R：按字母差异过滤单词向量

Question

我正在使用以下命令创建一个单词向量：

DNA <- c("A","G","T","C")
randomDNA <- c()

for (i in 1:96){
  randomDNA[i] <- paste0(sample(DNA, 6, replace = TRUE), sep = "", collapse = "")
}

这将创建一个包含 96 个元素的向量。包含 A、T、C、G 的单词。 我该怎么做：

A. 在循环中插入一个条件，该条件将保持彼此之间至少有 3 个差异的单词，保持向量的大小不变？

B. 做同样的事情，但删除相同单词的重复。 谢谢大家

Answer 1

更新

根据您对Hamming distance 的尝试，您可以尝试以下代码

Humm_gt3 <- DNAall[1]
for (i in 2:length(DNAall)) {
  split_vector <- strsplit(DNAall[i], "")[[1]]
  flag_gt3 <- TRUE
  for (j in 1:length(Humm_gt3)) {
    split_vector2 <- strsplit(Humm_gt3[j], "")[[1]]
    flag_gt3 <- flag_gt3 & (sum(split_vector != split_vector2) >= 3)
  }
  if (flag_gt3) Humm_gt3 <- c(Humm_gt3, DNAall[i])
}

或更轻的版本（更高效）

Humm_gt3 <- DNAall[1]
for (i in DNAall[-1]) {
  v <- utf8ToInt(i)
  flag_gt3 <- TRUE
  for (j in Humm_gt3) {
    if (sum(v != utf8ToInt(j)) < 3) {
      flag_gt3 <- FALSE
      break
    }
  }
  if (flag_gt3) Humm_gt3 <- c(Humm_gt3, i)
}

给了

> Humm_gt3
 [1] "AAAAAA" "GGGAAA" "TTTAAA" "CCCAAA" "TGAGAA" "CAGGAA" "ACTGAA" "GTCGAA"
 [9] "CTATAA" "TCGTAA" "GATTAA" "AGCTAA" "GCACAA" "ATGCAA" "CGTCAA" "TACCAA"
[17] "CGAAGA" "TAGAGA" "GCTAGA" "ATCAGA" "GAAGGA" "AGGGGA" "CTTGGA" "TCCGGA"
[25] "ACATGA" "GTGTGA" "TGTTGA" "CACTGA" "TTACGA" "CCGCGA" "AATCGA" "GGCCGA"
[33] "GTAATA" "ACGATA" "CATATA" "TGCATA" "CCAGTA" "TTGGTA" "GGTGTA" "AACGTA"
[41] "TAATTA" "CGGTTA" "ATTTTA" "GCCTTA" "AGACTA" "GAGCTA" "TCTCTA" "CTCCTA"
[49] "TCAACA" "CTGACA" "AGTACA" "GACACA" "ATAGCA" "GCGGCA" "TATGCA" "CGCGCA"
[57] "GGATCA" "AAGTCA" "CCTTCA" "TTCTCA" "CAACCA" "TGGCCA" "GTTCCA" "ACCCCA"

---

上一个答案

1. 您可以尝试使用expand.grid 构建DNA 的所有组合，即DNAall，如下所示

DNAall <- do.call(paste0, expand.grid(rep(list(DNA), 6)))

1. 然后，您可以使用for 循环和adist 选择与DNA_gt3 中所有其他选定序列具有距离>=3 的DNA 序列

DNA_gt3 <- DNAall[1]
for (dna in DNAall[-1]) {
  if (all(adist(dna, DNA_gt3) >= 3)) DNA_gt3 <- c(DNA_gt3, dna)
}

1. 最后，您将获得一整套DNA，它们在DNA_gt3中的任何一对之间至少有3个距离，即，

> DNA_gt3
 [1] "AAAAAA" "GGGAAA" "TTTAAA" "CCCAAA" "TGAGAA" "CAGGAA" "ACTGAA" "GTCGAA"
 [9] "CTATAA" "GATTAA" "GCACAA" "TACCAA" "CGAAGA" "GCTAGA" "ATCAGA" "AGGGGA"
[17] "TATGGA" "GTGTGA" "TCCTGA" "TTACGA" "CCGCGA" "GGCCGA" "GTAATA" "TGCATA"
[25] "CCAGTA" "AACGTA" "TAGTTA" "CGTTTA" "ATTCTA" "TCAACA" "AGTACA" "GCGGCA"
[33] "CTTGCA" "GGATCA" "CACTCA" "AAGCCA" "AGCAAG" "TCGGAG" "ATGTAG" "CCTTAG"
[41] "GTTCAG" "GAAAGG" "TTGAGG" "ATAGGG" "GGTGGG" "CACGGG" "AATTGG" "TCTCGG"
[49] "AAGATG" "CTCATG" "CGGGTG" "TTTGTG" "GCCGTG" "TGATTG" "CAACTG" "TACACG"
[57] "GAGTCG" "ACCTCG" "AGACCG" "CTGCCG" "CGTGAT" "AGATAT" "GCCTAT" "GAGCAT"
[65] "ATCCAT" "CAGAGT" "TGCGGT" "TAATGT" "CTTCGT" "ACAATT" "GGTATT" "GAAGTT"
[73] "ATGGTT" "TCTTTT" "CCCCTT" "TGGACT" "GTCACT" "TTAGCT" "CCATCT" "CGGTAC"
[81] "ACGCAC" "TCAGGC" "GAGGGC" "AGCTGC" "AAACGC" "TGGCGC" "TAAATC" "CATGTC"
[89] "ATATTC" "GCGTTC" "TTCCTC" "CTAACC" "GATACC" "CGCGCC" "TTGTCC" "CCTCCC"

---

为了你的第二个目标

由于DNA_gt3是一个完整的集合，如果你想查看randomDNA中有哪些独特的元素属于这个集合，你可以使用

unique(randomDNA[randomDNA %in% DNA_gt3])