coolneng
/
locigenesis
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Document the repertoire script

This commit is contained in:
coolneng 2021-05-04 18:34:15 +02:00
parent 9e8beefd38
commit f4b7a41599
Signed by: coolneng
GPG Key ID: 9893DA236405AF57
1 changed files with 15 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
src/repertoire.r
View File

@ -1,6 +1,10 @@
library(immuneSIM) library(immuneSIM)
library(Biostrings) 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) { generate_repertoire <- function(number_of_sequences) {
return(immuneSIM( return(immuneSIM(
number_of_seqs = number_of_sequences, 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) { save_data <- function(data) {
Biostrings::writeXStringSet(data$sequence, Biostrings::writeXStringSet(data$sequence,
"data/sequence.fastq", "data/sequence.fastq",
@ -18,6 +25,11 @@ save_data <- function(data) {
Biostrings::writeXStringSet(data$junction, "data/HVR.fastq", format = "fastq") Biostrings::writeXStringSet(data$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) { process_data <- function(data, reads) {
dna_sequence <- Biostrings::DNAStringSet(data$sequence) dna_sequence <- Biostrings::DNAStringSet(data$sequence)
data$sequence <- Biostrings::reverseComplement(dna_sequence) data$sequence <- Biostrings::reverseComplement(dna_sequence)
@ -28,6 +40,9 @@ process_data <- function(data, reads) {
return(amplified_data) 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() { parse_cli_arguments <- function() {
args <- commandArgs(trailingOnly = TRUE) args <- commandArgs(trailingOnly = TRUE)
if (length(args) != 2) { if (length(args) != 2) {