Given a list of nucleotide IDs, fetch sequences and write to DNAStringSet

entrez2dss.R

entrez2dss <-
  function(id_list) {
    
    require(rentrez)    # v1.2.3
    require(Biostrings) # v2.66.0
    require(stringr)    # v1.5.0
    
    # fetch all sequences, trim empty elements
    raw_ <-
      entrez_fetch(db = "nucleotide",
                   rettype = "fasta",
                   id = id_list) |>
      str_split_1(pattern = "\n\n") |>
      head(-1)
    
    # get sequence names
    names_ <- 
      gsub(pattern = "\n.*",
           replacement = "",
           x = raw_) |>
      gsub(pattern = "^>",
           replacement  = "")
    
    # get sequences
    seqs_ <-
      sub(pattern = ".*?\n",
          replacement = "",
          x = raw_) |>
      gsub(pattern = "\n",
           replacement = "")
    
    # create named DNAStringSet object
    dss <- DNAStringSet(x = seqs_)
    names(dss) <- names_
    dss
    
  }

# test
seqlist <- c("NC_045512", "OR558592")
cov2 <- entrez2dss(seqlist)

https://bioinformatics.stackexchange.com/a/21716/3967