locigenesis/src/repertoire.r

library(immuneSIM)
library(Biostrings)

generate_repertoire <- function(number_of_sequences) {
  return(immuneSIM(
    number_of_seqs = number_of_sequences,
    species = "hs",
    receptor = "tr",
    chain = "b"
  ))
}

save_data <- function(data, reads) {
  Biostrings::writeXStringSet(data$sequence, "data/sequence.fasta")
  vdj_sequences <- data[-1]
  amplified_vdj <- vdj_sequences[rep(seq_len(nrow(vdj_sequences)), reads), ]
  write.csv(amplified_vdj, "data/vdj_alignment.csv", row.names = FALSE)
}

process_data <- function(repertoire, reads) {
  columns <- c(
    "sequence", "v_sequence_alignment",
    "d_sequence_alignment", "j_sequence_alignment"
  )
  data <- repertoire[, columns]
  dna_sequence <- Biostrings::DNAStringSet(data$sequence)
  data$sequence <- Biostrings::reverseComplement(dna_sequence)
  save_data(data, reads)
}

parse_cli_arguments <- function() {
  args <- commandArgs(trailingOnly = TRUE)
  if (length(args) != 2) {
    stop("usage: repertoire.r <number of sequences> <sequencing runs>")
  }
  return(c(args[1], args[2]))
}

args <- parse_cli_arguments()
repertoire <- generate_repertoire(number_of_sequences = as.integer(args[1]))
process_data(repertoire = repertoire, reads = as.integer(args[2]))