.gitignore

@@ -1,2 +1 @@
 *.txt
-*.fastq

generation.sh

@@ -1,19 +1,21 @@
 #!/bin/sh
 
 usage() {
-	echo "usage: generation.sh <number of sequences> <sequencing runs>"
+	echo "usage: generation.sh <number of sequences>"
 	exit 1
 }
 
-if [ $# != 2 ]; then
+if [ $# != 1 ]; then
 	usage
 fi
 
 sequences=$1
-sequencing_runs=$2
 data_directory="data/"
-file="sequence.fastq"
 prefix="curesim_"
 
-Rscript src/repertoire.r "$sequences" "$sequencing_runs"
-java -jar tools/CuReSim.jar -f "$data_directory$file" -o "$data_directory$prefix$file"
+Rscript src/repertoire.r "$sequences"
+
+for file in "$data_directory"*.fastq; do
+	file_name=$(echo "$file" | cut -d / -f 2)
+	java -jar tools/CuReSim.jar -f "$file" -o "$data_directory$prefix$file_name"
+done

shell.nix

@@ -8,7 +8,7 @@ mkShell {
     rPackages.immuneSIM
     rPackages.Biostrings
     jdk
-    # Development tools
+    # Develoment tools
     rPackages.languageserver
     rPackages.lintr
   ];

src/repertoire.r

@@ -2,6 +2,13 @@ library(immuneSIM)
 library(Biostrings)
 
 generate_repertoires <- function(number_of_sequences) {
+  a_chain <- immuneSIM(
+    number_of_seqs = number_of_sequences,
+    species = "hs",
+    receptor = "tr",
+    chain = "a",
+    verbose = TRUE
+  )
   b_chain <- immuneSIM(
     number_of_seqs = number_of_sequences,
     species = "hs",
@@ -9,35 +16,40 @@ generate_repertoires <- function(number_of_sequences) {
     chain = "b",
     verbose = TRUE
   )
-  return(b_chain)
+  return(list("a_chain" = a_chain, "b_chain" = b_chain))
 }
 
-# TODO save also v_call and j_call
-preprocess_data <- function(repertoire, sequencing_runs) {
+process_chain <- function(repertoire) {
   sequences <- as.character(repertoire$sequence)
-  reads <- Biostrings::DNAStringSet(rep(sequences, sequencing_runs))
+  counts <- as.integer(repertoire$counts)
+  reads <- Biostrings::DNAStringSet(rep(sequences, counts))
   names(reads) <- seq_len(length(reads))
   reverse_complement <- Biostrings::reverseComplement(reads)
   return(reverse_complement)
 }
 
-save_data <- function(repertoire) {
-  file_name <- "data/sequence.fastq"
-  # TODO Change format to fasta
-  Biostrings::writeXStringSet(repertoire, file_name, format = "fastq")
+preprocess_data <- function(repertoires) {
+  filtered_repertoires <- lapply(repertoires, process_chain)
+  names(filtered_repertoires) <- names(repertoires)
+  return(filtered_repertoires)
+}
+
+save_data <- function(repertoires) {
+  for (chain in names(repertoires)) {
+    file_name <- paste("data/", chain, ".fastq", sep = "")
+    Biostrings::writeXStringSet(repertoires[[chain]], file_name, format = "fastq")
+  }
 }
 
 parse_cli_arguments <- function(args) {
-  if (length(args) != 2) {
-    stop("usage: repertoire.r <number of sequences> <sequencing_runs>")
+  if (length(args) != 1) {
+    stop("usage: repertoire.r <number of sequences>")
   }
-  return(c(args[1], args[2]))
+  return(as.integer(args[1]))
 }
 
 args <- commandArgs(trailingOnly = TRUE)
-parameters <- parse_cli_arguments(args)
-number_of_sequences <- as.integer(parameters[1])
-sequencing_runs <- as.integer(parameters[2])
-repertoire <- generate_repertoires(number_of_sequences)
-processed_data <- preprocess_data(repertoire, sequencing_runs)
+number_of_sequences <- parse_cli_arguments(args)
+sim_repertoire <- generate_repertoires(number_of_sequences)
+processed_data <- preprocess_data(sim_repertoire)
 save_data(processed_data)