miR Enrichment
Burnet Bioinformatics
2024-06-20
Source: https://github.com/markziemann/miR-enrichment
Introduction
The predicted targets of microRNAs are used in functional enrichment analysis to justify the potential function of microRNAs, but there are some logical problems with this. In a biological tissue, not all of these targets will be expressed. Also the enrichment analysis requires a background list which is all the genes that can be measured. Not all genes are expressed in a tissue, at least half are silenced, so each enrichment analysis requires a custom background gene list. Unfortunately a custom background list is rarely used. We argue that this causes a dramatic distortion to the results.
Sample sheet
GSE188236
Control mRNA: SRR16776697, SRR16776698, SRR16776699, SRR16776700, SRR16776701
Case mRNA: SRR16776702, SRR16776703, SRR16776704, SRR16776705, SRR16776706
Methods
suppressPackageStartupMessages({
library("DESeq2")
library("gplots")
library("mitch")
library("eulerr")
library("getDEE2")
library("kableExtra")
})Import read counts
Importing RNA-seq data
myfiles <-list.files(".",pattern="ke.tsv",recursive=TRUE)
x <- lapply(myfiles,function(x) {
xx <- read.table(x,header=TRUE,row.names=1)
xx[,3,drop=FALSE]
})
x <- do.call(cbind,x)
colnames(x) <- gsub("_est_counts","",colnames(x))Need gene symbols to map to the transcripts.
mdat <- getDEE2Metadata("hsapiens")
d <- getDEE2(species="hsapiens",SRRvec="SRR11509477",mdat,outfile="NULL",counts="GeneCounts",legacy=TRUE)## For more information about DEE2 QC metrics, visit
## https://github.com/markziemann/dee2/blob/master/qc/qc_metrics.mdhead(d$TxInfo)## GeneID GeneSymbol TxLength
## ENST00000434970.2 ENSG00000237235.2 TRDD2 9
## ENST00000448914.1 ENSG00000228985.1 TRDD3 13
## ENST00000415118.1 ENSG00000223997.1 TRDD1 8
## ENST00000631435.1 ENSG00000282253.1 AC239618.6 12
## ENST00000632684.1 ENSG00000282431.1 AC245427.8 12
## ENST00000454908.1 ENSG00000236170.1 IGHD1-1 17txinfo <- d$TxInfoMerge txinfo.
xm <- merge(x,txinfo,by=0)
xm$GeneID_symbol <- paste(xm$GeneID,xm$GeneSymbol)
xm$Row.names = xm$GeneID = xm$GeneSymbol = xm$TxLength = NULL
xa <- aggregate(. ~ GeneID_symbol,xm,sum)
rownames(xa) <- xa[,1]
xa[,1] = NULLDifferential expression
xaf <- xa[which(rowMeans(xa)>=10),]
dim(xa) ; dim(xaf)## [1] 39297 10## [1] 16154 10ss <- data.frame("run"=colnames(xaf),"trt"=c(0,0,0,0,0,1,1,1,1,1))
rownames(ss) <- ss$run
mds <- cmdscale(dist(t(xaf)))
plot(mds,cex=2,col="gray",pch=19)
text(mds, labels=rownames(mds) ,col="black")
colSums(xaf)## SRR16776697 SRR16776698 SRR16776699 SRR16776700 SRR16776701 SRR16776702
## 20851813 15048854 16499348 23223668 18558851 17235920
## SRR16776703 SRR16776704 SRR16776705 SRR16776706
## 17302662 19596025 20248684 23226440dds <- DESeqDataSetFromMatrix(countData = round(xaf) , colData = ss , design = ~ trt )## converting counts to integer mode## the design formula contains one or more numeric variables with integer values,
## specifying a model with increasing fold change for higher values.
## did you mean for this to be a factor? if so, first convert
## this variable to a factor using the factor() functionres <- DESeq(dds)## estimating size factors## estimating dispersions## gene-wise dispersion estimates## mean-dispersion relationship## final dispersion estimates## fitting model and testingz <- results(res)
vsd <- vst(dds, blind=FALSE)
zz <- cbind(as.data.frame(z),assay(vsd))
dge <- as.data.frame(zz[order(zz$pvalue),])
head(dge)## baseMean log2FoldChange lfcSE stat
## ENSG00000175899.14 A2M 800.81446 -2.992388 0.3829692 -7.813650
## ENSG00000036448.9 MYOM2 42.80861 -3.863181 0.5497154 -7.027603
## ENSG00000155792.9 DEPTOR 54.00814 -1.328929 0.2253752 -5.896519
## ENSG00000140022.9 STON2 122.21686 -1.339664 0.2514313 -5.328152
## ENSG00000183230.16 CTNNA3 30.30637 -3.233864 0.6400371 -5.052620
## ENSG00000203805.10 PLPP4 16.28701 1.938232 0.3872831 5.004689
## pvalue padj SRR16776697 SRR16776698
## ENSG00000175899.14 A2M 5.555501e-15 8.948246e-11 10.107534 11.618025
## ENSG00000036448.9 MYOM2 2.101113e-12 1.692131e-08 7.546546 7.269915
## ENSG00000155792.9 DEPTOR 3.712498e-09 1.993240e-05 7.010804 7.120820
## ENSG00000140022.9 STON2 9.921700e-08 3.995221e-04 7.739233 8.009003
## ENSG00000183230.16 CTNNA3 4.357899e-07 1.403853e-03 7.055342 6.816519
## ENSG00000203805.10 PLPP4 5.595224e-07 1.502038e-03 5.440559 5.627143
## SRR16776699 SRR16776700 SRR16776701 SRR16776702
## ENSG00000175899.14 A2M 9.442345 9.713343 10.626583 7.158413
## ENSG00000036448.9 MYOM2 6.112004 6.541083 6.892428 5.063438
## ENSG00000155792.9 DEPTOR 6.556042 6.930972 6.982053 6.145468
## ENSG00000140022.9 STON2 6.966114 7.941694 8.069984 6.864357
## ENSG00000183230.16 CTNNA3 5.498888 6.443474 6.767443 5.420513
## ENSG00000203805.10 PLPP4 5.253353 5.219782 5.359617 6.095143
## SRR16776703 SRR16776704 SRR16776705 SRR16776706
## ENSG00000175899.14 A2M 7.528419 8.032977 7.955137 8.184869
## ENSG00000036448.9 MYOM2 5.357869 5.491584 5.523437 4.906753
## ENSG00000155792.9 DEPTOR 6.157142 6.255327 6.190020 6.106284
## ENSG00000140022.9 STON2 6.847433 6.816014 6.874447 6.747807
## ENSG00000183230.16 CTNNA3 5.413657 4.645806 5.604366 5.165596
## ENSG00000203805.10 PLPP4 6.057143 6.094705 5.952312 6.045172ups <- rownames(subset(dge,padj<0.05 & log2FoldChange>0))
dns <- rownames(subset(dge,padj<0.05 & log2FoldChange<0))
lapply(list("UPs"=ups,"DNs"=dns),length)## $UPs
## [1] 20
##
## $DNs
## [1] 35nrow(dge)## [1] 16154saveRDS(dge,file="GSE188236.Rds")Session information
For reproducibility.
sessionInfo()## R version 4.4.0 (2024-04-24)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 22.04.4 LTS
##
## Matrix products: default
## BLAS: /usr/lib/x86_64-linux-gnu/blas/libblas.so.3.10.0
## LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.10.0
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8
## [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8
## [7] LC_PAPER=en_US.UTF-8 LC_NAME=C
## [9] LC_ADDRESS=C LC_TELEPHONE=C
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
##
## time zone: Australia/Melbourne
## tzcode source: system (glibc)
##
## attached base packages:
## [1] stats4 stats graphics grDevices utils datasets methods
## [8] base
##
## other attached packages:
## [1] kableExtra_1.4.0 getDEE2_1.14.0
## [3] eulerr_7.0.2 mitch_1.16.0
## [5] gplots_3.1.3.1 DESeq2_1.44.0
## [7] SummarizedExperiment_1.34.0 Biobase_2.64.0
## [9] MatrixGenerics_1.16.0 matrixStats_1.3.0
## [11] GenomicRanges_1.56.0 GenomeInfoDb_1.40.0
## [13] IRanges_2.38.0 S4Vectors_0.42.0
## [15] BiocGenerics_0.50.0
##
## loaded via a namespace (and not attached):
## [1] tidyselect_1.2.1 viridisLite_0.4.2 dplyr_1.1.4
## [4] bitops_1.0-7 fastmap_1.2.0 GGally_2.2.1
## [7] promises_1.3.0 digest_0.6.35 mime_0.12
## [10] lifecycle_1.0.4 magrittr_2.0.3 compiler_4.4.0
## [13] rlang_1.1.4 sass_0.4.9 tools_4.4.0
## [16] utf8_1.2.4 yaml_2.3.8 knitr_1.47
## [19] S4Arrays_1.4.0 htmlwidgets_1.6.4 DelayedArray_0.30.1
## [22] xml2_1.3.6 plyr_1.8.9 RColorBrewer_1.1-3
## [25] abind_1.4-5 BiocParallel_1.38.0 KernSmooth_2.23-24
## [28] purrr_1.0.2 grid_4.4.0 fansi_1.0.6
## [31] caTools_1.18.2 xtable_1.8-4 colorspace_2.1-0
## [34] ggplot2_3.5.1 MASS_7.3-60.2 scales_1.3.0
## [37] gtools_3.9.5 cli_3.6.2 rmarkdown_2.27
## [40] crayon_1.5.2 generics_0.1.3 rstudioapi_0.16.0
## [43] reshape2_1.4.4 httr_1.4.7 cachem_1.1.0
## [46] stringr_1.5.1 zlibbioc_1.50.0 parallel_4.4.0
## [49] XVector_0.44.0 vctrs_0.6.5 Matrix_1.7-0
## [52] jsonlite_1.8.8 echarts4r_0.4.5 beeswarm_0.4.0
## [55] systemfonts_1.1.0 locfit_1.5-9.9 jquerylib_0.1.4
## [58] tidyr_1.3.1 glue_1.7.0 ggstats_0.6.0
## [61] codetools_0.2-20 stringi_1.8.4 gtable_0.3.5
## [64] later_1.3.2 UCSC.utils_1.0.0 htm2txt_2.2.2
## [67] munsell_0.5.1 tibble_3.2.1 pillar_1.9.0
## [70] htmltools_0.5.8.1 GenomeInfoDbData_1.2.12 R6_2.5.1
## [73] evaluate_0.23 shiny_1.8.1.1 lattice_0.22-6
## [76] highr_0.11 httpuv_1.6.15 bslib_0.7.0
## [79] Rcpp_1.0.12 svglite_2.1.3 gridExtra_2.3
## [82] SparseArray_1.4.3 xfun_0.44 pkgconfig_2.0.3