Results from the univariate regressions performed using can be combined in a post-processing step to perform multivariate hypothesis testing. In this example, we fit on transcript-level counts and then perform multivariate hypothesis testing by combining transcripts at the gene-level. This is done with the function.
Read in transcript counts from the package.
library(readr)
library(tximport)
library(tximportData)
# specify directory
path <- system.file("extdata", package = "tximportData")
# read sample meta-data
samples <- read.table(file.path(path, "samples.txt"), header = TRUE)
samples.ext <- read.table(file.path(path, "samples_extended.txt"), header = TRUE, sep = "\t")
# read assignment of transcripts to genes
# remove genes on the PAR, since these are present twice
tx2gene <- read_csv(file.path(path, "tx2gene.gencode.v27.csv"))
tx2gene <- tx2gene[grep("PAR_Y", tx2gene$GENEID, invert = TRUE), ]
# read transcript-level quatifictions
files <- file.path(path, "salmon", samples$run, "quant.sf.gz")
txi <- tximport(files, type = "salmon", txOut = TRUE)
# Create metadata simulating two conditions
sampleTable <- data.frame(condition = factor(rep(c("A", "B"), each = 3)))
rownames(sampleTable) <- paste0("Sample", 1:6)Perform standard analysis at the transcript-level
library(variancePartition)
library(edgeR)
# Prepare transcript-level reads
dge <- DGEList(txi$counts)
design <- model.matrix(~condition, data = sampleTable)
isexpr <- filterByExpr(dge, design)
dge <- dge[isexpr, ]
dge <- calcNormFactors(dge)
# Estimate precision weights
vobj <- voomWithDreamWeights(dge, ~condition, sampleTable)
# Fit regression model one transcript at a time
fit <- dream(vobj, ~condition, sampleTable)
fit <- eBayes(fit)Combine the transcript-level results at the gene-level. The mapping between transcript and gene is stored in as a list.
# Prepare transcript to gene mapping
# keep only transcripts present in vobj
# then convert to list with key GENEID and values TXNAMEs
keep <- tx2gene$TXNAME %in% rownames(vobj)
tx2gene.lst <- unstack(tx2gene[keep, ])
# Run multivariate test on entries in each feature set
# Default method is "FE.empirical", but use "FE" here to reduce runtime
res <- mvTest(fit, vobj, tx2gene.lst, coef = "conditionB", method = "FE")
# truncate gene names since they have version numbers
# ENST00000498289.5 -> ENST00000498289
res$ID.short <- gsub("\\..+", "", res$ID)Perform gene set analysis using on the gene-level test statistics.
# must have zenith > v1.0.2
library(zenith)
library(GSEABase)
gs <- get_MSigDB("C1", to = "ENSEMBL")
df_gsa <- zenithPR_gsa(res$stat, res$ID.short, gs, inter.gene.cor = .05)
head(df_gsa)## NGenes Correlation delta se p.less p.greater PValue Direction
## chr7p13 28 0.05 7.1442404 2.034359 0.9997768 0.0002231723 0.0004463445 Up
## chr12q22 21 0.05 -1.2430448 2.168941 0.2832887 0.7167112635 0.5665774729 Down
## chr2q34 11 0.05 -0.2681142 2.595116 0.4588572 0.5411428235 0.9177143530 Down
## FDR Geneset coef
## chr7p13 0.001339034 chr7p13 zenithPR
## chr12q22 0.849866209 chr12q22 zenithPR
## chr2q34 0.917714353 chr2q34 zenithPR## R version 4.5.0 beta (2025-04-02 r88102)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 24.04.2 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.22-bioc/R/lib/libRblas.so
## LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.12.0 LAPACK version 3.12.0
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C LC_TIME=en_GB
## [4] LC_COLLATE=C LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8
## [7] LC_PAPER=en_US.UTF-8 LC_NAME=C LC_ADDRESS=C
## [10] LC_TELEPHONE=C 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 base
##
## other attached packages:
## [1] GSEABase_1.71.0 graph_1.87.0 annotate_1.87.0
## [4] XML_3.99-0.18 AnnotationDbi_1.71.0 IRanges_2.43.0
## [7] S4Vectors_0.47.0 Biobase_2.69.0 BiocGenerics_0.55.0
## [10] generics_0.1.3 zenith_1.11.0 tximportData_1.35.0
## [13] tximport_1.37.0 readr_2.1.5 edgeR_4.7.0
## [16] pander_0.6.6 variancePartition_1.39.0 BiocParallel_1.43.0
## [19] limma_3.65.0 ggplot2_3.5.2 knitr_1.50
##
## loaded via a namespace (and not attached):
## [1] jsonlite_2.0.0 magrittr_2.0.3 farver_2.1.2
## [4] nloptr_2.2.1 rmarkdown_2.29 vctrs_0.6.5
## [7] memoise_2.0.1 minqa_1.2.8 RCurl_1.98-1.17
## [10] progress_1.2.3 S4Arrays_1.9.0 htmltools_0.5.8.1
## [13] broom_1.0.8 SparseArray_1.9.0 sass_0.4.10
## [16] KernSmooth_2.23-26 bslib_0.9.0 pbkrtest_0.5.3
## [19] plyr_1.8.9 cachem_1.1.0 lifecycle_1.0.4
## [22] iterators_1.0.14 pkgconfig_2.0.3 Matrix_1.7-3
## [25] R6_2.6.1 fastmap_1.2.0 GenomeInfoDbData_1.2.14
## [28] rbibutils_2.3 MatrixGenerics_1.21.0 digest_0.6.37
## [31] numDeriv_2016.8-1.1 colorspace_2.1-1 GenomicRanges_1.61.0
## [34] RSQLite_2.3.9 labeling_0.4.3 abind_1.4-8
## [37] httr_1.4.7 compiler_4.5.0 bit64_4.6.0-1
## [40] aod_1.3.3 withr_3.0.2 backports_1.5.0
## [43] DBI_1.2.3 gplots_3.2.0 MASS_7.3-65
## [46] DelayedArray_0.35.0 corpcor_1.6.10 gtools_3.9.5
## [49] caTools_1.18.3 tools_4.5.0 msigdbr_10.0.2
## [52] remaCor_0.0.18 glue_1.8.0 nlme_3.1-168
## [55] grid_4.5.0 reshape2_1.4.4 snow_0.4-4
## [58] gtable_0.3.6 tzdb_0.5.0 tidyr_1.3.1
## [61] hms_1.1.3 XVector_0.49.0 pillar_1.10.2
## [64] stringr_1.5.1 babelgene_22.9 vroom_1.6.5
## [67] splines_4.5.0 dplyr_1.1.4 lattice_0.22-7
## [70] bit_4.6.0 tidyselect_1.2.1 locfit_1.5-9.12
## [73] Biostrings_2.77.0 reformulas_0.4.0 SummarizedExperiment_1.39.0
## [76] RhpcBLASctl_0.23-42 xfun_0.52 statmod_1.5.0
## [79] matrixStats_1.5.0 KEGGgraph_1.69.0 stringi_1.8.7
## [82] UCSC.utils_1.5.0 yaml_2.3.10 boot_1.3-31
## [85] evaluate_1.0.3 codetools_0.2-20 archive_1.1.12
## [88] tibble_3.2.1 Rgraphviz_2.53.0 cli_3.6.4
## [91] RcppParallel_5.1.10 xtable_1.8-4 Rdpack_2.6.4
## [94] munsell_0.5.1 jquerylib_0.1.4 Rcpp_1.0.14
## [97] GenomeInfoDb_1.45.0 zigg_0.0.2 EnvStats_3.0.0
## [100] png_0.1-8 Rfast_2.1.5.1 parallel_4.5.0
## [103] assertthat_0.2.1 blob_1.2.4 prettyunits_1.2.0
## [106] bitops_1.0-9 lme4_1.1-37 mvtnorm_1.3-3
## [109] lmerTest_3.1-3 scales_1.3.0 purrr_1.0.4
## [112] crayon_1.5.3 fANCOVA_0.6-1 rlang_1.1.6
## [115] EnrichmentBrowser_2.39.0 KEGGREST_1.49.0<>