根据字符串给定位置的字符进行过滤答案

【问题标题】：Filter based on a character in a given position of string根据字符串给定位置的字符进行过滤
【发布时间】：2022-11-29 03:28:41
【问题描述】：

我有以下字符串，我想根据第一个位置的 A 或 T，然后是第二个位置的 C 或 T 等进行过滤。

structure(list(barcode.Universe.sub = c("TCCGCTGGTGCG", "GTCGCGGACTGC", 
"CTTCCAAAATAG", "CCCCTTTCGTGG", "TTTCAGCGTCAG", "TACGAGCCTGGT", 
"AGCAGTATCAAC", "TAACCGTATAGA", "GGCTAATTCCGC", "CTCGGTTGGGCG", 
"TCCCGTGCGCCC", "TCTCCCAAACGA", "ATCATGGTCAAC", "ACCGCACTGAAC", 
"AAGTTTTCCTCA", "CTAGAGACCGAT", "CATTCTCATGGA", "ATGCGCGGCGAA", 
"GAGTGCCCTAGG", "ATGAGTAGTAGG", "TCTAGCGTCATT", "TCTCAACTTCTC", 
"GAGAACGCTCCT", "TACAGGACACAC", "GATTCTCACGAT", "GAGACGGAGGCC", 
"GCGGCTCCTCTA", "TGGATACTCTGC", "GCACCGCGTTCA", "GAATTGATAAGT", 
"GGGCAGCAGATA", "GGCATATACGGC", "TCATCACTATGA", "CGCGGCTGGGAT", 
"AGTCGCCACGCT", "TTGGCCGAAATT", "CGAGACCCACCG", "TGGTGCCTCACT", 
"CTGATACTGGGT", "AGGTGGCGTCTA", "GGCAAGGAGTAC", "GCGACTGAAATA", 
"AGCTTCGGATTA", "GTTGCCAGACTC", "AGCTGTCGCACG", "AGGGTTCGCTGT", 
"GTGCGTACCGCG", "CGCTTACACATG", "ACAACGCCATGT", "ATATACTAAGCC", 
"ACCGGAATAGCT", "CTACGAACGACT", "TAACCTTATGCT", "GCCTGCAGATGA", 
"CGAGTGCGGTGG", "TGGAGGTGTACT", "CTTCAATATTGA", "AACGACATAAAC", 
"TACAGTGGATGC", "ATCTAAGCTGTT", "GCCTGGCATCTT", "CATGGGGAACCT", 
"GCCCGAGCTAAG", "GGGTGCTCCGAC", "TAATTAGGACGC", "TACCTAAGCGAT", 
"TAGTCTGTAGGC", "CGTTAACTCCGC", "GCACGAAGTCAC", "GAGCGTCCAGCT", 
"CCGACTTACAAA", "CCGGTTCAGATG", "TGCAGCTGTGTG", "AATCTATTTCTT", 
"TCGTATAAGGTA", "AACTGGATGCCC", "ACGAAGAACGCT", "AGTGCTCTTCTG", 
"CTACAGTGTACA", "AGGGCCATACTC", "AACAACCGCTTA", "CTAGACGGCAAT", 
"GGGTTGAAGAAG", "GGAGCATACTAA", "CGAACCCCGGTA", "TGTACCATGGAA", 
"TTCGAGGTTGAT", "GTGCTTAGGATC", "CAACCGTATGAC", "GACGTCCTTCAG", 
"TGGTAATGGACA", "ACGAGCGCTATG", "GCGGAGCCACCC", "TCAGAGGCTGGA", 
"GGCCTTACGCAA", "TACGACCCATAG", "CCATTCAGCATG", "CCTAAGGGCCTT", 
"GGTCTATCGCAT", "CAGTACATGTCG")), class = c("tbl_df", "tbl", 
"data.frame"), row.names = c(NA, -100L))

我已经尝试过 stringr 和 DNA 序列（猿）的特定包，但还没有很好的结果。

【问题讨论】：

标签： r string dplyr stringr

【解决方案1】：

您可以使用grep。

grep("^[AT][CT]", s[,1])
# [1]  1  5 11 12 13 14 18 20 21 22 33 36 49 50 51 60 75 77 87 92 94

s[grep("^[AT][CT]", s[,1]), 1]
# [1] "TCCGCTGGTGCG" "TTTCAGCGTCAG" "TCCCGTGCGCCC" "TCTCCCAAACGA" "ATCATGGTCAAC"
# [6] "ACCGCACTGAAC" "ATGCGCGGCGAA" "ATGAGTAGTAGG" "TCTAGCGTCATT" "TCTCAACTTCTC"
#[11] "TCATCACTATGA" "TTGGCCGAAATT" "ACAACGCCATGT" "ATATACTAAGCC" "ACCGGAATAGCT"
#[16] "ATCTAAGCTGTT" "TCGTATAAGGTA" "ACGAAGAACGCT" "TTCGAGGTTGAT" "ACGAGCGCTATG"
#[21] "TCAGAGGCTGGA"

其中^表示字符串的开始，[AT]匹配A或T，[CT]匹配C或T。

数据

s <- structure(list(barcode.Universe.sub = c("TCCGCTGGTGCG", "GTCGCGGACTGC", 
"CTTCCAAAATAG", "CCCCTTTCGTGG", "TTTCAGCGTCAG", "TACGAGCCTGGT", 
"AGCAGTATCAAC", "TAACCGTATAGA", "GGCTAATTCCGC", "CTCGGTTGGGCG", 
"TCCCGTGCGCCC", "TCTCCCAAACGA", "ATCATGGTCAAC", "ACCGCACTGAAC", 
"AAGTTTTCCTCA", "CTAGAGACCGAT", "CATTCTCATGGA", "ATGCGCGGCGAA", 
"GAGTGCCCTAGG", "ATGAGTAGTAGG", "TCTAGCGTCATT", "TCTCAACTTCTC", 
"GAGAACGCTCCT", "TACAGGACACAC", "GATTCTCACGAT", "GAGACGGAGGCC", 
"GCGGCTCCTCTA", "TGGATACTCTGC", "GCACCGCGTTCA", "GAATTGATAAGT", 
"GGGCAGCAGATA", "GGCATATACGGC", "TCATCACTATGA", "CGCGGCTGGGAT", 
"AGTCGCCACGCT", "TTGGCCGAAATT", "CGAGACCCACCG", "TGGTGCCTCACT", 
"CTGATACTGGGT", "AGGTGGCGTCTA", "GGCAAGGAGTAC", "GCGACTGAAATA", 
"AGCTTCGGATTA", "GTTGCCAGACTC", "AGCTGTCGCACG", "AGGGTTCGCTGT", 
"GTGCGTACCGCG", "CGCTTACACATG", "ACAACGCCATGT", "ATATACTAAGCC", 
"ACCGGAATAGCT", "CTACGAACGACT", "TAACCTTATGCT", "GCCTGCAGATGA", 
"CGAGTGCGGTGG", "TGGAGGTGTACT", "CTTCAATATTGA", "AACGACATAAAC", 
"TACAGTGGATGC", "ATCTAAGCTGTT", "GCCTGGCATCTT", "CATGGGGAACCT", 
"GCCCGAGCTAAG", "GGGTGCTCCGAC", "TAATTAGGACGC", "TACCTAAGCGAT", 
"TAGTCTGTAGGC", "CGTTAACTCCGC", "GCACGAAGTCAC", "GAGCGTCCAGCT", 
"CCGACTTACAAA", "CCGGTTCAGATG", "TGCAGCTGTGTG", "AATCTATTTCTT", 
"TCGTATAAGGTA", "AACTGGATGCCC", "ACGAAGAACGCT", "AGTGCTCTTCTG", 
"CTACAGTGTACA", "AGGGCCATACTC", "AACAACCGCTTA", "CTAGACGGCAAT", 
"GGGTTGAAGAAG", "GGAGCATACTAA", "CGAACCCCGGTA", "TGTACCATGGAA", 
"TTCGAGGTTGAT", "GTGCTTAGGATC", "CAACCGTATGAC", "GACGTCCTTCAG", 
"TGGTAATGGACA", "ACGAGCGCTATG", "GCGGAGCCACCC", "TCAGAGGCTGGA", 
"GGCCTTACGCAA", "TACGACCCATAG", "CCATTCAGCATG", "CCTAAGGGCCTT", 
"GGTCTATCGCAT", "CAGTACATGTCG")), class = c("tbl_df", "tbl", 
"data.frame"), row.names = c(NA, -100L))

【讨论】：

非常感谢您的回答。有趣的是，我正在复制粘贴您的数据和代码，结果在 RStudio 中我只收到“整数（0）”。
也许你在复制时犯了错误？哪个R版本？
对不起，我刚刚编辑。当我在终端中执行它时，它工作得很好。谢谢！出于教育目的，您能否简要解释一下代码中的“[,1]), 1”是什么？
您提供了一个 data.frame，然后我选择了包含该字符串的列。