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) {
  Biostrings::writeXStringSet(data$sequence,
    "data/sequence.fastq",
    format = "fastq"
  )
  Biostrings::writeXStringSet(data$junction, "data/HVR.fastq", format = "fastq")
}

process_data <- function(data, reads) {
  dna_sequence <- Biostrings::DNAStringSet(data$sequence)
  data$sequence <- Biostrings::reverseComplement(dna_sequence)
  names(data$sequence) <- paste(rownames(data), data$v_call, data$j_call, " ")
  data$junction <- Biostrings::DNAStringSet(data$junction)
  names(data$junction) <- rownames(data)
  amplified_data <- data[rep(seq_len(nrow(data)), reads), ]
  return(amplified_data)
}

parse_cli_arguments <- function() {
  args <- commandArgs(trailingOnly = TRUE)
  if (length(args) != 2) {
    stop("usage: repertoire.r <number of sequences> <number of reads>")
  }
  return(args)
}

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