Identifying active genes for subsequent analysis
We calculate zFPKM for existing FPKM from gse94802.
library(dplyr)
library(GEOquery)
library(stringr)
library(SummarizedExperiment)
library(tidyr)
getSpecificGEOSupp <- function(url) {
temp <- tempfile()
download.file(url, temp)
out <- read.csv(gzfile(temp), row.names=1, check.names=FALSE)
out <- select(out, -MGI_Symbol)
return(out)
}
gse94802_fpkm <- "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE94nnn/GSE94802/suppl/GSE94802_Minkina_etal_normalized_FPKM.csv.gz"
gse94802_counts <- "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE94nnn/GSE94802/suppl/GSE94802_Minkina_etal_raw_counts.csv.gz"
if (file.exists("gse94802.rds")) {
esetlist <- readRDS("gse94802.rds")
} else {
esetlist <- getGEO("gse94802")
}
doe <- pData(esetlist[[1]])
colData <- DataFrame(
condition=ifelse(str_detect(doe$title, regex("control", ignore_case=TRUE)), "control", "mutant"),
sample_id=str_match(doe$title, "rep\\d_(.+)")[, 2],
row.names=str_match(doe$title, "rep\\d_(.+)")[, 2])
se <- SummarizedExperiment(assays=SimpleList(fpkm=getSpecificGEOSupp(gse94802_fpkm),
counts=getSpecificGEOSupp(gse94802_counts)),
colData=colData)
# clear namespace
rm(esetlist, gse94802_fpkm, gse94802_counts, doe, colData, getSpecificGEOSupp)We compute zFPKM.
We can also plot the Guassian fit to the FPKM data for which the z-scores are based.
To determine which genes are active, we compute the median expression within each group.
activeGenes <- assay(se, "zfpkm") %>%
mutate(gene=rownames(assay(se, "zfpkm"))) %>%
gather(sample_id, zfpkm, -gene) %>%
left_join(select(as.data.frame(colData(se)), sample_id, condition), by="sample_id") %>%
group_by(gene, condition) %>%
summarize(median_zfpkm=median(zfpkm)) %>%
ungroup() %>%
mutate(active=(median_zfpkm > -3)) %>%
filter(active) %>%
select(gene) %>%
distinct()
seActive <- SummarizedExperiment(
assays=SimpleList(counts=as.matrix(assay(se, "counts")[activeGenes$gene, ])),
colData=colData(se))In the following DE analysis, we only use genes that were active in either group.
library(limma)
library(edgeR)
# Generate normalized log2CPM from counts AFTER we filter for protein-coding
# genes that are detectably expressed.
dge <- DGEList(counts=assay(seActive, "counts"))
dge <- calcNormFactors(dge)
design <- model.matrix(~ 0 + condition, data=colData(seActive))
vq <- voomWithQualityWeights(dge, design, plot=TRUE)
fit <- lmFit(vq, design)
contrastMatrix <- makeContrasts(conditioncontrol - conditionmutant, levels=design)
fit <- contrasts.fit(fit, contrastMatrix)
fit <- eBayes(fit, robust=TRUE)
deGenes <- topTable(fit, number=Inf)References
Hart T, Komori HK, LaMere S, Podshivalova K, Salomon DR. Finding the active genes in deep RNA-seq gene expression studies. BMC Genomics. 2013 Nov 11;14:778. doi: 10.1186/1471-2164-14-778.
## R version 4.0.3 (2020-10-10)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 18.04.5 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.12-bioc/R/lib/libRblas.so
## LAPACK: /home/biocbuild/bbs-3.12-bioc/R/lib/libRlapack.so
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_US.UTF-8 LC_COLLATE=C
## [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
##
## attached base packages:
## [1] stats4 parallel stats graphics grDevices utils datasets
## [8] methods base
##
## other attached packages:
## [1] edgeR_3.32.0 limma_3.46.0
## [3] zFPKM_1.12.0 tidyr_1.1.2
## [5] SummarizedExperiment_1.20.0 GenomicRanges_1.42.0
## [7] GenomeInfoDb_1.26.0 IRanges_2.24.0
## [9] S4Vectors_0.28.0 MatrixGenerics_1.2.0
## [11] matrixStats_0.57.0 stringr_1.4.0
## [13] GEOquery_2.58.0 Biobase_2.50.0
## [15] BiocGenerics_0.36.0 dplyr_1.0.2
## [17] printr_0.1
##
## loaded via a namespace (and not attached):
## [1] statmod_1.4.35 locfit_1.5-9.4 tidyselect_1.1.0
## [4] xfun_0.18 purrr_0.3.4 lattice_0.20-41
## [7] colorspace_1.4-1 vctrs_0.3.4 generics_0.0.2
## [10] htmltools_0.5.0 yaml_2.2.1 rlang_0.4.8
## [13] pillar_1.4.6 glue_1.4.2 GenomeInfoDbData_1.2.4
## [16] lifecycle_0.2.0 zlibbioc_1.36.0 munsell_0.5.0
## [19] gtable_0.3.0 evaluate_0.14 labeling_0.4.2
## [22] knitr_1.30 Rcpp_1.0.5 readr_1.4.0
## [25] backports_1.1.10 scales_1.1.1 checkmate_2.0.0
## [28] DelayedArray_0.16.0 XVector_0.30.0 farver_2.0.3
## [31] ggplot2_3.3.2 hms_0.5.3 digest_0.6.27
## [34] stringi_1.5.3 grid_4.0.3 tools_4.0.3
## [37] bitops_1.0-6 magrittr_1.5 RCurl_1.98-1.2
## [40] tibble_3.0.4 crayon_1.3.4 pkgconfig_2.0.3
## [43] ellipsis_0.3.1 Matrix_1.2-18 xml2_1.3.2
## [46] rmarkdown_2.5 R6_2.4.1 compiler_4.0.3