From 576597cb0464c4580963c20f70fa80aa1ee66754 Mon Sep 17 00:00:00 2001
From: coolneng <akasroua@gmail.com>
Date: Mon, 29 Mar 2021 20:30:16 +0200
Subject: [PATCH] Remove redundant sequencing runs argument

---
 generation.sh    |  3 +--
 src/repertoire.r | 37 ++++++++++++-------------------------
 2 files changed, 13 insertions(+), 27 deletions(-)

diff --git a/generation.sh b/generation.sh
index 9853ac2..fa6ae17 100755
--- a/generation.sh
+++ b/generation.sh
@@ -19,6 +19,5 @@ fastq=".fastq"
 filename="sequence"
 prefix="curesim_"
 
-Rscript src/repertoire.r "$sequences" "$sequencing_runs"
-java -jar tools/CuReSim.jar -m "$read_mean_size" -sd "$read_variance_size" -f "$data_directory$filename$fasta" -o "$data_directory$prefix$filename$fastq"
+Rscript src/repertoire.r "$sequences" && java -jar tools/CuReSim.jar -n "$sequencing_runs" -m "$read_mean_size" -sd "$read_variance_size" -f "$data_directory$filename$fasta" -o "$data_directory$prefix$filename$fastq"
 rm "$data_directory/log.txt"
diff --git a/src/repertoire.r b/src/repertoire.r
index dcf2909..60c03c3 100644
--- a/src/repertoire.r
+++ b/src/repertoire.r
@@ -10,44 +10,31 @@ generate_repertoire <- function(number_of_sequences) {
   ))
 }
 
-amplify_rows <- function(data, column, factor) {
-  if (column == "sequence") {
-    dna_string <- Biostrings::DNAStringSet(data)
-    reverse_complement <- Biostrings::reverseComplement(dna_string)
-    return(rep(reverse_complement, factor))
-  }
-  return(rep(data, factor))
-}
-
 save_data <- function(data) {
   Biostrings::writeXStringSet(data$sequence, "data/sequence.fasta")
   vdj_sequences <- data[-1]
   write.csv(vdj_sequences, "data/vdj_alignment.csv", row.names = FALSE)
 }
 
-process_data <- function(repertoire, sequencing_runs) {
+process_data <- function(repertoire) {
   columns <- c(
     "sequence", "v_sequence_alignment",
     "d_sequence_alignment", "j_sequence_alignment"
   )
   data <- repertoire[, columns]
-  amplified_data <- mapply(data, names(data),
-    sequencing_runs,
-    FUN = amplify_rows
-  )
-  save_data(amplified_data)
+  dna_sequence <- Biostrings::DNAStringSet(data$sequence)
+  data$sequence <- Biostrings::reverseComplement(dna_sequence)
+  save_data(data)
 }
 
-parse_cli_arguments <- function(args) {
-  if (length(args) != 2) {
-    stop("usage: repertoire.r <number of sequences> <sequencing_runs>")
+parse_cli_arguments <- function() {
+  args <- commandArgs(trailingOnly = TRUE)
+  if (length(args) != 1) {
+    stop("usage: repertoire.r <number of sequences>")
   }
-  return(c(args[1], args[2]))
+  return(args[1])
 }
 
-args <- commandArgs(trailingOnly = TRUE)
-arguments <- parse_cli_arguments(args)
-number_of_sequences <- as.integer(arguments[1])
-sequencing_runs <- as.integer(arguments[2])
-repertoire <- generate_repertoire(number_of_sequences)
-process_data(repertoire, sequencing_runs)
\ No newline at end of file
+args <- parse_cli_arguments()
+repertoire <- generate_repertoire(number_of_sequences = as.integer(args[1]))
+process_data(repertoire)
\ No newline at end of file