GSEA分析
根據(jù)測(cè)序公司返回來(lái)的分析數(shù)據(jù)，打開(kāi)包含所有基因的數(shù)據(jù)的excel表

image.png

image.png

在excel 表中先進(jìn)行部分操作

1. 去除不含EntrezID的行，通過(guò)篩選去掉空的列
2. 只保留gene_name, EntrezID 列以及l(fā)og2（fc）列，其余列數(shù)去除

3. 根據(jù)log2（fc）從大到小進(jìn)行排列

   
   
   image.png

2. 轉(zhuǎn)到R

setwd("I:/trit1/T202111_8dpf_and_16dpf/revised 更換了個(gè)野生型16d/Summary/coverage_gene")
library(stringr) 
library(clusterProfiler) 
library(org.Hs.eg.db)
library(ggridges)

T16<-read.csv("test1.csv") ## 讀入之前保存的數(shù)據(jù)
head(T16)
dim(T16)

image.png

gene_fc=T16[,3]
head(gene_fc)
names(gene_fc)<-T16$EntrezID

gene_fc_sort<-sort(gene_fc,decreasing = TRUE)
head(gene_fc)

image.png

go_result <- gseGO(geneList = gene_fc, ont = "BP", OrgDb = org.Dr.eg.db,keyType = "ENTREZID",pvalueCutoff = 0.05, pAdjustMethod = "BH")#p值校正方法
head(go_result)

kegg_result <- gseKEGG(
  geneList = gene_fc,
  organism = "dre",
  keyType = "kegg",
  exponent = 1,
  minGSSize = 10,
  maxGSSize = 500,
  eps = 1e-10,
  pvalueCutoff = 0.05,
  pAdjustMethod = "BH",
  verbose = TRUE,
  use_internal_data = FALSE,
  seed = FALSE,
  by = "fgsea")
head(kegg_result)
head(go_result)

image.png

image.png

做圖

library(enrichplot)

gseaplot2(
  go_result, #gseaResult object，即GSEA結(jié)果
  "GO:0007059",#富集的ID編號(hào)
  #標(biāo)題
  color = "green",#GSEA線條顏色
  base_size = 11,#基礎(chǔ)字體大小
  rel_heights = c(1.5, 0.5, 1),#副圖的相對(duì)高度
  subplots = 1:3, #要顯示哪些副圖 如subplots=c(1,3) #只要第一和第三個(gè)圖，subplots=1#只要第一個(gè)圖
  pvalue_table = FALSE, #是否添加 pvalue table
  ES_geom = "line") #running enrichment score用先還是用點(diǎn)ES_geom = "dot"



gseaplot2(
  kegg_result, #gseaResult object，即GSEA結(jié)果
  "dre04744",#富集的ID編號(hào)
  #標(biāo)題
  color = "green",#GSEA線條顏色
  base_size = 11,#基礎(chǔ)字體大小
  rel_heights = c(1.5, 0.5, 1),#副圖的相對(duì)高度
  subplots = 1:3, #要顯示哪些副圖 如subplots=c(1,3) #只要第一和第三個(gè)圖，subplots=1#只要第一個(gè)圖
  pvalue_table = FALSE, #是否添加 pvalue table
  ES_geom = "line") #running enrichment score用先還是用點(diǎn)ES_geom = "dot"

ridgeplot(go_result)
ridgeplot(kegg_result)

image.png

image.png

image.png

image.png

paths<-c("GO:0007601","GO:0000070")

gseaplot2(
  go_result, #gseaResult object，即GSEA結(jié)果
  paths,#富集的ID編號(hào)
  #標(biāo)題
  color = "green",#GSEA線條顏色
  base_size = 11,#基礎(chǔ)字體大小
  rel_heights = c(1.5, 0.5, 1),#副圖的相對(duì)高度
  subplots = 1:3, #要顯示哪些副圖 如subplots=c(1,3) #只要第一和第三個(gè)圖，subplots=1#只要第一個(gè)圖
  pvalue_table = FALSE, #是否添加 pvalue table
  ES_geom = "line") #running enrichment score用先還是用點(diǎn)ES_geom = "dot"

image.png