如何用R按不同分隔符拆分数据框多列元素并拆分行？

需求说明 #

需要将DataFrame中的alt列（含中文逗号分隔的多个等位基因）和info列（含GT:AD结构，GT用斜杠分隔、AD用英文逗号分隔）拆分到不同行，同时保留其余列的内容，且拆分后info列需对应每个alt值生成0/n:ref_depth,alt_depth的格式。

输入数据 #

structure(list(ref = c("A", "C", "A", "G", "C"), alt = c("T，TAA，TAAAA，TAAAAA", 
"G，GC，GCCG", "T", "A G", "G"), chr = c("chr1", "chr1", 
"chr1", "chr1", "chr2"), pos_s = c(2313007, 2456780, 2578901, 
2689511, 18907652), pos_e = c(2313009, 2456784, 2578903, 2689513, 
18907654), format = c("GT:AD", "GT:AD", "GT:AD", "GT:AD", "GT:AD"
), info = c("0/1/2/3/4:296,5,33,29,55", "0/1/2/3:376,22,13,7", 
"0/1:323,24", "0/1:288,21", "0/1:3342,25")), class = c("tbl_df", 
"tbl", "data.frame"), row.names = c(NA, -5L))

期望输出数据 #

structure(list(ref = c("A", "A", "A", "A", "C", "C", "C", "A", 
"G", "C"), alt = c("T", "TAA", "TAAAA", "TAAAAA", "G", "GC", 
"GCCG", "T", "A G", "G"), chr = c("chr1", "chr1", "chr1", "chr1", 
"chr1", "chr1", "chr1", "chr1", "chr1", "chr2"), pos_s = c(2313007, 
2313007, 2313007, 2313007, 2456780, 2456780, 2456780, 2578901, 
2689511, 18907652), pos_e = c(2313009, 2313009, 2313009, 2313009, 
2456784, 2456784, 2456784, 2578903, 2689513, 18907654), format = c("GT:AD", 
"GT:AD", "GT:AD", "GT:AD", "GT:AD", "GT:AD", "GT:AD", "GT:AD", 
"GT:AD", "GT:AD"), info = c("0/1:296,5", "0/2:296,33", "0/3:296,29", 
"0/4:296,55", "0/1:376,22", "0/2:376,13", "0/3:376,7", "0/1:323,24", 
"0/1:288,21", "0/1:3342,25")), class = c("tbl_df", "tbl", "data.frame"
), row.names = c(NA, -10L))

解决代码及说明 #

使用R的tidyverse工具集，通过分步拆分、映射匹配实现需求：

library(tidyverse)

# 读取输入数据（若已加载可跳过）
df <- structure(list(ref = c("A", "C", "A", "G", "C"), alt = c("T，TAA，TAAAA，TAAAAA", 
"G，GC，GCCG", "T", "A G", "G"), chr = c("chr1", "chr1", 
"chr1", "chr1", "chr2"), pos_s = c(2313007, 2456780, 2578901, 
2689511, 18907652), pos_e = c(2313009, 2456784, 2578903, 2689513, 
18907654), format = c("GT:AD", "GT:AD", "GT:AD", "GT:AD", "GT:AD"
), info = c("0/1/2/3/4:296,5,33,29,55", "0/1/2/3:376,22,13,7", 
"0/1:323,24", "0/1:288,21", "0/1:3342,25")), class = c("tbl_df", 
"tbl", "data.frame"), row.names = c(NA, -5L))

# 核心处理流程
result_df <- df %>%
  # 拆分alt列（注意使用中文逗号作为分隔符）
  separate_rows(alt, sep = "，") %>%
  # 将info列拆分为GT（基因型）和AD（深度）两部分
  separate(info, into = c("GT", "AD"), sep = ":") %>%
  # 对每行的GT和AD进行映射处理，生成对应每个alt的info字符串
  mutate(
    # 拆分GT为基因型向量，去掉第一个"0"
    gt_parts = str_split(GT, "/"),
    # 拆分AD为深度向量，第一个元素是参考深度，后续是各alt对应深度
    ad_parts = str_split(AD, ","),
    # 组合生成匹配的info条目
    info = map2_chr(gt_parts, ad_parts, function(g, a) {
      ref_ad <- a[1]
      alt_ad_list <- a[-1]
      gt_pair_list <- paste0("0/", g[-1])
      paste0(gt_pair_list, ":", ref_ad, ",", alt_ad_list)
    })
  ) %>%
  # 将info的向量拆分为多行，与alt的拆分结果对应
  unnest(info) %>%
  # 清理中间生成的临时列
  select(-GT, -AD, -gt_parts, -ad_parts)

# 查看最终结果
print(result_df)

关键细节说明 #

• alt列拆分：注意输入中alt使用的是中文逗号“，”，必须在separate_rows中指定sep = "，"，否则无法正确拆分；
• info列映射：通过map2_chr将每行的基因型和深度一一对应，生成0/n:ref_depth,alt_depth格式的字符串，确保每个alt值匹配正确的info内容；
• 行数对应：separate_rows拆分alt后，原行的行数会扩展为alt的元素个数，再通过unnest将生成的info向量拆分为多行，保证每行的alt和info完全对应。

内容的提问来源于stack exchange，提问作者Pokemoon