Add usage instructions to the README

.gitignore

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

README.org

@@ -1,3 +1,49 @@
 * locigenesis
 
 locigenesis is a tool that generates an immune repertoire and runs it through a sequence reader simulation tool, to generate sequencing errors.
+
+** Installation
+
+This project uses [[https://nixos.org/][Nix]] to ensure reproducible builds.
+
+1. Install Nix (compatible with MacOS, Linux and [[https://docs.microsoft.com/en-us/windows/wsl/about][WSL]]):
+
+#+begin_src shell
+curl -L https://nixos.org/nix/install | sh
+#+end_src
+
+1. Clone the repository:
+
+#+begin_src shell
+git clone https://git.coolneng.duckdns.org/coolneng/locigenesis
+#+end_src
+
+3. Change the working directory to the project:
+
+#+begin_src shell
+cd locigenesis
+#+end_src
+
+4. Enter the nix-shell:
+
+#+begin_src shell
+nix-shell
+#+end_src
+
+After running these commands, you will find yourself in a shell that contains all the needed dependencies.
+
+** Usage
+
+An execution script that accepts 2 parameters is provided, the following command invokes it:
+
+#+begin_src shell
+./generation.sh <number of sequences> <number of reads>
+#+end_src
+
+- <number of sequences>: an integer that specifies the number of different sequences to generate
+- <number of reads>: an integer that specifies the number of reads to perform on each sequence
+
+The script will generate 2 files under the data directory:
+
+| HVR.fastq         | Contains the original CDR3 sequence                             |
+| CuReSim-HVR.fastq | Contains CDR3 after the read simulation, with sequencing errors |

generation.sh

@@ -1,7 +1,7 @@
 #!/bin/sh
 
 usage() {
-	echo "usage: generation.sh <number of sequences> <number_of_reads>"
+	echo "usage: generation.sh <number of sequences> <number of reads>"
 	exit 1
 }
 
@@ -11,14 +11,12 @@ fi
 
 sequences=$1
 number_of_reads=$2
-read_mean_size=350
-read_variance_size=0.0
 data_directory="data/"
-fasta=".fasta"
 fastq=".fastq"
 filename="sequence"
 prefix="curesim_"
 
-Rscript src/repertoire.r "$sequences" &&
+Rscript src/repertoire.r "$sequences" "$number_of_reads" &&
-	java -jar tools/CuReSim.jar -n $((number_of_reads * sequences)) -m "$read_mean_size" -sd "$read_variance_size" -f "$data_directory$filename$fasta" -o "$data_directory$prefix$filename$fastq"
+	CuReSim -f "$data_directory$filename$fastq" -o "$data_directory$prefix$filename$fastq"
+Rscript src/alignment.r
 rm "$data_directory/log.txt"

shell.nix

@@ -2,14 +2,35 @@
 
 with pkgs;
 
-mkShell {
+let
+  CuReSim = stdenv.mkDerivation rec {
+    name = "CuReSim";
+    version = "1.3";
+    src = fetchzip {
+      url =
+        "http://www.pegase-biosciences.com/wp-content/uploads/2015/08/${name}${version}.zip";
+      sha256 = "1hvlpgy4haqgqq52mkxhcl9i1fx67kgwi6f1mijvqzk0xff77hkp";
+      stripRoot = true;
+      extraPostFetch = ''
+        chmod go-w $out
+      '';
+    };
+
+    nativeBuildInputs = [ makeWrapper ];
+
+    installPhase = ''
+      mkdir -pv $out/share/java $out/bin
+      cp -r ${src} $out/share/java/${name}
+      makeWrapper ${pkgs.jdk}/bin/java $out/bin/CuReSim --add-flags "-jar $out/share/java/${name}/${name}.jar"
+    '';
+  };
+in mkShell {
   buildInputs = [
     R
     rPackages.immuneSIM
     rPackages.Biostrings
+    rPackages.stringr
     jdk
-    # Development tools
+    CuReSim
-    rPackages.languageserver
-    rPackages.lintr
   ];
 }

src/alignment.r

@@ -50,16 +50,52 @@ align_sequence <- function(sequence, vdj_segment) {
   ))
 }
 
-# TODO Extract CDR3
+handle_indels <- function(insertion, deletion, cys, alignment) {
-get_hvr_sequences <- function(sequences, vdj_segments) {
+  ins_start <- sum(Biostrings::width(deletion[start(deletion) <= cys$start]))
+  ins_end <- sum(Biostrings::width(deletion[end(deletion) <= cys$end]))
+  shift_num <- c(0, cumsum(Biostrings::width(insertion))[-length(ins_start)])
+  shifted_ins <- IRanges::shift(insertion, shift_num)
+  gaps <- sum(width(shifted_ins[end(shifted_ins) < cys$start + ins_start])) +
+    nchar(stringr::str_extract(alignedSubject(alignment), "^-*"))
+  return(list("start" = ins_start - gaps, "end" = ins_end - gaps))
+}
+
+get_cys_coordinates <- function(alignment) {
+  cys <- list("start" = 310, "end" = 312)
+  insertion <- unlist(Biostrings::insertion(alignment))
+  deletion <- unlist(Biostrings::deletion(alignment))
+  delta_coordinates <- handle_indels(insertion, deletion, cys, alignment)
+  cys_start <- cys$start + delta_coordinates$start
+  cys_end <- cys$end + delta_coordinates$end
+  return(list("start" = cys_start, "end" = cys_end))
+}
+
+get_hvr_sequences <- function(sequences, vdj_segments, cores = detectCores()) {
   df <- fetch_vj_sequences(sequences, vdj_segments)
-  v_alignment <- parallel::mcmapply(sequences, df$v_seq, FUN = align_sequence)
+  v_alignment <- parallel::mcmapply(sequences,
-  j_alignment <- parallel::mcmapply(sequences, df$j_seq, FUN = align_sequence)
+    df$v_seq,
-  print(v_alignment)
+    FUN = align_sequence,
+    mc.cores = cores
+  )
+  cys_coordinates <- parallel::mclapply(v_alignment, FUN = get_cys_coordinates)
+  cys_df <- as.data.frame(do.call(rbind, cys_coordinates))
+  remaining <- Biostrings::subseq(sequences, start = unlist(cys_df$end))
+  j_alignment <- parallel::mcmapply(remaining,
+    df$j_seq,
+    FUN = align_sequence,
+    mc.cores = cores
+  )
+  j_start <- parallel::mclapply(
+    j_alignment,
+    function(x) start(Biostrings::Views(x)),
+    mc.cores = cores
+  )
+  hvr_start <- unlist(cys_df$start)
+  hvr_end <- unlist(cys_df$start) + unlist(j_start) + 2
+  hvr <- Biostrings::subseq(sequences, start = hvr_start, end = hvr_end)
+  return(hvr)
 }
 
 data <- parse_data(file = "data/curesim_sequence.fastq")
-hvr_sequences <- get_hvr_sequences(
+hvr <- get_hvr_sequences(sequences = data[[1]], vdj_segments = data[[2]])
-  sequences = data[[1]],
+Biostrings::writeXStringSet(hvr, "data/CuReSim-HVR.fastq", format = "fastq")
-  vdj_segments = data[[2]]
-)

src/repertoire.r

@@ -11,26 +11,32 @@ generate_repertoire <- function(number_of_sequences) {
 }
 
 save_data <- function(data) {
-  Biostrings::writeXStringSet(data$sequence, "data/sequence.fasta")
+  Biostrings::writeXStringSet(data$sequence,
-  Biostrings::writeXStringSet(data$junction, "data/HVR.fasta")
+    "data/sequence.fastq",
+    format = "fastq"
+  )
+  Biostrings::writeXStringSet(data$junction, "data/HVR.fastq", format = "fastq")
 }
 
-process_data <- function(data) {
+process_data <- function(data, reads) {
   dna_sequence <- Biostrings::DNAStringSet(data$sequence)
   data$sequence <- Biostrings::reverseComplement(dna_sequence)
   names(data$sequence) <- paste(rownames(data), data$v_call, data$j_call, " ")
-  return(data)
+  data$junction <- Biostrings::DNAStringSet(data$junction)
+  names(data$junction) <- rownames(data)
+  amplified_data <- data[rep(seq_len(nrow(data)), reads), ]
+  return(amplified_data)
 }
 
 parse_cli_arguments <- function() {
   args <- commandArgs(trailingOnly = TRUE)
-  if (length(args) != 1) {
+  if (length(args) != 2) {
-    stop("usage: repertoire.r <number of sequences>")
+    stop("usage: repertoire.r <number of sequences> <number of reads>")
   }
-  return(args[1])
+  return(args)
 }
 
-argument <- parse_cli_arguments()
+args <- parse_cli_arguments()
-repertoire <- generate_repertoire(number_of_sequences = as.integer(argument))
+repertoire <- generate_repertoire(number_of_sequences = as.integer(args[1]))
-data <- process_data(data = repertoire)
+data <- process_data(data = repertoire, reads = args[2])
 save_data(data)