KEGG富集分析可视化

---

一、数据处理

#数据处理
install.packages("xlsx")
library(xlsx)
# setwd("E:/")
A <- read.csv("/kaggle/input/kegggo/KEGG.csv", header = T) #读取KEGG文件

# 提取"Pathway.ID","Description","Gene.Count"三列创建新表
new_x <- A[c("Pathway.ID","Description","Gene.Count")] 

B = read.xlsx("/kaggle/input/kegggo/KEGG-pathway-classification.xlsx",sheetIndex = 1) #读取KEGG关系文件
AB <- merge(new_x, B, by = "Pathway.ID")  # 根据Pathway.ID 将两个表融合为一个表AB

# 表AB提取"Description.x","Gene.Count","Pathway.Class.1"三列创建新表
AB <- AB[c("Description.x","Gene.Count","Pathway.Class.1")] 
CD <- AB[order(AB$Pathway.Class.1), ] #按照Pathway.Class.1将AB排序 并赋给CD表

二、绘柱状图

#画图
library(ggplot2)
# type <- AB$Pathway.Class.1
p <-ggplot(data=CD, aes(x=CD$Description.x, y=CD$Gene.Count, fill=CD$Pathway.Class.1)) + #横纵轴取值
      geom_bar(stat="identity") + #柱状图的宽度，可以自己设置
      geom_text(aes(label=Gene.Count, y=Gene.Count+0.2),size=3)+ #数字
      scale_fill_manual(values = c("#FF6666", "#66CCFF", "#99CC33","#66C3A5", "#8DA1CB", "#FD8D62"))+ #颜色
      coord_flip() + ##这一步是让柱状图横过来，不加的话柱状图是竖着的
      xlab("GO term") +  #x轴标题
      ylab("Gene_Number") +  #y轴标题
      labs(title = "The Most Enriched GO Terms")+ #图片标题
      facet_grid(Pathway.Class.1~., scale = 'free_y', space = 'free_y')  #分类款
p

三、保存图片

ggsave("plot.png", plot = p, width = 20, height = 20, dpi = 300)