8  clusterProfiler包做GO，KEGG富集

8.1 安装clusterProfiler包及所需文件

# 安装clusterProfiler包。
# 可能会报错，可以下载到本地安装，可参考https://zhuanlan.zhihu.com/p/436671645
BiocManager::install("clusterProfiler")

# 安装所需的物种数据库注释文件
BiocManager::install("org.Hs.eg.db") # 人的注释数据库。其他物种的可在https://bioconductor.org/packages/3.6/data/annotation/找到

8.2 ID Mapping

# 通过bitr函数，做Symbol，Gene ID，uniprot ID 等之间的转换
# 支持如下类型之间的相互转换：ACCNUM, ALIAS, ENSEMBL, ENSEMBLPROT, ENSEMBLTRANS, ENTREZID, ENZYME, EVIDENCE, EVIDENCEALL, GENENAME, GO, GOALL, IPI, MAP, OMIM, ONTOLOGY, ONTOLOGYALL, PATH, PFAM, PMID, PROSITE, REFSEQ, SYMBOL, UCSCKG, UNIGENE, UNIPROT
library(clusterProfiler)
symbolList <- c("GPX3",  "GLRX",   "LBP",   "CRYAB", "DEFB1", "HCLS1",   "SOD2",   "HSPA2", 
                 "ORM1",  "IGFBP1", "PTHLH", "GPC3",  "IGFBP3","TOB1",    "MITF",   "NDRG1", 
                 "NR1H4", "FGFR3",  "PVR",   "IL6",   "PTPRM", "ERBB2",   "NID2",   "LAMB1", 
                 "COMP",  "PLS3",   "MCAM",  "SPP1",  "LAMC1", "COL4A2",  "COL4A1", "MYOC",  
                 "ANXA4", "TFPI2",  "CST6",  "SLPI",  "TIMP2", "CPM",     "GGT1",   "NNMT",
                 "MAL",   "EEF1A2", "HGD",   "TCN2",  "CDA",   "PCCA",    "CRYM",   "PDXK",  
                 "STC1",  "WARS",  "HMOX1", "FXYD2", "RBP4",   "SLC6A12", "KDELR3", "ITM2B")
eg <- bitr(symbolList, 
           fromType="SYMBOL",    # 定义输入类型
           toType=c("ENTREZID","ENSEMBL","UNIPROT"),  # 输出何种类型
           OrgDb="org.Hs.eg.db") # （人）物种数据库

8.3 GO富集

genelist <- eg$ENTREZID
genelist = genelist[-duplicated(genelist)] # 去重

go <- enrichGO(genelist,
               OrgDb = org.Hs.eg.db,   # 选择对应物种的数据库
               ont='ALL',              # 选择GO富集的种类"BP", "MF", "CC" OR "ALL"
               pAdjustMethod = 'BH',   # FDR算法
               pvalueCutoff = 1,       # 过滤p值小于多少的条目，1为不过滤
               qvalueCutoff = 1,       # 过滤q值小于多少的条目，1为不过滤
               keyType = 'ENTREZID',   # 定义输入类型为NCBI的Gene ID
               readable = T            # 是否将结果表格中的富集条目改为Gene Symbol,增加可读性
)
head(go)
barplot(go,showCategory=20,drop=T) # 绘制富集条形图
dotplot(go,showCategory=20)        # 绘制富集气泡图

8.4 KEGG富集

kegg <- enrichKEGG(genelist, 
                   organism = 'hsa',     # 选择对应物种的数据库，通过如下网址，获取对应物种的三字母缩写http://www.genome.jp/kegg/catalog/org_list.html
                   keyType = 'kegg',     # 定义输入类型
                   pvalueCutoff = 1,     # 过滤p值小于多少的条目，1为不过滤
                   qvalueCutoff = 1,     # 过滤q值小于多少的条目，1为不过滤
                   pAdjustMethod = 'BH', # FDR算法
                   use_internal_data = F # 是否使用KEGG.db本地数据库
)
head(kegg)
barplot(kegg,showCategory=20,drop=T)     # 绘制富集条形图
dotplot(kegg,showCategory=20)            # 绘制富集气泡图