Entering edit mode
Hi there! I'm trying to perform gene ontology analysis comparing tumor and normal samples. There are about 250 and 350 differentially enriched peaks in the tumor and normal samples respectively.
However, there are 0 enriched terms found
when I performed the enrichGO()
function on the tumor and normal gene lists containing the respective entrez ID of the differentially enriched genes.
May I ask if anyone encountered a similar issue and if there are any ways to resolve this please?
Thank you!
samplefiles <- list.files("/path/diffbind_enriched_bed",
pattern= ".bed",
full.names=T)
samplefiles <- as.list(samplefiles)
names(samplefiles) <- c("Normal", "Tumor")
txdb <- TxDb.Hsapiens.UCSC.hg38.knownGene
peakAnnoList <- lapply(samplefiles,
annotatePeak,
TxDb=txdb,
tssRegion=c(-1000, 1000),
verbose=FALSE)
# ====================== Retrieve annotations ======================
normal_annot <- data.frame(peakAnnoList[["Normal"]]@anno)
tumor_annot <- data.frame(peakAnnoList[["Tumor"]]@anno)
# ====== Obtain the gene symbols from the annotations ======
entrez_normal <- normal_annot$geneId
annotations_edb_normal <- AnnotationDbi::select(EnsDb.Hsapiens.v86,
keys = entrez_normal,
columns = c("GENENAME"),
keytype = "ENTREZID")
normal_annot %>%
left_join(annotations_edb_normal, by=c("geneId"="ENTREZID")) %>%
write.table(file="results/chipseeker/Normal_peak_annotation.txt", sep="\t", quote=F, row.names=F)
entrez_tumor <- tumor_annot$geneId
annotations_edb_tumor <- AnnotationDbi::select(EnsDb.Hsapiens.v86,
keys = entrez_tumor,
columns = c("GENENAME"),
keytype = "ENTREZID")
annotations_edb_tumor$ENTREZID <- as.character(annotations_edb_tumor$ENTREZID)
tumor_annot %>%
left_join(annotations_edb_tumor, by=c("geneId"="ENTREZID")) %>%
write.table(file="results/chipseeker/Tumor_peak_annotation.txt", sep="\t", quote=F, row.names=F)
# ================================= GO enrichment analysis ==============================================
# Over-representation analysis
ego_normal <- enrichGO(gene = entrez_normal,
keyType = "ENTREZID",
OrgDb = org.Hs.eg.db,
ont = "BP",
pAdjustMethod = "BH",
qvalueCutoff = 0.05,
readable = TRUE)
> ego_normal
# over-representation test
#
#...@organism Homo sapiens
#...@ontology BP
#...@keytype ENTREZID
#...@gene chr [1:350] "54541" "2027" "79633" "5097" "81565" "54508" "7580" "5048" "494470" "143425" "124900546" "2274" ...
#...pvalues adjusted by 'BH' with cutoff <0.05
#...0 enriched terms found
#...Citation
T Wu, E Hu, S Xu, M Chen, P Guo, Z Dai, T Feng, L Zhou, W Tang, L Zhan, X Fu, S Liu, X Bo, and G Yu.
clusterProfiler 4.0: A universal enrichment tool for interpreting omics data.
The Innovation. 2021, 2(3):100141
ego_tumor <- enrichGO(gene = entrez_tumor,
keyType = "ENTREZID",
OrgDb = org.Hs.eg.db,
ont = "BP",
pAdjustMethod = "BH",
qvalueCutoff = 0.05,
readable = TRUE)
> ego_tumor
#
# over-representation test
#
#...@organism Homo sapiens
#...@ontology BP
#...@keytype ENTREZID
#...@gene chr [1:240] "9684" "587" "341" "340371" "439965" "2743" "387893" "29894" "57142" "8733" "4796" "10485" "8644" ...
#...pvalues adjusted by 'BH' with cutoff <0.05
#...0 enriched terms found
#...Citation
T Wu, E Hu, S Xu, M Chen, P Guo, Z Dai, T Feng, L Zhou, W Tang, L Zhan, X Fu, S Liu, X Bo, and G Yu.
clusterProfiler 4.0: A universal enrichment tool for interpreting omics data.
The Innovation. 2021, 2(3):100141
sessionInfo( )
R version 4.3.3 (2024-02-29)
Platform: aarch64-apple-darwin20 (64-bit)
Running under: macOS Sonoma 14.1.2
Matrix products: default
BLAS: /System/Library/Frameworks/Accelerate.framework/Versions/A/Frameworks/vecLib.framework/Versions/A/libBLAS.dylib
LAPACK: /Library/Frameworks/R.framework/Versions/4.3-arm64/Resources/lib/libRlapack.dylib; LAPACK version 3.11.0
locale:
[1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
tzcode source: internal
attached base packages:
[1] stats4 stats graphics grDevices utils datasets methods base
other attached packages:
[1] org.Hs.eg.db_3.18.0 dplyr_1.1.4
[3] ChIPseeker_1.38.0 clusterProfiler_4.10.1
[5] EnsDb.Hsapiens.v86_2.99.0 ensembldb_2.26.0
[7] AnnotationFilter_1.26.0 TxDb.Hsapiens.UCSC.hg38.knownGene_3.18.0
[9] GenomicFeatures_1.54.4 AnnotationDbi_1.64.1
[11] Biobase_2.62.0 GenomicRanges_1.54.1
[13] GenomeInfoDb_1.38.8 IRanges_2.36.0
[15] S4Vectors_0.40.2 BiocGenerics_0.48.1
loaded via a namespace (and not attached):
[1] splines_4.3.3 BiocIO_1.12.0
[3] ggplotify_0.1.2 bitops_1.0-7
[5] filelock_1.0.3 tibble_3.2.1
[7] polyclip_1.10-6 XML_3.99-0.16.1
[9] lifecycle_1.0.4 mixsqp_0.3-54
[11] lattice_0.22-6 MASS_7.3-60.0.1
[13] systemPipeR_2.8.0 magrittr_2.0.3
[15] limma_3.58.1 plotrix_3.8-4
[17] yaml_2.3.8 cowplot_1.1.3
[19] DBI_1.2.2 RColorBrewer_1.1-3
[21] abind_1.4-5 ShortRead_1.60.0
[23] zlibbioc_1.48.2 purrr_1.0.2
[25] ggraph_2.2.1 RCurl_1.98-1.14
[27] yulab.utils_0.1.4 tweenr_2.0.3
[29] rappdirs_0.3.3 GenomeInfoDbData_1.2.11
[31] enrichplot_1.22.0 ggrepel_0.9.5
[33] irlba_2.3.5.1 tidytree_0.4.6
[35] codetools_0.2-20 DelayedArray_0.28.0
[37] DOSE_3.28.2 xml2_1.3.6
[39] ggforce_0.4.2 tidyselect_1.2.1
[41] aplot_0.2.2 farver_2.1.1
[43] viridis_0.6.5 matrixStats_1.3.0
[45] BiocFileCache_2.10.2 jsonlite_1.8.8
[47] GenomicAlignments_1.38.2 tidygraph_1.3.1
[49] bbmle_1.0.25.1 tools_4.3.3
[51] progress_1.2.3 TxDb.Hsapiens.UCSC.hg19.knownGene_3.2.2
[53] treeio_1.26.0 Rcpp_1.0.12
[55] glue_1.7.0 gridExtra_2.3
[57] SparseArray_1.2.4 DESeq2_1.42.1
[59] qvalue_2.34.0 MatrixGenerics_1.14.0
[61] amap_0.8-19 withr_3.0.0
[63] numDeriv_2016.8-1.1 BiocManager_1.30.22
[65] fastmap_1.1.1 boot_1.3-30
[67] latticeExtra_0.6-30 fansi_1.0.6
[69] caTools_1.18.2 digest_0.6.35
[71] truncnorm_1.0-9 gridGraphics_0.5-1
[73] R6_2.5.1 colorspace_2.1-0
[75] GO.db_3.18.0 GreyListChIP_1.34.0
[77] gtools_3.9.5 jpeg_0.1-10
[79] biomaRt_2.58.2 RSQLite_2.3.6
[81] utf8_1.2.4 tidyr_1.3.1
[83] generics_0.1.3 data.table_1.15.4
[85] rtracklayer_1.62.0 graphlayouts_1.1.1
[87] prettyunits_1.2.0 httr_1.4.7
[89] htmlwidgets_1.6.4 S4Arrays_1.2.1
[91] scatterpie_0.2.2 pkgconfig_2.0.3
[93] gtable_0.3.4 blob_1.2.4
[95] hwriter_1.3.2.1 XVector_0.42.0
[97] shadowtext_0.1.3 htmltools_0.5.8.1
[99] fgsea_1.28.0 ProtGenerics_1.34.0
[101] scales_1.3.0 png_0.1-8
[103] ggfun_0.1.4 ashr_2.2-63
[105] rstudioapi_0.16.0 reshape2_1.4.4
[107] rjson_0.2.21 nlme_3.1-164
[109] coda_0.19-4.1 curl_5.2.1
[111] bdsmatrix_1.3-7 cachem_1.0.8
[113] stringr_1.5.1 KernSmooth_2.23-22
[115] parallel_4.3.3 HDO.db_0.99.1
[117] restfulr_0.0.15 apeglm_1.24.0
[119] pillar_1.9.0 grid_4.3.3
[121] vctrs_0.6.5 gplots_3.1.3.1
[123] dbplyr_2.5.0 invgamma_1.1
[125] mvtnorm_1.2-4 cli_3.6.2
[127] locfit_1.5-9.9 compiler_4.3.3
[129] Rsamtools_2.18.0 rlang_1.1.3
[131] crayon_1.5.2 SQUAREM_2021.1
[133] labeling_0.4.3 interp_1.1-6
[135] emdbook_1.3.13 plyr_1.8.9
[137] fs_1.6.3 stringi_1.8.3
[139] viridisLite_0.4.2 deldir_2.0-4
[141] BiocParallel_1.36.0 munsell_0.5.1
[143] Biostrings_2.70.3 lazyeval_0.2.2
[145] GOSemSim_2.28.1 Matrix_1.6-5
[147] BSgenome_1.70.2 patchwork_1.2.0
[149] hms_1.1.3 bit64_4.0.5
[151] ggplot2_3.5.0 KEGGREST_1.42.0
[153] statmod_1.5.0 SummarizedExperiment_1.32.0
[155] igraph_2.0.3 memoise_2.0.1
[157] ggtree_3.10.1 fastmatch_1.1-4
[159] DiffBind_3.12.0 bit_4.0.5
[161] gson_0.1.0 ape_5.8