Change output format to FASTA

.gitignore

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

generation.sh

@@ -11,9 +11,11 @@ fi
 
 sequences=$1
 sequencing_runs=$2
+read_mean_size=350
+read_variance_size=0.0
 data_directory="data/"
-file="sequence.fastq"
+file="sequence.fasta"
 prefix="curesim_"
 
 Rscript src/repertoire.r "$sequences" "$sequencing_runs"
-java -jar tools/CuReSim.jar -f "$data_directory$file" -o "$data_directory$prefix$file"
+java -jar tools/CuReSim.jar -m "$read_mean_size" -sd "$read_variance_size" -f "$data_directory$file" -o "$data_directory$prefix$file"

src/repertoire.r

@@ -1,7 +1,7 @@
 library(immuneSIM)
 library(Biostrings)
 
-generate_repertoires <- function(number_of_sequences) {
+generate_repertoire <- function(number_of_sequences) {
   b_chain <- immuneSIM(
     number_of_seqs = number_of_sequences,
     species = "hs",
@@ -22,9 +22,8 @@ preprocess_data <- function(repertoire, sequencing_runs) {
 }
 
 save_data <- function(repertoire) {
-  file_name <- "data/sequence.fastq"
-  # TODO Change format to fasta
-  Biostrings::writeXStringSet(repertoire, file_name, format = "fastq")
+  file_name <- "data/sequence.fasta"
+  Biostrings::writeXStringSet(repertoire, file_name, format = "fasta")
 }
 
 parse_cli_arguments <- function(args) {
@@ -35,9 +34,9 @@ parse_cli_arguments <- function(args) {
 }
 
 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)
+arguments <- parse_cli_arguments(args)
+number_of_sequences <- as.integer(arguments[1])
+sequencing_runs <- as.integer(arguments[2])
+repertoire <- generate_repertoire(number_of_sequences)
 processed_data <- preprocess_data(repertoire, sequencing_runs)
 save_data(processed_data)