分离物种注释表中的分类信息

处理前

处理后

otu_taxa_tableNORMAL <- read.csv("D:/test/16sOTU/reslut/otu_taxa_tableNORMAL.csv", row.names=1)
library(tidyverse)#加载tidyverse包
otu2 <- otu_taxa_tableNORMAL %>%
separate(taxonomy,c("Domain","Phylum","Class","Order","Family","Genus","Species"),"; ")
##将otu表格重新命名并且把分类的那一列按照分级分为七列，分隔符是“；”

##清理没用的字符
otu2$Domain <- gsub("d__","",otu2$Domain)
otu2$Phylum <- gsub("p__","",otu2$Phylum)
otu2$Class <- gsub("c__","",otu2$Class)
otu2$Order <- gsub("o__","",otu2$Order)
otu2$Family <- gsub("f__","",otu2$Family)
otu2$Genus <- gsub("g__","",otu2$Genus)
otu2$Species <- gsub("s__","",otu2$Species)

write.csv(otu2,"111.csv",row.names = TRUE)

##把门水平缺失的给删了
otu2 <- otu2[complete.cases(otu2$Phylum),]
##把域水平注释成unassignable和unclassified的给删了
otu2 <- otu2[otu2$Domain != "Unassignable",]
otu2 <- otu2[otu2$Domain != "Unclassified",]
##仅保留从第一列到倒数第 8 列之间的列之和大于 1 的行
otu2 <- otu2[rowSums(otu2[,1:(ncol(otu2)-7)]) > 1,]