GO富集分析＼KEGG

##Time:2017-10-8

##Author:Feng Shengyu

#&＃8212;&＃8212;&＃8212;&＃8212;&＃8212;&＃8212;&＃8212;&＃8212;&＃8212;&＃8212;&＃8212;&＃8212;&＃8212;&＃8212;&＃8212;&＃8212;&＃8212;-

#一、安装必须的R包（推荐使用的R版本3.2.2）

#必须要安装的包：

#  1、clusterprofilter

#  source(&＃8220;http://bioconductor.org/biocLite.R&＃8221;)

#  biocLite(&＃8220;clusterprofilter&＃8221;)

#  2、org.Mm.eg.db/org.Hs.eg.db(对应需要研究的物种-小鼠/人)

#  biocLite(&＃8220;org.Mm.eg.db&＃8221;)/biocLite(&＃8220;org.Hs.eg.db&＃8221;)

#  3、DOSE

#  biocLite(DOSE)

library(clusterProfiler)

library(DOSE)

library(org.Mm.eg.db)

#二 change the type of gene

#使用的上游数据是RNA-seq做完的差异表达的基因列表

#example:

# 15431

# 244091

# 15430

# 319158

# 13871

# 109663

# 735269

# 378431

# 21384

# 105247262

#读取gene list

gene <- read.table(&＃8220;C:\\Users\\Feng\\Desktop\\up_regulate_symbolGene.txt&＃8221;)

geneSymbol <- gene[,1]

geneSymbol

#转化基因类型，一般用cufflinks做的结果是symbol,此时需要转化为entrzid

geneEntrezID <- bitr(geneSymbol, fromType=&＃8221;SYMBOL&＃8221;, toType=&＃8221;ENTREZID&＃8221;, OrgDb=&＃8221;org.Mm.eg.db&＃8221;)

#可以同时转为多个类型的基因

#geneEntrezID <- bitr(geneSymbol, fromType=&＃8221;SYMBOL&＃8221;, toType=c(&＃8220;ENTREZID&＃8221;,&＃8221;UNIPROT&＃8221;), OrgDb=&＃8221;org.Mm.eg.db&＃8221;,)

#三、enrichment analysis

#GO富集分析

ego_cc <- enrichGO(gene = geneEntrezID[,2], #使用entrezID作为输入

OrgDb=org.Mm.eg.db,

Ont= &＃8220;CC&＃8221;,

pAdjustMethod = &＃8220;BH&＃8221;,

minGSSize = 1,

pvalueCutoff = 0.05,

qvalueCutoff = 0.05,

readable = TRUE

)

setwd(&＃8220;F:\\生信工具大全\\R&＃8221;)

write.table(as.data.frame(ego_cc@result),file=&＃8221;test_CC.txt&＃8221;,sep=&＃8221;\t&＃8221;)

#KEGG富集分析

kk <- enrichKEGG(gene = geneEntrezID[,2],

organism =&＃8221;mouse&＃8221;,

pvalueCutoff = 0.05,

qvalueCutoff = 0.01,

minGSSize = 1,

use_internal_data =FALSE

)

write.table(as.data.frame(kk@result), file=&＃8221;test_kk.txt&＃8221;,sep=&＃8221;\t&＃8221;)

#作图展示结果

barplot(ego_cc, showCategory=15, title=&＃8221;EnrichmentGO_CC&＃8221;) #条状图，按p从小到大排的

dotplot(ego_BP,title=&＃8221;EnrichmentGO_CC_dot&＃8221;) #点图，按富集的数从大到小的

#&＃8212;&＃8212;&＃8212;&＃8212;&＃8212;&＃8212;&＃8211;核心代码&＃8212;&＃8212;&＃8212;&＃8212;&＃8212;&＃8212;&＃8212;&＃8211;

setwd(&＃8220;F:\\硕士生\\GO和KEGG富集分析&＃8221;)

library(clusterProfiler)

library(DOSE)

library(org.Mm.eg.db)

gene <- read.table(&＃8220;C:\\Users\\Feng\\Desktop\\up_regulate.gene&＃8221;)

geneSymbol <- gene[,1]

geneEntrezID <- bitr(geneSymbol, fromType=&＃8221;SYMBOL&＃8221;, toType=&＃8221;ENTREZID&＃8221;, OrgDb=&＃8221;org.Mm.eg.db&＃8221;)

ego_cc <- enrichGO(gene = geneEntrezID[,2], #使用entrezID作为输入

OrgDb=org.Mm.eg.db,

Ont= &＃8220;CC&＃8221;,

pAdjustMethod = &＃8220;BH&＃8221;,

minGSSize = 1,

pvalueCutoff = 0.01,

qvalueCutoff = 0.01,

readable = TRUE

)

write.table(as.data.frame(ego_cc@result),file=&＃8221;haimati_M_up_enrich_GO.txt&＃8221;,sep=&＃8221;\t&＃8221;)

barplot(ego_cc, showCategory=15, title=&＃8221;GO_Enrichment&＃8221;) #条状图，按p从小到大排的

ego_BP <- enrichKEGG(gene = geneEntrezID[,2],

organism =&＃8221;mouse&＃8221;,  #http://www.genome.jp/kegg/catalog/org_list.html(species names)

pvalueCutoff = 0.05,

qvalueCutoff = 0.01,

minGSSize = 1,

use_internal_data =FALSE

)

write.table(as.data.frame(ego_BP@result), file=&＃8221;haimati_M_up_enrich_KEGG.txt&＃8221;,sep=&＃8221;\t&＃8221;)

dotplot(ego_BP,title=&＃8221;EnrichmentGO_CC_dot&＃8221;) #点图，按富集的数从大到小的