Function to read various geneset file formats and returns a list of vectors containing gene names.

read_geneset(x, min_size = 15)

Arguments

x

file,

min_size

minimum size of geneset otherwise filter out.

Value

Returns a list of gene sets

Examples

gmt_file <- system.file("extdata", "h.all.v7.4.symbols.gmt", package = "bowerbird")
gs <- read_geneset(gmt_file)
head(gs)
#> $HALLMARK_TNFA_SIGNALING_VIA_NFKB
#>   [1] "JUNB"     "CXCL2"    "ATF3"     "NFKBIA"   "TNFAIP3"  "PTGS2"   
#>   [7] "CXCL1"    "IER3"     "CD83"     "CCL20"    "CXCL3"    "MAFF"    
#>  [13] "NFKB2"    "TNFAIP2"  "HBEGF"    "KLF6"     "BIRC3"    "PLAUR"   
#>  [19] "ZFP36"    "ICAM1"    "JUN"      "EGR3"     "IL1B"     "BCL2A1"  
#>  [25] "PPP1R15A" "ZC3H12A"  "SOD2"     "NR4A2"    "IL1A"     "RELB"    
#>  [31] "TRAF1"    "BTG2"     "DUSP1"    "MAP3K8"   "ETS2"     "F3"      
#>  [37] "SDC4"     "EGR1"     "IL6"      "TNF"      "KDM6B"    "NFKB1"   
#>  [43] "LIF"      "PTX3"     "FOSL1"    "NR4A1"    "JAG1"     "CCL4"    
#>  [49] "GCH1"     "CCL2"     "RCAN1"    "DUSP2"    "EHD1"     "IER2"    
#>  [55] "REL"      "CFLAR"    "RIPK2"    "NFKBIE"   "NR4A3"    "PHLDA1"  
#>  [61] "IER5"     "TNFSF9"   "GEM"      "GADD45A"  "CXCL10"   "PLK2"    
#>  [67] "BHLHE40"  "EGR2"     "SOCS3"    "SLC2A6"   "PTGER4"   "DUSP5"   
#>  [73] "SERPINB2" "NFIL3"    "SERPINE1" "TRIB1"    "TIPARP"   "RELA"    
#>  [79] "BIRC2"    "CXCL6"    "LITAF"    "TNFAIP6"  "CD44"     "INHBA"   
#>  [85] "PLAU"     "MYC"      "TNFRSF9"  "SGK1"     "TNIP1"    "NAMPT"   
#>  [91] "FOSL2"    "PNRC1"    "ID2"      "CD69"     "IL7R"     "EFNA1"   
#>  [97] "PHLDA2"   "PFKFB3"   "CCL5"     "YRDC"     "IFNGR2"   "SQSTM1"  
#> [103] "BTG3"     "GADD45B"  "KYNU"     "G0S2"     "BTG1"     "MCL1"    
#> [109] "VEGFA"    "MAP2K3"   "CDKN1A"   "CCN1"     "TANK"     "IFIT2"   
#> [115] "IL18"     "TUBB2A"   "IRF1"     "FOS"      "OLR1"     "RHOB"    
#> [121] "AREG"     "NINJ1"    "ZBTB10"   "PLPP3"    "KLF4"     "CXCL11"  
#> [127] "SAT1"     "CSF1"     "GPR183"   "PMEPA1"   "PTPRE"    "TLR2"    
#> [133] "ACKR3"    "KLF10"    "MARCKS"   "LAMB3"    "CEBPB"    "TRIP10"  
#> [139] "F2RL1"    "KLF9"     "LDLR"     "TGIF1"    "RNF19B"   "DRAM1"   
#> [145] "B4GALT1"  "DNAJB4"   "CSF2"     "PDE4B"    "SNN"      "PLEK"    
#> [151] "STAT5A"   "DENND5A"  "CCND1"    "DDX58"    "SPHK1"    "CD80"    
#> [157] "TNFAIP8"  "CCNL1"    "FUT4"     "CCRL2"    "SPSB1"    "TSC22D1" 
#> [163] "B4GALT5"  "SIK1"     "CLCF1"    "NFE2L2"   "FOSB"     "PER1"    
#> [169] "NFAT5"    "ATP2B1"   "IL12B"    "IL6ST"    "SLC16A6"  "ABCA1"   
#> [175] "HES1"     "BCL6"     "IRS2"     "SLC2A3"   "CEBPD"    "IL23A"   
#> [181] "SMAD3"    "TAP1"     "MSC"      "IFIH1"    "IL15RA"   "TNIP2"   
#> [187] "BCL3"     "PANX1"    "FJX1"     "EDN1"     "EIF1"     "BMP2"    
#> [193] "DUSP4"    "PDLIM5"   "ICOSLG"   "GFPT2"    "KLF2"     "TNC"     
#> [199] "SERPINB8" "MXD1"    
#> 
#> $HALLMARK_HYPOXIA
#>   [1] "PGK1"     "PDK1"     "GBE1"     "PFKL"     "ALDOA"    "ENO2"    
#>   [7] "PGM1"     "NDRG1"    "HK2"      "ALDOC"    "GPI"      "MXI1"    
#>  [13] "SLC2A1"   "P4HA1"    "ADM"      "P4HA2"    "ENO1"     "PFKP"    
#>  [19] "AK4"      "FAM162A"  "PFKFB3"   "VEGFA"    "BNIP3L"   "TPI1"    
#>  [25] "ERO1A"    "KDM3A"    "CCNG2"    "LDHA"     "GYS1"     "GAPDH"   
#>  [31] "BHLHE40"  "ANGPTL4"  "JUN"      "SERPINE1" "LOX"      "GCK"     
#>  [37] "PPFIA4"   "MAFF"     "DDIT4"    "SLC2A3"   "IGFBP3"   "NFIL3"   
#>  [43] "FOS"      "RBPJ"     "HK1"      "CITED2"   "ISG20"    "GALK1"   
#>  [49] "WSB1"     "PYGM"     "STC1"     "ZNF292"   "BTG1"     "PLIN2"   
#>  [55] "CSRP2"    "VLDLR"    "JMJD6"    "EXT1"     "F3"       "PDK3"    
#>  [61] "ANKZF1"   "UGP2"     "ALDOB"    "STC2"     "ERRFI1"   "ENO3"    
#>  [67] "PNRC1"    "HMOX1"    "PGF"      "GAPDHS"   "CHST2"    "TMEM45A" 
#>  [73] "BCAN"     "ATF3"     "CAV1"     "AMPD3"    "GPC3"     "NDST1"   
#>  [79] "IRS2"     "SAP30"    "GAA"      "SDC4"     "STBD1"    "IER3"    
#>  [85] "PKLR"     "IGFBP1"   "PLAUR"    "CAVIN3"   "CCN5"     "LARGE1"  
#>  [91] "NOCT"     "S100A4"   "RRAGD"    "ZFP36"    "EGFR"     "EDN2"    
#>  [97] "IDS"      "CDKN1A"   "RORA"     "DUSP1"    "MIF"      "PPP1R3C" 
#> [103] "DPYSL4"   "KDELR3"   "DTNA"     "ADORA2B"  "HS3ST1"   "CAVIN1"  
#> [109] "NR3C1"    "KLF6"     "GPC4"     "CCN1"     "TNFAIP3"  "CA12"    
#> [115] "HEXA"     "BGN"      "PPP1R15A" "PGM2"     "PIM1"     "PRDX5"   
#> [121] "NAGK"     "CDKN1B"   "BRS3"     "TKTL1"    "MT1E"     "ATP7A"   
#> [127] "MT2A"     "SDC3"     "TIPARP"   "PKP1"     "ANXA2"    "PGAM2"   
#> [133] "DDIT3"    "PRKCA"    "SLC37A4"  "CXCR4"    "EFNA3"    "CP"      
#> [139] "KLF7"     "CCN2"     "CHST3"    "TPD52"    "LXN"      "B4GALNT2"
#> [145] "PPARGC1A" "BCL2"     "GCNT2"    "HAS1"     "KLHL24"   "SCARB1"  
#> [151] "SLC25A1"  "SDC2"     "CASP6"    "VHL"      "FOXO3"    "PDGFB"   
#> [157] "B3GALT6"  "SLC2A5"   "SRPX"     "EFNA1"    "GLRX"     "ACKR3"   
#> [163] "PAM"      "TGFBI"    "DCN"      "SIAH2"    "PLAC8"    "FBP1"    
#> [169] "TPST2"    "PHKG1"    "MYH9"     "CDKN1C"   "GRHPR"    "PCK1"    
#> [175] "INHA"     "HSPA5"    "NDST2"    "NEDD4L"   "TPBG"     "XPNPEP1" 
#> [181] "IL6"      "SLC6A6"   "MAP3K1"   "LDHC"     "AKAP12"   "TES"     
#> [187] "KIF5A"    "LALBA"    "COL5A1"   "GPC1"     "HDLBP"    "ILVBL"   
#> [193] "NCAN"     "TGM2"     "ETS1"     "HOXB9"    "SELENBP1" "FOSL2"   
#> [199] "SULT2B1"  "TGFB3"   
#> 
#> $HALLMARK_CHOLESTEROL_HOMEOSTASIS
#>  [1] "FDPS"      "CYP51A1"   "IDI1"      "FDFT1"     "DHCR7"     "SQLE"     
#>  [7] "HMGCS1"    "NSDHL"     "LSS"       "MVD"       "LDLR"      "TM7SF2"   
#> [13] "ALDOC"     "EBP"       "SCD"       "PMVK"      "MVK"       "LPL"      
#> [19] "SC5D"      "FADS2"     "HMGCR"     "HSD17B7"   "ANXA13"    "SREBF2"   
#> [25] "PCYT2"     "ACSS2"     "ATF3"      "ADH4"      "ETHE1"     "ECH1"     
#> [31] "CBS"       "GUSB"      "FASN"      "LGALS3"    "ATF5"      "ANXA5"    
#> [37] "TP53INP1"  "CHKA"      "GSTM2"     "ACAT2"     "AVPR1A"    "PLSCR1"   
#> [43] "CLU"       "ERRFI1"    "TRIB3"     "CXCL16"    "TNFRSF12A" "ACTG1"    
#> [49] "JAG1"      "LGMN"      "FBXO6"     "GPX8"      "PNRC1"     "ANTXR2"   
#> [55] "MAL2"      "CD9"       "PPARG"     "GLDC"      "STX5"      "STARD4"   
#> [61] "CTNNB1"    "TMEM97"    "NIBAN1"    "PDK3"      "PLAUR"     "SEMA3B"   
#> [67] "GNAI1"     "ABCA2"     "ATXN2"     "NFIL3"     "ALCAM"     "FABP5"    
#> [73] "S100A11"   "CPEB2"    
#> 
#> $HALLMARK_MITOTIC_SPINDLE
#>   [1] "ARHGEF2"  "CLASP1"   "KIF11"    "KIF23"    "ALS2"     "ARF6"    
#>   [7] "MYO9B"    "MYH9"     "TUBGCP3"  "CKAP5"    "RACGAP1"  "PREX1"   
#>  [13] "ARHGEF3"  "NUMA1"    "SPTBN1"   "KIF2C"    "KIF5B"    "TTK"     
#>  [19] "APC"      "CEP250"   "PAFAH1B1" "CDC42EP2" "KIF3B"    "CCDC88A" 
#>  [25] "KIF15"    "BIRC5"    "CNTROB"   "NF1"      "TSC1"     "CDC27"   
#>  [31] "CNTRL"    "TUBGCP5"  "KIF4A"    "MAPRE1"   "FGD6"     "BRCA2"   
#>  [37] "PLK1"     "RASA1"    "NEK2"     "WASF1"    "TOP2A"    "TRIO"    
#>  [43] "ARHGEF11" "KATNB1"   "PRC1"     "ANLN"     "CDK5RAP2" "SMC3"    
#>  [49] "TUBGCP2"  "ESPL1"    "MAP1S"    "ARHGAP27" "DOCK4"    "SAC3D1"  
#>  [55] "INCENP"   "ARHGAP5"  "GSN"      "NET1"     "LRPPRC"   "RABGAP1" 
#>  [61] "FLNB"     "ARAP3"    "FGD4"     "ABR"      "CENPJ"    "NCK1"    
#>  [67] "CENPF"    "KIF20B"   "WASF2"    "MYH10"    "CENPE"    "CYTH2"   
#>  [73] "MID1"     "KLC1"     "MARK4"    "ARL8A"    "CEP57"    "UXT"     
#>  [79] "ARHGAP4"  "CDC42EP4" "SASS6"    "LATS1"    "OPHN1"    "WASL"    
#>  [85] "MAP3K11"  "SOS1"     "ABL1"     "TIAM1"    "KIF1B"    "ITSN1"   
#>  [91] "SHROOM1"  "NCK2"     "DLGAP5"   "BCR"      "RANBP9"   "EPB41L2" 
#>  [97] "SEPTIN9"  "KATNA1"   "TUBD1"    "TPX2"     "KIF3C"    "SHROOM2" 
#> [103] "TUBGCP6"  "SPTAN1"   "PALLD"    "ARFIP2"   "KNTC1"    "HOOK3"   
#> [109] "SUN2"     "MID1IP1"  "DLG1"     "FLNA"     "ARHGAP10" "CDC42BPA"
#> [115] "ARHGEF12" "MARCKS"   "NIN"      "PCM1"     "RALBP1"   "EZR"     
#> [121] "SSH2"     "CDK1"     "RAB3GAP1" "FARP1"    "SYNPO"    "RHOF"    
#> [127] "ECT2"     "EPB41"    "RAPGEF6"  "KIF22"    "PCGF5"    "STAU1"   
#> [133] "ARHGDIA"  "AURKA"    "FBXO5"    "NUSAP1"   "PXN"      "BCAR1"   
#> [139] "CD2AP"    "AKAP13"   "HDAC6"    "CEP131"   "LLGL1"    "ATG4B"   
#> [145] "PCNT"     "ALMS1"    "KPTN"     "DST"      "KIFAP3"   "PPP4R2"  
#> [151] "ARHGAP29" "RASAL2"   "CCNB2"    "PIF1"     "RASA2"    "NEDD9"   
#> [157] "SMC1A"    "ACTN4"    "PKD2"     "CLIP2"    "CDC42"    "NDC80"   
#> [163] "TLK1"     "TAOK2"    "TBCD"     "CAPZB"    "DOCK2"    "CTTN"    
#> [169] "SMC4"     "ARFGEF1"  "TUBA4A"   "LMNB1"    "ABI1"     "ROCK1"   
#> [175] "CEP192"   "BUB1"     "GEMIN4"   "PLEKHG2"  "RICTOR"   "BCL2L11" 
#> [181] "DYNC1H1"  "FSCN1"    "ARHGEF7"  "DYNLL2"   "MYO1E"    "BIN1"    
#> [187] "NOTCH2"   "RFC1"     "PDLIM5"   "RHOT2"    "SORBS2"   "CDC42EP1"
#> [193] "VCL"      "CLIP1"    "STK38L"   "YWHAE"    "RAPGEF5"  "CEP72"   
#> [199] "CSNK1D"  
#> 
#> $HALLMARK_WNT_BETA_CATENIN_SIGNALING
#>  [1] "MYC"    "CTNNB1" "JAG2"   "NOTCH1" "DLL1"   "AXIN2"  "PSEN2"  "FZD1"  
#>  [9] "NOTCH4" "LEF1"   "AXIN1"  "NKD1"   "WNT5B"  "CUL1"   "JAG1"   "MAML1" 
#> [17] "KAT2A"  "GNAI1"  "WNT6"   "PTCH1"  "NCOR2"  "DKK4"   "HDAC2"  "DKK1"  
#> [25] "TCF7"   "WNT1"   "NUMB"   "ADAM17" "DVL2"   "PPARD"  "NCSTN"  "HDAC5" 
#> [33] "CCND2"  "FRAT1"  "CSNK1E" "RBPJ"   "FZD8"   "TP53"   "SKP2"   "HEY2"  
#> [41] "HEY1"   "HDAC11"
#> 
#> $HALLMARK_TGF_BETA_SIGNALING
#>  [1] "TGFBR1"   "SMAD7"    "TGFB1"    "SMURF2"   "SMURF1"   "BMPR2"   
#>  [7] "SKIL"     "SKI"      "ACVR1"    "PMEPA1"   "NCOR2"    "SERPINE1"
#> [13] "JUNB"     "SMAD1"    "SMAD6"    "PPP1R15A" "TGIF1"    "FURIN"   
#> [19] "SMAD3"    "FKBP1A"   "MAP3K7"   "BMPR1A"   "CTNNB1"   "HIPK2"   
#> [25] "KLF10"    "BMP2"     "ENG"      "APC"      "PPM1A"    "XIAP"    
#> [31] "CDH1"     "ID1"      "LEFTY2"   "CDKN1C"   "TRIM33"   "RAB31"   
#> [37] "TJP1"     "SLC20A1"  "CDK9"     "ID3"      "NOG"      "ARID4B"  
#> [43] "IFNGR2"   "ID2"      "PPP1CA"   "SPTBN1"   "WWTR1"    "BCAR3"   
#> [49] "THBS1"    "FNTA"     "HDAC1"    "UBE2D3"   "LTBP2"    "RHOA"    
#>