From f4b7a4159994eb52b9bd0882f6bdcb2012e6c51e Mon Sep 17 00:00:00 2001
From: coolneng <akasroua@gmail.com>
Date: Tue, 4 May 2021 18:34:15 +0200
Subject: [PATCH] Document the repertoire script

---
 src/repertoire.r | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/src/repertoire.r b/src/repertoire.r
index 8edb480..28ea1a3 100644
--- a/src/repertoire.r
+++ b/src/repertoire.r
@@ -1,6 +1,10 @@
 library(immuneSIM)
 library(Biostrings)
 
+#' Generate the beta chain of a human T-cell receptor (TCR)
+#'
+#' @param number_of_sequences Number of different sequences to generate
+#' @return A \code{data.frame} with the sequences, V and J genes and CDR3
 generate_repertoire <- function(number_of_sequences) {
   return(immuneSIM(
     number_of_seqs = number_of_sequences,
@@ -10,6 +14,9 @@ generate_repertoire <- function(number_of_sequences) {
   ))
 }
 
+#' Saves the sequences and CDR3 to FASTQ files
+#'
+#' @param data A \code{data.frame} with the preprocessed TCR sequences and CDR3
 save_data <- function(data) {
   Biostrings::writeXStringSet(data$sequence,
     "data/sequence.fastq",
@@ -18,6 +25,11 @@ save_data <- function(data) {
   Biostrings::writeXStringSet(data$junction, "data/HVR.fastq", format = "fastq")
 }
 
+#' Applies the reverse complement and amplifies the number of sequences
+#'
+#' @param data A \code{data.frame} containing the TCR sequences and CDR3
+#' @param reads Number of times to amplify each sequence
+#' @return A \code{data.frame} with reverse complement sequences and VJ metadata
 process_data <- function(data, reads) {
   dna_sequence <- Biostrings::DNAStringSet(data$sequence)
   data$sequence <- Biostrings::reverseComplement(dna_sequence)
@@ -28,6 +40,9 @@ process_data <- function(data, reads) {
   return(amplified_data)
 }
 
+#' Checks the number of command line arguments and captures them
+#'
+#' @return A \code{vector} containing the command line arguments
 parse_cli_arguments <- function() {
   args <- commandArgs(trailingOnly = TRUE)
   if (length(args) != 2) {