GO 富集结果可视化优化笔记

作者：ahworld
链接：GO 富集结果可视化优化笔记
来源：微信公众号seqyuan
著作权归作者所有，任何形式的转载都请联系作者。

image.png

library(clusterProfiler)
library(ggplot2)
library(dplyr)
library(org.Hs.eg.db)
library(viridis)

genes_df <- read.table('genes.txt') # 一列基因，SYMBOL格式

geneID <- bitr(genes_df$V1, fromType = "SYMBOL", 
               toType = c("ENTREZID", "SYMBOL"),
               OrgDb = org.Hs.eg.db) 
                             
all.GO <- enrichGO(gene = geneID$ENTREZID,
                    OrgDb = org.Hs.eg.db,
                    keyType = "ENTREZID",
                    ont = "ALL",
                    pAdjustMethod = "BH",
                    pvalueCutoff = 0.01,
                    qvalueCutoff = 0.05,
                    readable = T)
                                            
allgg <- as.data.frame(all.GO)

# 按照pvalue取每个ONTOLOGY的前5
top5 <- allgg %>%
  group_by(ONTOLOGY) %>%
  arrange(pvalue) %>%
  slice_head(n = 5)

# 我这里设置的只取CC和MF
df_top5 <- rbind(subset(top5, ONTOLOGY=="CC"), subset(top5, ONTOLOGY=="MF"))

df_top5$ONTOLOGY <- factor(df_top5$ONTOLOGY, levels=c('CC', 'MF'))
df_top5$Description <- factor(df_top5$Description, levels = rev(df_top5$Description))                            

options(repr.plot.width=7, repr.plot.height=6.5)

mycol3 <- c('#6BA5CE', '#F5AA5F')
cmap <- c("viridis", "magma", "inferno", "plasma", "cividis", "rocket", "mako", "turbo")

p <- ggplot(data = df_top5, aes(x = Count, y = Description, fill=ONTOLOGY)) +
     geom_bar(width = 0.5,stat = 'identity') +
     theme_classic() + 
     scale_x_continuous(expand = c(0,0.5)) +
     scale_fill_manual(values = alpha(mycol3, 0.66))

p <- p + theme(axis.text.y = element_blank()) + 
     geom_text(data = df_top5,
            aes(x = 0.1, y = Description, label = Description),
            size = 4.8,
            hjust = 0) 

p <- p + geom_text(data = df_top5,
            aes(x = 0.1, y = Description, label = geneID , color=-log10(pvalue)),
            size = 4,
            fontface = 'italic',
            hjust = 0,
            vjust = 2.7) +
          scale_colour_viridis(option=cmap[7], direction=-1) 

p <- p + labs(title = 'Enriched top 5 CC and MF') +
     theme(
      plot.title = element_text(size = 14, face = 'bold'),
      axis.title = element_text(size = 13),
      axis.text = element_text(size = 11),
      axis.ticks.y = element_blank())


ggsave("gene_GO.pdf", p, w=7, h=6.5)