Question

我需要帮助合并数据（mydf）中具有相同名称（即起始列）的行并连接“ALT”列中的内容，从而根据起始列中的类似值删除所有重复行。我想合并行并连接用逗号分隔的“ALT”列中的内容，并得到如下所示的结果。谢谢你的帮助。

> mydf
         chr          start      end REF ALT         TYPE refGene               
       chr10 chr10:176131 176131   C   A          snp nonsynonymous SNV 
       chr10 chr10:159149 159149   C   G snp:17659149 nonsynonymous SNV 
       chr10 chr10:159149 159149   C   T snp:17659149 nonsynonymous SNV 
       chr10 chr10:241469 241469   T   C          snp          splicing 

> result
         chr          start      end REF ALT         TYPE refGene                   
       chr10 chr10:176131 176131   C   A          snp nonsynonymous SNV 
       chr10 chr10:159149 159149   C   G,T snp:17659149 nonsynonymous SNV 
       chr10 chr10:241469 241469   T   C          snp          splicing

DPUT在这里：

structure(list(chr = c("chr3", "chr3", "chr3", "chr3"), start = c("chr3:75786036", 
"chr3:75786337", "chr3:75786337", "chr3:75788226"), end = c(75786036, 
75786337, 75786337, 75788226), REF = c("A", "G", "G", "C"), ALT = c("G", 
"A", "T", "A"), TYPE = c("snp:75786036", "snp:75786337", "snp:75786337", 
"snp:75788226"), `refGene::location` = c("nonsynonymous SNV", 
"nonsynonymous SNV", "nonsynonymous SNV", "nonsynonymous SNV"
), `refGene::type` = c("ZNF717:NM_001290208:exon5:c.T2738C:p.F913S,ZNF717:NM_001128223:exon5:c.T2738C:p.F913S,ZNF717:NM_001290209:exon5:c.T2588C:p.F863S,", 
"ZNF717:NM_001290208:exon5:c.C2437T:p.P813S,ZNF717:NM_001128223:exon5:c.C2437T:p.P813S,ZNF717:NM_001290209:exon5:c.C2287T:p.P763S,", 
"ZNF717:NM_001290208:exon5:c.C2437A:p.P813T,ZNF717:NM_001128223:exon5:c.C2437A:p.P813T,ZNF717:NM_001290209:exon5:c.C2287A:p.P763T,", 
"ZNF717:NM_001290208:exon5:c.G548T:p.C183F,ZNF717:NM_001128223:exon5:c.G548T:p.C183F,ZNF717:NM_001290209:exon5:c.G398T:p.C133F,"
)), .Names = c("chr", "start", "end", "REF", "ALT", "TYPE", "refGene::location", 
"refGene::type"), row.names = c("4041", "4051", "4052", "4128"
), class = "data.frame")

Answer 1

这是一个dplyr解决方案：

library(dplyr)
df %>% group_by(start) %>% 
       mutate(ALT = paste(ALT, collapse=",")) %>%
       distinct(start)

Answer 2

在基地R中尝试aggregate：

newdf <- mydf[!duplicated(mydf$start),]
newdf[, 'ALT'] <- aggregate(ALT~start, data=mydf, toString)[,2]

Answer 3

这样的东西会起作用（未测试：请dput数据）

library(data.table)
setDT(mydf)[,.(REF=paste(REF,collapse=",")),by="TYPE"]
unique(mydf, by="TYPE")
    chr         start      end REF ALT         TYPE refGene::location
1: chr3 chr3:75786036 75786036   A   G snp:75786036 nonsynonymous SNV
2: chr3 chr3:75786337 75786337 G,G   A snp:75786337 nonsynonymous SNV
3: chr3 chr3:75788226 75788226   C   A snp:75788226 nonsynonymous SNV
                                                                                                                       refGene::type
1: ZNF717:NM_001290208:exon5:c.T2738C:p.F913S,ZNF717:NM_001128223:exon5:c.T2738C:p.F913S,ZNF717:NM_001290209:exon5:c.T2588C:p.F863S,
2: ZNF717:NM_001290208:exon5:c.C2437T:p.P813S,ZNF717:NM_001128223:exon5:c.C2437T:p.P813S,ZNF717:NM_001290209:exon5:c.C2287T:p.P763S,
3:    ZNF717:NM_001290208:exon5:c.G548T:p.C183F,ZNF717:NM_001128223:exon5:c.G548T:p.C183F,ZNF717:NM_001290209:exon5:c.G398T:p.C133F,
>

合并行连接由逗号-R编程分隔的其中一列中的内容

3 个答案: