From 66b39485a93f130730cf151ec5d731fc0560e1e5 Mon Sep 17 00:00:00 2001
From: coolneng <akasroua@gmail.com>
Date: Tue, 23 Mar 2021 19:33:32 +0100
Subject: [PATCH] Save vdj alignment sequences to a CSV

---
 .gitignore       |  2 +-
 src/repertoire.r | 26 ++++++++++++++------------
 2 files changed, 15 insertions(+), 13 deletions(-)

diff --git a/.gitignore b/.gitignore
index 919f14d..11cc81f 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,3 @@
-*.txt
+*.csv
 *.fasta
 *.fastq
diff --git a/src/repertoire.r b/src/repertoire.r
index 0cb40b8..dcf2909 100644
--- a/src/repertoire.r
+++ b/src/repertoire.r
@@ -19,21 +19,23 @@ amplify_rows <- function(data, column, factor) {
   return(rep(data, factor))
 }
 
-save_data <- function(data, name) {
-  if (name == "sequence") {
-    file_name <- paste("data/", name, ".fasta", sep = "")
-    Biostrings::writeXStringSet(data, file_name, format = "fasta")
-  } else {
-    file_name <- paste("data/", name, ".txt", sep = "")
-    cat(data, file = file_name, sep = "\n")
-  }
+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) {
-  columns <- c("sequence", "v_call", "j_call")
+  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)
-  invisible(mapply(amplified_data, names(amplified_data), FUN = save_data))
+  amplified_data <- mapply(data, names(data),
+    sequencing_runs,
+    FUN = amplify_rows
+  )
+  save_data(amplified_data)
 }
 
 parse_cli_arguments <- function(args) {
@@ -48,4 +50,4 @@ 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)
+process_data(repertoire, sequencing_runs)
\ No newline at end of file