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 4.4.0 beta (2024-04-15 r86425)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 22.04.4 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.19-bioc/R/lib/libRblas.so
## 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: America/New_York
## tzcode source: system (glibc)
##
## attached base packages:
## [1] stats4 stats graphics grDevices utils datasets methods
## [8] base
##
## other attached packages:
## [1] edgeR_4.2.0 limma_3.60.0
## [3] zFPKM_1.26.0 tidyr_1.3.1
## [5] SummarizedExperiment_1.34.0 GenomicRanges_1.56.0
## [7] GenomeInfoDb_1.40.0 IRanges_2.38.0
## [9] S4Vectors_0.42.0 MatrixGenerics_1.16.0
## [11] matrixStats_1.3.0 stringr_1.5.1
## [13] GEOquery_2.72.0 Biobase_2.64.0
## [15] BiocGenerics_0.50.0 dplyr_1.1.4
## [17] printr_0.3
##
## loaded via a namespace (and not attached):
## [1] gtable_0.3.5 ggplot2_3.5.1 xfun_0.43
## [4] bslib_0.7.0 lattice_0.22-6 tzdb_0.4.0
## [7] vctrs_0.6.5 tools_4.4.0 generics_0.1.3
## [10] tibble_3.2.1 fansi_1.0.6 highr_0.10
## [13] pkgconfig_2.0.3 Matrix_1.7-0 data.table_1.15.4
## [16] checkmate_2.3.1 lifecycle_1.0.4 GenomeInfoDbData_1.2.12
## [19] farver_2.1.1 compiler_4.4.0 munsell_0.5.1
## [22] statmod_1.5.0 htmltools_0.5.8.1 sass_0.4.9
## [25] yaml_2.3.8 pillar_1.9.0 crayon_1.5.2
## [28] jquerylib_0.1.4 cachem_1.0.8 DelayedArray_0.30.0
## [31] abind_1.4-5 locfit_1.5-9.9 tidyselect_1.2.1
## [34] digest_0.6.35 stringi_1.8.3 purrr_1.0.2
## [37] labeling_0.4.3 fastmap_1.1.1 grid_4.4.0
## [40] colorspace_2.1-0 cli_3.6.2 SparseArray_1.4.0
## [43] magrittr_2.0.3 S4Arrays_1.4.0 utf8_1.2.4
## [46] readr_2.1.5 withr_3.0.0 scales_1.3.0
## [49] backports_1.4.1 UCSC.utils_1.0.0 rmarkdown_2.26
## [52] XVector_0.44.0 httr_1.4.7 hms_1.1.3
## [55] evaluate_0.23 knitr_1.46 rlang_1.1.3
## [58] Rcpp_1.0.12 glue_1.7.0 xml2_1.3.6
## [61] jsonlite_1.8.8 R6_2.5.1 zlibbioc_1.50.0