自己构建物种包OrgDb，然后用clusterProfiler富

利用clusterProfiler进行富集分析时，发现网上没有物种包OrgDb，利用网上教程构建了一个。主要参考了刘小泽的简书，特别感谢一下！！！

emapper首先得到注释文件，前提是自己安装好eggnog-mapper并且下载好相应的数据库

emapper.py --cpu 20 -i filter.pep.fa_16 --output filter.pep.fa_16.out -d virNOG  -m diamond

or

emapper.py -m diamond \
           -i sesame.fa \
           -o diamond \
           --cpu 19

得到注释文件后进行处理，只保留表头query_name这一行的注释信息，去掉头尾的# 等信息

sed -i '/^# /d' diamond.emapper.annotations 
sed -i 's/#//' diamond.emapper.annotations

开始一定要加上options(stringsAsFactors = F)，否则所有的字符在数据框中都会被R默认设置为factor！！！

library(clusterProfiler)
library(dplyr)
library(stringr)
options(stringsAsFactors = F)
#hub <- AnnotationHub::AnnotationHub()
#query(hub,"Theobroma cacao")

#STEP1：自己构建的话，首先

需要读入文件
setwd("G:/xxx")
egg_f <- "xx_annotations1"
egg <- read.table(egg_f, header=TRUE, sep = "\t")

#egg_f <- "test111"
#egg <- read.table(egg_f, header=TRUE, sep = "\t")
#gene_info_new<-read.table("id.txt" , header=TRUE, sep = "\t")

egg[egg==""]<-NA #这个代码来自花花的指导(将空行变成NA，方便下面的去除)

#STEP2: 从文件中挑出基因query_name与eggnog注释信息
gene_info <- egg %>% 
  dplyr::select(GID = query_name, GENENAME = eggNOG_annot) %>% na.omit()

#STEP3-1：挑出query_name与GO注释信息
gterms <- egg %>%
  dplyr::select(query_name, GO_terms) %>% na.omit()

#STEP3-2：我们想得到query_name与GO号的对应信息
# 先构建一个空的数据框(弄好大体的架构，表示其中要有GID =》query_name，GO =》GO号， EVIDENCE =》默认IDA)
# 关于IEA：就是一个标准，除了这个标准以外还有许多。IEA就是表示我们的注释是自动注释，无需人工检查http://wiki.geneontology.org/index.php/Inferred_from_Electronic_Annotation_(IEA)
# 两种情况下需要用IEA：1. manually constructed mappings between external classification systems and GO terms； 2.automatic transfer of annotation to orthologous gene products.
gene2go <- data.frame(GID = character(),
                      GO = character(),
                      EVIDENCE = character())

# 然后向其中填充：注意到有的query_name对应多个GO，因此我们以GO号为标准，每一行只能有一个GO号，但query_name和Evidence可以重复
for (row in 1:nrow(gterms)) {
  gene_terms <- str_split(gterms[row,"GO_terms"], ",", simplify = FALSE)[[1]]  
  gene_id <- gterms[row, "query_name"][[1]]
  tmp <- data_frame(GID = rep(gene_id, length(gene_terms)),
                    GO = gene_terms,
                    EVIDENCE = rep("IEA", length(gene_terms)))
  gene2go <- rbind(gene2go, tmp)
} 

#STEP4-1: 挑出query_name与KEGG注释信息
gene2ko <- egg %>%
  dplyr::select(GID = query_name, KO = KEGG_KOs) %>%
  na.omit()

#STEP4-2: 得到pathway2name, ko2pathway
# 需要下载 json文件(这是是经常更新的)
# https://www.genome.jp/kegg-bin/get_htext?ko00001
# 代码来自：http://www.genek.tv/course/225/task/4861/show

if(F){
  # 需要下载 json文件(这是是经常更新的)
  # https://www.genome.jp/kegg-bin/get_htext?ko00001
  # 代码来自：http://www.genek.tv/course/225/task/4861/show
  library(jsonlite)
  library(purrr)
  library(RCurl)

  update_kegg <- function(json = "ko00001.json") {
    pathway2name <- tibble(Pathway = character(), Name = character())
    ko2pathway <- tibble(Ko = character(), Pathway = character())

    kegg <- fromJSON(json)

    for (a in seq_along(kegg[["children"]][["children"]])) {
      A <- kegg[["children"]][["name"]][[a]]

      for (b in seq_along(kegg[["children"]][["children"]][[a]][["children"]])) {
        B <- kegg[["children"]][["children"]][[a]][["name"]][[b]] 

        for (c in seq_along(kegg[["children"]][["children"]][[a]][["children"]][[b]][["children"]])) {
          pathway_info <- kegg[["children"]][["children"]][[a]][["children"]][[b]][["name"]][[c]]

          pathway_id <- str_match(pathway_info, "ko[0-9]{5}")[1]
          pathway_name <- str_replace(pathway_info, " \\[PATH:ko[0-9]{5}\\]", "") %>% str_replace("[0-9]{5} ", "")
          pathway2name <- rbind(pathway2name, tibble(Pathway = pathway_id, Name = pathway_name))

          kos_info <- kegg[["children"]][["children"]][[a]][["children"]][[b]][["children"]][[c]][["name"]]

          kos <- str_match(kos_info, "K[0-9]*")[,1]

          ko2pathway <- rbind(ko2pathway, tibble(Ko = kos, Pathway = rep(pathway_id, length(kos))))
        }
      }
    }

    save(pathway2name, ko2pathway, file = "kegg_info.RData")
  }

  update_kegg(json = "ko00001.json")

}

#STEP5: 利用GO将gene与pathway联系起来，然后挑出query_name与pathway注释信息
load(file = "kegg_info.RData")
gene2pathway <- gene2ko %>% left_join(ko2pathway, by = "KO") %>% 
  dplyr::select(GID, Pathway) %>%
  na.omit()

library(AnnotationForge)  

#STEP6： 制作自己的Orgdb
  # 查询物种的Taxonomy，例如要查sesame
  # https://www.ncbi.nlm.nih.gov/taxonomy/?term= sesame
tax_id = "4182"
genus = "Sesamum" 
species = "indicum"
#gene2go <- unique(gene2go)

#gene2go<-gene2go[!duplicated(gene2go),]
#gene2ko<-gene2ko[!duplicated(gene2ko),]
#gene2pathway<-gene2pathway[!duplicated(gene2pathway),]

makeOrgPackage(gene_info=gene_info,
               go=gene2go,
               ko=gene2ko,
               maintainer = "xxx <xxx@163.com>",
               author = "",
               pathway=gene2pathway,
               version="0.0.1",
               outputDir = ".",
               tax_id=tax_id,
               genus=genus,
               species=species,
               goTable="go")
ricenew.orgdb <- str_c("org.", str_to_upper(str_sub(genus, 1, 1)) , species, ".eg.db", sep = "")

options(stringsAsFactors = F) 的作用

如果说一个data.frame中的元素是factor，你想转化成numeric，你会怎么做？比如d[1,1]是factor

正确答案是 先as.character(x) 再as.numeric(x)

哈哈，我刚发现如果直接as.numeric,就不是以前的数字了，坑爹啊。

原来as.data.frame()有一个参数stringsAsFactors

如果stringAsFactor=F

就不会把字符转换为factor 这样以来，原来看起来是数字变成了character，原来是character的还是character

KEGG富集分析

setwd("G:/xxx")
library(purrr)
library(tidyverse)
library(clusterProfiler)
################################################
# 导入自己构建的 OrgDb
################################################
install.packages("org.xxx.db", repos=NULL, type="sources")
library(org.xxx.db)
columns(org.xxx.db)

# 导入需要进行富集分析的基因列表，并转换为向量
#########################################################################################
DD<-"DEGs"
DEGs<- read.table(DD, header=TRUE, sep = "\t")
gene_list <- DEGs[,1]

################################################
# 从 OrgDB 提取 Pathway 和基因的对应关系
################################################

pathway2gene <- AnnotationDbi::select(org.xxx.db, 
                                      keys = keys(org.xxx.db), 
                                      columns = c("Pathway","KO")) %>%
  na.omit() %>%
  dplyr::select(Pathway, GID)

################################################
# 导入 Pathway 与名称对应关系
################################################
load("kegg_info.RData")

#KEGG pathway 富集
ekp <- enricher(gene_list, 
                TERM2GENE = pathway2gene, 
                TERM2NAME = pathway2name, 
                pvalueCutoff = 1, 
                qvalueCutoff = 1,
                pAdjustMethod = "BH",
                minGSSize = 1)

ekp_results <- as.data.frame(ekp)

barplot(ekp, showCategory=20,color="pvalue",
        font.size=10)
dotplot(ekp)

emapplot(ekp)

GO富集分析

#########################################################################################
GO 分析
#########################################################################################

ego <- enrichGO(gene = gene_list,                       #差异基因 vector 
                keyType = "GID",                                   #差异基因的 ID 类型，需要是 OrgDb 支持的 
                OrgDb = org.xxx.db,                               #对应的OrgDb 
                ont = "CC",                                             #GO 分类名称，CC BP MF 
                pvalueCutoff = 1,                                   #Pvalue 阈值 （pvalue=1指输出所有结果，pvalue=0.05指输出符合要求的结果） 
                qvalueCutoff = 1,                                   #qvalue 阈值 pAdjustMethod = "BH", #Pvalue 矫正方法 
                readable = FALSE)                               #TRUE 则展示SYMBOL，FALSE 则展示原来的ID（选false是因为不是所有gene都有symbol的)

ego_results<-as.data.frame(ego)                          ###生成的ego文件转换成data.frame格式即可。

write.table(ego_results, file = "ego_results.txt", quote = F)                    ###让保存的字符串不用“”引起来
pdf(file = "ego_barplot.pdf")                                                                   ##打开一个PDF文件
barplot(ego, showCategory=20, x = "GeneRatio")                                ##把图画到这个PDF文件里
dev.off()                                                                                                 ##关闭PDF

dotplot(ego)               
emapplot(ego)

参考
https://www.jianshu.com/p/9c9e97167377
https://www.jianshu.com/p/5d5394e0774f