GSEA on avgLoading
2020-06-10
suppressPackageStartupMessages({
library(magrittr)
library(clusterProfiler)
library(SummarizedExperiment)
library(GenomicSignatures)
library(AnnotationDbi)
library(org.Hs.eg.db)
})clusterProfiler::enrichr for overrepresentation analysis (ORA) and clusterProfiler::GSEA
for gene set enrichment analysis. ORA takes genes with a significant expression
change (it doesn’t contain all the genes), while GSEA take the full gene vector
ordered by direction.
‘When to subset genes’ is still an on-going issue. Currently, I’m selecting gene sets for downstream annotation, and subset training data to common genes before row-normalization. But it might be better to keep all the genes longer, so I can apply different annotation database without repeating pre-processing.
1 Load avgLoading
PCAclusters includes avgLoading calcualted from 13,570 PCs (677 refine.bio +
10 PC1s from neg.control + TCGA-COAD training dataset) using hierarchical clustering
(Spearman correlation + ward.D agglomeration).
dat_dir <- "~/data2/Genomic_Super_Signature/refinebio/methods/5_Hierarchical_Clustering_with_SpikeInTCGA"
PCclusters <- readRDS(file.path(dat_dir, "PCclusters.rds"))2 PCcluster_263
Based on validation in refinebio/methods/5_Hierarchical_Clustering_with_SpikeInTCGA.Rmd,
Cl4935_263 is very highly correlated with one of the top 8 PCs of TCGA-BRCA dataset.
which(PCclusters$cluster == 263)
## ERP016798.PC2 SRP191514.PC2
## 322 133022.1 Involved studies
PCcluster_263 contains two PCs, ERP016798.PC2 and SRP191514.PC2.
mesh_terms <- readRDS("~/data2/Genomic_Super_Signature/refinebio/data/MeSH_terms_889refinebio.rds")
mesh_terms_sub <- mesh_terms[which(mesh_terms$identifier %in% c("ERP016798", "SRP191514")),]
table(mesh_terms_sub$name)
##
## Breast Breast Neoplasms Cell Proliferation
## 1 2 1
## Control Groups Exercise Exercise Therapy
## 1 1 1
## Female Humans Preoperative Care
## 1 2 1
## RNA-Seq Sedentary Behavior Transcriptome
## 1 1 1
## Transcriptome Profiling Utah Whole Exome Sequencing
## 1 1 1ERP016798 is RNA-Seq was used to profile the transcriptomes of 63 breast cancer patient tumour samples (51 x ER+, 12 x triple negative) collected from the Utah Breast Cancer Study (UBCS).
SRP191514 is RNAseq analysis of primary breast cancer samples Overall design: Inactive women with newly diagnosed breast cancer were randomized to an exercise intervention or mind-body control group, and participated in the study between enrollment and surgery (mean 29.3 days). Tumor were collected at baseline and surgery..
2.2 Format for enrichment analysis
For ORA, we need a vector of gene IDs. For GSEA, we need a ranked list of genes. Gene list for GSEA should meet three criteria: 1) numeric vector, 2) every number is named by the corresponding gene ID, and 3) sorted in decreasing order.
al <- PCclusters$avgLoading[,263] ## feature 1: numeric vector
names(al) <- AnnotationDbi::mapIds(org.Hs.eg.db, keys=names(al),
column='ENTREZID', keytype='SYMBOL') ## feature 2: named vector
## 'select()' returned 1:many mapping between keys and columns
al <- sort(al, decreasing = TRUE) ## feature 3: decreasing order
geneList <- al
gene <- names(geneList)[abs(geneList) > mean(abs(geneList))]
keyword <- "breast"3 Universal enrichment analysis
3.1 WikiPathways analysis
wpgmtfile <- "~/data2/Genomic_Super_Signature/GSEA/data/wikipathways-20200510-gmt-Homo_sapiens.gmt"
wp2gene <- read.gmt(wpgmtfile)
wp2gene <- wp2gene %>% tidyr::separate(term, c("name","version","wpid","org"), "%")
wpid2gene <- wp2gene %>% dplyr::select(wpid, gene) #TERM2GENE
wpid2name <- wp2gene %>% dplyr::select(wpid, name) #TERM2NAME
wp <- enricher(gene, TERM2GENE = wpid2gene, TERM2NAME = wpid2name)
head(wp)
## ID Description GeneRatio BgRatio
## WP3937 WP3937 Microglia Pathogen Phagocytosis Pathway 26/1582 40/7368
## WP179 WP179 Cell Cycle 55/1582 122/7368
## WP2446 WP2446 Retinoblastoma Gene in Cancer 43/1582 88/7368
## WP3929 WP3929 Chemokine signaling pathway 64/1582 165/7368
## WP2328 WP2328 Allograft Rejection 41/1582 90/7368
## WP619 WP619 Type II interferon signaling (IFNG) 22/1582 37/7368
## pvalue p.adjust qvalue
## WP3937 3.451813e-09 9.318682e-07 7.498803e-07
## WP179 3.720033e-09 9.318682e-07 7.498803e-07
## WP2446 9.860562e-09 1.646714e-06 1.325121e-06
## WP3929 2.410516e-07 2.557582e-05 2.058103e-05
## WP2328 2.552477e-07 2.557582e-05 2.058103e-05
## WP619 5.593955e-07 4.670952e-05 3.758745e-05
## geneID
## WP3937 10451/5777/7305/6850/27040/10095/3684/5880/7409/4689/1535/5336/1536/5294/3071/4688/3055/653361/2207/5293/4067/712/3689/713/714/54210
## WP179 10912/7043/6500/7534/10971/472/7042/5591/5885/4176/9134/2810/7027/8243/5111/6502/894/11200/10459/10926/1875/4172/4175/5933/3066/1032/4173/994/8317/4171/891/4174/1871/995/983/9088/9700/1869/23594/890/1111/1021/5347/8318/990/9232/1870/4998/699/9133/7272/993/991/1029/898
## WP2446 5591/8819/10592/580/4176/9134/7027/8243/3148/2956/1633/5111/6502/1786/5947/5984/6839/4172/10733/4175/4173/994/8317/891/7153/1871/983/3925/1869/890/81620/6241/1111/1021/7298/24137/8318/1870/4998/9133/7272/993/898
## WP3929 9547/10451/25759/56477/115/111/112/57580/3551/2791/4893/9844/6773/2185/5330/7852/5594/6654/109/10235/1445/4793/26230/409/2870/7454/59345/5880/23533/7409/1794/6351/53358/5294/113/3055/653361/6366/58191/6772/5293/2268/4067/6376/1230/5579/6367/1236/5613/3702/6369/6356/6364/6352/3718/2833/2921/10663/6374/2786/3627/4283/6373/10563
## WP2328 730/727/836/1459/7422/3108/10376/5156/3122/3115/3107/3133/3127/3123/3119/3111/3109/3553/3106/6366/6772/3117/3135/942/958/3134/712/713/714/3118/3105/717/50943/10578/5551/3559/3112/3002/4283/6373/10563
## WP619 4843/9021/3433/6773/5967/3659/3459/4261/6688/3394/3553/3106/1536/6772/5698/3383/2633/6890/8651/3662/3627/4283
## Count
## WP3937 26
## WP179 55
## WP2446 43
## WP3929 64
## WP2328 41
## WP619 22
# DT::datatable(as.data.frame(wp)[c("ID", "Description", "GeneRatio", "BgRatio", "p.adjust", "Count")])
wp2 <- GSEA(geneList, TERM2GENE = wpid2gene, TERM2NAME = wpid2name, verbose = FALSE)
head(wp2)
## ID Description
## WP2446 WP2446 Retinoblastoma Gene in Cancer
## WP2328 WP2328 Allograft Rejection
## WP179 WP179 Cell Cycle
## WP4536 WP4536 Genes related to primary cilium development (based on CRISPR)
## WP2877 WP2877 Vitamin D Receptor Pathway
## WP4754 WP4754 IL-18 signaling pathway
## setSize enrichmentScore NES pvalue p.adjust qvalues
## WP2446 82 -0.6256003 -2.060696 5.427469e-08 1.776214e-05 1.552518e-05
## WP2328 58 -0.6819629 -2.114797 7.929527e-08 1.776214e-05 1.552518e-05
## WP179 115 -0.5591999 -1.926600 4.398817e-07 6.159687e-05 5.383937e-05
## WP4536 73 0.5936978 2.244666 5.499721e-07 6.159687e-05 5.383937e-05
## WP2877 110 -0.5475147 -1.877940 1.863276e-06 1.669496e-04 1.459240e-04
## WP4754 198 -0.4735258 -1.737448 6.748606e-06 5.038959e-04 4.404353e-04
## rank leading_edge
## WP2446 1918 tags=57%, list=25%, signal=44%
## WP2328 1231 tags=55%, list=16%, signal=47%
## WP179 1759 tags=45%, list=23%, signal=36%
## WP4536 1099 tags=42%, list=14%, signal=37%
## WP2877 1394 tags=43%, list=18%, signal=36%
## WP4754 1912 tags=40%, list=25%, signal=31%
## core_enrichment
## WP2446 2189/10714/5983/6117/5591/8819/10592/580/4176/9134/7027/8243/3148/2956/1633/5111/6502/1786/5947/5984/6839/4172/10733/4175/4173/994/8317/891/7153/1871/983/3925/1869/890/81620/6241/1111/1021/7298/24137/8318/1870/4998/9133/7272/993/898
## WP2328 3115/3107/3133/3127/3123/3119/3111/3109/3553/3106/6366/6772/3117/3135/942/958/3134/712/713/714/3118/3105/717/50943/10578/5551/3559/3112/3002/4283/6373/10563
## WP179 7534/10971/472/7042/5591/5885/4176/9134/2810/7027/8243/5111/6502/894/11200/10459/10926/1875/4172/4175/5933/3066/1032/4173/994/8317/4171/891/4174/1871/995/983/9088/9700/1869/23594/890/1111/1021/5347/8318/990/9232/1870/4998/699/9133/7272/993/991/1029/898
## WP4536 123016/79600/8100/9742/585/79659/56912/403/79867/51626/129880/54585/80199/91147/112752/150737/23059/582/57728/28981/57545/583/11116/255758/26146/80173/55112/23288/54903/27241/84455
## WP2877 5734/6275/892/219855/5467/3965/3400/3663/3684/6546/240/3123/57167/215/3091/3394/10125/929/1032/7128/7292/3117/50486/639/958/25928/3294/1305/29785/3118/6696/8600/1946/54210/6273/3662/6280/1594/5588/6819/1029/838/6279/875/898/5653/768
## WP4754 22821/860/7076/29781/5905/9021/7114/56886/836/2896/58/55294/581/7422/4314/23/5594/1674/10452/2920/4791/5743/4615/8809/8078/54205/567/6004/3659/8985/274/7185/6347/3654/5337/7052/8837/3162/3553/10062/6351/84823/637/7128/2023/7913/4688/653361/58191/1051/3757/3606/10068/5578/3569/650/8698/5579/330/3925/6696/3383/8600/3801/4794/890/4050/5778/6364/3932/6352/9133/2921/4318/321/7941/3559/4312/6362
# DT::datatable(as.data.frame(wp2))3.2 Cell Markder
cell_markers <- vroom::vroom('http://bio-bigdata.hrbmu.edu.cn/CellMarker/download/Human_cell_markers.txt') %>%
tidyr::unite("cellMarker", tissueType, cancerType, cellName, sep=", ") %>%
dplyr::select(cellMarker, geneID) %>%
dplyr::mutate(geneID = strsplit(geneID, ', '))
## Rows: 2,868
## Columns: 15
## Delimiter: "\t"
## chr [15]: speciesType, tissueType, UberonOntologyID, cancerType, cellType, cellName, CellO...
##
## Use `spec()` to retrieve the guessed column specification
## Pass a specification to the `col_types` argument to quiet this message
cm <- enricher(gene, TERM2GENE = cell_markers, minGSSize = 1)
cm <- as.data.frame(cm)
rownames(cm) <- NULL
cm2 <- GSEA(geneList, TERM2GENE = cell_markers, verbose = FALSE)
## Warning in fgseaMultilevel(...): For some pathways, in reality P-values are less
## than 1e-10. You can set the `eps` argument to zero for better estimation.
cm2 <- as.data.frame(cm2)
rownames(cm2) <- NULLDT::datatable(cm[c("ID", "Description", "GeneRatio", "BgRatio", "p.adjust", "Count")])grep(keyword, cm$Description, ignore.case = TRUE)
## [1] 83
grep(keyword, cm2$Description, ignore.case = TRUE)
## integer(0)3.3 MSigDB analysis
library(msigdbr)
m_c2 <- msigdbr(species = "Homo sapiens", category = "C2") %>%
dplyr::select(gs_name, entrez_gene)
head(m_c2, 3)
## # A tibble: 3 x 2
## gs_name entrez_gene
## <chr> <int>
## 1 ABBUD_LIF_SIGNALING_1_DN 79026
## 2 ABBUD_LIF_SIGNALING_1_DN 91369
## 3 ABBUD_LIF_SIGNALING_1_DN 8289msC2 <- enricher(gene, TERM2GENE=m_c2)
msC2_2 <- GSEA(geneList, TERM2GENE = m_c2)
## preparing geneSet collections...
## GSEA analysis...
## Warning in fgseaMultilevel(...): For some pathways, in reality P-values are less
## than 1e-10. You can set the `eps` argument to zero for better estimation.
## leading edge analysis...
## done...
head(msC2)
## ID
## FARMER_BREAST_CANCER_BASAL_VS_LULMINAL FARMER_BREAST_CANCER_BASAL_VS_LULMINAL
## POOLA_INVASIVE_BREAST_CANCER_UP POOLA_INVASIVE_BREAST_CANCER_UP
## SHEDDEN_LUNG_CANCER_POOR_SURVIVAL_A6 SHEDDEN_LUNG_CANCER_POOR_SURVIVAL_A6
## DUTERTRE_ESTRADIOL_RESPONSE_24HR_UP DUTERTRE_ESTRADIOL_RESPONSE_24HR_UP
## KOBAYASHI_EGFR_SIGNALING_24HR_DN KOBAYASHI_EGFR_SIGNALING_24HR_DN
## VANTVEER_BREAST_CANCER_ESR1_DN VANTVEER_BREAST_CANCER_ESR1_DN
## Description
## FARMER_BREAST_CANCER_BASAL_VS_LULMINAL FARMER_BREAST_CANCER_BASAL_VS_LULMINAL
## POOLA_INVASIVE_BREAST_CANCER_UP POOLA_INVASIVE_BREAST_CANCER_UP
## SHEDDEN_LUNG_CANCER_POOR_SURVIVAL_A6 SHEDDEN_LUNG_CANCER_POOR_SURVIVAL_A6
## DUTERTRE_ESTRADIOL_RESPONSE_24HR_UP DUTERTRE_ESTRADIOL_RESPONSE_24HR_UP
## KOBAYASHI_EGFR_SIGNALING_24HR_DN KOBAYASHI_EGFR_SIGNALING_24HR_DN
## VANTVEER_BREAST_CANCER_ESR1_DN VANTVEER_BREAST_CANCER_ESR1_DN
## GeneRatio BgRatio pvalue
## FARMER_BREAST_CANCER_BASAL_VS_LULMINAL 190/2633 328/20738 1.155881e-85
## POOLA_INVASIVE_BREAST_CANCER_UP 173/2633 292/20738 3.754383e-80
## SHEDDEN_LUNG_CANCER_POOR_SURVIVAL_A6 207/2633 459/20738 2.040067e-67
## DUTERTRE_ESTRADIOL_RESPONSE_24HR_UP 168/2633 323/20738 3.521104e-66
## KOBAYASHI_EGFR_SIGNALING_24HR_DN 145/2633 252/20738 7.268922e-65
## VANTVEER_BREAST_CANCER_ESR1_DN 148/2633 269/20738 1.238764e-62
## p.adjust qvalue
## FARMER_BREAST_CANCER_BASAL_VS_LULMINAL 5.374845e-82 2.227808e-82
## POOLA_INVASIVE_BREAST_CANCER_UP 8.728940e-77 3.618039e-77
## SHEDDEN_LUNG_CANCER_POOR_SURVIVAL_A6 3.162104e-64 1.310653e-64
## DUTERTRE_ESTRADIOL_RESPONSE_24HR_UP 4.093283e-63 1.696616e-63
## KOBAYASHI_EGFR_SIGNALING_24HR_DN 6.760098e-62 2.801978e-62
## VANTVEER_BREAST_CANCER_ESR1_DN 9.600419e-60 3.979257e-60
## geneID
## FARMER_BREAST_CANCER_BASAL_VS_LULMINAL 7031/7033/57758/25803/1555/80736/9/10753/2674/7802/771/65055/8416/22977/5733/2330/4602/2593/18/9518/6337/10560/27289/25800/9254/540/2947/36/55733/11226/8800/8821/374/10610/81031/23030/23171/10916/51466/388/3572/80310/3875/2203/55614/10512/10140/51809/7357/4329/3667/596/64087/4832/23194/7466/55568/54681/7043/3315/6405/11059/5087/54894/9135/51097/200734/5914/10455/9368/2530/1728/253782/7108/5002/2194/6720/3487/51474/3856/10965/83752/7020/51181/3693/2954/582/8490/57728/11163/23600/644/4116/23198/86/55144/22929/22978/5500/9474/892/9444/4690/6502/1054/8898/60487/1736/57162/4783/8833/6632/10549/23229/6347/5621/55240/84617/4478/9957/55689/3066/10479/6251/4904/4781/10797/29967/9654/123/2744/23683/1051/1466/4174/29078/4067/6566/1871/6376/688/1183/6491/4651/6285/262/133/4281/3930/2171/8543/23590/6648/5613/5214/83439/23321/23432/1111/23650/24137/3945/2950/1824/22974/9232/9435/699/7272/10635/991/9928/1029/10403/2305/1058/5266/6374/55388/10644/26227/597/6518/898/7368/5317/1116/51083/3854/4321
## POOLA_INVASIVE_BREAST_CANCER_UP 4680/1048/9518/5284/26047/27132/1300/6571/90993/4016/2212/26585/6713/9935/972/4314/7852/11015/4327/9134/23213/8809/6404/55843/11010/1301/3965/4332/6004/4033/54509/3123/3059/7805/7185/91543/813/3371/8477/695/1880/3937/3687/3676/963/7083/6775/3109/57405/9938/5552/3394/1794/5788/6351/4173/113/23643/55215/4688/3669/6646/29899/962/7292/2207/51514/80896/3117/51316/1368/6402/3606/9123/7153/11339/2214/586/4085/10257/942/9837/958/3832/22797/23406/1520/983/1043/3689/1230/5329/5579/64151/5341/10859/341/10437/9056/50515/1439/6503/9332/9055/923/2633/1236/10112/4069/10288/890/701/11184/1063/8530/4751/64581/9051/3561/9787/6241/9235/3702/8140/56992/4050/641/7298/914/6790/3001/1075/332/2215/2359/7412/1824/939/22974/6356/9232/915/3932/11004/11006/9133/2833/10635/974/991/7804/3957/9582/10403/10578/1058/4318/973/7941/597/3627/27074/952/6999/3002/25975/4283/6373/27299/4312/6362/10563/4321
## SHEDDEN_LUNG_CANCER_POOR_SURVIVAL_A6 8614/81621/5167/11116/4893/79677/3843/10059/55233/1841/10767/1832/25804/28998/5591/8819/23225/10592/7422/9462/790/79980/1763/23310/23141/205/112950/22948/10452/5217/22929/5898/55326/5718/9134/3556/8936/55720/3052/55055/6723/6627/7027/23160/9474/6628/11047/5686/3148/55907/2956/5690/55166/1633/23636/5467/5111/11130/5352/5230/78999/5901/2937/8767/5688/10926/10622/10096/9735/29028/64785/8851/5984/5558/10733/54892/26271/56942/4175/7083/5817/57405/5933/27338/55689/4001/4830/3066/6513/1032/11332/4173/55110/54913/3070/1678/55215/8317/675/10797/891/7004/29899/7277/10460/4860/4704/2643/51514/3159/123/29127/6715/4174/9123/7153/7849/4603/6566/11339/6182/4085/3161/9837/2597/3832/9918/2146/995/983/64151/84296/133/3925/1062/81930/3838/1978/9055/10112/79814/55839/890/701/1063/6648/5214/4751/83990/23149/55247/81620/4647/9787/6241/1111/8140/56992/54821/2491/55143/7298/6790/24137/2175/3945/332/8438/8318/22974/990/9156/9232/11004/4998/699/9133/23397/7272/79019/8836/11065/10635/993/220134/4605/991/9212/9928/9582/55355/10874/1029/146909/79733/10403/1138/2305/1058/51512/55388/875/3559/898/7368/29968/4321
## DUTERTRE_ESTRADIOL_RESPONSE_24HR_UP 7031/123099/2674/771/8614/4602/25800/7494/11001/7869/64798/374/6584/26018/596/6478/9368/403/8204/3487/55540/9424/7374/7443/55835/84131/3251/64858/25804/10592/8914/580/79980/1763/23310/4277/2176/29893/4176/9134/3556/55526/23213/55055/55157/2289/7027/25788/9942/5111/6502/11130/1786/29089/2177/7112/51053/122769/56915/93323/64116/84930/9735/29028/64785/7164/10293/5984/6839/4172/10733/10682/54892/84515/26271/4175/7083/5933/4001/4830/5424/6513/4173/91687/3070/55215/675/4171/11113/10460/51514/3619/8208/4796/29127/4174/2237/79172/7153/4603/79723/7516/9837/3832/9918/983/29128/6491/9088/64151/3925/157570/3613/9055/9700/23590/9824/1869/3833/5888/10721/55839/890/701/83990/81620/9787/6241/1111/8140/641/2491/7298/5347/6790/24137/2175/144455/332/8438/8318/128239/22974/55789/990/9156/9232/147841/1870/11004/699/9133/23397/7272/79019/113130/8836/11065/4605/9212/79733/63967/1138/2305/51512/8645/55388/83879
## KOBAYASHI_EGFR_SIGNALING_24HR_DN 6947/8309/374/1846/55568/8870/200734/5905/7374/7443/8771/10528/3655/10592/8914/5433/580/79980/23310/25937/29893/4176/9134/55055/8091/6723/6627/7027/3148/25788/2956/51182/10212/5111/11130/899/7398/203068/7112/2119/51053/10926/6632/5902/54517/7371/29028/64785/1163/5984/4172/10051/10733/54892/56942/4175/7083/57405/84617/27338/4233/4001/4830/84823/4173/3070/55215/4171/891/29899/1894/51514/50486/29127/4174/4953/2237/8877/7153/4603/8061/4085/3161/9837/6376/7378/3832/2146/983/6491/9088/64151/28231/2171/3838/9055/9700/1869/23594/5888/55839/890/701/4751/8638/81620/9787/6241/56992/54821/641/55143/7298/5347/6790/24137/332/8318/22974/990/9156/11004/4998/136/699/23397/7272/79019/11065/10635/993/4605/7039/991/9212/9928/55355/146909/79733/10403/1058/51512/55388/29968/2707
## VANTVEER_BREAST_CANCER_ESR1_DN 29094/51465/9019/23198/4771/440/55343/5236/9519/9749/5500/6281/892/7347/4690/2230/1054/11010/8898/483/10477/6768/9111/80727/23216/8833/274/11173/8566/7371/7388/10130/55240/5558/3091/140885/64764/10133/4175/5552/3855/3608/10397/4478/1535/8568/1827/5962/22808/1536/6251/7128/84230/51700/3455/4904/2023/1672/5360/29899/6624/4828/8291/1466/4174/1476/445/4953/1612/4067/5292/2597/6376/3601/9918/114793/1183/6948/3689/135112/6491/4651/10859/262/133/4281/3613/23175/8543/2633/51560/4794/2526/1844/6648/5214/83439/54757/84706/27242/641/84002/55143/4064/23650/11240/2175/3945/1075/81624/1824/11025/8438/6352/11004/11182/9435/699/9133/7272/25984/4605/991/1001/9582/55355/5031/3101/3783/1058/8645/26227/56938/145864/597/83879/6518/27074/7368/5317/1116/29968/25975/3620/4316/768/6362/3854
## Count
## FARMER_BREAST_CANCER_BASAL_VS_LULMINAL 190
## POOLA_INVASIVE_BREAST_CANCER_UP 173
## SHEDDEN_LUNG_CANCER_POOR_SURVIVAL_A6 207
## DUTERTRE_ESTRADIOL_RESPONSE_24HR_UP 168
## KOBAYASHI_EGFR_SIGNALING_24HR_DN 145
## VANTVEER_BREAST_CANCER_ESR1_DN 148
head(msC2_2)
## ID
## BASAKI_YBX1_TARGETS_UP BASAKI_YBX1_TARGETS_UP
## BENPORATH_CYCLING_GENES BENPORATH_CYCLING_GENES
## BENPORATH_ES_1 BENPORATH_ES_1
## BENPORATH_PROLIFERATION BENPORATH_PROLIFERATION
## BERENJENO_TRANSFORMED_BY_RHOA_UP BERENJENO_TRANSFORMED_BY_RHOA_UP
## BERTUCCI_MEDULLARY_VS_DUCTAL_BREAST_CANCER_UP BERTUCCI_MEDULLARY_VS_DUCTAL_BREAST_CANCER_UP
## Description
## BASAKI_YBX1_TARGETS_UP BASAKI_YBX1_TARGETS_UP
## BENPORATH_CYCLING_GENES BENPORATH_CYCLING_GENES
## BENPORATH_ES_1 BENPORATH_ES_1
## BENPORATH_PROLIFERATION BENPORATH_PROLIFERATION
## BERENJENO_TRANSFORMED_BY_RHOA_UP BERENJENO_TRANSFORMED_BY_RHOA_UP
## BERTUCCI_MEDULLARY_VS_DUCTAL_BREAST_CANCER_UP BERTUCCI_MEDULLARY_VS_DUCTAL_BREAST_CANCER_UP
## setSize enrichmentScore NES
## BASAKI_YBX1_TARGETS_UP 203 -0.6074380 -2.225255
## BENPORATH_CYCLING_GENES 431 -0.4956352 -1.898459
## BENPORATH_ES_1 248 -0.5589326 -2.078097
## BENPORATH_PROLIFERATION 110 -0.7387197 -2.535434
## BERENJENO_TRANSFORMED_BY_RHOA_UP 404 -0.5545070 -2.122571
## BERTUCCI_MEDULLARY_VS_DUCTAL_BREAST_CANCER_UP 129 -0.6788072 -2.374899
## pvalue p.adjust qvalues
## BASAKI_YBX1_TARGETS_UP 1e-10 4.282e-09 3.314737e-09
## BENPORATH_CYCLING_GENES 1e-10 4.282e-09 3.314737e-09
## BENPORATH_ES_1 1e-10 4.282e-09 3.314737e-09
## BENPORATH_PROLIFERATION 1e-10 4.282e-09 3.314737e-09
## BERENJENO_TRANSFORMED_BY_RHOA_UP 1e-10 4.282e-09 3.314737e-09
## BERTUCCI_MEDULLARY_VS_DUCTAL_BREAST_CANCER_UP 1e-10 4.282e-09 3.314737e-09
## rank
## BASAKI_YBX1_TARGETS_UP 1475
## BENPORATH_CYCLING_GENES 1283
## BENPORATH_ES_1 1197
## BENPORATH_PROLIFERATION 1340
## BERENJENO_TRANSFORMED_BY_RHOA_UP 2347
## BERTUCCI_MEDULLARY_VS_DUCTAL_BREAST_CANCER_UP 1573
## leading_edge
## BASAKI_YBX1_TARGETS_UP tags=49%, list=19%, signal=41%
## BENPORATH_CYCLING_GENES tags=34%, list=16%, signal=30%
## BENPORATH_ES_1 tags=38%, list=15%, signal=33%
## BENPORATH_PROLIFERATION tags=75%, list=17%, signal=63%
## BERENJENO_TRANSFORMED_BY_RHOA_UP tags=60%, list=30%, signal=45%
## BERTUCCI_MEDULLARY_VS_DUCTAL_BREAST_CANCER_UP tags=65%, list=20%, signal=53%
## core_enrichment
## BASAKI_YBX1_TARGETS_UP 29893/4176/10762/348235/2810/55055/6627/84259/2316/3148/10212/2618/11130/26147/122769/4502/5694/11164/192111/10602/10189/3654/4172/7083/4501/84617/3608/84823/4173/1663/55215/4171/891/9688/7277/10785/51514/51316/2744/3918/4494/4174/2237/79172/4603/11339/4495/4085/9837/23406/9918/983/79866/29128/3838/9055/9700/10112/23594/5888/55839/890/701/4751/1111/27242/8140/2491/55143/7298/5347/6790/24137/144455/332/2950/81624/83540/22974/55789/990/9232/147841/11004/6273/699/9133/79019/11065/991/9212/55355/10874/10403/1058/51512/55388/387103/9982/3897
## BENPORATH_CYCLING_GENES 8975/3148/2619/55166/10238/5111/80308/11130/29089/11200/899/2177/7398/7112/51053/1736/1122/2870/5901/9585/93323/54972/2653/3110/84930/9712/2534/1875/29028/64785/1163/10293/5984/5558/3091/10051/3111/4973/84515/9829/4175/3608/6581/27338/8837/4233/4001/8568/1827/1032/4173/91687/994/3070/1663/51700/55215/8317/4171/891/11113/29899/10460/1894/51514/6772/100133941/1244/4828/8208/6715/5293/4174/2237/10068/7153/650/4085/3161/3832/9918/995/79866/29128/6491/9088/262/4281/3930/1062/8543/3838/9055/9700/9824/1869/3833/5888/10721/890/701/1063/4751/55247/9787/6241/55143/7298/5347/6790/2175/332/7412/8438/83540/8318/22974/55789/990/9156/9232/11004/4998/699/9133/23397/7272/79019/11065/10635/993/991/9212/84057/9928/55355/79733/10403/63967/2305/1058/51512/83879/898/3620
## BENPORATH_ES_1 2618/8886/11200/10459/51599/7112/51053/22800/6091/4074/56915/9456/10622/4521/80324/54517/57167/11168/5771/6535/5984/4172/5558/54892/4175/23246/57405/2118/249/4173/8324/3070/7913/4171/10797/891/7004/1525/1894/4257/100133941/1789/3159/23683/4174/29078/2237/6566/11339/4240/11245/3161/983/262/84296/29785/347733/2171/3838/890/701/5163/5613/83439/81620/9787/6241/1111/54821/24137/1075/332/990/9232/3932/11004/4998/699/23397/113130/10635/11040/993/991/9212/7804/10874/1690/55388/10644/875/3620/51083
## BENPORATH_PROLIFERATION 84079/84259/5692/3418/51182/5111/1054/2618/29089/6637/51645/7159/11164/9111/51571/10926/6632/5902/29028/64785/1163/5984/4172/5558/59345/56942/5202/3608/3066/5962/55110/7913/4171/29899/51514/8208/29127/1476/7153/79723/4085/2146/983/9088/64151/3930/3925/1062/7037/3838/9055/23590/58528/5888/55839/1063/4751/81620/6241/7298/6790/2175/332/2178/8438/83540/9156/9232/699/9133/7272/79019/113130/10635/6280/4605/84057/7804/9582/10403/1058/83879
## BERENJENO_TRANSFORMED_BY_RHOA_UP 10946/3624/5717/100287932/3692/55320/2730/8662/64425/9588/22822/6634/191/57122/7295/23082/5597/27101/10471/23649/25791/28232/10171/64981/3939/56945/10963/9994/10055/29107/2539/9097/4609/26524/27000/5693/6633/1729/5211/79902/87178/56902/4436/7965/5791/1073/5983/6117/6888/5223/7076/5905/7114/7443/3843/1841/3251/836/1459/7187/83443/25804/58/8819/3433/5691/3655/581/64432/10592/22824/7422/81/10574/86/8914/51703/1763/79101/205/8726/57819/5464/51377/10452/10054/2920/1024/4176/5743/6749/10762/55720/3329/5734/9188/8091/9446/6723/6627/7027/23160/1839/54801/7296/2091/3148/54205/51182/1633/23636/10436/5111/2618/1786/8886/29089/899/5230/7398/7112/1104/23597/483/51053/2870/5901/84844/5688/3037/6632/5902/7371/10189/6347/8407/3371/26472/1163/5984/4172/5558/10051/10733/286827/7083/5817/23246/84617/5933/4478/4830/4839/5424/286826/6513/705/11332/4173/3070/7128/2710/84230/1678/7913/8317/4171/10797/891/9688/10460/1894/51514/3619/3918/8208/29127/5321/7167/4174/29078/4953/2237/72/7153/8061/6182/586/4085/2597/3832/2146/995/983/29128/5329/133/3930/3925/6696/7037/3838/9055/3105/1869/10112/23594/3833/5888/890/6648/4751/9787/1111/55143/7298/6790/24137/332/81624/8318/128239/990/9156/9232/11004/4998/136/699/7272/113130/10635/4605/991/9212/79733/2305/1058/51512/64093/55388/83879/29968/10232
## BERTUCCI_MEDULLARY_VS_DUCTAL_BREAST_CANCER_UP 51703/5660/5464/56983/4277/4791/29780/57559/2091/5686/11331/5690/10436/5696/7097/716/130589/26147/6541/79668/4074/4200/3659/51056/29121/5699/7133/80324/1875/10384/10396/5552/5996/1535/1890/10062/4839/843/55110/5912/348/9688/5971/7004/653361/6772/2120/117289/115361/84541/101/10257/3601/1520/5698/10437/330/3695/3383/6890/3600/79814/4794/6648/64581/9235/9466/3001/7412/3902/11182/29126/11040/3594/51513/115362/2305/1058/51512/55388/56938/875/3112/952MSigDB C2 (curated gene sets) database seems to connect the most breast-related genesets to the loading.
grep(keyword, msC2$Description, ignore.case = TRUE)
## [1] 1 2 6 8 13 20 22 29 54 62 63 68 90 104 109
## [16] 147 174 179 193 207 232 244 252 276 299 309 317 326 331 357
## [31] 377 382 392 398 402 410 449 483 497 525 540 556 569 573 583
## [46] 598 607 609 650 685 686 705 707 709 736 823 839 928 1071 1158
## [61] 1164 1261 1366 1388 1414 1419 1473 1497 1519 1595 1654 1671 1696 1728 1771
## [76] 1775 1799 1847 1854 1879 1954 1981 1998 2012 2048 2164 2214 2225 2226 2284
## [91] 2322 2336 2388 2394 2476 2534 2552
grep(keyword, msC2_2$Description, ignore.case = TRUE)
## [1] 6 11 12 13 14 19 20 44 58 74 75 76 77 78 79 80 81 82 83
## [20] 86 87 88 96 104 106 111 121 123 127 135 159 163 165 170 181 183 185 213
## [39] 224 241 246 265 279 297 320 327 339 348 361 392 421 466 469 482 483 524 532
## [58] 588m_c6 <- msigdbr(species = "Homo sapiens", category = "C6") %>%
dplyr::select(gs_name, entrez_gene)
msC6 <- enricher(gene, TERM2GENE=m_c6)
msC6_2 <- GSEA(geneList, TERM2GENE = m_c6)
## preparing geneSet collections...
## GSEA analysis...
## Warning in fgseaMultilevel(...): For some pathways, in reality P-values are less
## than 1e-10. You can set the `eps` argument to zero for better estimation.
## leading edge analysis...
## done...
head(msC6)
## ID Description GeneRatio BgRatio pvalue
## MEL18_DN.V1_UP MEL18_DN.V1_UP MEL18_DN.V1_UP 61/1991 140/10897 3.110028e-12
## EGFR_UP.V1_UP EGFR_UP.V1_UP EGFR_UP.V1_UP 73/1991 192/10897 6.778155e-11
## RPS14_DN.V1_UP RPS14_DN.V1_UP RPS14_DN.V1_UP 71/1991 190/10897 3.068284e-10
## SNF5_DN.V1_UP SNF5_DN.V1_UP SNF5_DN.V1_UP 66/1991 172/10897 3.529191e-10
## P53_DN.V1_UP P53_DN.V1_UP P53_DN.V1_UP 70/1991 193/10897 1.837635e-09
## RAF_UP.V1_UP RAF_UP.V1_UP RAF_UP.V1_UP 70/1991 193/10897 1.837635e-09
## p.adjust qvalue
## MEL18_DN.V1_UP 5.877954e-10 3.666560e-10
## EGFR_UP.V1_UP 6.405357e-09 3.995544e-09
## RPS14_DN.V1_UP 1.667543e-08 1.040182e-08
## SNF5_DN.V1_UP 1.667543e-08 1.040182e-08
## P53_DN.V1_UP 5.788551e-08 3.610792e-08
## RAF_UP.V1_UP 5.788551e-08 3.610792e-08
## geneID
## MEL18_DN.V1_UP 771/8614/22885/5327/26018/7049/6583/25777/26585/7042/7422/3710/5045/6573/4277/54541/1839/10184/5069/1464/3914/719/5361/3037/9945/23657/55240/8876/3676/7436/3696/1663/8828/3936/23046/3117/6536/4494/3782/8061/9469/22797/1520/5329/1305/133/50515/28231/6696/8728/6890/3575/8140/81029/11182/9435/63967/2919/3604/51083/4316
## EGFR_UP.V1_UP 4680/27289/10451/2261/8835/1846/5167/6558/51097/3306/9314/9915/4128/3790/1545/2114/7042/2634/2650/4791/23433/5873/4017/22978/3437/1839/10184/9060/4217/1956/2119/6004/3659/6303/4783/5699/9456/23657/25825/6347/25816/3855/116984/1827/10479/2710/3669/6197/1525/72/5142/3601/23406/5698/6367/133/23175/3383/2633/6890/51129/27242/655/6280/1594/7804/9582/5031/6279/10644/3620/51083/4312
## RPS14_DN.V1_UP 4680/9518/150/388/1960/54677/5205/214/10769/2201/1545/4600/5168/64393/9462/290/10346/3108/9450/3556/5734/7305/834/10457/7045/5328/4082/4332/25780/719/3684/10602/3683/6347/3119/1880/4599/8876/29992/3687/140885/3109/9938/3553/929/9934/100/23643/1475/4688/3055/1368/8013/11314/26191/5800/22797/1520/3689/330/6696/64581/2153/8942/11240/2672/9047/3604/7941/597/27299
## SNF5_DN.V1_UP 347/51466/2006/114899/7043/6423/481/2331/135228/23646/3433/1436/86/290/26270/57819/2224/7852/55256/9450/23760/10791/55055/6515/5696/716/1104/719/2870/4200/715/7454/968/54892/963/6688/5933/10507/5788/3669/3936/348/962/51514/84624/4174/445/3134/25928/1043/3689/5698/5341/714/6891/2633/3105/10112/8638/699/11065/9212/55355/8549/3627/25975
## P53_DN.V1_UP 563/4680/6337/374/7433/7025/3875/90576/26018/652/629/3625/1308/1363/10873/10267/8412/7026/3880/4016/26509/4052/1832/8819/23213/3429/9734/10184/5467/7045/7525/4217/5328/4082/7398/51599/4507/1956/22800/3659/5947/2534/1404/7388/8218/1032/10656/29899/7277/1525/100133941/50486/3606/445/11339/688/7345/1305/133/1824/136/5268/10874/1029/10403/27074/7368/5646/10232/4312
## RAF_UP.V1_UP 4488/8835/2624/1846/51097/3306/58494/5274/8863/7089/10144/23092/1545/3655/22848/10577/5236/55526/5734/1839/56913/4217/8898/1956/2119/22800/4200/6303/10602/5699/9111/64781/25825/23596/2534/91543/25816/64764/10133/51191/9397/2182/10892/1827/79695/2760/2702/10656/25797/80896/8013/10257/7378/23406/1230/5698/3613/10331/51129/27242/1824/11182/6280/10874/10403/3783/827/6279/7368/3897
## Count
## MEL18_DN.V1_UP 61
## EGFR_UP.V1_UP 73
## RPS14_DN.V1_UP 71
## SNF5_DN.V1_UP 66
## P53_DN.V1_UP 70
## RAF_UP.V1_UP 70
head(msC6_2)
## ID
## RAF_UP.V1_DN RAF_UP.V1_DN
## RPS14_DN.V1_DN RPS14_DN.V1_DN
## KRAS.600.LUNG.BREAST_UP.V1_UP KRAS.600.LUNG.BREAST_UP.V1_UP
## KRAS.BREAST_UP.V1_UP KRAS.BREAST_UP.V1_UP
## KRAS.LUNG.BREAST_UP.V1_UP KRAS.LUNG.BREAST_UP.V1_UP
## BMI1_DN_MEL18_DN.V1_UP BMI1_DN_MEL18_DN.V1_UP
## Description setSize
## RAF_UP.V1_DN RAF_UP.V1_DN 124
## RPS14_DN.V1_DN RPS14_DN.V1_DN 109
## KRAS.600.LUNG.BREAST_UP.V1_UP KRAS.600.LUNG.BREAST_UP.V1_UP 107
## KRAS.BREAST_UP.V1_UP KRAS.BREAST_UP.V1_UP 46
## KRAS.LUNG.BREAST_UP.V1_UP KRAS.LUNG.BREAST_UP.V1_UP 65
## BMI1_DN_MEL18_DN.V1_UP BMI1_DN_MEL18_DN.V1_UP 95
## enrichmentScore NES pvalue
## RAF_UP.V1_DN 0.5972080 2.467707 1.000000e-10
## RPS14_DN.V1_DN -0.6268603 -2.146505 3.691517e-10
## KRAS.600.LUNG.BREAST_UP.V1_UP -0.6191844 -2.115243 1.030922e-09
## KRAS.BREAST_UP.V1_UP -0.7239233 -2.201967 5.140891e-08
## KRAS.LUNG.BREAST_UP.V1_UP -0.6708917 -2.142749 6.099317e-08
## BMI1_DN_MEL18_DN.V1_UP -0.5828157 -1.964062 2.522474e-07
## p.adjust qvalues rank
## RAF_UP.V1_DN 1.860000e-08 1.147368e-08 613
## RPS14_DN.V1_DN 3.433111e-08 2.117765e-08 951
## KRAS.600.LUNG.BREAST_UP.V1_UP 6.391714e-08 3.942823e-08 1055
## KRAS.BREAST_UP.V1_UP 2.268946e-06 1.399633e-06 1055
## KRAS.LUNG.BREAST_UP.V1_UP 2.268946e-06 1.399633e-06 1055
## BMI1_DN_MEL18_DN.V1_UP 7.633291e-06 4.708708e-06 1336
## leading_edge
## RAF_UP.V1_DN tags=31%, list=8%, signal=29%
## RPS14_DN.V1_DN tags=41%, list=12%, signal=37%
## KRAS.600.LUNG.BREAST_UP.V1_UP tags=45%, list=14%, signal=39%
## KRAS.BREAST_UP.V1_UP tags=52%, list=14%, signal=45%
## KRAS.LUNG.BREAST_UP.V1_UP tags=49%, list=14%, signal=43%
## BMI1_DN_MEL18_DN.V1_UP tags=45%, list=17%, signal=38%
## core_enrichment
## RAF_UP.V1_DN 7031/7033/57758/2674/6947/771/6542/8614/5507/4602/18/10560/10451/12/8821/2690/5046/3480/1960/6505/4254/27250/26018/3667/596/7358/23327/1955/3485/2353/9915/1363/403/214/863/3487/10769/7020
## RPS14_DN.V1_DN 29028/6535/55240/7052/26271/7083/5424/705/1894/3619/4174/8877/79723/6182/586/3601/1183/347733/1062/9055/9700/10046/3574/9824/10112/9787/56992/54821/23650/5347/79094/990/9156/11004/4998/9133/23397/4605/991/10874/79733/55388/875/29968/51083
## KRAS.600.LUNG.BREAST_UP.V1_UP 3037/2113/7185/1084/3770/2118/3553/5740/7128/23643/3669/951/50856/50486/4796/3757/1240/8877/5365/639/650/101/9966/54752/3294/5329/6367/919/330/28231/8728/51129/3902/6364/9435/51561/2921/7850/55613/3290/2919/2672/9047/6374/4318/1299/5646/4312
## KRAS.BREAST_UP.V1_UP 3037/7185/1084/3770/3553/7128/51700/1240/639/3294/6367/330/5140/3561/1946/2921/7850/3290/2672/4318/1299/1297/5653/27299
## KRAS.LUNG.BREAST_UP.V1_UP 3037/2113/7185/1084/3770/7128/3669/951/50486/1240/639/101/9966/54752/3294/919/330/28231/8728/51129/6364/51561/2921/7850/3290/2919/2672/9047/6374/4318/5646/4312
## BMI1_DN_MEL18_DN.V1_UP 1839/10184/5069/1464/3914/719/3037/9945/23657/1404/8876/3676/7436/4045/3696/5294/8828/3936/23046/6536/4494/3782/8061/5292/9469/22797/5329/1305/133/330/50515/8728/3575/79924/8140/81029/2919/3783/3604/56938/29968/51083/4316
grep(keyword, msC6$Description, ignore.case = TRUE)
## [1] 53
grep(keyword, msC6_2$Description, ignore.case = TRUE)
## [1] 3 4 5I tried other MSigDB categories (H,C1,C3,C4,C5,C7), but they didn’t
have information on breast.
3.3.1 Visualization
barplot(msC2, showCategory = 8)
dotplot(msC2, showCategory = 8)
emapplot(msC2)
4 Disease Analysis
4.1 enrichDO (Disease Ontology)
library(DOSE)
## DOSE v3.15.0 For help: https://guangchuangyu.github.io/software/DOSE
##
## If you use DOSE in published research, please cite:
## Guangchuang Yu, Li-Gen Wang, Guang-Rong Yan, Qing-Yu He. DOSE: an R/Bioconductor package for Disease Ontology Semantic and Enrichment analysis. Bioinformatics 2015, 31(4):608-609
edo <- enrichDO(gene = gene,
ont = "DO",
pvalueCutoff = 0.01,
pAdjustMethod = "BH",
universe = names(geneList),
qvalueCutoff = 0.01)
head(edo,3)
## ID Description GeneRatio BgRatio pvalue
## DOID:3213 DOID:3213 demyelinating disease 82/1667 113/4338 9.131900e-14
## DOID:2377 DOID:2377 multiple sclerosis 78/1667 109/4338 1.266316e-12
## DOID:3342 DOID:3342 bone inflammation disease 262/1667 495/4338 2.499925e-12
## p.adjust qvalue
## DOID:3213 6.465385e-11 4.046873e-11
## DOID:2377 4.482758e-10 2.805889e-10
## DOID:3342 5.899822e-10 3.692871e-10
## geneID
## DOID:3213 6505/730/5327/183/3485/1675/4179/5777/2212/2896/4314/3028/3557/4277/2213/1636/3122/3672/3429/6404/834/965/3115/961/3107/1152/3663/3659/3127/3123/6347/3119/4599/4261/3676/3394/3162/3553/929/64127/5788/3570/3106/920/348/3117/100133941/3135/3606/64135/3569/1410/2214/6507/2597/958/6376/3689/1230/6285/330/3925/923/3383/1236/3575/3105/2215/6556/1234/6352/2833/1594/2672/4318/3627/3559/1116/3002/3620/5653/4321
## DOID:2377 6505/730/5327/183/1675/4179/5777/2212/2896/4314/3028/3557/4277/2213/1636/3122/3672/3429/6404/834/965/3115/961/3107/1152/3663/3659/3127/3123/6347/3119/4599/4261/3676/3394/3162/3553/929/64127/5788/3570/3106/920/348/3117/100133941/3135/3606/64135/3569/1410/2214/6507/2597/958/6376/1230/330/3925/923/3383/1236/3575/3105/2215/6556/1234/6352/2833/1594/2672/4318/3627/3559/1116/3002/3620/4321
## DOID:3342 9518/7177/4488/6097/7079/9547/374/3081/2690/7432/54829/6584/4843/7433/388/10512/5327/10/10266/596/652/2487/3306/5914/2353/9368/7049/3291/8633/1958/1902/6583/1311/1191/3479/4128/3551/59307/727/862/5654/4331/7098/2064/55835/2212/1947/3251/4650/472/871/8771/2896/5591/9423/8718/5320/1436/581/7422/4314/3557/3709/6573/3108/64750/7852/5594/6590/56172/2213/22861/5743/1636/6282/5873/3329/23213/8797/5734/64221/6275/2289/3672/7099/6850/2956/567/965/3115/3680/7045/3107/811/7097/3965/4217/5328/5730/3820/1080/3663/578/3133/3459/3684/4481/64167/7133/240/3123/5947/11173/5713/7185/5371/5732/6347/2512/8793/3119/2821/3654/3937/4261/3091/54/3676/963/4851/9641/6775/3109/8837/3162/4689/3553/929/5996/1535/64127/5788/3570/728/3106/3066/843/6351/6513/637/249/5740/7128/5294/100/8828/2023/920/7913/5915/348/6366/50856/140766/58191/3117/1789/3135/126014/2357/117289/5321/7167/3606/5293/64135/9034/8877/10855/26191/9398/3569/1410/639/2214/650/101/942/1508/958/6376/9966/23406/1520/3689/1230/201294/10859/6367/919/133/9507/6696/25939/6891/3383/6890/3600/3574/1236/84868/3575/3105/8600/176/64170/6648/64581/9051/10673/9235/4050/7298/5347/3560/914/11240/6401/332/6369/2215/6556/7412/1234/655/6356/6364/54210/6352/8651/2833/29126/51561/6280/3934/50943/5008/3957/9047/5551/4318/6279/3604/50615/3627/27074/3559/1116/3002/4312/6362/10563
## Count
## DOID:3213 82
## DOID:2377 78
## DOID:3342 262
nrow(edo)
## [1] 141
grep(keyword, edo$Description, ignore.case = TRUE)
## [1] 1104.2 enrichNCG (Network of Cancer Gene)
gene2 <- names(geneList)[abs(geneList) < mean(abs(geneList))]
ncg <- enrichNCG(gene2)
head(ncg,3)
## ID Description GeneRatio BgRatio pvalue p.adjust
## prostate prostate prostate 34/516 53/1571 2.016079e-06 4.511725e-05
## breast breast breast 46/516 80/1571 2.819828e-06 4.511725e-05
## endometrial endometrial endometrial 31/516 53/1571 8.395634e-05 8.955343e-04
## qvalue
## prostate 0.0000222618
## breast 0.0000222618
## endometrial 0.0004418755
## geneID
## prostate 5295/595/1105/8405/3265/463/7403/207/324/9612/8289/4292/2077/5925/7113/673/5728/51755/5290/9611/84133/1030/9968/1027/7157/81614/672/3417/1499/5894/2778/5291/4609/4436
## breast 5295/595/196528/91/861/7188/55770/677/6416/207/324/6794/4763/51135/29072/8289/57492/2874/5925/5728/5290/208/79728/8314/6602/4089/9611/23451/55193/9968/1027/7157/999/83737/171023/672/2132/545/9175/896/841/114907/2033/3845/10664/79718
## endometrial 280/5295/595/8405/54880/57721/463/7130/54989/2122/25942/27316/6872/10060/4216/8289/84159/5728/4780/6146/5518/5290/7157/1108/7812/8239/545/1499/5426/3845/10664
## Count
## prostate 34
## breast 46
## endometrial 31
nrow(ncg)
## [1] 16
grep(keyword, ncg$Description, ignore.case = TRUE)
## [1] 24.3 enrichDGN (Disease-Gene Association)
dgn <- enrichDGN(gene)
head(dgn,3)
## ID Description GeneRatio BgRatio pvalue
## umls:C3495559 umls:C3495559 Juvenile arthritis 131/2426 333/17381 5.327870e-31
## umls:C0036202 umls:C0036202 Sarcoidosis 104/2426 253/17381 1.170121e-26
## umls:C0005695 umls:C0005695 Bladder Neoplasm 149/2426 442/17381 1.195323e-26
## p.adjust qvalue
## umls:C3495559 2.026722e-27 1.016782e-27
## umls:C0036202 1.515670e-23 7.603934e-24
## umls:C0005695 1.515670e-23 7.603934e-24
## geneID
## umls:C3495559 374/23541/3480/4929/1846/2065/2354/2353/9314/2194/1958/1191/10769/3693/2791/727/27086/3310/9790/800/8844/7422/4314/6786/3557/6573/7852/5594/22861/1636/5873/3329/7027/1839/7099/9734/51182/6515/3115/5696/5352/3663/3133/3659/3127/7133/3123/9334/7185/6347/10810/25816/3119/5771/3654/4261/3091/4973/6775/4478/3162/3553/929/5996/64127/2766/7128/113/7913/3669/84441/6366/58191/6772/3117/8013/2120/3135/8291/117289/3606/64135/1612/26191/3569/2214/1717/958/353514/5329/5698/201294/919/6696/6891/3383/6890/1236/3575/3105/8600/1844/9051/54757/1021/6401/2215/6556/2950/1234/6364/54210/6352/2833/8836/6280/1594/5588/50943/5008/926/10663/2919/9047/5551/6279/3627/3559/366/3002/6373
## umls:C0036202 4582/23541/4843/2735/7043/183/4485/3485/2353/3487/3479/727/10998/57728/4331/7098/9531/23583/4684/7042/51715/7422/8914/3557/3108/7852/5743/1636/5718/8809/3122/7099/3115/3107/5696/7097/54739/1080/3133/3127/3459/3123/6347/3371/3119/968/4261/3091/3791/3109/10892/3682/3553/929/64127/3106/1536/3669/6646/3117/100133941/6624/3135/3606/3569/2214/942/6367/4360/6696/6891/3383/6890/3600/3574/84868/3575/3105/6648/10673/9787/3702/6401/6556/7412/1234/6352/2833/6280/1594/3594/50943/59272/3120/727897/6374/6279/3627/3559/259307/1116/4283/27299/4321
## umls:C0005695 1555/9/2947/4582/119391/2261/1154/4843/4929/2735/2065/10/596/3908/6817/3485/6423/1728/7161/2194/214/267/1191/53834/648/3479/10769/152503/2272/90993/2954/6424/23221/4016/2064/4893/1545/2114/2706/472/26986/6714/2896/5591/5447/581/7422/290/10970/6573/23604/80781/7852/5898/4176/5743/6282/8797/9446/6275/7099/3429/8243/2619/5690/5467/5111/6916/811/3400/11200/5328/54739/1956/3659/3684/4502/3683/240/3732/6347/3091/59345/10682/6581/10397/4233/1890/286826/6513/1678/7913/5915/4171/5465/10460/6772/6624/2744/3918/3135/445/10855/7153/3569/4240/4085/1871/688/2146/29128/5329/6285/864/4360/330/7037/9332/9700/3383/3105/1869/6648/6241/7298/5347/6790/2175/332/7364/2950/699/29126/5268/8836/6280/1594/9582/10874/1029/2919/117247/4318/6279/597/898/5080/5646/4312
## Count
## umls:C3495559 131
## umls:C0036202 104
## umls:C0005695 149
nrow(dgn)
## [1] 1702
grep(keyword, dgn$Description, ignore.case = TRUE)
## [1] 8 25 40 100 361 421 448 585 665 723 744 783 871 1078 1145
## [16] 1159 1161 1224 1225 1284 1379 1419 17024.4 gseDO
edo2 <- gseDO(geneList)
## preparing geneSet collections...
## GSEA analysis...
## Warning in fgseaMultilevel(...): For some pathways, in reality P-values are less
## than 1e-10. You can set the `eps` argument to zero for better estimation.
## leading edge analysis...
## done...
head(edo2,3)
## ID Description setSize
## DOID:0050161 DOID:0050161 lower respiratory tract disease 331
## DOID:0050338 DOID:0050338 primary bacterial infectious disease 150
## DOID:0060056 DOID:0060056 hypersensitivity reaction disease 428
## enrichmentScore NES pvalue p.adjust qvalues rank
## DOID:0050161 -0.5145600 -1.964878 1e-10 4.164706e-09 2.352941e-09 1646
## DOID:0050338 -0.6059806 -2.151627 1e-10 4.164706e-09 2.352941e-09 1624
## DOID:0060056 -0.5138929 -1.982878 1e-10 4.164706e-09 2.352941e-09 1231
## leading_edge
## DOID:0050161 tags=41%, list=21%, signal=34%
## DOID:0050338 tags=55%, list=21%, signal=44%
## DOID:0060056 tags=36%, list=16%, signal=32%
## core_enrichment
## DOID:0050161 581/10592/7422/10630/10875/4314/3557/80781/7852/6590/3631/6446/22861/5743/1636/3329/8797/8091/9446/8809/2627/2294/57016/7099/3429/6404/5111/7097/3965/5328/1080/3663/719/3659/3459/3684/7498/3683/4481/3123/5270/2534/6347/3371/3119/50506/3091/10051/3676/3791/8837/3162/3682/3553/929/4233/64127/728/6338/3779/5294/3587/100/1475/51393/4688/1672/3055/348/653361/6366/6772/3918/3606/5293/59341/64135/3569/101/942/958/6376/1520/3689/5329/6367/6285/133/1439/6696/81930/6891/3383/6890/3574/4794/6648/3702/3001/6369/2215/6556/925/2950/7412/1234/990/6356/3932/54210/6352/8651/136/2833/29126/6280/3594/7039/50943/59272/1029/10663/1138/727897/5266/6374/4318/3627/1116/4283/3620/6373/27299/4316/4312/6362/4321
## DOID:0050338 7422/79139/4314/3557/8717/7852/5743/1636/5236/3329/1839/7099/7296/834/3115/5696/7097/3659/3459/3683/7133/240/3123/5028/6347/3371/3119/3687/7096/3553/929/64127/728/3106/6351/100/23643/1672/348/6402/3606/1510/26191/3569/639/942/5329/5698/6367/919/4360/6891/3383/6890/1236/3105/7535/9235/3001/6556/1234/30835/939/6356/6364/3932/54210/6352/8651/29126/3934/3594/5551/4318/26227/597/3627/3559/952/3620/6373/4312
## DOID:0060056 3115/961/81567/3107/5696/6916/7097/5328/5352/1080/3663/578/3133/3659/3459/3684/7498/3683/7512/7133/9043/3123/5270/7185/5954/6347/3371/11168/3119/4599/3654/4261/3091/3791/140885/7052/6775/10892/3162/3682/3553/929/4233/64127/10062/5788/3570/3106/843/7128/3587/100/3455/920/8784/1672/675/348/653361/5465/7292/6366/58191/6772/3117/100133941/3135/1051/117289/6402/3606/7293/64135/79172/10068/6614/26191/4067/3569/2214/10257/942/958/6376/23406/5329/5698/6367/6285/919/10437/133/4360/3930/6696/43/7037/923/6891/8989/3383/6890/3600/3574/1236/84868/3575/3105/6648/1131/10673/4064/6401/332/2215/6556/925/2950/1234/30835/939/6356/54210/6352/2833/29126/6280/1594/3934/50943/926/59272/10663/10578/1058/6374/4318/6279/3604/26227/3627/3559/1116/3002/4283/3620/27299/10537/4312/6362/10563/4321
nrow(edo2)
## [1] 274
grep(keyword, edo2$Description, ignore.case = TRUE)
## [1] 2554.5 gseNCG
ncg2 <- gseNCG(geneList)
## preparing geneSet collections...
## GSEA analysis...
## no term enriched under specific pvalueCutoff...
head(ncg2,3)
## [1] ID Description setSize enrichmentScore
## [5] NES pvalue p.adjust qvalues
## <0 rows> (or 0-length row.names)
nrow(ncg2)
## [1] 0
grep(keyword, ncg2$Description, ignore.case = TRUE)
## integer(0)4.6 gseDGN
dgn2 <- gseDGN(geneList)
## preparing geneSet collections...
## GSEA analysis...
## Warning in fgseaMultilevel(...): For some pathways, in reality P-values are less
## than 1e-10. You can set the `eps` argument to zero for better estimation.
## leading edge analysis...
## done...
head(dgn2,3)
## ID Description setSize enrichmentScore
## umls:C0003864 umls:C0003864 Arthritis 340 -0.4916472
## umls:C0004364 umls:C0004364 Autoimmune Diseases 478 -0.5180893
## umls:C0011615 umls:C0011615 Dermatitis, Atopic 250 -0.5815581
## NES pvalue p.adjust qvalues rank
## umls:C0003864 -1.876806 1e-10 1.477895e-08 1.057618e-08 1231
## umls:C0004364 -2.014219 1e-10 1.477895e-08 1.057618e-08 1541
## umls:C0011615 -2.172049 1e-10 1.477895e-08 1.057618e-08 1364
## leading_edge
## umls:C0003864 tags=35%, list=16%, signal=31%
## umls:C0004364 tags=42%, list=20%, signal=36%
## umls:C0011615 tags=46%, list=17%, signal=39%
## core_enrichment
## umls:C0003864 3115/961/81567/7097/3965/409/4217/6223/3133/3659/3684/3683/7133/240/3123/11173/7185/91543/6347/3371/3119/5771/2821/3654/7454/8856/54/284/3791/5337/6775/7096/3553/929/64127/2048/728/3106/10849/1536/7128/5294/3587/2023/51393/3669/6646/653361/6366/2643/3117/1051/126014/5321/6402/3606/445/9034/9123/8877/26191/3569/2214/650/1508/958/9966/3689/5698/201294/6285/9507/4360/3118/6696/9055/6891/8989/3383/6890/3600/3574/3105/8600/7535/176/4069/6648/10673/51129/9235/4050/11240/9466/2215/6556/2950/7412/1234/939/54210/6352/51561/6280/50943/5008/1029/10663/2305/4318/146433/6279/50615/3627/3559/1116/4312/4321
## umls:C0004364 57819/7852/5594/6654/10461/2213/9377/22861/5743/6749/1636/29933/3329/64221/7305/8809/7099/9474/9734/2091/56913/7873/9170/51182/567/10457/3115/55697/961/3107/5696/811/7097/1786/716/3820/26147/3663/719/84876/122769/578/3133/3127/3684/4783/5699/3683/64167/8833/7133/2113/3123/7185/5371/6347/11168/3119/215/5771/3654/7454/8856/4261/3111/140885/5337/7052/963/6775/5817/10892/3394/3162/3553/929/5996/64127/5788/3570/728/3106/1032/55824/7128/5294/113/4904/2023/920/7913/3669/1672/6646/653361/5465/23046/7292/6366/4860/50856/3117/10993/100133941/8013/3135/117289/7167/6402/3606/5293/7293/445/64135/9034/23250/10855/26191/3569/10320/5292/2214/4240/650/942/1508/958/3134/9966/23406/2146/1043/3689/5698/10859/6285/919/133/864/4360/330/3118/6696/10603/25939/6891/3383/2633/3600/3574/1236/84868/3575/3105/8600/6648/64581/9051/10673/2153/3561/340348/9235/8140/10870/2491/916/3560/914/2215/6556/717/939/6352/8651/3718/11006/2833/29126/3662/51561/6280/1594/7850/50943/3120/1029/10663/2919/5551/6374/4318/8645/6279/3604/50615/1299/3627/3559/3112/3002/3620/4312
## umls:C0011615 9882/6275/8809/7099/63940/7296/6281/6404/834/706/1593/5696/7097/1786/5328/5730/1956/84876/3133/3459/3684/7903/7133/3123/3059/5713/6347/3371/11168/3119/7454/8856/4261/8876/3111/4851/7096/84433/3162/4689/3553/929/64127/3106/1475/8784/3669/1672/5971/5465/962/25797/2207/80896/3117/2744/29127/3606/1510/9034/3569/1508/958/6376/9966/5329/5698/6367/341/4360/3930/6891/3383/6890/3600/3574/3575/3105/64581/79924/5140/9235/3560/6401/6369/6556/2950/7412/1234/30835/939/6356/6364/54210/6352/8651/6273/2833/51561/6280/1594/3594/50943/5008/3120/2919/6279/50615/597/3627/3559/4283/5653/6362
nrow(dgn2)
## [1] 518
grep(keyword, dgn2$Description, ignore.case = TRUE)
## [1] 53 134 335 341 4495 Gene Ontology Analysis
5.1 GO over-representation test
5.2 GO GSEA
library(clusterProfiler)
ego2 <- gseGO(geneList = geneList,
OrgDb = org.Hs.eg.db,
ont = "MF",
nPerm = 1000,
minGSSize = 50,
maxGSSize = 500,
pvalueCutoff = 0.05,
verbose = FALSE)
## Warning in .GSEA(geneList = geneList, exponent = exponent, minGSSize =
## minGSSize, : We do not recommend using nPerm parameter incurrent and future
## releases
## Warning in fgsea(pathways = geneSets, stats = geneList, nperm = nPerm, minSize
## = minGSSize, : 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.
head(ego2,3)
## ID Description setSize
## GO:0038023 GO:0038023 signaling receptor activity 435
## GO:0060089 GO:0060089 molecular transducer activity 435
## GO:0004888 GO:0004888 transmembrane signaling receptor activity 323
## enrichmentScore NES pvalue p.adjust qvalues rank
## GO:0038023 -0.4592867 -1.761631 0.001036269 0.03532835 0.03135436 1135
## GO:0060089 -0.4592867 -1.761631 0.001036269 0.03532835 0.03135436 1135
## GO:0004888 -0.4829783 -1.819230 0.001069519 0.03532835 0.03135436 1135
## leading_edge
## GO:0038023 tags=33%, list=15%, signal=30%
## GO:0060089 tags=33%, list=15%, signal=30%
## GO:0004888 tags=37%, list=15%, signal=33%
## core_enrichment
## GO:0038023 5789/3820/1956/719/6091/5361/4074/6608/3459/29121/3683/7133/23596/5732/5028/2049/5621/8477/8793/3119/132014/1880/8856/10682/3687/3676/3791/3111/4851/2906/5817/10990/7096/5796/10507/929/4233/10062/5788/3570/2048/9934/728/8324/7436/3696/3587/8828/3455/5724/23643/920/8784/5915/2564/1944/5465/10082/962/50856/2207/150372/3117/8013/5727/126014/2357/11314/2047/7293/59341/9034/1240/8877/5365/5800/7849/11245/54756/942/958/3601/25928/8698/3689/1230/5329/10859/919/4360/1439/3695/3118/3383/6693/1236/165140/3575/65078/59352/971/10288/1131/23432/3561/916/3560/914/9466/921/6401/925/2359/56963/3902/1234/11025/939/915/54210/136/11006/2833/974/10913/3594/7850/7804/926/924/3120/5031/10663/8549/1138/3872/973/3604/50615/3559/3112/3897/51083/27199
## GO:0060089 5789/3820/1956/719/6091/5361/4074/6608/3459/29121/3683/7133/23596/5732/5028/2049/5621/8477/8793/3119/132014/1880/8856/10682/3687/3676/3791/3111/4851/2906/5817/10990/7096/5796/10507/929/4233/10062/5788/3570/2048/9934/728/8324/7436/3696/3587/8828/3455/5724/23643/920/8784/5915/2564/1944/5465/10082/962/50856/2207/150372/3117/8013/5727/126014/2357/11314/2047/7293/59341/9034/1240/8877/5365/5800/7849/11245/54756/942/958/3601/25928/8698/3689/1230/5329/10859/919/4360/1439/3695/3118/3383/6693/1236/165140/3575/65078/59352/971/10288/1131/23432/3561/916/3560/914/9466/921/6401/925/2359/56963/3902/1234/11025/939/915/54210/136/11006/2833/974/10913/3594/7850/7804/926/924/3120/5031/10663/8549/1138/3872/973/3604/50615/3559/3112/3897/51083/27199
## GO:0004888 5789/3820/1956/719/6091/5361/4074/6608/3459/29121/3683/7133/23596/5732/5028/2049/8477/8793/3119/132014/1880/10682/3791/3111/4851/2906/10990/7096/5796/10507/929/4233/5788/3570/2048/9934/728/8324/7436/3587/8828/3455/5724/920/8784/2564/1944/50856/2207/150372/3117/5727/126014/2357/2047/7293/59341/9034/1240/8877/5365/5800/7849/11245/54756/3601/25928/8698/3689/1230/10859/919/4360/1439/3118/3383/6693/1236/165140/3575/65078/59352/971/10288/1131/23432/3561/916/3560/9466/921/6401/2359/3902/1234/11025/939/915/136/2833/974/10913/3594/7850/7804/3120/5031/10663/8549/1138/3872/973/50615/3559/3112/3897/51083/27199
nrow(ego2)
## [1] 9
grep(keyword, ego2$Description, ignore.case = TRUE)
## integer(0)5.3 GO semantic similarity analysis
6 KEGG analysis
6.1 KEGG ORA
kk <- enrichKEGG(gene = gene,
organism = 'hsa',
pvalueCutoff = 0.05)
## Reading KEGG annotation online:
##
## Reading KEGG annotation online:
head(kk,3)
## ID Description GeneRatio BgRatio
## hsa05166 hsa05166 Human T-cell leukemia virus 1 infection 88/1685 219/8040
## hsa05169 hsa05169 Epstein-Barr virus infection 81/1685 201/8040
## hsa04110 hsa04110 Cell cycle 57/1685 124/8040
## pvalue p.adjust qvalue
## hsa05166 4.285444e-11 1.384198e-08 9.473087e-09
## hsa05169 2.190592e-10 3.248737e-08 2.223350e-08
## hsa04110 3.017403e-10 3.248737e-08 2.223350e-08
## geneID
## hsa05166 4488/148327/115/7043/111/4776/2353/4214/112/1958/3551/90993/4893/2114/472/7042/581/3108/2224/8295/5594/4791/109/4775/9134/9519/3122/567/706/3115/55697/3107/894/811/11200/3133/5901/3127/3683/2113/3123/5902/3119/3111/64764/6688/3109/3106/6513/113/920/5971/3117/3135/5293/8061/3569/4085/1871/958/3601/3134/3689/3118/9700/3383/3600/3105/1869/890/701/3561/1111/916/3560/9232/915/3932/1870/3718/9133/991/7850/1029/3559/898/3112/4316
## hsa05169 377841/10912/596/3551/4940/836/7187/5708/7186/8819/6773/581/5704/8717/3108/10213/4791/5718/9134/4615/4793/3122/11047/6850/54205/567/965/4939/3115/3107/6502/894/811/7097/578/3133/3127/3683/3123/5713/3119/695/3654/3111/9641/3109/5336/3106/3066/637/7128/3455/5971/6772/3117/3135/6300/5293/4067/3569/1871/958/3134/919/864/3118/6891/3383/6890/3105/1869/4794/890/1021/916/915/1870/3718/3627/898/3112
## hsa04110 10912/7043/6500/7534/10971/472/7042/5591/5885/4176/9134/2810/7027/8243/5111/6502/894/11200/10459/10926/1875/4172/4175/5933/3066/1032/4173/994/8317/4171/891/4174/4085/1871/995/983/9088/9700/1869/23594/890/701/1111/1021/5347/8318/990/9232/1870/4998/699/9133/7272/993/991/1029/898
## Count
## hsa05166 88
## hsa05169 81
## hsa04110 57
nrow(kk)
## [1] 79
grep(keyword, kk$Description, ignore.case = TRUE)
## integer(0)6.2 KEGG GSEA
kk2 <- gseKEGG(geneList = geneList,
organism = 'hsa',
nPerm = 1000,
minGSSize = 120,
pvalueCutoff = 0.05,
verbose = FALSE)
## Warning in .GSEA(geneList = geneList, exponent = exponent, minGSSize =
## minGSSize, : We do not recommend using nPerm parameter incurrent and future
## releases
## Warning in fgsea(pathways = geneSets, stats = geneList, nperm = nPerm, minSize
## = minGSSize, : 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.
head(kk2,3)
## ID Description setSize
## hsa05166 hsa05166 Human T-cell leukemia virus 1 infection 196
## hsa05169 hsa05169 Epstein-Barr virus infection 173
## hsa04062 hsa04062 Chemokine signaling pathway 136
## enrichmentScore NES pvalue p.adjust qvalues rank
## hsa05166 -0.4802437 -1.752611 0.001119821 0.006898873 0.004782274 1550
## hsa05169 -0.5024881 -1.811147 0.001129944 0.006898873 0.004782274 2115
## hsa04062 -0.5286815 -1.851880 0.001166861 0.006898873 0.004782274 905
## leading_edge
## hsa05166 tags=36%, list=20%, signal=30%
## hsa05169 tags=50%, list=27%, signal=37%
## hsa04062 tags=30%, list=12%, signal=27%
## core_enrichment
## hsa05166 3108/2224/8295/5594/4791/109/4775/9134/9519/3122/567/706/3115/55697/3107/894/811/11200/3133/5901/3127/3683/2113/3123/5902/3119/3111/64764/6688/3109/3106/6513/113/920/5971/3117/3135/5293/8061/3569/4085/1871/958/3601/3134/3689/3118/9700/3383/3600/3105/1869/890/701/3561/1111/916/3560/9232/915/3932/1870/3718/9133/991/7850/1029/3559/898/3112/4316
## hsa05169 5291/3113/7431/5707/355/6892/4609/5702/5600/5606/4940/836/7187/5708/7186/8819/6773/581/5704/8717/3108/10213/4791/5718/9134/4615/4793/3122/11047/6850/54205/567/965/4939/3115/3107/6502/894/811/7097/578/3133/3127/3683/3123/5713/3119/695/3654/3111/9641/3109/5336/3106/3066/637/7128/3455/5971/6772/3117/3135/6300/5293/4067/3569/1871/958/3134/919/864/3118/6891/3383/6890/3105/1869/4794/890/1021/916/915/1870/3718/3627/898/3112
## hsa04062 7454/59345/5880/23533/7409/1794/6351/53358/5294/113/3055/653361/6366/58191/6772/5293/2268/4067/6376/1230/5579/6367/1236/3702/6369/1234/6356/6364/6352/3718/2833/2921/10663/2919/6374/2786/3627/4283/6373/6362/10563
nrow(kk2)
## [1] 12
grep(keyword, kk2$Description, ignore.case = TRUE)
## integer(0)6.3 KEGG Module over-representation test
mkk <- enrichMKEGG(gene = gene,
organism = 'hsa')
## Reading KEGG annotation online:
##
## Reading KEGG annotation online:
head(mkk,3)
## [1] ID Description GeneRatio BgRatio pvalue p.adjust
## [7] qvalue geneID Count
## <0 rows> (or 0-length row.names)
nrow(mkk)
## [1] 0
grep(keyword, mkk$Description, ignore.case = TRUE)
## integer(0)6.4 KEGG Module GSEA
mkk2 <- gseMKEGG(geneList = geneList,
organism = 'hsa')
## preparing geneSet collections...
## GSEA analysis...
## leading edge analysis...
## done...
head(mkk2,3)
## ID Description setSize enrichmentScore NES
## M00099 M00099 Sphingosine biosynthesis 12 0.8334802 2.178786
## M00094 M00094 Ceramide biosynthesis 10 0.8362049 2.084306
## pvalue p.adjust qvalues rank leading_edge
## M00099 0.0001856406 0.003668212 0.003146224 634 tags=42%, list=8%, signal=38%
## M00094 0.0002717194 0.003668212 0.003146224 634 tags=40%, list=8%, signal=37%
## core_enrichment
## M00099 123099/79603/340485/253782/29956
## M00094 123099/79603/253782/29956
nrow(mkk2)
## [1] 2
grep(keyword, mkk2$Description, ignore.case = TRUE)
## integer(0)7 Reactome pathway analysis
7.1 Pathway Enrichment Analysis
library(ReactomePA)
## ReactomePA v1.33.0 For help: https://guangchuangyu.github.io/ReactomePA
##
## If you use ReactomePA in published research, please cite:
## Guangchuang Yu, Qing-Yu He. ReactomePA: an R/Bioconductor package for reactome pathway analysis and visualization. Molecular BioSystems 2016, 12(2):477-479
rp <- enrichPathway(gene = gene, pvalueCutoff = 0.05, readable = TRUE)
head(rp,3)
## ID Description GeneRatio BgRatio
## R-HSA-877300 R-HSA-877300 Interferon gamma signaling 48/2402 92/10654
## R-HSA-453279 R-HSA-453279 Mitotic G1-G1/S phases 65/2402 149/10654
## R-HSA-194315 R-HSA-194315 Signaling by Rho GTPases 151/2402 455/10654
## pvalue p.adjust qvalue
## R-HSA-877300 4.834203e-10 6.685703e-07 5.887551e-07
## R-HSA-453279 7.143124e-09 4.939470e-06 4.349787e-06
## R-HSA-194315 6.891989e-08 2.669242e-05 2.350583e-05
## geneID
## R-HSA-877300 TRIM45/TRIM3/SOCS3/NCAM1/PTPN6/OAS3/GBP2/CAMK2D/TRIM22/HLA-DRA/B2M/OAS2/HLA-DPB1/HLA-C/IRF5/HLA-E/IRF1/HLA-DRB5/IFNGR1/MT2A/HLA-DRB1/PML/HLA-DQB1/PTPN2/CIITA/IRF8/HLA-B/PTAFR/STAT1/HLA-DQA1/HLA-G/GBP4/TRIM10/HLA-F/IFI30/MID1/HLA-DQA2/ICAM1/GBP1/HLA-A/TRIM2/OASL/TRIM29/VCAM1/SOCS1/IRF4/HLA-DQB2/GBP5
## R-HSA-453279 PTK6/CABLES1/SKP1/MNAT1/PSMA2/PSMD2/SRC/PSMB3/PSMC4/PSMD14/PSMA4/MCM7/PSMD12/CCNE2/TFDP1/PSMB4/PSMA5/PSMB2/PCNA/PSMB8/SKP2/CCND2/GMNN/PSMB6/PSMA7/PSMB10/DBF4/PSMD7/E2F5/CKS1B/MCM3/PRIM2/MCM8/FBXO5/MCM6/TK1/RBL1/LIN9/CDKN2D/MCM4/CDC7/MCM2/CCNB1/MCM5/TOP2A/LYN/E2F3/CDK1/PSMB9/E2F1/ORC6/CCNA2/CDT1/RRM2/CDK6/TYMS/CDC45/CDC6/E2F2/ORC1/CDC25A/MYBL2/CDKN2A/MCM10/CCNE1
## R-HSA-194315 ARHGEF38/TUBAL3/VAV3/FGD3/EVL/RHOB/SYDE2/MYH11/ARHGEF16/ARHGAP6/STARD13/ARHGEF37/ARHGEF26/CENPP/NOXA1/RHOD/PPP2R5A/ARHGEF15/ARHGAP32/PREX1/RHOBTB2/RHOH/GDI2/RANGAP1/FAM13A/ARHGAP26/CKAP5/RTKN/SEH1L/FGD4/ARHGEF10L/SRGAP2/ACTR2/YWHAZ/MYO9B/YWHAQ/BCR/RHOG/DIAPH2/SRC/ARPC2/ARHGAP18/ACTB/NF2/FGD1/DSN1/TUBA1B/MAPK1/SOS1/DEPDC7/PFN2/ARHGAP21/LIMK2/LIMK1/RHOQ/SKA2/SEC13/WASF1/SFN/CENPK/ZWILCH/TIAM2/PPP1CB/FLNA/GMIP/CENPQ/NCK1/RHOV/PFN1/ARHGAP15/ZWINT/ARPC5/KLC3/ARHGAP4/CFTR/ARPC1B/RHOF/ARHGEF9/FMNL1/ACTR3/KNTC1/WASF3/ARHGAP27/BTK/WAS/WIPF1/PLEKHG2/RAC2/SPC25/ARHGAP25/TUBB6/VAV1/TUBA1C/TUBA8/NCF4/ARAP2/CYBA/ARHGAP9/KALRN/CYBB/CENPL/NCKAP1L/NCF2/CIT/NCF1/TUBA4A/ECT2/INCENP/ARHGAP30/RACGAP1/TAGAP/CENPO/ARHGAP22/PRKCA/MAD2L1/FGD2/NOXO1/CDC25C/FMNL2/PRKCB/TUBB2B/CENPE/KIF18A/PRC1/ARHGAP11A/CENPN/BUB1B/CENPF/ERCC6L/CENPI/CDCA8/PLK1/BIRC5/DIAPH3/NUF2/IQGAP3/DEPDC1B/ARHGEF4/SPC24/KIF2C/BUB1/CENPM/S100A9/SKA1/CDC20/AURKB/KIF14/NDC80/TUBB3/CENPA/S100A8
## Count
## R-HSA-877300 48
## R-HSA-453279 65
## R-HSA-194315 151
nrow(rp)
## [1] 84
grep(keyword, rp$Description, ignore.case = TRUE)
## integer(0)7.2 Gene Set Enrichment Analysis
rp2 <- gsePathway(geneList, nPerm = 10000, pvalueCutoff = 0.05, pAdjustMethod = "BH", verbose = FALSE)
## Warning in .GSEA(geneList = geneList, exponent = exponent, minGSSize =
## minGSSize, : We do not recommend using nPerm parameter incurrent and future
## releases
## Warning in fgsea(pathways = geneSets, stats = geneList, nperm = nPerm, minSize
## = minGSSize, : 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.
rp2 <- as.data.frame(rp2)
head(rp2,3)
## ID Description setSize enrichmentScore
## R-HSA-69278 R-HSA-69278 Cell Cycle, Mitotic 446 -0.4881128
## R-HSA-6798695 R-HSA-6798695 Neutrophil degranulation 389 -0.4226073
## R-HSA-194315 R-HSA-194315 Signaling by Rho GTPases 360 -0.4154017
## NES pvalue p.adjust qvalues rank
## R-HSA-69278 -1.883439 0.0001037237 0.004134591 0.003556713 2008
## R-HSA-6798695 -1.620113 0.0001046244 0.004134591 0.003556713 2154
## R-HSA-194315 -1.587254 0.0001051635 0.004134591 0.003556713 1958
## leading_edge
## R-HSA-69278 tags=40%, list=26%, signal=32%
## R-HSA-6798695 tags=41%, list=28%, signal=31%
## R-HSA-194315 tags=38%, list=25%, signal=30%
## core_enrichment
## R-HSA-69278 3796/4609/5693/51529/1874/79902/5702/5048/5982/10714/5983/6117/55920/29781/5905/5683/9793/81929/7443/55835/84131/1459/5708/6714/23165/23225/23198/5691/10592/5885/5704/9663/79980/1763/23310/10376/23141/5594/10213/5685/4176/23354/10762/348235/5718/9134/6396/55722/64105/55055/7027/5500/5692/54801/8243/5686/55559/5690/55166/23636/5111/5696/6502/894/11130/203068/7112/51053/93323/5694/5688/5699/10926/84930/5713/9735/1875/64785/1163/5984/4172/5558/10051/10733/22995/54892/84515/26271/10133/4175/7083/57405/84617/5933/84790/51807/4001/5424/286826/1032/4173/91687/994/8317/4171/891/9688/7277/3619/4174/2237/79172/7153/4067/5578/4085/3161/1871/9837/9918/995/983/79866/9088/5579/5698/64151/84296/157570/347733/23175/1062/81930/9700/1869/10112/23594/55839/890/701/1063/4751/81620/6241/54821/1021/2491/55143/7298/5347/6790/332/83540/8318/22974/990/9232/147841/1870/11004/4998/699/9133/23397/79019/113130/11065/993/220134/4605/991/9212/1029/10403/10381/2305/1058/51512/55388/898
## R-HSA-6798695 5795/10043/10312/10694/5834/23071/2547/5707/6386/8907/683/2992/81619/23593/1729/121260/5211/55754/2519/5702/4831/2720/1509/1512/64386/5223/4893/2665/5683/5777/3310/2212/1832/10097/5708/391/2896/10875/290/79980/10970/56888/5660/5594/6590/10213/7226/25798/6282/5873/5718/10577/5236/7305/51071/3482/11322/4125/5686/567/6515/965/961/81567/3107/9535/11010/7097/84329/10092/80301/5328/4332/203068/719/4033/54509/3684/6793/3683/7133/240/10549/1522/5713/8566/2512/2821/1084/272/968/8876/3687/4973/140885/5337/411/10396/963/3608/51411/23114/1794/929/1535/5788/728/64333/3106/8514/23200/1536/2760/5912/5724/79930/3071/3903/25797/4860/2207/150372/4257/51316/126014/2357/11314/6402/1476/23250/10855/2268/374403/101/1508/23406/1520/3689/5329/201294/230/2171/4069/11240/1075/2215/6556/2950/8836/6280/3934/10326/2919/3101/4318/6279/6518/5317/5646/1116
## R-HSA-194315 1729/79902/10093/5048/4627/10006/5600/55920/2665/5905/10144/23092/9793/6242/81929/121512/55160/23380/10097/7534/4650/10971/613/391/1730/6714/10109/93663/60/4771/2245/79980/10376/5594/6654/91614/5217/57584/3985/3984/23433/348235/6396/8936/2810/64105/55055/26230/5500/2316/51291/55166/4690/171177/5216/55843/11130/10092/147700/393/1080/10095/54509/23229/752/10096/9735/10810/201176/695/7454/7456/64857/5880/57405/9938/84617/7409/84790/51807/4689/116984/1535/64333/8997/1536/91687/3071/4688/11113/653361/7277/1894/3619/257106/29127/117289/79172/58504/5578/4085/221472/124056/995/114793/5579/347733/1062/81930/9055/9824/55839/701/1063/54821/2491/55143/5347/332/81624/83540/128239/55789/50649/147841/11004/699/79019/6280/220134/991/9212/9928/10403/10381/1058/6279
nrow(rp2)
## [1] 95
grep(keyword, rp2$Description, ignore.case = TRUE)
## integer(0)8 MeSH enrichment analysis
8.1 Over representation analysis
library(meshes)
## meshes v1.15.0
##
## If you use meshes in published research, please cite the most appropriate paper(s):
##
## Guangchuang Yu.Using meshes for MeSH term enrichment and semantic analyses.Bioinformatics 2018, 34(21):3766-3767, doi:10.1093/bioinformatics/bty410
##
## Attaching package: 'meshes'
## The following object is masked from 'package:DOSE':
##
## geneSim
library(MeSH.Hsa.eg.db)
## Loading required package: MeSHDbi
##
## Attaching package: 'MeSHDbi'
## The following object is masked from 'package:utils':
##
## packageName
emesh <- enrichMeSH(gene, MeSHDb = "MeSH.Hsa.eg.db", database = 'gendoo', category = 'C')
head(emesh)
## ID Description GeneRatio BgRatio
## D016399 D016399 Lymphoma, T-Cell 159/2371 391/16528
## D016403 D016403 Lymphoma, Large B-Cell, Diffuse 173/2371 459/16528
## D003093 D003093 Colitis, Ulcerative 172/2371 474/16528
## D007239 D007239 Infection 149/2371 385/16528
## D015459 D015459 Leukemia-Lymphoma, Adult T-Cell 156/2371 419/16528
## D019698 D019698 Hepatitis C, Chronic 130/2371 317/16528
## pvalue p.adjust qvalue
## D016399 4.042133e-38 9.026083e-35 3.497509e-35
## D016403 2.496510e-36 2.787354e-33 1.080069e-33
## D003093 1.049215e-33 7.809656e-31 3.026156e-31
## D007239 7.143407e-33 3.987807e-30 1.545232e-30
## D015459 4.211671e-32 1.880932e-29 7.288407e-30
## D019698 9.557356e-32 3.556929e-29 1.378271e-29
## geneID
## D016399 6947/10560/638/2261/5618/4843/10/2057/596/10840/2042/1728/7161/3708/1191/6927/3164/10588/9021/5777/2734/836/472/613/8771/5591/6773/581/2280/7422/3710/790/3557/3709/6573/8726/2650/5594/5156/5743/3556/8797/4793/26230/6404/11047/867/27040/567/706/5111/5696/894/1786/11200/578/3659/3459/5699/2113/752/2534/10863/3119/7454/968/4261/3091/3676/3791/4851/6775/6688/84433/7409/4478/8837/10125/3682/3553/5788/4830/6513/10849/637/2242/100/5272/920/8784/5971/7277/962/6772/2120/3135/7293/29078/1612/6614/7153/639/6566/942/3601/1043/6491/5698/6932/10859/919/3695/43/7037/6891/6890/6693/3600/1236/5452/1869/971/7535/83439/3561/3702/4050/1021/7298/916/3560/914/332/1234/9232/3932/8651/3718/2833/29126/3662/974/5588/7850/50943/5008/51513/2672/9047/973/838/875/3559/898/952/3002/4283/6373/10563
## D016403 1287/4843/5327/596/1728/7161/1191/648/3551/6430/2272/27086/399/5777/2212/1832/836/472/8771/7186/57019/581/7422/3557/6573/2213/4791/5743/6282/3329/8797/5734/6480/241/8809/6627/7099/892/6850/2956/567/5111/894/3400/11200/5328/4082/1282/1080/1956/7159/4033/578/3133/54509/3659/1284/3459/2113/3123/7805/60489/3732/3119/5771/7454/968/4261/3091/54/10682/3687/4851/9641/6688/3855/10892/84433/7409/4478/8837/3553/4233/64127/5336/5788/4830/6513/1032/705/637/55824/994/5294/3587/100/5272/2023/4171/891/6772/6624/1051/7293/6614/7153/4067/5578/3569/10320/5292/639/2214/942/958/5142/3601/712/1043/6491/5329/5579/3925/7037/1978/9055/3383/6693/3600/1236/3575/5452/1869/8600/7535/10673/1111/916/5347/6790/3001/921/6401/332/6556/2950/2178/7412/1234/9232/6352/8651/3718/7272/2833/3662/993/974/50943/5008/1029/10663/4318/973/10644/50615/898/259307/952/3002/4283/4316/10563
## D003093 7031/7033/9/1811/7494/7432/4583/6584/4843/3480/3572/10/4485/3306/79148/3382/3485/6423/4214/9863/7122/3291/2169/6583/3856/3479/3551/8639/79589/2272/83998/7098/23600/6550/9021/836/4650/10109/7042/8718/5320/581/6789/4314/5967/3557/4277/6590/2920/5743/6749/1636/3556/3122/2289/3672/7099/2956/5111/3107/7097/3914/3820/1080/1956/3659/8767/3683/7133/2113/3123/7185/6347/3119/5771/7454/8856/968/4261/3091/3687/9641/6688/3855/7096/3162/4689/3682/3553/929/56667/1535/4233/64127/6338/3106/3384/4585/4904/8784/1672/7292/6366/6772/3117/1244/3135/3606/7293/26191/3569/4085/942/2597/958/9966/6948/3689/5329/5579/6367/864/330/6696/9332/6891/3383/6890/6693/3600/1236/3105/8600/890/64170/2153/1111/4050/3560/332/6369/2215/6556/2950/1234/30835/6356/6364/54210/8651/699/2833/8836/51561/3934/50943/1029/2919/5266/6374/4318/321/7941/3627/952/3002/4283/11254/4316/4312/10563/4321
## D007239 9/5733/6337/7079/126/7432/4843/3480/30061/3875/5327/10/3315/125/3306/2053/2157/3479/3551/51478/727/116835/4179/7098/9021/5777/23210/3310/2212/836/871/8771/7186/60/7422/4314/3557/55343/6590/22861/5743/1636/3556/8797/7305/4615/8809/7099/51182/567/5216/3107/7097/2177/3820/1080/3659/3459/8767/4502/7133/5732/6347/3119/695/968/3091/9641/6688/7096/3394/3162/3553/929/64127/10062/3570/2048/3106/1536/3587/100/3455/348/5971/7292/6366/6772/3117/3135/5321/3606/7293/26191/3569/2214/942/3601/995/1043/6948/133/9332/6891/3383/6890/6693/3600/3574/1236/3105/7535/4794/5888/6648/10673/2153/1111/4050/81030/3560/1946/332/2215/6556/2950/717/30835/6356/54210/6352/8651/29126/3662/51561/6280/3934/7850/50943/3290/2919/4318/6279/875/3627/3559/952/3002/4312
## D015459 4680/4602/10560/8912/4582/1154/3214/4843/3213/1960/3667/596/3315/5167/21/9314/1728/267/3708/648/10401/3551/3727/3164/3977/4363/9021/9793/5777/1947/8660/836/472/613/8771/55294/6773/581/7422/10875/3709/10461/1024/4791/8797/5734/4793/6597/867/3635/2956/1633/3115/55697/5111/894/3965/2177/4507/1956/578/5150/3459/7133/2113/3123/2534/1084/272/968/4851/9641/6688/84433/7409/8837/5996/4233/5788/3106/843/637/100/8784/7913/84441/5971/7292/6366/6772/8013/2120/3606/7293/1612/7153/4067/10320/5292/2214/942/2597/5142/3601/995/1043/6491/5329/6367/919/3925/1439/7037/1978/6693/3574/1236/84868/3575/65078/3105/1869/8600/7535/5888/83439/5140/3561/1021/916/3001/332/2950/30835/915/3932/6352/8651/3718/699/2833/10225/3662/114836/50943/5008/924/1029/4318/973/3604/3627/3559/952/3002/6362
## D019698 2674/2705/4582/9547/2690/4843/3480/30061/3875/3667/2719/7043/183/3315/5950/3856/3479/10401/727/4179/7098/399/9021/836/5168/7042/23225/6773/581/7422/4314/3557/55502/4277/5743/1636/3556/8797/8809/7099/3429/5111/3107/5696/7097/4082/3820/1080/3659/3459/7133/3123/91543/6347/3119/4599/968/7036/7052/3855/3394/3553/929/3106/100/3455/8784/4171/348/5465/6366/58191/6772/3117/3606/64135/3569/5292/2214/942/2597/958/983/1230/5698/341/133/3925/6696/7037/9332/6891/6890/3600/1236/3575/3105/8600/6648/8638/10673/2153/916/332/2215/6556/2950/7412/1234/6364/6352/8651/2833/29126/3594/7850/50943/10663/4318/838/3627/952/1116/3002/4283/3620/6373/4312/6362/10563
## Count
## D016399 159
## D016403 173
## D003093 172
## D007239 149
## D015459 156
## D019698 130
nrow(emesh)
## [1] 1310
grep(keyword, emesh$Description, ignore.case = TRUE)
## [1] 237 358 5038.2 GSEA
emesh2 <- gseMeSH(geneList, MeSHDb = "MeSH.Hsa.eg.db", database = 'gene2pubmed', category = "G")
## preparing geneSet collections...
## GSEA analysis...
## Warning in .GSEA(geneList = geneList, exponent = exponent, minGSSize =
## minGSSize, : We do not recommend using nPerm parameter incurrent and future
## releases
## Warning in fgsea(pathways = geneSets, stats = geneList, nperm = nPerm, minSize
## = minGSSize, : 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.
## leading edge analysis...
## done...
## Loading required package: MeSH.db
head(emesh2)
## ID Description setSize enrichmentScore NES
## D003602 D003602 Cytotoxicity, Immunologic 479 -0.5171097 -2.003974
## D005720 D005720 Gamma Rays 481 -0.3762177 -1.458614
## D017951 D017951 Antigen Presentation 478 -0.4828499 -1.870471
## D000705 D000705 Anaphase 464 -0.4094642 -1.585418
## D016192 D016192 Resting Phase, Cell Cycle 467 -0.4062869 -1.572549
## D009336 D009336 Necrosis 436 -0.4094364 -1.579894
## pvalue p.adjust qvalues rank leading_edge
## D003602 0.001024590 0.01114076 0.007477986 1549 tags=41%, list=20%, signal=35%
## D005720 0.001025641 0.01114076 0.007477986 2042 tags=33%, list=26%, signal=26%
## D017951 0.001026694 0.01114076 0.007477986 1610 tags=39%, list=21%, signal=33%
## D000705 0.001027749 0.01114076 0.007477986 2460 tags=38%, list=32%, signal=28%
## D016192 0.001029866 0.01114076 0.007477986 2065 tags=37%, list=26%, signal=29%
## D009336 0.001033058 0.01114076 0.007477986 1742 tags=33%, list=22%, signal=27%
## core_enrichment
## D003602 10376/64750/26270/7852/5594/81704/4277/6590/2176/2213/127544/5898/6452/5743/5873/84937/3329/55666/7305/4615/8809/3122/7099/29940/5069/3482/6850/867/27040/567/965/1464/4690/3115/5216/89845/961/5111/10525/3107/6502/811/7097/3965/4217/11200/899/432/3820/203068/1956/55008/84876/3133/3127/3459/4502/29121/3683/7133/3123/2534/10096/60489/3371/8793/7454/3937/3091/29992/3687/7036/3791/5880/963/6775/6688/5817/51191/5552/10892/84433/7409/3394/8837/10125/3162/10507/3682/3553/5336/5788/3106/115290/3384/6351/637/7128/5294/5272/2023/920/3936/3903/962/7292/6366/2207/6772/3135/2357/5321/6402/3606/197259/79626/3569/639/2214/4248/8676/1508/3161/83706/958/6376/3601/3134/9966/1043/3689/201294/10859/6367/919/3383/6890/6693/3600/3574/84868/3575/3105/1869/971/7535/2526/10288/1844/64170/1131/10673/9235/3702/8140/10870/3560/914/6790/3001/921/2215/925/2359/11025/939/9232/915/3932/6352/8651/11006/7272/29126/10225/3662/57823/114836/50943/1029/10578/5551/3783/4318/8645/3604/50615/3627/3559/952/3002/3620/10537/10232/768/6362/10563
## D005720 5052/3658/355/4609/26524/10200/1072/4691/23350/87178/1509/2189/4436/860/10449/6117/64782/10059/5757/3251/836/10097/8525/7486/472/26986/8771/7186/6598/64393/5591/55294/23198/5691/581/835/7422/6477/580/10376/5594/22948/2176/6446/7226/4176/5743/2810/9188/8091/6275/5500/8243/6597/834/25788/1633/5111/11010/7097/11200/2177/10885/1956/578/5901/3659/348654/5688/3037/10926/23657/2678/5902/84930/5371/4521/5954/10096/813/8407/695/5984/3091/8876/140885/26271/4851/7083/5933/7409/8837/3162/3553/4233/4001/5424/10849/637/64421/994/2023/920/55215/675/891/9688/5971/51514/6772/1789/3135/6300/3606/2237/8877/7153/1410/650/7516/958/995/983/29128/6615/262/330/3930/3383/1869/7535/5888/6648/83990/55247/9787/1111/146956/1021/641/5347/6790/10481/2175/332/2950/8438/22974/25984/10635/993/1029/5031/2672/2305/4318/55388/898/1116/3897
## D017951 972/6477/80176/290/5704/5660/3108/10376/64750/8726/26270/7852/5594/4277/2213/5685/127544/5873/5718/84937/3329/1445/4615/3122/5692/7099/9474/2091/11047/5686/5690/567/965/10457/3115/3107/5696/6502/811/7097/3965/899/1080/55008/4033/3133/3659/3127/7498/5694/5688/5699/23657/64167/2113/6632/3123/3059/5713/5371/5641/6347/3119/2821/4261/7456/3687/3111/4973/140885/7052/963/4851/6688/3109/51191/5796/7409/3394/3162/4689/1794/3553/929/64127/5788/3106/115290/6351/637/1536/3587/920/951/5971/1525/7292/6366/50856/2207/6772/3117/27071/2120/3135/126014/7167/5293/1510/7293/6614/26191/9398/3569/639/942/1508/221472/3161/84166/958/6376/3601/3134/9966/1520/2146/983/5698/6932/10859/341/919/10437/4360/3118/25939/7037/9332/923/6891/3383/6890/3600/3574/1236/3575/3105/7535/176/10288/64581/10673/916/914/332/925/2359/3902/1234/30835/11025/6364/915/3932/6352/29126/3662/51561/6280/974/50943/9582/926/3120/10578/3783/4318/973/3604/3112/1116/3002/3620/10537
## D000705 5714/23279/7280/1994/27097/1019/10000/11117/57520/5049/5689/22919/1783/5717/9985/5687/191/57122/7532/5479/9690/8454/5721/22944/301/9183/7321/2313/54464/51144/10171/10426/7431/9972/5707/23173/6629/3796/4609/23381/1072/5693/51529/9136/8555/170506/55183/5702/154810/6117/55920/5683/81929/55233/23481/5708/7486/10973/2896/1159/5591/55294/23198/5691/5885/86/55131/5704/79980/64750/5464/10213/5685/3984/348235/5718/3607/3329/55666/55055/7027/84259/5692/7296/2037/8243/6597/5686/25788/54205/5690/8986/10436/5696/6502/11130/11200/10459/203068/51053/5901/5694/5688/5699/84930/5713/9735/10293/10940/10051/26271/57405/2182/27338/4001/285643/675/891/11113/29899/4860/1894/3619/8291/29127/7153/4085/25902/3832/983/5698/230/3930/3925/1062/81930/9055/9700/10112/3801/3833/5888/890/701/1063/4751/81620/6241/1111/54821/641/5347/6790/24137/332/8438/83540/128239/22974/990/9232/147841/11004/699/7272/113130/11065/220134/991/9212/9928/10403/2305/1058/51512/898/10232
## D016192 3269/9150/1906/5707/355/912/9097/4609/1072/5693/51529/1874/292/5702/22821/5982/6612/5983/3301/4363/5683/5777/836/1459/7187/84108/5708/472/6714/7186/6598/7042/51379/5691/581/4771/440/3710/6786/5704/5594/3631/10213/5685/5743/3985/5718/29933/91582/8797/7027/5692/11047/892/5686/867/9170/2619/5690/10212/961/5111/5696/6502/894/7097/1786/11200/1956/7112/51053/3659/5694/5688/5699/5713/7185/10189/1875/8477/5984/6839/3937/8856/3091/5880/4851/4175/10397/5933/7409/3394/3162/3553/9934/3106/843/5424/5997/1032/4173/7128/5294/5724/920/8784/7913/5915/675/891/6197/5465/100133941/3159/5727/50486/84879/29127/3757/1612/7153/5800/5578/3569/1508/1871/9966/995/983/7345/5329/5698/6932/330/3838/3574/3575/3105/1869/971/2526/890/9046/6648/1131/5214/3561/81620/1021/914/6790/332/925/1234/655/939/22974/990/1870/3718/29126/11065/993/51561/4605/991/50943/1029/5031/5551/3783/898/952/3002
## D009336 7486/837/6714/7186/2896/7042/5591/58/8718/5320/2542/581/835/7422/10630/4314/3557/8717/25937/7852/5594/10461/2920/6446/7226/24145/5743/6749/4017/29933/8797/4615/7099/1317/5069/255738/7873/834/8260/2956/23636/961/5111/10525/7097/4217/1080/1152/1956/7112/3663/719/578/57162/192111/6472/7133/240/3123/5954/6347/11168/8477/8856/3091/284/8542/4973/7096/8837/3162/3553/4233/64127/3570/3106/843/6513/4173/7128/4904/675/84441/348/6646/5465/100133941/1244/123/2120/1051/2357/3606/59341/197259/10855/7153/5578/3569/6566/101/942/1508/958/2146/7345/29128/6615/133/6696/60386/3383/1063/6648/2153/27242/81030/89790/7298/5347/6790/3945/332/717/11025/6364/6352/29126/6280/7850/1029/2919/10578/5551/2305/4318/6279/7941/3627/5080/3002/2707/4316/768
nrow(emesh2)
## [1] 220
grep(keyword, emesh2$Description, ignore.case = TRUE)
## [1] 196