1, KK216006.1, KK216007.1, KK216008.1, KK216009.1, KK216011.1, KK216012.1, KK216015.1, KK216016.1, KK216017.1, KK216018.1, KK216021.1, KK216022.1, KK216023.1, KK216024.1, KK216025.1, KK216026.1, KK216027.1, KK216028.1, KK216029.1, KK216030.1, KK216032.1, KK216033.1, KK216034.1, KK216035.1, KK216036.1, KK216037.1, KK216038.1, KK216039.1, KK216040.1, KK216041.1, KK216042.1, KK216043.1, KK216044.1, KK216047.1, KK216048.1, KK216049.1, KK216050.1, KK216053.1, KK216055.1, KK216056.1, KK216058.1, KK216059.1, KK216062.1, KK216063.1, KK216064.1, KK216065.1, KK216066.1, KK216067.1, KK216068.1, KK216069.1, KK216070.1, KK216071.1, KK216072.1, KK216074.1, KK216075.1, KK216076.1, KK216077.1, KK216078.1, KK216079.1, KK216080.1, KK216082.1, KK216083.1, KK216084.1, KK216085.1, KK216086.1, KK216087.1, KK216089.1, KK216091.1, KK216093.1, KK216094.1, KK216095.1, KK216096.1, KK216097.1, KK216098.1, KK216099.1, KK216102.1, KK216103.1, KK216106.1, KK216109.1, KK216110.1, KK216111.1, KK216112.1, KK216113.1, KK216114.1, KK216115.1, KK216117.1, KK216118.1, KK216120.1, KK216122.1, KK216124.1, KK216125.1, KK216126.1, KK216127.1, KK216128.1, KK216131.1, KK216133.1, KK216134.1, KK216135.1, KK216137.1, KK216138.1, KK216140.1, KK216141.1, KK216142.1, KK216143.1, KK216144.1, KK216145.1, KK216146.1, KK216150.1, KK216151.1, KK216152.1, KK216154.1, KK216155.1, KK216157.1, KK216158.1, KK216159.1, KK216160.1, KK216162.1, KK216163.1, KK216164.1, KK216165.1, KK216166.1, KK216168.1, KK216169.1, KK216171.1, KK216172.1, KK216173.1, KK216174.1, KK216175.1, KK216176.1, KK216177.1, KK216178.1, KK216180.1, KK216181.1, KK216182.1, KK216184.1, KK216186.1, KK216190.1, KK216192.1, KK216193.1, KK216194.1, KK216195.1, KK216196.1, KK216197.1, KK216198.1, KK216200.1, KK216201.1, KK216202.1, KK216203.1, KK216205.1, KK216206.1, KK216208.1, KK216212.1, KK216213.1, KK216214.1, KK216215.1, KK216217.1, KK216218.1, KK216219.1, KK216221.1, KK216222.1, KK216224.1, KK216225.1, KK216226.1, KK216227.1, KK216229.1, KK216231.1, KK216232.1, KK216234.1, KK216235.1, KK216236.1, KK216237.1, KK216238.1, KK216239.1, KK216240.1, KK216241.1, KK216242.1, KK216243.1, KK216244.1, KK216245.1, KK216248.1, KK216249.1, KK216251.1, KK216252.1, KK216253.1, KK216254.1, KK216256.1, KK216258.1, KK216259.1, KK216260.1, KK216261.1, KK216262.1, KK216263.1, KK216264.1, KK216265.1, KK216266.1, KK216267.1, KK216269.1, KK216270.1, KK216271.1, KK216272.1, KK216273.1, KK216274.1, KK216275.1, KK216276.1, KK216278.1, KK216280.1, KK216281.1, KK216282.1, KK216283.1, KK216284.1, KK216285.1, KK216287.1, KK216288.1, KK216289.1, KK216290.1, KK216291.1, KK216292.1, KK216293.1, KK216295.1, KK216296.1, KK216297.1, KK216298.1, KK216299.1, KK216301.1, KK216302.1, KK216303.1, KK216304.1, KK216306.1, KK216307.1, KK216308.1, KK216310.1, KK216311.1, KK216313.1, KK216315.1, KK216316.1, KK216317.1, KK216318.1, KK216319.1, KK216320.1, KK216321.1, KK216322.1, KK216323.1, KK216324.1, KK216325.1, KK216326.1, KK216327.1, KK216328.1, KK216329.1, KK216330.1, KK216331.1, KK216333.1, KK216334.1, KK216335.1, KK216336.1, KK216337.1, KK216338.1, KK216340.1, KK216341.1, KK216342.1, KK216343.1, KK216344.1, KK216345.1, KK216346.1, KK216347.ol1## Hits object with 1854709 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 28287 16047
## [2] 28288 16047
## [3] 28289 16047
## [4] 28290 16047
## [5] 28291 16047
## ... ... ...
## [1854705] 21226633 2480
## [1854706] 21226634 2479
## [1854707] 21226634 2480
## [1854708] 21226635 2479
## [1854709] 21226635 2480
## -------
## queryLength: 21234500 / subjectLength: 34314GvLpromoters <- methylkitGvLGR[queryHits(ol1)]
myPromotersol1 <- my_Promoters[subjectHits(ol1)]
head(GvLpromoters)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | pvalue qvalue meth.diff
## <Rle> <IRanges> <Rle> | <numeric> <numeric> <numeric>
## [1] KK215283.1 633237 + | 0.672548 0.985470 2.003205
## [2] KK215283.1 633238 + | 0.615264 0.985470 -2.165725
## [3] KK215283.1 633265 + | 0.977517 0.985470 -0.150150
## [4] KK215283.1 633266 + | 0.389647 0.937638 -5.670376
## [5] KK215283.1 633284 + | 0.921664 0.985470 -0.377074
## [6] KK215283.1 633285 + | 0.400779 0.942238 -4.333333
## -------
## seqinfo: 2483 sequences from an unspecified genome; no seqlengthsmyPromotersol1## GRanges object with 1854709 ranges and 3 metadata columns:
## seqnames ranges strand | V5
## <Rle> <IRanges> <Rle> | <character>
## [1] KK215283.1 633221-636222 + | ENSPREG00000018045
## [2] KK215283.1 633221-636222 + | ENSPREG00000018045
## [3] KK215283.1 633221-636222 + | ENSPREG00000018045
## [4] KK215283.1 633221-636222 + | ENSPREG00000018045
## [5] KK215283.1 633221-636222 + | ENSPREG00000018045
## ... ... ... ... . ...
## [1854705] LG9 34072750-34075751 + | ENSPREG00000019083
## [1854706] LG9 34072714-34075715 + | ENSPREG00000019083
## [1854707] LG9 34072750-34075751 + | ENSPREG00000019083
## [1854708] LG9 34072714-34075715 + | ENSPREG00000019083
## [1854709] LG9 34072750-34075751 + | ENSPREG00000019083
## V6 V7
## <character> <character>
## [1] ENSPRET00000026955 uncharacterised
## [2] ENSPRET00000026955 uncharacterised
## [3] ENSPRET00000026955 uncharacterised
## [4] ENSPRET00000026955 uncharacterised
## [5] ENSPRET00000026955 uncharacterised
## ... ... ...
## [1854705] ENSPRET00000028582 adamtsl2
## [1854706] ENSPRET00000028533 adamtsl2
## [1854707] ENSPRET00000028582 adamtsl2
## [1854708] ENSPRET00000028533 adamtsl2
## [1854709] ENSPRET00000028582 adamtsl2
## -------
## seqinfo: 452 sequences from an unspecified genome; no seqlengthsGvLpromotersdf <- as.data.frame(GvLpromoters,row.names = 1:nrow(as.data.frame(ranges(GvLpromoters))))
str(GvLpromotersdf)## 'data.frame': 1854709 obs. of 8 variables:
## $ seqnames : Factor w/ 2483 levels "KK215283.1","KK215284.1",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ start : int 633237 633238 633265 633266 633284 633285 633309 633310 633320 633321 ...
## $ end : int 633237 633238 633265 633266 633284 633285 633309 633310 633320 633321 ...
## $ width : int 1 1 1 1 1 1 1 1 1 1 ...
## $ strand : Factor w/ 3 levels "+","-","*": 1 1 1 1 1 1 1 1 1 1 ...
## $ pvalue : num 0.673 0.615 0.978 0.39 0.922 ...
## $ qvalue : num 0.985 0.985 0.985 0.938 0.985 ...
## $ meth.diff: num 2.003 -2.166 -0.15 -5.67 -0.377 ...myPromotersoldf1 <- as.data.frame(myPromotersol1,row.names = 1:nrow(as.data.frame(ranges(myPromotersol1))))
head(myPromotersoldf1)## seqnames start end width strand V5 V6
## 1 KK215283.1 633221 636222 3002 + ENSPREG00000018045 ENSPRET00000026955
## 2 KK215283.1 633221 636222 3002 + ENSPREG00000018045 ENSPRET00000026955
## 3 KK215283.1 633221 636222 3002 + ENSPREG00000018045 ENSPRET00000026955
## 4 KK215283.1 633221 636222 3002 + ENSPREG00000018045 ENSPRET00000026955
## 5 KK215283.1 633221 636222 3002 + ENSPREG00000018045 ENSPRET00000026955
## 6 KK215283.1 633221 636222 3002 + ENSPREG00000018045 ENSPRET00000026955
## V7
## 1 uncharacterised
## 2 uncharacterised
## 3 uncharacterised
## 4 uncharacterised
## 5 uncharacterised
## 6 uncharacterisedGvLpromotersdf <- cbind(GvLpromotersdf,myPromotersoldf1[c("V5","V6","V7")])
GvLpromotersdf$seqnames <- as.character(GvLpromotersdf$seqnames)
head(GvLpromotersdf)## seqnames start end width strand pvalue qvalue meth.diff
## 1 KK215283.1 633237 633237 1 + 0.6725484 0.9854701 2.0032051
## 2 KK215283.1 633238 633238 1 + 0.6152642 0.9854701 -2.1657250
## 3 KK215283.1 633265 633265 1 + 0.9775173 0.9854701 -0.1501502
## 4 KK215283.1 633266 633266 1 + 0.3896472 0.9376377 -5.6703763
## 5 KK215283.1 633284 633284 1 + 0.9216643 0.9854701 -0.3770739
## 6 KK215283.1 633285 633285 1 + 0.4007792 0.9422377 -4.3333333
## V5 V6 V7
## 1 ENSPREG00000018045 ENSPRET00000026955 uncharacterised
## 2 ENSPREG00000018045 ENSPRET00000026955 uncharacterised
## 3 ENSPREG00000018045 ENSPRET00000026955 uncharacterised
## 4 ENSPREG00000018045 ENSPRET00000026955 uncharacterised
## 5 ENSPREG00000018045 ENSPRET00000026955 uncharacterised
## 6 ENSPREG00000018045 ENSPRET00000026955 uncharacterisedGvLpromoterschrdf <- GvLpromotersdf[grep("LG",GvLpromotersdf$seqnames),]
head(GvLpromoterschrdf)## seqnames start end width strand pvalue qvalue meth.diff
## 106172 LG1 369385 369385 1 + 0.6989677 0.9854701 -3.4457478
## 106173 LG1 369386 369386 1 + 0.8586282 0.9854701 1.7165006
## 106174 LG1 369399 369399 1 + 0.4374333 0.9540203 -7.5000000
## 106175 LG1 369400 369400 1 + 0.4284609 0.9513410 -7.2511536
## 106176 LG1 369413 369413 1 + 0.9409084 0.9854701 0.6379585
## 106177 LG1 369414 369414 1 + 0.2853841 0.9010715 -8.1926204
## V5 V6 V7
## 106172 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 106173 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 106174 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 106175 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 106176 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 106177 ENSPREG00000000039 ENSPRET00000000039 uncharacterisedGvLpromoterschrdf <- GvLpromoterschrdf[order(GvLpromoterschrdf[,7]), ]
colnames(GvLpromoterschrdf) <- c("seqnames","start","end","width","strand","pvalue","qvalue","meth.diff","gene_id","transcript_id","gene_name")
head(GvLpromoterschrdf,50)## seqnames start end width strand pvalue qvalue
## 1338222 LG4 1846766 1846766 1 + 5.358976e-19 1.121417e-11
## 1338320 LG4 1847697 1847697 1 + 4.085825e-16 4.274991e-09
## 1338321 LG4 1847697 1847697 1 + 4.085825e-16 4.274991e-09
## 1338314 LG4 1847679 1847679 1 + 1.170641e-15 6.124197e-09
## 1338315 LG4 1847679 1847679 1 + 1.170641e-15 6.124197e-09
## 1338318 LG4 1847691 1847691 1 + 1.160716e-15 6.124197e-09
## 1338319 LG4 1847691 1847691 1 + 1.160716e-15 6.124197e-09
## 1338310 LG4 1847677 1847677 1 + 2.302746e-15 9.637436e-09
## 1338311 LG4 1847677 1847677 1 + 2.302746e-15 9.637436e-09
## 1338223 LG4 1846768 1846768 1 + 7.446573e-12 2.597112e-05
## 1338221 LG4 1846756 1846756 1 + 1.483015e-11 4.433360e-05
## 1338302 LG4 1847635 1847635 1 + 5.926712e-11 1.550277e-04
## 1338303 LG4 1847635 1847635 1 + 5.926712e-11 1.550277e-04
## 1338218 LG4 1846719 1846719 1 + 1.834129e-10 4.264546e-04
## 1338220 LG4 1846735 1846735 1 + 7.537840e-10 1.577366e-03
## 1338224 LG4 1846769 1846769 1 + 3.273650e-07 2.740171e-01
## 635178 LG16 977139 977139 1 + 1.076013e-06 3.958443e-01
## 1338312 LG4 1847678 1847678 1 + 2.029187e-06 4.437762e-01
## 1338313 LG4 1847678 1847678 1 + 2.029187e-06 4.437762e-01
## 1850278 LG9 33269563 33269563 1 + 3.285153e-06 4.903430e-01
## 276610 LG11 3917143 3917143 1 + 3.427679e-06 5.009101e-01
## 276611 LG11 3917143 3917143 1 + 3.427679e-06 5.009101e-01
## 276612 LG11 3917143 3917143 1 + 3.427679e-06 5.009101e-01
## 1338316 LG4 1847680 1847680 1 + 3.811746e-06 5.086716e-01
## 1338317 LG4 1847680 1847680 1 + 3.811746e-06 5.086716e-01
## 1333742 LG3 33658554 33658554 1 + 4.014771e-06 5.174109e-01
## 1338308 LG4 1847655 1847655 1 + 4.382833e-06 5.174109e-01
## 1338309 LG4 1847655 1847655 1 + 4.382833e-06 5.174109e-01
## 333811 LG11 26232425 26232425 1 + 5.208163e-06 5.399271e-01
## 1368283 LG4 14772797 14772797 1 + 6.228189e-06 5.399271e-01
## 685890 LG16 18243995 18243995 1 + 6.455997e-06 5.428080e-01
## 1672259 LG7 30615424 30615424 1 + 7.502705e-06 5.652092e-01
## 1338322 LG4 1847698 1847698 1 + 8.963056e-06 5.832898e-01
## 1338323 LG4 1847698 1847698 1 + 8.963056e-06 5.832898e-01
## 1340153 LG4 2407096 2407096 1 + 9.187451e-06 5.835209e-01
## 424332 LG13 5920568 5920568 1 + 1.038167e-05 5.963467e-01
## 482250 LG13 32464674 32464674 1 + 1.202075e-05 6.053786e-01
## 482251 LG13 32464674 32464674 1 + 1.202075e-05 6.053786e-01
## 1451211 LG5 14374263 14374263 1 + 1.209255e-05 6.053786e-01
## 1632264 LG7 18074652 18074652 1 + 1.313089e-05 6.113527e-01
## 997193 LG2 28556994 28556994 1 + 1.484600e-05 6.209488e-01
## 997194 LG2 28556994 28556994 1 + 1.484600e-05 6.209488e-01
## 1247493 LG23 9546055 9546055 1 + 1.447137e-05 6.209488e-01
## 1247494 LG23 9546055 9546055 1 + 1.447137e-05 6.209488e-01
## 1263473 LG23 14827467 14827467 1 + 1.489499e-05 6.209488e-01
## 688324 LG16 19176997 19176997 1 + 1.715184e-05 6.357508e-01
## 829403 LG18 19353892 19353892 1 + 1.795938e-05 6.357508e-01
## 1338225 LG4 1846781 1846781 1 + 1.654617e-05 6.357508e-01
## 1676735 LG8 1198225 1198225 1 + 1.925937e-05 6.357508e-01
## 1711548 LG8 10112971 10112971 1 + 1.720263e-05 6.357508e-01
## meth.diff gene_id transcript_id gene_name
## 1338222 -69.27181 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1338320 -68.91892 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1338321 -68.91892 ENSPREG00000021490 ENSPRET00000032134 nasp
## 1338314 -69.78610 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1338315 -69.78610 ENSPREG00000021490 ENSPRET00000032134 nasp
## 1338318 -68.38710 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1338319 -68.38710 ENSPREG00000021490 ENSPRET00000032134 nasp
## 1338310 -71.92571 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1338311 -71.92571 ENSPREG00000021490 ENSPRET00000032134 nasp
## 1338223 -56.01915 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1338221 -52.01427 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1338302 -56.33363 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1338303 -56.33363 ENSPREG00000021490 ENSPRET00000032134 nasp
## 1338218 -51.03567 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1338220 -48.66543 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1338224 -37.09677 ENSPREG00000021490 ENSPRET00000032090 nasp
## 635178 -58.46154 ENSPREG00000016099 ENSPRET00000024230 uncharacterised
## 1338312 -36.65414 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1338313 -36.65414 ENSPREG00000021490 ENSPRET00000032134 nasp
## 1850278 31.42857 ENSPREG00000017617 ENSPRET00000026323 ercc6l
## 276610 32.65460 ENSPREG00000015759 ENSPRET00000023954 ST3GAL1
## 276611 32.65460 ENSPREG00000015759 ENSPRET00000023969 ST3GAL1
## 276612 32.65460 ENSPREG00000015759 ENSPRET00000023985 ST3GAL1
## 1338316 -36.50794 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1338317 -36.50794 ENSPREG00000021490 ENSPRET00000032134 nasp
## 1333742 32.35294 ENSPREG00000018741 ENSPRET00000027994 ero1a
## 1338308 -39.18919 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1338309 -39.18919 ENSPREG00000021490 ENSPRET00000032134 nasp
## 333811 -42.93651 ENSPREG00000006976 ENSPRET00000010392 bmp8a
## 1368283 -40.00000 ENSPREG00000013521 ENSPRET00000020181 aatf
## 685890 32.43243 ENSPREG00000002163 ENSPRET00000003291 DNAH11
## 1672259 -41.93548 ENSPREG00000003508 ENSPRET00000006007 iqsec2a
## 1338322 -31.98276 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1338323 -31.98276 ENSPREG00000021490 ENSPRET00000032134 nasp
## 1340153 -51.62509 ENSPREG00000022526 ENSPRET00000033618 tmem69
## 424332 77.77778 ENSPREG00000014276 ENSPRET00000021363 arcn1b
## 482250 30.43478 ENSPREG00000020685 ENSPRET00000030891 srsf7a
## 482251 30.43478 ENSPREG00000020685 ENSPRET00000030898 srsf7a
## 1451211 41.66667 ENSPREG00000015188 ENSPRET00000022725 matn4
## 1632264 36.49886 ENSPREG00000003225 ENSPRET00000004685 nt5dc2
## 997193 34.28571 ENSPREG00000001170 ENSPRET00000001598 ackr3a
## 997194 34.28571 ENSPREG00000001170 ENSPRET00000001598 ackr3a
## 1247493 35.13514 ENSPREG00000008627 ENSPRET00000013174 SLC6A13
## 1247494 35.13514 ENSPREG00000008627 ENSPRET00000013234 SLC6A13
## 1263473 46.29847 ENSPREG00000014429 ENSPRET00000021574 uncharacterised
## 688324 46.81818 ENSPREG00000003929 ENSPRET00000005743 uncharacterised
## 829403 -44.00000 ENSPREG00000001670 ENSPRET00000002297 uncharacterised
## 1338225 -34.21053 ENSPREG00000021490 ENSPRET00000032090 nasp
## 1676735 -50.00000 ENSPREG00000006467 ENSPRET00000009640 uncharacterised
## 1711548 45.78947 ENSPREG00000019918 ENSPRET00000029766 drg2rm(GvLpromoters)
rm(GvLpromotersdf)Methyl kit tile results annotated to promoters
ol1 <- findOverlaps(methylkitTilesCvGGR,my_Promoters)## Warning in .Seqinfo.mergexy(x, y): Each of the 2 combined objects has sequence levels not in the other:
## - in 'x': KK215332.1, KK215339.1, KK215341.1, KK215351.1, KK215360.1, KK215378.1, KK215383.1, KK215387.1, KK215391.1, KK215393.1, KK215395.1, KK215396.1, KK215400.1, KK215401.1, KK215402.1, KK215403.1, KK215405.1, KK215406.1, KK215407.1, KK215408.1, KK215411.1, KK215412.1, KK215414.1, KK215415.1, KK215418.1, KK215419.1, KK215420.1, KK215421.1, KK215424.1, KK215425.1, KK215427.1, KK215430.1, KK215432.1, KK215433.1, KK215435.1, KK215439.1, KK215440.1, KK215441.1, KK215443.1, KK215444.1, KK215446.1, KK215448.1, KK215451.1, KK215453.1, KK215454.1, KK215455.1, KK215456.1, KK215459.1, KK215462.1, KK215463.1, KK215465.1, KK215466.1, KK215467.1, KK215472.1, KK215474.1, KK215475.1, KK215479.1, KK215480.1, KK215482.1, KK215484.1, KK215485.1, KK215486.1, KK215488.1, KK215490.1, KK215491.1, KK215492.1, KK215494.1, KK215496.1, KK215497.1, KK215498.1, KK215501.1, KK215502.1, KK215503.1, KK215504.1, KK215506.1, KK215507.1, KK215508.1, KK215511.1, KK215512.1, KK215513.1, KK215514.1, KK215515.1, KK215516.1, KK215517.1, KK215518.1, KK215519.1, KK215521.1, KK215523.1, KK215524.1, KK215525.1, KK215526.1, KK215528.1, KK215529.1, KK215530.1, KK215531.1, KK215533.1, KK215538.1, KK215540.1, KK215541.1, KK215543.1, KK215544.1, KK215545.1, KK215546.1, KK215547.1, KK215548.1, KK215549.1, KK215551.1, KK215553.1, KK215554.1, KK215556.1, KK215558.1, KK215559.1, KK215560.1, KK215561.1, KK215562.1, KK215567.1, KK215568.1, KK215573.1, KK215574.1, KK215577.1, KK215578.1, KK215579.1, KK215581.1, KK215582.1, KK215583.1, KK215584.1, KK215585.1, KK215586.1, KK215587.1, KK215588.1, KK215589.1, KK215590.1, KK215594.1, KK215595.1, KK215597.1, KK215598.1, KK215601.1, KK215602.1, KK215603.1, KK215605.1, KK215606.1, KK215608.1, KK215615.1, KK215616.1, KK215620.1, KK215621.1, KK215622.1, KK215624.1, KK215625.1, KK215626.1, KK215627.1, KK215628.1, KK215629.1, KK215630.1, KK215632.1, KK215633.1, KK215634.1, KK215635.1, KK215636.1, KK215637.1, KK215638.1, KK215639.1, KK215641.1, KK215642.1, KK215644.1, KK215645.1, KK215646.1, KK215647.1, KK215649.1, KK215652.1, KK215654.1, KK215655.1, KK215657.1, KK215658.1, KK215661.1, KK215662.1, KK215663.1, KK215664.1, KK215665.1, KK215668.1, KK215669.1, KK215670.1, KK215671.1, KK215672.1, KK215673.1, KK215675.1, KK215677.1, KK215678.1, KK215683.1, KK215684.1, KK215688.1, KK215689.1, KK215692.1, KK215694.1, KK215695.1, KK215699.1, KK215700.1, KK215701.1, KK215703.1, KK215704.1, KK215705.1, KK215706.1, KK215707.1, KK215709.1, KK215710.1, KK215711.1, KK215712.1, KK215715.1, KK215718.1, KK215719.1, KK215720.1, KK215721.1, KK215722.1, KK215723.1, KK215724.1, KK215726.1, KK215727.1, KK215728.1, KK215733.1, KK215734.1, KK215736.1, KK215737.1, KK215738.1, KK215739.1, KK215740.1, KK215741.1, KK215742.1, KK215743.1, KK215745.1, KK215748.1, KK215750.1, KK215752.1, KK215753.1, KK215754.1, KK215755.1, KK215756.1, KK215757.1, KK215758.1, KK215759.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215767.1, KK215768.1, KK215769.1, KK215770.1, KK215771.1, KK215772.1, KK215774.1, KK215775.1, KK215776.1, KK215777.1, KK215778.1, KK215779.1, KK215780.1, KK215782.1, KK215783.1, KK215785.1, KK215786.1, KK215788.1, KK215789.1, KK215792.1, KK215794.1, KK215795.1, KK215796.1, KK215797.1, KK215798.1, KK215802.1, KK215804.1, KK215807.1, KK215810.1, KK215812.1, KK215814.1, KK215815.1, KK215816.1, KK215818.1, KK215819.1, KK215821.1, KK215825.1, KK215827.1, KK215832.1, KK215834.1, KK215836.1, KK215837.1, KK215838.1, KK215839.1, KK215840.1, KK215841.1, KK215842.1, KK215843.1, KK215846.1, KK215847.1, KK215848.1, KK215849.1, KK215851.1, KK215852.1, KK215854.1, KK215857.1, KK215858.1, KK215859.1, KK215860.1, KK215861.1, KK215863.1, KK215864.1, KK215865.1, KK215866.1, KK215867.1, KK215869.1, KK215870.1, KK215872.1, KK215873.1, KK215875.1, KK215877.1, KK215878.1, KK215880.1, KK215881.1, KK215882.1, KK215884.1, KK215885.1, KK215886.1, KK215890.1, KK215891.1, KK215892.1, KK215893.1, KK215894.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215902.1, KK215903.1, KK215907.1, KK215908.1, KK215909.1, KK215910.1, KK215911.1, KK215913.1, KK215915.1, KK215917.1, KK215918.1, KK215920.1, KK215921.1, KK215922.1, KK215923.1, KK215924.1, KK215927.1, KK215928.1, KK215929.1, KK215933.1, KK215934.1, KK215935.1, KK215937.1, KK215938.1, KK215940.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215946.1, KK215949.1, KK215951.1, KK215952.1, KK215953.1, KK215956.1, KK215957.1, KK215960.1, KK215962.1, KK215963.1, KK215965.1, KK215967.1, KK215969.1, KK215970.1, KK215971.1, KK215972.1, KK215973.1, KK215974.1, KK215975.1, KK215976.1, KK215977.1, KK215978.1, KK215979.1, KK215982.1, KK215983.1, KK215984.1, KK215985.1, KK215987.1, KK215989.1, KK215990.1, KK215993.1, KK215994.1, KK215995.1, KK215996.1, KK215997.1, KK215999.1, KK216000.1, KK216001.1, KK216006.1, KK216007.1, KK216008.1, KK216009.1, KK216011.1, KK216012.1, KK216015.1, KK216017.1, KK216018.1, KK216021.1, KK216022.1, KK216023.1, KK216024.1, KK216025.1, KK216026.1, KK216027.1, KK216028.1, KK216029.1, KK216030.1, KK216032.1, KK216033.1, KK216034.1, KK216035.1, KK216036.1, KK216037.1, KK216038.1, KK216039.1, KK216040.1, KK216041.1, KK216042.1, KK216043.1, KK216044.1, KK216047.1, KK216048.1, KK216049.1, KK216050.1, KK216053.1, KK216055.1, KK216056.1, KK216058.1, KK216059.1, KK216062.1, KK216063.1, KK216064.1, KK216065.1, KK216066.1, KK216067.1, KK216068.1, KK216069.1, KK216070.1, KK216071.1, KK216072.1, KK216074.1, KK216075.1, KK216076.1, KK216077.1, KK216078.1, KK216079.1, KK216080.1, KK216082.1, KK216083.1, KK216084.1, KK216085.1, KK216086.1, KK216087.1, KK216089.1, KK216093.1, KK216094.1, KK216095.1, KK216096.1, KK216097.1, KK216098.1, KK216099.1, KK216102.1, KK216103.1, KK216106.1, KK216109.1, KK216111.1, KK216112.1, KK216113.1, KK216114.1, KK216115.1, KK216117.1, KK216118.1, KK216120.1, KK216122.1, KK216124.1, KK216125.1, KK216126.1, KK216128.1, KK216131.1, KK216133.1, KK216134.1, KK216135.1, KK216137.1, KK216138.1, KK216140.1, KK216141.1, KK216142.1, KK216143.1, KK216144.1, KK216145.1, KK216146.1, KK216150.1, KK216151.1, KK216152.1, KK216154.1, KK216155.1, KK216157.1, KK216158.1, KK216159.1, KK216160.1, KK216162.1, KK216163.1, KK216164.1, KK216165.1, KK216166.1, KK216168.1, KK216169.1, KK216171.1, KK216172.1, KK216173.1, KK216174.1, KK216175.1, KK216176.1, KK216177.1, KK216178.1, KK216180.1, KK216181.1, KK216182.1, KK216184.1, KK216186.1, KK216190.1, KK216192.1, KK216193.1, KK216194.1, KK216195.1, KK216197.1, KK216198.1, KK216200.1, KK216201.1, KK216202.1, KK216203.1, KK216205.1, KK216206.1, KK216208.1, KK216212.1, KK216213.1, KK216214.1, KK216215.1, KK216217.1, KK216219.1, KK216221.1, KK216222.1, KK216224.1, KK216225.1, KK216226.1, KK216227.1, KK216229.1, KK216231.1, KK216232.1, KK216234.1, KK216235.1, KK216236.1, KK216237.1, KK216238.1, KK216240.1, KK216241.1, KK216242.1, KK216244.1, KK216245.1, KK216248.1, KK216251.1, KK216252.1, KK216253.1, KK216254.1, KK216256.1, KK216258.1, KK216259.1, KK216260.1, KK216261.1, KK216262.1, KK216263.1, KK216264.1, KK216265.1, KK216266.1, KK216267.1, KK216269.1, KK216270.1, KK216272.1, KK216273.1, KK216275.1, KK216276.1, KK216278.1, KK216280.1, KK216281.1, KK216282.1, KK216283.1, KK216284.1, KK216285.1, KK216287.1, KK216288.1, KK216289.1, KK216290.1, KK216291.1, KK216293.1, KK216295.1, KK216296.1, KK216297.1, KK216299.1, KK216302.1, KK216303.1, KK216304.1, KK216306.1, KK216307.1, KK216308.1, KK216310.1, KK216311.1, KK216313.1, KK216315.1, KK216316.1, KK216317.1, KK216318.1, KK216319.1, KK216320.1, KK216321.1, KK216322.1, KK216323.1, KK216324.1, KK216325.1, KK216326.1, KK216328.1, KK216329.1, KK216330.1, KK216331.1, KK216333.1, KK216334.1, KK216337.1, KK216338.1, KK216341.1, KK216342.1, KK216343.1, KK216344.1, KK216345.1, KK216346.1, KK216347.1, KK216351.1, KK216353.1, KK216354.1, KK216356.1, KK216359.1, KK216360.1, KK216362.1, KK216363.1, KK216364.1, KK216365.1, KK216366.1, KK216368.1, KK216369.1, KK216370.1, KK216371.1, KK216372.1, KK216374.1, KK216375.1, KK216376.1, KK216377.1, KK216378.1, KK216379.1, KK216381.1, KK216382.1, KK216383.1, KK216384.1, KK216386.1, KK216387.1, KK216388.1, KK216389.1, KK216390.1, KK216391.1, KK216392.ol1## Hits object with 121434 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 47 33417
## [2] 47 33416
## [3] 48 33417
## [4] 48 33416
## [5] 49 33417
## ... ... ...
## [121430] 612819 19561
## [121431] 612820 19562
## [121432] 612820 19561
## [121433] 612821 19562
## [121434] 612821 19561
## -------
## queryLength: 612876 / subjectLength: 34314CvGpromoters <- methylkitTilesCvGGR[queryHits(ol1)]
myPromotersol1 <- my_Promoters[subjectHits(ol1)]
head(CvGpromoters)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | pvalue qvalue meth.diff
## <Rle> <IRanges> <Rle> | <numeric> <numeric> <numeric>
## [1] KK215283.1 48001-49000 * | 0.350262 0.519396 -1.012623
## [2] KK215283.1 48001-49000 * | 0.350262 0.519396 -1.012623
## [3] KK215283.1 49001-50000 * | 0.330626 0.504929 1.328265
## [4] KK215283.1 49001-50000 * | 0.330626 0.504929 1.328265
## [5] KK215283.1 50001-51000 * | 0.769683 0.741508 -0.390752
## [6] KK215283.1 50001-51000 * | 0.769683 0.741508 -0.390752
## -------
## seqinfo: 2173 sequences from an unspecified genome; no seqlengthsmyPromotersol1## GRanges object with 121434 ranges and 3 metadata columns:
## seqnames ranges strand | V5
## <Rle> <IRanges> <Rle> | <character>
## [1] KK215283.1 48608-51609 - | ENSPREG00000017956
## [2] KK215283.1 48699-51700 - | ENSPREG00000017956
## [3] KK215283.1 48608-51609 - | ENSPREG00000017956
## [4] KK215283.1 48699-51700 - | ENSPREG00000017956
## [5] KK215283.1 48608-51609 - | ENSPREG00000017956
## ... ... ... ... . ...
## [121430] LG9 34111750-34114751 - | ENSPREG00000019150
## [121431] LG9 34111727-34114728 - | ENSPREG00000019150
## [121432] LG9 34111750-34114751 - | ENSPREG00000019150
## [121433] LG9 34111727-34114728 - | ENSPREG00000019150
## [121434] LG9 34111750-34114751 - | ENSPREG00000019150
## V6 V7
## <character> <character>
## [1] ENSPRET00000026836 usp6nl
## [2] ENSPRET00000026836 usp6nl
## [3] ENSPRET00000026836 usp6nl
## [4] ENSPRET00000026836 usp6nl
## [5] ENSPRET00000026836 usp6nl
## ... ... ...
## [121430] ENSPRET00000028600 FAM163B
## [121431] ENSPRET00000028600 FAM163B
## [121432] ENSPRET00000028600 FAM163B
## [121433] ENSPRET00000028600 FAM163B
## [121434] ENSPRET00000028600 FAM163B
## -------
## seqinfo: 452 sequences from an unspecified genome; no seqlengthsCvGpromotersdf <- as.data.frame(CvGpromoters,row.names = 1:nrow(as.data.frame(ranges(CvGpromoters))))
str(CvGpromotersdf)## 'data.frame': 121434 obs. of 8 variables:
## $ seqnames : Factor w/ 2173 levels "KK215283.1","KK215284.1",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ start : int 48001 48001 49001 49001 50001 50001 51001 51001 152001 153001 ...
## $ end : int 49000 49000 50000 50000 51000 51000 52000 52000 153000 154000 ...
## $ width : int 1000 1000 1000 1000 1000 1000 1000 1000 1000 1000 ...
## $ strand : Factor w/ 3 levels "+","-","*": 3 3 3 3 3 3 3 3 3 3 ...
## $ pvalue : num 0.35 0.35 0.331 0.331 0.77 ...
## $ qvalue : num 0.519 0.519 0.505 0.505 0.742 ...
## $ meth.diff: num -1.013 -1.013 1.328 1.328 -0.391 ...myPromotersoldf1 <- as.data.frame(myPromotersol1,row.names = 1:nrow(as.data.frame(ranges(myPromotersol1))))
head(myPromotersoldf1,200)## seqnames start end width strand V5
## 1 KK215283.1 48608 51609 3002 - ENSPREG00000017956
## 2 KK215283.1 48699 51700 3002 - ENSPREG00000017956
## 3 KK215283.1 48608 51609 3002 - ENSPREG00000017956
## 4 KK215283.1 48699 51700 3002 - ENSPREG00000017956
## 5 KK215283.1 48608 51609 3002 - ENSPREG00000017956
## 6 KK215283.1 48699 51700 3002 - ENSPREG00000017956
## 7 KK215283.1 48608 51609 3002 - ENSPREG00000017956
## 8 KK215283.1 48699 51700 3002 - ENSPREG00000017956
## 9 KK215283.1 152857 155858 3002 - ENSPREG00000018002
## 10 KK215283.1 152857 155858 3002 - ENSPREG00000018002
## 11 KK215283.1 152857 155858 3002 - ENSPREG00000018002
## 12 KK215283.1 152857 155858 3002 - ENSPREG00000018002
## 13 KK215283.1 159179 162180 3002 - ENSPREG00000018002
## 14 KK215283.1 159179 162180 3002 - ENSPREG00000018002
## 15 KK215283.1 159179 162180 3002 - ENSPREG00000018002
## 16 KK215283.1 205095 208096 3002 - ENSPREG00000018002
## 17 KK215283.1 205095 208096 3002 - ENSPREG00000018002
## 18 KK215283.1 205095 208096 3002 - ENSPREG00000018002
## 19 KK215283.1 205095 208096 3002 - ENSPREG00000018002
## 20 KK215283.1 285101 288102 3002 - ENSPREG00000018002
## 21 KK215283.1 285101 288102 3002 - ENSPREG00000018002
## 22 KK215283.1 285101 288102 3002 - ENSPREG00000018002
## 23 KK215283.1 633221 636222 3002 + ENSPREG00000018045
## 24 KK215283.1 633221 636222 3002 + ENSPREG00000018045
## 25 KK215283.1 633221 636222 3002 + ENSPREG00000018045
## 26 KK215283.1 633221 636222 3002 + ENSPREG00000018045
## 27 KK215283.1 750103 753104 3002 - ENSPREG00000018055
## 28 KK215283.1 750103 753104 3002 - ENSPREG00000018055
## 29 KK215283.1 750103 753104 3002 - ENSPREG00000018055
## 30 KK215283.1 819886 822887 3002 - ENSPREG00000018064
## 31 KK215283.1 819886 822887 3002 - ENSPREG00000018064
## 32 KK215283.1 820402 823403 3002 + ENSPREG00000018077
## 33 KK215283.1 819886 822887 3002 - ENSPREG00000018064
## 34 KK215283.1 820402 823403 3002 + ENSPREG00000018077
## 35 KK215283.1 819886 822887 3002 - ENSPREG00000018064
## 36 KK215283.1 820402 823403 3002 + ENSPREG00000018077
## 37 KK215283.1 820402 823403 3002 + ENSPREG00000018077
## 38 KK215283.1 833277 836278 3002 - ENSPREG00000018089
## 39 KK215283.1 833277 836278 3002 - ENSPREG00000018089
## 40 KK215283.1 833277 836278 3002 - ENSPREG00000018089
## 41 KK215283.1 833277 836278 3002 - ENSPREG00000018089
## 42 KK215283.1 842131 845132 3002 - ENSPREG00000018096
## 43 KK215283.1 843386 846387 3002 + ENSPREG00000018107
## 44 KK215283.1 842131 845132 3002 - ENSPREG00000018096
## 45 KK215283.1 843386 846387 3002 + ENSPREG00000018107
## 46 KK215283.1 842131 845132 3002 - ENSPREG00000018096
## 47 KK215283.1 843386 846387 3002 + ENSPREG00000018107
## 48 KK215283.1 843386 846387 3002 + ENSPREG00000018107
## 49 KK215283.1 863768 866769 3002 - ENSPREG00000018132
## 50 KK215283.1 863768 866769 3002 - ENSPREG00000018132
## 51 KK215283.1 863768 866769 3002 - ENSPREG00000018132
## 52 KK215283.1 863768 866769 3002 - ENSPREG00000018132
## 53 KK215283.1 868736 871737 3002 + ENSPREG00000018176
## 54 KK215283.1 868736 871737 3002 + ENSPREG00000018176
## 55 KK215283.1 868736 871737 3002 + ENSPREG00000018176
## 56 KK215283.1 868736 871737 3002 + ENSPREG00000018176
## 57 KK215283.1 872726 875727 3002 + ENSPREG00000018176
## 58 KK215283.1 872726 875727 3002 + ENSPREG00000018176
## 59 KK215283.1 873475 876476 3002 + ENSPREG00000018176
## 60 KK215283.1 874227 877228 3002 + ENSPREG00000018176
## 61 KK215283.1 874254 877255 3002 + ENSPREG00000018176
## 62 KK215283.1 872726 875727 3002 + ENSPREG00000018176
## 63 KK215283.1 873475 876476 3002 + ENSPREG00000018176
## 64 KK215283.1 874227 877228 3002 + ENSPREG00000018176
## 65 KK215283.1 874254 877255 3002 + ENSPREG00000018176
## 66 KK215283.1 873475 876476 3002 + ENSPREG00000018176
## 67 KK215283.1 874227 877228 3002 + ENSPREG00000018176
## 68 KK215283.1 874254 877255 3002 + ENSPREG00000018176
## 69 KK215283.1 874227 877228 3002 + ENSPREG00000018176
## 70 KK215283.1 874254 877255 3002 + ENSPREG00000018176
## 71 KK215283.1 907874 910875 3002 + ENSPREG00000018319
## 72 KK215283.1 907874 910875 3002 + ENSPREG00000018319
## 73 KK215283.1 908866 911867 3002 + ENSPREG00000018319
## 74 KK215283.1 907874 910875 3002 + ENSPREG00000018319
## 75 KK215283.1 908866 911867 3002 + ENSPREG00000018319
## 76 KK215283.1 908866 911867 3002 + ENSPREG00000018319
## 77 KK215283.1 934210 937211 3002 - ENSPREG00000018359
## 78 KK215283.1 934974 937975 3002 - ENSPREG00000018359
## 79 KK215283.1 934210 937211 3002 - ENSPREG00000018359
## 80 KK215283.1 934974 937975 3002 - ENSPREG00000018359
## 81 KK215283.1 934210 937211 3002 - ENSPREG00000018359
## 82 KK215283.1 934974 937975 3002 - ENSPREG00000018359
## 83 KK215283.1 934210 937211 3002 - ENSPREG00000018359
## 84 KK215283.1 934974 937975 3002 - ENSPREG00000018359
## 85 KK215283.1 938908 941909 3002 + ENSPREG00000018388
## 86 KK215283.1 938908 941909 3002 + ENSPREG00000018388
## 87 KK215283.1 938908 941909 3002 + ENSPREG00000018388
## 88 KK215283.1 938908 941909 3002 + ENSPREG00000018388
## 89 KK215283.1 958382 961383 3002 - ENSPREG00000018415
## 90 KK215283.1 958382 961383 3002 - ENSPREG00000018415
## 91 KK215283.1 958382 961383 3002 - ENSPREG00000018415
## 92 KK215283.1 958382 961383 3002 - ENSPREG00000018415
## 93 KK215283.1 961546 964547 3002 - ENSPREG00000018425
## 94 KK215283.1 961546 964547 3002 - ENSPREG00000018425
## 95 KK215283.1 961546 964547 3002 - ENSPREG00000018425
## 96 KK215283.1 961546 964547 3002 - ENSPREG00000018425
## 97 KK215283.1 964071 967072 3002 - ENSPREG00000018437
## 98 KK215283.1 964071 967072 3002 - ENSPREG00000018437
## 99 KK215283.1 965649 968650 3002 - ENSPREG00000018451
## 100 KK215283.1 964071 967072 3002 - ENSPREG00000018437
## 101 KK215283.1 965649 968650 3002 - ENSPREG00000018451
## 102 KK215283.1 964071 967072 3002 - ENSPREG00000018437
## 103 KK215283.1 965649 968650 3002 - ENSPREG00000018451
## 104 KK215283.1 965649 968650 3002 - ENSPREG00000018451
## 105 KK215283.1 968473 971474 3002 + ENSPREG00000018467
## 106 KK215283.1 968473 971474 3002 + ENSPREG00000018467
## 107 KK215283.1 968473 971474 3002 + ENSPREG00000018467
## 108 KK215283.1 968473 971474 3002 + ENSPREG00000018467
## 109 KK215283.1 978444 981445 3002 - ENSPREG00000018505
## 110 KK215283.1 978444 981445 3002 - ENSPREG00000018505
## 111 KK215283.1 978444 981445 3002 - ENSPREG00000018505
## 112 KK215283.1 978444 981445 3002 - ENSPREG00000018505
## 113 KK215283.1 981045 984046 3002 + ENSPREG00000018550
## 114 KK215283.1 981296 984297 3002 + ENSPREG00000018550
## 115 KK215283.1 981045 984046 3002 + ENSPREG00000018550
## 116 KK215283.1 981296 984297 3002 + ENSPREG00000018550
## 117 KK215283.1 982433 985434 3002 + ENSPREG00000018563
## 118 KK215283.1 981045 984046 3002 + ENSPREG00000018550
## 119 KK215283.1 981296 984297 3002 + ENSPREG00000018550
## 120 KK215283.1 982433 985434 3002 + ENSPREG00000018563
## 121 KK215283.1 981045 984046 3002 + ENSPREG00000018550
## 122 KK215283.1 981296 984297 3002 + ENSPREG00000018550
## 123 KK215283.1 982433 985434 3002 + ENSPREG00000018563
## 124 KK215283.1 982433 985434 3002 + ENSPREG00000018563
## 125 KK215283.1 1040715 1043716 3002 + ENSPREG00000018581
## 126 KK215283.1 1040715 1043716 3002 + ENSPREG00000018581
## 127 KK215283.1 1040715 1043716 3002 + ENSPREG00000018581
## 128 KK215283.1 1040715 1043716 3002 + ENSPREG00000018581
## 129 KK215283.1 1064330 1067331 3002 + ENSPREG00000018590
## 130 KK215283.1 1064330 1067331 3002 + ENSPREG00000018590
## 131 KK215283.1 1064330 1067331 3002 + ENSPREG00000018590
## 132 KK215283.1 1064330 1067331 3002 + ENSPREG00000018590
## 133 KK215283.1 1071694 1074695 3002 + ENSPREG00000018598
## 134 KK215283.1 1071694 1074695 3002 + ENSPREG00000018598
## 135 KK215283.1 1071694 1074695 3002 + ENSPREG00000018598
## 136 KK215283.1 1079628 1082629 3002 - ENSPREG00000018606
## 137 KK215283.1 1081891 1084892 3002 + ENSPREG00000018618
## 138 KK215283.1 1081891 1084892 3002 + ENSPREG00000018618
## 139 KK215283.1 1081891 1084892 3002 + ENSPREG00000018618
## 140 KK215283.1 1088235 1091236 3002 + ENSPREG00000018627
## 141 KK215283.1 1088235 1091236 3002 + ENSPREG00000018627
## 142 KK215283.1 1088235 1091236 3002 + ENSPREG00000018627
## 143 KK215283.1 1088235 1091236 3002 + ENSPREG00000018627
## 144 KK215283.1 1097033 1100034 3002 + ENSPREG00000018643
## 145 KK215283.1 1097033 1100034 3002 + ENSPREG00000018643
## 146 KK215283.1 1097033 1100034 3002 + ENSPREG00000018643
## 147 KK215283.1 1097033 1100034 3002 + ENSPREG00000018643
## 148 KK215283.1 1110466 1113467 3002 + ENSPREG00000018704
## 149 KK215283.1 1110466 1113467 3002 + ENSPREG00000018704
## 150 KK215283.1 1110466 1113467 3002 + ENSPREG00000018704
## 151 KK215283.1 1110466 1113467 3002 + ENSPREG00000018704
## 152 KK215283.1 1121640 1124641 3002 + ENSPREG00000018866
## 153 KK215283.1 1121640 1124641 3002 + ENSPREG00000018866
## 154 KK215283.1 1122906 1125907 3002 + ENSPREG00000018866
## 155 KK215283.1 1121640 1124641 3002 + ENSPREG00000018866
## 156 KK215283.1 1122906 1125907 3002 + ENSPREG00000018866
## 157 KK215283.1 1121640 1124641 3002 + ENSPREG00000018866
## 158 KK215283.1 1122906 1125907 3002 + ENSPREG00000018866
## 159 KK215283.1 1122906 1125907 3002 + ENSPREG00000018866
## 160 KK215283.1 1125032 1128033 3002 - ENSPREG00000018876
## 161 KK215283.1 1125032 1128033 3002 - ENSPREG00000018876
## 162 KK215283.1 1125032 1128033 3002 - ENSPREG00000018876
## 163 KK215283.1 1125032 1128033 3002 - ENSPREG00000018876
## 164 KK215283.1 1128023 1131024 3002 + ENSPREG00000018898
## 165 KK215283.1 1128023 1131024 3002 + ENSPREG00000018898
## 166 KK215283.1 1128023 1131024 3002 + ENSPREG00000018898
## 167 KK215283.1 1128023 1131024 3002 + ENSPREG00000018898
## 168 KK215283.1 1148867 1151868 3002 + ENSPREG00000018918
## 169 KK215283.1 1148867 1151868 3002 + ENSPREG00000018918
## 170 KK215283.1 1148867 1151868 3002 + ENSPREG00000018918
## 171 KK215283.1 1177886 1180887 3002 + ENSPREG00000018943
## 172 KK215283.1 1177886 1180887 3002 + ENSPREG00000018943
## 173 KK215283.1 1177886 1180887 3002 + ENSPREG00000018943
## 174 KK215283.1 1177886 1180887 3002 + ENSPREG00000018943
## 175 KK215283.1 1214415 1217416 3002 - ENSPREG00000018966
## 176 KK215283.1 1214415 1217416 3002 - ENSPREG00000018966
## 177 KK215283.1 1220728 1223729 3002 + ENSPREG00000018984
## 178 KK215283.1 1220728 1223729 3002 + ENSPREG00000018984
## 179 KK215283.1 1220728 1223729 3002 + ENSPREG00000018984
## 180 KK215283.1 1234807 1237808 3002 + ENSPREG00000019014
## 181 KK215283.1 1234807 1237808 3002 + ENSPREG00000019014
## 182 KK215283.1 1234807 1237808 3002 + ENSPREG00000019014
## 183 KK215283.1 1234807 1237808 3002 + ENSPREG00000019014
## 184 KK215283.1 1251975 1254976 3002 + ENSPREG00000019022
## 185 KK215283.1 1251975 1254976 3002 + ENSPREG00000019022
## 186 KK215283.1 1251975 1254976 3002 + ENSPREG00000019022
## 187 KK215283.1 1251975 1254976 3002 + ENSPREG00000019022
## 188 KK215283.1 1273320 1276321 3002 + ENSPREG00000019047
## 189 KK215283.1 1273320 1276321 3002 + ENSPREG00000019047
## 190 KK215283.1 1273320 1276321 3002 + ENSPREG00000019047
## 191 KK215283.1 1273320 1276321 3002 + ENSPREG00000019047
## 192 KK215283.1 1281251 1284252 3002 + ENSPREG00000019105
## 193 KK215283.1 1281251 1284252 3002 + ENSPREG00000019105
## 194 KK215283.1 1281251 1284252 3002 + ENSPREG00000019105
## 195 KK215283.1 1281251 1284252 3002 + ENSPREG00000019105
## 196 KK215283.1 1289865 1292866 3002 + ENSPREG00000019162
## 197 KK215283.1 1289865 1292866 3002 + ENSPREG00000019162
## 198 KK215283.1 1289865 1292866 3002 + ENSPREG00000019162
## 199 KK215283.1 1289865 1292866 3002 + ENSPREG00000019162
## 200 KK215283.1 1335255 1338256 3002 + ENSPREG00000019251
## V6 V7
## 1 ENSPRET00000026836 usp6nl
## 2 ENSPRET00000026836 usp6nl
## 3 ENSPRET00000026836 usp6nl
## 4 ENSPRET00000026836 usp6nl
## 5 ENSPRET00000026836 usp6nl
## 6 ENSPRET00000026836 usp6nl
## 7 ENSPRET00000026836 usp6nl
## 8 ENSPRET00000026836 usp6nl
## 9 ENSPRET00000026943 celf2
## 10 ENSPRET00000026943 celf2
## 11 ENSPRET00000026943 celf2
## 12 ENSPRET00000026943 celf2
## 13 ENSPRET00000026921 celf2
## 14 ENSPRET00000026921 celf2
## 15 ENSPRET00000026921 celf2
## 16 ENSPRET00000026901 celf2
## 17 ENSPRET00000026901 celf2
## 18 ENSPRET00000026901 celf2
## 19 ENSPRET00000026901 celf2
## 20 ENSPRET00000026888 celf2
## 21 ENSPRET00000026888 celf2
## 22 ENSPRET00000026888 celf2
## 23 ENSPRET00000026955 uncharacterised
## 24 ENSPRET00000026955 uncharacterised
## 25 ENSPRET00000026955 uncharacterised
## 26 ENSPRET00000026955 uncharacterised
## 27 ENSPRET00000026972 gata3
## 28 ENSPRET00000026972 gata3
## 29 ENSPRET00000026972 gata3
## 30 ENSPRET00000026998 atp5f1c
## 31 ENSPRET00000026998 atp5f1c
## 32 ENSPRET00000027020 kin
## 33 ENSPRET00000026998 atp5f1c
## 34 ENSPRET00000027020 kin
## 35 ENSPRET00000026998 atp5f1c
## 36 ENSPRET00000027020 kin
## 37 ENSPRET00000027020 kin
## 38 ENSPRET00000027046 uncharacterised
## 39 ENSPRET00000027046 uncharacterised
## 40 ENSPRET00000027046 uncharacterised
## 41 ENSPRET00000027046 uncharacterised
## 42 ENSPRET00000027061 uncharacterised
## 43 ENSPRET00000027079 itih5
## 44 ENSPRET00000027061 uncharacterised
## 45 ENSPRET00000027079 itih5
## 46 ENSPRET00000027061 uncharacterised
## 47 ENSPRET00000027079 itih5
## 48 ENSPRET00000027079 itih5
## 49 ENSPRET00000027122 tmem110l
## 50 ENSPRET00000027122 tmem110l
## 51 ENSPRET00000027122 tmem110l
## 52 ENSPRET00000027122 tmem110l
## 53 ENSPRET00000027180 sfmbt2
## 54 ENSPRET00000027180 sfmbt2
## 55 ENSPRET00000027180 sfmbt2
## 56 ENSPRET00000027180 sfmbt2
## 57 ENSPRET00000027194 sfmbt2
## 58 ENSPRET00000027194 sfmbt2
## 59 ENSPRET00000027194 sfmbt2
## 60 ENSPRET00000027329 sfmbt2
## 61 ENSPRET00000027366 sfmbt2
## 62 ENSPRET00000027194 sfmbt2
## 63 ENSPRET00000027194 sfmbt2
## 64 ENSPRET00000027329 sfmbt2
## 65 ENSPRET00000027366 sfmbt2
## 66 ENSPRET00000027194 sfmbt2
## 67 ENSPRET00000027329 sfmbt2
## 68 ENSPRET00000027366 sfmbt2
## 69 ENSPRET00000027329 sfmbt2
## 70 ENSPRET00000027366 sfmbt2
## 71 ENSPRET00000027410 prkcq
## 72 ENSPRET00000027410 prkcq
## 73 ENSPRET00000027410 prkcq
## 74 ENSPRET00000027410 prkcq
## 75 ENSPRET00000027410 prkcq
## 76 ENSPRET00000027410 prkcq
## 77 ENSPRET00000027444 tbc1d30
## 78 ENSPRET00000027444 tbc1d30
## 79 ENSPRET00000027444 tbc1d30
## 80 ENSPRET00000027444 tbc1d30
## 81 ENSPRET00000027444 tbc1d30
## 82 ENSPRET00000027444 tbc1d30
## 83 ENSPRET00000027444 tbc1d30
## 84 ENSPRET00000027444 tbc1d30
## 85 ENSPRET00000027500 lta4h
## 86 ENSPRET00000027500 lta4h
## 87 ENSPRET00000027500 lta4h
## 88 ENSPRET00000027500 lta4h
## 89 ENSPRET00000027530 uncharacterised
## 90 ENSPRET00000027530 uncharacterised
## 91 ENSPRET00000027530 uncharacterised
## 92 ENSPRET00000027530 uncharacterised
## 93 ENSPRET00000027543 uncharacterised
## 94 ENSPRET00000027543 uncharacterised
## 95 ENSPRET00000027543 uncharacterised
## 96 ENSPRET00000027543 uncharacterised
## 97 ENSPRET00000027565 uncharacterised
## 98 ENSPRET00000027565 uncharacterised
## 99 ENSPRET00000027580 uncharacterised
## 100 ENSPRET00000027565 uncharacterised
## 101 ENSPRET00000027580 uncharacterised
## 102 ENSPRET00000027565 uncharacterised
## 103 ENSPRET00000027580 uncharacterised
## 104 ENSPRET00000027580 uncharacterised
## 105 ENSPRET00000027619 rtcb
## 106 ENSPRET00000027619 rtcb
## 107 ENSPRET00000027619 rtcb
## 108 ENSPRET00000027619 rtcb
## 109 ENSPRET00000027705 xpot
## 110 ENSPRET00000027705 xpot
## 111 ENSPRET00000027705 xpot
## 112 ENSPRET00000027705 xpot
## 113 ENSPRET00000027721 rpl18a
## 114 ENSPRET00000027721 rpl18a
## 115 ENSPRET00000027721 rpl18a
## 116 ENSPRET00000027721 rpl18a
## 117 ENSPRET00000027763 uncharacterised
## 118 ENSPRET00000027721 rpl18a
## 119 ENSPRET00000027721 rpl18a
## 120 ENSPRET00000027763 uncharacterised
## 121 ENSPRET00000027721 rpl18a
## 122 ENSPRET00000027721 rpl18a
## 123 ENSPRET00000027763 uncharacterised
## 124 ENSPRET00000027763 uncharacterised
## 125 ENSPRET00000027773 uncharacterised
## 126 ENSPRET00000027773 uncharacterised
## 127 ENSPRET00000027773 uncharacterised
## 128 ENSPRET00000027773 uncharacterised
## 129 ENSPRET00000027781 uncharacterised
## 130 ENSPRET00000027781 uncharacterised
## 131 ENSPRET00000027781 uncharacterised
## 132 ENSPRET00000027781 uncharacterised
## 133 ENSPRET00000027795 C11orf98
## 134 ENSPRET00000027795 C11orf98
## 135 ENSPRET00000027795 C11orf98
## 136 ENSPRET00000027802 SNORD82
## 137 ENSPRET00000027814 uncharacterised
## 138 ENSPRET00000027814 uncharacterised
## 139 ENSPRET00000027814 uncharacterised
## 140 ENSPRET00000027840 LRP6
## 141 ENSPRET00000027840 LRP6
## 142 ENSPRET00000027840 LRP6
## 143 ENSPRET00000027840 LRP6
## 144 ENSPRET00000027884 lrp6
## 145 ENSPRET00000027884 lrp6
## 146 ENSPRET00000027884 lrp6
## 147 ENSPRET00000027884 lrp6
## 148 ENSPRET00000028035 tbk1
## 149 ENSPRET00000028035 tbk1
## 150 ENSPRET00000028035 tbk1
## 151 ENSPRET00000028035 tbk1
## 152 ENSPRET00000028192 gpr19
## 153 ENSPRET00000028192 gpr19
## 154 ENSPRET00000028192 gpr19
## 155 ENSPRET00000028192 gpr19
## 156 ENSPRET00000028192 gpr19
## 157 ENSPRET00000028192 gpr19
## 158 ENSPRET00000028192 gpr19
## 159 ENSPRET00000028192 gpr19
## 160 ENSPRET00000028204 crebl2
## 161 ENSPRET00000028204 crebl2
## 162 ENSPRET00000028204 crebl2
## 163 ENSPRET00000028204 crebl2
## 164 ENSPRET00000028242 dusp16
## 165 ENSPRET00000028242 dusp16
## 166 ENSPRET00000028242 dusp16
## 167 ENSPRET00000028242 dusp16
## 168 ENSPRET00000028288 eps8a
## 169 ENSPRET00000028288 eps8a
## 170 ENSPRET00000028288 eps8a
## 171 ENSPRET00000028318 kcnd2
## 172 ENSPRET00000028318 kcnd2
## 173 ENSPRET00000028318 kcnd2
## 174 ENSPRET00000028318 kcnd2
## 175 ENSPRET00000028337 tspan12
## 176 ENSPRET00000028337 tspan12
## 177 ENSPRET00000028385 ing3
## 178 ENSPRET00000028385 ing3
## 179 ENSPRET00000028385 ing3
## 180 ENSPRET00000028398 wnt16
## 181 ENSPRET00000028398 wnt16
## 182 ENSPRET00000028398 wnt16
## 183 ENSPRET00000028398 wnt16
## 184 ENSPRET00000028427 uncharacterised
## 185 ENSPRET00000028427 uncharacterised
## 186 ENSPRET00000028427 uncharacterised
## 187 ENSPRET00000028427 uncharacterised
## 188 ENSPRET00000028505 uncharacterised
## 189 ENSPRET00000028505 uncharacterised
## 190 ENSPRET00000028505 uncharacterised
## 191 ENSPRET00000028505 uncharacterised
## 192 ENSPRET00000028568 parp12b
## 193 ENSPRET00000028568 parp12b
## 194 ENSPRET00000028568 parp12b
## 195 ENSPRET00000028568 parp12b
## 196 ENSPRET00000028713 flncb
## 197 ENSPRET00000028713 flncb
## 198 ENSPRET00000028713 flncb
## 199 ENSPRET00000028713 flncb
## 200 ENSPRET00000028784 socs2CvGpromotersdf <- cbind(CvGpromotersdf,myPromotersoldf1[c("V5","V6","V7")])
CvGpromotersdf$seqnames <- as.character(CvGpromotersdf$seqnames)
head(CvGpromotersdf)## seqnames start end width strand pvalue qvalue meth.diff
## 1 KK215283.1 48001 49000 1000 * 0.3502625 0.5193963 -1.0126228
## 2 KK215283.1 48001 49000 1000 * 0.3502625 0.5193963 -1.0126228
## 3 KK215283.1 49001 50000 1000 * 0.3306258 0.5049290 1.3282648
## 4 KK215283.1 49001 50000 1000 * 0.3306258 0.5049290 1.3282648
## 5 KK215283.1 50001 51000 1000 * 0.7696833 0.7415077 -0.3907522
## 6 KK215283.1 50001 51000 1000 * 0.7696833 0.7415077 -0.3907522
## V5 V6 V7
## 1 ENSPREG00000017956 ENSPRET00000026836 usp6nl
## 2 ENSPREG00000017956 ENSPRET00000026836 usp6nl
## 3 ENSPREG00000017956 ENSPRET00000026836 usp6nl
## 4 ENSPREG00000017956 ENSPRET00000026836 usp6nl
## 5 ENSPREG00000017956 ENSPRET00000026836 usp6nl
## 6 ENSPREG00000017956 ENSPRET00000026836 usp6nlCvGpromoterschrdf <- CvGpromotersdf[grep("LG",CvGpromotersdf$seqnames),]
head(CvGpromoterschrdf)## seqnames start end width strand pvalue qvalue meth.diff
## 5072 LG1 369001 370000 1000 * 0.322523764 0.49887590 1.3393239
## 5073 LG1 370001 371000 1000 * 0.001067668 0.01709797 8.0374510
## 5074 LG1 371001 372000 1000 * 0.098296250 0.26851123 -4.0579934
## 5075 LG1 417001 418000 1000 * 0.261851460 0.45010440 1.1490468
## 5076 LG1 418001 419000 1000 * 0.853154090 0.77266747 0.1426543
## 5077 LG1 419001 420000 1000 * 0.552119623 0.64321982 0.4380303
## V5 V6 V7
## 5072 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 5073 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 5074 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 5075 ENSPREG00000000040 ENSPRET00000000040 uncharacterised
## 5076 ENSPREG00000000040 ENSPRET00000000040 uncharacterised
## 5077 ENSPREG00000000040 ENSPRET00000000040 uncharacterisedCvGpromoterschrdf <- CvGpromoterschrdf[order(CvGpromoterschrdf[,7]), ]
colnames(CvGpromoterschrdf) <- c("seqnames","start","end","width","strand","pvalue","qvalue","meth.diff","gene_id","V6","gene_name")
CvGpromoterschrdf <- CvGpromoterschrdf[which(rownames(CvGpromoterschrdf)%in%rownames(unique(CvGpromoterschrdf[,c("seqnames","start","gene_name")]))),]
head(CvGpromoterschrdf,50)## seqnames start end width strand pvalue qvalue
## 86983 LG4 1847001 1848000 1000 * 9.714622e-131 4.885614e-125
## 86984 LG4 1847001 1848000 1000 * 9.714622e-131 4.885614e-125
## 86981 LG4 1846001 1847000 1000 * 1.196917e-89 3.009727e-84
## 86982 LG4 1846001 1847000 1000 * 1.196917e-89 3.009727e-84
## 6509 LG1 9073001 9074000 1000 * 3.550053e-47 2.550528e-42
## 8294 LG1 17897001 17898000 1000 * 1.654721e-42 9.246461e-38
## 8295 LG1 17897001 17898000 1000 * 1.654721e-42 9.246461e-38
## 77529 LG22 14521001 14522000 1000 * 7.000381e-34 2.514704e-29
## 92712 LG5 2971001 2972000 1000 * 5.312984e-29 1.113321e-24
## 73774 LG21 16656001 16657000 1000 * 5.936152e-29 1.148219e-24
## 41173 LG16 6723001 6724000 1000 * 1.402234e-25 2.431732e-21
## 46766 LG17 4283001 4284000 1000 * 8.116861e-25 1.236993e-20
## 17404 LG11 10641001 10642000 1000 * 1.878573e-24 2.624332e-20
## 9801 LG1 26024001 26025000 1000 * 4.593077e-24 6.078736e-20
## 115636 LG8 27880001 27881000 1000 * 1.082929e-23 1.266557e-19
## 27565 LG13 16672001 16673000 1000 * 1.053648e-22 1.103945e-18
## 39662 LG15 30358001 30359000 1000 * 1.656064e-21 1.365339e-17
## 76277 LG22 8862001 8863000 1000 * 2.680237e-21 2.042313e-17
## 20311 LG11 25036001 25037000 1000 * 8.288033e-21 6.221138e-17
## 83219 LG3 10041001 10042000 1000 * 1.341634e-20 9.371191e-17
## 9967 LG1 26801001 26802000 1000 * 3.698637e-20 2.384736e-16
## 9719 LG1 25597001 25598000 1000 * 5.231134e-20 3.247910e-16
## 39789 LG16 189001 190000 1000 * 1.012671e-19 5.658729e-16
## 87293 LG4 4118001 4119000 1000 * 2.880164e-19 1.493271e-15
## 27933 LG13 18419001 18420000 1000 * 4.860795e-19 2.447502e-15
## 89582 LG4 18951001 18952000 1000 * 1.081553e-18 5.230073e-15
## 93452 LG5 6245001 6246000 1000 * 1.375441e-18 6.525734e-15
## 28083 LG13 19074001 19075000 1000 * 2.045440e-18 9.437421e-15
## 20918 LG11 28397001 28398000 1000 * 2.257122e-18 1.031943e-14
## 32526 LG14 9176001 9177000 1000 * 2.342806e-18 1.061467e-14
## 64273 LG2 27140001 27141000 1000 * 2.471305e-18 1.109689e-14
## 64202 LG2 26915001 26916000 1000 * 3.771989e-18 1.594104e-14
## 76276 LG22 8861001 8862000 1000 * 7.024900e-18 2.849126e-14
## 116690 LG9 8023001 8024000 1000 * 8.282235e-18 3.305752e-14
## 52732 LG18 8495001 8496000 1000 * 1.084262e-17 4.293622e-14
## 87179 LG4 3392001 3393000 1000 * 1.191330e-17 4.608737e-14
## 17287 LG11 10208001 10209000 1000 * 2.813722e-17 1.025405e-13
## 76147 LG22 7991001 7992000 1000 * 3.298895e-17 1.176637e-13
## 39529 LG15 29789001 29790000 1000 * 3.461099e-17 1.225798e-13
## 112998 LG8 17517001 17518000 1000 * 4.327631e-17 1.511405e-13
## 55662 LG19 5100001 5101000 1000 * 1.181292e-16 3.882925e-13
## 59236 LG19 25901001 25902000 1000 * 1.602430e-16 5.100530e-13
## 18221 LG11 14223001 14224000 1000 * 2.221600e-16 6.812636e-13
## 25293 LG12 25520001 25521000 1000 * 3.399650e-16 1.023790e-12
## 87491 LG4 4685001 4686000 1000 * 4.397824e-16 1.278454e-12
## 27764 LG13 17708001 17709000 1000 * 9.782753e-16 2.659393e-12
## 12412 LG10 8251001 8252000 1000 * 2.133495e-15 5.588350e-12
## 16859 LG11 6448001 6449000 1000 * 3.900187e-15 9.710180e-12
## 49016 LG17 17118001 17119000 1000 * 5.615884e-15 1.332219e-11
## 111547 LG8 11341001 11342000 1000 * 6.331941e-15 1.488046e-11
## meth.diff gene_id V6 gene_name
## 86983 19.239478 ENSPREG00000021468 ENSPRET00000032035 gpc5b
## 86984 19.239478 ENSPREG00000021490 ENSPRET00000032090 nasp
## 86981 19.897694 ENSPREG00000021468 ENSPRET00000032035 gpc5b
## 86982 19.897694 ENSPREG00000021490 ENSPRET00000032090 nasp
## 6509 14.606176 ENSPREG00000000312 ENSPRET00000000435 slx4
## 8294 -6.231157 ENSPREG00000004582 ENSPRET00000006703 uncharacterised
## 8295 -6.231157 ENSPREG00000004594 ENSPRET00000006746 lgi2b
## 77529 -31.913947 ENSPREG00000003390 ENSPRET00000004900 uncharacterised
## 92712 13.827373 ENSPREG00000022867 ENSPRET00000034154 asb14a
## 73774 11.441065 ENSPREG00000015620 ENSPRET00000023480 entpd5b
## 41173 10.994454 ENSPREG00000003585 ENSPRET00000005191 tnfb
## 46766 -13.230054 ENSPREG00000003984 ENSPRET00000005798 MYOC
## 17404 11.992462 ENSPREG00000001606 ENSPRET00000002349 uncharacterised
## 9801 -8.098931 ENSPREG00000020267 ENSPRET00000030271 pgap4
## 115636 10.411414 ENSPREG00000013036 ENSPRET00000019524 uncharacterised
## 27565 -12.159464 ENSPREG00000022573 ENSPRET00000033792 dock10
## 39662 -8.744550 ENSPREG00000013474 ENSPRET00000020140 uncharacterised
## 76277 -13.619528 ENSPREG00000015260 ENSPRET00000022840 uncharacterised
## 20311 17.675599 ENSPREG00000002484 ENSPRET00000003477 uncharacterised
## 83219 15.374176 ENSPREG00000018896 ENSPRET00000028232 slc27a2a
## 9967 -5.203589 ENSPREG00000021245 ENSPRET00000031717 CNNM1
## 9719 -7.530227 ENSPREG00000018820 ENSPRET00000028181 uncharacterised
## 39789 -4.175055 ENSPREG00000014105 ENSPRET00000021062 uncharacterised
## 87293 -4.391443 ENSPREG00000001239 ENSPRET00000001709 zbtb37
## 27933 -11.332975 ENSPREG00000001609 ENSPRET00000002207 SH2B2
## 89582 -9.781802 ENSPREG00000018864 ENSPRET00000028226 zar1
## 93452 9.964270 ENSPREG00000005431 ENSPRET00000008086 A3GALT2
## 28083 -15.311617 ENSPREG00000002366 ENSPRET00000003347 schip1
## 20918 -7.026094 ENSPREG00000009968 ENSPRET00000014921 meaf6
## 32526 -10.224418 ENSPREG00000021264 ENSPRET00000031741 ppm1nb
## 64273 11.185888 ENSPREG00000022618 ENSPRET00000033756 xk
## 64202 -13.875083 ENSPREG00000022492 ENSPRET00000033565 mstna
## 76276 -13.783559 ENSPREG00000015260 ENSPRET00000022840 uncharacterised
## 116690 -13.732587 ENSPREG00000000612 ENSPRET00000000840 uncharacterised
## 52732 -15.754982 ENSPREG00000010979 ENSPRET00000016449 dnajc3b
## 87179 -6.541203 ENSPREG00000022798 ENSPRET00000034024 si:ch211-198n5.11
## 17287 -9.781974 ENSPREG00000000557 ENSPRET00000000778 hoxa4a
## 76147 -18.150875 ENSPREG00000013282 ENSPRET00000019818 tmem62
## 39529 7.287919 ENSPREG00000012218 ENSPRET00000018275 uncharacterised
## 112998 11.841448 ENSPREG00000010040 ENSPRET00000015020 gfap
## 55662 13.480742 ENSPREG00000021677 ENSPRET00000032354 uncharacterised
## 59236 -14.597615 ENSPREG00000001288 ENSPRET00000001784 galk1
## 18221 -12.225422 ENSPREG00000007615 ENSPRET00000011309 lrrc14b
## 25293 -6.425448 ENSPREG00000005998 ENSPRET00000008873 uncharacterised
## 87491 8.905571 ENSPREG00000003007 ENSPRET00000004307 uncharacterised
## 27764 -12.413782 ENSPREG00000022956 ENSPRET00000034268 uncharacterised
## 12412 -1.367078 ENSPREG00000004266 ENSPRET00000006205 cxxc5b
## 16859 -14.734955 ENSPREG00000017999 ENSPRET00000026915 cckb
## 49016 11.055986 ENSPREG00000000936 ENSPRET00000001297 uncharacterised
## 111547 8.785566 ENSPREG00000000841 ENSPRET00000001373 cacna1aanrow(subset(CvGpromoterschrdf,qvalue<0.05))## [1] 8873nrow(subset(CvGpromoterschrdf,qvalue<0.05&meth.diff>0))## [1] 3037nrow(subset(CvGpromoterschrdf,qvalue<0.05&meth.diff<0))## [1] 5836saveRDS(object=CvGpromoterschrdf,file="CvGtiles_genepromoters.rds",compress="gzip")
rm(CvGpromoters)
rm(CvGpromotersdf)ol1 <- findOverlaps(methylkitTilesCvLGR,my_Promoters)## Warning in .Seqinfo.mergexy(x, y): Each of the 2 combined objects has sequence levels not in the other:
## - in 'x': KK215332.1, KK215339.1, KK215341.1, KK215351.1, KK215360.1, KK215378.1, KK215383.1, KK215387.1, KK215391.1, KK215393.1, KK215395.1, KK215396.1, KK215400.1, KK215401.1, KK215402.1, KK215403.1, KK215405.1, KK215406.1, KK215407.1, KK215408.1, KK215411.1, KK215412.1, KK215414.1, KK215415.1, KK215418.1, KK215419.1, KK215420.1, KK215421.1, KK215424.1, KK215425.1, KK215427.1, KK215430.1, KK215432.1, KK215433.1, KK215435.1, KK215439.1, KK215440.1, KK215441.1, KK215443.1, KK215444.1, KK215446.1, KK215448.1, KK215451.1, KK215453.1, KK215454.1, KK215455.1, KK215456.1, KK215459.1, KK215462.1, KK215463.1, KK215465.1, KK215466.1, KK215467.1, KK215472.1, KK215474.1, KK215475.1, KK215479.1, KK215480.1, KK215482.1, KK215484.1, KK215485.1, KK215486.1, KK215488.1, KK215490.1, KK215491.1, KK215492.1, KK215494.1, KK215496.1, KK215497.1, KK215498.1, KK215501.1, KK215502.1, KK215503.1, KK215504.1, KK215506.1, KK215507.1, KK215508.1, KK215511.1, KK215512.1, KK215513.1, KK215514.1, KK215515.1, KK215516.1, KK215517.1, KK215518.1, KK215519.1, KK215521.1, KK215523.1, KK215524.1, KK215525.1, KK215526.1, KK215528.1, KK215529.1, KK215530.1, KK215531.1, KK215533.1, KK215538.1, KK215540.1, KK215541.1, KK215543.1, KK215544.1, KK215545.1, KK215546.1, KK215547.1, KK215548.1, KK215549.1, KK215551.1, KK215553.1, KK215554.1, KK215556.1, KK215558.1, KK215559.1, KK215560.1, KK215561.1, KK215562.1, KK215567.1, KK215568.1, KK215573.1, KK215574.1, KK215577.1, KK215578.1, KK215579.1, KK215581.1, KK215582.1, KK215583.1, KK215584.1, KK215585.1, KK215586.1, KK215587.1, KK215588.1, KK215589.1, KK215590.1, KK215594.1, KK215595.1, KK215597.1, KK215598.1, KK215601.1, KK215602.1, KK215603.1, KK215605.1, KK215606.1, KK215608.1, KK215615.1, KK215616.1, KK215620.1, KK215621.1, KK215622.1, KK215624.1, KK215625.1, KK215626.1, KK215627.1, KK215628.1, KK215629.1, KK215630.1, KK215632.1, KK215633.1, KK215634.1, KK215635.1, KK215636.1, KK215637.1, KK215638.1, KK215639.1, KK215641.1, KK215642.1, KK215644.1, KK215645.1, KK215646.1, KK215647.1, KK215649.1, KK215652.1, KK215654.1, KK215655.1, KK215657.1, KK215658.1, KK215661.1, KK215662.1, KK215663.1, KK215664.1, KK215665.1, KK215668.1, KK215669.1, KK215670.1, KK215671.1, KK215672.1, KK215673.1, KK215675.1, KK215677.1, KK215678.1, KK215683.1, KK215684.1, KK215688.1, KK215689.1, KK215692.1, KK215694.1, KK215695.1, KK215699.1, KK215700.1, KK215701.1, KK215703.1, KK215704.1, KK215705.1, KK215706.1, KK215707.1, KK215709.1, KK215710.1, KK215711.1, KK215712.1, KK215715.1, KK215718.1, KK215719.1, KK215720.1, KK215721.1, KK215722.1, KK215723.1, KK215724.1, KK215726.1, KK215727.1, KK215728.1, KK215733.1, KK215734.1, KK215736.1, KK215737.1, KK215738.1, KK215739.1, KK215740.1, KK215741.1, KK215742.1, KK215743.1, KK215745.1, KK215748.1, KK215750.1, KK215752.1, KK215753.1, KK215754.1, KK215755.1, KK215756.1, KK215757.1, KK215758.1, KK215759.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215767.1, KK215768.1, KK215769.1, KK215770.1, KK215771.1, KK215772.1, KK215774.1, KK215775.1, KK215776.1, KK215777.1, KK215778.1, KK215779.1, KK215780.1, KK215782.1, KK215783.1, KK215785.1, KK215786.1, KK215788.1, KK215789.1, KK215792.1, KK215794.1, KK215795.1, KK215796.1, KK215797.1, KK215798.1, KK215802.1, KK215804.1, KK215807.1, KK215810.1, KK215812.1, KK215814.1, KK215815.1, KK215816.1, KK215818.1, KK215819.1, KK215821.1, KK215825.1, KK215827.1, KK215832.1, KK215834.1, KK215836.1, KK215837.1, KK215838.1, KK215839.1, KK215840.1, KK215841.1, KK215842.1, KK215843.1, KK215846.1, KK215847.1, KK215848.1, KK215849.1, KK215851.1, KK215852.1, KK215854.1, KK215857.1, KK215858.1, KK215859.1, KK215860.1, KK215861.1, KK215863.1, KK215864.1, KK215865.1, KK215866.1, KK215867.1, KK215869.1, KK215872.1, KK215873.1, KK215875.1, KK215877.1, KK215878.1, KK215880.1, KK215881.1, KK215882.1, KK215884.1, KK215885.1, KK215886.1, KK215890.1, KK215891.1, KK215892.1, KK215893.1, KK215894.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215902.1, KK215903.1, KK215907.1, KK215908.1, KK215909.1, KK215910.1, KK215911.1, KK215913.1, KK215915.1, KK215917.1, KK215918.1, KK215920.1, KK215921.1, KK215922.1, KK215923.1, KK215924.1, KK215927.1, KK215928.1, KK215929.1, KK215933.1, KK215934.1, KK215935.1, KK215937.1, KK215938.1, KK215940.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215946.1, KK215949.1, KK215951.1, KK215952.1, KK215953.1, KK215956.1, KK215957.1, KK215960.1, KK215962.1, KK215963.1, KK215965.1, KK215967.1, KK215969.1, KK215970.1, KK215971.1, KK215972.1, KK215973.1, KK215974.1, KK215975.1, KK215976.1, KK215977.1, KK215978.1, KK215979.1, KK215982.1, KK215983.1, KK215984.1, KK215985.1, KK215987.1, KK215989.1, KK215990.1, KK215993.1, KK215994.1, KK215995.1, KK215996.1, KK215997.1, KK215999.1, KK216000.1, KK216001.1, KK216006.1, KK216007.1, KK216008.1, KK216009.1, KK216011.1, KK216012.1, KK216015.1, KK216017.1, KK216018.1, KK216021.1, KK216022.1, KK216023.1, KK216024.1, KK216025.1, KK216026.1, KK216027.1, KK216028.1, KK216029.1, KK216030.1, KK216032.1, KK216033.1, KK216034.1, KK216035.1, KK216036.1, KK216037.1, KK216038.1, KK216039.1, KK216040.1, KK216041.1, KK216042.1, KK216043.1, KK216044.1, KK216047.1, KK216048.1, KK216049.1, KK216050.1, KK216053.1, KK216055.1, KK216056.1, KK216058.1, KK216059.1, KK216062.1, KK216063.1, KK216064.1, KK216065.1, KK216066.1, KK216067.1, KK216068.1, KK216069.1, KK216070.1, KK216071.1, KK216072.1, KK216074.1, KK216075.1, KK216076.1, KK216077.1, KK216078.1, KK216079.1, KK216080.1, KK216082.1, KK216083.1, KK216084.1, KK216085.1, KK216086.1, KK216087.1, KK216089.1, KK216093.1, KK216094.1, KK216095.1, KK216096.1, KK216097.1, KK216098.1, KK216099.1, KK216102.1, KK216103.1, KK216106.1, KK216109.1, KK216111.1, KK216112.1, KK216113.1, KK216114.1, KK216115.1, KK216117.1, KK216118.1, KK216120.1, KK216122.1, KK216124.1, KK216125.1, KK216126.1, KK216128.1, KK216131.1, KK216133.1, KK216134.1, KK216135.1, KK216137.1, KK216138.1, KK216140.1, KK216141.1, KK216142.1, KK216143.1, KK216144.1, KK216145.1, KK216146.1, KK216150.1, KK216151.1, KK216152.1, KK216154.1, KK216155.1, KK216157.1, KK216158.1, KK216159.1, KK216160.1, KK216162.1, KK216163.1, KK216164.1, KK216165.1, KK216166.1, KK216168.1, KK216169.1, KK216171.1, KK216172.1, KK216173.1, KK216174.1, KK216175.1, KK216176.1, KK216177.1, KK216178.1, KK216180.1, KK216181.1, KK216182.1, KK216184.1, KK216186.1, KK216190.1, KK216192.1, KK216193.1, KK216194.1, KK216195.1, KK216197.1, KK216198.1, KK216200.1, KK216201.1, KK216202.1, KK216203.1, KK216205.1, KK216206.1, KK216208.1, KK216212.1, KK216213.1, KK216214.1, KK216215.1, KK216217.1, KK216219.1, KK216221.1, KK216222.1, KK216224.1, KK216225.1, KK216226.1, KK216227.1, KK216229.1, KK216231.1, KK216232.1, KK216234.1, KK216235.1, KK216236.1, KK216237.1, KK216238.1, KK216240.1, KK216241.1, KK216242.1, KK216244.1, KK216245.1, KK216248.1, KK216251.1, KK216252.1, KK216253.1, KK216254.1, KK216256.1, KK216258.1, KK216259.1, KK216260.1, KK216261.1, KK216262.1, KK216263.1, KK216264.1, KK216265.1, KK216266.1, KK216267.1, KK216269.1, KK216270.1, KK216272.1, KK216273.1, KK216275.1, KK216276.1, KK216278.1, KK216280.1, KK216281.1, KK216282.1, KK216283.1, KK216284.1, KK216285.1, KK216287.1, KK216288.1, KK216289.1, KK216290.1, KK216291.1, KK216293.1, KK216295.1, KK216296.1, KK216297.1, KK216299.1, KK216302.1, KK216303.1, KK216304.1, KK216306.1, KK216307.1, KK216308.1, KK216310.1, KK216311.1, KK216313.1, KK216315.1, KK216316.1, KK216317.1, KK216318.1, KK216319.1, KK216320.1, KK216321.1, KK216322.1, KK216323.1, KK216324.1, KK216325.1, KK216326.1, KK216328.1, KK216329.1, KK216330.1, KK216331.1, KK216333.1, KK216334.1, KK216337.1, KK216338.1, KK216341.1, KK216342.1, KK216343.1, KK216344.1, KK216345.1, KK216346.1, KK216347.1, KK216351.1, KK216353.1, KK216354.1, KK216356.1, KK216359.1, KK216360.1, KK216362.1, KK216363.1, KK216364.1, KK216365.1, KK216366.1, KK216368.1, KK216369.1, KK216370.1, KK216371.1, KK216372.1, KK216374.1, KK216375.1, KK216376.1, KK216377.1, KK216379.1, KK216381.1, KK216382.1, KK216383.1, KK216384.1, KK216386.1, KK216387.1, KK216388.1, KK216389.1, KK216390.1, KK216391.1, KK216392.1, KK216393.1, KK216394.ol1## Hits object with 121231 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 47 33417
## [2] 47 33416
## [3] 48 33417
## [4] 48 33416
## [5] 49 33417
## ... ... ...
## [121227] 611504 19561
## [121228] 611505 19562
## [121229] 611505 19561
## [121230] 611506 19562
## [121231] 611506 19561
## -------
## queryLength: 611561 / subjectLength: 34314CvLpromoters <- methylkitTilesCvLGR[queryHits(ol1)]
myPromotersol1 <- my_Promoters[subjectHits(ol1)]
head(CvLpromoters)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | pvalue qvalue meth.diff
## <Rle> <IRanges> <Rle> | <numeric> <numeric> <numeric>
## [1] KK215283.1 48001-49000 * | 0.000247297 0.00703713 3.89491
## [2] KK215283.1 48001-49000 * | 0.000247297 0.00703713 3.89491
## [3] KK215283.1 49001-50000 * | 0.017572709 0.10856320 3.30815
## [4] KK215283.1 49001-50000 * | 0.017572709 0.10856320 3.30815
## [5] KK215283.1 50001-51000 * | 0.167372450 0.37609640 -1.89436
## [6] KK215283.1 50001-51000 * | 0.167372450 0.37609640 -1.89436
## -------
## seqinfo: 2159 sequences from an unspecified genome; no seqlengthsmyPromotersol1## GRanges object with 121231 ranges and 3 metadata columns:
## seqnames ranges strand | V5
## <Rle> <IRanges> <Rle> | <character>
## [1] KK215283.1 48608-51609 - | ENSPREG00000017956
## [2] KK215283.1 48699-51700 - | ENSPREG00000017956
## [3] KK215283.1 48608-51609 - | ENSPREG00000017956
## [4] KK215283.1 48699-51700 - | ENSPREG00000017956
## [5] KK215283.1 48608-51609 - | ENSPREG00000017956
## ... ... ... ... . ...
## [121227] LG9 34111750-34114751 - | ENSPREG00000019150
## [121228] LG9 34111727-34114728 - | ENSPREG00000019150
## [121229] LG9 34111750-34114751 - | ENSPREG00000019150
## [121230] LG9 34111727-34114728 - | ENSPREG00000019150
## [121231] LG9 34111750-34114751 - | ENSPREG00000019150
## V6 V7
## <character> <character>
## [1] ENSPRET00000026836 usp6nl
## [2] ENSPRET00000026836 usp6nl
## [3] ENSPRET00000026836 usp6nl
## [4] ENSPRET00000026836 usp6nl
## [5] ENSPRET00000026836 usp6nl
## ... ... ...
## [121227] ENSPRET00000028600 FAM163B
## [121228] ENSPRET00000028600 FAM163B
## [121229] ENSPRET00000028600 FAM163B
## [121230] ENSPRET00000028600 FAM163B
## [121231] ENSPRET00000028600 FAM163B
## -------
## seqinfo: 452 sequences from an unspecified genome; no seqlengthsCvLpromotersdf <- as.data.frame(CvLpromoters,row.names = 1:nrow(as.data.frame(ranges(CvLpromoters))))
str(CvLpromotersdf)## 'data.frame': 121231 obs. of 8 variables:
## $ seqnames : Factor w/ 2159 levels "KK215283.1","KK215284.1",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ start : int 48001 48001 49001 49001 50001 50001 51001 51001 152001 153001 ...
## $ end : int 49000 49000 50000 50000 51000 51000 52000 52000 153000 154000 ...
## $ width : int 1000 1000 1000 1000 1000 1000 1000 1000 1000 1000 ...
## $ strand : Factor w/ 3 levels "+","-","*": 3 3 3 3 3 3 3 3 3 3 ...
## $ pvalue : num 0.000247 0.000247 0.017573 0.017573 0.167372 ...
## $ qvalue : num 0.00704 0.00704 0.10856 0.10856 0.3761 ...
## $ meth.diff: num 3.89 3.89 3.31 3.31 -1.89 ...myPromotersoldf1 <- as.data.frame(myPromotersol1,row.names = 1:nrow(as.data.frame(ranges(myPromotersol1))))
head(myPromotersoldf1)## seqnames start end width strand V5 V6
## 1 KK215283.1 48608 51609 3002 - ENSPREG00000017956 ENSPRET00000026836
## 2 KK215283.1 48699 51700 3002 - ENSPREG00000017956 ENSPRET00000026836
## 3 KK215283.1 48608 51609 3002 - ENSPREG00000017956 ENSPRET00000026836
## 4 KK215283.1 48699 51700 3002 - ENSPREG00000017956 ENSPRET00000026836
## 5 KK215283.1 48608 51609 3002 - ENSPREG00000017956 ENSPRET00000026836
## 6 KK215283.1 48699 51700 3002 - ENSPREG00000017956 ENSPRET00000026836
## V7
## 1 usp6nl
## 2 usp6nl
## 3 usp6nl
## 4 usp6nl
## 5 usp6nl
## 6 usp6nlCvLpromotersdf <- cbind(CvLpromotersdf,myPromotersoldf1[c("V5","V6","V7")])
CvLpromotersdf$seqnames <- as.character(CvLpromotersdf$seqnames)
head(CvLpromotersdf)## seqnames start end width strand pvalue qvalue meth.diff
## 1 KK215283.1 48001 49000 1000 * 0.0002472971 0.00703713 3.894907
## 2 KK215283.1 48001 49000 1000 * 0.0002472971 0.00703713 3.894907
## 3 KK215283.1 49001 50000 1000 * 0.0175727090 0.10856320 3.308154
## 4 KK215283.1 49001 50000 1000 * 0.0175727090 0.10856320 3.308154
## 5 KK215283.1 50001 51000 1000 * 0.1673724495 0.37609640 -1.894358
## 6 KK215283.1 50001 51000 1000 * 0.1673724495 0.37609640 -1.894358
## V5 V6 V7
## 1 ENSPREG00000017956 ENSPRET00000026836 usp6nl
## 2 ENSPREG00000017956 ENSPRET00000026836 usp6nl
## 3 ENSPREG00000017956 ENSPRET00000026836 usp6nl
## 4 ENSPREG00000017956 ENSPRET00000026836 usp6nl
## 5 ENSPREG00000017956 ENSPRET00000026836 usp6nl
## 6 ENSPREG00000017956 ENSPRET00000026836 usp6nlCvLpromoterschrdf <- CvLpromotersdf[grep("LG",CvLpromotersdf$seqnames),]
head(CvLpromoterschrdf)## seqnames start end width strand pvalue qvalue meth.diff
## 5069 LG1 369001 370000 1000 * 0.9286774 0.8115699 0.12780055
## 5070 LG1 370001 371000 1000 * 0.1466453 0.3515362 3.78593053
## 5071 LG1 371001 372000 1000 * 0.9564776 0.8198574 0.13100794
## 5072 LG1 417001 418000 1000 * 0.9788204 0.8264302 0.02779689
## 5073 LG1 418001 419000 1000 * 0.5807445 0.6738893 -0.45905043
## 5074 LG1 419001 420000 1000 * 0.6238856 0.6947058 0.38551032
## V5 V6 V7
## 5069 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 5070 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 5071 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 5072 ENSPREG00000000040 ENSPRET00000000040 uncharacterised
## 5073 ENSPREG00000000040 ENSPRET00000000040 uncharacterised
## 5074 ENSPREG00000000040 ENSPRET00000000040 uncharacterisedCvLpromoterschrdf <- CvLpromoterschrdf[order(CvLpromoterschrdf[,7]), ]
colnames(CvLpromoterschrdf) <- c("seqnames","start","end","width","strand","pvalue","qvalue","meth.diff","gene_id","V6","gene_name")
CvLpromoterschrdf <- CvLpromoterschrdf[which(rownames(CvLpromoterschrdf)%in%rownames(unique(CvLpromoterschrdf[,c("seqnames","start","gene_name")]))),]
head(CvLpromoterschrdf,50)## seqnames start end width strand pvalue qvalue
## 63161 LG2 20995001 20996000 1000 * 4.065070e-48 2.956357e-43
## 106383 LG7 18259001 18260000 1000 * 8.559718e-41 4.357590e-36
## 20949 LG11 28461001 28462000 1000 * 1.078697e-40 4.992221e-36
## 70661 LG21 538001 539000 1000 * 5.735034e-40 2.432998e-35
## 31311 LG14 4148001 4149000 1000 * 8.688214e-40 3.402312e-35
## 20618 LG11 27368001 27369000 1000 * 1.892756e-31 4.588411e-27
## 36545 LG15 10977001 10978000 1000 * 1.506553e-29 3.195656e-25
## 74546 LG21 23640001 23641000 1000 * 3.073884e-29 6.018677e-25
## 70641 LG21 525001 526000 1000 * 2.428540e-28 4.121079e-24
## 70642 LG21 525001 526000 1000 * 2.428540e-28 4.121079e-24
## 51832 LG18 4888001 4889000 1000 * 4.182440e-27 6.452124e-23
## 115239 LG8 27195001 27196000 1000 * 2.737017e-26 3.981038e-22
## 52654 LG18 8495001 8496000 1000 * 1.263746e-25 1.693024e-21
## 61839 LG2 14437001 14438000 1000 * 1.448573e-25 1.890874e-21
## 87348 LG4 4685001 4686000 1000 * 4.286691e-25 5.195889e-21
## 87036 LG4 3392001 3393000 1000 * 2.827911e-24 3.129644e-20
## 39782 LG16 262001 263000 1000 * 4.935184e-23 4.652609e-19
## 72218 LG21 9381001 9382000 1000 * 7.442204e-23 6.746760e-19
## 80183 LG23 6138001 6139000 1000 * 7.542854e-23 6.746760e-19
## 59136 LG19 25901001 25902000 1000 * 1.596133e-22 1.400967e-18
## 70312 LG20 25508001 25509000 1000 * 4.961261e-22 4.124959e-18
## 17251 LG11 10184001 10185000 1000 * 1.758368e-21 1.316400e-17
## 25429 LG12 26139001 26140000 1000 * 1.879367e-21 1.386594e-17
## 32740 LG14 10074001 10075000 1000 * 3.453622e-21 2.476301e-17
## 18198 LG11 14223001 14224000 1000 * 5.614843e-21 3.970015e-17
## 72630 LG21 11205001 11206000 1000 * 5.524836e-20 3.232861e-16
## 106094 LG7 17085001 17086000 1000 * 7.610205e-20 4.402513e-16
## 41130 LG16 6723001 6724000 1000 * 1.185920e-19 6.562277e-16
## 115225 LG8 27128001 27129000 1000 * 1.804360e-19 9.568393e-16
## 115226 LG8 27128001 27129000 1000 * 1.804360e-19 9.568393e-16
## 46090 LG17 936001 937000 1000 * 2.189746e-19 1.137508e-15
## 107908 LG7 26483001 26484000 1000 * 1.937343e-18 9.217424e-15
## 39621 LG15 30358001 30359000 1000 * 3.001852e-18 1.340514e-14
## 77403 LG22 14521001 14522000 1000 * 6.804987e-18 2.960932e-14
## 93302 LG5 6245001 6246000 1000 * 7.724966e-18 3.332740e-14
## 113036 LG8 18444001 18445000 1000 * 1.739921e-17 7.143231e-14
## 46752 LG17 4434001 4435000 1000 * 2.794487e-17 1.129064e-13
## 9958 LG1 26801001 26802000 1000 * 1.030599e-16 3.694779e-13
## 8365 LG1 18070001 18071000 1000 * 1.936849e-16 6.518408e-13
## 20833 LG11 28250001 28251000 1000 * 2.036616e-16 6.732485e-13
## 20834 LG11 28250001 28251000 1000 * 2.036616e-16 6.732485e-13
## 86884 LG4 2175001 2176000 1000 * 2.158572e-16 7.044156e-13
## 79414 LG23 1377001 1378000 1000 * 2.455011e-16 7.762731e-13
## 86516 LG3 33819001 33820000 1000 * 2.655718e-16 8.243753e-13
## 56249 LG19 8951001 8952000 1000 * 3.851640e-16 1.133409e-12
## 21744 LG12 3809001 3810000 1000 * 4.255568e-16 1.230926e-12
## 105497 LG7 14104001 14105000 1000 * 4.412111e-16 1.268996e-12
## 98734 LG6 6024001 6025000 1000 * 5.162607e-16 1.452036e-12
## 68125 LG20 10565001 10566000 1000 * 5.979903e-16 1.654487e-12
## 40232 LG16 1772001 1773000 1000 * 6.034607e-16 1.660597e-12
## meth.diff gene_id V6 gene_name
## 63161 -20.266832 ENSPREG00000014846 ENSPRET00000022204 zgc:194275
## 106383 23.291524 ENSPREG00000003617 ENSPRET00000005305 uts2a
## 20949 -13.623576 ENSPREG00000010182 ENSPRET00000015234 tfap2e
## 70661 -13.783047 ENSPREG00000012722 ENSPRET00000019142 uncharacterised
## 31311 -21.043219 ENSPREG00000009393 ENSPRET00000014038 zgc:112437
## 20618 13.365924 ENSPREG00000008406 ENSPRET00000012667 fabp10b
## 36545 -11.297619 ENSPREG00000009538 ENSPRET00000014224 grid1a
## 74546 -19.150044 ENSPREG00000001261 ENSPRET00000001765 gabrr2b
## 70641 -14.582528 ENSPREG00000012371 ENSPRET00000018458 uncharacterised
## 70642 -14.582528 ENSPREG00000012615 ENSPRET00000018820 crnkl1
## 51832 -14.779337 ENSPREG00000004844 ENSPRET00000007125 uncharacterised
## 115239 12.089474 ENSPREG00000011953 ENSPRET00000017861 mvp
## 52654 -19.846524 ENSPREG00000010979 ENSPRET00000016449 dnajc3b
## 61839 -9.041329 ENSPREG00000003675 ENSPRET00000005379 dhrs12
## 87348 11.527850 ENSPREG00000003007 ENSPRET00000004307 uncharacterised
## 87036 -7.442466 ENSPREG00000022798 ENSPRET00000034024 si:ch211-198n5.11
## 39782 12.931286 ENSPREG00000014351 ENSPRET00000021444 uncharacterised
## 72218 -16.843180 ENSPREG00000005263 ENSPRET00000007773 ostm1
## 80183 -13.552038 ENSPREG00000004887 ENSPRET00000007189 TMEM60
## 59136 -17.081765 ENSPREG00000001288 ENSPRET00000001784 galk1
## 70312 -17.938777 ENSPREG00000010635 ENSPRET00000015945 uncharacterised
## 17251 6.626665 ENSPREG00000021725 ENSPRET00000032420 hoxa5a
## 25429 8.860628 ENSPREG00000007143 ENSPRET00000010589 spra
## 32740 -9.171029 ENSPREG00000022506 ENSPRET00000033581 gnb2
## 18198 -14.280181 ENSPREG00000007615 ENSPRET00000011309 lrrc14b
## 72630 -8.563215 ENSPREG00000008410 ENSPRET00000012534 nfkbie
## 106094 13.327808 ENSPREG00000001520 ENSPRET00000002091 zgc:198371
## 41130 10.126664 ENSPREG00000003585 ENSPRET00000005191 tnfb
## 115225 12.152390 ENSPREG00000011868 ENSPRET00000017736 sgf29
## 115226 12.152390 ENSPREG00000011889 ENSPRET00000017756 nupr1b
## 46090 -9.782204 ENSPREG00000021836 ENSPRET00000032596 uncharacterised
## 107908 -8.279852 ENSPREG00000020332 ENSPRET00000030363 hoxc4a
## 39621 -8.651465 ENSPREG00000013474 ENSPRET00000020140 uncharacterised
## 77403 -23.246876 ENSPREG00000003390 ENSPRET00000004900 uncharacterised
## 93302 10.197080 ENSPREG00000005431 ENSPRET00000008086 A3GALT2
## 113036 -5.791803 ENSPREG00000011051 ENSPRET00000016508 akt1s1
## 46752 -12.258747 ENSPREG00000004307 ENSPRET00000006277 uncharacterised
## 9958 -4.919240 ENSPREG00000021245 ENSPRET00000031717 CNNM1
## 8365 -14.772477 ENSPREG00000005128 ENSPRET00000007557 slc25a4
## 20833 6.101246 ENSPREG00000009817 ENSPRET00000014653 uncharacterised
## 20834 6.101246 ENSPREG00000009828 ENSPRET00000014669 smim13
## 86884 -8.900972 ENSPREG00000021655 ENSPRET00000032328 U1
## 79414 -11.443555 ENSPREG00000022413 ENSPRET00000033466 ppfia2
## 86516 -9.315578 ENSPREG00000019149 ENSPRET00000028603 uncharacterised
## 56249 -17.149610 ENSPREG00000023154 ENSPRET00000034560 zgc:123217
## 21744 1.608623 ENSPREG00000018037 ENSPRET00000026958 ZSWIM6
## 105497 15.792709 ENSPREG00000020868 ENSPRET00000031165 uncharacterised
## 98734 -8.331926 ENSPREG00000007903 ENSPRET00000011732 uncharacterised
## 68125 -7.808026 ENSPREG00000014982 ENSPRET00000022436 uncharacterised
## 40232 -17.194137 ENSPREG00000017337 ENSPRET00000025948 rab25bnrow(subset(CvLpromoterschrdf,qvalue<0.05))## [1] 7784nrow(subset(CvLpromoterschrdf,qvalue<0.05&meth.diff>0))## [1] 3285nrow(subset(CvLpromoterschrdf,qvalue<0.05&meth.diff<0))## [1] 4499saveRDS(object=CvLpromoterschrdf,file="CvLtiles_genepromoters.rds",compress="gzip")
rm(CvLpromoters)
rm(CvLpromotersdf)ol1 <- findOverlaps(methylkitTilesGvLGR,my_Promoters)## Warning in .Seqinfo.mergexy(x, y): Each of the 2 combined objects has sequence levels not in the other:
## - in 'x': KK215332.1, KK215339.1, KK215341.1, KK215351.1, KK215360.1, KK215378.1, KK215383.1, KK215387.1, KK215391.1, KK215393.1, KK215395.1, KK215396.1, KK215397.1, KK215400.1, KK215401.1, KK215402.1, KK215403.1, KK215405.1, KK215406.1, KK215407.1, KK215408.1, KK215411.1, KK215412.1, KK215414.1, KK215415.1, KK215418.1, KK215419.1, KK215420.1, KK215421.1, KK215424.1, KK215425.1, KK215427.1, KK215429.1, KK215430.1, KK215432.1, KK215433.1, KK215435.1, KK215439.1, KK215440.1, KK215441.1, KK215443.1, KK215444.1, KK215446.1, KK215448.1, KK215451.1, KK215453.1, KK215454.1, KK215455.1, KK215456.1, KK215459.1, KK215462.1, KK215463.1, KK215465.1, KK215466.1, KK215467.1, KK215472.1, KK215474.1, KK215475.1, KK215479.1, KK215480.1, KK215482.1, KK215484.1, KK215485.1, KK215486.1, KK215488.1, KK215490.1, KK215491.1, KK215492.1, KK215494.1, KK215496.1, KK215497.1, KK215498.1, KK215501.1, KK215502.1, KK215503.1, KK215504.1, KK215506.1, KK215507.1, KK215508.1, KK215511.1, KK215512.1, KK215513.1, KK215514.1, KK215515.1, KK215516.1, KK215517.1, KK215518.1, KK215519.1, KK215521.1, KK215523.1, KK215524.1, KK215525.1, KK215526.1, KK215528.1, KK215529.1, KK215530.1, KK215531.1, KK215533.1, KK215538.1, KK215540.1, KK215541.1, KK215543.1, KK215544.1, KK215545.1, KK215546.1, KK215547.1, KK215548.1, KK215549.1, KK215551.1, KK215553.1, KK215554.1, KK215556.1, KK215558.1, KK215559.1, KK215560.1, KK215561.1, KK215562.1, KK215567.1, KK215568.1, KK215573.1, KK215574.1, KK215577.1, KK215578.1, KK215579.1, KK215581.1, KK215582.1, KK215583.1, KK215584.1, KK215585.1, KK215586.1, KK215587.1, KK215588.1, KK215589.1, KK215590.1, KK215594.1, KK215595.1, KK215597.1, KK215598.1, KK215601.1, KK215602.1, KK215603.1, KK215605.1, KK215606.1, KK215608.1, KK215615.1, KK215616.1, KK215620.1, KK215621.1, KK215622.1, KK215624.1, KK215625.1, KK215626.1, KK215627.1, KK215628.1, KK215629.1, KK215630.1, KK215632.1, KK215633.1, KK215634.1, KK215635.1, KK215636.1, KK215637.1, KK215638.1, KK215639.1, KK215641.1, KK215642.1, KK215644.1, KK215645.1, KK215646.1, KK215647.1, KK215649.1, KK215652.1, KK215654.1, KK215655.1, KK215657.1, KK215658.1, KK215661.1, KK215662.1, KK215663.1, KK215664.1, KK215665.1, KK215668.1, KK215669.1, KK215670.1, KK215671.1, KK215672.1, KK215673.1, KK215675.1, KK215677.1, KK215678.1, KK215683.1, KK215684.1, KK215688.1, KK215689.1, KK215692.1, KK215694.1, KK215695.1, KK215699.1, KK215700.1, KK215701.1, KK215703.1, KK215704.1, KK215705.1, KK215706.1, KK215707.1, KK215709.1, KK215710.1, KK215711.1, KK215712.1, KK215715.1, KK215718.1, KK215719.1, KK215720.1, KK215721.1, KK215722.1, KK215723.1, KK215724.1, KK215726.1, KK215727.1, KK215728.1, KK215733.1, KK215734.1, KK215736.1, KK215737.1, KK215738.1, KK215739.1, KK215740.1, KK215741.1, KK215742.1, KK215743.1, KK215745.1, KK215748.1, KK215750.1, KK215752.1, KK215753.1, KK215754.1, KK215755.1, KK215756.1, KK215757.1, KK215758.1, KK215759.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215767.1, KK215768.1, KK215769.1, KK215770.1, KK215771.1, KK215772.1, KK215774.1, KK215775.1, KK215776.1, KK215777.1, KK215778.1, KK215779.1, KK215780.1, KK215782.1, KK215783.1, KK215785.1, KK215786.1, KK215788.1, KK215789.1, KK215792.1, KK215794.1, KK215795.1, KK215796.1, KK215797.1, KK215798.1, KK215802.1, KK215804.1, KK215805.1, KK215807.1, KK215810.1, KK215812.1, KK215814.1, KK215815.1, KK215816.1, KK215818.1, KK215819.1, KK215821.1, KK215825.1, KK215827.1, KK215832.1, KK215834.1, KK215836.1, KK215837.1, KK215838.1, KK215839.1, KK215840.1, KK215841.1, KK215842.1, KK215843.1, KK215846.1, KK215847.1, KK215848.1, KK215849.1, KK215851.1, KK215852.1, KK215854.1, KK215857.1, KK215858.1, KK215859.1, KK215860.1, KK215861.1, KK215863.1, KK215864.1, KK215865.1, KK215866.1, KK215867.1, KK215869.1, KK215870.1, KK215872.1, KK215873.1, KK215875.1, KK215877.1, KK215878.1, KK215880.1, KK215881.1, KK215882.1, KK215884.1, KK215885.1, KK215886.1, KK215890.1, KK215891.1, KK215892.1, KK215893.1, KK215894.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215902.1, KK215903.1, KK215905.1, KK215907.1, KK215908.1, KK215909.1, KK215910.1, KK215911.1, KK215913.1, KK215915.1, KK215917.1, KK215918.1, KK215920.1, KK215921.1, KK215922.1, KK215923.1, KK215924.1, KK215927.1, KK215928.1, KK215929.1, KK215933.1, KK215934.1, KK215935.1, KK215937.1, KK215938.1, KK215940.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215946.1, KK215949.1, KK215951.1, KK215952.1, KK215953.1, KK215956.1, KK215957.1, KK215960.1, KK215962.1, KK215963.1, KK215965.1, KK215967.1, KK215969.1, KK215970.1, KK215971.1, KK215972.1, KK215973.1, KK215974.1, KK215975.1, KK215976.1, KK215977.1, KK215978.1, KK215979.1, KK215982.1, KK215983.1, KK215984.1, KK215985.1, KK215987.1, KK215989.1, KK215990.1, KK215993.1, KK215994.1, KK215995.1, KK215996.1, KK215997.1, KK215999.1, KK216000.1, KK216001.1, KK216005.1, KK216006.1, KK216007.1, KK216008.1, KK216009.1, KK216011.1, KK216012.1, KK216015.1, KK216017.1, KK216018.1, KK216021.1, KK216022.1, KK216023.1, KK216024.1, KK216025.1, KK216026.1, KK216027.1, KK216028.1, KK216029.1, KK216030.1, KK216032.1, KK216033.1, KK216034.1, KK216035.1, KK216036.1, KK216037.1, KK216038.1, KK216039.1, KK216040.1, KK216041.1, KK216042.1, KK216043.1, KK216044.1, KK216047.1, KK216048.1, KK216049.1, KK216050.1, KK216053.1, KK216055.1, KK216056.1, KK216058.1, KK216059.1, KK216062.1, KK216063.1, KK216064.1, KK216065.1, KK216066.1, KK216067.1, KK216068.1, KK216069.1, KK216070.1, KK216071.1, KK216072.1, KK216074.1, KK216075.1, KK216076.1, KK216077.1, KK216078.1, KK216079.1, KK216080.1, KK216082.1, KK216083.1, KK216084.1, KK216085.1, KK216086.1, KK216087.1, KK216089.1, KK216091.1, KK216093.1, KK216094.1, KK216095.1, KK216096.1, KK216097.1, KK216098.1, KK216099.1, KK216102.1, KK216103.1, KK216106.1, KK216109.1, KK216110.1, KK216111.1, KK216112.1, KK216113.1, KK216114.1, KK216115.1, KK216117.1, KK216118.1, KK216120.1, KK216122.1, KK216124.1, KK216125.1, KK216126.1, KK216128.1, KK216131.1, KK216133.1, KK216134.1, KK216135.1, KK216137.1, KK216138.1, KK216140.1, KK216141.1, KK216142.1, KK216143.1, KK216144.1, KK216145.1, KK216146.1, KK216150.1, KK216151.1, KK216152.1, KK216154.1, KK216155.1, KK216157.1, KK216158.1, KK216159.1, KK216160.1, KK216162.1, KK216163.1, KK216164.1, KK216165.1, KK216166.1, KK216168.1, KK216169.1, KK216171.1, KK216172.1, KK216173.1, KK216174.1, KK216175.1, KK216176.1, KK216177.1, KK216178.1, KK216180.1, KK216181.1, KK216182.1, KK216184.1, KK216186.1, KK216190.1, KK216192.1, KK216193.1, KK216194.1, KK216195.1, KK216197.1, KK216198.1, KK216200.1, KK216201.1, KK216202.1, KK216203.1, KK216205.1, KK216206.1, KK216208.1, KK216212.1, KK216213.1, KK216214.1, KK216215.1, KK216217.1, KK216218.1, KK216219.1, KK216221.1, KK216222.1, KK216224.1, KK216225.1, KK216226.1, KK216227.1, KK216229.1, KK216231.1, KK216232.1, KK216234.1, KK216235.1, KK216236.1, KK216237.1, KK216238.1, KK216239.1, KK216240.1, KK216241.1, KK216242.1, KK216244.1, KK216245.1, KK216248.1, KK216251.1, KK216252.1, KK216253.1, KK216254.1, KK216256.1, KK216258.1, KK216259.1, KK216260.1, KK216261.1, KK216262.1, KK216263.1, KK216264.1, KK216265.1, KK216266.1, KK216267.1, KK216269.1, KK216270.1, KK216271.1, KK216272.1, KK216273.1, KK216275.1, KK216276.1, KK216278.1, KK216280.1, KK216281.1, KK216282.1, KK216283.1, KK216284.1, KK216285.1, KK216287.1, KK216288.1, KK216289.1, KK216290.1, KK216291.1, KK216293.1, KK216295.1, KK216296.1, KK216297.1, KK216298.1, KK216299.1, KK216302.1, KK216303.1, KK216304.1, KK216306.1, KK216307.1, KK216308.1, KK216310.1, KK216311.1, KK216313.1, KK216315.1, KK216316.1, KK216317.1, KK216318.1, KK216319.1, KK216320.1, KK216321.1, KK216322.1, KK216323.1, KK216324.1, KK216325.1, KK216326.1, KK216327.1, KK216328.1, KK216329.1, KK216330.1, KK216331.1, KK216333.1, KK216334.1, KK216336.1, KK216337.1, KK216338.1, KK216340.1, KK216341.1, KK216342.1, KK216343.1, KK216344.1, KK216345.1, KK216346.1, KK216347.1, KK216349.1, KK216351.1, KK216353.1, KK216354.1, KK216356.1, KK216357.1, KK216359.1, KK216360.1, KK216362.1, KK216363.1, KK216364.1, KK216365.1, KK216366.1, KK216368.1, KK216369.1, KK216370.1, KK216371.1, KK216372.1, KK216374.ol1## Hits object with 123972 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 47 33417
## [2] 47 33416
## [3] 48 33417
## [4] 48 33416
## [5] 49 33417
## ... ... ...
## [123968] 628125 19561
## [123969] 628126 19562
## [123970] 628126 19561
## [123971] 628127 19562
## [123972] 628127 19561
## -------
## queryLength: 628182 / subjectLength: 34314GvLpromoters <- methylkitTilesGvLGR[queryHits(ol1)]
myPromotersol1 <- my_Promoters[subjectHits(ol1)]
head(GvLpromoters)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | pvalue qvalue meth.diff
## <Rle> <IRanges> <Rle> | <numeric> <numeric> <numeric>
## [1] KK215283.1 48001-49000 * | 7.39691e-07 0.000100273 4.90753
## [2] KK215283.1 48001-49000 * | 7.39691e-07 0.000100273 4.90753
## [3] KK215283.1 49001-50000 * | 9.08920e-02 0.272105893 1.97989
## [4] KK215283.1 49001-50000 * | 9.08920e-02 0.272105893 1.97989
## [5] KK215283.1 50001-51000 * | 2.33511e-01 0.441112158 -1.50361
## [6] KK215283.1 50001-51000 * | 2.33511e-01 0.441112158 -1.50361
## -------
## seqinfo: 2259 sequences from an unspecified genome; no seqlengthsmyPromotersol1## GRanges object with 123972 ranges and 3 metadata columns:
## seqnames ranges strand | V5
## <Rle> <IRanges> <Rle> | <character>
## [1] KK215283.1 48608-51609 - | ENSPREG00000017956
## [2] KK215283.1 48699-51700 - | ENSPREG00000017956
## [3] KK215283.1 48608-51609 - | ENSPREG00000017956
## [4] KK215283.1 48699-51700 - | ENSPREG00000017956
## [5] KK215283.1 48608-51609 - | ENSPREG00000017956
## ... ... ... ... . ...
## [123968] LG9 34111750-34114751 - | ENSPREG00000019150
## [123969] LG9 34111727-34114728 - | ENSPREG00000019150
## [123970] LG9 34111750-34114751 - | ENSPREG00000019150
## [123971] LG9 34111727-34114728 - | ENSPREG00000019150
## [123972] LG9 34111750-34114751 - | ENSPREG00000019150
## V6 V7
## <character> <character>
## [1] ENSPRET00000026836 usp6nl
## [2] ENSPRET00000026836 usp6nl
## [3] ENSPRET00000026836 usp6nl
## [4] ENSPRET00000026836 usp6nl
## [5] ENSPRET00000026836 usp6nl
## ... ... ...
## [123968] ENSPRET00000028600 FAM163B
## [123969] ENSPRET00000028600 FAM163B
## [123970] ENSPRET00000028600 FAM163B
## [123971] ENSPRET00000028600 FAM163B
## [123972] ENSPRET00000028600 FAM163B
## -------
## seqinfo: 452 sequences from an unspecified genome; no seqlengthsGvLpromotersdf <- as.data.frame(GvLpromoters,row.names = 1:nrow(as.data.frame(ranges(GvLpromoters))))
str(GvLpromotersdf)## 'data.frame': 123972 obs. of 8 variables:
## $ seqnames : Factor w/ 2259 levels "KK215283.1","KK215284.1",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ start : int 48001 48001 49001 49001 50001 50001 51001 51001 152001 153001 ...
## $ end : int 49000 49000 50000 50000 51000 51000 52000 52000 153000 154000 ...
## $ width : int 1000 1000 1000 1000 1000 1000 1000 1000 1000 1000 ...
## $ strand : Factor w/ 3 levels "+","-","*": 3 3 3 3 3 3 3 3 3 3 ...
## $ pvalue : num 7.40e-07 7.40e-07 9.09e-02 9.09e-02 2.34e-01 ...
## $ qvalue : num 0.0001 0.0001 0.2721 0.2721 0.4411 ...
## $ meth.diff: num 4.91 4.91 1.98 1.98 -1.5 ...myPromotersoldf1 <- as.data.frame(myPromotersol1,row.names = 1:nrow(as.data.frame(ranges(myPromotersol1))))
head(myPromotersoldf1)## seqnames start end width strand V5 V6
## 1 KK215283.1 48608 51609 3002 - ENSPREG00000017956 ENSPRET00000026836
## 2 KK215283.1 48699 51700 3002 - ENSPREG00000017956 ENSPRET00000026836
## 3 KK215283.1 48608 51609 3002 - ENSPREG00000017956 ENSPRET00000026836
## 4 KK215283.1 48699 51700 3002 - ENSPREG00000017956 ENSPRET00000026836
## 5 KK215283.1 48608 51609 3002 - ENSPREG00000017956 ENSPRET00000026836
## 6 KK215283.1 48699 51700 3002 - ENSPREG00000017956 ENSPRET00000026836
## V7
## 1 usp6nl
## 2 usp6nl
## 3 usp6nl
## 4 usp6nl
## 5 usp6nl
## 6 usp6nlGvLpromotersdf <- cbind(GvLpromotersdf,myPromotersoldf1[c("V5","V6","V7")])
GvLpromotersdf$seqnames <- as.character(GvLpromotersdf$seqnames)
head(GvLpromotersdf)## seqnames start end width strand pvalue qvalue meth.diff
## 1 KK215283.1 48001 49000 1000 * 7.396905e-07 0.0001002726 4.907530
## 2 KK215283.1 48001 49000 1000 * 7.396905e-07 0.0001002726 4.907530
## 3 KK215283.1 49001 50000 1000 * 9.089199e-02 0.2721058928 1.979890
## 4 KK215283.1 49001 50000 1000 * 9.089199e-02 0.2721058928 1.979890
## 5 KK215283.1 50001 51000 1000 * 2.335110e-01 0.4411121582 -1.503605
## 6 KK215283.1 50001 51000 1000 * 2.335110e-01 0.4411121582 -1.503605
## V5 V6 V7
## 1 ENSPREG00000017956 ENSPRET00000026836 usp6nl
## 2 ENSPREG00000017956 ENSPRET00000026836 usp6nl
## 3 ENSPREG00000017956 ENSPRET00000026836 usp6nl
## 4 ENSPREG00000017956 ENSPRET00000026836 usp6nl
## 5 ENSPREG00000017956 ENSPRET00000026836 usp6nl
## 6 ENSPREG00000017956 ENSPRET00000026836 usp6nlGvLpromoterschrdf <- GvLpromotersdf[grep("LG",GvLpromotersdf$seqnames),]
head(GvLpromoterschrdf)## seqnames start end width strand pvalue qvalue meth.diff
## 5249 LG1 369001 370000 1000 * 0.32894138 0.5204025 -1.2115234
## 5250 LG1 370001 371000 1000 * 0.06338203 0.2239325 -4.2515205
## 5251 LG1 371001 372000 1000 * 0.07465046 0.2447560 4.1890014
## 5252 LG1 417001 418000 1000 * 0.24771108 0.4541834 -1.1212499
## 5253 LG1 418001 419000 1000 * 0.40156661 0.5711652 -0.6017048
## 5254 LG1 419001 420000 1000 * 0.93905746 0.8136933 -0.0525200
## V5 V6 V7
## 5249 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 5250 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 5251 ENSPREG00000000039 ENSPRET00000000039 uncharacterised
## 5252 ENSPREG00000000040 ENSPRET00000000040 uncharacterised
## 5253 ENSPREG00000000040 ENSPRET00000000040 uncharacterised
## 5254 ENSPREG00000000040 ENSPRET00000000040 uncharacterisedGvLpromoterschrdf <- GvLpromoterschrdf[order(GvLpromoterschrdf[,7]), ]
colnames(GvLpromoterschrdf) <- c("seqnames","start","end","width","strand","pvalue","qvalue","meth.diff","gene_id","transcript_id","gene_name")
GvLpromoterschrdf <- GvLpromoterschrdf[which(rownames(GvLpromoterschrdf)%in%rownames(unique(GvLpromoterschrdf[,c("seqnames","start","gene_name")]))),]
head(GvLpromoterschrdf,50)## seqnames start end width strand pvalue qvalue
## 88849 LG4 1847001 1848000 1000 * 7.503577e-141 3.921253e-135
## 88850 LG4 1847001 1848000 1000 * 7.503577e-141 3.921253e-135
## 88847 LG4 1846001 1847000 1000 * 8.017760e-104 2.094979e-98
## 88848 LG4 1846001 1847000 1000 * 8.017760e-104 2.094979e-98
## 72353 LG21 538001 539000 1000 * 5.180641e-40 4.512205e-35
## 32069 LG14 4148001 4149000 1000 * 2.644311e-35 1.727345e-30
## 47593 LG17 3558001 3559000 1000 * 8.543377e-35 4.960707e-30
## 8532 LG1 17897001 17898000 1000 * 2.744822e-33 1.434401e-28
## 8533 LG1 17897001 17898000 1000 * 2.744822e-33 1.434401e-28
## 94665 LG5 2971001 2972000 1000 * 5.782685e-32 2.518285e-27
## 47803 LG17 4434001 4435000 1000 * 7.173123e-31 2.677545e-26
## 21465 LG11 28461001 28462000 1000 * 1.453293e-28 4.079260e-24
## 22282 LG12 3809001 3810000 1000 * 8.326373e-28 2.175617e-23
## 28392 LG13 17708001 17709000 1000 * 9.099195e-28 2.264333e-23
## 64666 LG2 20995001 20996000 1000 * 4.298768e-27 9.360290e-23
## 118077 LG8 27880001 27881000 1000 * 4.180084e-27 9.360290e-23
## 53035 LG18 4888001 4889000 1000 * 1.242411e-25 2.028953e-21
## 117861 LG8 27195001 27196000 1000 * 7.887942e-25 1.212387e-20
## 93902 LG4 29343001 29344000 1000 * 1.006482e-23 1.314930e-19
## 118228 LG9 1044001 1045000 1000 * 2.615483e-23 3.254311e-19
## 65881 LG2 27977001 27978000 1000 * 1.469236e-22 1.651170e-18
## 65882 LG2 27977001 27978000 1000 * 1.469236e-22 1.651170e-18
## 12177 LG10 5124001 5125000 1000 * 6.513977e-22 6.546353e-18
## 40401 LG15 29800001 29801000 1000 * 6.507149e-22 6.546353e-18
## 56130 LG19 600001 601000 1000 * 8.752257e-22 8.315989e-18
## 117089 LG8 24182001 24183000 1000 * 9.608583e-21 8.326629e-17
## 6720 LG1 9073001 9074000 1000 * 1.030136e-20 8.682789e-17
## 75381 LG21 16656001 16657000 1000 * 1.711524e-20 1.355176e-16
## 73093 LG21 5165001 5166000 1000 * 2.026204e-20 1.557151e-16
## 82037 LG23 6138001 6139000 1000 * 4.229792e-20 3.113273e-16
## 108797 LG7 18259001 18260000 1000 * 5.473349e-19 3.446130e-15
## 25886 LG12 25520001 25521000 1000 * 6.191884e-19 3.852122e-15
## 72333 LG21 525001 526000 1000 * 9.321717e-19 5.664401e-15
## 72334 LG21 525001 526000 1000 * 9.321717e-19 5.664401e-15
## 87790 LG3 28941001 28942000 1000 * 1.140042e-18 6.694025e-15
## 98700 LG5 24679001 24680000 1000 * 1.953426e-18 1.052402e-14
## 21374 LG11 28291001 28292000 1000 * 2.269693e-18 1.198087e-14
## 33866 LG14 11275001 11276000 1000 * 3.973062e-18 1.940430e-14
## 77934 LG22 8861001 8862000 1000 * 5.519080e-18 2.646042e-14
## 29101 LG13 21440001 21441000 1000 * 1.419891e-17 6.396663e-14
## 47829 LG17 4493001 4494000 1000 * 1.471745e-17 6.573598e-14
## 77935 LG22 8862001 8863000 1000 * 5.235978e-17 2.137689e-13
## 15115 LG10 24446001 24447000 1000 * 1.186494e-16 4.460743e-13
## 8607 LG1 18070001 18071000 1000 * 2.034900e-16 7.333844e-13
## 47130 LG17 936001 937000 1000 * 2.643664e-16 9.398216e-13
## 55686 LG18 21125001 21126000 1000 * 3.441787e-16 1.183306e-12
## 50960 LG17 22401001 22402000 1000 * 5.470871e-16 1.775772e-12
## 47039 LG17 710001 711000 1000 * 9.352467e-16 2.874973e-12
## 47749 LG17 4283001 4284000 1000 * 1.088387e-15 3.287712e-12
## 25043 LG12 19333001 19334000 1000 * 1.416712e-15 4.113065e-12
## meth.diff gene_id transcript_id gene_name
## 88849 -19.016257 ENSPREG00000021468 ENSPRET00000032035 gpc5b
## 88850 -19.016257 ENSPREG00000021490 ENSPRET00000032090 nasp
## 88847 -19.309795 ENSPREG00000021468 ENSPRET00000032035 gpc5b
## 88848 -19.309795 ENSPREG00000021490 ENSPRET00000032090 nasp
## 72353 -12.608880 ENSPREG00000012722 ENSPRET00000019142 uncharacterised
## 32069 -17.151052 ENSPREG00000009393 ENSPRET00000014038 zgc:112437
## 47593 19.287516 ENSPREG00000002699 ENSPRET00000003812 uncharacterised
## 8532 4.758557 ENSPREG00000004582 ENSPRET00000006703 uncharacterised
## 8533 4.758557 ENSPREG00000004594 ENSPRET00000006746 lgi2b
## 94665 -13.468644 ENSPREG00000022867 ENSPRET00000034154 asb14a
## 47803 -15.590322 ENSPREG00000004307 ENSPRET00000006277 uncharacterised
## 21465 -10.520805 ENSPREG00000010182 ENSPRET00000015234 tfap2e
## 22282 1.780137 ENSPREG00000018037 ENSPRET00000026958 ZSWIM6
## 28392 15.489531 ENSPREG00000022956 ENSPRET00000034268 uncharacterised
## 64666 -13.793773 ENSPREG00000014846 ENSPRET00000022204 zgc:194275
## 118077 -11.484597 ENSPREG00000013036 ENSPRET00000019524 uncharacterised
## 53035 -13.589308 ENSPREG00000004844 ENSPRET00000007125 uncharacterised
## 117861 10.650774 ENSPREG00000011953 ENSPRET00000017861 mvp
## 93902 5.650027 ENSPREG00000018536 ENSPRET00000027704 rnf11b
## 118228 11.639632 ENSPREG00000014053 ENSPRET00000020996 zgc:64051
## 65881 14.431800 ENSPREG00000000547 ENSPRET00000000766 GPR89B
## 65882 14.431800 ENSPREG00000000555 ENSPRET00000000771 zgc:113337
## 12177 7.416709 ENSPREG00000022019 ENSPRET00000032858 uncharacterised
## 40401 4.145243 ENSPREG00000012251 ENSPRET00000018308 uncharacterised
## 56130 15.084020 ENSPREG00000016582 ENSPRET00000024795 uncharacterised
## 117089 -4.534799 ENSPREG00000007071 ENSPRET00000010488 gprc5ba
## 6720 -9.327175 ENSPREG00000000312 ENSPRET00000000435 slx4
## 75381 -8.765341 ENSPREG00000015620 ENSPRET00000023480 entpd5b
## 73093 16.362007 ENSPREG00000018419 ENSPRET00000027544 slc30a2
## 82037 -11.125183 ENSPREG00000004887 ENSPRET00000007189 TMEM60
## 108797 14.371317 ENSPREG00000003617 ENSPRET00000005305 uts2a
## 25886 6.335628 ENSPREG00000005998 ENSPRET00000008873 uncharacterised
## 72333 -10.677087 ENSPREG00000012371 ENSPRET00000018458 uncharacterised
## 72334 -10.677087 ENSPREG00000012615 ENSPRET00000018820 crnkl1
## 87790 -14.230245 ENSPREG00000012212 ENSPRET00000018240 uncharacterised
## 98700 11.097071 ENSPREG00000012853 ENSPRET00000019215 ankrd33ab
## 21374 6.778916 ENSPREG00000009854 ENSPRET00000014711 eya3
## 33866 11.925891 ENSPREG00000023124 ENSPRET00000034520 KCNAB3
## 77934 12.915100 ENSPREG00000015260 ENSPRET00000022840 uncharacterised
## 29101 10.316344 ENSPREG00000005224 ENSPRET00000007683 uncharacterised
## 47829 -14.939055 ENSPREG00000004418 ENSPRET00000006446 TMEM69
## 77935 11.659553 ENSPREG00000015260 ENSPRET00000022840 uncharacterised
## 15115 -9.413947 ENSPREG00000001077 ENSPRET00000001487 uncharacterised
## 8607 -13.034439 ENSPREG00000005128 ENSPRET00000007557 slc25a4
## 47130 -8.374901 ENSPREG00000021836 ENSPRET00000032596 uncharacterised
## 55686 9.317910 ENSPREG00000005872 ENSPRET00000008705 uncharacterised
## 50960 -12.836569 ENSPREG00000010283 ENSPRET00000015408 uncharacterised
## 47039 -17.118200 ENSPREG00000021620 ENSPRET00000032269 uncharacterised
## 47749 9.470523 ENSPREG00000003984 ENSPRET00000005798 MYOC
## 25043 6.600396 ENSPREG00000016627 ENSPRET00000024920 PLPP7nrow(subset(GvLpromoterschrdf,qvalue<0.05))## [1] 8135nrow(subset(GvLpromoterschrdf,qvalue<0.05&meth.diff>0))## [1] 4718nrow(subset(GvLpromoterschrdf,qvalue<0.05&meth.diff<0))## [1] 3417saveRDS(object=GvLpromoterschrdf,file="GvLtiles_genepromoters.rds",compress="gzip")
rm(GvLpromoters)
rm(GvLpromotersdf)Create RCircos plot for CvG comparison promoter annotated
CvGpromoterschrdftiles <- head(CvGpromoterschrdf,75)
head(CvGpromoterschrdftiles)## seqnames start end width strand pvalue qvalue
## 86983 LG4 1847001 1848000 1000 * 9.714622e-131 4.885614e-125
## 86984 LG4 1847001 1848000 1000 * 9.714622e-131 4.885614e-125
## 86981 LG4 1846001 1847000 1000 * 1.196917e-89 3.009727e-84
## 86982 LG4 1846001 1847000 1000 * 1.196917e-89 3.009727e-84
## 6509 LG1 9073001 9074000 1000 * 3.550053e-47 2.550528e-42
## 8294 LG1 17897001 17898000 1000 * 1.654721e-42 9.246461e-38
## meth.diff gene_id V6 gene_name
## 86983 19.239478 ENSPREG00000021468 ENSPRET00000032035 gpc5b
## 86984 19.239478 ENSPREG00000021490 ENSPRET00000032090 nasp
## 86981 19.897694 ENSPREG00000021468 ENSPRET00000032035 gpc5b
## 86982 19.897694 ENSPREG00000021490 ENSPRET00000032090 nasp
## 6509 14.606176 ENSPREG00000000312 ENSPRET00000000435 slx4
## 8294 -6.231157 ENSPREG00000004582 ENSPRET00000006703 uncharacterisedChr.Label.Data <- dplyr::select(CvGpromoterschrdftiles,seqnames,start,end,gene_name)
colnames(Chr.Label.Data) <- c("Chromosome","chromStart","chromEnd","GeneName")
head(Chr.Label.Data)## Chromosome chromStart chromEnd GeneName
## 86983 LG4 1847001 1848000 gpc5b
## 86984 LG4 1847001 1848000 nasp
## 86981 LG4 1846001 1847000 gpc5b
## 86982 LG4 1846001 1847000 nasp
## 6509 LG1 9073001 9074000 slx4
## 8294 LG1 17897001 17898000 uncharacterisedChr.Label.Data <- Chr.Label.Data[-which(Chr.Label.Data$GeneName == "uncharacterised" | is.na(Chr.Label.Data$GeneName)), ]
head(Chr.Label.Data,10)## Chromosome chromStart chromEnd GeneName
## 86983 LG4 1847001 1848000 gpc5b
## 86984 LG4 1847001 1848000 nasp
## 86981 LG4 1846001 1847000 gpc5b
## 86982 LG4 1846001 1847000 nasp
## 6509 LG1 9073001 9074000 slx4
## 8295 LG1 17897001 17898000 lgi2b
## 92712 LG5 2971001 2972000 asb14a
## 73774 LG21 16656001 16657000 entpd5b
## 41173 LG16 6723001 6724000 tnfb
## 46766 LG17 4283001 4284000 MYOChead(CvGgeneschrdf)## seqnames start end width strand pvalue qvalue
## 157446 LG19 1188001 1189000 1000 * 1.774652e-81 2.974987e-76
## 76291 LG13 18161001 18162000 1000 * 3.721408e-59 3.743092e-54
## 14405 LG1 9073001 9074000 1000 * 3.550053e-47 2.550528e-42
## 203997 LG21 1055001 1056000 1000 * 2.372031e-46 1.491158e-41
## 18677 LG1 17897001 17898000 1000 * 1.654721e-42 9.246461e-38
## 156721 LG18 21720001 21721000 1000 * 1.092368e-36 4.994240e-32
## meth.diff gene_id gene_biotype gene_name
## 157446 -22.272263 ENSPREG00000017528 protein_coding SHANK1
## 76291 20.536203 ENSPREG00000001265 protein_coding <NA>
## 14405 14.606176 ENSPREG00000000312 protein_coding slx4
## 203997 14.585360 ENSPREG00000013853 protein_coding hivep2a
## 18677 -6.231157 ENSPREG00000004582 protein_coding <NA>
## 156721 -15.394290 ENSPREG00000014753 protein_coding aimp1bRCircos.histogramV <- dplyr::select(CvGpromoterschrdf,seqnames,start,end,qvalue)
head(RCircos.histogramV)## seqnames start end qvalue
## 86983 LG4 1847001 1848000 4.885614e-125
## 86984 LG4 1847001 1848000 4.885614e-125
## 86981 LG4 1846001 1847000 3.009727e-84
## 86982 LG4 1846001 1847000 3.009727e-84
## 6509 LG1 9073001 9074000 2.550528e-42
## 8294 LG1 17897001 17898000 9.246461e-38RCircos.histogramV$qvalue <- log(RCircos.histogramV$qvalue)
head(RCircos.histogramV)## seqnames start end qvalue
## 86983 LG4 1847001 1848000 -286.23684
## 86984 LG4 1847001 1848000 -286.23684
## 86981 LG4 1846001 1847000 -192.31530
## 86982 LG4 1846001 1847000 -192.31530
## 6509 LG1 9073001 9074000 -95.77227
## 8294 LG1 17897001 17898000 -85.27399colnames(RCircos.histogramV) <- c("Chromosome","chromStart","chromEnd","Data")
head(RCircos.histogramV)## Chromosome chromStart chromEnd Data
## 86983 LG4 1847001 1848000 -286.23684
## 86984 LG4 1847001 1848000 -286.23684
## 86981 LG4 1846001 1847000 -192.31530
## 86982 LG4 1846001 1847000 -192.31530
## 6509 LG1 9073001 9074000 -95.77227
## 8294 LG1 17897001 17898000 -85.27399head(CvGgeneschrdf)## seqnames start end width strand pvalue qvalue
## 157446 LG19 1188001 1189000 1000 * 1.774652e-81 2.974987e-76
## 76291 LG13 18161001 18162000 1000 * 3.721408e-59 3.743092e-54
## 14405 LG1 9073001 9074000 1000 * 3.550053e-47 2.550528e-42
## 203997 LG21 1055001 1056000 1000 * 2.372031e-46 1.491158e-41
## 18677 LG1 17897001 17898000 1000 * 1.654721e-42 9.246461e-38
## 156721 LG18 21720001 21721000 1000 * 1.092368e-36 4.994240e-32
## meth.diff gene_id gene_biotype gene_name
## 157446 -22.272263 ENSPREG00000017528 protein_coding SHANK1
## 76291 20.536203 ENSPREG00000001265 protein_coding <NA>
## 14405 14.606176 ENSPREG00000000312 protein_coding slx4
## 203997 14.585360 ENSPREG00000013853 protein_coding hivep2a
## 18677 -6.231157 ENSPREG00000004582 protein_coding <NA>
## 156721 -15.394290 ENSPREG00000014753 protein_coding aimp1bRCircos.heatmapV <- dplyr::select(CvGpromoterschrdf,seqnames,start,end,gene_name,meth.diff)
head(RCircos.heatmapV)## seqnames start end gene_name meth.diff
## 86983 LG4 1847001 1848000 gpc5b 19.239478
## 86984 LG4 1847001 1848000 nasp 19.239478
## 86981 LG4 1846001 1847000 gpc5b 19.897694
## 86982 LG4 1846001 1847000 nasp 19.897694
## 6509 LG1 9073001 9074000 slx4 14.606176
## 8294 LG1 17897001 17898000 uncharacterised -6.231157colnames(RCircos.heatmapV) <- c("Chromosome","chromStart","chromEnd","GeneName","CvG")
head(RCircos.heatmapV)## Chromosome chromStart chromEnd GeneName CvG
## 86983 LG4 1847001 1848000 gpc5b 19.239478
## 86984 LG4 1847001 1848000 nasp 19.239478
## 86981 LG4 1846001 1847000 gpc5b 19.897694
## 86982 LG4 1846001 1847000 nasp 19.897694
## 6509 LG1 9073001 9074000 slx4 14.606176
## 8294 LG1 17897001 17898000 uncharacterised -6.231157data(UCSC.Mouse.GRCm38.CytoBandIdeogram)
str(UCSC.Mouse.GRCm38.CytoBandIdeogram)## 'data.frame': 403 obs. of 5 variables:
## $ Chromosome: Factor w/ 21 levels "chr1","chr10",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ ChromStart: int 0 8840440 12278390 20136559 22101102 30941543 43219933 54516052 55989459 59427408 ...
## $ ChromEnd : int 8840440 12278390 20136559 22101102 30941543 43219933 54516052 55989459 59427408 65321035 ...
## $ Band : Factor w/ 97 levels "qA","qA1","qA1.1",..: 2 6 7 11 12 20 40 41 42 43 ...
## $ Stain : Factor w/ 5 levels "gneg","gpos100",..: 2 1 3 1 2 1 4 1 5 1 ...chrlen <- read.table("/mnt/data/aaron/projects/guppy-methylation/chrlen.tsv")
str(chrlen)## 'data.frame': 23 obs. of 2 variables:
## $ V1: chr "LG1" "LG2" "LG3" "LG4" ...
## $ V2: int 34115677 46286544 35265442 31497199 33908744 31529174 31413364 27946405 34117797 32819797 ...segs <- apply(X = chrlen,MARGIN = 1,FUN = function(l){
chr <- l[1]
len <- l[2]
seg <- seq(1,len,1000000)
df <- data.frame(chr,as.integer(seg),as.integer(seg+999999))
df$band <- paste("x",1:nrow(df),sep = "")
stain <- c("gneg","gpos")
df$stain <- as.vector(matrix(data = stain,nrow = nrow(df),ncol = 1))
return(df)
})## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded## Warning in matrix(data = stain, nrow = nrow(df), ncol = 1): data length [2] is
## not a sub-multiple or multiple of the number of rows [35]## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded## Warning in matrix(data = stain, nrow = nrow(df), ncol = 1): data length [2] is
## not a sub-multiple or multiple of the number of rows [47]## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded
## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded
## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded
## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded
## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded
## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded
## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded## Warning in matrix(data = stain, nrow = nrow(df), ncol = 1): data length [2] is
## not a sub-multiple or multiple of the number of rows [35]## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded## Warning in matrix(data = stain, nrow = nrow(df), ncol = 1): data length [2] is
## not a sub-multiple or multiple of the number of rows [33]## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded## Warning in matrix(data = stain, nrow = nrow(df), ncol = 1): data length [2] is
## not a sub-multiple or multiple of the number of rows [29]## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded## Warning in matrix(data = stain, nrow = nrow(df), ncol = 1): data length [2] is
## not a sub-multiple or multiple of the number of rows [27]## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded
## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded## Warning in matrix(data = stain, nrow = nrow(df), ncol = 1): data length [2] is
## not a sub-multiple or multiple of the number of rows [29]## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded## Warning in matrix(data = stain, nrow = nrow(df), ncol = 1): data length [2] is
## not a sub-multiple or multiple of the number of rows [31]## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded
## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded## Warning in matrix(data = stain, nrow = nrow(df), ncol = 1): data length [2] is
## not a sub-multiple or multiple of the number of rows [31]## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded## Warning in matrix(data = stain, nrow = nrow(df), ncol = 1): data length [2] is
## not a sub-multiple or multiple of the number of rows [23]## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded## Warning in matrix(data = stain, nrow = nrow(df), ncol = 1): data length [2] is
## not a sub-multiple or multiple of the number of rows [29]## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded## Warning in matrix(data = stain, nrow = nrow(df), ncol = 1): data length [2] is
## not a sub-multiple or multiple of the number of rows [27]## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded
## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded
## Warning in data.frame(chr, as.integer(seg), as.integer(seg + 999999)): row names
## were found from a short variable and have been discarded## Warning in matrix(data = stain, nrow = nrow(df), ncol = 1): data length [2] is
## not a sub-multiple or multiple of the number of rows [19]segs <- do.call(rbind, segs)
colnames(segs) <- c("Chromosome","ChromStart","ChromEnd","Band","Stain")
str(segs)## 'data.frame': 709 obs. of 5 variables:
## $ Chromosome: chr "LG1" "LG1" "LG1" "LG1" ...
## $ ChromStart: int 1 1000001 2000001 3000001 4000001 5000001 6000001 7000001 8000001 9000001 ...
## $ ChromEnd : int 1000000 2000000 3000000 4000000 5000000 6000000 7000000 8000000 9000000 10000000 ...
## $ Band : chr "x1" "x2" "x3" "x4" ...
## $ Stain : chr "gneg" "gpos" "gneg" "gpos" ...head(segs)## Chromosome ChromStart ChromEnd Band Stain
## 1 LG1 1 1000000 x1 gneg
## 2 LG1 1000001 2000000 x2 gpos
## 3 LG1 2000001 3000000 x3 gneg
## 4 LG1 3000001 4000000 x4 gpos
## 5 LG1 4000001 5000000 x5 gneg
## 6 LG1 5000001 6000000 x6 gposRCircos.Set.Core.Components(cyto.info = segs,tracks.inside = 4,chr.exclude = NULL,tracks.outside = 0)##
## RCircos.Core.Components initialized.
## Type ?RCircos.Reset.Plot.Parameters to see how to modify the core components.rcircos.params <- RCircos.Get.Plot.Parameters()
rcircos.cyto <- RCircos.Get.Plot.Ideogram()
rcircos.position <- RCircos.Get.Plot.Positions()
rcircos.params$hist.width <- 30
rcircos.params$heatmap.width <- 30
rcircos.params$text.size <- 0.75
RCircos.Reset.Plot.Parameters(new.params = rcircos.params)
#out.file <- "RCircosGuppyMethylome.pdf";
#pdf(file=out.file, height=8, width=8, compress=TRUE)#Setup RCircos plot
plot.new()
RCircos.Set.Plot.Area()
#Include ideogram
RCircos.Chromosome.Ideogram.Plot()
data(RCircos.histogramV)## Warning in data(RCircos.histogramV): data set 'RCircos.histogramV' not found#Create Heatmap
data(RCircos.heatmapV)## Warning in data(RCircos.heatmapV): data set 'RCircos.heatmapV' not foundRCircos.Heatmap.Plot(heatmap.data = head(RCircos.heatmapV,75), data.col = 5,track.num = 1,side = "in")
#Create histogram
RCircos.Histogram.Plot(head(RCircos.histogramV,75),data.col=4, track.num=2, side="in")
#Include gene names and create connectors to histogram
RCircos.Gene.Connector.Plot(genomic.data = Chr.Label.Data,track.num = 3, side = "in")## There is unsupported chromosome names in ideogram
## and chromosomes are sorted in alphabetical order.## Not all labels will be plotted.## Type RCircos.Get.Gene.Name.Plot.Parameters()## to see the number of labels for each chromosome.RCircos.Gene.Name.Plot(head(Chr.Label.Data,75), name.col=4,track.num=4, side="in")## There is unsupported chromosome names in ideogram
## and chromosomes are sorted in alphabetical order.## Not all labels will be plotted.## Type RCircos.Get.Gene.Name.Plot.Parameters()## to see the number of labels for each chromosome.
Create RCircos plot for CvL comparison promoter annotated
CvLpromoterschrdftiles <- head(CvLpromoterschrdf,75)
head(CvLpromoterschrdftiles)## seqnames start end width strand pvalue qvalue
## 63161 LG2 20995001 20996000 1000 * 4.065070e-48 2.956357e-43
## 106383 LG7 18259001 18260000 1000 * 8.559718e-41 4.357590e-36
## 20949 LG11 28461001 28462000 1000 * 1.078697e-40 4.992221e-36
## 70661 LG21 538001 539000 1000 * 5.735034e-40 2.432998e-35
## 31311 LG14 4148001 4149000 1000 * 8.688214e-40 3.402312e-35
## 20618 LG11 27368001 27369000 1000 * 1.892756e-31 4.588411e-27
## meth.diff gene_id V6 gene_name
## 63161 -20.26683 ENSPREG00000014846 ENSPRET00000022204 zgc:194275
## 106383 23.29152 ENSPREG00000003617 ENSPRET00000005305 uts2a
## 20949 -13.62358 ENSPREG00000010182 ENSPRET00000015234 tfap2e
## 70661 -13.78305 ENSPREG00000012722 ENSPRET00000019142 uncharacterised
## 31311 -21.04322 ENSPREG00000009393 ENSPRET00000014038 zgc:112437
## 20618 13.36592 ENSPREG00000008406 ENSPRET00000012667 fabp10bChr.Label.Data <- dplyr::select(CvLpromoterschrdftiles,seqnames,start,end,gene_name)
colnames(Chr.Label.Data) <- c("Chromosome","chromStart","chromEnd","GeneName")
head(Chr.Label.Data, 75)## Chromosome chromStart chromEnd GeneName
## 63161 LG2 20995001 20996000 zgc:194275
## 106383 LG7 18259001 18260000 uts2a
## 20949 LG11 28461001 28462000 tfap2e
## 70661 LG21 538001 539000 uncharacterised
## 31311 LG14 4148001 4149000 zgc:112437
## 20618 LG11 27368001 27369000 fabp10b
## 36545 LG15 10977001 10978000 grid1a
## 74546 LG21 23640001 23641000 gabrr2b
## 70641 LG21 525001 526000 uncharacterised
## 70642 LG21 525001 526000 crnkl1
## 51832 LG18 4888001 4889000 uncharacterised
## 115239 LG8 27195001 27196000 mvp
## 52654 LG18 8495001 8496000 dnajc3b
## 61839 LG2 14437001 14438000 dhrs12
## 87348 LG4 4685001 4686000 uncharacterised
## 87036 LG4 3392001 3393000 si:ch211-198n5.11
## 39782 LG16 262001 263000 uncharacterised
## 72218 LG21 9381001 9382000 ostm1
## 80183 LG23 6138001 6139000 TMEM60
## 59136 LG19 25901001 25902000 galk1
## 70312 LG20 25508001 25509000 uncharacterised
## 17251 LG11 10184001 10185000 hoxa5a
## 25429 LG12 26139001 26140000 spra
## 32740 LG14 10074001 10075000 gnb2
## 18198 LG11 14223001 14224000 lrrc14b
## 72630 LG21 11205001 11206000 nfkbie
## 106094 LG7 17085001 17086000 zgc:198371
## 41130 LG16 6723001 6724000 tnfb
## 115225 LG8 27128001 27129000 sgf29
## 115226 LG8 27128001 27129000 nupr1b
## 46090 LG17 936001 937000 uncharacterised
## 107908 LG7 26483001 26484000 hoxc4a
## 39621 LG15 30358001 30359000 uncharacterised
## 77403 LG22 14521001 14522000 uncharacterised
## 93302 LG5 6245001 6246000 A3GALT2
## 113036 LG8 18444001 18445000 akt1s1
## 46752 LG17 4434001 4435000 uncharacterised
## 9958 LG1 26801001 26802000 CNNM1
## 8365 LG1 18070001 18071000 slc25a4
## 20833 LG11 28250001 28251000 uncharacterised
## 20834 LG11 28250001 28251000 smim13
## 86884 LG4 2175001 2176000 U1
## 79414 LG23 1377001 1378000 ppfia2
## 86516 LG3 33819001 33820000 uncharacterised
## 56249 LG19 8951001 8952000 zgc:123217
## 21744 LG12 3809001 3810000 ZSWIM6
## 105497 LG7 14104001 14105000 uncharacterised
## 98734 LG6 6024001 6025000 uncharacterised
## 68125 LG20 10565001 10566000 uncharacterised
## 40232 LG16 1772001 1773000 rab25b
## 41108 LG16 6611001 6612000 mgat1a
## 110998 LG8 9050001 9051000 TST
## 17265 LG11 10208001 10209000 hoxa4a
## 82809 LG3 8381001 8382000 anp32a
## 91814 LG4 29343001 29344000 rnf11b
## 6554 LG1 9248001 9249000 slc27a1b
## 115433 LG8 27867001 27868000 uncharacterised
## 66908 LG2 45341001 45342000 igfbp2b
## 110474 LG8 7184001 7185000 grb2b
## 118910 LG9 22206001 22207000 uncharacterised
## 80705 LG23 9549001 9550000 SLC6A13
## 96500 LG5 24679001 24680000 ankrd33ab
## 18166 LG11 14181001 14182000 uncharacterised
## 54089 LG18 19797001 19798000 rnf150b
## 115357 LG8 27594001 27595000 cyt1
## 41769 LG16 11138001 11139000 tmc4
## 27533 LG13 16672001 16673000 dock10
## 21990 LG12 5210001 5211000 pik3r1
## 16013 LG10 32452001 32453000 ABCA1
## 51833 LG18 4889001 4890000 uncharacterised
## 88444 LG4 11541001 11542000 arrdc2
## 109320 LG8 1611001 1612000 uncharacterised
## 78899 LG22 23365001 23366000 si:ch211-160f23.7
## 71426 LG21 5396001 5397000 crip2l
## 11171 LG1 33775001 33776000 psen2Chr.Label.Data <- Chr.Label.Data[-which(Chr.Label.Data$GeneName == "uncharacterised" | is.na(Chr.Label.Data$GeneName)), ]
head(Chr.Label.Data,10)## Chromosome chromStart chromEnd GeneName
## 63161 LG2 20995001 20996000 zgc:194275
## 106383 LG7 18259001 18260000 uts2a
## 20949 LG11 28461001 28462000 tfap2e
## 31311 LG14 4148001 4149000 zgc:112437
## 20618 LG11 27368001 27369000 fabp10b
## 36545 LG15 10977001 10978000 grid1a
## 74546 LG21 23640001 23641000 gabrr2b
## 70642 LG21 525001 526000 crnkl1
## 115239 LG8 27195001 27196000 mvp
## 52654 LG18 8495001 8496000 dnajc3bhead(CvLgeneschrdf)## seqnames start end width strand pvalue qvalue
## 113524 LG16 509001 510000 1000 * 3.213330e-96 1.635845e-90
## 203638 LG21 1055001 1056000 1000 * 8.837088e-72 2.249397e-66
## 157168 LG19 1188001 1189000 1000 * 1.236241e-66 2.097822e-61
## 161585 LG19 10333001 10334000 1000 * 5.976181e-65 7.605902e-60
## 344625 LG9 23623001 23624000 1000 * 3.595176e-58 3.660472e-53
## 180121 LG2 20995001 20996000 1000 * 4.065070e-48 2.956357e-43
## meth.diff gene_id gene_biotype gene_name
## 113524 -25.98584 ENSPREG00000014798 protein_coding <NA>
## 203638 19.69921 ENSPREG00000013853 protein_coding hivep2a
## 157168 -20.54554 ENSPREG00000017528 protein_coding SHANK1
## 161585 22.88567 ENSPREG00000002350 protein_coding QRFPR
## 344625 20.83910 ENSPREG00000003004 protein_coding homer1b
## 180121 -20.26683 ENSPREG00000014863 protein_coding ephx2RCircos.histogramV <- dplyr::select(CvLpromoterschrdf,seqnames,start,end,qvalue)
head(RCircos.histogramV)## seqnames start end qvalue
## 63161 LG2 20995001 20996000 2.956357e-43
## 106383 LG7 18259001 18260000 4.357590e-36
## 20949 LG11 28461001 28462000 4.992221e-36
## 70661 LG21 538001 539000 2.432998e-35
## 31311 LG14 4148001 4149000 3.402312e-35
## 20618 LG11 27368001 27369000 4.588411e-27RCircos.histogramV$qvalue <- log(RCircos.histogramV$qvalue)
head(RCircos.histogramV)## seqnames start end qvalue
## 63161 LG2 20995001 20996000 -97.92720
## 106383 LG7 18259001 18260000 -81.42114
## 20949 LG11 28461001 28462000 -81.28518
## 70661 LG21 538001 539000 -79.70135
## 31311 LG14 4148001 4149000 -79.36602
## 20618 LG11 27368001 27369000 -60.64626colnames(RCircos.histogramV) <- c("Chromosome","chromStart","chromEnd","Data")
head(RCircos.histogramV)## Chromosome chromStart chromEnd Data
## 63161 LG2 20995001 20996000 -97.92720
## 106383 LG7 18259001 18260000 -81.42114
## 20949 LG11 28461001 28462000 -81.28518
## 70661 LG21 538001 539000 -79.70135
## 31311 LG14 4148001 4149000 -79.36602
## 20618 LG11 27368001 27369000 -60.64626head(CvGgeneschrdf)## seqnames start end width strand pvalue qvalue
## 157446 LG19 1188001 1189000 1000 * 1.774652e-81 2.974987e-76
## 76291 LG13 18161001 18162000 1000 * 3.721408e-59 3.743092e-54
## 14405 LG1 9073001 9074000 1000 * 3.550053e-47 2.550528e-42
## 203997 LG21 1055001 1056000 1000 * 2.372031e-46 1.491158e-41
## 18677 LG1 17897001 17898000 1000 * 1.654721e-42 9.246461e-38
## 156721 LG18 21720001 21721000 1000 * 1.092368e-36 4.994240e-32
## meth.diff gene_id gene_biotype gene_name
## 157446 -22.272263 ENSPREG00000017528 protein_coding SHANK1
## 76291 20.536203 ENSPREG00000001265 protein_coding <NA>
## 14405 14.606176 ENSPREG00000000312 protein_coding slx4
## 203997 14.585360 ENSPREG00000013853 protein_coding hivep2a
## 18677 -6.231157 ENSPREG00000004582 protein_coding <NA>
## 156721 -15.394290 ENSPREG00000014753 protein_coding aimp1bRCircos.heatmapV <- dplyr::select(CvLpromoterschrdf,seqnames,start,end,gene_name,meth.diff)
head(RCircos.heatmapV)## seqnames start end gene_name meth.diff
## 63161 LG2 20995001 20996000 zgc:194275 -20.26683
## 106383 LG7 18259001 18260000 uts2a 23.29152
## 20949 LG11 28461001 28462000 tfap2e -13.62358
## 70661 LG21 538001 539000 uncharacterised -13.78305
## 31311 LG14 4148001 4149000 zgc:112437 -21.04322
## 20618 LG11 27368001 27369000 fabp10b 13.36592colnames(RCircos.heatmapV) <- c("Chromosome","chromStart","chromEnd","GeneName","CvG")
head(RCircos.heatmapV)## Chromosome chromStart chromEnd GeneName CvG
## 63161 LG2 20995001 20996000 zgc:194275 -20.26683
## 106383 LG7 18259001 18260000 uts2a 23.29152
## 20949 LG11 28461001 28462000 tfap2e -13.62358
## 70661 LG21 538001 539000 uncharacterised -13.78305
## 31311 LG14 4148001 4149000 zgc:112437 -21.04322
## 20618 LG11 27368001 27369000 fabp10b 13.36592RCircos.Set.Core.Components(cyto.info = segs,tracks.inside = 4,chr.exclude = NULL,tracks.outside = 0)##
## RCircos.Core.Components initialized.
## Type ?RCircos.Reset.Plot.Parameters to see how to modify the core components.rcircos.params <- RCircos.Get.Plot.Parameters()
rcircos.cyto <- RCircos.Get.Plot.Ideogram()
rcircos.position <- RCircos.Get.Plot.Positions()
rcircos.params$hist.width <- 30
rcircos.params$heatmap.width <- 30
rcircos.params$text.size <- 0.75
RCircos.Reset.Plot.Parameters(new.params = rcircos.params)
#out.file <- "RCircosGuppyMethylome.pdf";
#pdf(file=out.file, height=8, width=8, compress=TRUE)#Setup RCircos plot
plot.new()
RCircos.Set.Plot.Area()
#Include ideogram
RCircos.Chromosome.Ideogram.Plot()
data(RCircos.histogramV)## Warning in data(RCircos.histogramV): data set 'RCircos.histogramV' not found#Create Heatmap
data(RCircos.heatmapV)## Warning in data(RCircos.heatmapV): data set 'RCircos.heatmapV' not foundRCircos.Heatmap.Plot(heatmap.data = head(RCircos.heatmapV,75), data.col = 5,track.num = 1,side = "in")
#Create histogram
RCircos.Histogram.Plot(head(RCircos.histogramV,75),data.col=4, track.num=2, side="in")
#Include gene names and create connectors to histogram
RCircos.Gene.Connector.Plot(genomic.data = Chr.Label.Data,track.num = 3, side = "in")## There is unsupported chromosome names in ideogram
## and chromosomes are sorted in alphabetical order.## Not all labels will be plotted.## Type RCircos.Get.Gene.Name.Plot.Parameters()## to see the number of labels for each chromosome.RCircos.Gene.Name.Plot(head(Chr.Label.Data,75), name.col=4,track.num=4, side="in")## There is unsupported chromosome names in ideogram
## and chromosomes are sorted in alphabetical order.## Not all labels will be plotted.## Type RCircos.Get.Gene.Name.Plot.Parameters()## to see the number of labels for each chromosome.
Create RCircos plot for GvL comparison promoter annotated
GvLpromoterschrdftiles <- head(GvLpromoterschrdf,75)
head(GvLpromoterschrdftiles)## seqnames start end width strand pvalue qvalue
## 88849 LG4 1847001 1848000 1000 * 7.503577e-141 3.921253e-135
## 88850 LG4 1847001 1848000 1000 * 7.503577e-141 3.921253e-135
## 88847 LG4 1846001 1847000 1000 * 8.017760e-104 2.094979e-98
## 88848 LG4 1846001 1847000 1000 * 8.017760e-104 2.094979e-98
## 72353 LG21 538001 539000 1000 * 5.180641e-40 4.512205e-35
## 32069 LG14 4148001 4149000 1000 * 2.644311e-35 1.727345e-30
## meth.diff gene_id transcript_id gene_name
## 88849 -19.01626 ENSPREG00000021468 ENSPRET00000032035 gpc5b
## 88850 -19.01626 ENSPREG00000021490 ENSPRET00000032090 nasp
## 88847 -19.30979 ENSPREG00000021468 ENSPRET00000032035 gpc5b
## 88848 -19.30979 ENSPREG00000021490 ENSPRET00000032090 nasp
## 72353 -12.60888 ENSPREG00000012722 ENSPRET00000019142 uncharacterised
## 32069 -17.15105 ENSPREG00000009393 ENSPRET00000014038 zgc:112437Chr.Label.Data <- dplyr::select(GvLpromoterschrdftiles,seqnames,start,end,gene_name)
colnames(Chr.Label.Data) <- c("Chromosome","chromStart","chromEnd","GeneName")
head(Chr.Label.Data)## Chromosome chromStart chromEnd GeneName
## 88849 LG4 1847001 1848000 gpc5b
## 88850 LG4 1847001 1848000 nasp
## 88847 LG4 1846001 1847000 gpc5b
## 88848 LG4 1846001 1847000 nasp
## 72353 LG21 538001 539000 uncharacterised
## 32069 LG14 4148001 4149000 zgc:112437Chr.Label.Data <- Chr.Label.Data[-which(Chr.Label.Data$GeneName == "uncharacterised" | is.na(Chr.Label.Data$GeneName)), ]
head(Chr.Label.Data,10)## Chromosome chromStart chromEnd GeneName
## 88849 LG4 1847001 1848000 gpc5b
## 88850 LG4 1847001 1848000 nasp
## 88847 LG4 1846001 1847000 gpc5b
## 88848 LG4 1846001 1847000 nasp
## 32069 LG14 4148001 4149000 zgc:112437
## 8533 LG1 17897001 17898000 lgi2b
## 94665 LG5 2971001 2972000 asb14a
## 21465 LG11 28461001 28462000 tfap2e
## 22282 LG12 3809001 3810000 ZSWIM6
## 64666 LG2 20995001 20996000 zgc:194275head(GvLgeneschrdf)## seqnames start end width strand pvalue qvalue
## 116121 LG16 509001 510000 1000 * 1.433189e-54 1.872407e-49
## 77967 LG13 18161001 18162000 1000 * 1.900156e-51 1.985985e-46
## 207930 LG21 538001 539000 1000 * 5.180641e-40 4.512205e-35
## 207931 LG21 538001 539000 1000 * 5.180641e-40 4.512205e-35
## 160079 LG18 21720001 21721000 1000 * 2.190222e-39 1.635109e-34
## 160080 LG18 21720001 21721000 1000 * 2.190222e-39 1.635109e-34
## meth.diff gene_id gene_biotype gene_name
## 116121 -17.40373 ENSPREG00000014798 protein_coding <NA>
## 77967 -17.69560 ENSPREG00000001265 protein_coding <NA>
## 207930 -12.60888 ENSPREG00000012615 protein_coding crnkl1
## 207931 -12.60888 ENSPREG00000012722 protein_coding <NA>
## 160079 14.86976 ENSPREG00000014753 protein_coding aimp1b
## 160080 14.86976 ENSPREG00000014824 protein_coding <NA>RCircos.histogramV <- dplyr::select(GvLpromoterschrdf,seqnames,start,end,qvalue)
head(RCircos.histogramV)## seqnames start end qvalue
## 88849 LG4 1847001 1848000 3.921253e-135
## 88850 LG4 1847001 1848000 3.921253e-135
## 88847 LG4 1846001 1847000 2.094979e-98
## 88848 LG4 1846001 1847000 2.094979e-98
## 72353 LG21 538001 539000 4.512205e-35
## 32069 LG14 4148001 4149000 1.727345e-30RCircos.histogramV$qvalue <- log(RCircos.histogramV$qvalue)
head(RCircos.histogramV)## seqnames start end qvalue
## 88849 LG4 1847001 1848000 -309.48258
## 88850 LG4 1847001 1848000 -309.48258
## 88847 LG4 1846001 1847000 -224.91380
## 88848 LG4 1846001 1847000 -224.91380
## 72353 LG21 538001 539000 -79.08369
## 32069 LG14 4148001 4149000 -68.53097colnames(RCircos.histogramV) <- c("Chromosome","chromStart","chromEnd","Data")
head(RCircos.histogramV)## Chromosome chromStart chromEnd Data
## 88849 LG4 1847001 1848000 -309.48258
## 88850 LG4 1847001 1848000 -309.48258
## 88847 LG4 1846001 1847000 -224.91380
## 88848 LG4 1846001 1847000 -224.91380
## 72353 LG21 538001 539000 -79.08369
## 32069 LG14 4148001 4149000 -68.53097head(GvLgeneschrdf)## seqnames start end width strand pvalue qvalue
## 116121 LG16 509001 510000 1000 * 1.433189e-54 1.872407e-49
## 77967 LG13 18161001 18162000 1000 * 1.900156e-51 1.985985e-46
## 207930 LG21 538001 539000 1000 * 5.180641e-40 4.512205e-35
## 207931 LG21 538001 539000 1000 * 5.180641e-40 4.512205e-35
## 160079 LG18 21720001 21721000 1000 * 2.190222e-39 1.635109e-34
## 160080 LG18 21720001 21721000 1000 * 2.190222e-39 1.635109e-34
## meth.diff gene_id gene_biotype gene_name
## 116121 -17.40373 ENSPREG00000014798 protein_coding <NA>
## 77967 -17.69560 ENSPREG00000001265 protein_coding <NA>
## 207930 -12.60888 ENSPREG00000012615 protein_coding crnkl1
## 207931 -12.60888 ENSPREG00000012722 protein_coding <NA>
## 160079 14.86976 ENSPREG00000014753 protein_coding aimp1b
## 160080 14.86976 ENSPREG00000014824 protein_coding <NA>RCircos.heatmapV <- dplyr::select(GvLpromoterschrdf,seqnames,start,end,gene_name,meth.diff)
head(RCircos.heatmapV)## seqnames start end gene_name meth.diff
## 88849 LG4 1847001 1848000 gpc5b -19.01626
## 88850 LG4 1847001 1848000 nasp -19.01626
## 88847 LG4 1846001 1847000 gpc5b -19.30979
## 88848 LG4 1846001 1847000 nasp -19.30979
## 72353 LG21 538001 539000 uncharacterised -12.60888
## 32069 LG14 4148001 4149000 zgc:112437 -17.15105colnames(RCircos.heatmapV) <- c("Chromosome","chromStart","chromEnd","GeneName","CvG")
head(RCircos.heatmapV)## Chromosome chromStart chromEnd GeneName CvG
## 88849 LG4 1847001 1848000 gpc5b -19.01626
## 88850 LG4 1847001 1848000 nasp -19.01626
## 88847 LG4 1846001 1847000 gpc5b -19.30979
## 88848 LG4 1846001 1847000 nasp -19.30979
## 72353 LG21 538001 539000 uncharacterised -12.60888
## 32069 LG14 4148001 4149000 zgc:112437 -17.15105RCircos.Set.Core.Components(cyto.info = segs,tracks.inside = 4,chr.exclude = NULL,tracks.outside = 0)##
## RCircos.Core.Components initialized.
## Type ?RCircos.Reset.Plot.Parameters to see how to modify the core components.rcircos.params <- RCircos.Get.Plot.Parameters()
rcircos.cyto <- RCircos.Get.Plot.Ideogram()
rcircos.position <- RCircos.Get.Plot.Positions()
rcircos.params$hist.width <- 30
rcircos.params$heatmap.width <- 30
rcircos.params$text.size <- 0.75
RCircos.Reset.Plot.Parameters(new.params = rcircos.params)
#out.file <- "RCircosGuppyMethylome.pdf";
#pdf(file=out.file, height=8, width=8, compress=TRUE)#Setup RCircos plot
plot.new()
RCircos.Set.Plot.Area()
#Include ideogram
RCircos.Chromosome.Ideogram.Plot()
data(RCircos.histogramV)## Warning in data(RCircos.histogramV): data set 'RCircos.histogramV' not found#Create Heatmap
data(RCircos.heatmapV)## Warning in data(RCircos.heatmapV): data set 'RCircos.heatmapV' not foundRCircos.Heatmap.Plot(heatmap.data = head(RCircos.heatmapV,75), data.col = 5,track.num = 1,side = "in")
#Create histogram
RCircos.Histogram.Plot(head(RCircos.histogramV,75),data.col=4, track.num=2, side="in")
#Include gene names and create connectors to histogram
RCircos.Gene.Connector.Plot(genomic.data = Chr.Label.Data,track.num = 3, side = "in")## There is unsupported chromosome names in ideogram
## and chromosomes are sorted in alphabetical order.## Not all labels will be plotted.## Type RCircos.Get.Gene.Name.Plot.Parameters()## to see the number of labels for each chromosome.RCircos.Gene.Name.Plot(head(Chr.Label.Data,75), name.col=4,track.num=4, side="in")## There is unsupported chromosome names in ideogram
## and chromosomes are sorted in alphabetical order.## Not all labels will be plotted.## Type RCircos.Get.Gene.Name.Plot.Parameters()## to see the number of labels for each chromosome.
Read in the methylation data from Biscuit
ClearR1 <- read.table("meth_data/Clear2F-R1.bam.vcf.gz.cg.bed.gz")
ClearR2 <- read.table("meth_data/Clear2F-R2.bam.vcf.gz.cg.bed.gz")
ClearR3 <- read.table("meth_data/Clear2F-R3.bam.vcf.gz.cg.bed.gz")
Foundation <- read.table("meth_data/Foundation.bam.vcf.gz.cg.bed.gz")
GreenR1 <- read.table("meth_data/Green3F-R1.bam.vcf.gz.cg.bed.gz")
GreenR2 <- read.table("meth_data/Green3F-R2.bam.vcf.gz.cg.bed.gz")
GreenR3 <- read.table("meth_data/Green3F-R3.bam.vcf.gz.cg.bed.gz")
LilacR1 <- read.table("meth_data/Lilac4F-R1.bam.vcf.gz.cg.bed.gz")
LilacR2 <- read.table("meth_data/Lilac4F-R2.bam.vcf.gz.cg.bed.gz")
LilacR3 <- read.table("meth_data/Lilac4F-R3.bam.vcf.gz.cg.bed.gz")Make some plots to investigate CpG methylation in differentially methylated tiles
library(vioplot)## Loading required package: sm## Package 'sm', version 2.2-5.7: type help(sm) for summary information## Loading required package: zoo##
## Attaching package: 'zoo'## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numericlibrary(beeswarm)
methylkitplots <- function(tiles){
seqnames <- tiles[1]
start <- tiles[2]
end <- tiles[3]
gene_name <- tiles[11]
Foundationsub <- Foundation[which( Foundation$V1==seqnames & Foundation$V2>start & Foundation$V3<end ),4]
ClearR1sub <- ClearR1[which( ClearR1$V1==seqnames & ClearR1$V2>start & ClearR1$V3<end ),4]
ClearR2sub <- ClearR2[which( ClearR2$V1==seqnames & ClearR2$V2>start & ClearR2$V3<end ),4]
ClearR3sub <- ClearR3[which( ClearR3$V1==seqnames & ClearR3$V2>start & ClearR3$V3<end ),4]
GreenR1sub <- GreenR1[which( GreenR1$V1==seqnames & GreenR1$V2>start & GreenR1$V3<end ),4]
GreenR2sub <- GreenR2[which( GreenR2$V1==seqnames & GreenR2$V2>start & GreenR2$V3<end ),4]
GreenR3sub <- GreenR3[which( GreenR3$V1==seqnames & GreenR3$V2>start & GreenR3$V3<end ),4]
LilacR1sub <- LilacR1[which( LilacR1$V1==seqnames & LilacR1$V2>start & LilacR1$V3<end ),4]
LilacR2sub <- LilacR2[which( LilacR2$V1==seqnames & LilacR2$V2>start & LilacR2$V3<end ),4]
LilacR3sub <- LilacR3[which( LilacR3$V1==seqnames & LilacR3$V2>start & LilacR3$V3<end ),4]
ml <- list("Foundation"=Foundationsub,
"ClearR1"=ClearR1sub,
"ClearR2"=ClearR2sub,
"ClearR3"=ClearR3sub,
"GreenR1"=GreenR1sub,
"GreenR2"=GreenR2sub,
"GreenR3"=GreenR3sub,
"LilacR1"=LilacR1sub,
"LilacR2"=LilacR2sub,
"LilacR3"=LilacR3sub)
HEADER = paste(seqnames,start,end,gene_name)
par(mar=c(5,10,3,1))
vioplot(ml, main = HEADER, xlab = "% Methylation", horizontal=TRUE,las=1)
beeswarm(ml, main = HEADER, xlab = "% Methylation", horizontal = TRUE, las=1,pch=19,cex=0.5)
mlm <- unlist(lapply(ml,mean))
barplot( mlm, main = HEADER, xlab = "% Methylation", horiz=TRUE,las=1,xlim=c(min(mlm)-0.01,max(mlm)+0.01))
}
# test that one works
# dmr <- GvLgeneschrdf[1,,drop=TRUE]
# dmrplots(dmr)
# with lapply
lapply(X=1:10, function(i) {
tiles <- CvGpromoterschrdf[i,,drop=TRUE]
methylkitplots(tiles)
})
## [[1]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[2]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[3]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[4]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[5]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[6]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[7]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[8]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[9]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[10]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5library(vioplot)
library(beeswarm)
methylkitplots <- function(tiles){
seqnames <- tiles[1]
start <- tiles[2]
end <- tiles[3]
gene_name <- tiles[11]
Foundationsub <- Foundation[which( Foundation$V1==seqnames & Foundation$V2>start & Foundation$V3<end ),4]
ClearR1sub <- ClearR1[which( ClearR1$V1==seqnames & ClearR1$V2>start & ClearR1$V3<end ),4]
ClearR2sub <- ClearR2[which( ClearR2$V1==seqnames & ClearR2$V2>start & ClearR2$V3<end ),4]
ClearR3sub <- ClearR3[which( ClearR3$V1==seqnames & ClearR3$V2>start & ClearR3$V3<end ),4]
GreenR1sub <- GreenR1[which( GreenR1$V1==seqnames & GreenR1$V2>start & GreenR1$V3<end ),4]
GreenR2sub <- GreenR2[which( GreenR2$V1==seqnames & GreenR2$V2>start & GreenR2$V3<end ),4]
GreenR3sub <- GreenR3[which( GreenR3$V1==seqnames & GreenR3$V2>start & GreenR3$V3<end ),4]
LilacR1sub <- LilacR1[which( LilacR1$V1==seqnames & LilacR1$V2>start & LilacR1$V3<end ),4]
LilacR2sub <- LilacR2[which( LilacR2$V1==seqnames & LilacR2$V2>start & LilacR2$V3<end ),4]
LilacR3sub <- LilacR3[which( LilacR3$V1==seqnames & LilacR3$V2>start & LilacR3$V3<end ),4]
ml <- list("Foundation"=Foundationsub,
"ClearR1"=ClearR1sub,
"ClearR2"=ClearR2sub,
"ClearR3"=ClearR3sub,
"GreenR1"=GreenR1sub,
"GreenR2"=GreenR2sub,
"GreenR3"=GreenR3sub,
"LilacR1"=LilacR1sub,
"LilacR2"=LilacR2sub,
"LilacR3"=LilacR3sub)
HEADER = paste(seqnames,start,end,gene_name)
par(mar=c(5,10,3,1))
vioplot(ml, main = HEADER, xlab = "% Methylation", horizontal=TRUE,las=1)
beeswarm(ml, main = HEADER, xlab = "% Methylation", horizontal = TRUE, las=1,pch=19,cex=0.5)
mlm <- unlist(lapply(ml,mean))
barplot( mlm, main = HEADER, xlab = "% Methylation", horiz=TRUE,las=1,xlim=c(min(mlm)-0.01,max(mlm)+0.01))
}
# test that one works
# dmr <- GvLgeneschrdf[1,,drop=TRUE]
# dmrplots(dmr)
# with lapply
lapply(X=1:10, function(i) {
tiles <- CvLpromoterschrdf[i,,drop=TRUE]
methylkitplots(tiles)
})
## [[1]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[2]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[3]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[4]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[5]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[6]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[7]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[8]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[9]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[10]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5library(vioplot)
library(beeswarm)
methylkitplots <- function(tiles){
seqnames <- tiles[1]
start <- tiles[2]
end <- tiles[3]
gene_name <- tiles[11]
Foundationsub <- Foundation[which( Foundation$V1==seqnames & Foundation$V2>start & Foundation$V3<end ),4]
ClearR1sub <- ClearR1[which( ClearR1$V1==seqnames & ClearR1$V2>start & ClearR1$V3<end ),4]
ClearR2sub <- ClearR2[which( ClearR2$V1==seqnames & ClearR2$V2>start & ClearR2$V3<end ),4]
ClearR3sub <- ClearR3[which( ClearR3$V1==seqnames & ClearR3$V2>start & ClearR3$V3<end ),4]
GreenR1sub <- GreenR1[which( GreenR1$V1==seqnames & GreenR1$V2>start & GreenR1$V3<end ),4]
GreenR2sub <- GreenR2[which( GreenR2$V1==seqnames & GreenR2$V2>start & GreenR2$V3<end ),4]
GreenR3sub <- GreenR3[which( GreenR3$V1==seqnames & GreenR3$V2>start & GreenR3$V3<end ),4]
LilacR1sub <- LilacR1[which( LilacR1$V1==seqnames & LilacR1$V2>start & LilacR1$V3<end ),4]
LilacR2sub <- LilacR2[which( LilacR2$V1==seqnames & LilacR2$V2>start & LilacR2$V3<end ),4]
LilacR3sub <- LilacR3[which( LilacR3$V1==seqnames & LilacR3$V2>start & LilacR3$V3<end ),4]
ml <- list("Foundation"=Foundationsub,
"ClearR1"=ClearR1sub,
"ClearR2"=ClearR2sub,
"ClearR3"=ClearR3sub,
"GreenR1"=GreenR1sub,
"GreenR2"=GreenR2sub,
"GreenR3"=GreenR3sub,
"LilacR1"=LilacR1sub,
"LilacR2"=LilacR2sub,
"LilacR3"=LilacR3sub)
HEADER = paste(seqnames,start,end,gene_name)
par(mar=c(5,10,3,1))
vioplot(ml, main = HEADER, xlab = "% Methylation", horizontal=TRUE,las=1)
beeswarm(ml, main = HEADER, xlab = "% Methylation", horizontal = TRUE, las=1,pch=19,cex=0.5)
mlm <- unlist(lapply(ml,mean))
barplot( mlm, main = HEADER, xlab = "% Methylation", horiz=TRUE,las=1,xlim=c(min(mlm)-0.01,max(mlm)+0.01))
}
# test that one works
# dmr <- GvLgeneschrdf[1,,drop=TRUE]
# dmrplots(dmr)
# with lapply
lapply(X=1:10, function(i) {
tiles <- GvLpromoterschrdf[i,,drop=TRUE]
methylkitplots(tiles)
})
## [[1]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[2]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[3]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[4]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[5]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[6]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[7]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[8]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[9]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5
##
## [[10]]
## [,1]
## [1,] 0.7
## [2,] 1.9
## [3,] 3.1
## [4,] 4.3
## [5,] 5.5
## [6,] 6.7
## [7,] 7.9
## [8,] 9.1
## [9,] 10.3
## [10,] 11.5Barplot of differentially methylated tiles in gene promoter regions
head(CvGpromoterschrdf)## seqnames start end width strand pvalue qvalue
## 86983 LG4 1847001 1848000 1000 * 9.714622e-131 4.885614e-125
## 86984 LG4 1847001 1848000 1000 * 9.714622e-131 4.885614e-125
## 86981 LG4 1846001 1847000 1000 * 1.196917e-89 3.009727e-84
## 86982 LG4 1846001 1847000 1000 * 1.196917e-89 3.009727e-84
## 6509 LG1 9073001 9074000 1000 * 3.550053e-47 2.550528e-42
## 8294 LG1 17897001 17898000 1000 * 1.654721e-42 9.246461e-38
## meth.diff gene_id V6 gene_name
## 86983 19.239478 ENSPREG00000021468 ENSPRET00000032035 gpc5b
## 86984 19.239478 ENSPREG00000021490 ENSPRET00000032090 nasp
## 86981 19.897694 ENSPREG00000021468 ENSPRET00000032035 gpc5b
## 86982 19.897694 ENSPREG00000021490 ENSPRET00000032090 nasp
## 6509 14.606176 ENSPREG00000000312 ENSPRET00000000435 slx4
## 8294 -6.231157 ENSPREG00000004582 ENSPRET00000006703 uncharacterisedm <- CvGpromoterschrdf
genes <- unique(paste(CvGpromoterschrdf$gene_id,CvGpromoterschrdf$gene_name))
up <- subset(m, qvalue<0.05 & meth.diff > 0)
dn <- subset(m, qvalue<0.05 & meth.diff < 0)
cnt <- t(sapply(genes,function(g) {
id <- sapply(strsplit(g," "),"[[",1)
up_n <- length(which(up$gene_id==id))
dn_n <- length(which(dn$gene_id==id))
return(c(up_n,dn_n))
}))
colnames(cnt) <- c("up","down")
head(cnt[order(-cnt[,1]),],20)## up down
## ENSPREG00000019859 NFIB 4 0
## ENSPREG00000000942 uncharacterised 4 1
## ENSPREG00000002366 schip1 3 1
## ENSPREG00000017857 syngap1b 3 0
## ENSPREG00000018480 si:ch211-176g6.2 3 0
## ENSPREG00000003894 uncharacterised 3 2
## ENSPREG00000016462 adcyap1r1a 3 1
## ENSPREG00000009769 si:ch211-10a23.2 3 0
## ENSPREG00000003185 fam131a 3 0
## ENSPREG00000011277 taok2a 3 1
## ENSPREG00000008872 ndfip2 3 0
## ENSPREG00000021572 uncharacterised 3 3
## ENSPREG00000019119 nrg2a 3 0
## ENSPREG00000008863 NRCAM 3 0
## ENSPREG00000010588 uncharacterised 3 0
## ENSPREG00000008818 arhgap23a 3 1
## ENSPREG00000021385 si:dkey-25g12.4 3 0
## ENSPREG00000016483 klhl29 3 1
## ENSPREG00000004180 prkag2a 3 0
## ENSPREG00000000103 stox2a 3 0head(cnt[order(-cnt[,2]),],20)## up down
## ENSPREG00000007902 r3hdm1 1 5
## ENSPREG00000019594 ppp2r2ca 0 5
## ENSPREG00000012737 uncharacterised 0 4
## ENSPREG00000008709 atl2 0 4
## ENSPREG00000015260 uncharacterised 0 3
## ENSPREG00000020498 uncharacterised 0 3
## ENSPREG00000012546 peak1 0 3
## ENSPREG00000020838 efr3a 0 3
## ENSPREG00000009854 eya3 0 3
## ENSPREG00000021211 GOT1 0 3
## ENSPREG00000014076 gkup 0 3
## ENSPREG00000001808 igf2bp3 0 3
## ENSPREG00000003165 clcn3 0 3
## ENSPREG00000012587 uncharacterised 0 3
## ENSPREG00000010244 CLSPN 0 3
## ENSPREG00000017858 gnptg 0 3
## ENSPREG00000017631 znf668 0 3
## ENSPREG00000017637 znf646 0 3
## ENSPREG00000013796 uncharacterised 0 3
## ENSPREG00000004581 mef2cb 1 3x <- rbind(head(cnt[order(-cnt[,1]),],20) , tail(cnt[order(cnt[,2]),],20))
x## up down
## ENSPREG00000019859 NFIB 4 0
## ENSPREG00000000942 uncharacterised 4 1
## ENSPREG00000002366 schip1 3 1
## ENSPREG00000017857 syngap1b 3 0
## ENSPREG00000018480 si:ch211-176g6.2 3 0
## ENSPREG00000003894 uncharacterised 3 2
## ENSPREG00000016462 adcyap1r1a 3 1
## ENSPREG00000009769 si:ch211-10a23.2 3 0
## ENSPREG00000003185 fam131a 3 0
## ENSPREG00000011277 taok2a 3 1
## ENSPREG00000008872 ndfip2 3 0
## ENSPREG00000021572 uncharacterised 3 3
## ENSPREG00000019119 nrg2a 3 0
## ENSPREG00000008863 NRCAM 3 0
## ENSPREG00000010588 uncharacterised 3 0
## ENSPREG00000008818 arhgap23a 3 1
## ENSPREG00000021385 si:dkey-25g12.4 3 0
## ENSPREG00000016483 klhl29 3 1
## ENSPREG00000004180 prkag2a 3 0
## ENSPREG00000000103 stox2a 3 0
## ENSPREG00000022286 uncharacterised 0 3
## ENSPREG00000001965 npy 0 3
## ENSPREG00000017425 rpz5 0 3
## ENSPREG00000005925 ABR 0 3
## ENSPREG00000022526 tmem69 0 3
## ENSPREG00000011561 wnt7bb 1 3
## ENSPREG00000001234 nagk 0 3
## ENSPREG00000022344 si:ch211-25d12.7 0 3
## ENSPREG00000017759 trioa 0 3
## ENSPREG00000017731 tmem91 0 3
## ENSPREG00000010793 bicc1a 0 3
## ENSPREG00000002903 prkd4 1 3
## ENSPREG00000004182 SLC6A17 1 3
## ENSPREG00000008369 apbb2b 0 3
## ENSPREG00000010983 nrsn1 0 3
## ENSPREG00000020241 copz1 0 3
## ENSPREG00000012737 uncharacterised 0 4
## ENSPREG00000008709 atl2 0 4
## ENSPREG00000007902 r3hdm1 1 5
## ENSPREG00000019594 ppp2r2ca 0 5x[,2] <- x[,2] * -1
x <- x[nrow(x):1,]
xmax=max(x)
xmin=min(x)
par(mar=c(5,15,3,1))
barplot(main = "Differentially methylated tiles in promoters", xlab = "Differentially methylated tiles", x[,1],horiz=TRUE,las=1,xlim=c(xmin,xmax),cex.names=0.75,col="pink")
barplot(x[,2], horiz=TRUE,las=1,xlim=c(xmin,xmax),cex.names=0.75, col="lightblue",add=T, xaxt='n')
Session information
For reproducibility.
sessionInfo()## R version 4.1.1 (2021-08-10)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 20.04.3 LTS
##
## Matrix products: default
## BLAS: /usr/lib/x86_64-linux-gnu/blas/libblas.so.3.9.0
## LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.9.0
##
## locale:
## [1] LC_CTYPE=en_AU.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_AU.UTF-8 LC_COLLATE=en_AU.UTF-8
## [5] LC_MONETARY=en_AU.UTF-8 LC_MESSAGES=en_AU.UTF-8
## [7] LC_PAPER=en_AU.UTF-8 LC_NAME=C
## [9] LC_ADDRESS=C LC_TELEPHONE=C
## [11] LC_MEASUREMENT=en_AU.UTF-8 LC_IDENTIFICATION=C
##
## attached base packages:
## [1] stats4 parallel stats graphics grDevices utils datasets
## [8] methods base
##
## other attached packages:
## [1] beeswarm_0.4.0 vioplot_0.3.7 zoo_1.8-9
## [4] sm_2.2-5.7 methylKit_1.18.0 data.table_1.14.0
## [7] dplyr_1.0.7 RCircos_1.2.1 BiocManager_1.30.16
## [10] GenomicFeatures_1.44.2 AnnotationDbi_1.54.1 Biobase_2.52.0
## [13] GenomicRanges_1.44.0 GenomeInfoDb_1.28.4 IRanges_2.26.0
## [16] S4Vectors_0.30.0 BiocGenerics_0.38.0
##
## loaded via a namespace (and not attached):
## [1] bitops_1.0-7 matrixStats_0.60.1
## [3] bit64_4.0.5 filelock_1.0.2
## [5] progress_1.2.2 httr_1.4.2
## [7] numDeriv_2016.8-1.1 tools_4.1.1
## [9] bslib_0.3.0 utf8_1.2.2
## [11] R6_2.5.1 colorspace_2.0-2
## [13] DBI_1.1.1 fastseg_1.38.0
## [15] tidyselect_1.1.1 prettyunits_1.1.1
## [17] bit_4.0.4 curl_4.3.2
## [19] compiler_4.1.1 xml2_1.3.2
## [21] DelayedArray_0.18.0 rtracklayer_1.52.1
## [23] sass_0.4.0 scales_1.1.1
## [25] mvtnorm_1.1-2 rappdirs_0.3.3
## [27] stringr_1.4.0 digest_0.6.27
## [29] Rsamtools_2.8.0 R.utils_2.10.1
## [31] rmarkdown_2.11 XVector_0.32.0
## [33] pkgconfig_2.0.3 htmltools_0.5.2
## [35] MatrixGenerics_1.4.3 highr_0.9
## [37] limma_3.48.3 dbplyr_2.1.1
## [39] fastmap_1.1.0 bbmle_1.0.24
## [41] rlang_0.4.11 RSQLite_2.2.8
## [43] jquerylib_0.1.4 BiocIO_1.2.0
## [45] generics_0.1.0 jsonlite_1.7.2
## [47] mclust_5.4.7 gtools_3.9.2
## [49] BiocParallel_1.26.2 R.oo_1.24.0
## [51] RCurl_1.98-1.4 magrittr_2.0.1
## [53] GenomeInfoDbData_1.2.6 Matrix_1.3-4
## [55] munsell_0.5.0 Rcpp_1.0.7
## [57] fansi_0.5.0 R.methodsS3_1.8.1
## [59] lifecycle_1.0.0 stringi_1.7.4
## [61] yaml_2.2.1 MASS_7.3-54
## [63] SummarizedExperiment_1.22.0 zlibbioc_1.38.0
## [65] plyr_1.8.6 qvalue_2.24.0
## [67] BiocFileCache_2.0.0 grid_4.1.1
## [69] blob_1.2.2 bdsmatrix_1.3-4
## [71] crayon_1.4.1 lattice_0.20-45
## [73] splines_4.1.1 Biostrings_2.60.2
## [75] hms_1.1.0 KEGGREST_1.32.0
## [77] knitr_1.34 pillar_1.6.2
## [79] rjson_0.2.20 reshape2_1.4.4
## [81] biomaRt_2.48.3 XML_3.99-0.7
## [83] glue_1.4.2 evaluate_0.14
## [85] png_0.1-7 vctrs_0.3.8
## [87] gtable_0.3.0 purrr_0.3.4
## [89] assertthat_0.2.1 cachem_1.0.6
## [91] ggplot2_3.3.5 emdbook_1.3.12
## [93] xfun_0.26 restfulr_0.0.13
## [95] coda_0.19-4 tibble_3.1.4
## [97] GenomicAlignments_1.28.0 memoise_2.0.0
## [99] ellipsis_0.3.2