Parse HMMER domtblout in R, no dependencies

parse_domtblout.R

parse_domtblout_file <- function(dom){
  dom = readLines(dom)
  dom <- dom[!grepl("^#", dom)]
  dom <- lapply(strsplit(dom, "[ ]{1,}"), 
                function(x){
                  parsed <- c(x[1:22], paste0(x[23:length(x)], collapse = " "))
                  as.data.frame(t(parsed))
                })
  dom <- do.call(rbind, dom)
  colnames(dom) <- c("target_name",
                     "target_accession",
                     "tlen",
                     "query_name",
                     "accession",
                     "qlen",
                     "E_value",
                     "score",
                     "bias",
                     "number",
                     "of",
                     "cEvalue",
                     "i_Evalue",
                     "score",
                     "bias",
                     "from_hmm_coord",
                     "to_hmm_coord",
                     "from_ali_coord",
                     "to_ali_coord",
                     "from_env_coord",
                     "to_env_coord",
                     "acc",
                     "description_of_target")
  dom
  }