dmrseq Results Analysis
Aaron Kovacs & Mark Ziemann
2021-10-16
This code is available at https://github.com/aaronsk7/guppy-methylation
https://cran.r-project.org/web/packages/RCircos/vignettes/Using_RCircos.pdf
dmrs before annotation
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, seconddmrseqCvG <- readRDS("/mnt/data/aaron/projects/guppy-methylation/dmrseqrds/dmrseqCvG.rds")
dmrseqCvL <- readRDS("/mnt/data/aaron/projects/guppy-methylation/dmrseqrds/dmrseqCvL.rds")
dmrseqGvL <- readRDS("/mnt/data/aaron/projects/guppy-methylation/dmrseqrds/dmrseqGvL.rds")
dmrseqCvG## GRanges object with 110780 ranges and 7 metadata columns:
## seqnames ranges strand | L area
## <Rle> <IRanges> <Rle> | <integer> <numeric>
## [1] LG21 15968848-15969922 * | 69 15.17042
## [2] LG13 18160946-18161700 * | 75 17.10434
## [3] LG8 27368425-27368499 * | 22 1.10760
## [4] KK215287.1 628700-629071 * | 42 2.46231
## [5] KK215308.1 92510-92874 * | 65 4.00345
## ... ... ... ... . ... ...
## [110776] LG23 9878111-9878189 * | 5 0.325355
## [110777] LG4 23297854-23297875 * | 5 0.255117
## [110778] LG7 27950078-27950229 * | 6 0.313935
## [110779] LG5 6841358-6841438 * | 10 0.530287
## [110780] LG11 26442624-26442768 * | 5 0.269579
## beta stat pval qval index
## <numeric> <numeric> <numeric> <numeric> <IRanges>
## [1] -0.512678 -12.8289 3.16845e-05 0.719377 11675769-11675837
## [2] 0.480479 12.3558 4.01337e-05 0.719377 4371608-4371682
## [3] -0.359863 -12.3461 4.11898e-05 0.719377 18010981-18011002
## [4] -0.357702 -12.2466 4.22460e-05 0.719377 186337-186378
## [5] -0.303095 -12.1655 4.43583e-05 0.719377 437886-437950
## ... ... ... ... ... ...
## [110776] -1.01705e-04 -0.000542256 0.999958 0.999982 12925373-12925377
## [110777] 6.70295e-05 0.000511830 0.999960 0.999982 14612277-14612281
## [110778] -3.85822e-05 -0.000399293 0.999964 0.999982 17189367-17189372
## [110779] -1.24165e-05 -0.000137088 0.999985 0.999989 15004610-15004619
## [110780] -1.32305e-05 -0.000108119 0.999989 0.999989 3196546-3196550
## -------
## seqinfo: 1181 sequences from an unspecified genome; no seqlengthshead(dmrseqCvL)## GRanges object with 6 ranges and 7 metadata columns:
## seqnames ranges strand | L area beta
## <Rle> <IRanges> <Rle> | <integer> <numeric> <numeric>
## [1] LG19 10333007-10333692 * | 71 16.55967 0.576766
## [2] LG21 14273013-14273749 * | 81 14.61418 0.464748
## [3] KK215293.1 186354-186845 * | 61 5.16072 0.391140
## [4] LG13 22015858-22016352 * | 82 14.22619 0.439795
## [5] KK215283.1 1376211-1376895 * | 104 13.72310 0.361397
## [6] LG17 1251474-1251938 * | 61 12.56082 -0.401292
## stat pval qval index
## <numeric> <numeric> <numeric> <IRanges>
## [1] 18.9921 9.99999e-07 0.111437 8673138-8673208
## [2] 15.3892 7.99999e-06 0.445748 11372899-11372979
## [3] 12.1651 4.00000e-05 0.910330 296821-296881
## [4] 11.5744 6.59999e-05 0.910330 4374338-4374419
## [5] 11.5460 6.59999e-05 0.910330 56943-57046
## [6] -11.4403 7.09999e-05 0.910330 7069344-7069404
## -------
## seqinfo: 1180 sequences from an unspecified genome; no seqlengthshead(dmrseqGvL)## GRanges object with 6 ranges and 7 metadata columns:
## seqnames ranges strand | L area beta
## <Rle> <IRanges> <Rle> | <integer> <numeric> <numeric>
## [1] LG11 28461237-28461741 * | 108 11.63697 -0.277374
## [2] KK215283.1 1376121-1376899 * | 156 18.40713 0.329127
## [3] LG20 17269425-17270374 * | 73 10.41376 0.475571
## [4] LG1 22240537-22241922 * | 78 8.68085 0.351599
## [5] LG2 28494008-28495445 * | 65 9.70966 0.462682
## [6] LG13 18160946-18161831 * | 95 16.31186 -0.397064
## stat pval qval index
## <numeric> <numeric> <numeric> <IRanges>
## [1] -16.2750 7.14404e-06 0.653851 3678849-3678956
## [2] 15.2345 1.78601e-05 0.749204 65611-65766
## [3] 14.5876 2.50041e-05 0.749204 12375529-12375601
## [4] 13.2709 4.64363e-05 0.749204 1550715-1550792
## [5] 12.8543 5.47710e-05 0.749204 11413014-11413078
## [6] -12.7574 5.59616e-05 0.749204 4929871-4929965
## -------
## seqinfo: 1169 sequences from an unspecified genome; no seqlengthsCvGdmrs <- as.data.frame(dmrseqCvG,row.names = 1:nrow(as.data.frame(ranges(dmrseqCvG))))
head(CvGdmrs,10)## seqnames start end width strand L area beta stat
## 1 LG21 15968848 15969922 1075 * 69 15.170417 -0.5126778 -12.82890
## 2 LG13 18160946 18161700 755 * 75 17.104340 0.4804793 12.35578
## 3 LG8 27368425 27368499 75 * 22 1.107603 -0.3598625 -12.34614
## 4 KK215287.1 628700 629071 372 * 42 2.462310 -0.3577019 -12.24660
## 5 KK215308.1 92510 92874 365 * 65 4.003455 -0.3030945 -12.16552
## 6 LG2 18092802 18093635 834 * 53 9.373725 -0.3978501 -12.07243
## 7 LG5 2971274 2971545 272 * 61 8.495669 0.3785743 11.65333
## 8 KK215283.1 934758 935340 583 * 78 5.694514 0.3357201 11.28039
## 9 LG10 32171882 32172301 420 * 46 8.597024 0.4390605 11.17294
## 10 LG13 18052556 18054100 1545 * 81 10.961955 -0.3413481 -11.11704
## pval qval index.start index.end index.width
## 1 3.168447e-05 0.7193775 11675769 11675837 69
## 2 4.013367e-05 0.7193775 4371608 4371682 75
## 3 4.118982e-05 0.7193775 18010981 18011002 22
## 4 4.224596e-05 0.7193775 186337 186378 42
## 5 4.435826e-05 0.7193775 437886 437950 65
## 6 4.541441e-05 0.7193775 9863892 9863944 53
## 7 6.442510e-05 0.7193775 14903599 14903659 61
## 8 8.449193e-05 0.7193775 37410 37487 78
## 9 9.082882e-05 0.7193775 2481310 2481355 46
## 10 9.399727e-05 0.7193775 4367383 4367463 81CvLdmrs <- as.data.frame(dmrseqCvL,row.names = 1:nrow(as.data.frame(ranges(dmrseqCvL))))
head(CvLdmrs,10)## seqnames start end width strand L area beta stat
## 1 LG19 10333007 10333692 686 * 71 16.559670 0.5767663 18.99209
## 2 LG21 14273013 14273749 737 * 81 14.614182 0.4647484 15.38915
## 3 KK215293.1 186354 186845 492 * 61 5.160722 0.3911403 12.16515
## 4 LG13 22015858 22016352 495 * 82 14.226193 0.4397952 11.57442
## 5 KK215283.1 1376211 1376895 685 * 104 13.723096 0.3613973 11.54604
## 6 LG17 1251474 1251938 465 * 61 12.560822 -0.4012925 -11.44033
## 7 LG8 18982718 18983377 660 * 60 7.212046 -0.3746378 -11.38354
## 8 LG11 14181818 14182182 365 * 58 4.745863 -0.3570840 -11.25378
## 9 LG2 16355666 16355981 316 * 76 6.324347 0.3183476 10.87880
## 10 LG4 15409098 15410303 1206 * 85 11.219454 -0.3823658 -10.81088
## pval qval index.start index.end index.width
## 1 9.999990e-07 0.1114369 8673138 8673208 71
## 2 7.999992e-06 0.4457476 11372899 11372979 81
## 3 3.999996e-05 0.9103295 296821 296881 61
## 4 6.599993e-05 0.9103295 4374338 4374419 82
## 5 6.599993e-05 0.9103295 56943 57046 104
## 6 7.099993e-05 0.9103295 7069344 7069404 61
## 7 7.399993e-05 0.9103295 17405986 17406045 60
## 8 8.099992e-05 0.9103295 2836015 2836072 58
## 9 1.009999e-04 0.9103295 9599998 9600073 76
## 10 1.069999e-04 0.9103295 14042960 14043044 85GvLdmrs <- as.data.frame(dmrseqGvL,row.names = 1:nrow(as.data.frame(ranges(dmrseqGvL))))
head(GvLdmrs,10)## seqnames start end width strand L area beta stat
## 1 LG11 28461237 28461741 505 * 108 11.636971 -0.2773737 -16.27500
## 2 KK215283.1 1376121 1376899 779 * 156 18.407129 0.3291269 15.23454
## 3 LG20 17269425 17270374 950 * 73 10.413759 0.4755714 14.58765
## 4 LG1 22240537 22241922 1386 * 78 8.680847 0.3515985 13.27092
## 5 LG2 28494008 28495445 1438 * 65 9.709663 0.4626823 12.85427
## 6 LG13 18160946 18161831 886 * 95 16.311864 -0.3970642 -12.75740
## 7 KK215287.1 944627 944828 202 * 36 4.299457 -0.4584372 -12.68316
## 8 LG11 10041760 10042135 376 * 75 6.666626 0.3701602 12.64751
## 9 KK215306.1 101373 102087 715 * 68 9.626653 0.4324903 12.37528
## 10 LG5 2971274 2971545 272 * 58 7.527239 -0.3990748 -12.02408
## pval qval index.start index.end index.width
## 1 7.144039e-06 0.6538511 3678849 3678956 108
## 2 1.786010e-05 0.7492043 65611 65766 156
## 3 2.500414e-05 0.7492043 12375529 12375601 73
## 4 4.643626e-05 0.7492043 1550715 1550792 78
## 5 5.477097e-05 0.7492043 11413014 11413078 65
## 6 5.596164e-05 0.7492043 4929871 4929965 95
## 7 6.072433e-05 0.7492043 223719 223754 36
## 8 6.548703e-05 0.7492043 3123427 3123501 75
## 9 7.620309e-05 0.7749346 479142 479209 68
## 10 9.287251e-05 0.7879743 16775120 16775177 58gtf <- 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 seqlengthsdmrs annotated to genes
ol1 <- findOverlaps(dmrseqCvG,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, KK215360.1, KK215378.1, KK215383.1, KK215387.1, KK215391.1, KK215393.1, KK215395.1, KK215396.1, KK215400.1, KK215401.1, KK215405.1, KK215406.1, KK215407.1, KK215408.1, KK215411.1, KK215415.1, KK215418.1, KK215421.1, KK215424.1, 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, KK215513.1, KK215514.1, KK215515.1, KK215516.1, KK215517.1, KK215518.1, KK215519.1, KK215521.1, KK215523.1, KK215524.1, KK215525.1, KK215528.1, KK215529.1, KK215530.1, KK215531.1, KK215533.1, KK215538.1, KK215540.1, KK215541.1, KK215543.1, KK215544.1, KK215545.1, KK215547.1, KK215548.1, KK215549.1, KK215551.1, KK215556.1, KK215558.1, KK215559.1, KK215560.1, KK215561.1, KK215567.1, KK215568.1, KK215573.1, KK215574.1, KK215577.1, KK215578.1, KK215581.1, KK215583.1, KK215585.1, KK215586.1, KK215587.1, KK215588.1, KK215589.1, KK215590.1, KK215594.1, KK215595.1, KK215597.1, KK215598.1, KK215601.1, KK215605.1, KK215606.1, KK215608.1, KK215615.1, KK215616.1, KK215620.1, KK215621.1, KK215624.1, KK215625.1, KK215626.1, KK215627.1, KK215628.1, KK215629.1, KK215630.1, KK215633.1, KK215634.1, KK215635.1, KK215636.1, KK215637.1, KK215639.1, KK215641.1, KK215642.1, 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, KK215683.1, KK215684.1, KK215688.1, KK215692.1, KK215695.1, KK215700.1, KK215701.1, KK215703.1, KK215704.1, KK215705.1, KK215706.1, KK215709.1, KK215710.1, KK215711.1, KK215719.1, KK215720.1, KK215721.1, KK215722.1, KK215724.1, KK215726.1, KK215727.1, KK215728.1, KK215733.1, KK215734.1, KK215736.1, KK215737.1, KK215738.1, KK215739.1, KK215741.1, KK215742.1, KK215743.1, KK215745.1, KK215750.1, KK215752.1, KK215753.1, KK215754.1, KK215755.1, KK215756.1, KK215757.1, KK215762.1, KK215763.1, KK215767.1, KK215768.1, KK215769.1, KK215770.1, KK215772.1, 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, KK215797.1, KK215798.1, KK215802.1, KK215804.1, KK215807.1, KK215810.1, KK215812.1, KK215814.1, KK215815.1, KK215816.1, KK215821.1, KK215825.1, KK215827.1, KK215832.1, KK215834.1, KK215836.1, KK215837.1, KK215838.1, KK215843.1, KK215848.1, KK215849.1, KK215854.1, KK215857.1, KK215858.1, KK215859.1, KK215861.1, KK215863.1, KK215864.1, KK215872.1, KK215873.1, KK215875.1, KK215877.1, KK215878.1, KK215880.1, KK215881.1, KK215882.1, KK215885.1, KK215886.1, KK215890.1, KK215891.1, KK215894.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215907.1, KK215909.1, KK215910.1, KK215911.1, KK215914.1, KK215915.1, KK215918.1, KK215921.1, KK215922.1, KK215923.1, KK215928.1, KK215929.1, KK215934.1, KK215935.1, KK215937.1, KK215942.1, KK215943.1, KK215945.1, KK215946.1, KK215949.1, KK215951.1, KK215953.1, KK215956.1, KK215957.1, KK215960.1, KK215962.1, KK215965.1, KK215967.1, KK215969.1, KK215970.1, KK215973.1, KK215974.1, KK215976.1, KK215977.1, KK215979.1, KK215982.1, KK215983.1, KK215984.1, KK215987.1, KK215990.1, KK215993.1, KK215994.1, KK215997.1, KK215999.1, KK216000.1, KK216001.1, KK216012.1, KK216015.1, KK216017.1, KK216018.1, KK216021.1, KK216023.1, KK216025.1, KK216026.1, KK216028.1, KK216029.1, KK216030.1, KK216032.1, KK216033.1, KK216034.1, KK216035.1, KK216037.1, KK216038.1, KK216039.1, KK216040.1, KK216041.1, KK216044.1, KK216049.1, KK216053.1, 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, KK216079.1, KK216082.1, KK216084.1, KK216085.1, KK216086.1, KK216089.1, KK216093.1, KK216094.1, KK216097.1, KK216099.1, KK216102.1, KK216103.1, KK216109.1, KK216111.1, KK216114.1, KK216118.1, KK216120.1, KK216122.1, KK216124.1, KK216128.1, KK216133.1, KK216134.1, KK216135.1, KK216141.1, KK216142.1, KK216143.1, KK216150.1, KK216152.1, KK216155.1, KK216157.1, KK216158.1, KK216165.1, KK216166.1, KK216169.1, KK216171.1, KK216172.1, KK216173.1, KK216174.1, KK216175.1, KK216177.1, KK216180.1, KK216184.1, KK216186.1, KK216190.1, KK216193.1, KK216194.1, KK216195.1, KK216197.1, KK216200.1, KK216203.1, KK216208.1, KK216212.1, KK216213.1, KK216215.1, KK216219.1, KK216222.1, KK216225.1, KK216226.1, KK216227.1, KK216229.1, KK216232.1, KK216236.1, KK216237.1, KK216238.1, KK216240.1, KK216241.1, KK216244.1, KK216245.1, KK216251.1, KK216253.1, KK216254.1, KK216256.1, KK216259.1, KK216260.1, KK216261.1, KK216264.1, KK216266.1, KK216270.1, KK216273.1, KK216275.1, KK216278.1, KK216280.1, KK216281.1, KK216282.1, KK216284.1, KK216285.1, KK216287.1, KK216289.1, KK216290.1, KK216295.1, KK216303.1, KK216306.1, KK216310.1, KK216313.1, KK216320.1, KK216322.1, KK216323.1, KK216324.1, KK216325.1, KK216326.1, KK216329.1, KK216330.1, KK216331.1, KK216334.1, KK216336.1, KK216341.1, KK216342.1, KK216351.1, KK216359.1, KK216360.1, KK216363.1, KK216364.1, KK216366.1, KK216368.1, KK216370.1, KK216371.1, KK216377.1, KK216383.1, KK216384.1, KK216389.1, KK216391.1, KK216394.1, KK216396.1, KK216402.1, KK216404.1, KK216405.1, KK216408.1, KK216410.1, KK216414.1, KK216418.1, KK216420.1, KK216422.1, KK216423.1, KK216428.1, KK216432.1, KK216433.1, KK216436.1, KK216438.1, KK216440.1, KK216442.1, KK216445.1, KK216447.1, KK216451.1, KK216452.1, KK216453.1, KK216456.1, KK216457.1, KK216458.1, KK216462.1, KK216468.1, KK216477.1, KK216482.1, KK216492.1, KK216502.1, KK216504.1, KK216506.1, KK216507.1, KK216508.1, KK216510.1, KK216511.1, KK216512.1, KK216513.1, KK216514.1, KK216515.1, KK216519.1, KK216523.1, KK216526.1, KK216530.1, KK216531.1, KK216538.1, KK216540.1, KK216548.1, KK216552.1, KK216553.1, KK216556.1, KK216569.1, KK216571.1, KK216572.1, KK216574.1, KK216576.1, KK216592.1, KK216599.1, KK216606.1, KK216607.1, KK216610.1, KK216615.1, KK216627.1, KK216638.1, KK216640.1, KK216647.1, KK216651.1, KK216657.1, KK216661.1, KK216665.1, KK216672.1, KK216674.1, KK216678.1, KK216680.1, KK216685.1, KK216691.1, KK216695.1, KK216709.1, KK216712.1, KK216714.1, KK216716.1, KK216717.1, KK216725.1, KK216726.1, KK216732.1, KK216737.1, KK216740.1, KK216745.1, KK216746.1, KK216748.1, KK216752.1, KK216758.1, KK216763.1, KK216773.1, KK216779.1, KK216780.1, KK216782.1, KK216784.1, KK216792.1, KK216800.1, KK216804.1, KK216811.1, KK216814.1, KK216815.1, KK216817.1, KK216830.1, KK216831.1, KK216834.1, KK216842.1, KK216848.1, KK216852.1, KK216859.1, KK216861.1, KK216863.1, KK216865.1, KK216867.1, KK216870.1, KK216873.1, KK216879.1, KK216881.1, KK216887.1, KK216896.1, KK216898.1, KK216899.1, KK216903.1, KK216905.1, KK216912.1, KK216913.1, KK216914.1, KK216921.1, KK216922.1, KK216923.1, KK216930.1, KK216931.1, KK216934.1, KK216942.1, KK216943.1, KK216945.1, KK216946.1, KK216950.1, KK216954.1, KK216957.1, KK216959.1, KK216963.1, KK216964.1, KK216965.1, KK216968.1, KK216971.1, KK216973.1, KK216974.1, KK216975.1, KK216980.1, KK216987.1, KK216988.1, KK216994.1, KK216999.1, KK217000.1, KK217001.1, KK217002.1, KK217003.1, KK217007.1, KK217012.1, KK217019.1, KK217032.1, KK217037.1, KK217059.1, KK217063.1, KK217065.1, KK217066.1, KK217072.1, KK217074.1, KK217076.1, KK217077.1, KK217079.1, KK217082.1, KK217083.1, KK217086.1, KK217088.1, KK217093.1, KK217098.1, KK217101.1, KK217103.1, KK217105.1, KK217109.1, KK217111.1, KK217112.1, KK217114.1, KK217117.1, KK217119.1, KK217120.1, KK217121.1, KK217123.1, KK217126.1, KK217128.1, KK217130.1, KK217135.1, KK217140.1, KK217146.1, KK217147.1, KK217182.ol1## Hits object with 56579 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 2 6028
## [2] 3 17487
## [3] 3 17488
## [4] 4 22168
## [5] 7 4577
## ... ... ...
## [56575] 110773 21103
## [56576] 110775 7760
## [56577] 110776 21716
## [56578] 110777 10297
## [56579] 110779 4735
## -------
## queryLength: 110780 / subjectLength: 23254CvGgenes <- dmrseqCvG[queryHits(ol1)]
mygenesol1 <- my_genes[subjectHits(ol1)]
head(CvGgenes)## GRanges object with 6 ranges and 7 metadata columns:
## seqnames ranges strand | L area beta
## <Rle> <IRanges> <Rle> | <integer> <numeric> <numeric>
## [1] LG13 18160946-18161700 * | 75 17.10434 0.480479
## [2] LG8 27368425-27368499 * | 22 1.10760 -0.359863
## [3] LG8 27368425-27368499 * | 22 1.10760 -0.359863
## [4] KK215287.1 628700-629071 * | 42 2.46231 -0.357702
## [5] LG5 2971274-2971545 * | 61 8.49567 0.378574
## [6] LG5 2971274-2971545 * | 61 8.49567 0.378574
## stat pval qval index
## <numeric> <numeric> <numeric> <IRanges>
## [1] 12.3558 4.01337e-05 0.719377 4371608-4371682
## [2] -12.3461 4.11898e-05 0.719377 18010981-18011002
## [3] -12.3461 4.11898e-05 0.719377 18010981-18011002
## [4] -12.2466 4.22460e-05 0.719377 186337-186378
## [5] 11.6533 6.44251e-05 0.719377 14903599-14903659
## [6] 11.6533 6.44251e-05 0.719377 14903599-14903659
## -------
## seqinfo: 1181 sequences from an unspecified genome; no seqlengthsmygenesol1## GRanges object with 56579 ranges and 3 metadata columns:
## seqnames ranges strand | gene_id
## <Rle> <IRanges> <Rle> | <character>
## [1] LG13 18160798-18170662 - | ENSPREG00000001265
## [2] LG8 27350463-27375917 - | ENSPREG00000012374
## [3] LG8 27361755-27370706 - | ENSPREG00000012413
## [4] KK215287.1 624615-641867 - | ENSPREG00000006712
## [5] LG5 2895024-3016337 + | ENSPREG00000022808
## ... ... ... ... . ...
## [56575] LG18 11954586-12063344 - | ENSPREG00000015063
## [56576] LG10 4384736-4654413 + | ENSPREG00000021348
## [56577] LG23 9858311-9900905 + | ENSPREG00000009690
## [56578] LG4 23260611-23303354 + | ENSPREG00000008408
## [56579] LG5 6823071-6850398 + | ENSPREG00000006274
## gene_biotype gene_name
## <character> <character>
## [1] protein_coding <NA>
## [2] protein_coding btr30
## [3] protein_coding <NA>
## [4] protein_coding supt5h
## [5] protein_coding <NA>
## ... ... ...
## [56575] protein_coding efnb3b
## [56576] protein_coding TENM1
## [56577] protein_coding ahcyl2b
## [56578] protein_coding unc13a
## [56579] protein_coding iffo2b
## -------
## 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': 56579 obs. of 14 variables:
## $ seqnames : Factor w/ 1181 levels "KK215283.1","KK215284.1",..: 1163 1180 1180 5 1177 1177 1 1160 1163 1169 ...
## $ start : int 18160946 27368425 27368425 628700 2971274 2971274 934758 32171882 18052556 10333007 ...
## $ end : int 18161700 27368499 27368499 629071 2971545 2971545 935340 32172301 18054100 10333692 ...
## $ width : int 755 75 75 372 272 272 583 420 1545 686 ...
## $ strand : Factor w/ 3 levels "+","-","*": 3 3 3 3 3 3 3 3 3 3 ...
## $ L : int 75 22 22 42 61 61 78 46 81 70 ...
## $ area : num 17.1 1.11 1.11 2.46 8.5 ...
## $ beta : num 0.48 -0.36 -0.36 -0.358 0.379 ...
## $ stat : num 12.4 -12.3 -12.3 -12.2 11.7 ...
## $ pval : num 4.01e-05 4.12e-05 4.12e-05 4.22e-05 6.44e-05 ...
## $ qval : num 0.719 0.719 0.719 0.719 0.719 ...
## $ index.start: int 4371608 18010981 18010981 186337 14903599 14903599 37410 2481310 4367383 8864531 ...
## $ index.end : int 4371682 18011002 18011002 186378 14903659 14903659 37487 2481355 4367463 8864600 ...
## $ index.width: int 75 22 22 42 61 61 78 46 81 70 ...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 LG13 18160798 18170662 9865 - ENSPREG00000001265 protein_coding
## 2 LG8 27350463 27375917 25455 - ENSPREG00000012374 protein_coding
## 3 LG8 27361755 27370706 8952 - ENSPREG00000012413 protein_coding
## 4 KK215287.1 624615 641867 17253 - ENSPREG00000006712 protein_coding
## 5 LG5 2895024 3016337 121314 + ENSPREG00000022808 protein_coding
## 6 LG5 2967898 2981871 13974 + ENSPREG00000022867 protein_coding
## gene_name
## 1 <NA>
## 2 btr30
## 3 <NA>
## 4 supt5h
## 5 <NA>
## 6 asb14aCvGgenesdf <- cbind(CvGgenesdf,mygenesoldf1[c("gene_id","gene_biotype","gene_name")])
CvGgenesdf$seqnames <- as.character(CvGgenesdf$seqnames)
head(CvGgenesdf)## seqnames start end width strand L area beta stat
## 1 LG13 18160946 18161700 755 * 75 17.104340 0.4804793 12.35578
## 2 LG8 27368425 27368499 75 * 22 1.107603 -0.3598625 -12.34614
## 3 LG8 27368425 27368499 75 * 22 1.107603 -0.3598625 -12.34614
## 4 KK215287.1 628700 629071 372 * 42 2.462310 -0.3577019 -12.24660
## 5 LG5 2971274 2971545 272 * 61 8.495669 0.3785743 11.65333
## 6 LG5 2971274 2971545 272 * 61 8.495669 0.3785743 11.65333
## pval qval index.start index.end index.width gene_id
## 1 4.013367e-05 0.7193775 4371608 4371682 75 ENSPREG00000001265
## 2 4.118982e-05 0.7193775 18010981 18011002 22 ENSPREG00000012374
## 3 4.118982e-05 0.7193775 18010981 18011002 22 ENSPREG00000012413
## 4 4.224596e-05 0.7193775 186337 186378 42 ENSPREG00000006712
## 5 6.442510e-05 0.7193775 14903599 14903659 61 ENSPREG00000022808
## 6 6.442510e-05 0.7193775 14903599 14903659 61 ENSPREG00000022867
## gene_biotype gene_name
## 1 protein_coding <NA>
## 2 protein_coding btr30
## 3 protein_coding <NA>
## 4 protein_coding supt5h
## 5 protein_coding <NA>
## 6 protein_coding asb14aCvGgeneschrdf <- CvGgenesdf[grep("LG",CvGgenesdf$seqnames),]
head(CvGgeneschrdf,20)## seqnames start end width strand L area beta stat
## 1 LG13 18160946 18161700 755 * 75 17.104340 0.4804793 12.35578
## 2 LG8 27368425 27368499 75 * 22 1.107603 -0.3598625 -12.34614
## 3 LG8 27368425 27368499 75 * 22 1.107603 -0.3598625 -12.34614
## 5 LG5 2971274 2971545 272 * 61 8.495669 0.3785743 11.65333
## 6 LG5 2971274 2971545 272 * 61 8.495669 0.3785743 11.65333
## 8 LG10 32171882 32172301 420 * 46 8.597024 0.4390605 11.17294
## 9 LG13 18052556 18054100 1545 * 81 10.961955 -0.3413481 -11.11704
## 10 LG19 10333007 10333692 686 * 70 10.588759 0.4116465 10.86281
## 11 LG19 8889655 8889899 245 * 47 2.420966 -0.2756728 -10.81171
## 13 LG20 10526898 10527306 409 * 61 5.646018 0.2998656 10.73088
## 14 LG19 25883884 25884226 343 * 27 1.833101 -0.3775782 -10.70954
## 15 LG11 3353555 3354323 769 * 64 7.604367 0.3888157 10.70122
## 16 LG11 10641658 10642177 520 * 56 6.750824 0.4028755 10.69685
## 17 LG4 4685116 4685638 523 * 91 11.170358 0.2888801 10.61794
## 18 LG10 14876068 14876399 332 * 40 6.857049 -0.4594013 -10.43686
## 19 LG1 17896682 17897364 683 * 78 7.067168 -0.4086131 -10.41726
## 20 LG2 43981407 43981496 90 * 17 2.421572 -0.5597475 -10.38898
## 21 LG15 25594055 25594564 510 * 40 5.525193 -0.3638675 -10.28654
## 22 LG22 7737092 7737838 747 * 53 9.508586 -0.3861418 -10.21539
## 23 LG4 20353270 20354327 1058 * 106 14.873154 -0.3722110 -10.15553
## pval qval index.start index.end index.width gene_id
## 1 4.013367e-05 0.7193775 4371608 4371682 75 ENSPREG00000001265
## 2 4.118982e-05 0.7193775 18010981 18011002 22 ENSPREG00000012374
## 3 4.118982e-05 0.7193775 18010981 18011002 22 ENSPREG00000012413
## 5 6.442510e-05 0.7193775 14903599 14903659 61 ENSPREG00000022808
## 6 6.442510e-05 0.7193775 14903599 14903659 61 ENSPREG00000022867
## 8 9.082882e-05 0.7193775 2481310 2481355 46 ENSPREG00000011064
## 9 9.399727e-05 0.7193775 4367383 4367463 81 ENSPREG00000000933
## 10 1.214571e-04 0.7193775 8864531 8864600 70 ENSPREG00000002350
## 11 1.267379e-04 0.7193775 8825906 8825952 47 ENSPREG00000023139
## 13 1.288502e-04 0.7193775 10806313 10806373 61 ENSPREG00000014890
## 14 1.320186e-04 0.7193775 9287677 9287703 27 ENSPREG00000001233
## 15 1.320186e-04 0.7193775 2578887 2578950 64 ENSPREG00000015120
## 16 1.320186e-04 0.7193775 2790037 2790092 56 ENSPREG00000001606
## 17 1.394117e-04 0.7193775 14118347 14118437 91 ENSPREG00000003007
## 18 1.679277e-04 0.7193775 2066128 2066167 40 ENSPREG00000009354
## 19 1.700400e-04 0.7193775 1269169 1269246 78 ENSPREG00000004582
## 20 1.721523e-04 0.7193775 10466014 10466030 17 ENSPREG00000020262
## 21 1.869384e-04 0.7193775 6174658 6174697 40 ENSPREG00000008175
## 22 1.996122e-04 0.7193775 12131403 12131455 53 ENSPREG00000012960
## 23 2.101737e-04 0.7193775 14521160 14521265 106 ENSPREG00000021212
## gene_biotype gene_name
## 1 protein_coding <NA>
## 2 protein_coding btr30
## 3 protein_coding <NA>
## 5 protein_coding <NA>
## 6 protein_coding asb14a
## 8 protein_coding NFKB1
## 9 protein_coding capn12
## 10 protein_coding QRFPR
## 11 protein_coding eif3c
## 13 protein_coding <NA>
## 14 protein_coding bbs1
## 15 protein_coding kcnk9
## 16 protein_coding <NA>
## 17 protein_coding <NA>
## 18 protein_coding dlg3
## 19 protein_coding <NA>
## 20 protein_coding cry3a
## 21 protein_coding GNG4
## 22 protein_coding efna2a
## 23 protein_coding DAB1rm(CvGgenes)
rm(CvGgenesdf)ol2 <- findOverlaps(dmrseqCvL,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, KK215351.1, KK215360.1, KK215378.1, KK215387.1, KK215391.1, KK215393.1, KK215395.1, KK215396.1, KK215400.1, KK215401.1, KK215405.1, KK215406.1, KK215407.1, KK215408.1, KK215411.1, KK215412.1, KK215414.1, KK215415.1, KK215418.1, KK215420.1, KK215421.1, KK215424.1, KK215427.1, KK215430.1, KK215432.1, KK215433.1, KK215435.1, KK215439.1, 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, 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, KK215581.1, KK215582.1, KK215583.1, KK215585.1, KK215586.1, KK215587.1, KK215588.1, 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, KK215621.1, 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, KK215646.1, KK215647.1, KK215649.1, KK215652.1, KK215654.1, KK215655.1, KK215657.1, KK215658.1, KK215661.1, KK215662.1, KK215663.1, KK215665.1, KK215668.1, KK215670.1, KK215671.1, KK215672.1, KK215673.1, KK215675.1, KK215677.1, KK215683.1, KK215688.1, KK215692.1, KK215700.1, KK215701.1, KK215703.1, KK215704.1, KK215705.1, KK215706.1, KK215707.1, KK215709.1, KK215710.1, KK215711.1, KK215712.1, KK215719.1, KK215720.1, KK215721.1, KK215722.1, KK215723.1, KK215724.1, KK215726.1, KK215727.1, KK215733.1, KK215734.1, KK215736.1, KK215737.1, KK215738.1, KK215739.1, KK215741.1, KK215742.1, KK215748.1, KK215750.1, KK215752.1, KK215753.1, KK215754.1, KK215755.1, KK215756.1, KK215757.1, KK215758.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215767.1, KK215768.1, KK215769.1, KK215770.1, KK215772.1, KK215775.1, KK215776.1, KK215777.1, KK215778.1, KK215780.1, KK215782.1, KK215783.1, KK215785.1, KK215788.1, KK215789.1, KK215792.1, KK215794.1, KK215795.1, KK215797.1, KK215798.1, KK215802.1, KK215804.1, KK215807.1, KK215810.1, KK215812.1, KK215814.1, KK215816.1, KK215819.1, KK215825.1, KK215827.1, KK215832.1, KK215834.1, KK215838.1, KK215839.1, KK215840.1, KK215841.1, KK215842.1, KK215843.1, KK215849.1, KK215857.1, KK215860.1, KK215861.1, KK215863.1, KK215864.1, KK215870.1, KK215875.1, KK215878.1, KK215881.1, KK215885.1, KK215886.1, KK215891.1, KK215894.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215903.1, KK215907.1, KK215908.1, KK215909.1, KK215911.1, KK215915.1, KK215917.1, KK215918.1, KK215920.1, KK215921.1, KK215923.1, KK215927.1, KK215928.1, KK215929.1, KK215934.1, KK215935.1, KK215937.1, KK215938.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215949.1, KK215951.1, KK215952.1, KK215953.1, KK215956.1, KK215957.1, KK215960.1, KK215962.1, KK215965.1, KK215969.1, KK215970.1, KK215971.1, KK215972.1, KK215973.1, KK215974.1, KK215976.1, KK215978.1, KK215979.1, KK215983.1, KK215989.1, KK215990.1, KK215993.1, KK215995.1, KK215997.1, KK215999.1, KK216000.1, KK216001.1, KK216006.1, KK216008.1, KK216012.1, KK216015.1, KK216017.1, KK216021.1, KK216023.1, KK216026.1, KK216027.1, KK216030.1, KK216032.1, KK216036.1, KK216037.1, KK216038.1, KK216039.1, KK216040.1, KK216041.1, KK216044.1, KK216048.1, KK216049.1, KK216050.1, KK216053.1, KK216056.1, KK216059.1, KK216064.1, KK216065.1, KK216068.1, KK216069.1, KK216071.1, KK216072.1, KK216074.1, KK216075.1, KK216076.1, KK216079.1, KK216080.1, KK216082.1, KK216083.1, KK216084.1, KK216087.1, KK216094.1, KK216096.1, KK216097.1, KK216103.1, KK216106.1, KK216109.1, KK216110.1, KK216111.1, KK216112.1, KK216114.1, KK216115.1, KK216118.1, KK216128.1, KK216131.1, KK216135.1, KK216140.1, KK216141.1, KK216143.1, KK216146.1, KK216150.1, KK216159.1, KK216162.1, KK216164.1, KK216165.1, KK216166.1, KK216168.1, KK216171.1, KK216174.1, KK216175.1, KK216176.1, KK216177.1, KK216181.1, KK216184.1, KK216190.1, KK216192.1, KK216193.1, KK216194.1, KK216195.1, KK216197.1, KK216198.1, KK216200.1, KK216202.1, KK216203.1, KK216206.1, KK216208.1, KK216212.1, KK216213.1, KK216214.1, KK216215.1, KK216219.1, KK216225.1, KK216226.1, KK216227.1, KK216229.1, KK216231.1, KK216232.1, KK216234.1, KK216235.1, KK216237.1, KK216241.1, KK216244.1, KK216245.1, KK216251.1, KK216253.1, KK216254.1, KK216256.1, KK216258.1, KK216259.1, KK216263.1, KK216264.1, KK216265.1, KK216266.1, KK216267.1, KK216272.1, KK216273.1, KK216275.1, KK216278.1, KK216280.1, KK216285.1, KK216287.1, KK216288.1, KK216289.1, KK216290.1, KK216291.1, KK216292.1, KK216295.1, KK216304.1, KK216308.1, KK216310.1, KK216316.1, KK216317.1, KK216319.1, KK216320.1, KK216322.1, KK216323.1, KK216324.1, KK216325.1, KK216329.1, KK216341.1, KK216342.1, KK216345.1, KK216347.1, KK216351.1, KK216359.1, KK216364.1, KK216366.1, KK216369.1, KK216370.1, KK216379.1, KK216384.1, KK216385.1, KK216386.1, KK216387.1, KK216388.1, KK216389.1, KK216391.1, KK216392.1, KK216393.1, KK216394.1, KK216396.1, KK216402.1, KK216403.1, KK216404.1, KK216405.1, KK216414.1, KK216418.1, KK216420.1, KK216422.1, KK216430.1, KK216431.1, KK216433.1, KK216436.1, KK216437.1, KK216438.1, KK216440.1, KK216443.1, KK216447.1, KK216452.1, KK216456.1, KK216457.1, KK216462.1, KK216467.1, KK216477.1, KK216486.1, KK216491.1, KK216492.1, KK216499.1, KK216503.1, KK216504.1, KK216506.1, KK216507.1, KK216511.1, KK216512.1, KK216520.1, KK216523.1, KK216530.1, KK216534.1, KK216538.1, KK216540.1, KK216556.1, KK216558.1, KK216570.1, KK216571.1, KK216572.1, KK216574.1, KK216586.1, KK216592.1, KK216595.1, KK216598.1, KK216604.1, KK216606.1, KK216609.1, KK216611.1, KK216615.1, KK216618.1, KK216622.1, KK216627.1, KK216630.1, KK216638.1, KK216641.1, KK216645.1, KK216646.1, KK216647.1, KK216648.1, KK216649.1, KK216650.1, KK216652.1, KK216657.1, KK216661.1, KK216674.1, KK216685.1, KK216688.1, KK216696.1, KK216697.1, KK216704.1, KK216705.1, KK216707.1, KK216709.1, KK216710.1, KK216716.1, KK216717.1, KK216721.1, KK216723.1, KK216725.1, KK216726.1, KK216733.1, KK216737.1, KK216740.1, KK216746.1, KK216747.1, KK216748.1, KK216752.1, KK216761.1, KK216763.1, KK216764.1, KK216767.1, KK216780.1, KK216782.1, KK216784.1, KK216792.1, KK216796.1, KK216803.1, KK216807.1, KK216815.1, KK216817.1, KK216820.1, KK216830.1, KK216841.1, KK216842.1, KK216846.1, KK216847.1, KK216851.1, KK216852.1, KK216865.1, KK216867.1, KK216868.1, KK216870.1, KK216871.1, KK216879.1, KK216880.1, KK216884.1, KK216887.1, KK216895.1, KK216902.1, KK216905.1, KK216908.1, KK216912.1, KK216914.1, KK216918.1, KK216921.1, KK216922.1, KK216930.1, KK216931.1, KK216932.1, KK216945.1, KK216953.1, KK216957.1, KK216968.1, KK216969.1, KK216970.1, KK216971.1, KK216974.1, KK216978.1, KK216980.1, KK216989.1, KK216990.1, KK216994.1, KK216995.1, KK217000.1, KK217002.1, KK217007.1, KK217008.1, KK217012.1, KK217014.1, KK217016.1, KK217019.1, KK217023.1, KK217024.1, KK217026.1, KK217040.1, KK217049.1, KK217053.1, KK217059.1, KK217063.1, KK217064.1, KK217065.1, KK217066.1, KK217068.1, KK217073.1, KK217076.1, KK217079.1, KK217082.1, KK217083.1, KK217088.1, KK217093.1, KK217095.1, KK217098.1, KK217100.1, KK217103.1, KK217104.1, KK217105.1, KK217111.1, KK217112.1, KK217114.1, KK217120.1, KK217123.1, KK217126.1, KK217128.1, KK217130.1, KK217132.1, KK217133.1, KK217135.1, KK217137.1, KK217139.1, KK217140.1, KK217149.1, KK217150.1, KK217154.1, KK217160.1, KK217169.1, KK217172.ol2## Hits object with 56357 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 1 14834
## [2] 3 22340
## [3] 4 6146
## [4] 5 21997
## [5] 5 21998
## ... ... ...
## [56353] 111423 3088
## [56354] 111429 11988
## [56355] 111430 7310
## [56356] 111436 20203
## [56357] 111437 14928
## -------
## queryLength: 111437 / subjectLength: 23254CvLgenes <- dmrseqCvL[queryHits(ol2)]
mygenesol2 <- my_genes[subjectHits(ol2)]
head(mygenesol2)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | gene_id gene_biotype
## <Rle> <IRanges> <Rle> | <character> <character>
## [1] LG19 10324269-10333389 + | ENSPREG00000002350 protein_coding
## [2] KK215293.1 156791-231222 - | ENSPREG00000013418 protein_coding
## [3] LG13 22005868-22053375 - | ENSPREG00000006590 protein_coding
## [4] KK215283.1 1372895-1376892 - | ENSPREG00000019483 protein_coding
## [5] KK215283.1 1376883-1386241 + | ENSPREG00000019522 protein_coding
## [6] LG8 18973748-18997964 + | ENSPREG00000011882 protein_coding
## gene_name
## <character>
## [1] QRFPR
## [2] <NA>
## [3] ankrd13b
## [4] sco2
## [5] calua
## [6] rapgefl1
## -------
## seqinfo: 463 sequences from an unspecified genome; no seqlengthsCvLgenesdf <- as.data.frame(CvLgenes,row.names = 1:nrow(as.data.frame(ranges(CvLgenes))))
head(CvLgenesdf)## seqnames start end width strand L area beta stat
## 1 LG19 10333007 10333692 686 * 71 16.559670 0.5767663 18.99209
## 2 KK215293.1 186354 186845 492 * 61 5.160722 0.3911403 12.16515
## 3 LG13 22015858 22016352 495 * 82 14.226193 0.4397952 11.57442
## 4 KK215283.1 1376211 1376895 685 * 104 13.723096 0.3613973 11.54604
## 5 KK215283.1 1376211 1376895 685 * 104 13.723096 0.3613973 11.54604
## 6 LG8 18982718 18983377 660 * 60 7.212046 -0.3746378 -11.38354
## pval qval index.start index.end index.width
## 1 9.999990e-07 0.1114369 8673138 8673208 71
## 2 3.999996e-05 0.9103295 296821 296881 61
## 3 6.599993e-05 0.9103295 4374338 4374419 82
## 4 6.599993e-05 0.9103295 56943 57046 104
## 5 6.599993e-05 0.9103295 56943 57046 104
## 6 7.399993e-05 0.9103295 17405986 17406045 60mygenesoldf2 <- as.data.frame(mygenesol2,row.names = 1:nrow(as.data.frame(ranges(mygenesol2))))
head(mygenesoldf2)## seqnames start end width strand gene_id gene_biotype
## 1 LG19 10324269 10333389 9121 + ENSPREG00000002350 protein_coding
## 2 KK215293.1 156791 231222 74432 - ENSPREG00000013418 protein_coding
## 3 LG13 22005868 22053375 47508 - ENSPREG00000006590 protein_coding
## 4 KK215283.1 1372895 1376892 3998 - ENSPREG00000019483 protein_coding
## 5 KK215283.1 1376883 1386241 9359 + ENSPREG00000019522 protein_coding
## 6 LG8 18973748 18997964 24217 + ENSPREG00000011882 protein_coding
## gene_name
## 1 QRFPR
## 2 <NA>
## 3 ankrd13b
## 4 sco2
## 5 calua
## 6 rapgefl1CvLgenesdf <- cbind(CvLgenesdf,mygenesoldf2[c("gene_id","gene_biotype","gene_name")])
CvLgenesdf$seqnames <- as.character(CvLgenesdf$seqnames)
CvLgeneschrdf <- CvLgenesdf[grep("LG",CvLgenesdf$seqnames),]
head(CvLgeneschrdf)## seqnames start end width strand L area beta stat
## 1 LG19 10333007 10333692 686 * 71 16.559670 0.5767663 18.99209
## 3 LG13 22015858 22016352 495 * 82 14.226193 0.4397952 11.57442
## 6 LG8 18982718 18983377 660 * 60 7.212046 -0.3746378 -11.38354
## 7 LG11 14181818 14182182 365 * 58 4.745863 -0.3570840 -11.25378
## 8 LG14 4297874 4299069 1196 * 45 9.873079 -0.4990115 -10.64895
## 10 LG12 21371716 21372025 310 * 58 3.735525 -0.3274811 -10.48784
## pval qval index.start index.end index.width gene_id
## 1 9.999990e-07 0.1114369 8673138 8673208 71 ENSPREG00000002350
## 3 6.599993e-05 0.9103295 4374338 4374419 82 ENSPREG00000006590
## 6 7.399993e-05 0.9103295 17405986 17406045 60 ENSPREG00000011882
## 7 8.099992e-05 0.9103295 2836015 2836072 58 ENSPREG00000007449
## 8 1.209999e-04 0.9103295 4766186 4766230 45 ENSPREG00000009813
## 10 1.389999e-04 0.9103295 3729020 3729077 58 ENSPREG00000019970
## gene_biotype gene_name
## 1 protein_coding QRFPR
## 3 protein_coding ankrd13b
## 6 protein_coding rapgefl1
## 7 protein_coding <NA>
## 8 protein_coding rab34b
## 10 protein_coding <NA>rm(CvLgenes)
rm(CvLgenesdf)ol3 <- findOverlaps(dmrseqGvL,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, KK215360.1, KK215378.1, KK215387.1, KK215391.1, KK215393.1, KK215395.1, KK215396.1, KK215400.1, KK215401.1, KK215402.1, KK215405.1, KK215406.1, KK215407.1, KK215408.1, KK215411.1, KK215412.1, KK215415.1, KK215418.1, KK215420.1, KK215421.1, KK215424.1, KK215427.1, KK215430.1, KK215432.1, KK215433.1, KK215435.1, KK215439.1, KK215440.1, KK215441.1, KK215444.1, KK215446.1, KK215448.1, KK215451.1, KK215453.1, KK215455.1, KK215456.1, KK215459.1, KK215462.1, KK215463.1, KK215465.1, KK215466.1, KK215467.1, 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, KK215502.1, KK215503.1, KK215504.1, KK215506.1, KK215507.1, KK215508.1, KK215511.1, KK215513.1, KK215514.1, KK215515.1, KK215516.1, KK215517.1, KK215518.1, KK215519.1, KK215521.1, KK215523.1, KK215524.1, KK215525.1, KK215528.1, KK215529.1, KK215530.1, KK215531.1, KK215533.1, KK215538.1, KK215540.1, KK215541.1, KK215543.1, KK215544.1, KK215545.1, KK215546.1, KK215548.1, KK215549.1, KK215551.1, KK215553.1, KK215554.1, 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, KK215624.1, KK215625.1, KK215626.1, 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, KK215647.1, KK215649.1, KK215652.1, KK215654.1, KK215655.1, KK215657.1, KK215658.1, KK215661.1, KK215662.1, KK215663.1, KK215664.1, KK215668.1, KK215669.1, KK215670.1, KK215671.1, KK215672.1, KK215673.1, KK215675.1, KK215677.1, KK215678.1, KK215684.1, KK215688.1, KK215692.1, KK215695.1, KK215699.1, KK215700.1, KK215701.1, KK215703.1, KK215705.1, KK215706.1, KK215707.1, KK215709.1, KK215711.1, KK215712.1, KK215715.1, KK215719.1, KK215720.1, KK215721.1, KK215722.1, KK215724.1, KK215726.1, KK215727.1, KK215728.1, KK215733.1, KK215734.1, KK215736.1, KK215737.1, KK215738.1, KK215739.1, KK215743.1, KK215745.1, KK215748.1, KK215750.1, KK215753.1, KK215754.1, KK215755.1, KK215756.1, KK215757.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215767.1, KK215768.1, KK215769.1, KK215770.1, KK215771.1, KK215772.1, KK215775.1, KK215776.1, KK215777.1, KK215778.1, KK215782.1, KK215783.1, KK215786.1, KK215788.1, KK215789.1, KK215792.1, KK215797.1, KK215798.1, KK215802.1, KK215804.1, KK215807.1, KK215810.1, KK215812.1, KK215814.1, KK215816.1, KK215818.1, KK215821.1, KK215825.1, KK215834.1, KK215836.1, KK215839.1, KK215842.1, KK215843.1, KK215847.1, KK215849.1, KK215852.1, KK215857.1, KK215858.1, KK215859.1, KK215860.1, KK215864.1, KK215867.1, KK215870.1, KK215872.1, KK215873.1, KK215877.1, KK215881.1, KK215885.1, KK215886.1, KK215890.1, KK215891.1, KK215893.1, KK215894.1, KK215897.1, KK215902.1, KK215905.1, KK215907.1, KK215908.1, KK215909.1, KK215910.1, KK215911.1, KK215914.1, KK215915.1, KK215917.1, KK215918.1, KK215920.1, KK215921.1, KK215927.1, KK215928.1, KK215929.1, KK215934.1, KK215938.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215946.1, KK215949.1, KK215951.1, KK215952.1, KK215960.1, KK215965.1, KK215967.1, KK215969.1, KK215970.1, KK215972.1, KK215974.1, KK215975.1, KK215976.1, KK215977.1, KK215978.1, KK215979.1, KK215982.1, KK215983.1, KK215984.1, KK215987.1, KK215993.1, KK215995.1, KK215997.1, KK215999.1, KK216000.1, KK216012.1, KK216017.1, KK216021.1, KK216023.1, KK216029.1, KK216030.1, KK216033.1, KK216034.1, KK216035.1, KK216038.1, KK216039.1, KK216041.1, KK216044.1, KK216048.1, KK216050.1, KK216053.1, KK216056.1, KK216059.1, KK216063.1, KK216064.1, KK216067.1, KK216069.1, KK216072.1, KK216075.1, KK216076.1, KK216077.1, KK216079.1, KK216085.1, KK216086.1, KK216087.1, KK216089.1, KK216093.1, KK216094.1, KK216095.1, KK216099.1, KK216106.1, KK216109.1, KK216110.1, KK216114.1, KK216115.1, KK216120.1, KK216124.1, KK216128.1, KK216131.1, KK216134.1, KK216135.1, KK216140.1, KK216141.1, KK216142.1, KK216143.1, KK216150.1, KK216152.1, KK216157.1, KK216158.1, KK216162.1, KK216163.1, KK216165.1, KK216168.1, KK216169.1, KK216171.1, KK216174.1, KK216176.1, KK216177.1, KK216181.1, KK216184.1, KK216190.1, KK216192.1, KK216193.1, KK216194.1, KK216195.1, KK216197.1, KK216198.1, KK216201.1, KK216202.1, KK216203.1, KK216205.1, KK216212.1, KK216213.1, KK216214.1, KK216215.1, KK216217.1, KK216218.1, KK216219.1, KK216222.1, KK216225.1, KK216226.1, KK216227.1, KK216231.1, KK216234.1, KK216235.1, KK216236.1, KK216240.1, KK216241.1, KK216242.1, KK216245.1, KK216248.1, KK216253.1, KK216256.1, KK216258.1, KK216259.1, KK216261.1, KK216264.1, KK216265.1, KK216266.1, KK216267.1, KK216269.1, KK216273.1, KK216278.1, KK216282.1, KK216284.1, KK216285.1, KK216287.1, KK216289.1, KK216290.1, KK216291.1, KK216292.1, KK216293.1, KK216295.1, KK216303.1, KK216304.1, KK216306.1, KK216307.1, KK216310.1, KK216313.1, KK216315.1, KK216316.1, KK216317.1, KK216318.1, KK216319.1, KK216320.1, KK216323.1, KK216324.1, KK216325.1, KK216326.1, KK216329.1, KK216330.1, KK216331.1, KK216333.1, KK216336.1, KK216341.1, KK216342.1, KK216345.1, KK216351.1, KK216361.1, KK216363.1, KK216368.1, KK216369.1, KK216370.1, KK216374.1, KK216377.1, KK216383.1, KK216387.1, KK216388.1, KK216390.1, KK216391.1, KK216393.1, KK216394.1, KK216396.1, KK216400.1, KK216402.1, KK216403.1, KK216404.1, KK216410.1, KK216418.1, KK216420.1, KK216423.1, KK216427.1, KK216429.1, KK216430.1, KK216431.1, KK216437.1, KK216440.1, KK216442.1, KK216443.1, KK216447.1, KK216454.1, KK216456.1, KK216458.1, KK216462.1, KK216465.1, KK216467.1, KK216476.1, KK216478.1, KK216485.1, KK216486.1, KK216491.1, KK216492.1, KK216499.1, KK216500.1, KK216502.1, KK216506.1, KK216507.1, KK216508.1, KK216510.1, KK216511.1, KK216513.1, KK216515.1, KK216523.1, KK216526.1, KK216527.1, KK216530.1, KK216531.1, KK216534.1, KK216543.1, KK216552.1, KK216559.1, KK216566.1, KK216571.1, KK216574.1, KK216584.1, KK216596.1, KK216598.1, KK216602.1, KK216603.1, KK216606.1, KK216629.1, KK216630.1, KK216636.1, KK216638.1, KK216640.1, KK216643.1, KK216644.1, KK216648.1, KK216650.1, KK216652.1, KK216657.1, KK216661.1, KK216665.1, KK216668.1, KK216671.1, KK216674.1, KK216678.1, KK216679.1, KK216686.1, KK216688.1, KK216696.1, KK216697.1, KK216702.1, KK216717.1, KK216725.1, KK216728.1, KK216731.1, KK216732.1, KK216733.1, KK216745.1, KK216748.1, KK216767.1, KK216771.1, KK216774.1, KK216775.1, KK216782.1, KK216784.1, KK216795.1, KK216796.1, KK216804.1, KK216807.1, KK216811.1, KK216813.1, KK216814.1, KK216817.1, KK216823.1, KK216841.1, KK216848.1, KK216852.1, KK216859.1, KK216861.1, KK216866.1, KK216867.1, KK216870.1, KK216881.1, KK216882.1, KK216884.1, KK216892.1, KK216895.1, KK216896.1, KK216907.1, KK216908.1, KK216911.1, KK216912.1, KK216913.1, KK216914.1, KK216921.1, KK216929.1, KK216934.1, KK216935.1, KK216936.1, KK216942.1, KK216945.1, KK216946.1, KK216950.1, KK216954.1, KK216957.1, KK216959.1, KK216964.1, KK216965.1, KK216969.1, KK216971.1, KK216973.1, KK216977.1, KK216978.1, KK216980.1, KK216987.1, KK216988.1, KK216994.1, KK216995.1, KK216998.1, KK216999.1, KK217001.1, KK217003.1, KK217007.1, KK217008.1, KK217010.1, KK217011.1, KK217012.1, KK217016.1, KK217017.1, KK217019.1, KK217021.1, KK217032.1, KK217040.1, KK217049.1, KK217059.1, KK217063.1, KK217076.1, KK217077.1, KK217080.1, KK217083.1, KK217090.1, KK217091.1, KK217098.1, KK217100.1, KK217101.1, KK217104.1, KK217105.1, KK217111.1, KK217120.1, KK217123.1, KK217128.1, KK217133.1, KK217135.1, KK217147.1, KK217151.1, KK217161.1, KK217163.1, KK217174.1, KK217179.1, KK217182.1, KK217183.1, KK217186.1, KK217187.1, KK217189.1, KK217190.1, KK217193.1, KK217200.1, KK217203.1, KK217204.1, KK217206.1, KK217209.1, KK217228.1, KK217233.1, KK217237.1, KK217238.1, KK217241.1, KK217242.ol3## Hits object with 45925 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 1 14440
## [2] 2 21997
## [3] 2 21998
## [4] 5 891
## [5] 6 6028
## ... ... ...
## [45921] 91515 14451
## [45922] 91516 4865
## [45923] 91519 1058
## [45924] 91520 5503
## [45925] 91522 16070
## -------
## queryLength: 91524 / subjectLength: 23254GvLgenes <- dmrseqGvL[queryHits(ol3)]
mygenesol3 <- my_genes[subjectHits(ol3)]
head(mygenesol3)## GRanges object with 6 ranges and 3 metadata columns:
## seqnames ranges strand | gene_id gene_biotype
## <Rle> <IRanges> <Rle> | <character> <character>
## [1] LG11 28457673-28466140 + | ENSPREG00000010167 protein_coding
## [2] KK215283.1 1372895-1376892 - | ENSPREG00000019483 protein_coding
## [3] KK215283.1 1376883-1386241 + | ENSPREG00000019522 protein_coding
## [4] LG2 28489230-28494380 + | ENSPREG00000001027 protein_coding
## [5] LG13 18160798-18170662 - | ENSPREG00000001265 protein_coding
## [6] KK215287.1 939495-948585 - | ENSPREG00000007395 protein_coding
## gene_name
## <character>
## [1] ncdn
## [2] sco2
## [3] calua
## [4] casq2
## [5] <NA>
## [6] wdr74
## -------
## seqinfo: 463 sequences from an unspecified genome; no seqlengthsGvLgenesdf <- as.data.frame(GvLgenes,row.names = 1:nrow(as.data.frame(ranges(GvLgenes))))
head(GvLgenesdf)## seqnames start end width strand L area beta stat
## 1 LG11 28461237 28461741 505 * 108 11.636971 -0.2773737 -16.27500
## 2 KK215283.1 1376121 1376899 779 * 156 18.407129 0.3291269 15.23454
## 3 KK215283.1 1376121 1376899 779 * 156 18.407129 0.3291269 15.23454
## 4 LG2 28494008 28495445 1438 * 65 9.709663 0.4626823 12.85427
## 5 LG13 18160946 18161831 886 * 95 16.311864 -0.3970642 -12.75740
## 6 KK215287.1 944627 944828 202 * 36 4.299457 -0.4584372 -12.68316
## pval qval index.start index.end index.width
## 1 7.144039e-06 0.6538511 3678849 3678956 108
## 2 1.786010e-05 0.7492043 65611 65766 156
## 3 1.786010e-05 0.7492043 65611 65766 156
## 4 5.477097e-05 0.7492043 11413014 11413078 65
## 5 5.596164e-05 0.7492043 4929871 4929965 95
## 6 6.072433e-05 0.7492043 223719 223754 36mygenesoldf3 <- as.data.frame(mygenesol3,row.names = 1:nrow(as.data.frame(ranges(mygenesol3))))
head(mygenesoldf3)## seqnames start end width strand gene_id gene_biotype
## 1 LG11 28457673 28466140 8468 + ENSPREG00000010167 protein_coding
## 2 KK215283.1 1372895 1376892 3998 - ENSPREG00000019483 protein_coding
## 3 KK215283.1 1376883 1386241 9359 + ENSPREG00000019522 protein_coding
## 4 LG2 28489230 28494380 5151 + ENSPREG00000001027 protein_coding
## 5 LG13 18160798 18170662 9865 - ENSPREG00000001265 protein_coding
## 6 KK215287.1 939495 948585 9091 - ENSPREG00000007395 protein_coding
## gene_name
## 1 ncdn
## 2 sco2
## 3 calua
## 4 casq2
## 5 <NA>
## 6 wdr74GvLgenesdf <- cbind(GvLgenesdf,mygenesoldf3[c("gene_id","gene_biotype","gene_name")])
GvLgenesdf$seqnames <- as.character(GvLgenesdf$seqnames)
GvLgeneschrdf <- GvLgenesdf[grep("LG",GvLgenesdf$seqnames),]
head(GvLgeneschrdf)## seqnames start end width strand L area beta stat
## 1 LG11 28461237 28461741 505 * 108 11.636971 -0.2773737 -16.27500
## 4 LG2 28494008 28495445 1438 * 65 9.709663 0.4626823 12.85427
## 5 LG13 18160946 18161831 886 * 95 16.311864 -0.3970642 -12.75740
## 7 LG11 10041760 10042135 376 * 75 6.666626 0.3701602 12.64751
## 9 LG5 2971274 2971545 272 * 58 7.527239 -0.3990748 -12.02408
## 10 LG5 2971274 2971545 272 * 58 7.527239 -0.3990748 -12.02408
## pval qval index.start index.end index.width gene_id
## 1 7.144039e-06 0.6538511 3678849 3678956 108 ENSPREG00000010167
## 4 5.477097e-05 0.7492043 11413014 11413078 65 ENSPREG00000001027
## 5 5.596164e-05 0.7492043 4929871 4929965 95 ENSPREG00000001265
## 7 6.548703e-05 0.7492043 3123427 3123501 75 ENSPREG00000021580
## 9 9.287251e-05 0.7879743 16775120 16775177 58 ENSPREG00000022808
## 10 9.287251e-05 0.7879743 16775120 16775177 58 ENSPREG00000022867
## gene_biotype gene_name
## 1 protein_coding ncdn
## 4 protein_coding casq2
## 5 protein_coding <NA>
## 7 protein_coding jazf1a
## 9 protein_coding <NA>
## 10 protein_coding asb14arm(GvLgenes)
rm(GvLgenesdf)dmrs annotated to CpG islands
ol1 <- findOverlaps(dmrseqCvG,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, KK215370.1, KK215371.1, KK215372.1, KK215373.1, KK215378.1, KK215380.1, KK215381.1, KK215393.1, KK215396.1, KK215405.1, KK215406.1, KK215417.1, KK215421.1, KK215422.1, 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, KK215494.1, KK215497.1, KK215498.1, KK215501.1, KK215503.1, KK215504.1, KK215506.1, KK215508.1, KK215515.1, KK215519.1, KK215521.1, KK215523.1, KK215524.1, KK215525.1, KK215528.1, KK215531.1, KK215533.1, KK215536.1, KK215538.1, KK215541.1, KK215544.1, KK215545.1, KK215547.1, KK215548.1, KK215549.1, KK215551.1, KK215556.1, KK215559.1, KK215560.1, KK215565.1, KK215570.1, KK215572.1, KK215573.1, KK215574.1, KK215577.1, KK215580.1, KK215585.1, KK215591.1, KK215592.1, KK215593.1, KK215595.1, KK215598.1, KK215609.1, KK215614.1, KK215615.1, KK215620.1, KK215621.1, KK215623.1, KK215625.1, KK215626.1, KK215634.1, KK215635.1, KK215636.1, KK215637.1, KK215642.1, KK215643.1, KK215645.1, KK215647.1, KK215649.1, KK215651.1, KK215652.1, KK215654.1, KK215656.1, KK215657.1, KK215661.1, KK215662.1, KK215663.1, KK215665.1, KK215668.1, KK215671.1, KK215673.1, KK215675.1, KK215677.1, KK215681.1, KK215684.1, KK215687.1, KK215688.1, KK215691.1, KK215692.1, KK215695.1, KK215697.1, KK215698.1, KK215703.1, KK215705.1, KK215708.1, KK215710.1, KK215717.1, KK215720.1, KK215721.1, KK215724.1, KK215727.1, KK215728.1, KK215730.1, KK215734.1, KK215735.1, KK215736.1, KK215738.1, KK215741.1, KK215742.1, KK215743.1, KK215756.1, KK215757.1, KK215760.1, KK215761.1, KK215762.1, KK215763.1, KK215767.1, KK215770.1, KK215772.1, KK215775.1, KK215776.1, KK215777.1, KK215779.1, KK215780.1, KK215785.1, KK215786.1, KK215787.1, KK215789.1, KK215790.1, KK215794.1, KK215795.1, KK215798.1, KK215800.1, KK215802.1, KK215803.1, KK215804.1, KK215808.1, KK215809.1, KK215810.1, KK215813.1, KK215814.1, KK215815.1, KK215816.1, KK215824.1, KK215825.1, KK215827.1, KK215828.1, KK215834.1, KK215838.1, KK215843.1, KK215844.1, KK215849.1, KK215854.1, KK215856.1, KK215857.1, KK215858.1, KK215859.1, KK215861.1, KK215863.1, KK215864.1, KK215873.1, KK215875.1, KK215878.1, KK215880.1, KK215881.1, KK215885.1, KK215886.1, KK215887.1, KK215888.1, KK215890.1, KK215891.1, KK215895.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215909.1, KK215911.1, KK215914.1, KK215915.1, KK215918.1, KK215921.1, KK215923.1, KK215928.1, KK215934.1, KK215942.1, KK215943.1, KK215945.1, KK215947.1, KK215949.1, KK215951.1, KK215953.1, KK215956.1, KK215957.1, KK215960.1, KK215968.1, KK215969.1, KK215970.1, KK215973.1, KK215976.1, KK215979.1, KK215982.1, KK215983.1, KK215984.1, KK215987.1, KK215993.1, KK215994.1, KK215997.1, KK216000.1, KK216001.1, KK216012.1, KK216014.1, KK216015.1, KK216017.1, KK216018.1, 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, KK216044.1, KK216049.1, KK216053.1, KK216063.1, KK216064.1, KK216065.1, KK216066.1, KK216068.1, KK216069.1, KK216072.1, KK216075.1, KK216076.1, KK216079.1, KK216082.1, KK216084.1, KK216085.1, KK216086.1, KK216089.1, KK216093.1, KK216097.1, KK216100.1, KK216107.1, KK216114.1, KK216116.1, KK216120.1, KK216122.1, KK216124.1, KK216128.1, KK216130.1, KK216133.1, KK216134.1, KK216135.1, KK216136.1, KK216141.1, KK216142.1, KK216143.1, KK216147.1, KK216152.1, KK216155.1, KK216157.1, KK216158.1, KK216165.1, KK216166.1, KK216169.1, KK216171.1, KK216174.1, KK216184.1, KK216186.1, KK216190.1, KK216193.1, KK216194.1, KK216195.1, KK216197.1, KK216200.1, KK216208.1, KK216212.1, KK216215.1, KK216222.1, KK216225.1, KK216226.1, KK216227.1, KK216228.1, KK216230.1, KK216232.1, KK216237.1, KK216238.1, KK216240.1, KK216241.1, KK216244.1, KK216245.1, KK216251.1, KK216253.1, KK216254.1, KK216256.1, KK216259.1, KK216260.1, KK216261.1, KK216264.1, KK216266.1, KK216270.1, KK216278.1, KK216280.1, KK216281.1, KK216284.1, KK216287.1, KK216289.1, KK216290.1, KK216294.1, KK216295.1, KK216306.1, KK216310.1, KK216313.1, KK216320.1, KK216322.1, KK216324.1, KK216325.1, KK216329.1, KK216330.1, KK216336.1, KK216341.1, KK216342.1, KK216351.1, KK216352.1, KK216355.1, KK216359.1, KK216360.1, KK216363.1, KK216366.1, KK216370.1, KK216371.1, KK216377.1, KK216380.1, KK216383.1, KK216384.1, KK216389.1, KK216391.1, KK216394.1, KK216396.1, KK216402.1, KK216404.1, KK216405.1, KK216408.1, KK216410.1, KK216414.1, KK216418.1, KK216420.1, KK216422.1, KK216423.1, KK216425.1, KK216428.1, KK216432.1, KK216433.1, KK216438.1, KK216440.1, KK216442.1, KK216445.1, KK216451.1, KK216452.1, KK216453.1, KK216456.1, KK216457.1, KK216458.1, KK216459.1, KK216462.1, KK216468.1, KK216477.1, KK216479.1, KK216482.1, KK216492.1, KK216502.1, KK216504.1, KK216506.1, KK216508.1, KK216510.1, KK216511.1, KK216512.1, KK216513.1, KK216514.1, KK216515.1, KK216523.1, KK216526.1, KK216530.1, KK216531.1, KK216538.1, KK216548.1, KK216552.1, KK216553.1, KK216556.1, KK216569.1, KK216571.1, KK216572.1, KK216574.1, KK216576.1, KK216592.1, KK216599.1, KK216606.1, KK216607.1, KK216610.1, KK216615.1, KK216619.1, KK216640.1, KK216647.1, KK216651.1, KK216657.1, KK216661.1, KK216665.1, KK216672.1, KK216674.1, KK216678.1, KK216680.1, KK216685.1, KK216691.1, KK216699.1, KK216709.1, KK216712.1, KK216714.1, KK216716.1, KK216717.1, KK216725.1, KK216726.1, KK216732.1, KK216737.1, KK216740.1, KK216745.1, KK216746.1, KK216748.1, KK216752.1, KK216758.1, KK216763.1, KK216773.1, KK216779.1, KK216780.1, KK216782.1, KK216784.1, KK216792.1, KK216800.1, KK216814.1, KK216815.1, KK216817.1, KK216824.1, KK216830.1, KK216831.1, KK216834.1, KK216848.1, KK216852.1, KK216859.1, KK216861.1, KK216863.1, KK216865.1, KK216867.1, KK216870.1, KK216873.1, KK216879.1, KK216887.1, KK216896.1, KK216898.1, KK216899.1, KK216903.1, KK216905.1, KK216912.1, KK216913.1, KK216914.1, KK216921.1, KK216922.1, KK216923.1, KK216930.1, KK216931.1, KK216933.1, KK216934.1, KK216938.1, KK216942.1, KK216943.1, KK216945.1, KK216946.1, KK216950.1, KK216954.1, KK216957.1, KK216959.1, KK216963.1, KK216964.1, KK216965.1, KK216968.1, KK216971.1, KK216973.1, KK216974.1, KK216975.1, KK216980.1, KK216987.1, KK216988.1, KK216994.1, KK216999.1, KK217000.1, KK217001.1, KK217002.1, KK217003.1, KK217007.1, KK217012.1, KK217019.1, KK217028.1, KK217032.1, KK217037.1, KK217059.1, KK217060.1, KK217063.1, KK217065.1, KK217066.1, KK217072.1, KK217074.1, KK217076.1, KK217077.1, KK217079.1, KK217082.1, KK217083.1, KK217086.1, KK217088.1, KK217093.1, KK217098.1, KK217101.1, KK217103.1, KK217105.1, KK217112.1, KK217114.1, KK217119.1, KK217120.1, KK217121.1, KK217123.1, KK217126.1, KK217128.1, KK217130.1, KK217135.1, KK217140.1, KK217146.1, KK217147.1, KK217182.1, KK217185.1, KK217193.1, KK217195.1, KK217196.1, KK217203.1, KK217204.1, KK217206.1, KK217207.1, KK217214.1, KK217222.1, KK217227.1, KK217228.1, KK217233.1, KK217237.1, KK217240.1, KK217242.1, KK217244.1, KK217249.1, KK217255.1, KK217257.1, KK217263.1, KK217265.1, KK217279.1, KK217284.1, KK217289.1, KK217295.1, KK217303.1, KK217305.1, KK217313.1, KK217314.1, KK217320.1, KK217323.1, KK217324.1, KK217325.1, KK217331.1, KK217334.1, KK217343.1, KK217345.1, KK217346.1, KK217360.1, KK217363.1, KK217379.1, KK217382.1, KK217384.1, KK217385.1, KK217388.1, KK217389.1, KK217390.1, KK217396.1, KK217397.1, KK217398.1, KK217401.1, KK217402.1, KK217416.1, KK217423.1, KK217426.1, KK217431.1, KK217432.1, KK217437.1, KK217442.1, KK217445.1, KK217446.1, KK217449.1, KK217452.1, KK217461.1, KK217470.1, KK217471.1, KK217473.1, KK217475.1, KK217478.1, KK217479.1, KK217482.1, KK217484.1, KK217485.1, KK217486.1, KK217490.1, KK217499.1, KK217508.1, KK217510.1, KK217523.1, KK217528.1, KK217533.1, KK217537.1, KK217540.1, KK217548.1, KK217551.1, KK217554.1, KK217555.1, KK217558.1, KK217559.1, KK217567.1, KK217571.1, KK217572.1, KK217585.1, KK217586.1, KK217593.1, KK217596.1, KK217614.1, KK217616.1, KK217623.1, KK217630.1, KK217633.1, KK217635.ol1## Hits object with 6624 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 2 32069
## [2] 3 21175
## [3] 4 57357
## [4] 5 58973
## [5] 6 4736
## ... ... ...
## [6620] 110673 26710
## [6621] 110694 24046
## [6622] 110697 30955
## [6623] 110721 47416
## [6624] 110773 43887
## -------
## queryLength: 110780 / subjectLength: 60897CvGCpGislands <- dmrseqCvG[queryHits(ol1)]
my_CpGislandsol1 <- my_CpGislands[subjectHits(ol1)]
head(CvGCpGislands)## GRanges object with 6 ranges and 7 metadata columns:
## seqnames ranges strand | L area beta
## <Rle> <IRanges> <Rle> | <integer> <numeric> <numeric>
## [1] LG13 18160946-18161700 * | 75 17.10434 0.480479
## [2] LG8 27368425-27368499 * | 22 1.10760 -0.359863
## [3] KK215287.1 628700-629071 * | 42 2.46231 -0.357702
## [4] KK215308.1 92510-92874 * | 65 4.00345 -0.303095
## [5] LG2 18092802-18093635 * | 53 9.37373 -0.397850
## [6] LG5 2971274-2971545 * | 61 8.49567 0.378574
## stat pval qval index
## <numeric> <numeric> <numeric> <IRanges>
## [1] 12.3558 4.01337e-05 0.719377 4371608-4371682
## [2] -12.3461 4.11898e-05 0.719377 18010981-18011002
## [3] -12.2466 4.22460e-05 0.719377 186337-186378
## [4] -12.1655 4.43583e-05 0.719377 437886-437950
## [5] -12.0724 4.54144e-05 0.719377 9863892-9863944
## [6] 11.6533 6.44251e-05 0.719377 14903599-14903659
## -------
## seqinfo: 1181 sequences from an unspecified genome; no seqlengthsmy_CpGislandsol1## GRanges object with 6624 ranges and 2 metadata columns:
## seqnames ranges strand | source ID
## <Rle> <IRanges> <Rle> | <factor> <character>
## [1] LG13 18160935-18161432 + | cpgplot LG13.1141
## [2] LG8 27368282-27368834 + | cpgplot LG8.2475
## [3] KK215287.1 628647-628865 + | cpgplot KK215287.1.117
## [4] KK215308.1 92486-92833 + | cpgplot KK215308.1.25
## [5] LG2 18092818-18093060 + | cpgplot LG2.1904
## ... ... ... ... . ... ...
## [6620] LG11 7839037-7839328 + | cpgplot LG11.575
## [6621] LG10 4122858-4123057 + | cpgplot LG10.312
## [6622] LG13 647418-647839 + | cpgplot LG13.27
## [6623] LG19 23592736-23592941 + | cpgplot LG19.2566
## [6624] LG18 12011108-12011511 + | cpgplot LG18.1052
## -------
## 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': 6624 obs. of 14 variables:
## $ seqnames : Factor w/ 1181 levels "KK215283.1","KK215284.1",..: 1163 1180 5 26 1170 1177 1 1160 1163 316 ...
## $ start : int 18160946 27368425 628700 92510 18092802 2971274 934758 32171882 18052556 8328 ...
## $ end : int 18161700 27368499 629071 92874 18093635 2971545 935340 32172301 18054100 9236 ...
## $ width : int 755 75 372 365 834 272 583 420 1545 909 ...
## $ strand : Factor w/ 3 levels "+","-","*": 3 3 3 3 3 3 3 3 3 3 ...
## $ L : int 75 22 42 65 53 61 78 46 81 45 ...
## $ area : num 17.1 1.11 2.46 4 9.37 ...
## $ beta : num 0.48 -0.36 -0.358 -0.303 -0.398 ...
## $ stat : num 12.4 -12.3 -12.2 -12.2 -12.1 ...
## $ pval : num 4.01e-05 4.12e-05 4.22e-05 4.44e-05 4.54e-05 ...
## $ qval : num 0.719 0.719 0.719 0.719 0.719 ...
## $ index.start: int 4371608 18010981 186337 437886 9863892 14903599 37410 2481310 4367383 672143 ...
## $ index.end : int 4371682 18011002 186378 437950 9863944 14903659 37487 2481355 4367463 672187 ...
## $ index.width: int 75 22 42 65 53 61 78 46 81 45 ...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 LG13 18160935 18161432 498 + cpgplot LG13.1141
## 2 LG8 27368282 27368834 553 + cpgplot LG8.2475
## 3 KK215287.1 628647 628865 219 + cpgplot KK215287.1.117
## 4 KK215308.1 92486 92833 348 + cpgplot KK215308.1.25
## 5 LG2 18092818 18093060 243 + cpgplot LG2.1904
## 6 LG5 2971248 2971572 325 + cpgplot LG5.532CvGCpGislandsdf <- cbind(CvGCpGislandsdf,my_CpGislandsol1[c("source","ID")])
CvGCpGislandsdf$seqnames <- as.character(CvGCpGislandsdf$seqnames)
head(CvGCpGislandsdf)## seqnames start end width strand L area beta stat
## 1 LG13 18160946 18161700 755 * 75 17.104340 0.4804793 12.35578
## 2 LG8 27368425 27368499 75 * 22 1.107603 -0.3598625 -12.34614
## 3 KK215287.1 628700 629071 372 * 42 2.462310 -0.3577019 -12.24660
## 4 KK215308.1 92510 92874 365 * 65 4.003455 -0.3030945 -12.16552
## 5 LG2 18092802 18093635 834 * 53 9.373725 -0.3978501 -12.07243
## 6 LG5 2971274 2971545 272 * 61 8.495669 0.3785743 11.65333
## pval qval index.start index.end index.width source
## 1 4.013367e-05 0.7193775 4371608 4371682 75 cpgplot
## 2 4.118982e-05 0.7193775 18010981 18011002 22 cpgplot
## 3 4.224596e-05 0.7193775 186337 186378 42 cpgplot
## 4 4.435826e-05 0.7193775 437886 437950 65 cpgplot
## 5 4.541441e-05 0.7193775 9863892 9863944 53 cpgplot
## 6 6.442510e-05 0.7193775 14903599 14903659 61 cpgplot
## ID
## 1 LG13.1141
## 2 LG8.2475
## 3 KK215287.1.117
## 4 KK215308.1.25
## 5 LG2.1904
## 6 LG5.532CvGCpGislandschrdf <- CvGCpGislandsdf[grep("LG",CvGCpGislandsdf$seqnames),]
head(CvGCpGislandschrdf)## seqnames start end width strand L area beta stat
## 1 LG13 18160946 18161700 755 * 75 17.104340 0.4804793 12.35578
## 2 LG8 27368425 27368499 75 * 22 1.107603 -0.3598625 -12.34614
## 5 LG2 18092802 18093635 834 * 53 9.373725 -0.3978501 -12.07243
## 6 LG5 2971274 2971545 272 * 61 8.495669 0.3785743 11.65333
## 8 LG10 32171882 32172301 420 * 46 8.597024 0.4390605 11.17294
## 9 LG13 18052556 18054100 1545 * 81 10.961955 -0.3413481 -11.11704
## pval qval index.start index.end index.width source ID
## 1 4.013367e-05 0.7193775 4371608 4371682 75 cpgplot LG13.1141
## 2 4.118982e-05 0.7193775 18010981 18011002 22 cpgplot LG8.2475
## 5 4.541441e-05 0.7193775 9863892 9863944 53 cpgplot LG2.1904
## 6 6.442510e-05 0.7193775 14903599 14903659 61 cpgplot LG5.532
## 8 9.082882e-05 0.7193775 2481310 2481355 46 cpgplot LG10.2195
## 9 9.399727e-05 0.7193775 4367383 4367463 81 cpgplot LG13.1122CvGCpGislandschrdf <- CvGCpGislandschrdf[order(CvGCpGislandschrdf[,11]), ]
head(CvGCpGislandschrdf,10)## seqnames start end width strand L area beta stat
## 1 LG13 18160946 18161700 755 * 75 17.104340 0.4804793 12.35578
## 2 LG8 27368425 27368499 75 * 22 1.107603 -0.3598625 -12.34614
## 5 LG2 18092802 18093635 834 * 53 9.373725 -0.3978501 -12.07243
## 6 LG5 2971274 2971545 272 * 61 8.495669 0.3785743 11.65333
## 8 LG10 32171882 32172301 420 * 46 8.597024 0.4390605 11.17294
## 9 LG13 18052556 18054100 1545 * 81 10.961955 -0.3413481 -11.11704
## 11 LG19 10333007 10333692 686 * 70 10.588759 0.4116465 10.86281
## 12 LG19 8889655 8889899 245 * 47 2.420966 -0.2756728 -10.81171
## 14 LG20 10526898 10527306 409 * 61 5.646018 0.2998656 10.73088
## 15 LG11 10641658 10642177 520 * 56 6.750824 0.4028755 10.69685
## pval qval index.start index.end index.width source ID
## 1 4.013367e-05 0.7193775 4371608 4371682 75 cpgplot LG13.1141
## 2 4.118982e-05 0.7193775 18010981 18011002 22 cpgplot LG8.2475
## 5 4.541441e-05 0.7193775 9863892 9863944 53 cpgplot LG2.1904
## 6 6.442510e-05 0.7193775 14903599 14903659 61 cpgplot LG5.532
## 8 9.082882e-05 0.7193775 2481310 2481355 46 cpgplot LG10.2195
## 9 9.399727e-05 0.7193775 4367383 4367463 81 cpgplot LG13.1122
## 11 1.214571e-04 0.7193775 8864531 8864600 70 cpgplot LG19.1464
## 12 1.267379e-04 0.7193775 8825906 8825952 47 cpgplot LG19.1372
## 14 1.288502e-04 0.7193775 10806313 10806373 61 cpgplot LG20.800
## 15 1.320186e-04 0.7193775 2790037 2790092 56 cpgplot LG11.783rm(CvGCpGislands)
rm(CvGCpGislandsdf)ol1 <- findOverlaps(dmrseqCvL,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, KK215370.1, KK215371.1, KK215372.1, KK215373.1, KK215378.1, KK215381.1, KK215382.1, KK215393.1, KK215396.1, KK215404.1, KK215405.1, KK215406.1, KK215412.1, KK215414.1, KK215417.1, KK215420.1, KK215421.1, KK215422.1, KK215423.1, KK215430.1, KK215433.1, KK215435.1, KK215437.1, KK215438.1, 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, 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, KK215554.1, KK215556.1, KK215559.1, KK215560.1, KK215562.1, KK215565.1, KK215570.1, KK215573.1, KK215574.1, KK215577.1, KK215580.1, KK215582.1, KK215585.1, KK215591.1, KK215592.1, KK215593.1, KK215595.1, KK215598.1, KK215609.1, KK215612.1, KK215613.1, KK215615.1, KK215621.1, KK215625.1, KK215626.1, KK215634.1, KK215635.1, KK215636.1, KK215637.1, KK215638.1, KK215642.1, KK215643.1, KK215647.1, KK215649.1, KK215652.1, KK215654.1, KK215656.1, KK215657.1, KK215661.1, KK215662.1, KK215663.1, KK215665.1, KK215668.1, KK215671.1, KK215673.1, KK215675.1, KK215677.1, KK215681.1, KK215688.1, KK215691.1, KK215692.1, KK215698.1, KK215703.1, KK215705.1, KK215707.1, KK215708.1, KK215710.1, KK215712.1, KK215717.1, KK215720.1, KK215721.1, KK215723.1, KK215724.1, KK215727.1, KK215730.1, KK215731.1, KK215734.1, KK215735.1, KK215736.1, KK215738.1, KK215741.1, KK215742.1, KK215748.1, KK215756.1, KK215757.1, KK215758.1, KK215761.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215767.1, KK215770.1, KK215772.1, KK215775.1, KK215776.1, KK215777.1, KK215780.1, KK215785.1, KK215787.1, KK215789.1, KK215790.1, KK215794.1, KK215795.1, KK215798.1, KK215800.1, KK215802.1, KK215803.1, KK215804.1, KK215808.1, KK215809.1, KK215810.1, KK215813.1, KK215814.1, KK215816.1, KK215819.1, KK215824.1, KK215825.1, KK215827.1, KK215828.1, KK215834.1, KK215838.1, KK215839.1, KK215840.1, KK215842.1, KK215843.1, KK215844.1, KK215849.1, KK215856.1, KK215857.1, KK215860.1, KK215861.1, KK215863.1, KK215864.1, KK215870.1, KK215871.1, KK215875.1, KK215878.1, KK215879.1, KK215881.1, KK215885.1, KK215886.1, KK215887.1, KK215888.1, KK215891.1, KK215895.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215903.1, KK215908.1, KK215909.1, KK215911.1, KK215915.1, KK215918.1, KK215920.1, KK215921.1, KK215923.1, KK215927.1, KK215928.1, KK215934.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215949.1, KK215950.1, KK215951.1, KK215952.1, KK215953.1, KK215956.1, KK215957.1, KK215960.1, KK215969.1, KK215970.1, KK215971.1, KK215972.1, KK215973.1, KK215976.1, KK215978.1, KK215979.1, KK215983.1, KK215993.1, KK215997.1, KK216000.1, KK216001.1, KK216006.1, KK216012.1, KK216015.1, KK216017.1, KK216026.1, KK216030.1, KK216032.1, KK216037.1, KK216039.1, KK216040.1, KK216041.1, KK216044.1, KK216048.1, KK216049.1, KK216050.1, KK216053.1, KK216056.1, KK216059.1, KK216064.1, KK216065.1, KK216068.1, KK216069.1, KK216072.1, KK216075.1, KK216076.1, KK216079.1, KK216080.1, KK216082.1, KK216083.1, KK216084.1, KK216087.1, KK216092.1, KK216097.1, KK216101.1, KK216106.1, KK216107.1, KK216108.1, KK216110.1, KK216112.1, KK216114.1, KK216116.1, KK216128.1, KK216130.1, KK216131.1, KK216135.1, KK216136.1, KK216140.1, KK216141.1, KK216143.1, KK216146.1, KK216159.1, KK216161.1, KK216164.1, KK216165.1, KK216166.1, KK216168.1, KK216171.1, KK216174.1, KK216176.1, KK216181.1, KK216184.1, KK216190.1, KK216193.1, KK216194.1, KK216195.1, KK216197.1, KK216198.1, KK216200.1, KK216202.1, KK216206.1, KK216208.1, KK216212.1, KK216214.1, KK216215.1, KK216225.1, KK216226.1, KK216227.1, KK216228.1, KK216230.1, KK216231.1, KK216232.1, KK216234.1, KK216237.1, KK216241.1, KK216244.1, KK216245.1, KK216251.1, KK216253.1, KK216254.1, KK216256.1, KK216258.1, KK216259.1, KK216263.1, KK216264.1, KK216266.1, KK216267.1, KK216278.1, KK216280.1, KK216287.1, KK216288.1, KK216289.1, KK216290.1, KK216291.1, KK216292.1, KK216295.1, KK216304.1, KK216310.1, KK216317.1, KK216319.1, KK216320.1, KK216322.1, KK216324.1, KK216325.1, KK216329.1, KK216332.1, KK216341.1, KK216342.1, KK216345.1, KK216347.1, KK216351.1, KK216355.1, KK216359.1, KK216366.1, KK216369.1, KK216370.1, KK216379.1, KK216380.1, KK216384.1, KK216385.1, KK216387.1, KK216388.1, KK216389.1, KK216391.1, KK216393.1, KK216394.1, KK216396.1, KK216402.1, KK216403.1, KK216404.1, KK216405.1, KK216414.1, KK216418.1, KK216420.1, KK216422.1, KK216430.1, KK216431.1, KK216433.1, KK216437.1, KK216438.1, KK216440.1, KK216443.1, KK216452.1, KK216456.1, KK216457.1, KK216462.1, KK216467.1, KK216477.1, KK216479.1, KK216486.1, KK216491.1, KK216492.1, KK216503.1, KK216504.1, KK216506.1, KK216511.1, KK216512.1, KK216520.1, KK216523.1, KK216530.1, KK216534.1, KK216538.1, KK216556.1, KK216558.1, KK216570.1, KK216571.1, KK216572.1, KK216574.1, KK216586.1, KK216592.1, KK216595.1, KK216598.1, KK216604.1, KK216606.1, KK216609.1, KK216611.1, KK216615.1, KK216618.1, KK216622.1, KK216630.1, KK216641.1, KK216645.1, KK216646.1, KK216647.1, KK216649.1, KK216650.1, KK216652.1, KK216657.1, KK216661.1, KK216674.1, KK216685.1, KK216688.1, KK216697.1, KK216699.1, KK216704.1, KK216705.1, KK216707.1, KK216709.1, KK216710.1, KK216716.1, KK216717.1, KK216721.1, KK216723.1, KK216725.1, KK216726.1, KK216733.1, KK216737.1, KK216739.1, KK216740.1, KK216741.1, KK216746.1, KK216747.1, KK216748.1, KK216752.1, KK216761.1, KK216763.1, KK216764.1, KK216767.1, KK216780.1, KK216782.1, KK216784.1, KK216792.1, KK216796.1, KK216803.1, KK216807.1, KK216815.1, KK216817.1, KK216820.1, KK216830.1, KK216846.1, KK216847.1, KK216851.1, KK216852.1, KK216865.1, KK216867.1, KK216868.1, KK216870.1, KK216871.1, KK216879.1, KK216880.1, KK216884.1, KK216887.1, KK216891.1, KK216895.1, KK216902.1, KK216905.1, KK216908.1, KK216912.1, KK216914.1, KK216918.1, KK216921.1, KK216922.1, KK216930.1, KK216931.1, KK216932.1, KK216938.1, KK216945.1, KK216953.1, KK216957.1, KK216968.1, KK216969.1, KK216970.1, KK216971.1, KK216974.1, KK216978.1, KK216980.1, KK216989.1, KK216990.1, KK216994.1, KK216995.1, KK217000.1, KK217002.1, KK217007.1, KK217008.1, KK217012.1, KK217014.1, KK217016.1, KK217019.1, KK217023.1, KK217024.1, KK217026.1, KK217040.1, KK217049.1, KK217053.1, KK217059.1, KK217063.1, KK217064.1, KK217065.1, KK217066.1, KK217068.1, KK217073.1, KK217076.1, KK217079.1, KK217082.1, KK217083.1, KK217088.1, KK217093.1, KK217095.1, KK217098.1, KK217100.1, KK217103.1, KK217104.1, KK217105.1, KK217112.1, KK217114.1, KK217120.1, KK217123.1, KK217126.1, KK217128.1, KK217130.1, KK217132.1, KK217133.1, KK217135.1, KK217137.1, KK217139.1, KK217140.1, KK217149.1, KK217150.1, KK217154.1, KK217160.1, KK217169.1, KK217172.1, KK217174.1, KK217176.1, KK217182.1, KK217186.1, KK217187.1, KK217191.1, KK217193.1, KK217195.1, KK217203.1, KK217204.1, KK217206.1, KK217210.1, KK217215.1, KK217216.1, KK217224.1, KK217228.1, KK217229.1, KK217233.1, KK217237.1, KK217254.1, KK217257.1, KK217263.1, KK217265.1, KK217266.1, KK217272.1, KK217280.1, KK217284.1, KK217291.1, KK217295.1, KK217303.1, KK217311.1, KK217314.1, KK217322.1, KK217323.1, KK217324.1, KK217325.1, KK217328.1, KK217330.1, KK217331.1, KK217342.1, KK217346.1, KK217352.1, KK217353.1, KK217354.1, KK217359.1, KK217360.1, KK217363.1, KK217369.1, KK217373.1, KK217379.1, KK217384.1, KK217388.1, KK217389.1, KK217396.1, KK217397.1, KK217399.1, KK217414.1, KK217416.1, KK217419.1, KK217424.1, KK217431.1, KK217434.1, KK217438.1, KK217443.1, KK217444.1, KK217446.1, KK217447.1, KK217453.1, KK217457.1, KK217458.1, KK217470.1, KK217472.1, KK217474.1, KK217478.1, KK217479.1, KK217486.1, KK217495.1, KK217507.1, KK217510.1, KK217523.1, KK217531.1, KK217540.1, KK217547.1, KK217551.1, KK217555.1, KK217558.1, KK217562.1, KK217571.1, KK217572.1, KK217574.1, KK217582.1, KK217586.1, KK217588.1, KK217590.1, KK217591.ol1## Hits object with 6906 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 1 46314
## [2] 2 51389
## [3] 3 58239
## [4] 4 32335
## [5] 5 56687
## ... ... ...
## [6902] 111304 31864
## [6903] 111332 13232
## [6904] 111348 47105
## [6905] 111360 774
## [6906] 111427 40641
## -------
## queryLength: 111437 / subjectLength: 60897CvLCpGislands <- dmrseqCvL[queryHits(ol1)]
my_CpGislandsol1 <- my_CpGislands[subjectHits(ol1)]
head(CvLCpGislands)## GRanges object with 6 ranges and 7 metadata columns:
## seqnames ranges strand | L area beta
## <Rle> <IRanges> <Rle> | <integer> <numeric> <numeric>
## [1] LG19 10333007-10333692 * | 71 16.55967 0.576766
## [2] LG21 14273013-14273749 * | 81 14.61418 0.464748
## [3] KK215293.1 186354-186845 * | 61 5.16072 0.391140
## [4] LG13 22015858-22016352 * | 82 14.22619 0.439795
## [5] KK215283.1 1376211-1376895 * | 104 13.72310 0.361397
## [6] LG17 1251474-1251938 * | 61 12.56082 -0.401292
## stat pval qval index
## <numeric> <numeric> <numeric> <IRanges>
## [1] 18.9921 9.99999e-07 0.111437 8673138-8673208
## [2] 15.3892 7.99999e-06 0.445748 11372899-11372979
## [3] 12.1651 4.00000e-05 0.910330 296821-296881
## [4] 11.5744 6.59999e-05 0.910330 4374338-4374419
## [5] 11.5460 6.59999e-05 0.910330 56943-57046
## [6] -11.4403 7.09999e-05 0.910330 7069344-7069404
## -------
## seqinfo: 1180 sequences from an unspecified genome; no seqlengthsmy_CpGislandsol1## GRanges object with 6906 ranges and 2 metadata columns:
## seqnames ranges strand | source ID
## <Rle> <IRanges> <Rle> | <factor> <character>
## [1] LG19 10333012-10333278 + | cpgplot LG19.1464
## [2] LG21 14273253-14273572 + | cpgplot LG21.1424
## [3] KK215293.1 186168-186505 + | cpgplot KK215293.1.65
## [4] LG13 22015853-22016336 + | cpgplot LG13.1407
## [5] KK215283.1 1376061-1376879 + | cpgplot KK215283.1.456
## ... ... ... ... . ... ...
## [6902] LG13 16655249-16655453 + | cpgplot LG13.936
## [6903] LG5 20090853-20091191 + | cpgplot LG5.1504
## [6904] LG19 20458688-20458935 + | cpgplot LG19.2255
## [6905] LG1 9750075-9750417 + | cpgplot LG1.774
## [6906] LG17 1992096-1992367 + | cpgplot LG17.225
## -------
## 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': 6906 obs. of 14 variables:
## $ seqnames : Factor w/ 1180 levels "KK215283.1","KK215284.1",..: 1168 1171 11 1162 1 1166 1179 1160 1169 1169 ...
## $ start : int 10333007 14273013 186354 22015858 1376211 1251474 18982718 14181818 16355666 16355666 ...
## $ end : int 10333692 14273749 186845 22016352 1376895 1251938 18983377 14182182 16355981 16355981 ...
## $ width : int 686 737 492 495 685 465 660 365 316 316 ...
## $ strand : Factor w/ 3 levels "+","-","*": 3 3 3 3 3 3 3 3 3 3 ...
## $ L : int 71 81 61 82 104 61 60 58 76 76 ...
## $ area : num 16.56 14.61 5.16 14.23 13.72 ...
## $ beta : num 0.577 0.465 0.391 0.44 0.361 ...
## $ stat : num 19 15.4 12.2 11.6 11.5 ...
## $ pval : num 1.0e-06 8.0e-06 4.0e-05 6.6e-05 6.6e-05 ...
## $ qval : num 0.111 0.446 0.91 0.91 0.91 ...
## $ index.start: int 8673138 11372899 296821 4374338 56943 7069344 17405986 2836015 9599998 9599998 ...
## $ index.end : int 8673208 11372979 296881 4374419 57046 7069404 17406045 2836072 9600073 9600073 ...
## $ index.width: int 71 81 61 82 104 61 60 58 76 76 ...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 LG19 10333012 10333278 267 + cpgplot LG19.1464
## 2 LG21 14273253 14273572 320 + cpgplot LG21.1424
## 3 KK215293.1 186168 186505 338 + cpgplot KK215293.1.65
## 4 LG13 22015853 22016336 484 + cpgplot LG13.1407
## 5 KK215283.1 1376061 1376879 819 + cpgplot KK215283.1.456
## 6 LG17 1251463 1251798 336 + cpgplot LG17.120CvLCpGislandsdf <- cbind(CvLCpGislandsdf,my_CpGislandsol1[c("source","ID")])
CvLCpGislandsdf$seqnames <- as.character(CvLCpGislandsdf$seqnames)
head(CvLCpGislandsdf)## seqnames start end width strand L area beta stat
## 1 LG19 10333007 10333692 686 * 71 16.559670 0.5767663 18.99209
## 2 LG21 14273013 14273749 737 * 81 14.614182 0.4647484 15.38915
## 3 KK215293.1 186354 186845 492 * 61 5.160722 0.3911403 12.16515
## 4 LG13 22015858 22016352 495 * 82 14.226193 0.4397952 11.57442
## 5 KK215283.1 1376211 1376895 685 * 104 13.723096 0.3613973 11.54604
## 6 LG17 1251474 1251938 465 * 61 12.560822 -0.4012925 -11.44033
## pval qval index.start index.end index.width source
## 1 9.999990e-07 0.1114369 8673138 8673208 71 cpgplot
## 2 7.999992e-06 0.4457476 11372899 11372979 81 cpgplot
## 3 3.999996e-05 0.9103295 296821 296881 61 cpgplot
## 4 6.599993e-05 0.9103295 4374338 4374419 82 cpgplot
## 5 6.599993e-05 0.9103295 56943 57046 104 cpgplot
## 6 7.099993e-05 0.9103295 7069344 7069404 61 cpgplot
## ID
## 1 LG19.1464
## 2 LG21.1424
## 3 KK215293.1.65
## 4 LG13.1407
## 5 KK215283.1.456
## 6 LG17.120CvLCpGislandschrdf <- CvLCpGislandsdf[grep("LG",CvLCpGislandsdf$seqnames),]
head(CvLCpGislandschrdf)## seqnames start end width strand L area beta stat
## 1 LG19 10333007 10333692 686 * 71 16.559670 0.5767663 18.99209
## 2 LG21 14273013 14273749 737 * 81 14.614182 0.4647484 15.38915
## 4 LG13 22015858 22016352 495 * 82 14.226193 0.4397952 11.57442
## 6 LG17 1251474 1251938 465 * 61 12.560822 -0.4012925 -11.44033
## 7 LG8 18982718 18983377 660 * 60 7.212046 -0.3746378 -11.38354
## 8 LG11 14181818 14182182 365 * 58 4.745863 -0.3570840 -11.25378
## pval qval index.start index.end index.width source ID
## 1 9.999990e-07 0.1114369 8673138 8673208 71 cpgplot LG19.1464
## 2 7.999992e-06 0.4457476 11372899 11372979 81 cpgplot LG21.1424
## 4 6.599993e-05 0.9103295 4374338 4374419 82 cpgplot LG13.1407
## 6 7.099993e-05 0.9103295 7069344 7069404 61 cpgplot LG17.120
## 7 7.399993e-05 0.9103295 17405986 17406045 60 cpgplot LG8.1584
## 8 8.099992e-05 0.9103295 2836015 2836072 58 cpgplot LG11.1123CvLCpGislandschrdf <- CvLCpGislandschrdf[order(CvLCpGislandschrdf[,11]), ]
head(CvLCpGislandschrdf,10)## seqnames start end width strand L area beta stat
## 1 LG19 10333007 10333692 686 * 71 16.559670 0.5767663 18.99209
## 2 LG21 14273013 14273749 737 * 81 14.614182 0.4647484 15.38915
## 4 LG13 22015858 22016352 495 * 82 14.226193 0.4397952 11.57442
## 6 LG17 1251474 1251938 465 * 61 12.560822 -0.4012925 -11.44033
## 7 LG8 18982718 18983377 660 * 60 7.212046 -0.3746378 -11.38354
## 8 LG11 14181818 14182182 365 * 58 4.745863 -0.3570840 -11.25378
## 9 LG2 16355666 16355981 316 * 76 6.324347 0.3183476 10.87880
## 10 LG2 16355666 16355981 316 * 76 6.324347 0.3183476 10.87880
## 12 LG12 21371716 21372025 310 * 58 3.735525 -0.3274811 -10.48784
## 13 LG19 1188386 1188923 538 * 66 13.787455 -0.5147304 -10.45875
## pval qval index.start index.end index.width source ID
## 1 9.999990e-07 0.1114369 8673138 8673208 71 cpgplot LG19.1464
## 2 7.999992e-06 0.4457476 11372899 11372979 81 cpgplot LG21.1424
## 4 6.599993e-05 0.9103295 4374338 4374419 82 cpgplot LG13.1407
## 6 7.099993e-05 0.9103295 7069344 7069404 61 cpgplot LG17.120
## 7 7.399993e-05 0.9103295 17405986 17406045 60 cpgplot LG8.1584
## 8 8.099992e-05 0.9103295 2836015 2836072 58 cpgplot LG11.1123
## 9 1.009999e-04 0.9103295 9599998 9600073 76 cpgplot LG2.1704
## 10 1.009999e-04 0.9103295 9599998 9600073 76 cpgplot LG2.1705
## 12 1.389999e-04 0.9103295 3729020 3729077 58 cpgplot LG12.1498
## 13 1.399999e-04 0.9103295 8418295 8418360 66 cpgplot LG19.359rm(CvLCpGislands)
rm(CvLCpGislandsdf)ol1 <- findOverlaps(dmrseqGvL,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, KK215370.1, KK215371.1, KK215372.1, KK215373.1, KK215378.1, KK215380.1, KK215381.1, KK215393.1, KK215396.1, KK215402.1, KK215404.1, KK215405.1, KK215406.1, KK215412.1, KK215417.1, KK215420.1, KK215421.1, KK215422.1, KK215423.1, KK215430.1, KK215433.1, KK215435.1, KK215437.1, KK215438.1, KK215440.1, KK215442.1, KK215456.1, KK215458.1, KK215461.1, KK215462.1, KK215463.1, KK215465.1, KK215466.1, KK215467.1, KK215468.1, KK215474.1, KK215480.1, KK215482.1, KK215483.1, KK215484.1, KK215485.1, KK215486.1, KK215487.1, KK215493.1, KK215494.1, KK215497.1, KK215498.1, KK215503.1, KK215504.1, KK215506.1, KK215508.1, KK215515.1, KK215519.1, KK215521.1, KK215523.1, KK215524.1, KK215525.1, KK215528.1, KK215531.1, KK215533.1, KK215534.1, KK215536.1, KK215538.1, KK215541.1, KK215544.1, KK215545.1, KK215546.1, KK215548.1, KK215549.1, KK215551.1, KK215554.1, KK215557.1, KK215559.1, KK215560.1, KK215562.1, KK215565.1, 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, KK215615.1, KK215620.1, KK215621.1, 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, KK215668.1, KK215671.1, KK215673.1, KK215675.1, KK215677.1, KK215684.1, KK215687.1, KK215688.1, KK215692.1, KK215695.1, KK215697.1, KK215698.1, KK215703.1, KK215705.1, KK215707.1, KK215708.1, KK215712.1, KK215715.1, KK215720.1, KK215721.1, KK215724.1, KK215727.1, KK215728.1, KK215730.1, KK215731.1, KK215734.1, KK215735.1, KK215736.1, KK215738.1, KK215743.1, KK215748.1, KK215756.1, KK215757.1, KK215761.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215767.1, KK215770.1, KK215772.1, KK215775.1, KK215776.1, KK215777.1, KK215786.1, KK215787.1, KK215789.1, KK215790.1, KK215798.1, KK215800.1, KK215802.1, KK215804.1, KK215808.1, KK215809.1, KK215810.1, KK215814.1, KK215816.1, KK215818.1, KK215824.1, KK215825.1, KK215834.1, KK215839.1, KK215842.1, KK215843.1, KK215844.1, KK215847.1, KK215849.1, KK215852.1, KK215857.1, KK215858.1, KK215859.1, KK215860.1, KK215864.1, KK215867.1, KK215870.1, KK215873.1, KK215881.1, KK215885.1, KK215886.1, KK215888.1, KK215890.1, KK215891.1, KK215893.1, KK215895.1, KK215897.1, KK215902.1, KK215905.1, KK215906.1, KK215908.1, KK215909.1, KK215911.1, KK215914.1, KK215915.1, KK215916.1, KK215918.1, KK215920.1, KK215921.1, KK215927.1, KK215928.1, KK215934.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215947.1, KK215949.1, KK215951.1, KK215952.1, KK215960.1, KK215961.1, KK215968.1, KK215969.1, KK215970.1, KK215972.1, KK215975.1, KK215976.1, KK215978.1, KK215979.1, KK215982.1, KK215983.1, KK215984.1, KK215987.1, KK215993.1, KK215997.1, KK216000.1, KK216012.1, KK216017.1, KK216029.1, KK216030.1, KK216033.1, KK216034.1, KK216035.1, KK216039.1, KK216041.1, KK216044.1, KK216048.1, KK216050.1, KK216053.1, KK216056.1, KK216059.1, KK216063.1, KK216064.1, KK216069.1, KK216072.1, KK216075.1, KK216076.1, KK216077.1, KK216079.1, KK216085.1, KK216086.1, KK216087.1, KK216089.1, KK216092.1, KK216093.1, KK216100.1, KK216101.1, KK216106.1, KK216110.1, KK216114.1, KK216116.1, KK216120.1, KK216124.1, KK216128.1, KK216130.1, KK216131.1, KK216134.1, KK216135.1, KK216136.1, KK216140.1, KK216141.1, KK216142.1, KK216143.1, KK216147.1, KK216152.1, KK216157.1, KK216158.1, KK216163.1, KK216165.1, KK216168.1, KK216169.1, KK216171.1, KK216174.1, KK216176.1, KK216181.1, KK216184.1, KK216190.1, KK216193.1, KK216194.1, KK216195.1, KK216197.1, KK216198.1, KK216201.1, KK216202.1, KK216205.1, KK216212.1, KK216214.1, KK216215.1, KK216218.1, KK216222.1, KK216225.1, KK216226.1, KK216227.1, KK216228.1, KK216230.1, KK216231.1, KK216234.1, KK216240.1, KK216241.1, KK216242.1, KK216245.1, KK216248.1, KK216253.1, KK216256.1, KK216258.1, KK216259.1, KK216261.1, KK216264.1, KK216266.1, KK216267.1, KK216269.1, KK216277.1, KK216278.1, KK216284.1, KK216287.1, KK216289.1, KK216290.1, KK216291.1, KK216292.1, KK216294.1, KK216295.1, KK216304.1, KK216306.1, KK216307.1, KK216310.1, KK216313.1, KK216315.1, KK216317.1, KK216318.1, KK216319.1, KK216320.1, KK216324.1, KK216325.1, KK216329.1, KK216330.1, KK216332.1, KK216333.1, KK216336.1, KK216341.1, KK216342.1, KK216345.1, KK216351.1, KK216355.1, KK216361.1, KK216363.1, KK216369.1, KK216370.1, KK216374.1, KK216377.1, KK216380.1, KK216383.1, KK216387.1, KK216388.1, KK216390.1, KK216391.1, KK216393.1, KK216394.1, KK216396.1, KK216400.1, KK216402.1, KK216403.1, KK216404.1, KK216410.1, KK216418.1, KK216420.1, KK216423.1, KK216425.1, KK216427.1, KK216429.1, KK216430.1, KK216431.1, KK216437.1, KK216440.1, KK216442.1, KK216443.1, KK216454.1, KK216456.1, KK216458.1, KK216462.1, KK216465.1, KK216467.1, KK216476.1, KK216479.1, KK216486.1, KK216491.1, KK216492.1, KK216500.1, KK216502.1, KK216506.1, KK216508.1, KK216510.1, KK216511.1, KK216513.1, KK216515.1, KK216523.1, KK216526.1, KK216527.1, KK216530.1, KK216531.1, KK216534.1, KK216543.1, KK216551.1, KK216552.1, KK216559.1, KK216566.1, KK216571.1, KK216574.1, KK216584.1, KK216587.1, KK216596.1, KK216597.1, KK216598.1, KK216602.1, KK216603.1, KK216606.1, KK216619.1, KK216629.1, KK216630.1, KK216640.1, KK216643.1, KK216644.1, KK216650.1, KK216652.1, KK216657.1, KK216661.1, KK216665.1, KK216668.1, KK216671.1, KK216674.1, KK216678.1, KK216679.1, KK216686.1, KK216688.1, KK216697.1, KK216702.1, KK216717.1, KK216725.1, KK216728.1, KK216731.1, KK216732.1, KK216733.1, KK216739.1, KK216745.1, KK216748.1, KK216767.1, KK216771.1, KK216774.1, KK216775.1, KK216782.1, KK216784.1, KK216795.1, KK216796.1, KK216807.1, KK216813.1, KK216814.1, KK216817.1, KK216823.1, KK216848.1, KK216852.1, KK216859.1, KK216861.1, KK216866.1, KK216867.1, KK216870.1, KK216882.1, KK216884.1, KK216895.1, KK216896.1, KK216907.1, KK216908.1, KK216911.1, KK216912.1, KK216913.1, KK216914.1, KK216921.1, KK216929.1, KK216934.1, KK216935.1, KK216936.1, KK216942.1, KK216945.1, KK216946.1, KK216950.1, KK216954.1, KK216957.1, KK216959.1, KK216964.1, KK216965.1, KK216969.1, KK216971.1, KK216973.1, KK216977.1, KK216978.1, KK216980.1, KK216987.1, KK216988.1, KK216994.1, KK216995.1, KK216998.1, KK216999.1, KK217001.1, KK217003.1, KK217007.1, KK217008.1, KK217010.1, KK217011.1, KK217012.1, KK217016.1, KK217017.1, KK217019.1, KK217021.1, KK217028.1, KK217032.1, KK217040.1, KK217045.1, KK217049.1, KK217059.1, KK217060.1, KK217063.1, KK217076.1, KK217077.1, KK217080.1, KK217083.1, KK217090.1, KK217091.1, KK217098.1, KK217100.1, KK217101.1, KK217104.1, KK217105.1, KK217120.1, KK217123.1, KK217128.1, KK217133.1, KK217135.1, KK217147.1, KK217151.1, KK217161.1, KK217163.1, KK217174.1, KK217179.1, KK217182.1, KK217186.1, KK217187.1, KK217193.1, KK217200.1, KK217203.1, KK217204.1, KK217206.1, KK217209.1, KK217223.1, KK217228.1, KK217233.1, KK217237.1, KK217238.1, KK217241.1, KK217242.1, KK217263.1, KK217265.1, KK217274.1, KK217276.1, KK217278.1, KK217280.1, KK217294.1, KK217295.1, KK217301.1, KK217303.1, KK217305.1, KK217313.1, KK217314.1, KK217323.1, KK217325.1, KK217345.1, KK217346.1, KK217347.1, KK217352.1, KK217360.1, KK217367.1, KK217369.1, KK217372.1, KK217375.1, KK217381.1, KK217382.1, KK217395.1, KK217402.1, KK217406.1, KK217409.1, KK217414.1, KK217417.1, KK217419.1, KK217420.1, KK217422.1, KK217424.1, KK217427.1, KK217431.1, KK217437.1, KK217442.1, KK217444.1, KK217445.1, KK217446.1, KK217447.1, KK217452.1, KK217461.1, KK217462.1, KK217470.1, KK217474.1, KK217475.1, KK217481.1, KK217484.1, KK217485.1, KK217490.1, KK217492.1, KK217497.1, KK217499.1, KK217531.1, KK217532.1, KK217534.1, KK217538.1, KK217540.1, KK217541.1, KK217545.1, KK217551.1, KK217559.1, KK217562.1, KK217571.1, KK217574.1, KK217582.1, KK217584.1, KK217585.1, KK217588.1, KK217591.1, KK217596.1, KK217598.1, KK217602.1, KK217607.1, KK217610.1, KK217612.1, KK217613.1, KK217618.1, KK217619.1, KK217625.1, KK217630.1, KK217632.1, KK217635.1, KK217638.1, KK217640.1, KK217644.1, KK217651.1, KK217652.1, KK217656.ol1## Hits object with 5133 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 1 28631
## [2] 2 56687
## [3] 3 48988
## [4] 4 1612
## [5] 6 32069
## ... ... ...
## [5129] 91454 41415
## [5130] 91465 20788
## [5131] 91489 38403
## [5132] 91494 47546
## [5133] 91515 28729
## -------
## queryLength: 91524 / subjectLength: 60897GvLCpGislands <- dmrseqGvL[queryHits(ol1)]
my_CpGislandsol1 <- my_CpGislands[subjectHits(ol1)]
head(GvLCpGislands)## GRanges object with 6 ranges and 7 metadata columns:
## seqnames ranges strand | L area beta
## <Rle> <IRanges> <Rle> | <integer> <numeric> <numeric>
## [1] LG11 28461237-28461741 * | 108 11.63697 -0.277374
## [2] KK215283.1 1376121-1376899 * | 156 18.40713 0.329127
## [3] LG20 17269425-17270374 * | 73 10.41376 0.475571
## [4] LG1 22240537-22241922 * | 78 8.68085 0.351599
## [5] LG13 18160946-18161831 * | 95 16.31186 -0.397064
## [6] KK215287.1 944627-944828 * | 36 4.29946 -0.458437
## stat pval qval index
## <numeric> <numeric> <numeric> <IRanges>
## [1] -16.2750 7.14404e-06 0.653851 3678849-3678956
## [2] 15.2345 1.78601e-05 0.749204 65611-65766
## [3] 14.5876 2.50041e-05 0.749204 12375529-12375601
## [4] 13.2709 4.64363e-05 0.749204 1550715-1550792
## [5] -12.7574 5.59616e-05 0.749204 4929871-4929965
## [6] -12.6832 6.07243e-05 0.749204 223719-223754
## -------
## seqinfo: 1169 sequences from an unspecified genome; no seqlengthsmy_CpGislandsol1## GRanges object with 5133 ranges and 2 metadata columns:
## seqnames ranges strand | source ID
## <Rle> <IRanges> <Rle> | <factor> <character>
## [1] LG11 28461223-28461750 + | cpgplot LG11.2496
## [2] KK215283.1 1376061-1376879 + | cpgplot KK215283.1.456
## [3] LG20 17270266-17270490 + | cpgplot LG20.1278
## [4] LG1 22240830-22241036 + | cpgplot LG1.1612
## [5] LG13 18160935-18161432 + | cpgplot LG13.1141
## ... ... ... ... . ... ...
## [5129] LG17 11272216-11272425 + | cpgplot LG17.999
## [5130] LG8 23526042-23526320 + | cpgplot LG8.2088
## [5131] LG16 2070386-2070612 + | cpgplot LG16.501
## [5132] LG19 25355604-25355803 + | cpgplot LG19.2696
## [5133] LG11 28762243-28763456 + | cpgplot LG11.2594
## -------
## seqinfo: 646 sequences from an unspecified genome; no seqlengthsGvLCpGislandsdf <- as.data.frame(GvLCpGislands,row.names = 1:nrow(as.data.frame(ranges(GvLCpGislands))))
str(GvLCpGislands)## Formal class 'GRanges' [package "GenomicRanges"] with 7 slots
## ..@ seqnames :Formal class 'Rle' [package "S4Vectors"] with 4 slots
## .. .. ..@ values : Factor w/ 1169 levels "KK215283.1","KK215284.1",..: 1149 1 1159 1147 1151 5 1149 24 1165 1154 ...
## .. .. ..@ lengths : int [1:4810] 1 1 1 1 1 1 1 1 1 1 ...
## .. .. ..@ elementMetadata: NULL
## .. .. ..@ metadata : list()
## ..@ ranges :Formal class 'IRanges' [package "IRanges"] with 6 slots
## .. .. ..@ start : int [1:5133] 28461237 1376121 17269425 22240537 18160946 944627 10041760 101373 2971274 508971 ...
## .. .. ..@ width : int [1:5133] 505 779 950 1386 886 202 376 715 272 981 ...
## .. .. ..@ NAMES : NULL
## .. .. ..@ elementType : chr "ANY"
## .. .. ..@ elementMetadata: NULL
## .. .. ..@ metadata : list()
## ..@ strand :Formal class 'Rle' [package "S4Vectors"] with 4 slots
## .. .. ..@ values : Factor w/ 3 levels "+","-","*": 3
## .. .. ..@ lengths : int 5133
## .. .. ..@ elementMetadata: NULL
## .. .. ..@ metadata : list()
## ..@ seqinfo :Formal class 'Seqinfo' [package "GenomeInfoDb"] with 4 slots
## .. .. ..@ seqnames : chr [1:1169] "KK215283.1" "KK215284.1" "KK215285.1" "KK215286.1" ...
## .. .. ..@ seqlengths : int [1:1169] NA NA NA NA NA NA NA NA NA NA ...
## .. .. ..@ is_circular: logi [1:1169] NA NA NA NA NA NA ...
## .. .. ..@ genome : chr [1:1169] NA NA NA NA ...
## ..@ elementMetadata:Formal class 'DFrame' [package "S4Vectors"] with 6 slots
## .. .. ..@ rownames : NULL
## .. .. ..@ nrows : int 5133
## .. .. ..@ listData :List of 7
## .. .. .. ..$ L : int [1:5133] 108 156 73 78 95 36 75 68 58 88 ...
## .. .. .. ..$ area : num [1:5133] 11.64 18.41 10.41 8.68 16.31 ...
## .. .. .. ..$ beta : num [1:5133] -0.277 0.329 0.476 0.352 -0.397 ...
## .. .. .. ..$ stat : num [1:5133] -16.3 15.2 14.6 13.3 -12.8 ...
## .. .. .. ..$ pval : num [1:5133] 7.14e-06 1.79e-05 2.50e-05 4.64e-05 5.60e-05 ...
## .. .. .. ..$ qval : num [1:5133] 0.654 0.749 0.749 0.749 0.749 ...
## .. .. .. ..$ index:Formal class 'IRanges' [package "IRanges"] with 6 slots
## .. .. .. .. .. ..@ start : int [1:5133] 3678849 65611 12375529 1550715 4929871 223719 3123427 479142 16775120 7140119 ...
## .. .. .. .. .. ..@ width : int [1:5133] 108 156 73 78 95 36 75 68 58 88 ...
## .. .. .. .. .. ..@ NAMES : NULL
## .. .. .. .. .. ..@ elementType : chr "ANY"
## .. .. .. .. .. ..@ elementMetadata: NULL
## .. .. .. .. .. ..@ metadata : list()
## .. .. ..@ elementType : chr "ANY"
## .. .. ..@ elementMetadata: NULL
## .. .. ..@ metadata : list()
## ..@ elementType : chr "ANY"
## ..@ metadata : list()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 LG11 28461223 28461750 528 + cpgplot LG11.2496
## 2 KK215283.1 1376061 1376879 819 + cpgplot KK215283.1.456
## 3 LG20 17270266 17270490 225 + cpgplot LG20.1278
## 4 LG1 22240830 22241036 207 + cpgplot LG1.1612
## 5 LG13 18160935 18161432 498 + cpgplot LG13.1141
## 6 KK215287.1 944612 944830 219 + cpgplot KK215287.1.200GvLCpGislandsdf <- cbind(GvLCpGislandsdf,my_CpGislandsol1[c("source","ID")])
GvLCpGislandsdf$seqnames <- as.character(GvLCpGislandsdf$seqnames)
head(GvLCpGislandsdf)## seqnames start end width strand L area beta stat
## 1 LG11 28461237 28461741 505 * 108 11.636971 -0.2773737 -16.27500
## 2 KK215283.1 1376121 1376899 779 * 156 18.407129 0.3291269 15.23454
## 3 LG20 17269425 17270374 950 * 73 10.413759 0.4755714 14.58765
## 4 LG1 22240537 22241922 1386 * 78 8.680847 0.3515985 13.27092
## 5 LG13 18160946 18161831 886 * 95 16.311864 -0.3970642 -12.75740
## 6 KK215287.1 944627 944828 202 * 36 4.299457 -0.4584372 -12.68316
## pval qval index.start index.end index.width source
## 1 7.144039e-06 0.6538511 3678849 3678956 108 cpgplot
## 2 1.786010e-05 0.7492043 65611 65766 156 cpgplot
## 3 2.500414e-05 0.7492043 12375529 12375601 73 cpgplot
## 4 4.643626e-05 0.7492043 1550715 1550792 78 cpgplot
## 5 5.596164e-05 0.7492043 4929871 4929965 95 cpgplot
## 6 6.072433e-05 0.7492043 223719 223754 36 cpgplot
## ID
## 1 LG11.2496
## 2 KK215283.1.456
## 3 LG20.1278
## 4 LG1.1612
## 5 LG13.1141
## 6 KK215287.1.200GvLCpGislandschrdf <- GvLCpGislandsdf[grep("LG",GvLCpGislandsdf$seqnames),]
head(GvLCpGislandschrdf)## seqnames start end width strand L area beta stat
## 1 LG11 28461237 28461741 505 * 108 11.636971 -0.2773737 -16.27500
## 3 LG20 17269425 17270374 950 * 73 10.413759 0.4755714 14.58765
## 4 LG1 22240537 22241922 1386 * 78 8.680847 0.3515985 13.27092
## 5 LG13 18160946 18161831 886 * 95 16.311864 -0.3970642 -12.75740
## 7 LG11 10041760 10042135 376 * 75 6.666626 0.3701602 12.64751
## 9 LG5 2971274 2971545 272 * 58 7.527239 -0.3990748 -12.02408
## pval qval index.start index.end index.width source ID
## 1 7.144039e-06 0.6538511 3678849 3678956 108 cpgplot LG11.2496
## 3 2.500414e-05 0.7492043 12375529 12375601 73 cpgplot LG20.1278
## 4 4.643626e-05 0.7492043 1550715 1550792 78 cpgplot LG1.1612
## 5 5.596164e-05 0.7492043 4929871 4929965 95 cpgplot LG13.1141
## 7 6.548703e-05 0.7492043 3123427 3123501 75 cpgplot LG11.699
## 9 9.287251e-05 0.7879743 16775120 16775177 58 cpgplot LG5.532GvLCpGislandschrdf <- GvLCpGislandschrdf[order(GvLCpGislandschrdf[,11]), ]
head(GvLCpGislandschrdf,10)## seqnames start end width strand L area beta stat
## 1 LG11 28461237 28461741 505 * 108 11.636971 -0.2773737 -16.27500
## 3 LG20 17269425 17270374 950 * 73 10.413759 0.4755714 14.58765
## 4 LG1 22240537 22241922 1386 * 78 8.680847 0.3515985 13.27092
## 5 LG13 18160946 18161831 886 * 95 16.311864 -0.3970642 -12.75740
## 7 LG11 10041760 10042135 376 * 75 6.666626 0.3701602 12.64751
## 9 LG5 2971274 2971545 272 * 58 7.527239 -0.3990748 -12.02408
## 10 LG16 508971 509951 981 * 88 14.089129 -0.3991232 -11.83323
## 12 LG17 4434405 4435108 704 * 67 10.629923 -0.4174846 -11.47364
## 13 LG5 19662076 19662488 413 * 46 3.595347 0.3130988 11.43112
## 14 LG3 31400775 31402677 1903 * 73 10.270659 0.3407376 11.36557
## pval qval index.start index.end index.width source ID
## 1 7.144039e-06 0.6538511 3678849 3678956 108 cpgplot LG11.2496
## 3 2.500414e-05 0.7492043 12375529 12375601 73 cpgplot LG20.1278
## 4 4.643626e-05 0.7492043 1550715 1550792 78 cpgplot LG1.1612
## 5 5.596164e-05 0.7492043 4929871 4929965 95 cpgplot LG13.1141
## 7 6.548703e-05 0.7492043 3123427 3123501 75 cpgplot LG11.699
## 9 9.287251e-05 0.7879743 16775120 16775177 58 cpgplot LG5.532
## 10 1.059699e-04 0.7879743 7140119 7140206 88 cpgplot LG16.165
## 12 1.357367e-04 0.7879743 8251105 8251171 67 cpgplot LG17.545
## 13 1.357367e-04 0.7879743 17222347 17222392 46 cpgplot LG5.1484
## 14 1.464528e-04 0.7879743 15649137 15649209 73 cpgplot LG3.1584rm(GvLCpGislands)
rm(GvLCpGislandsdf)dmrs annotated to promoter regions
ol1 <- findOverlaps(dmrseqCvG,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, KK215360.1, KK215378.1, KK215383.1, KK215387.1, KK215391.1, KK215393.1, KK215395.1, KK215396.1, KK215400.1, KK215401.1, KK215405.1, KK215406.1, KK215407.1, KK215408.1, KK215411.1, KK215415.1, KK215418.1, KK215421.1, KK215424.1, 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, KK215513.1, KK215514.1, KK215515.1, KK215516.1, KK215517.1, KK215518.1, KK215519.1, KK215521.1, KK215523.1, KK215524.1, KK215525.1, KK215528.1, KK215529.1, KK215530.1, KK215531.1, KK215533.1, KK215538.1, KK215540.1, KK215541.1, KK215543.1, KK215544.1, KK215545.1, KK215547.1, KK215548.1, KK215549.1, KK215551.1, KK215556.1, KK215558.1, KK215559.1, KK215560.1, KK215561.1, KK215567.1, KK215568.1, KK215573.1, KK215574.1, KK215577.1, KK215578.1, KK215581.1, KK215583.1, KK215585.1, KK215586.1, KK215587.1, KK215588.1, KK215589.1, KK215590.1, KK215594.1, KK215595.1, KK215597.1, KK215598.1, KK215601.1, KK215605.1, KK215606.1, KK215608.1, KK215615.1, KK215616.1, KK215620.1, KK215621.1, KK215624.1, KK215625.1, KK215626.1, KK215627.1, KK215628.1, KK215629.1, KK215630.1, KK215633.1, KK215634.1, KK215635.1, KK215636.1, KK215637.1, KK215639.1, KK215641.1, KK215642.1, 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, KK215683.1, KK215684.1, KK215688.1, KK215692.1, KK215695.1, KK215700.1, KK215701.1, KK215703.1, KK215704.1, KK215705.1, KK215706.1, KK215709.1, KK215710.1, KK215711.1, KK215719.1, KK215720.1, KK215721.1, KK215722.1, KK215724.1, KK215726.1, KK215727.1, KK215728.1, KK215733.1, KK215734.1, KK215736.1, KK215737.1, KK215738.1, KK215739.1, KK215741.1, KK215742.1, KK215743.1, KK215745.1, KK215750.1, KK215752.1, KK215753.1, KK215754.1, KK215755.1, KK215756.1, KK215757.1, KK215762.1, KK215763.1, KK215767.1, KK215768.1, KK215769.1, KK215770.1, KK215772.1, 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, KK215797.1, KK215798.1, KK215802.1, KK215804.1, KK215807.1, KK215810.1, KK215812.1, KK215814.1, KK215815.1, KK215816.1, KK215821.1, KK215825.1, KK215827.1, KK215832.1, KK215834.1, KK215836.1, KK215837.1, KK215838.1, KK215843.1, KK215848.1, KK215849.1, KK215854.1, KK215857.1, KK215858.1, KK215859.1, KK215861.1, KK215863.1, KK215864.1, KK215872.1, KK215873.1, KK215875.1, KK215877.1, KK215878.1, KK215880.1, KK215881.1, KK215882.1, KK215885.1, KK215886.1, KK215890.1, KK215891.1, KK215894.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215907.1, KK215909.1, KK215910.1, KK215911.1, KK215914.1, KK215915.1, KK215918.1, KK215921.1, KK215922.1, KK215923.1, KK215928.1, KK215929.1, KK215934.1, KK215935.1, KK215937.1, KK215942.1, KK215943.1, KK215945.1, KK215946.1, KK215949.1, KK215951.1, KK215953.1, KK215956.1, KK215957.1, KK215960.1, KK215962.1, KK215965.1, KK215967.1, KK215969.1, KK215970.1, KK215973.1, KK215974.1, KK215976.1, KK215977.1, KK215979.1, KK215982.1, KK215983.1, KK215984.1, KK215987.1, KK215990.1, KK215993.1, KK215994.1, KK215997.1, KK215999.1, KK216000.1, KK216001.1, KK216012.1, KK216015.1, KK216017.1, KK216018.1, KK216021.1, KK216023.1, KK216025.1, KK216026.1, KK216028.1, KK216029.1, KK216030.1, KK216032.1, KK216033.1, KK216034.1, KK216035.1, KK216037.1, KK216038.1, KK216039.1, KK216040.1, KK216041.1, KK216044.1, KK216049.1, KK216053.1, 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, KK216079.1, KK216082.1, KK216084.1, KK216085.1, KK216086.1, KK216089.1, KK216093.1, KK216094.1, KK216097.1, KK216099.1, KK216102.1, KK216103.1, KK216109.1, KK216111.1, KK216114.1, KK216118.1, KK216120.1, KK216122.1, KK216124.1, KK216128.1, KK216133.1, KK216134.1, KK216135.1, KK216141.1, KK216142.1, KK216143.1, KK216150.1, KK216152.1, KK216155.1, KK216157.1, KK216158.1, KK216165.1, KK216166.1, KK216169.1, KK216171.1, KK216172.1, KK216173.1, KK216174.1, KK216175.1, KK216177.1, KK216180.1, KK216184.1, KK216186.1, KK216190.1, KK216193.1, KK216194.1, KK216195.1, KK216197.1, KK216200.1, KK216203.1, KK216208.1, KK216212.1, KK216213.1, KK216215.1, KK216219.1, KK216222.1, KK216225.1, KK216226.1, KK216227.1, KK216229.1, KK216232.1, KK216236.1, KK216237.1, KK216238.1, KK216240.1, KK216241.1, KK216244.1, KK216245.1, KK216251.1, KK216253.1, KK216254.1, KK216256.1, KK216259.1, KK216260.1, KK216261.1, KK216264.1, KK216266.1, KK216270.1, KK216273.1, KK216275.1, KK216278.1, KK216280.1, KK216281.1, KK216282.1, KK216284.1, KK216285.1, KK216287.1, KK216289.1, KK216290.1, KK216295.1, KK216303.1, KK216306.1, KK216310.1, KK216313.1, KK216320.1, KK216322.1, KK216323.1, KK216324.1, KK216325.1, KK216326.1, KK216329.1, KK216330.1, KK216331.1, KK216334.1, KK216336.1, KK216341.1, KK216342.1, KK216351.1, KK216359.1, KK216360.1, KK216363.1, KK216364.1, KK216366.1, KK216368.1, KK216370.1, KK216371.1, KK216377.1, KK216383.1, KK216384.1, KK216389.1, KK216391.1, KK216394.1, KK216396.1, KK216402.1, KK216404.1, KK216405.1, KK216408.1, KK216410.1, KK216414.1, KK216418.1, KK216420.1, KK216422.1, KK216423.1, KK216428.1, KK216432.1, KK216433.1, KK216436.1, KK216438.1, KK216440.1, KK216442.1, KK216445.1, KK216447.1, KK216451.1, KK216452.1, KK216453.1, KK216456.1, KK216457.1, KK216458.1, KK216462.1, KK216468.1, KK216477.1, KK216482.1, KK216492.1, KK216502.1, KK216504.1, KK216506.1, KK216507.1, KK216508.1, KK216510.1, KK216511.1, KK216512.1, KK216513.1, KK216514.1, KK216515.1, KK216519.1, KK216523.1, KK216526.1, KK216530.1, KK216531.1, KK216538.1, KK216540.1, KK216548.1, KK216552.1, KK216553.1, KK216556.1, KK216569.1, KK216571.1, KK216572.1, KK216574.1, KK216576.1, KK216592.1, KK216599.1, KK216606.1, KK216607.1, KK216610.1, KK216615.1, KK216627.1, KK216638.1, KK216640.1, KK216647.1, KK216651.1, KK216657.1, KK216661.1, KK216665.1, KK216672.1, KK216674.1, KK216678.1, KK216680.1, KK216685.1, KK216691.1, KK216695.1, KK216709.1, KK216712.1, KK216714.1, KK216716.1, KK216717.1, KK216725.1, KK216726.1, KK216732.1, KK216737.1, KK216740.1, KK216745.1, KK216746.1, KK216748.1, KK216752.1, KK216758.1, KK216763.1, KK216773.1, KK216779.1, KK216780.1, KK216782.1, KK216784.1, KK216792.1, KK216800.1, KK216804.1, KK216811.1, KK216814.1, KK216815.1, KK216817.1, KK216830.1, KK216831.1, KK216834.1, KK216842.1, KK216848.1, KK216852.1, KK216859.1, KK216861.1, KK216863.1, KK216865.1, KK216867.1, KK216870.1, KK216873.1, KK216879.1, KK216881.1, KK216887.1, KK216896.1, KK216898.1, KK216899.1, KK216903.1, KK216905.1, KK216912.1, KK216913.1, KK216914.1, KK216921.1, KK216922.1, KK216923.1, KK216930.1, KK216931.1, KK216934.1, KK216942.1, KK216943.1, KK216945.1, KK216946.1, KK216950.1, KK216954.1, KK216957.1, KK216959.1, KK216963.1, KK216964.1, KK216965.1, KK216968.1, KK216971.1, KK216973.1, KK216974.1, KK216975.1, KK216980.1, KK216987.1, KK216988.1, KK216994.1, KK216999.1, KK217000.1, KK217001.1, KK217002.1, KK217003.1, KK217007.1, KK217012.1, KK217019.1, KK217032.1, KK217037.1, KK217059.1, KK217063.1, KK217065.1, KK217066.1, KK217072.1, KK217074.1, KK217076.1, KK217077.1, KK217079.1, KK217082.1, KK217083.1, KK217086.1, KK217088.1, KK217093.1, KK217098.1, KK217101.1, KK217103.1, KK217105.1, KK217109.1, KK217111.1, KK217112.1, KK217114.1, KK217117.1, KK217119.1, KK217120.1, KK217121.1, KK217123.1, KK217126.1, KK217128.1, KK217130.1, KK217135.1, KK217140.1, KK217146.1, KK217147.1, KK217182.ol1## Hits object with 14102 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 7 3392
## [2] 8 33428
## [3] 8 33427
## [4] 14 16453
## [5] 18 10110
## ... ... ...
## [14098] 110742 18462
## [14099] 110742 18464
## [14100] 110756 29534
## [14101] 110756 29535
## [14102] 110769 33461
## -------
## queryLength: 110780 / subjectLength: 34314CvGpromoters <- dmrseqCvG[queryHits(ol1)]
myPromotersol1 <- my_Promoters[subjectHits(ol1)]
head(CvGpromoters)## GRanges object with 6 ranges and 7 metadata columns:
## seqnames ranges strand | L area beta
## <Rle> <IRanges> <Rle> | <integer> <numeric> <numeric>
## [1] LG5 2971274-2971545 * | 61 8.49567 0.378574
## [2] KK215283.1 934758-935340 * | 78 5.69451 0.335720
## [3] KK215283.1 934758-935340 * | 78 5.69451 0.335720
## [4] KK215297.1 56283-56546 * | 39 3.74232 -0.390374
## [5] LG11 10641658-10642177 * | 56 6.75082 0.402875
## [6] LG4 4685116-4685638 * | 91 11.17036 0.288880
## stat pval qval index
## <numeric> <numeric> <numeric> <IRanges>
## [1] 11.6533 6.44251e-05 0.719377 14903599-14903659
## [2] 11.2804 8.44919e-05 0.719377 37410-37487
## [3] 11.2804 8.44919e-05 0.719377 37410-37487
## [4] -10.8012 1.27794e-04 0.719377 339662-339700
## [5] 10.6969 1.32019e-04 0.719377 2790037-2790092
## [6] 10.6179 1.39412e-04 0.719377 14118347-14118437
## -------
## seqinfo: 1181 sequences from an unspecified genome; no seqlengthsmyPromotersol1## GRanges object with 14102 ranges and 3 metadata columns:
## seqnames ranges strand | V5
## <Rle> <IRanges> <Rle> | <character>
## [1] LG5 2969966-2972967 + | ENSPREG00000022867
## [2] KK215283.1 934210-937211 - | ENSPREG00000018359
## [3] KK215283.1 934974-937975 - | ENSPREG00000018359
## [4] KK215297.1 54834-57835 + | ENSPREG00000015292
## [5] LG11 10640186-10643187 + | ENSPREG00000001606
## ... ... ... ... . ...
## [14098] LG3 25503964-25506965 - | ENSPREG00000007085
## [14099] LG3 25504550-25507551 - | ENSPREG00000007085
## [14100] LG8 11492118-11495119 - | ENSPREG00000001025
## [14101] LG8 11493215-11496216 - | ENSPREG00000001157
## [14102] KK215284.1 497405-500406 - | ENSPREG00000002312
## V6 V7
## <character> <character>
## [1] ENSPRET00000034154 asb14a
## [2] ENSPRET00000027444 tbc1d30
## [3] ENSPRET00000027444 tbc1d30
## [4] ENSPRET00000023016 ube2c
## [5] ENSPRET00000002349 uncharacterised
## ... ... ...
## [14098] ENSPRET00000010508 adcy7
## [14099] ENSPRET00000010598 adcy7
## [14100] ENSPRET00000001572 uncharacterised
## [14101] ENSPRET00000001592 uncharacterised
## [14102] ENSPRET00000003263 med31
## -------
## 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': 14102 obs. of 14 variables:
## $ seqnames : Factor w/ 1181 levels "KK215283.1","KK215284.1",..: 1177 1 1 15 1161 1176 1159 1164 1177 735 ...
## $ start : int 2971274 934758 934758 56283 10641658 4685116 17896682 9176317 561500 1683 ...
## $ end : int 2971545 935340 935340 56546 10642177 4685638 17897364 9177886 562079 2330 ...
## $ width : int 272 583 583 264 520 523 683 1570 580 648 ...
## $ strand : Factor w/ 3 levels "+","-","*": 3 3 3 3 3 3 3 3 3 3 ...
## $ L : int 61 78 78 39 56 91 78 117 58 82 ...
## $ area : num 8.5 5.69 5.69 3.74 6.75 ...
## $ beta : num 0.379 0.336 0.336 -0.39 0.403 ...
## $ stat : num 11.7 11.3 11.3 -10.8 10.7 ...
## $ pval : num 6.44e-05 8.45e-05 8.45e-05 1.28e-04 1.32e-04 ...
## $ qval : num 0.719 0.719 0.719 0.719 0.719 ...
## $ index.start: int 14903599 37410 37410 339662 2790037 14118347 1269169 4982092 14828919 753522 ...
## $ index.end : int 14903659 37487 37487 339700 2790092 14118437 1269246 4982208 14828976 753603 ...
## $ index.width: int 61 78 78 39 56 91 78 117 58 82 ...myPromotersoldf1 <- as.data.frame(myPromotersol1,row.names = 1:nrow(as.data.frame(ranges(myPromotersol1))))
head(myPromotersoldf1)## seqnames start end width strand V5
## 1 LG5 2969966 2972967 3002 + ENSPREG00000022867
## 2 KK215283.1 934210 937211 3002 - ENSPREG00000018359
## 3 KK215283.1 934974 937975 3002 - ENSPREG00000018359
## 4 KK215297.1 54834 57835 3002 + ENSPREG00000015292
## 5 LG11 10640186 10643187 3002 + ENSPREG00000001606
## 6 LG4 4683335 4686336 3002 + ENSPREG00000003007
## V6 V7
## 1 ENSPRET00000034154 asb14a
## 2 ENSPRET00000027444 tbc1d30
## 3 ENSPRET00000027444 tbc1d30
## 4 ENSPRET00000023016 ube2c
## 5 ENSPRET00000002349 uncharacterised
## 6 ENSPRET00000004307 uncharacterisedCvGpromotersdf <- cbind(CvGpromotersdf,myPromotersoldf1[c("V5","V6","V7")])
CvGpromotersdf$seqnames <- as.character(CvGpromotersdf$seqnames)
head(CvGpromotersdf)## seqnames start end width strand L area beta stat
## 1 LG5 2971274 2971545 272 * 61 8.495669 0.3785743 11.65333
## 2 KK215283.1 934758 935340 583 * 78 5.694514 0.3357201 11.28039
## 3 KK215283.1 934758 935340 583 * 78 5.694514 0.3357201 11.28039
## 4 KK215297.1 56283 56546 264 * 39 3.742322 -0.3903736 -10.80117
## 5 LG11 10641658 10642177 520 * 56 6.750824 0.4028755 10.69685
## 6 LG4 4685116 4685638 523 * 91 11.170358 0.2888801 10.61794
## pval qval index.start index.end index.width V5
## 1 6.442510e-05 0.7193775 14903599 14903659 61 ENSPREG00000022867
## 2 8.449193e-05 0.7193775 37410 37487 78 ENSPREG00000018359
## 3 8.449193e-05 0.7193775 37410 37487 78 ENSPREG00000018359
## 4 1.277940e-04 0.7193775 339662 339700 39 ENSPREG00000015292
## 5 1.320186e-04 0.7193775 2790037 2790092 56 ENSPREG00000001606
## 6 1.394117e-04 0.7193775 14118347 14118437 91 ENSPREG00000003007
## V6 V7
## 1 ENSPRET00000034154 asb14a
## 2 ENSPRET00000027444 tbc1d30
## 3 ENSPRET00000027444 tbc1d30
## 4 ENSPRET00000023016 ube2c
## 5 ENSPRET00000002349 uncharacterised
## 6 ENSPRET00000004307 uncharacterisedCvGpromoterschrdf <- CvGpromotersdf[grep("LG",CvGpromotersdf$seqnames),]
head(CvGpromoterschrdf)## seqnames start end width strand L area beta stat
## 1 LG5 2971274 2971545 272 * 61 8.495669 0.3785743 11.653334
## 5 LG11 10641658 10642177 520 * 56 6.750824 0.4028755 10.696852
## 6 LG4 4685116 4685638 523 * 91 11.170358 0.2888801 10.617941
## 7 LG1 17896682 17897364 683 * 78 7.067168 -0.4086131 -10.417264
## 8 LG14 9176317 9177886 1570 * 117 12.973315 -0.2718633 -9.972136
## 9 LG5 561500 562079 580 * 58 4.402356 -0.3328806 -9.438165
## pval qval index.start index.end index.width V5
## 1 0.0000644251 0.7193775 14903599 14903659 61 ENSPREG00000022867
## 5 0.0001320186 0.7193775 2790037 2790092 56 ENSPREG00000001606
## 6 0.0001394117 0.7193775 14118347 14118437 91 ENSPREG00000003007
## 7 0.0001700400 0.7193775 1269169 1269246 78 ENSPREG00000004582
## 8 0.0002365774 0.7193775 4982092 4982208 117 ENSPREG00000021264
## 9 0.0003844383 0.7193775 14828919 14828976 58 ENSPREG00000021434
## V6 V7
## 1 ENSPRET00000034154 asb14a
## 5 ENSPRET00000002349 uncharacterised
## 6 ENSPRET00000004307 uncharacterised
## 7 ENSPRET00000006703 uncharacterised
## 8 ENSPRET00000031741 ppm1nb
## 9 ENSPRET00000031993 GRM7CvGpromoterschrdf <- CvGpromoterschrdf[order(CvGpromoterschrdf[,11]), ]
colnames(CvGpromoterschrdf) <- c("seqnames","start","end","width","strand","L","area", "beta","stat", "pvalue","qvalue","index.start", "index.width","L", "gene_id","transcript_id", "gene_name")
head(CvGpromoterschrdf,20)## seqnames start end width strand L area beta stat
## 1 LG5 2971274 2971545 272 * 61 8.495669 0.3785743 11.653334
## 5 LG11 10641658 10642177 520 * 56 6.750824 0.4028755 10.696852
## 6 LG4 4685116 4685638 523 * 91 11.170358 0.2888801 10.617941
## 7 LG1 17896682 17897364 683 * 78 7.067168 -0.4086131 -10.417264
## 8 LG14 9176317 9177886 1570 * 117 12.973315 -0.2718633 -9.972136
## 9 LG5 561500 562079 580 * 58 4.402356 -0.3328806 -9.438165
## 11 LG11 28397337 28398020 684 * 79 4.496291 -0.2993888 -9.354211
## 12 LG18 3020876 3021389 514 * 56 4.151694 -0.3258269 -9.316115
## 13 LG18 3020876 3021389 514 * 56 4.151694 -0.3258269 -9.316115
## 14 LG9 29010586 29010947 362 * 37 2.114055 -0.3274617 -9.312339
## 15 LG13 32607789 32608770 982 * 49 4.473201 -0.2909705 -9.299812
## 16 LG13 32607789 32608770 982 * 49 4.473201 -0.2909705 -9.299812
## 17 LG13 32607789 32608770 982 * 49 4.473201 -0.2909705 -9.299812
## 18 LG3 10040979 10041557 579 * 41 7.104433 0.4191580 9.242021
## 19 LG6 27375910 27376342 433 * 72 4.189514 -0.2413977 -9.242003
## 20 LG15 30357859 30358677 819 * 116 7.688326 -0.2033232 -9.216736
## 21 LG15 30357859 30358677 819 * 116 7.688326 -0.2033232 -9.216736
## 22 LG13 18419150 18419602 453 * 54 6.885688 -0.3786169 -9.120724
## 23 LG13 18419150 18419602 453 * 54 6.885688 -0.3786169 -9.120724
## 24 LG22 8861308 8862891 1584 * 92 11.836798 -0.3396811 -9.086127
## pvalue qvalue index.start index.width L gene_id
## 1 0.0000644251 0.7193775 14903599 14903659 61 ENSPREG00000022867
## 5 0.0001320186 0.7193775 2790037 2790092 56 ENSPREG00000001606
## 6 0.0001394117 0.7193775 14118347 14118437 91 ENSPREG00000003007
## 7 0.0001700400 0.7193775 1269169 1269246 78 ENSPREG00000004582
## 8 0.0002365774 0.7193775 4982092 4982208 117 ENSPREG00000021264
## 9 0.0003844383 0.7193775 14828919 14828976 58 ENSPREG00000021434
## 11 0.0004034490 0.7193775 3259562 3259640 79 ENSPREG00000009968
## 12 0.0004150666 0.7193775 8030468 8030523 56 ENSPREG00000000773
## 13 0.0004150666 0.7193775 8030468 8030523 56 ENSPREG00000000773
## 14 0.0004150666 0.7193775 18758558 18758594 37 ENSPREG00000010392
## 15 0.0004214035 0.7193775 4748898 4748946 49 ENSPREG00000020974
## 16 0.0004214035 0.7193775 4748898 4748946 49 ENSPREG00000020974
## 17 0.0004214035 0.7193775 4748898 4748946 49 ENSPREG00000020974
## 18 0.0004478072 0.7193775 13428876 13428916 41 ENSPREG00000018896
## 19 0.0004478072 0.7193775 16366428 16366499 72 ENSPREG00000015822
## 20 0.0004573126 0.7193775 6309589 6309704 116 ENSPREG00000013474
## 21 0.0004573126 0.7193775 6309589 6309704 116 ENSPREG00000013474
## 22 0.0005016708 0.7193775 4381929 4381982 54 ENSPREG00000001609
## 23 0.0005016708 0.7193775 4381929 4381982 54 ENSPREG00000001609
## 24 0.0005164569 0.7193775 12175632 12175723 92 ENSPREG00000015260
## transcript_id gene_name
## 1 ENSPRET00000034154 asb14a
## 5 ENSPRET00000002349 uncharacterised
## 6 ENSPRET00000004307 uncharacterised
## 7 ENSPRET00000006703 uncharacterised
## 8 ENSPRET00000031741 ppm1nb
## 9 ENSPRET00000031993 GRM7
## 11 ENSPRET00000014921 meaf6
## 12 ENSPRET00000001034 uncharacterised
## 13 ENSPRET00000001034 uncharacterised
## 14 ENSPRET00000015598 tbc1d10aa
## 15 ENSPRET00000031555 uncharacterised
## 16 ENSPRET00000031521 uncharacterised
## 17 ENSPRET00000031485 uncharacterised
## 18 ENSPRET00000028232 slc27a2a
## 19 ENSPRET00000023704 nptna
## 20 ENSPRET00000020140 uncharacterised
## 21 ENSPRET00000020129 uncharacterised
## 22 ENSPRET00000002207 SH2B2
## 23 ENSPRET00000002207 SH2B2
## 24 ENSPRET00000022840 uncharacterisedrm(CvGpromoters)
rm(CvGpromotersdf)ol1 <- findOverlaps(dmrseqCvL,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, KK215351.1, KK215360.1, KK215378.1, KK215387.1, KK215391.1, KK215393.1, KK215395.1, KK215396.1, KK215400.1, KK215401.1, KK215405.1, KK215406.1, KK215407.1, KK215408.1, KK215411.1, KK215412.1, KK215414.1, KK215415.1, KK215418.1, KK215420.1, KK215421.1, KK215424.1, KK215427.1, KK215430.1, KK215432.1, KK215433.1, KK215435.1, KK215439.1, 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, 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, KK215581.1, KK215582.1, KK215583.1, KK215585.1, KK215586.1, KK215587.1, KK215588.1, 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, KK215621.1, 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, KK215646.1, KK215647.1, KK215649.1, KK215652.1, KK215654.1, KK215655.1, KK215657.1, KK215658.1, KK215661.1, KK215662.1, KK215663.1, KK215665.1, KK215668.1, KK215670.1, KK215671.1, KK215672.1, KK215673.1, KK215675.1, KK215677.1, KK215683.1, KK215688.1, KK215692.1, KK215700.1, KK215701.1, KK215703.1, KK215704.1, KK215705.1, KK215706.1, KK215707.1, KK215709.1, KK215710.1, KK215711.1, KK215712.1, KK215719.1, KK215720.1, KK215721.1, KK215722.1, KK215723.1, KK215724.1, KK215726.1, KK215727.1, KK215733.1, KK215734.1, KK215736.1, KK215737.1, KK215738.1, KK215739.1, KK215741.1, KK215742.1, KK215748.1, KK215750.1, KK215752.1, KK215753.1, KK215754.1, KK215755.1, KK215756.1, KK215757.1, KK215758.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215767.1, KK215768.1, KK215769.1, KK215770.1, KK215772.1, KK215775.1, KK215776.1, KK215777.1, KK215778.1, KK215780.1, KK215782.1, KK215783.1, KK215785.1, KK215788.1, KK215789.1, KK215792.1, KK215794.1, KK215795.1, KK215797.1, KK215798.1, KK215802.1, KK215804.1, KK215807.1, KK215810.1, KK215812.1, KK215814.1, KK215816.1, KK215819.1, KK215825.1, KK215827.1, KK215832.1, KK215834.1, KK215838.1, KK215839.1, KK215840.1, KK215841.1, KK215842.1, KK215843.1, KK215849.1, KK215857.1, KK215860.1, KK215861.1, KK215863.1, KK215864.1, KK215870.1, KK215875.1, KK215878.1, KK215881.1, KK215885.1, KK215886.1, KK215891.1, KK215894.1, KK215896.1, KK215897.1, KK215898.1, KK215900.1, KK215903.1, KK215907.1, KK215908.1, KK215909.1, KK215911.1, KK215915.1, KK215917.1, KK215918.1, KK215920.1, KK215921.1, KK215923.1, KK215927.1, KK215928.1, KK215929.1, KK215934.1, KK215935.1, KK215937.1, KK215938.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215949.1, KK215951.1, KK215952.1, KK215953.1, KK215956.1, KK215957.1, KK215960.1, KK215962.1, KK215965.1, KK215969.1, KK215970.1, KK215971.1, KK215972.1, KK215973.1, KK215974.1, KK215976.1, KK215978.1, KK215979.1, KK215983.1, KK215989.1, KK215990.1, KK215993.1, KK215995.1, KK215997.1, KK215999.1, KK216000.1, KK216001.1, KK216006.1, KK216008.1, KK216012.1, KK216015.1, KK216017.1, KK216021.1, KK216023.1, KK216026.1, KK216027.1, KK216030.1, KK216032.1, KK216036.1, KK216037.1, KK216038.1, KK216039.1, KK216040.1, KK216041.1, KK216044.1, KK216048.1, KK216049.1, KK216050.1, KK216053.1, KK216056.1, KK216059.1, KK216064.1, KK216065.1, KK216068.1, KK216069.1, KK216071.1, KK216072.1, KK216074.1, KK216075.1, KK216076.1, KK216079.1, KK216080.1, KK216082.1, KK216083.1, KK216084.1, KK216087.1, KK216094.1, KK216096.1, KK216097.1, KK216103.1, KK216106.1, KK216109.1, KK216110.1, KK216111.1, KK216112.1, KK216114.1, KK216115.1, KK216118.1, KK216128.1, KK216131.1, KK216135.1, KK216140.1, KK216141.1, KK216143.1, KK216146.1, KK216150.1, KK216159.1, KK216162.1, KK216164.1, KK216165.1, KK216166.1, KK216168.1, KK216171.1, KK216174.1, KK216175.1, KK216176.1, KK216177.1, KK216181.1, KK216184.1, KK216190.1, KK216192.1, KK216193.1, KK216194.1, KK216195.1, KK216197.1, KK216198.1, KK216200.1, KK216202.1, KK216203.1, KK216206.1, KK216208.1, KK216212.1, KK216213.1, KK216214.1, KK216215.1, KK216219.1, KK216225.1, KK216226.1, KK216227.1, KK216229.1, KK216231.1, KK216232.1, KK216234.1, KK216235.1, KK216237.1, KK216241.1, KK216244.1, KK216245.1, KK216251.1, KK216253.1, KK216254.1, KK216256.1, KK216258.1, KK216259.1, KK216263.1, KK216264.1, KK216265.1, KK216266.1, KK216267.1, KK216272.1, KK216273.1, KK216275.1, KK216278.1, KK216280.1, KK216285.1, KK216287.1, KK216288.1, KK216289.1, KK216290.1, KK216291.1, KK216292.1, KK216295.1, KK216304.1, KK216308.1, KK216310.1, KK216316.1, KK216317.1, KK216319.1, KK216320.1, KK216322.1, KK216323.1, KK216324.1, KK216325.1, KK216329.1, KK216341.1, KK216342.1, KK216345.1, KK216347.1, KK216351.1, KK216359.1, KK216364.1, KK216366.1, KK216369.1, KK216370.1, KK216379.1, KK216384.1, KK216385.1, KK216386.1, KK216387.1, KK216388.1, KK216389.1, KK216391.1, KK216392.1, KK216393.1, KK216394.1, KK216396.1, KK216402.1, KK216403.1, KK216404.1, KK216405.1, KK216414.1, KK216418.1, KK216420.1, KK216422.1, KK216430.1, KK216431.1, KK216433.1, KK216436.1, KK216437.1, KK216438.1, KK216440.1, KK216443.1, KK216447.1, KK216452.1, KK216456.1, KK216457.1, KK216462.1, KK216467.1, KK216477.1, KK216486.1, KK216491.1, KK216492.1, KK216498.1, KK216499.1, KK216503.1, KK216504.1, KK216506.1, KK216507.1, KK216511.1, KK216512.1, KK216520.1, KK216523.1, KK216530.1, KK216534.1, KK216538.1, KK216540.1, KK216556.1, KK216558.1, KK216570.1, KK216571.1, KK216572.1, KK216574.1, KK216586.1, KK216592.1, KK216595.1, KK216598.1, KK216604.1, KK216606.1, KK216609.1, KK216611.1, KK216615.1, KK216618.1, KK216622.1, KK216627.1, KK216630.1, KK216638.1, KK216641.1, KK216645.1, KK216646.1, KK216647.1, KK216648.1, KK216649.1, KK216650.1, KK216652.1, KK216657.1, KK216661.1, KK216674.1, KK216685.1, KK216688.1, KK216696.1, KK216697.1, KK216704.1, KK216705.1, KK216707.1, KK216709.1, KK216710.1, KK216716.1, KK216717.1, KK216721.1, KK216723.1, KK216725.1, KK216726.1, KK216733.1, KK216737.1, KK216739.1, KK216740.1, KK216746.1, KK216747.1, KK216748.1, KK216752.1, KK216761.1, KK216763.1, KK216764.1, KK216767.1, KK216780.1, KK216782.1, KK216784.1, KK216792.1, KK216796.1, KK216803.1, KK216807.1, KK216815.1, KK216817.1, KK216820.1, KK216830.1, KK216841.1, KK216842.1, KK216846.1, KK216847.1, KK216851.1, KK216852.1, KK216865.1, KK216867.1, KK216868.1, KK216870.1, KK216871.1, KK216879.1, KK216880.1, KK216884.1, KK216887.1, KK216895.1, KK216902.1, KK216905.1, KK216908.1, KK216912.1, KK216914.1, KK216918.1, KK216921.1, KK216922.1, KK216930.1, KK216931.1, KK216932.1, KK216945.1, KK216953.1, KK216957.1, KK216968.1, KK216969.1, KK216970.1, KK216971.1, KK216974.1, KK216978.1, KK216980.1, KK216989.1, KK216990.1, KK216994.1, KK216995.1, KK217000.1, KK217002.1, KK217007.1, KK217008.1, KK217012.1, KK217014.1, KK217016.1, KK217019.1, KK217023.1, KK217024.1, KK217026.1, KK217040.1, KK217049.1, KK217053.1, KK217059.1, KK217063.1, KK217064.1, KK217065.1, KK217066.1, KK217068.1, KK217073.1, KK217076.1, KK217079.1, KK217082.1, KK217083.1, KK217088.1, KK217093.1, KK217095.1, KK217098.1, KK217100.1, KK217103.1, KK217104.1, KK217105.1, KK217111.1, KK217112.1, KK217114.1, KK217120.1, KK217123.1, KK217126.1, KK217128.1, KK217130.1, KK217132.1, KK217133.1, KK217135.1, KK217137.1, KK217139.1, KK217140.1, KK217149.1, KK217150.1, KK217154.1, KK217160.ol1## Hits object with 13757 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 3 33702
## [2] 3 16350
## [3] 5 16084
## [4] 5 33437
## [5] 5 16085
## ... ... ...
## [13753] 111375 16027
## [13754] 111406 25648
## [13755] 111412 5082
## [13756] 111415 30673
## [13757] 111419 9810
## -------
## queryLength: 111437 / subjectLength: 34314CvLpromoters <- dmrseqCvL[queryHits(ol1)]
myPromotersol1 <- my_Promoters[subjectHits(ol1)]
head(CvLpromoters)## GRanges object with 6 ranges and 7 metadata columns:
## seqnames ranges strand | L area beta
## <Rle> <IRanges> <Rle> | <integer> <numeric> <numeric>
## [1] KK215293.1 186354-186845 * | 61 5.16072 0.391140
## [2] KK215293.1 186354-186845 * | 61 5.16072 0.391140
## [3] KK215283.1 1376211-1376895 * | 104 13.72310 0.361397
## [4] KK215283.1 1376211-1376895 * | 104 13.72310 0.361397
## [5] KK215283.1 1376211-1376895 * | 104 13.72310 0.361397
## [6] KK215283.1 1376211-1376895 * | 104 13.72310 0.361397
## stat pval qval index
## <numeric> <numeric> <numeric> <IRanges>
## [1] 12.1651 4.00000e-05 0.91033 296821-296881
## [2] 12.1651 4.00000e-05 0.91033 296821-296881
## [3] 11.5460 6.59999e-05 0.91033 56943-57046
## [4] 11.5460 6.59999e-05 0.91033 56943-57046
## [5] 11.5460 6.59999e-05 0.91033 56943-57046
## [6] 11.5460 6.59999e-05 0.91033 56943-57046
## -------
## seqinfo: 1180 sequences from an unspecified genome; no seqlengthsmyPromotersol1## GRanges object with 13757 ranges and 3 metadata columns:
## seqnames ranges strand | V5
## <Rle> <IRanges> <Rle> | <character>
## [1] KK215293.1 184306-187307 - | ENSPREG00000013483
## [2] KK215293.1 186237-189238 + | ENSPREG00000013500
## [3] KK215283.1 1375383-1378384 + | ENSPREG00000019522
## [4] KK215283.1 1375391-1378392 - | ENSPREG00000019483
## [5] KK215283.1 1375441-1378442 + | ENSPREG00000019522
## ... ... ... ... . ...
## [13753] LG23 17233490-17236491 + | ENSPREG00000017022
## [13754] LG7 27300001-27303002 - | ENSPREG00000021367
## [13755] LG16 11055885-11058886 + | ENSPREG00000007507
## [13756] LG12 20232878-20235879 - | ENSPREG00000017960
## [13757] LG15 25203599-25206600 + | ENSPREG00000007341
## V6 V7
## <character> <character>
## [1] ENSPRET00000020133 uncharacterised
## [2] ENSPRET00000020155 uncharacterised
## [3] ENSPRET00000029315 calua
## [4] ENSPRET00000029113 sco2
## [5] ENSPRET00000029364 calua
## ... ... ...
## [13753] ENSPRET00000025534 net1
## [13754] ENSPRET00000031896 uncharacterised
## [13755] ENSPRET00000011125 uncharacterised
## [13756] ENSPRET00000026838 oacyl
## [13757] ENSPRET00000010865 uncharacterised
## -------
## 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': 13757 obs. of 14 variables:
## $ seqnames : Factor w/ 1180 levels "KK215283.1","KK215284.1",..: 11 11 1 1 1 1 1160 1160 1165 1165 ...
## $ start : int 186354 186354 1376211 1376211 1376211 1376211 14181818 14181818 852906 852906 ...
## $ end : int 186845 186845 1376895 1376895 1376895 1376895 14182182 14182182 853242 853242 ...
## $ width : int 492 492 685 685 685 685 365 365 337 337 ...
## $ strand : Factor w/ 3 levels "+","-","*": 3 3 3 3 3 3 3 3 3 3 ...
## $ L : int 61 61 104 104 104 104 58 58 59 59 ...
## $ area : num 5.16 5.16 13.72 13.72 13.72 ...
## $ beta : num 0.391 0.391 0.361 0.361 0.361 ...
## $ stat : num 12.2 12.2 11.5 11.5 11.5 ...
## $ pval : num 4.0e-05 4.0e-05 6.6e-05 6.6e-05 6.6e-05 ...
## $ qval : num 0.91 0.91 0.91 0.91 0.91 ...
## $ index.start: int 296821 296821 56943 56943 56943 56943 2836015 2836015 6214834 6214834 ...
## $ index.end : int 296881 296881 57046 57046 57046 57046 2836072 2836072 6214892 6214892 ...
## $ index.width: int 61 61 104 104 104 104 58 58 59 59 ...myPromotersoldf1 <- as.data.frame(myPromotersol1,row.names = 1:nrow(as.data.frame(ranges(myPromotersol1))))
head(myPromotersoldf1)## seqnames start end width strand V5 V6
## 1 KK215293.1 184306 187307 3002 - ENSPREG00000013483 ENSPRET00000020133
## 2 KK215293.1 186237 189238 3002 + ENSPREG00000013500 ENSPRET00000020155
## 3 KK215283.1 1375383 1378384 3002 + ENSPREG00000019522 ENSPRET00000029315
## 4 KK215283.1 1375391 1378392 3002 - ENSPREG00000019483 ENSPRET00000029113
## 5 KK215283.1 1375441 1378442 3002 + ENSPREG00000019522 ENSPRET00000029364
## 6 KK215283.1 1376555 1379556 3002 + ENSPREG00000019522 ENSPRET00000029379
## V7
## 1 uncharacterised
## 2 uncharacterised
## 3 calua
## 4 sco2
## 5 calua
## 6 caluaCvLpromotersdf <- cbind(CvLpromotersdf,myPromotersoldf1[c("V5","V6","V7")])
CvLpromotersdf$seqnames <- as.character(CvLpromotersdf$seqnames)
head(CvLpromotersdf)## seqnames start end width strand L area beta stat
## 1 KK215293.1 186354 186845 492 * 61 5.160722 0.3911403 12.16515
## 2 KK215293.1 186354 186845 492 * 61 5.160722 0.3911403 12.16515
## 3 KK215283.1 1376211 1376895 685 * 104 13.723096 0.3613973 11.54604
## 4 KK215283.1 1376211 1376895 685 * 104 13.723096 0.3613973 11.54604
## 5 KK215283.1 1376211 1376895 685 * 104 13.723096 0.3613973 11.54604
## 6 KK215283.1 1376211 1376895 685 * 104 13.723096 0.3613973 11.54604
## pval qval index.start index.end index.width V5
## 1 3.999996e-05 0.9103295 296821 296881 61 ENSPREG00000013483
## 2 3.999996e-05 0.9103295 296821 296881 61 ENSPREG00000013500
## 3 6.599993e-05 0.9103295 56943 57046 104 ENSPREG00000019522
## 4 6.599993e-05 0.9103295 56943 57046 104 ENSPREG00000019483
## 5 6.599993e-05 0.9103295 56943 57046 104 ENSPREG00000019522
## 6 6.599993e-05 0.9103295 56943 57046 104 ENSPREG00000019522
## V6 V7
## 1 ENSPRET00000020133 uncharacterised
## 2 ENSPRET00000020155 uncharacterised
## 3 ENSPRET00000029315 calua
## 4 ENSPRET00000029113 sco2
## 5 ENSPRET00000029364 calua
## 6 ENSPRET00000029379 caluaCvLpromoterschrdf <- CvLpromotersdf[grep("LG",CvLpromotersdf$seqnames),]
head(CvLpromoterschrdf)## seqnames start end width strand L area beta stat
## 7 LG11 14181818 14182182 365 * 58 4.745863 -0.3570840 -11.253784
## 8 LG11 14181818 14182182 365 * 58 4.745863 -0.3570840 -11.253784
## 9 LG16 852906 853242 337 * 59 5.256405 -0.3099585 -10.146571
## 10 LG16 852906 853242 337 * 59 5.256405 -0.3099585 -10.146571
## 11 LG16 852906 853242 337 * 59 5.256405 -0.3099585 -10.146571
## 12 LG4 4685053 4685638 586 * 95 13.510971 0.3158647 9.507047
## pval qval index.start index.end index.width V5
## 7 8.099992e-05 0.9103295 2836015 2836072 58 ENSPREG00000007449
## 8 8.099992e-05 0.9103295 2836015 2836072 58 ENSPREG00000007449
## 9 1.839998e-04 0.9103295 6214834 6214892 59 ENSPREG00000015724
## 10 1.839998e-04 0.9103295 6214834 6214892 59 ENSPREG00000015724
## 11 1.839998e-04 0.9103295 6214834 6214892 59 ENSPREG00000015724
## 12 3.109997e-04 0.9103295 13816123 13816217 95 ENSPREG00000003007
## V6 V7
## 7 ENSPRET00000011036 uncharacterised
## 8 ENSPRET00000011036 uncharacterised
## 9 ENSPRET00000023555 uncharacterised
## 10 ENSPRET00000023563 uncharacterised
## 11 ENSPRET00000023563 uncharacterised
## 12 ENSPRET00000004307 uncharacterisedCvLpromoterschrdf <- CvLpromoterschrdf[order(CvLpromoterschrdf[,11]), ]
colnames(CvGpromoterschrdf) <- c("seqnames","start","end","width","strand","L","area", "beta","stat", "pvalue","qvalue","index.start", "index.width","L", "gene_id","transcript_id", "gene_name")
head(CvLpromoterschrdf,20)## seqnames start end width strand L area beta stat
## 7 LG11 14181818 14182182 365 * 58 4.745863 -0.3570840 -11.253784
## 8 LG11 14181818 14182182 365 * 58 4.745863 -0.3570840 -11.253784
## 9 LG16 852906 853242 337 * 59 5.256405 -0.3099585 -10.146571
## 10 LG16 852906 853242 337 * 59 5.256405 -0.3099585 -10.146571
## 11 LG16 852906 853242 337 * 59 5.256405 -0.3099585 -10.146571
## 12 LG4 4685053 4685638 586 * 95 13.510971 0.3158647 9.507047
## 13 LG1 18070269 18071303 1035 * 89 8.962426 -0.2763986 -9.401986
## 14 LG23 1376882 1377608 727 * 61 8.986266 -0.4336691 -8.975553
## 15 LG7 18259264 18260110 847 * 28 6.708446 0.5276226 8.971170
## 18 LG7 17085665 17086479 815 * 101 13.436313 0.3494188 8.758125
## 19 LG2 36596343 36596990 648 * 50 3.500546 -0.2395078 -8.623741
## 20 LG5 24679174 24679587 414 * 45 5.861411 0.4044968 8.612346
## 21 LG7 19972809 19973456 648 * 29 5.172946 0.5530375 8.610610
## 22 LG7 19972809 19973456 648 * 29 5.172946 0.5530375 8.610610
## 23 LG9 9489130 9489710 581 * 42 4.072473 -0.3281138 -8.589622
## 24 LG9 9489130 9489710 581 * 42 4.072473 -0.3281138 -8.589622
## 26 LG11 10184557 10185539 983 * 120 11.815863 0.3049973 8.354479
## 27 LG3 19963040 19963388 349 * 26 2.761796 -0.4410081 -8.328988
## 28 LG18 4888241 4889449 1209 * 100 13.786780 -0.3311130 -8.323026
## 29 LG13 1652733 1653376 644 * 31 3.668329 0.4171294 8.204332
## pval qval index.start index.end index.width V5
## 7 8.099992e-05 0.9103295 2836015 2836072 58 ENSPREG00000007449
## 8 8.099992e-05 0.9103295 2836015 2836072 58 ENSPREG00000007449
## 9 1.839998e-04 0.9103295 6214834 6214892 59 ENSPREG00000015724
## 10 1.839998e-04 0.9103295 6214834 6214892 59 ENSPREG00000015724
## 11 1.839998e-04 0.9103295 6214834 6214892 59 ENSPREG00000015724
## 12 3.109997e-04 0.9103295 13816123 13816217 95 ENSPREG00000003007
## 13 3.399997e-04 0.9103295 1243346 1243434 89 ENSPREG00000005128
## 14 4.889995e-04 0.9103295 12382860 12382920 61 ENSPREG00000022413
## 15 4.909995e-04 0.9103295 16597659 16597686 28 ENSPREG00000003617
## 18 6.069994e-04 0.9261309 16563951 16564051 101 ENSPREG00000001520
## 19 6.929993e-04 0.9405804 10087471 10087520 50 ENSPREG00000013239
## 20 6.969993e-04 0.9405804 15117287 15117331 45 ENSPREG00000012853
## 21 6.979993e-04 0.9405804 16636303 16636331 29 ENSPREG00000006394
## 22 6.979993e-04 0.9405804 16636303 16636331 29 ENSPREG00000006394
## 23 7.089993e-04 0.9405804 17896665 17896706 42 ENSPREG00000003150
## 24 7.089993e-04 0.9405804 17896665 17896706 42 ENSPREG00000003150
## 26 8.829991e-04 0.9532280 2714240 2714359 120 ENSPREG00000021725
## 27 9.109991e-04 0.9532280 13367667 13367692 26 ENSPREG00000000589
## 28 9.189991e-04 0.9532280 7897415 7897514 100 ENSPREG00000004844
## 29 1.033999e-03 0.9532280 3888789 3888819 31 ENSPREG00000008830
## V6 V7
## 7 ENSPRET00000011036 uncharacterised
## 8 ENSPRET00000011036 uncharacterised
## 9 ENSPRET00000023555 uncharacterised
## 10 ENSPRET00000023563 uncharacterised
## 11 ENSPRET00000023563 uncharacterised
## 12 ENSPRET00000004307 uncharacterised
## 13 ENSPRET00000007557 slc25a4
## 14 ENSPRET00000033466 ppfia2
## 15 ENSPRET00000005305 uts2a
## 18 ENSPRET00000002091 zgc:198371
## 19 ENSPRET00000019775 lims2
## 20 ENSPRET00000019215 ankrd33ab
## 21 ENSPRET00000009531 asic1a
## 22 ENSPRET00000009545 asic1a
## 23 ENSPRET00000004527 prdm8b
## 24 ENSPRET00000004527 prdm8b
## 26 ENSPRET00000032420 hoxa5a
## 27 ENSPRET00000001109 nedd4a
## 28 ENSPRET00000007125 uncharacterised
## 29 ENSPRET00000013202 uncharacterisedrm(CvLpromoters)
rm(CvLpromotersdf)ol1 <- findOverlaps(dmrseqGvL,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, KK215360.1, KK215378.1, KK215387.1, KK215391.1, KK215393.1, KK215395.1, KK215396.1, KK215400.1, KK215401.1, KK215402.1, KK215405.1, KK215406.1, KK215407.1, KK215408.1, KK215411.1, KK215412.1, KK215415.1, KK215418.1, KK215420.1, KK215421.1, KK215424.1, KK215427.1, KK215430.1, KK215432.1, KK215433.1, KK215435.1, KK215439.1, KK215440.1, KK215441.1, KK215444.1, KK215446.1, KK215448.1, KK215451.1, KK215453.1, KK215455.1, KK215456.1, KK215459.1, KK215462.1, KK215463.1, KK215465.1, KK215466.1, KK215467.1, 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, KK215502.1, KK215503.1, KK215504.1, KK215506.1, KK215507.1, KK215508.1, KK215511.1, KK215513.1, KK215514.1, KK215515.1, KK215516.1, KK215517.1, KK215518.1, KK215519.1, KK215521.1, KK215523.1, KK215524.1, KK215525.1, KK215528.1, KK215529.1, KK215530.1, KK215531.1, KK215533.1, KK215538.1, KK215540.1, KK215541.1, KK215543.1, KK215544.1, KK215545.1, KK215546.1, KK215548.1, KK215549.1, KK215551.1, KK215553.1, KK215554.1, 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, KK215624.1, KK215625.1, KK215626.1, 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, KK215647.1, KK215649.1, KK215652.1, KK215654.1, KK215655.1, KK215657.1, KK215658.1, KK215661.1, KK215662.1, KK215663.1, KK215664.1, KK215668.1, KK215669.1, KK215670.1, KK215671.1, KK215672.1, KK215673.1, KK215675.1, KK215677.1, KK215678.1, KK215684.1, KK215688.1, KK215692.1, KK215695.1, KK215699.1, KK215700.1, KK215701.1, KK215703.1, KK215705.1, KK215706.1, KK215707.1, KK215709.1, KK215711.1, KK215712.1, KK215715.1, KK215719.1, KK215720.1, KK215721.1, KK215722.1, KK215724.1, KK215726.1, KK215727.1, KK215728.1, KK215733.1, KK215734.1, KK215736.1, KK215737.1, KK215738.1, KK215739.1, KK215743.1, KK215745.1, KK215748.1, KK215750.1, KK215753.1, KK215754.1, KK215755.1, KK215756.1, KK215757.1, KK215762.1, KK215763.1, KK215764.1, KK215765.1, KK215767.1, KK215768.1, KK215769.1, KK215770.1, KK215771.1, KK215772.1, KK215775.1, KK215776.1, KK215777.1, KK215778.1, KK215782.1, KK215783.1, KK215786.1, KK215788.1, KK215789.1, KK215792.1, KK215797.1, KK215798.1, KK215802.1, KK215804.1, KK215807.1, KK215810.1, KK215812.1, KK215814.1, KK215816.1, KK215818.1, KK215821.1, KK215825.1, KK215834.1, KK215836.1, KK215839.1, KK215842.1, KK215843.1, KK215847.1, KK215849.1, KK215852.1, KK215857.1, KK215858.1, KK215859.1, KK215860.1, KK215864.1, KK215867.1, KK215870.1, KK215872.1, KK215873.1, KK215877.1, KK215881.1, KK215885.1, KK215886.1, KK215890.1, KK215891.1, KK215893.1, KK215894.1, KK215897.1, KK215902.1, KK215905.1, KK215907.1, KK215908.1, KK215909.1, KK215910.1, KK215911.1, KK215914.1, KK215915.1, KK215917.1, KK215918.1, KK215920.1, KK215921.1, KK215927.1, KK215928.1, KK215929.1, KK215934.1, KK215938.1, KK215941.1, KK215942.1, KK215943.1, KK215945.1, KK215946.1, KK215949.1, KK215951.1, KK215952.1, KK215960.1, KK215965.1, KK215967.1, KK215969.1, KK215970.1, KK215972.1, KK215974.1, KK215975.1, KK215976.1, KK215977.1, KK215978.1, KK215979.1, KK215982.1, KK215983.1, KK215984.1, KK215987.1, KK215993.1, KK215995.1, KK215997.1, KK215999.1, KK216000.1, KK216012.1, KK216017.1, KK216021.1, KK216023.1, KK216029.1, KK216030.1, KK216033.1, KK216034.1, KK216035.1, KK216038.1, KK216039.1, KK216041.1, KK216044.1, KK216048.1, KK216050.1, KK216053.1, KK216056.1, KK216059.1, KK216063.1, KK216064.1, KK216067.1, KK216069.1, KK216072.1, KK216075.1, KK216076.1, KK216077.1, KK216079.1, KK216085.1, KK216086.1, KK216087.1, KK216089.1, KK216093.1, KK216094.1, KK216095.1, KK216099.1, KK216106.1, KK216109.1, KK216110.1, KK216114.1, KK216115.1, KK216120.1, KK216124.1, KK216128.1, KK216131.1, KK216134.1, KK216135.1, KK216140.1, KK216141.1, KK216142.1, KK216143.1, KK216150.1, KK216152.1, KK216157.1, KK216158.1, KK216162.1, KK216163.1, KK216165.1, KK216168.1, KK216169.1, KK216171.1, KK216174.1, KK216176.1, KK216177.1, KK216181.1, KK216184.1, KK216190.1, KK216192.1, KK216193.1, KK216194.1, KK216195.1, KK216197.1, KK216198.1, KK216201.1, KK216202.1, KK216203.1, KK216205.1, KK216212.1, KK216213.1, KK216214.1, KK216215.1, KK216217.1, KK216218.1, KK216219.1, KK216222.1, KK216225.1, KK216226.1, KK216227.1, KK216231.1, KK216234.1, KK216235.1, KK216236.1, KK216240.1, KK216241.1, KK216242.1, KK216245.1, KK216248.1, KK216253.1, KK216256.1, KK216258.1, KK216259.1, KK216261.1, KK216264.1, KK216265.1, KK216266.1, KK216267.1, KK216269.1, KK216273.1, KK216278.1, KK216282.1, KK216284.1, KK216285.1, KK216287.1, KK216289.1, KK216290.1, KK216291.1, KK216292.1, KK216293.1, KK216295.1, KK216303.1, KK216304.1, KK216306.1, KK216307.1, KK216310.1, KK216313.1, KK216315.1, KK216316.1, KK216317.1, KK216318.1, KK216319.1, KK216320.1, KK216323.1, KK216324.1, KK216325.1, KK216326.1, KK216329.1, KK216330.1, KK216331.1, KK216333.1, KK216336.1, KK216341.1, KK216342.1, KK216345.1, KK216351.1, KK216361.1, KK216363.1, KK216368.1, KK216369.1, KK216370.1, KK216374.1, KK216377.1, KK216383.1, KK216387.1, KK216388.1, KK216390.1, KK216391.1, KK216393.1, KK216394.1, KK216396.1, KK216400.1, KK216402.1, KK216403.1, KK216404.1, KK216410.1, KK216418.1, KK216420.1, KK216423.1, KK216427.1, KK216429.1, KK216430.1, KK216431.1, KK216437.1, KK216440.1, KK216442.1, KK216443.1, KK216447.1, KK216454.1, KK216456.1, KK216458.1, KK216462.1, KK216465.1, KK216467.1, KK216476.1, KK216478.1, KK216485.1, KK216486.1, KK216491.1, KK216492.1, KK216498.1, KK216499.1, KK216500.1, KK216502.1, KK216506.1, KK216507.1, KK216508.1, KK216510.1, KK216511.1, KK216513.1, KK216515.1, KK216523.1, KK216526.1, KK216527.1, KK216530.1, KK216531.1, KK216534.1, KK216543.1, KK216552.1, KK216559.1, KK216566.1, KK216571.1, KK216574.1, KK216584.1, KK216596.1, KK216598.1, KK216602.1, KK216603.1, KK216606.1, KK216629.1, KK216630.1, KK216636.1, KK216638.1, KK216640.1, KK216643.1, KK216644.1, KK216648.1, KK216650.1, KK216652.1, KK216657.1, KK216661.1, KK216665.1, KK216668.1, KK216671.1, KK216674.1, KK216678.1, KK216679.1, KK216686.1, KK216688.1, KK216696.1, KK216697.1, KK216702.1, KK216717.1, KK216725.1, KK216728.1, KK216731.1, KK216732.1, KK216733.1, KK216739.1, KK216745.1, KK216748.1, KK216767.1, KK216771.1, KK216774.1, KK216775.1, KK216782.1, KK216784.1, KK216795.1, KK216796.1, KK216804.1, KK216807.1, KK216811.1, KK216813.1, KK216814.1, KK216817.1, KK216823.1, KK216841.1, KK216848.1, KK216852.1, KK216859.1, KK216861.1, KK216866.1, KK216867.1, KK216870.1, KK216881.1, KK216882.1, KK216884.1, KK216892.1, KK216895.1, KK216896.1, KK216907.1, KK216908.1, KK216911.1, KK216912.1, KK216913.1, KK216914.1, KK216921.1, KK216929.1, KK216934.1, KK216935.1, KK216936.1, KK216942.1, KK216945.1, KK216946.1, KK216950.1, KK216954.1, KK216957.1, KK216959.1, KK216964.1, KK216965.1, KK216969.1, KK216971.1, KK216973.1, KK216977.1, KK216978.1, KK216980.1, KK216987.1, KK216988.1, KK216994.1, KK216995.1, KK216998.1, KK216999.1, KK217001.1, KK217003.1, KK217007.1, KK217008.1, KK217010.1, KK217011.1, KK217012.1, KK217016.1, KK217017.1, KK217019.1, KK217021.1, KK217032.1, KK217040.1, KK217049.1, KK217059.1, KK217063.1, KK217076.1, KK217077.1, KK217080.1, KK217083.1, KK217090.1, KK217091.1, KK217098.1, KK217100.1, KK217101.1, KK217104.1, KK217105.1, KK217111.1, KK217120.1, KK217123.1, KK217128.1, KK217133.1, KK217135.1, KK217147.1, KK217151.1, KK217161.1, KK217163.1, KK217174.1, KK217179.1, KK217182.1, KK217183.1, KK217186.1, KK217187.1, KK217189.1, KK217190.1, KK217193.1, KK217200.1, KK217203.1, KK217204.1, KK217206.1, KK217209.1, KK217228.1, KK217233.1, KK217237.1, KK217238.ol1## Hits object with 11399 hits and 0 metadata columns:
## queryHits subjectHits
## <integer> <integer>
## [1] 1 10594
## [2] 2 16084
## [3] 2 33437
## [4] 2 16085
## [5] 2 16086
## ... ... ...
## [11395] 91501 7318
## [11396] 91501 7319
## [11397] 91503 27731
## [11398] 91509 29991
## [11399] 91521 24112
## -------
## queryLength: 91524 / subjectLength: 34314GvLpromoters <- dmrseqGvL[queryHits(ol1)]
myPromotersol1 <- my_Promoters[subjectHits(ol1)]
head(GvLpromoters)## GRanges object with 6 ranges and 7 metadata columns:
## seqnames ranges strand | L area beta
## <Rle> <IRanges> <Rle> | <integer> <numeric> <numeric>
## [1] LG11 28461237-28461741 * | 108 11.63697 -0.277374
## [2] KK215283.1 1376121-1376899 * | 156 18.40713 0.329127
## [3] KK215283.1 1376121-1376899 * | 156 18.40713 0.329127
## [4] KK215283.1 1376121-1376899 * | 156 18.40713 0.329127
## [5] KK215283.1 1376121-1376899 * | 156 18.40713 0.329127
## [6] KK215306.1 101373-102087 * | 68 9.62665 0.432490
## stat pval qval index
## <numeric> <numeric> <numeric> <IRanges>
## [1] -16.2750 7.14404e-06 0.653851 3678849-3678956
## [2] 15.2345 1.78601e-05 0.749204 65611-65766
## [3] 15.2345 1.78601e-05 0.749204 65611-65766
## [4] 15.2345 1.78601e-05 0.749204 65611-65766
## [5] 15.2345 1.78601e-05 0.749204 65611-65766
## [6] 12.3753 7.62031e-05 0.774935 479142-479209
## -------
## seqinfo: 1169 sequences from an unspecified genome; no seqlengthsmyPromotersol1## GRanges object with 11399 ranges and 3 metadata columns:
## seqnames ranges strand | V5
## <Rle> <IRanges> <Rle> | <character>
## [1] LG11 28461480-28464481 + | ENSPREG00000010182
## [2] KK215283.1 1375383-1378384 + | ENSPREG00000019522
## [3] KK215283.1 1375391-1378392 - | ENSPREG00000019483
## [4] KK215283.1 1375441-1378442 + | ENSPREG00000019522
## [5] KK215283.1 1376555-1379556 + | ENSPREG00000019522
## ... ... ... ... . ...
## [11395] LG4 11998636-12001637 + | ENSPREG00000011784
## [11396] LG4 11999476-12002477 + | ENSPREG00000011784
## [11397] LG11 23158211-23161212 - | ENSPREG00000021767
## [11398] LG8 23950233-23953234 - | ENSPREG00000006506
## [11399] LG6 25925511-25928512 - | ENSPREG00000011372
## V6 V7
## <character> <character>
## [1] ENSPRET00000015234 tfap2e
## [2] ENSPRET00000029315 calua
## [3] ENSPRET00000029113 sco2
## [4] ENSPRET00000029364 calua
## [5] ENSPRET00000029379 calua
## ... ... ...
## [11395] ENSPRET00000017613 uncharacterised
## [11396] ENSPRET00000017624 uncharacterised
## [11397] ENSPRET00000032485 uncharacterised
## [11398] ENSPRET00000009725 CYTH3
## [11399] ENSPRET00000017007 si:ch211-247i17.1
## -------
## 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': 11399 obs. of 14 variables:
## $ seqnames : Factor w/ 1169 levels "KK215283.1","KK215284.1",..: 1149 1 1 1 1 24 24 1165 1 1155 ...
## $ start : int 28461237 1376121 1376121 1376121 1376121 101373 101373 2971274 1067054 4434405 ...
## $ end : int 28461741 1376899 1376899 1376899 1376899 102087 102087 2971545 1067919 4435108 ...
## $ width : int 505 779 779 779 779 715 715 272 866 704 ...
## $ strand : Factor w/ 3 levels "+","-","*": 3 3 3 3 3 3 3 3 3 3 ...
## $ L : int 108 156 156 156 156 68 68 58 63 67 ...
## $ area : num 11.6 18.4 18.4 18.4 18.4 ...
## $ beta : num -0.277 0.329 0.329 0.329 0.329 ...
## $ stat : num -16.3 15.2 15.2 15.2 15.2 ...
## $ pval : num 7.14e-06 1.79e-05 1.79e-05 1.79e-05 1.79e-05 ...
## $ qval : num 0.654 0.749 0.749 0.749 0.749 ...
## $ index.start: int 3678849 65611 65611 65611 65611 479142 479142 16775120 48980 8251105 ...
## $ index.end : int 3678956 65766 65766 65766 65766 479209 479209 16775177 49042 8251171 ...
## $ index.width: int 108 156 156 156 156 68 68 58 63 67 ...myPromotersoldf1 <- as.data.frame(myPromotersol1,row.names = 1:nrow(as.data.frame(ranges(myPromotersol1))))
head(myPromotersoldf1)## seqnames start end width strand V5
## 1 LG11 28461480 28464481 3002 + ENSPREG00000010182
## 2 KK215283.1 1375383 1378384 3002 + ENSPREG00000019522
## 3 KK215283.1 1375391 1378392 3002 - ENSPREG00000019483
## 4 KK215283.1 1375441 1378442 3002 + ENSPREG00000019522
## 5 KK215283.1 1376555 1379556 3002 + ENSPREG00000019522
## 6 KK215306.1 101374 104375 3002 - ENSPREG00000001826
## V6 V7
## 1 ENSPRET00000015234 tfap2e
## 2 ENSPRET00000029315 calua
## 3 ENSPRET00000029113 sco2
## 4 ENSPRET00000029364 calua
## 5 ENSPRET00000029379 calua
## 6 ENSPRET00000002537 galr1bGvLpromotersdf <- cbind(GvLpromotersdf,myPromotersoldf1[c("V5","V6","V7")])
GvLpromotersdf$seqnames <- as.character(GvLpromotersdf$seqnames)
head(GvLpromotersdf)## seqnames start end width strand L area beta stat
## 1 LG11 28461237 28461741 505 * 108 11.636971 -0.2773737 -16.27500
## 2 KK215283.1 1376121 1376899 779 * 156 18.407129 0.3291269 15.23454
## 3 KK215283.1 1376121 1376899 779 * 156 18.407129 0.3291269 15.23454
## 4 KK215283.1 1376121 1376899 779 * 156 18.407129 0.3291269 15.23454
## 5 KK215283.1 1376121 1376899 779 * 156 18.407129 0.3291269 15.23454
## 6 KK215306.1 101373 102087 715 * 68 9.626653 0.4324903 12.37528
## pval qval index.start index.end index.width V5
## 1 7.144039e-06 0.6538511 3678849 3678956 108 ENSPREG00000010182
## 2 1.786010e-05 0.7492043 65611 65766 156 ENSPREG00000019522
## 3 1.786010e-05 0.7492043 65611 65766 156 ENSPREG00000019483
## 4 1.786010e-05 0.7492043 65611 65766 156 ENSPREG00000019522
## 5 1.786010e-05 0.7492043 65611 65766 156 ENSPREG00000019522
## 6 7.620309e-05 0.7749346 479142 479209 68 ENSPREG00000001826
## V6 V7
## 1 ENSPRET00000015234 tfap2e
## 2 ENSPRET00000029315 calua
## 3 ENSPRET00000029113 sco2
## 4 ENSPRET00000029364 calua
## 5 ENSPRET00000029379 calua
## 6 ENSPRET00000002537 galr1bGvLpromoterschrdf <- GvLpromotersdf[grep("LG",GvLpromotersdf$seqnames),]
head(GvLpromoterschrdf)## seqnames start end width strand L area beta stat
## 1 LG11 28461237 28461741 505 * 108 11.636971 -0.2773737 -16.27500
## 8 LG5 2971274 2971545 272 * 58 7.527239 -0.3990748 -12.02408
## 10 LG17 4434405 4435108 704 * 67 10.629923 -0.4174846 -11.47364
## 11 LG17 4434405 4435108 704 * 67 10.629923 -0.4174846 -11.47364
## 12 LG4 19716877 19717452 576 * 71 4.981281 0.3020933 10.83986
## 13 LG21 16656091 16656658 568 * 92 9.790377 -0.2600441 -10.81785
## pval qval index.start index.end index.width V5
## 1 7.144039e-06 0.6538511 3678849 3678956 108 ENSPREG00000010182
## 8 9.287251e-05 0.7879743 16775120 16775177 58 ENSPREG00000022867
## 10 1.357367e-04 0.7879743 8251105 8251171 67 ENSPREG00000004307
## 11 1.357367e-04 0.7879743 8251105 8251171 67 ENSPREG00000004307
## 12 2.083678e-04 0.7879743 16318476 16318546 71 ENSPREG00000020177
## 13 2.131305e-04 0.7879743 13172129 13172220 92 ENSPREG00000015620
## V6 V7
## 1 ENSPRET00000015234 tfap2e
## 8 ENSPRET00000034154 asb14a
## 10 ENSPRET00000006277 uncharacterised
## 11 ENSPRET00000006277 uncharacterised
## 12 ENSPRET00000030158 ppat
## 13 ENSPRET00000023480 entpd5bGvLpromoterschrdf <- GvLpromoterschrdf[order(GvLpromoterschrdf[,11]), ]
colnames(CvGpromoterschrdf) <- c("seqnames","start","end","width","strand","L","area", "beta","stat", "pvalue","qvalue","index.start", "index.width","L", "gene_id","transcript_id", "gene_name")
head(GvLpromoterschrdf,20)## seqnames start end width strand L area beta stat
## 1 LG11 28461237 28461741 505 * 108 11.636971 -0.2773737 -16.274999
## 8 LG5 2971274 2971545 272 * 58 7.527239 -0.3990748 -12.024079
## 10 LG17 4434405 4435108 704 * 67 10.629923 -0.4174846 -11.473637
## 11 LG17 4434405 4435108 704 * 67 10.629923 -0.4174846 -11.473637
## 12 LG4 19716877 19717452 576 * 71 4.981281 0.3020933 10.839859
## 13 LG21 16656091 16656658 568 * 92 9.790377 -0.2600441 -10.817845
## 14 LG22 8861308 8862494 1187 * 107 13.845469 0.3227734 10.238006
## 15 LG1 17897041 17897428 388 * 79 4.272873 0.2553471 10.102065
## 16 LG17 4281596 4283884 2289 * 138 14.320803 0.2363804 9.707138
## 17 LG18 4887976 4888902 927 * 70 9.621193 -0.3148876 -9.641827
## 18 LG11 12873733 12874324 592 * 65 5.977088 0.2335116 9.600946
## 19 LG19 23419961 23420381 421 * 44 2.846027 -0.2897090 -9.526620
## 20 LG13 17708262 17709123 862 * 62 9.707475 0.3562946 9.521485
## 21 LG13 17708262 17709123 862 * 62 9.707475 0.3562946 9.521485
## 22 LG18 21124909 21125756 848 * 80 6.926514 0.2445258 9.460839
## 23 LG10 5124205 5124733 529 * 91 7.418948 0.2760693 9.372552
## 24 LG10 5124205 5124733 529 * 91 7.418948 0.2760693 9.372552
## 25 LG7 27074581 27075191 611 * 76 4.468701 0.2347441 9.370081
## 26 LG17 3557984 3558729 746 * 51 9.581551 0.4594205 9.348065
## 27 LG17 3557984 3558729 746 * 51 9.581551 0.4594205 9.348065
## pval qval index.start index.end index.width V5
## 1 7.144039e-06 0.6538511 3678849 3678956 108 ENSPREG00000010182
## 8 9.287251e-05 0.7879743 16775120 16775177 58 ENSPREG00000022867
## 10 1.357367e-04 0.7879743 8251105 8251171 67 ENSPREG00000004307
## 11 1.357367e-04 0.7879743 8251105 8251171 67 ENSPREG00000004307
## 12 2.083678e-04 0.7879743 16318476 16318546 71 ENSPREG00000020177
## 13 2.131305e-04 0.7879743 13172129 13172220 92 ENSPREG00000015620
## 14 3.298165e-04 0.9737459 13711563 13711669 107 ENSPREG00000015260
## 15 3.655367e-04 0.9928849 1438366 1438444 79 ENSPREG00000004582
## 16 5.250869e-04 0.9998670 8244713 8244850 138 ENSPREG00000003984
## 17 5.536630e-04 0.9998670 9087342 9087411 70 ENSPREG00000004844
## 18 5.655698e-04 0.9998670 3222323 3222387 65 ENSPREG00000005172
## 19 6.072433e-04 0.9998670 10382933 10382976 44 ENSPREG00000020727
## 20 6.084340e-04 0.9998670 4911914 4911975 62 ENSPREG00000022956
## 21 6.084340e-04 0.9998670 4911914 4911975 62 ENSPREG00000022956
## 22 6.370102e-04 0.9998670 9609256 9609335 80 ENSPREG00000005872
## 23 6.941625e-04 0.9998670 2078042 2078132 91 ENSPREG00000022019
## 24 6.941625e-04 0.9998670 2078042 2078132 91 ENSPREG00000022019
## 25 6.965438e-04 0.9998670 19308679 19308754 76 ENSPREG00000021152
## 26 7.144039e-04 0.9998670 8216908 8216958 51 ENSPREG00000002699
## 27 7.144039e-04 0.9998670 8216908 8216958 51 ENSPREG00000002699
## V6 V7
## 1 ENSPRET00000015234 tfap2e
## 8 ENSPRET00000034154 asb14a
## 10 ENSPRET00000006277 uncharacterised
## 11 ENSPRET00000006277 uncharacterised
## 12 ENSPRET00000030158 ppat
## 13 ENSPRET00000023480 entpd5b
## 14 ENSPRET00000022840 uncharacterised
## 15 ENSPRET00000006703 uncharacterised
## 16 ENSPRET00000005798 MYOC
## 17 ENSPRET00000007125 uncharacterised
## 18 ENSPRET00000007618 SDC3
## 19 ENSPRET00000030962 zc3h7bb
## 20 ENSPRET00000034268 uncharacterised
## 21 ENSPRET00000034268 uncharacterised
## 22 ENSPRET00000008705 uncharacterised
## 23 ENSPRET00000032858 uncharacterised
## 24 ENSPRET00000032858 uncharacterised
## 25 ENSPRET00000031614 kmt2d
## 26 ENSPRET00000003812 uncharacterised
## 27 ENSPRET00000003834 uncharacterisedrm(GvLpromoters)
rm(GvLpromotersdf)Create RCircos plot for CvG comparison
CvGgeneschrdfdmrs <- head(CvGgeneschrdf,75)
head(CvGgeneschrdfdmrs)## seqnames start end width strand L area beta stat
## 1 LG13 18160946 18161700 755 * 75 17.104340 0.4804793 12.35578
## 2 LG8 27368425 27368499 75 * 22 1.107603 -0.3598625 -12.34614
## 3 LG8 27368425 27368499 75 * 22 1.107603 -0.3598625 -12.34614
## 5 LG5 2971274 2971545 272 * 61 8.495669 0.3785743 11.65333
## 6 LG5 2971274 2971545 272 * 61 8.495669 0.3785743 11.65333
## 8 LG10 32171882 32172301 420 * 46 8.597024 0.4390605 11.17294
## pval qval index.start index.end index.width gene_id
## 1 4.013367e-05 0.7193775 4371608 4371682 75 ENSPREG00000001265
## 2 4.118982e-05 0.7193775 18010981 18011002 22 ENSPREG00000012374
## 3 4.118982e-05 0.7193775 18010981 18011002 22 ENSPREG00000012413
## 5 6.442510e-05 0.7193775 14903599 14903659 61 ENSPREG00000022808
## 6 6.442510e-05 0.7193775 14903599 14903659 61 ENSPREG00000022867
## 8 9.082882e-05 0.7193775 2481310 2481355 46 ENSPREG00000011064
## gene_biotype gene_name
## 1 protein_coding <NA>
## 2 protein_coding btr30
## 3 protein_coding <NA>
## 5 protein_coding <NA>
## 6 protein_coding asb14a
## 8 protein_coding NFKB1Chr.Label.Data <- dplyr::select(CvGgeneschrdfdmrs,seqnames,start,end,gene_name)
colnames(Chr.Label.Data) <- c("Chromosome","chromStart","chromEnd","GeneName")
head(Chr.Label.Data)## Chromosome chromStart chromEnd GeneName
## 1 LG13 18160946 18161700 <NA>
## 2 LG8 27368425 27368499 btr30
## 3 LG8 27368425 27368499 <NA>
## 5 LG5 2971274 2971545 <NA>
## 6 LG5 2971274 2971545 asb14a
## 8 LG10 32171882 32172301 NFKB1Chr.Label.Data <- Chr.Label.Data[-which(Chr.Label.Data$GeneName == "" | is.na(Chr.Label.Data$GeneName)), ]
head(Chr.Label.Data,10)## Chromosome chromStart chromEnd GeneName
## 2 LG8 27368425 27368499 btr30
## 6 LG5 2971274 2971545 asb14a
## 8 LG10 32171882 32172301 NFKB1
## 9 LG13 18052556 18054100 capn12
## 10 LG19 10333007 10333692 QRFPR
## 11 LG19 8889655 8889899 eif3c
## 14 LG19 25883884 25884226 bbs1
## 15 LG11 3353555 3354323 kcnk9
## 18 LG10 14876068 14876399 dlg3
## 20 LG2 43981407 43981496 cry3ahead(CvGgeneschrdf)## seqnames start end width strand L area beta stat
## 1 LG13 18160946 18161700 755 * 75 17.104340 0.4804793 12.35578
## 2 LG8 27368425 27368499 75 * 22 1.107603 -0.3598625 -12.34614
## 3 LG8 27368425 27368499 75 * 22 1.107603 -0.3598625 -12.34614
## 5 LG5 2971274 2971545 272 * 61 8.495669 0.3785743 11.65333
## 6 LG5 2971274 2971545 272 * 61 8.495669 0.3785743 11.65333
## 8 LG10 32171882 32172301 420 * 46 8.597024 0.4390605 11.17294
## pval qval index.start index.end index.width gene_id
## 1 4.013367e-05 0.7193775 4371608 4371682 75 ENSPREG00000001265
## 2 4.118982e-05 0.7193775 18010981 18011002 22 ENSPREG00000012374
## 3 4.118982e-05 0.7193775 18010981 18011002 22 ENSPREG00000012413
## 5 6.442510e-05 0.7193775 14903599 14903659 61 ENSPREG00000022808
## 6 6.442510e-05 0.7193775 14903599 14903659 61 ENSPREG00000022867
## 8 9.082882e-05 0.7193775 2481310 2481355 46 ENSPREG00000011064
## gene_biotype gene_name
## 1 protein_coding <NA>
## 2 protein_coding btr30
## 3 protein_coding <NA>
## 5 protein_coding <NA>
## 6 protein_coding asb14a
## 8 protein_coding NFKB1RCircos.histogramV <- dplyr::select(CvGgeneschrdf,seqnames,start,end,pval)
head(RCircos.histogramV)## seqnames start end pval
## 1 LG13 18160946 18161700 4.013367e-05
## 2 LG8 27368425 27368499 4.118982e-05
## 3 LG8 27368425 27368499 4.118982e-05
## 5 LG5 2971274 2971545 6.442510e-05
## 6 LG5 2971274 2971545 6.442510e-05
## 8 LG10 32171882 32172301 9.082882e-05RCircos.histogramV$pval <- log(RCircos.histogramV$pval)
head(RCircos.histogramV)## seqnames start end pval
## 1 LG13 18160946 18161700 -10.123295
## 2 LG8 27368425 27368499 -10.097320
## 3 LG8 27368425 27368499 -10.097320
## 5 LG5 2971274 2971545 -9.650007
## 6 LG5 2971274 2971545 -9.650007
## 8 LG10 32171882 32172301 -9.306534colnames(RCircos.histogramV) <- c("Chromosome","chromStart","chromEnd","Data")
head(RCircos.histogramV)## Chromosome chromStart chromEnd Data
## 1 LG13 18160946 18161700 -10.123295
## 2 LG8 27368425 27368499 -10.097320
## 3 LG8 27368425 27368499 -10.097320
## 5 LG5 2971274 2971545 -9.650007
## 6 LG5 2971274 2971545 -9.650007
## 8 LG10 32171882 32172301 -9.306534head(CvGgeneschrdf)## seqnames start end width strand L area beta stat
## 1 LG13 18160946 18161700 755 * 75 17.104340 0.4804793 12.35578
## 2 LG8 27368425 27368499 75 * 22 1.107603 -0.3598625 -12.34614
## 3 LG8 27368425 27368499 75 * 22 1.107603 -0.3598625 -12.34614
## 5 LG5 2971274 2971545 272 * 61 8.495669 0.3785743 11.65333
## 6 LG5 2971274 2971545 272 * 61 8.495669 0.3785743 11.65333
## 8 LG10 32171882 32172301 420 * 46 8.597024 0.4390605 11.17294
## pval qval index.start index.end index.width gene_id
## 1 4.013367e-05 0.7193775 4371608 4371682 75 ENSPREG00000001265
## 2 4.118982e-05 0.7193775 18010981 18011002 22 ENSPREG00000012374
## 3 4.118982e-05 0.7193775 18010981 18011002 22 ENSPREG00000012413
## 5 6.442510e-05 0.7193775 14903599 14903659 61 ENSPREG00000022808
## 6 6.442510e-05 0.7193775 14903599 14903659 61 ENSPREG00000022867
## 8 9.082882e-05 0.7193775 2481310 2481355 46 ENSPREG00000011064
## gene_biotype gene_name
## 1 protein_coding <NA>
## 2 protein_coding btr30
## 3 protein_coding <NA>
## 5 protein_coding <NA>
## 6 protein_coding asb14a
## 8 protein_coding NFKB1RCircos.heatmapV <- dplyr::select(CvGgeneschrdf,seqnames,start,end,gene_name,beta)
head(RCircos.heatmapV)## seqnames start end gene_name beta
## 1 LG13 18160946 18161700 <NA> 0.4804793
## 2 LG8 27368425 27368499 btr30 -0.3598625
## 3 LG8 27368425 27368499 <NA> -0.3598625
## 5 LG5 2971274 2971545 <NA> 0.3785743
## 6 LG5 2971274 2971545 asb14a 0.3785743
## 8 LG10 32171882 32172301 NFKB1 0.4390605colnames(RCircos.heatmapV) <- c("Chromosome","chromStart","chromEnd","GeneName","CvG")
head(RCircos.heatmapV)## Chromosome chromStart chromEnd GeneName CvG
## 1 LG13 18160946 18161700 <NA> 0.4804793
## 2 LG8 27368425 27368499 btr30 -0.3598625
## 3 LG8 27368425 27368499 <NA> -0.3598625
## 5 LG5 2971274 2971545 <NA> 0.3785743
## 6 LG5 2971274 2971545 asb14a 0.3785743
## 8 LG10 32171882 32172301 NFKB1 0.4390605data(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
CvLgeneschrdfdmrs <- head(CvLgeneschrdf,75)
head(CvLgeneschrdfdmrs)## seqnames start end width strand L area beta stat
## 1 LG19 10333007 10333692 686 * 71 16.559670 0.5767663 18.99209
## 3 LG13 22015858 22016352 495 * 82 14.226193 0.4397952 11.57442
## 6 LG8 18982718 18983377 660 * 60 7.212046 -0.3746378 -11.38354
## 7 LG11 14181818 14182182 365 * 58 4.745863 -0.3570840 -11.25378
## 8 LG14 4297874 4299069 1196 * 45 9.873079 -0.4990115 -10.64895
## 10 LG12 21371716 21372025 310 * 58 3.735525 -0.3274811 -10.48784
## pval qval index.start index.end index.width gene_id
## 1 9.999990e-07 0.1114369 8673138 8673208 71 ENSPREG00000002350
## 3 6.599993e-05 0.9103295 4374338 4374419 82 ENSPREG00000006590
## 6 7.399993e-05 0.9103295 17405986 17406045 60 ENSPREG00000011882
## 7 8.099992e-05 0.9103295 2836015 2836072 58 ENSPREG00000007449
## 8 1.209999e-04 0.9103295 4766186 4766230 45 ENSPREG00000009813
## 10 1.389999e-04 0.9103295 3729020 3729077 58 ENSPREG00000019970
## gene_biotype gene_name
## 1 protein_coding QRFPR
## 3 protein_coding ankrd13b
## 6 protein_coding rapgefl1
## 7 protein_coding <NA>
## 8 protein_coding rab34b
## 10 protein_coding <NA>Chr.Label.Data <- dplyr::select(CvLgeneschrdfdmrs,seqnames,start,end,gene_name)
colnames(Chr.Label.Data) <- c("Chromosome","chromStart","chromEnd","GeneName")
head(Chr.Label.Data)## Chromosome chromStart chromEnd GeneName
## 1 LG19 10333007 10333692 QRFPR
## 3 LG13 22015858 22016352 ankrd13b
## 6 LG8 18982718 18983377 rapgefl1
## 7 LG11 14181818 14182182 <NA>
## 8 LG14 4297874 4299069 rab34b
## 10 LG12 21371716 21372025 <NA>Chr.Label.Data <- Chr.Label.Data[-which(Chr.Label.Data$GeneName == "" | is.na(Chr.Label.Data$GeneName)), ]
head(Chr.Label.Data, 10)## Chromosome chromStart chromEnd GeneName
## 1 LG19 10333007 10333692 QRFPR
## 3 LG13 22015858 22016352 ankrd13b
## 6 LG8 18982718 18983377 rapgefl1
## 8 LG14 4297874 4299069 rab34b
## 11 LG19 1188386 1188923 SHANK1
## 12 LG19 28150293 28151137 bhlha15
## 13 LG16 483733 484086 atp2c1
## 14 LG22 9760595 9760997 map4k5
## 15 LG1 31411882 31412386 bnc2
## 17 LG1 5775276 5777164 fam20clhead(CvLgeneschrdf)## seqnames start end width strand L area beta stat
## 1 LG19 10333007 10333692 686 * 71 16.559670 0.5767663 18.99209
## 3 LG13 22015858 22016352 495 * 82 14.226193 0.4397952 11.57442
## 6 LG8 18982718 18983377 660 * 60 7.212046 -0.3746378 -11.38354
## 7 LG11 14181818 14182182 365 * 58 4.745863 -0.3570840 -11.25378
## 8 LG14 4297874 4299069 1196 * 45 9.873079 -0.4990115 -10.64895
## 10 LG12 21371716 21372025 310 * 58 3.735525 -0.3274811 -10.48784
## pval qval index.start index.end index.width gene_id
## 1 9.999990e-07 0.1114369 8673138 8673208 71 ENSPREG00000002350
## 3 6.599993e-05 0.9103295 4374338 4374419 82 ENSPREG00000006590
## 6 7.399993e-05 0.9103295 17405986 17406045 60 ENSPREG00000011882
## 7 8.099992e-05 0.9103295 2836015 2836072 58 ENSPREG00000007449
## 8 1.209999e-04 0.9103295 4766186 4766230 45 ENSPREG00000009813
## 10 1.389999e-04 0.9103295 3729020 3729077 58 ENSPREG00000019970
## gene_biotype gene_name
## 1 protein_coding QRFPR
## 3 protein_coding ankrd13b
## 6 protein_coding rapgefl1
## 7 protein_coding <NA>
## 8 protein_coding rab34b
## 10 protein_coding <NA>RCircos.histogramV <- dplyr::select(CvLgeneschrdf,seqnames,start,end,pval)
head(RCircos.histogramV)## seqnames start end pval
## 1 LG19 10333007 10333692 9.999990e-07
## 3 LG13 22015858 22016352 6.599993e-05
## 6 LG8 18982718 18983377 7.399993e-05
## 7 LG11 14181818 14182182 8.099992e-05
## 8 LG14 4297874 4299069 1.209999e-04
## 10 LG12 21371716 21372025 1.389999e-04RCircos.histogramV$pval <- log(RCircos.histogramV$pval)
head(RCircos.histogramV)## seqnames start end pval
## 1 LG19 10333007 10333692 -13.815512
## 3 LG13 22015858 22016352 -9.625857
## 6 LG8 18982718 18983377 -9.511446
## 7 LG11 14181818 14182182 -9.421062
## 8 LG14 4297874 4299069 -9.019721
## 10 LG12 21371716 21372025 -8.881038colnames(RCircos.histogramV) <- c("Chromosome","chromStart","chromEnd","Data")
head(RCircos.histogramV)## Chromosome chromStart chromEnd Data
## 1 LG19 10333007 10333692 -13.815512
## 3 LG13 22015858 22016352 -9.625857
## 6 LG8 18982718 18983377 -9.511446
## 7 LG11 14181818 14182182 -9.421062
## 8 LG14 4297874 4299069 -9.019721
## 10 LG12 21371716 21372025 -8.881038head(CvLgeneschrdf)## seqnames start end width strand L area beta stat
## 1 LG19 10333007 10333692 686 * 71 16.559670 0.5767663 18.99209
## 3 LG13 22015858 22016352 495 * 82 14.226193 0.4397952 11.57442
## 6 LG8 18982718 18983377 660 * 60 7.212046 -0.3746378 -11.38354
## 7 LG11 14181818 14182182 365 * 58 4.745863 -0.3570840 -11.25378
## 8 LG14 4297874 4299069 1196 * 45 9.873079 -0.4990115 -10.64895
## 10 LG12 21371716 21372025 310 * 58 3.735525 -0.3274811 -10.48784
## pval qval index.start index.end index.width gene_id
## 1 9.999990e-07 0.1114369 8673138 8673208 71 ENSPREG00000002350
## 3 6.599993e-05 0.9103295 4374338 4374419 82 ENSPREG00000006590
## 6 7.399993e-05 0.9103295 17405986 17406045 60 ENSPREG00000011882
## 7 8.099992e-05 0.9103295 2836015 2836072 58 ENSPREG00000007449
## 8 1.209999e-04 0.9103295 4766186 4766230 45 ENSPREG00000009813
## 10 1.389999e-04 0.9103295 3729020 3729077 58 ENSPREG00000019970
## gene_biotype gene_name
## 1 protein_coding QRFPR
## 3 protein_coding ankrd13b
## 6 protein_coding rapgefl1
## 7 protein_coding <NA>
## 8 protein_coding rab34b
## 10 protein_coding <NA>RCircos.heatmapV <- dplyr::select(CvLgeneschrdf,seqnames,start,end,gene_name,beta)
head(RCircos.heatmapV)## seqnames start end gene_name beta
## 1 LG19 10333007 10333692 QRFPR 0.5767663
## 3 LG13 22015858 22016352 ankrd13b 0.4397952
## 6 LG8 18982718 18983377 rapgefl1 -0.3746378
## 7 LG11 14181818 14182182 <NA> -0.3570840
## 8 LG14 4297874 4299069 rab34b -0.4990115
## 10 LG12 21371716 21372025 <NA> -0.3274811colnames(RCircos.heatmapV) <- c("Chromosome","chromStart","chromEnd","GeneName","CvG")
head(RCircos.heatmapV)## Chromosome chromStart chromEnd GeneName CvG
## 1 LG19 10333007 10333692 QRFPR 0.5767663
## 3 LG13 22015858 22016352 ankrd13b 0.4397952
## 6 LG8 18982718 18983377 rapgefl1 -0.3746378
## 7 LG11 14181818 14182182 <NA> -0.3570840
## 8 LG14 4297874 4299069 rab34b -0.4990115
## 10 LG12 21371716 21372025 <NA> -0.3274811RCircos.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
CvLgeneschrdfdmrs <- head(GvLgeneschrdf,75)
head(CvLgeneschrdfdmrs)## seqnames start end width strand L area beta stat
## 1 LG11 28461237 28461741 505 * 108 11.636971 -0.2773737 -16.27500
## 4 LG2 28494008 28495445 1438 * 65 9.709663 0.4626823 12.85427
## 5 LG13 18160946 18161831 886 * 95 16.311864 -0.3970642 -12.75740
## 7 LG11 10041760 10042135 376 * 75 6.666626 0.3701602 12.64751
## 9 LG5 2971274 2971545 272 * 58 7.527239 -0.3990748 -12.02408
## 10 LG5 2971274 2971545 272 * 58 7.527239 -0.3990748 -12.02408
## pval qval index.start index.end index.width gene_id
## 1 7.144039e-06 0.6538511 3678849 3678956 108 ENSPREG00000010167
## 4 5.477097e-05 0.7492043 11413014 11413078 65 ENSPREG00000001027
## 5 5.596164e-05 0.7492043 4929871 4929965 95 ENSPREG00000001265
## 7 6.548703e-05 0.7492043 3123427 3123501 75 ENSPREG00000021580
## 9 9.287251e-05 0.7879743 16775120 16775177 58 ENSPREG00000022808
## 10 9.287251e-05 0.7879743 16775120 16775177 58 ENSPREG00000022867
## gene_biotype gene_name
## 1 protein_coding ncdn
## 4 protein_coding casq2
## 5 protein_coding <NA>
## 7 protein_coding jazf1a
## 9 protein_coding <NA>
## 10 protein_coding asb14aChr.Label.Data <- dplyr::select(CvLgeneschrdfdmrs,seqnames,start,end,gene_name)
colnames(Chr.Label.Data) <- c("Chromosome","chromStart","chromEnd","GeneName")
head(Chr.Label.Data)## Chromosome chromStart chromEnd GeneName
## 1 LG11 28461237 28461741 ncdn
## 4 LG2 28494008 28495445 casq2
## 5 LG13 18160946 18161831 <NA>
## 7 LG11 10041760 10042135 jazf1a
## 9 LG5 2971274 2971545 <NA>
## 10 LG5 2971274 2971545 asb14aChr.Label.Data <- Chr.Label.Data[-which(Chr.Label.Data$GeneName == "" | is.na(Chr.Label.Data$GeneName)), ]
head(Chr.Label.Data,10)## Chromosome chromStart chromEnd GeneName
## 1 LG11 28461237 28461741 ncdn
## 4 LG2 28494008 28495445 casq2
## 7 LG11 10041760 10042135 jazf1a
## 10 LG5 2971274 2971545 asb14a
## 15 LG5 19662076 19662488 dlgap4b
## 16 LG3 31400775 31402677 shank2a
## 17 LG2 45915064 45915398 mstnb
## 18 LG3 9883425 9885124 scg3
## 19 LG4 19716877 19717452 ppat
## 20 LG4 19716877 19717452 paicshead(GvLgeneschrdf)## seqnames start end width strand L area beta stat
## 1 LG11 28461237 28461741 505 * 108 11.636971 -0.2773737 -16.27500
## 4 LG2 28494008 28495445 1438 * 65 9.709663 0.4626823 12.85427
## 5 LG13 18160946 18161831 886 * 95 16.311864 -0.3970642 -12.75740
## 7 LG11 10041760 10042135 376 * 75 6.666626 0.3701602 12.64751
## 9 LG5 2971274 2971545 272 * 58 7.527239 -0.3990748 -12.02408
## 10 LG5 2971274 2971545 272 * 58 7.527239 -0.3990748 -12.02408
## pval qval index.start index.end index.width gene_id
## 1 7.144039e-06 0.6538511 3678849 3678956 108 ENSPREG00000010167
## 4 5.477097e-05 0.7492043 11413014 11413078 65 ENSPREG00000001027
## 5 5.596164e-05 0.7492043 4929871 4929965 95 ENSPREG00000001265
## 7 6.548703e-05 0.7492043 3123427 3123501 75 ENSPREG00000021580
## 9 9.287251e-05 0.7879743 16775120 16775177 58 ENSPREG00000022808
## 10 9.287251e-05 0.7879743 16775120 16775177 58 ENSPREG00000022867
## gene_biotype gene_name
## 1 protein_coding ncdn
## 4 protein_coding casq2
## 5 protein_coding <NA>
## 7 protein_coding jazf1a
## 9 protein_coding <NA>
## 10 protein_coding asb14aRCircos.histogramV <- dplyr::select(GvLgeneschrdf,seqnames,start,end,pval)
head(RCircos.histogramV)## seqnames start end pval
## 1 LG11 28461237 28461741 7.144039e-06
## 4 LG2 28494008 28495445 5.477097e-05
## 5 LG13 18160946 18161831 5.596164e-05
## 7 LG11 10041760 10042135 6.548703e-05
## 9 LG5 2971274 2971545 9.287251e-05
## 10 LG5 2971274 2971545 9.287251e-05RCircos.histogramV$pval <- log(RCircos.histogramV$pval)
head(RCircos.histogramV)## seqnames start end pval
## 1 LG11 28461237 28461741 -11.849232
## 4 LG2 28494008 28495445 -9.812350
## 5 LG13 18160946 18161831 -9.790844
## 7 LG11 10041760 10042135 -9.633658
## 9 LG5 2971274 2971545 -9.284283
## 10 LG5 2971274 2971545 -9.284283colnames(RCircos.histogramV) <- c("Chromosome","chromStart","chromEnd","Data")
head(RCircos.histogramV)## Chromosome chromStart chromEnd Data
## 1 LG11 28461237 28461741 -11.849232
## 4 LG2 28494008 28495445 -9.812350
## 5 LG13 18160946 18161831 -9.790844
## 7 LG11 10041760 10042135 -9.633658
## 9 LG5 2971274 2971545 -9.284283
## 10 LG5 2971274 2971545 -9.284283head(GvLgeneschrdf)## seqnames start end width strand L area beta stat
## 1 LG11 28461237 28461741 505 * 108 11.636971 -0.2773737 -16.27500
## 4 LG2 28494008 28495445 1438 * 65 9.709663 0.4626823 12.85427
## 5 LG13 18160946 18161831 886 * 95 16.311864 -0.3970642 -12.75740
## 7 LG11 10041760 10042135 376 * 75 6.666626 0.3701602 12.64751
## 9 LG5 2971274 2971545 272 * 58 7.527239 -0.3990748 -12.02408
## 10 LG5 2971274 2971545 272 * 58 7.527239 -0.3990748 -12.02408
## pval qval index.start index.end index.width gene_id
## 1 7.144039e-06 0.6538511 3678849 3678956 108 ENSPREG00000010167
## 4 5.477097e-05 0.7492043 11413014 11413078 65 ENSPREG00000001027
## 5 5.596164e-05 0.7492043 4929871 4929965 95 ENSPREG00000001265
## 7 6.548703e-05 0.7492043 3123427 3123501 75 ENSPREG00000021580
## 9 9.287251e-05 0.7879743 16775120 16775177 58 ENSPREG00000022808
## 10 9.287251e-05 0.7879743 16775120 16775177 58 ENSPREG00000022867
## gene_biotype gene_name
## 1 protein_coding ncdn
## 4 protein_coding casq2
## 5 protein_coding <NA>
## 7 protein_coding jazf1a
## 9 protein_coding <NA>
## 10 protein_coding asb14aRCircos.heatmapV <- dplyr::select(GvLgeneschrdf,seqnames,start,end,gene_name,beta)
head(RCircos.heatmapV)## seqnames start end gene_name beta
## 1 LG11 28461237 28461741 ncdn -0.2773737
## 4 LG2 28494008 28495445 casq2 0.4626823
## 5 LG13 18160946 18161831 <NA> -0.3970642
## 7 LG11 10041760 10042135 jazf1a 0.3701602
## 9 LG5 2971274 2971545 <NA> -0.3990748
## 10 LG5 2971274 2971545 asb14a -0.3990748colnames(RCircos.heatmapV) <- c("Chromosome","chromStart","chromEnd","GeneName","CvG")
head(RCircos.heatmapV)## Chromosome chromStart chromEnd GeneName CvG
## 1 LG11 28461237 28461741 ncdn -0.2773737
## 4 LG2 28494008 28495445 casq2 0.4626823
## 5 LG13 18160946 18161831 <NA> -0.3970642
## 7 LG11 10041760 10042135 jazf1a 0.3701602
## 9 LG5 2971274 2971545 <NA> -0.3990748
## 10 LG5 2971274 2971545 asb14a -0.3990748RCircos.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 DMRs
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)
dmrplots <- function(dmr){
dmrseqname <- dmr[1]
dmrstart <- dmr[2]
dmrend <- dmr[3]
gene_name <- dmr[17]
Foundationsub <- Foundation[which( Foundation$V1==dmrseqname & Foundation$V2>dmrstart & Foundation$V3<dmrend ),4]
ClearR1sub <- ClearR1[which( ClearR1$V1==dmrseqname & ClearR1$V2>dmrstart & ClearR1$V3<dmrend ),4]
ClearR2sub <- ClearR2[which( ClearR2$V1==dmrseqname & ClearR2$V2>dmrstart & ClearR2$V3<dmrend ),4]
ClearR3sub <- ClearR3[which( ClearR3$V1==dmrseqname & ClearR3$V2>dmrstart & ClearR3$V3<dmrend ),4]
GreenR1sub <- GreenR1[which( GreenR1$V1==dmrseqname & GreenR1$V2>dmrstart & GreenR1$V3<dmrend ),4]
GreenR2sub <- GreenR2[which( GreenR2$V1==dmrseqname & GreenR2$V2>dmrstart & GreenR2$V3<dmrend ),4]
GreenR3sub <- GreenR3[which( GreenR3$V1==dmrseqname & GreenR3$V2>dmrstart & GreenR3$V3<dmrend ),4]
LilacR1sub <- LilacR1[which( LilacR1$V1==dmrseqname & LilacR1$V2>dmrstart & LilacR1$V3<dmrend ),4]
LilacR2sub <- LilacR2[which( LilacR2$V1==dmrseqname & LilacR2$V2>dmrstart & LilacR2$V3<dmrend ),4]
LilacR3sub <- LilacR3[which( LilacR3$V1==dmrseqname & LilacR3$V2>dmrstart & LilacR3$V3<dmrend ),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(dmrseqname,dmrstart,dmrend,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 <- CvGgeneschrdf[1,,drop=TRUE]
# dmrplots(dmr)
# with lapply
lapply(X=1:10, function(i) {
dmr <- CvGgeneschrdf[i,,drop=TRUE]
dmrplots(dmr)
})
## [[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)
dmrplots <- function(dmr){
dmrseqname <- dmr[1]
dmrstart <- dmr[2]
dmrend <- dmr[3]
gene_name <- dmr[17]
Foundationsub <- Foundation[which( Foundation$V1==dmrseqname & Foundation$V2>dmrstart & Foundation$V3<dmrend ),4]
ClearR1sub <- ClearR1[which( ClearR1$V1==dmrseqname & ClearR1$V2>dmrstart & ClearR1$V3<dmrend ),4]
ClearR2sub <- ClearR2[which( ClearR2$V1==dmrseqname & ClearR2$V2>dmrstart & ClearR2$V3<dmrend ),4]
ClearR3sub <- ClearR3[which( ClearR3$V1==dmrseqname & ClearR3$V2>dmrstart & ClearR3$V3<dmrend ),4]
GreenR1sub <- GreenR1[which( GreenR1$V1==dmrseqname & GreenR1$V2>dmrstart & GreenR1$V3<dmrend ),4]
GreenR2sub <- GreenR2[which( GreenR2$V1==dmrseqname & GreenR2$V2>dmrstart & GreenR2$V3<dmrend ),4]
GreenR3sub <- GreenR3[which( GreenR3$V1==dmrseqname & GreenR3$V2>dmrstart & GreenR3$V3<dmrend ),4]
LilacR1sub <- LilacR1[which( LilacR1$V1==dmrseqname & LilacR1$V2>dmrstart & LilacR1$V3<dmrend ),4]
LilacR2sub <- LilacR2[which( LilacR2$V1==dmrseqname & LilacR2$V2>dmrstart & LilacR2$V3<dmrend ),4]
LilacR3sub <- LilacR3[which( LilacR3$V1==dmrseqname & LilacR3$V2>dmrstart & LilacR3$V3<dmrend ),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(dmrseqname,dmrstart,dmrend,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 <- CvLgeneschrdf[1,,drop=TRUE]
# dmrplots(dmr)
# with lapply
lapply(X=1:10, function(i) {
dmr <- CvLgeneschrdf[i,,drop=TRUE]
dmrplots(dmr)
})
## [[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)
dmrplots <- function(dmr){
dmrseqname <- dmr[1]
dmrstart <- dmr[2]
dmrend <- dmr[3]
gene_name <- dmr[17]
Foundationsub <- Foundation[which( Foundation$V1==dmrseqname & Foundation$V2>dmrstart & Foundation$V3<dmrend ),4]
ClearR1sub <- ClearR1[which( ClearR1$V1==dmrseqname & ClearR1$V2>dmrstart & ClearR1$V3<dmrend ),4]
ClearR2sub <- ClearR2[which( ClearR2$V1==dmrseqname & ClearR2$V2>dmrstart & ClearR2$V3<dmrend ),4]
ClearR3sub <- ClearR3[which( ClearR3$V1==dmrseqname & ClearR3$V2>dmrstart & ClearR3$V3<dmrend ),4]
GreenR1sub <- GreenR1[which( GreenR1$V1==dmrseqname & GreenR1$V2>dmrstart & GreenR1$V3<dmrend ),4]
GreenR2sub <- GreenR2[which( GreenR2$V1==dmrseqname & GreenR2$V2>dmrstart & GreenR2$V3<dmrend ),4]
GreenR3sub <- GreenR3[which( GreenR3$V1==dmrseqname & GreenR3$V2>dmrstart & GreenR3$V3<dmrend ),4]
LilacR1sub <- LilacR1[which( LilacR1$V1==dmrseqname & LilacR1$V2>dmrstart & LilacR1$V3<dmrend ),4]
LilacR2sub <- LilacR2[which( LilacR2$V1==dmrseqname & LilacR2$V2>dmrstart & LilacR2$V3<dmrend ),4]
LilacR3sub <- LilacR3[which( LilacR3$V1==dmrseqname & LilacR3$V2>dmrstart & LilacR3$V3<dmrend ),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(dmrseqname,dmrstart,dmrend,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) {
dmr <- GvLgeneschrdf[i,,drop=TRUE]
dmrplots(dmr)
})
## [[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,] 11.5Session 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 data.table_1.14.0 dplyr_1.0.7
## [7] RCircos_1.2.1 BiocManager_1.30.16 GenomicFeatures_1.44.2
## [10] AnnotationDbi_1.54.1 Biobase_2.52.0 GenomicRanges_1.44.0
## [13] GenomeInfoDb_1.28.4 IRanges_2.26.0 S4Vectors_0.30.0
## [16] BiocGenerics_0.38.0
##
## loaded via a namespace (and not attached):
## [1] MatrixGenerics_1.4.3 httr_1.4.2
## [3] sass_0.4.0 bit64_4.0.5
## [5] jsonlite_1.7.2 bslib_0.3.0
## [7] assertthat_0.2.1 highr_0.9
## [9] BiocFileCache_2.0.0 blob_1.2.2
## [11] GenomeInfoDbData_1.2.6 Rsamtools_2.8.0
## [13] yaml_2.2.1 progress_1.2.2
## [15] pillar_1.6.2 RSQLite_2.2.8
## [17] lattice_0.20-45 glue_1.4.2
## [19] digest_0.6.27 XVector_0.32.0
## [21] htmltools_0.5.2 Matrix_1.3-4
## [23] XML_3.99-0.7 pkgconfig_2.0.3
## [25] biomaRt_2.48.3 zlibbioc_1.38.0
## [27] purrr_0.3.4 BiocParallel_1.26.2
## [29] tibble_3.1.4 KEGGREST_1.32.0
## [31] generics_0.1.0 ellipsis_0.3.2
## [33] cachem_1.0.6 SummarizedExperiment_1.22.0
## [35] magrittr_2.0.1 crayon_1.4.1
## [37] memoise_2.0.0 evaluate_0.14
## [39] fansi_0.5.0 xml2_1.3.2
## [41] tools_4.1.1 prettyunits_1.1.1
## [43] hms_1.1.0 BiocIO_1.2.0
## [45] lifecycle_1.0.0 matrixStats_0.60.1
## [47] stringr_1.4.0 DelayedArray_0.18.0
## [49] Biostrings_2.60.2 compiler_4.1.1
## [51] jquerylib_0.1.4 rlang_0.4.11
## [53] grid_4.1.1 RCurl_1.98-1.4
## [55] rjson_0.2.20 rappdirs_0.3.3
## [57] bitops_1.0-7 rmarkdown_2.11
## [59] restfulr_0.0.13 DBI_1.1.1
## [61] curl_4.3.2 R6_2.5.1
## [63] GenomicAlignments_1.28.0 knitr_1.34
## [65] rtracklayer_1.52.1 fastmap_1.1.0
## [67] bit_4.0.4 utf8_1.2.2
## [69] filelock_1.0.2 stringi_1.7.4
## [71] Rcpp_1.0.7 vctrs_0.3.8
## [73] png_0.1-7 dbplyr_2.1.1
## [75] tidyselect_1.1.1 xfun_0.26