GSEA annotation
Ehsan Razmara Monash Uni
22/03/2022
library(Seurat)## Registered S3 method overwritten by 'spatstat.geom':
## method from
## print.boxx cli## Attaching SeuratObjectlibrary(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──## ✓ ggplot2 3.3.5 ✓ purrr 0.3.4
## ✓ tibble 3.1.6 ✓ dplyr 1.0.7
## ✓ tidyr 1.2.0 ✓ stringr 1.4.0
## ✓ readr 2.1.2 ✓ forcats 0.5.1## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()library(GSVA)
library(msigdbr)
library(fgsea)
library(dplyr)
library(presto)## Loading required package: Rcpp## Loading required package: data.table##
## Attaching package: 'data.table'## The following objects are masked from 'package:dplyr':
##
## between, first, last## The following object is masked from 'package:purrr':
##
## transposelibrary(ggplot2)genesets <- msigdbr(species = "Mus musculus", category = "H") %>% dplyr::select("gs_name","gene_symbol") %>% as.data.frame()
genesets <- split(genesets$gene_symbol, genesets$gs_name)
head(genesets)## $HALLMARK_ADIPOGENESIS
## [1] "Abca1" "Abcb8" "Acaa2" "Acadl" "Acadm" "Acads"
## [7] "Acly" "Aco2" "Acox1" "Adcy6" "Adig" "Adipoq"
## [13] "Adipor2" "Agpat3" "Aifm1" "Ak2" "Aldh2" "Aldoa"
## [19] "Angpt1" "Angptl4" "Aplp2" "Apoe" "Araf" "Arl4a"
## [25] "Atl2" "Atp1b3" "Atp5o" "Baz2a" "Bckdha" "Bcl2l13"
## [31] "Bcl6" "C3" "Cat" "Cavin1" "Cavin2" "Ccng2"
## [37] "Cd151" "Cd302" "Cd36" "Cdkn2c" "Chchd10" "Chuk"
## [43] "Cidea" "Cmbl" "Cmpk1" "Col15a1" "Col4a1" "Coq3"
## [49] "Coq5" "Coq9" "Cox6a1" "Cox7b" "Cox8a" "Cpt2"
## [55] "Crat" "Cs" "Cyc1" "Cyp4b1" "Dbt" "Ddt"
## [61] "Decr1" "Dgat1" "Dhcr7" "Dhrs7" "Dhrs7b" "Dlat"
## [67] "Dld" "Dnajb9" "Dnajc15" "Dram2" "Ech1" "Echs1"
## [73] "Elmod3" "Elovl6" "Enpp2" "Ephx2" "Esrra" "Esyt1"
## [79] "Etfb" "Fabp4" "Fah" "Fzd4" "G3bp2" "Gadd45a"
## [85] "Gbe1" "Ghitm" "Gpam" "Gpat4" "Gpd2" "Gphn"
## [91] "Gpx3" "Gpx4" "Grpel1" "Hadh" "Hibch" "Hspb8"
## [97] "Idh1" "Idh3a" "Idh3g" "Ifngr1" "Immt" "Itga7"
## [103] "Itih5" "Itsn1" "Jagn1" "Lama4" "Lep" "Lifr"
## [109] "Lipe" "Lpcat3" "Lpl" "Ltc4s" "Map4k3" "Mccc1"
## [115] "Mdh2" "Me1" "Mgll" "Mgst3" "Miga2" "Mrap"
## [121] "Mrpl15" "Mtarc2" "Mtch2" "Mylk" "Nabp1" "Ndufa5"
## [127] "Ndufab1" "Ndufb7" "Ndufs3" "Nkiras1" "Nmt1" "Omd"
## [133] "Orm1" "Pdcd4" "Pemt" "Pex14" "Pfkfb3" "Pfkl"
## [139] "Pgm1" "Phldb1" "Phyh" "Pim3" "Plin2" "Por"
## [145] "Pparg" "Ppm1b" "Ppp1r15b" "Prdx3" "Preb" "Ptcd3"
## [151] "Ptger3" "Qdpr" "Rab34" "Reep5" "Reep6" "Retn"
## [157] "Retsat" "Riok3" "Rmdn3" "Rnf11" "Rreb1" "Rtn3"
## [163] "Samm50" "Scarb1" "Scp2" "Sdhb" "Sdhc" "Slc19a1"
## [169] "Slc1a5" "Slc25a1" "Slc25a10" "Slc27a1" "Slc5a6" "Pqlc3"
## [175] "Sncg" "Sod1" "Sorbs1" "Sowahc" "Sparcl1" "Sqor"
## [181] "Sspn" "Stat5a" "Stom" "Suclg1" "Sult1a1" "Taldo1"
## [187] "Tank" "Tkt" "Tob1" "Tst" "Ubc" "Ubqln1"
## [193] "Uck1" "Ucp2" "Uqcr10" "Uqcr11" "Uqcrc1" "Uqcrq"
## [199] "Vegfb" "Ywhag"
##
## $HALLMARK_ALLOGRAFT_REJECTION
## [1] "Aars" "Abce1" "Abi1" "Ache" "Acvr2a" "Akt1" "Apbb1"
## [8] "B2m" "Bcat1" "Bcl10" "Bcl3" "Brca1" "C2" "Capg"
## [15] "Cartpt" "Ccl11" "Ccl11" "Ccl2" "Ccl7" "Ccl19" "Ccl2"
## [22] "Ccl22" "Ccl4" "Ccl5" "Ccl7" "Ccnd2" "Ccnd3" "Ccr1"
## [29] "Ccr2" "Ccr5" "Cd1d1" "Cd2" "Cd247" "Cd28" "Cd3d"
## [36] "Cd3e" "Cd3g" "Cd4" "Cd40" "Cd40lg" "Cd47" "Cd7"
## [43] "Cd74" "Cd79a" "Cd80" "Cd86" "Cd8a" "Cd8b1" "Cd96"
## [50] "Cdkn2a" "Cfp" "Crtam" "Csf1" "Csk" "Ctss" "Cxcl13"
## [57] "Cxcl9" "Cxcr3" "Dars" "Degs1" "Dyrk3" "Egfr" "Eif3a"
## [64] "Eif3d" "Eif3j1" "Eif3j2" "Eif4g3" "Eif5a" "Elane" "Elf4"
## [71] "Ereg" "Ets1" "F2" "F2r" "Fas" "Fasl" "Fcgr2b"
## [78] "Fgr" "Flna" "Fyb" "Galnt1" "Gbp2" "Gcnt1" "Glmn"
## [85] "Gpr65" "Gzma" "Gzmb" "Hcls1" "Hdac9" "Hif1a" "H2-D1"
## [92] "H2-Q10" "H2-Q2" "H2-Q7" "H2-DMa" "H2-DMb1" "H2-DMb2" "H2-Oa"
## [99] "H2-Ob" "H2-Aa" "H2-Ea" "H2-T23" "H2-M3" "Icam1" "Icosl"
## [106] "Ifnar2" "Ifng" "Ifngr1" "Ifngr2" "Igsf6" "Ikbkb" "Il10"
## [113] "Il11" "Il12a" "Il12b" "Il12rb1" "Il13" "Il15" "Il16"
## [120] "Il18" "Il18rap" "Il1b" "Il2" "Il27ra" "Il2ra" "Il2rb"
## [127] "Il2rg" "Il4" "Il4ra" "Il6" "Il7" "Il9" "Inhba"
## [134] "Inhbb" "Irf4" "Irf7" "Irf8" "Itgal" "Itgb2" "Itk"
## [141] "Jak2" "Klrd1" "Krt1" "Lck" "Lcp2" "Lif" "Ltb"
## [148] "Ly75" "Ly86" "Lyn" "Map3k7" "Map4k1" "Mbl2" "Mmp9"
## [155] "Mrpl3" "Mtif2" "Ncf4" "Nck1" "Ncr1" "Nlrp3" "Nme1"
## [162] "Nos2" "Npm1" "Pf4" "Prf1" "Prkcb" "Prkcg" "Psmb10"
## [169] "Ptpn6" "Ptprc" "Rars" "Ripk2" "Rpl39" "Rpl3l" "Rpl9"
## [176] "Rps19" "Rps3a1" "Rps9" "Sit1" "Socs1" "Socs5" "Spi1"
## [183] "Srgn" "St8sia4" "Stab1" "Stat1" "Stat4" "Tap1" "Tap2"
## [190] "Tapbp" "Tgfb1" "Tgfb2" "Thy1" "Timp1" "Tlr1" "Tlr2"
## [197] "Tlr3" "Tlr6" "Tnf" "Tpd52" "Traf2" "Trat1" "Ube2d1"
## [204] "Ube2n" "Wars" "Was" "Zap70"
##
## $HALLMARK_ANDROGEN_RESPONSE
## [1] "Abcc4" "Abhd2" "Acsl3" "Actn1" "Adamts1" "Adrm1"
## [7] "Akap12" "Akt1" "Aldh1a3" "Ank" "Appbp2" "Arid5b"
## [13] "Azgp1" "B2m" "B4galt1" "Bmpr1b" "Camkk2" "Ccnd1"
## [19] "Ccnd3" "Cdc14b" "Cdk6" "Cenpn" "Dbi" "Dhcr24"
## [25] "Dnajb9" "Elk4" "Ell2" "Elovl5" "Fads1" "Fkbp5"
## [31] "Gnai3" "Gpd1l" "Gsr" "Gucy1a1" "H1f0" "Herc3"
## [37] "Hmgcr" "Hmgcs1" "Homer2" "Hpgd" "Hsd17b14" "Idi1"
## [43] "Inpp4b" "Insig1" "Iqgap2" "Itgav" "Klk1" "Klk1b1"
## [49] "Klk1b11" "Klk1b16" "Klk1b21" "Klk1b22" "Klk1b24" "Klk1b27"
## [55] "Klk1b3" "Klk1b4" "Klk1b5" "Klk1b8" "Klk1b9" "Klk1"
## [61] "Klk1b1" "Klk1b11" "Klk1b16" "Klk1b21" "Klk1b22" "Klk1b24"
## [67] "Klk1b27" "Klk1b3" "Klk1b4" "Klk1b5" "Klk1b8" "Klk1b9"
## [73] "Krt19" "Krt8" "Lifr" "Lman1" "Maf" "Mak"
## [79] "Map7" "Mertk" "Myl12a" "Ncoa4" "Ndrg1" "Ngly1"
## [85] "Nkx3-1" "Pa2g4" "Pdlim5" "Pgm3" "Pias1" "Plpp1"
## [91] "Pmepa1" "Ptk2b" "Ptpn21" "Rab4a" "Rps6ka3" "Rrp12"
## [97] "Sat1" "Scd1" "Scd2" "Sec24d" "Selenop" "Sgk1"
## [103] "Slc26a2" "Slc38a2" "Sms" "Sord" "Spcs3" "Spdef"
## [109] "Srf" "Srp19" "Steap4" "Stk39" "Tmem50a" "Tmprss2"
## [115] "Tnfaip8" "Tpd52" "Tsc22d1" "Uap1" "Ube2i" "Ube2j1"
## [121] "Vapa" "Xrcc5" "Xrcc6" "Zbtb10" "Zmiz1"
##
## $HALLMARK_ANGIOGENESIS
## [1] "Apoh" "App" "Ccnd2" "Col3a1" "Col5a2" "Cxcl5"
## [7] "Fgfr1" "Fstl1" "Itgav" "Jag1" "Jag2" "Kcnj8"
## [13] "Lpl" "Lrpap1" "Lum" "Msx1" "Nrp1" "Olr1"
## [19] "Pdgfa" "Pf4" "Pglyrp1" "Postn" "Prg2" "Ptk2"
## [25] "S100a4" "Serpina5" "Slco2a1" "Spp1" "Stc1" "Thbd"
## [31] "Timp1" "Tnfrsf21" "Vav2" "Vcan" "Vegfa" "Vtn"
##
## $HALLMARK_APICAL_JUNCTION
## [1] "Acta1" "Actb" "Actc1" "Actg1" "Actg2" "Actn1"
## [7] "Actn2" "Actn3" "Actn4" "Adam15" "Adam23" "Adam9"
## [13] "Adamts5" "Adra1b" "Akt2" "Akt3" "Alox8" "Amh"
## [19] "Amigo1" "Amigo2" "Arhgef6" "Arpc2" "Atp1a3" "B4galt1"
## [25] "Baiap2" "Bmp1" "Cadm2" "Cadm3" "Calb2" "Cap1"
## [31] "Cd209b" "Cd274" "Cd276" "Cd34" "Cd86" "Cdh1"
## [37] "Cdh11" "Cdh15" "Cdh3" "Cdh4" "Cdh6" "Cdh8"
## [43] "Cdk8" "Cdsn" "Cercam" "Cldn11" "Cldn14" "Cldn15"
## [49] "Cldn18" "Cldn19" "Cldn4" "Cldn5" "Cldn6" "Cldn7"
## [55] "Cldn8" "Cldn9" "Cnn2" "Cntn1" "Col16a1" "Col17a1"
## [61] "Col9a1" "Crat" "Crb3" "Ctnna1" "Ctnnd1" "Cx3cl1"
## [67] "Dhx16" "Dlg1" "Dmp1" "Dsc1" "Dsc3" "Egfr"
## [73] "Epb41l2" "Evl" "Exoc4" "Fbn1" "Flnc" "Fscn1"
## [79] "Fyb" "Gamt" "Gnai1" "Gnai2" "Grb7" "Gtf2f1"
## [85] "Hadh" "Hras" "Icam1" "Icam2" "Icam4" "Icam5"
## [91] "Ikbkg" "Inppl1" "Insig1" "Irs1" "Itga10" "Itga2"
## [97] "Itga3" "Itga9" "Itgb1" "Itgb4" "Jam3" "Jup"
## [103] "Kcnh2" "Krt31" "Lama3" "Lamb3" "Lamc2" "Layn"
## [109] "Ldlrap1" "Lima1" "Madcam1" "Map3k20" "Map4k2" "Mapk11"
## [115] "Mapk13" "Mapk14" "Mdk" "Mmp2" "Mmp9" "Pals1"
## [121] "Mpzl1" "Mpzl2" "Msn" "Mvd" "Myh10" "Myh9"
## [127] "Myl12b" "Myl9" "Nectin1" "Nectin2" "Nectin3" "Nectin4"
## [133] "Negr1" "Nexn" "Nf1" "Nf2" "Nfasc" "Nlgn2"
## [139] "Nlgn3" "Nrap" "Nrtn" "Nrxn2" "Pard6g" "Parva"
## [145] "Pbx2" "Pcdh1" "Pdzd3" "Pecam1" "Pfn1" "Pik3cb"
## [151] "Pik3r3" "Pkd1" "Plcg1" "Ppp2r2c" "Pten" "Ptk2"
## [157] "Ptprc" "Rac2" "Rasa1" "Rhof" "Rras" "Rsu1"
## [163] "Sdc3" "Sgce" "Shc1" "Shroom2" "Sirpa" "Skap2"
## [169] "Slc30a3" "Slit2" "Sorbs3" "Speg" "Src" "Stx4a"
## [175] "Syk" "Sympk" "Taok2" "Tgfbi" "Thbs3" "Thy1"
## [181] "Tial1" "Tjp1" "Tmem8b" "Tnfrsf11b" "Traf1" "Tro"
## [187] "Tsc1" "Tspan4" "Tubg1" "Vasp" "Vav2" "Vcam1"
## [193] "Vcan" "Vcl" "Vwf" "Wasl" "Wnk4" "Ywhah"
## [199] "Zyx"
##
## $HALLMARK_APICAL_SURFACE
## [1] "Adam10" "Adipor2" "Afap1l2" "Akap7" "App" "Atp6v0a4"
## [7] "Atp8b1" "B4galt1" "Brca1" "Cd160" "Crocc" "Crybg1"
## [13] "Cx3cl1" "Dcbld2" "Efna5" "Ephb4" "Flot2" "Gas1"
## [19] "Gata3" "Ghrl" "Gstm5" "Hspb1" "Il2rb" "Il2rg"
## [25] "Lyn" "Lypd3" "Mal" "Mdga1" "Ncoa6" "Ntng1"
## [31] "Pcsk9" "Pkhd1" "Plaur" "Rhcg" "Rtn4rl1" "Scube1"
## [37] "Shroom2" "Slc22a12" "Slc2a4" "Slc34a3" "Srpx" "Sulf2"
## [43] "Thy1" "Tmem8b"pbmc <- readRDS("/mnt/nectar_volume/home/eraz0001/KELLY 2020/E11.5/Final_15_clusters.RDS")
expr <- as.matrix(pbmc@assays$RNA@counts)system.time({res.counts = gsva(expr, genesets, method="ssgsea", parallel.sz=10)})## Warning in .filterFeatures(expr, method): 4 genes with constant expression
## values throuhgout the samples.## Setting parallel calculations through a MulticoreParam back-end
## with workers=10 and tasks=100.
## Estimating ssGSEA scores for 50 gene sets.
##
|
| | 0%
|
|= | 1%
|
|= | 2%
|
|== | 3%
|
|=== | 4%
|
|==== | 5%
|
|==== | 6%
|
|===== | 7%
|
|====== | 8%
|
|====== | 9%
|
|======= | 10%
|
|======== | 11%
|
|======== | 12%
|
|========= | 13%
|
|========== | 14%
|
|========== | 15%
|
|=========== | 16%
|
|============ | 17%
|
|============= | 18%
|
|============= | 19%
|
|============== | 20%
|
|=============== | 21%
|
|=============== | 22%
|
|================ | 23%
|
|================= | 24%
|
|================== | 25%
|
|================== | 26%
|
|=================== | 27%
|
|==================== | 28%
|
|==================== | 29%
|
|===================== | 30%
|
|====================== | 31%
|
|====================== | 32%
|
|======================= | 33%
|
|======================== | 34%
|
|======================== | 35%
|
|========================= | 36%
|
|========================== | 37%
|
|=========================== | 38%
|
|=========================== | 39%
|
|============================ | 40%
|
|============================= | 41%
|
|============================= | 42%
|
|============================== | 43%
|
|=============================== | 44%
|
|================================ | 45%
|
|================================ | 46%
|
|================================= | 47%
|
|================================== | 48%
|
|================================== | 49%
|
|=================================== | 50%
|
|==================================== | 51%
|
|==================================== | 52%
|
|===================================== | 53%
|
|====================================== | 54%
|
|====================================== | 55%
|
|======================================= | 56%
|
|======================================== | 57%
|
|========================================= | 58%
|
|========================================= | 59%
|
|========================================== | 60%
|
|=========================================== | 61%
|
|=========================================== | 62%
|
|============================================ | 63%
|
|============================================= | 64%
|
|============================================== | 65%
|
|============================================== | 66%
|
|=============================================== | 67%
|
|================================================ | 68%
|
|================================================ | 69%
|
|================================================= | 70%
|
|================================================== | 71%
|
|================================================== | 72%
|
|=================================================== | 73%
|
|==================================================== | 74%
|
|==================================================== | 75%
|
|===================================================== | 76%
|
|====================================================== | 77%
|
|======================================================= | 78%
|
|======================================================= | 79%
|
|======================================================== | 80%
|
|========================================================= | 81%
|
|========================================================= | 82%
|
|========================================================== | 83%
|
|=========================================================== | 84%
|
|============================================================ | 85%
|
|============================================================ | 86%
|
|============================================================= | 87%
|
|============================================================== | 88%
|
|============================================================== | 89%
|
|=============================================================== | 90%
|
|================================================================ | 91%
|
|================================================================ | 92%
|
|================================================================= | 93%
|
|================================================================== | 94%
|
|================================================================== | 95%
|
|=================================================================== | 96%
|
|==================================================================== | 97%
|
|===================================================================== | 98%
|
|===================================================================== | 99%
|
|======================================================================| 100%## user system elapsed
## 257.579 20.003 47.815expr <- as.matrix(pbmc@assays$RNA@data)system.time({res.scaledata = gsva(expr, genesets, method="ssgsea", parallel.sz=10)})## Warning in .filterFeatures(expr, method): 4 genes with constant expression
## values throuhgout the samples.## Setting parallel calculations through a MulticoreParam back-end
## with workers=10 and tasks=100.
## Estimating ssGSEA scores for 50 gene sets.
##
|
| | 0%
|
|= | 1%
|
|= | 2%
|
|== | 3%
|
|=== | 4%
|
|==== | 5%
|
|==== | 6%
|
|===== | 7%
|
|====== | 8%
|
|====== | 9%
|
|======= | 10%
|
|======== | 11%
|
|======== | 12%
|
|========= | 13%
|
|========== | 14%
|
|========== | 15%
|
|=========== | 16%
|
|============ | 17%
|
|============= | 18%
|
|============= | 19%
|
|============== | 20%
|
|=============== | 21%
|
|=============== | 22%
|
|================ | 23%
|
|================= | 24%
|
|================== | 25%
|
|================== | 26%
|
|=================== | 27%
|
|==================== | 28%
|
|==================== | 29%
|
|===================== | 30%
|
|====================== | 31%
|
|====================== | 32%
|
|======================= | 33%
|
|======================== | 34%
|
|======================== | 35%
|
|========================= | 36%
|
|========================== | 37%
|
|=========================== | 38%
|
|=========================== | 39%
|
|============================ | 40%
|
|============================= | 41%
|
|============================= | 42%
|
|============================== | 43%
|
|=============================== | 44%
|
|================================ | 45%
|
|================================ | 46%
|
|================================= | 47%
|
|================================== | 48%
|
|================================== | 49%
|
|=================================== | 50%
|
|==================================== | 51%
|
|==================================== | 52%
|
|===================================== | 53%
|
|====================================== | 54%
|
|====================================== | 55%
|
|======================================= | 56%
|
|======================================== | 57%
|
|========================================= | 58%
|
|========================================= | 59%
|
|========================================== | 60%
|
|=========================================== | 61%
|
|=========================================== | 62%
|
|============================================ | 63%
|
|============================================= | 64%
|
|============================================== | 65%
|
|============================================== | 66%
|
|=============================================== | 67%
|
|================================================ | 68%
|
|================================================ | 69%
|
|================================================= | 70%
|
|================================================== | 71%
|
|================================================== | 72%
|
|=================================================== | 73%
|
|==================================================== | 74%
|
|==================================================== | 75%
|
|===================================================== | 76%
|
|====================================================== | 77%
|
|======================================================= | 78%
|
|======================================================= | 79%
|
|======================================================== | 80%
|
|========================================================= | 81%
|
|========================================================= | 82%
|
|========================================================== | 83%
|
|=========================================================== | 84%
|
|============================================================ | 85%
|
|============================================================ | 86%
|
|============================================================= | 87%
|
|============================================================== | 88%
|
|============================================================== | 89%
|
|=============================================================== | 90%
|
|================================================================ | 91%
|
|================================================================ | 92%
|
|================================================================= | 93%
|
|================================================================== | 94%
|
|================================================================== | 95%
|
|=================================================================== | 96%
|
|==================================================================== | 97%
|
|===================================================================== | 98%
|
|===================================================================== | 99%
|
|======================================================================| 100%## user system elapsed
## 256.435 31.238 45.869pbmc <- readRDS("/mnt/nectar_volume/home/eraz0001/KELLY 2020/E11.5/Final_15_clusters.RDS")
pbmc.genes <- wilcoxauc(pbmc, 'seurat_clusters')
head(pbmc.genes)## feature group avgExpr logFC statistic auc pval
## 1 Rp1 0 0.00000000 -0.001058592 253570.5 0.4992823 5.551645e-01
## 2 Sox17 0 0.01253712 -0.195274103 219665.5 0.4325231 7.080678e-09
## 3 Mrpl15 0 0.67851596 0.035286670 262961.0 0.5177723 3.519954e-01
## 4 Lypla1 0 0.55899612 -0.037224555 246219.0 0.4848071 4.236172e-01
## 5 Tcea1 0 0.67248993 0.029178272 262011.0 0.5159017 4.063825e-01
## 6 Gm6104 0 0.02344033 0.004344293 256500.0 0.5050505 3.654255e-01
## padj pct_in pct_out
## 1 7.432695e-01 0.000000 0.1435407
## 2 3.449738e-07 1.646091 14.9760766
## 3 6.394024e-01 67.489712 63.2057416
## 4 6.924795e-01 58.024691 61.4832536
## 5 6.753671e-01 66.666667 64.9760766
## 6 6.466255e-01 3.703704 2.6794258dplyr::count(pbmc.genes, group)## group n
## 1 0 16968
## 2 1 16968
## 3 10 16968
## 4 11 16968
## 5 12 16968
## 6 13 16968
## 7 14 16968
## 8 15 16968
## 9 2 16968
## 10 3 16968
## 11 4 16968
## 12 5 16968
## 13 6 16968
## 14 7 16968
## 15 8 16968
## 16 9 16968msigdbr_show_species()## Warning: 'msigdbr_show_species' is deprecated.
## Use 'msigdbr_species' instead.
## See help("Deprecated")## [1] "Anolis carolinensis" "Bos taurus"
## [3] "Caenorhabditis elegans" "Canis lupus familiaris"
## [5] "Danio rerio" "Drosophila melanogaster"
## [7] "Equus caballus" "Felis catus"
## [9] "Gallus gallus" "Homo sapiens"
## [11] "Macaca mulatta" "Monodelphis domestica"
## [13] "Mus musculus" "Ornithorhynchus anatinus"
## [15] "Pan troglodytes" "Rattus norvegicus"
## [17] "Saccharomyces cerevisiae" "Schizosaccharomyces pombe 972h-"
## [19] "Sus scrofa" "Xenopus tropicalis"m_df<- msigdbr(species = "Mus musculus")
head(m_df)## # A tibble: 6 × 18
## gs_cat gs_subcat gs_name gene_symbol entrez_gene ensembl_gene human_gene_symb…
## <chr> <chr> <chr> <chr> <int> <chr> <chr>
## 1 C3 MIR:MIR_… AAACCA… Abcc4 239273 ENSMUSG0000… ABCC4
## 2 C3 MIR:MIR_… AAACCA… Abraxas2 109359 ENSMUSG0000… ABRAXAS2
## 3 C3 MIR:MIR_… AAACCA… Actn4 60595 ENSMUSG0000… ACTN4
## 4 C3 MIR:MIR_… AAACCA… Acvr1 11477 ENSMUSG0000… ACVR1
## 5 C3 MIR:MIR_… AAACCA… Adam9 11502 ENSMUSG0000… ADAM9
## 6 C3 MIR:MIR_… AAACCA… Adamts5 23794 ENSMUSG0000… ADAMTS5
## # … with 11 more variables: human_entrez_gene <int>, human_ensembl_gene <chr>,
## # gs_id <chr>, gs_pmid <chr>, gs_geoid <chr>, gs_exact_source <chr>,
## # gs_url <chr>, gs_description <chr>, taxon_id <int>, ortholog_sources <chr>,
## # num_ortholog_sources <dbl>fgsea_sets<- m_df %>% split(x = .$gene_symbol, f = .$gs_name)
fgsea_sets$GSE11057_NAIVE_VS_MEMORY_CD4_TCELL_UP## [1] "Ablim1" "Acer1" "Adgra3" "Adgrl1" "Aebp1" "Agrn"
## [7] "Aif1" "Alg10b" "Amn1" "Apba2" "Apbb1" "Armcx2"
## [13] "Bach2" "Bend5" "Bnip3l" "Btbd3" "Car6" "Cadps2"
## [19] "Camk4" "Cd248" "Cd55" "Cd55b" "Cenpv" "Cep41"
## [25] "Chml" "Chmp7" "Ciapin1" "Clcn5" "Col5a2" "Crlf3"
## [31] "Cyhr1" "Ddr1" "Dnhd1" "Dntt" "Dsc1" "Edar"
## [37] "Eea1" "Efna1" "Engase" "Exph5" "Fcgrt" "Gal3st4"
## [43] "Gnai1" "Gp5" "Gpr160" "Gprasp1" "Gprasp2" "Gprc5b"
## [49] "Hemgn" "Hipk2" "Hsf2" "Igf1r" "Igip" "Itga6"
## [55] "Kcnq5" "Kctd3" "Klhdc1" "Klhl13" "Klhl24" "Krt18"
## [61] "Krt2" "Krt72" "Krt73" "Lmln" "Lrrn3" "Mall"
## [67] "Maml2" "Mansc1" "Me3" "Mef2a" "Mest" "Metap1d"
## [73] "Mir101a" "Mlxip" "Mpp1" "Mpp7" "Myb" "Mzf1"
## [79] "Naa16" "Nbea" "Ndc1" "Ndfip1" "Net1" "Npas2"
## [85] "Npm3" "Nsun5" "Nucb2" "Nudt12" "Nudt17" "Padi4"
## [91] "Pced1b" "Pcsk5" "Pde3b" "Pde7a" "Pde7b" "Pde9a"
## [97] "Pdk1" "Pecam1" "Phgdh" "Pigl" "Pik3cd" "Pik3ip1"
## [103] "Pitpnm2" "Pjvk" "Pkig" "Pla2g12a" "Plag1" "Pllp"
## [109] "Prrt1" "Prxl2a" "Ptprk" "Pxylp1" "Rapgef6" "Reg4"
## [115] "Retreg1" "Rgs10" "Rhpn2" "Rin3" "Rnf227" "Robo3"
## [121] "Satb1" "Scai" "Scarb1" "Scml2" "Serpine2" "Sertad2"
## [127] "Sertm1" "Setd1b" "Sfmbt2" "Sfxn2" "Sh3rf3" "Siah1a"
## [133] "Slc11a2" "Slc25a37" "Slc29a2" "Smpd1" "Snph" "Snrpn"
## [139] "Snx9" "Sorcs3" "Sppl2b" "Srebf1" "Stap1" "Taf4b"
## [145] "Tarbp1" "Tbc1d32" "Tgfbr2" "Timp2" "Tle2" "Tmem170b"
## [151] "Tmem220" "Tmem263" "Tmem41b" "Tom1l2" "Tspan3" "Ttc28"
## [157] "Tug1" "Ube2e2" "Usp44" "Vps52" "Zbtb18" "Zc4h2"
## [163] "Zmynd8" "Zfp182" "Zkscan17" "Zfp458" "Zfp729a" "Zfp516"
## [169] "Zfp780b" "Zfp974" "Zfp617" "Zfp780b" "Polr1has"pbmc.genes %>%
dplyr::filter(group == "0") %>%
arrange(desc(logFC), desc(auc)) %>%
head(n = 10)## feature group avgExpr logFC statistic auc pval
## 1 Ube2c 0 1.857285 0.9851233 390962.0 0.7698072 2.566173e-46
## 2 Cdc20 0 1.737249 0.9181571 392978.0 0.7737768 2.381441e-47
## 3 Ebf1 0 1.323902 0.8965392 411422.0 0.8100931 5.008972e-70
## 4 Arl6ip1 0 2.237411 0.8793446 387303.5 0.7626036 2.912793e-41
## 5 Col9a1 0 1.532510 0.8552051 380096.5 0.7484130 1.263399e-42
## 6 Cenpa 0 1.786319 0.8427422 385044.5 0.7581556 2.449435e-41
## 7 H1fx 0 2.381727 0.8012411 405541.0 0.7985134 1.300211e-52
## 8 Top2a 0 1.739902 0.8002118 382955.0 0.7540414 2.207671e-40
## 9 Hoxa11os 0 1.320248 0.7964133 398513.0 0.7846752 1.965767e-57
## 10 H2afx 0 2.320449 0.7931150 383905.5 0.7559129 3.445982e-39
## padj pct_in pct_out
## 1 4.354282e-43 90.94650 55.26316
## 2 4.489810e-44 92.18107 56.45933
## 3 8.499223e-66 86.41975 36.55502
## 4 2.907310e-38 96.29630 81.05263
## 5 1.649028e-39 85.59671 43.77990
## 6 2.597626e-38 92.59259 62.53589
## 7 3.676995e-49 99.17695 87.27273
## 8 1.872988e-37 94.65021 60.09569
## 9 8.338784e-54 90.94650 39.13876
## 10 2.542236e-36 95.47325 84.44976cluster0.genes<- pbmc.genes %>%
dplyr::filter(group == "0") %>%
arrange(desc(auc)) %>%
dplyr::select(feature, auc)
ranks<- deframe(cluster0.genes)
head(ranks)## Hmgb2 Ebf1 H1fx Tpx2 Cdca3 Hoxa11os
## 0.8299663 0.8100931 0.7985134 0.7944228 0.7859206 0.7846752fgseaRes<- fgsea(fgsea_sets, stats = ranks, nperm = 1000)## Warning in fgsea(fgsea_sets, stats = ranks, nperm = 1000): You are trying to run
## fgseaSimple. It is recommended to use fgseaMultilevel. To run fgseaMultilevel,
## you need to remove the nperm argument in the fgsea function call.## Warning in preparePathwaysAndStats(pathways, stats, minSize, maxSize, gseaParam, : There are ties in the preranked stats (28.65% of the list).
## The order of those tied genes will be arbitrary, which may produce unexpected results.## Warning in preparePathwaysAndStats(pathways, stats, minSize, maxSize,
## gseaParam, : All values in the stats vector are greater than zero and scoreType
## is "std", maybe you should switch to scoreType = "pos".fgseaResTidy <- fgseaRes %>%
as_tibble() %>%
arrange(desc(NES))
fgseaResTidy %>%
dplyr::select(-leadingEdge, -ES, -nMoreExtreme) %>%
arrange(padj) %>%
head()## # A tibble: 6 × 5
## pathway pval padj NES size
## <chr> <dbl> <dbl> <dbl> <int>
## 1 FISCHER_DREAM_TARGETS 0.00109 0.0171 10.9 871
## 2 FAN_EMBRYONIC_CTX_NSC_2 0.00132 0.0171 9.75 217
## 3 GOCC_NUCLEAR_PROTEIN_CONTAINING_COMPLEX 0.00108 0.0171 9.64 1069
## 4 ZHONG_PFC_C1_OPC 0.00131 0.0171 9.42 220
## 5 GOBERT_OLIGODENDROCYTE_DIFFERENTIATION_UP 0.00117 0.0171 8.99 536
## 6 GOBP_CHROMOSOME_ORGANIZATION 0.00108 0.0171 8.95 1020ggplot(fgseaResTidy %>% filter(padj < 0.008) %>% head(n= 20), aes(reorder(pathway, NES), NES)) + geom_col(aes(fill= NES < 7.5)) +
coord_flip() + labs(x="Pathway", y="Normalized Enrichment Score", title="Hallmark pathways NES from GSEA")
plotEnrichment(fgsea_sets[["FISCHER_DREAM_TARGETS"]],
ranks) + labs(title="FISCHER_DREAM_TARGETS")