Replace niv with flakes

.gitignore

@@ -0,0 +1 @@
+*.fastq

README.md

@@ -0,0 +1,68 @@
+# locigenesis
+
+locigenesis is a tool that generates a human T-cell receptor (TCR), runs
+it through a sequence reader simulation tool and extracts CDR3.
+
+The goal of this project is to generate both HVR sequences with and
+without sequencing errors, in order to create datasets for a Machine
+Learning algorithm.
+
+## Technologies
+
+-   [immuneSIM](https://github.com/GreiffLab/immuneSIM/): in silico
+    generation of human and mouse BCR and TCR repertoires
+-   [CuReSim](http://www.pegase-biosciences.com/curesim-a-customized-read-simulator/):
+    read simulator that mimics Ion Torrent sequencing
+
+## Installation
+
+This project uses [Nix](https://nixos.org/) to ensure reproducible
+builds.
+
+1.  Install Nix (compatible with MacOS, Linux and
+    [WSL](https://docs.microsoft.com/en-us/windows/wsl/about)):
+
+```bash
+curl -L https://nixos.org/nix/install | sh
+```
+
+2.  Clone the repository:
+
+```bash
+git clone https://git.coolneng.duckdns.org/coolneng/locigenesis
+```
+
+3.  Change the working directory to the project:
+
+```bash
+cd locigenesis
+```
+
+4.  Enter the nix-shell:
+
+```bash
+nix-shell
+```
+
+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:
+
+```bash
+./generation.sh <number of sequences> <number of reads>
+```
+
+-   \<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  | curesim-HVR.fastq |
+|:----:|:-----:|
+|Contains the original CDR3 sequence|Contains CDR3 after the read simulation, with sequencing errors |

README.org

@@ -1,3 +0,0 @@
-* locigenesis
-
-locigenesis is a tool that generates an immune repertoire and runs it through a sequence reader simulation tool, to generate sequencing errors.

flake.lock

@@ -0,0 +1,41 @@
+{
+  "nodes": {
+    "flake-utils": {
+      "locked": {
+        "lastModified": 1634851050,
+        "narHash": "sha256-N83GlSGPJJdcqhUxSCS/WwW5pksYf3VP1M13cDRTSVA=",
+        "owner": "numtide",
+        "repo": "flake-utils",
+        "rev": "c91f3de5adaf1de973b797ef7485e441a65b8935",
+        "type": "github"
+      },
+      "original": {
+        "owner": "numtide",
+        "repo": "flake-utils",
+        "type": "github"
+      }
+    },
+    "nixpkgs": {
+      "locked": {
+        "lastModified": 1635865339,
+        "narHash": "sha256-fmI8PxMmL7WXV/O8m6vT9/yW42buxvAYeRNpcABvnKs=",
+        "owner": "NixOS",
+        "repo": "nixpkgs",
+        "rev": "26a56abd090ec5c8f4c6c9e1189fbfa4bcb8db3f",
+        "type": "github"
+      },
+      "original": {
+        "id": "nixpkgs",
+        "type": "indirect"
+      }
+    },
+    "root": {
+      "inputs": {
+        "flake-utils": "flake-utils",
+        "nixpkgs": "nixpkgs"
+      }
+    }
+  },
+  "root": "root",
+  "version": 7
+}

flake.nix

@@ -0,0 +1,13 @@
+{
+  description = ''
+    locigenesis is a tool that generates a human T-cell receptor (TCR), runs
+    it through a sequence reader simulation tool and extracts CDR3.
+  '';
+
+  inputs.flake-utils.url = "github:numtide/flake-utils";
+
+  outputs = { self, nixpkgs, flake-utils }:
+    flake-utils.lib.eachDefaultSystem (system:
+      let pkgs = nixpkgs.legacyPackages.${system};
+      in { devShell = import ./shell.nix { inherit pkgs; }; });
+}

generation.sh

@@ -1,21 +1,22 @@
 #!/bin/sh
 
 usage() {
-	echo "usage: generation.sh <number of sequences>"
+	echo "usage: generation.sh <number of sequences> <number of reads>"
 	exit 1
 }
 
-if [ $# != 1 ]; then
+if [ $# != 2 ]; then
 	usage
 fi
 
 sequences=$1
+number_of_reads=$2
 data_directory="data/"
+fastq=".fastq"
+filename="sequence"
 prefix="curesim_"
 
-Rscript src/repertoire.r "$sequences"
+Rscript src/repertoire.r "$sequences" "$number_of_reads" &&
-
+	CuReSim -f "$data_directory$filename$fastq" -o "$data_directory$prefix$filename$fastq"
-for file in "$data_directory"*.fastq; do
+Rscript src/alignment.r
-	file_name=$(echo "$file" | cut -d / -f 2)
+rm "$data_directory/log.txt"
-	java -jar tools/CuReSim.jar -f "$file" -o "$data_directory$prefix$file_name"
-done

nix/sources.json

@@ -1,26 +0,0 @@
-{
-    "niv": {
-        "branch": "master",
-        "description": "Easy dependency management for Nix projects",
-        "homepage": "https://github.com/nmattia/niv",
-        "owner": "nmattia",
-        "repo": "niv",
-        "rev": "af958e8057f345ee1aca714c1247ef3ba1c15f5e",
-        "sha256": "1qjavxabbrsh73yck5dcq8jggvh3r2jkbr6b5nlz5d9yrqm9255n",
-        "type": "tarball",
-        "url": "https://github.com/nmattia/niv/archive/af958e8057f345ee1aca714c1247ef3ba1c15f5e.tar.gz",
-        "url_template": "https://github.com/<owner>/<repo>/archive/<rev>.tar.gz"
-    },
-    "nixpkgs": {
-        "branch": "release-20.09",
-        "description": "Nix Packages collection",
-        "homepage": "",
-        "owner": "NixOS",
-        "repo": "nixpkgs",
-        "rev": "6f1ce38d0c0b1b25727d86637fd2f3baf7b0f1f6",
-        "sha256": "16da722vqn96k1scls8mr8l909hl66r7y4ik6sad4ms3vmxbkbb3",
-        "type": "tarball",
-        "url": "https://github.com/NixOS/nixpkgs/archive/6f1ce38d0c0b1b25727d86637fd2f3baf7b0f1f6.tar.gz",
-        "url_template": "https://github.com/<owner>/<repo>/archive/<rev>.tar.gz"
-    }
-}

nix/sources.nix

@@ -1,174 +0,0 @@
-# This file has been generated by Niv.
-
-let
-
-  #
-  # The fetchers. fetch_<type> fetches specs of type <type>.
-  #
-
-  fetch_file = pkgs: name: spec:
-    let
-      name' = sanitizeName name + "-src";
-    in
-      if spec.builtin or true then
-        builtins_fetchurl { inherit (spec) url sha256; name = name'; }
-      else
-        pkgs.fetchurl { inherit (spec) url sha256; name = name'; };
-
-  fetch_tarball = pkgs: name: spec:
-    let
-      name' = sanitizeName name + "-src";
-    in
-      if spec.builtin or true then
-        builtins_fetchTarball { name = name'; inherit (spec) url sha256; }
-      else
-        pkgs.fetchzip { name = name'; inherit (spec) url sha256; };
-
-  fetch_git = name: spec:
-    let
-      ref =
-        if spec ? ref then spec.ref else
-          if spec ? branch then "refs/heads/${spec.branch}" else
-            if spec ? tag then "refs/tags/${spec.tag}" else
-              abort "In git source '${name}': Please specify `ref`, `tag` or `branch`!";
-    in
-      builtins.fetchGit { url = spec.repo; inherit (spec) rev; inherit ref; };
-
-  fetch_local = spec: spec.path;
-
-  fetch_builtin-tarball = name: throw
-    ''[${name}] The niv type "builtin-tarball" is deprecated. You should instead use `builtin = true`.
-        $ niv modify ${name} -a type=tarball -a builtin=true'';
-
-  fetch_builtin-url = name: throw
-    ''[${name}] The niv type "builtin-url" will soon be deprecated. You should instead use `builtin = true`.
-        $ niv modify ${name} -a type=file -a builtin=true'';
-
-  #
-  # Various helpers
-  #
-
-  # https://github.com/NixOS/nixpkgs/pull/83241/files#diff-c6f540a4f3bfa4b0e8b6bafd4cd54e8bR695
-  sanitizeName = name:
-    (
-      concatMapStrings (s: if builtins.isList s then "-" else s)
-        (
-          builtins.split "[^[:alnum:]+._?=-]+"
-            ((x: builtins.elemAt (builtins.match "\\.*(.*)" x) 0) name)
-        )
-    );
-
-  # The set of packages used when specs are fetched using non-builtins.
-  mkPkgs = sources: system:
-    let
-      sourcesNixpkgs =
-        import (builtins_fetchTarball { inherit (sources.nixpkgs) url sha256; }) { inherit system; };
-      hasNixpkgsPath = builtins.any (x: x.prefix == "nixpkgs") builtins.nixPath;
-      hasThisAsNixpkgsPath = <nixpkgs> == ./.;
-    in
-      if builtins.hasAttr "nixpkgs" sources
-      then sourcesNixpkgs
-      else if hasNixpkgsPath && ! hasThisAsNixpkgsPath then
-        import <nixpkgs> {}
-      else
-        abort
-          ''
-            Please specify either <nixpkgs> (through -I or NIX_PATH=nixpkgs=...) or
-            add a package called "nixpkgs" to your sources.json.
-          '';
-
-  # The actual fetching function.
-  fetch = pkgs: name: spec:
-
-    if ! builtins.hasAttr "type" spec then
-      abort "ERROR: niv spec ${name} does not have a 'type' attribute"
-    else if spec.type == "file" then fetch_file pkgs name spec
-    else if spec.type == "tarball" then fetch_tarball pkgs name spec
-    else if spec.type == "git" then fetch_git name spec
-    else if spec.type == "local" then fetch_local spec
-    else if spec.type == "builtin-tarball" then fetch_builtin-tarball name
-    else if spec.type == "builtin-url" then fetch_builtin-url name
-    else
-      abort "ERROR: niv spec ${name} has unknown type ${builtins.toJSON spec.type}";
-
-  # If the environment variable NIV_OVERRIDE_${name} is set, then use
-  # the path directly as opposed to the fetched source.
-  replace = name: drv:
-    let
-      saneName = stringAsChars (c: if isNull (builtins.match "[a-zA-Z0-9]" c) then "_" else c) name;
-      ersatz = builtins.getEnv "NIV_OVERRIDE_${saneName}";
-    in
-      if ersatz == "" then drv else
-        # this turns the string into an actual Nix path (for both absolute and
-        # relative paths)
-        if builtins.substring 0 1 ersatz == "/" then /. + ersatz else /. + builtins.getEnv "PWD" + "/${ersatz}";
-
-  # Ports of functions for older nix versions
-
-  # a Nix version of mapAttrs if the built-in doesn't exist
-  mapAttrs = builtins.mapAttrs or (
-    f: set: with builtins;
-    listToAttrs (map (attr: { name = attr; value = f attr set.${attr}; }) (attrNames set))
-  );
-
-  # https://github.com/NixOS/nixpkgs/blob/0258808f5744ca980b9a1f24fe0b1e6f0fecee9c/lib/lists.nix#L295
-  range = first: last: if first > last then [] else builtins.genList (n: first + n) (last - first + 1);
-
-  # https://github.com/NixOS/nixpkgs/blob/0258808f5744ca980b9a1f24fe0b1e6f0fecee9c/lib/strings.nix#L257
-  stringToCharacters = s: map (p: builtins.substring p 1 s) (range 0 (builtins.stringLength s - 1));
-
-  # https://github.com/NixOS/nixpkgs/blob/0258808f5744ca980b9a1f24fe0b1e6f0fecee9c/lib/strings.nix#L269
-  stringAsChars = f: s: concatStrings (map f (stringToCharacters s));
-  concatMapStrings = f: list: concatStrings (map f list);
-  concatStrings = builtins.concatStringsSep "";
-
-  # https://github.com/NixOS/nixpkgs/blob/8a9f58a375c401b96da862d969f66429def1d118/lib/attrsets.nix#L331
-  optionalAttrs = cond: as: if cond then as else {};
-
-  # fetchTarball version that is compatible between all the versions of Nix
-  builtins_fetchTarball = { url, name ? null, sha256 }@attrs:
-    let
-      inherit (builtins) lessThan nixVersion fetchTarball;
-    in
-      if lessThan nixVersion "1.12" then
-        fetchTarball ({ inherit url; } // (optionalAttrs (!isNull name) { inherit name; }))
-      else
-        fetchTarball attrs;
-
-  # fetchurl version that is compatible between all the versions of Nix
-  builtins_fetchurl = { url, name ? null, sha256 }@attrs:
-    let
-      inherit (builtins) lessThan nixVersion fetchurl;
-    in
-      if lessThan nixVersion "1.12" then
-        fetchurl ({ inherit url; } // (optionalAttrs (!isNull name) { inherit name; }))
-      else
-        fetchurl attrs;
-
-  # Create the final "sources" from the config
-  mkSources = config:
-    mapAttrs (
-      name: spec:
-        if builtins.hasAttr "outPath" spec
-        then abort
-          "The values in sources.json should not have an 'outPath' attribute"
-        else
-          spec // { outPath = replace name (fetch config.pkgs name spec); }
-    ) config.sources;
-
-  # The "config" used by the fetchers
-  mkConfig =
-    { sourcesFile ? if builtins.pathExists ./sources.json then ./sources.json else null
-    , sources ? if isNull sourcesFile then {} else builtins.fromJSON (builtins.readFile sourcesFile)
-    , system ? builtins.currentSystem
-    , pkgs ? mkPkgs sources system
-    }: rec {
-      # The sources, i.e. the attribute set of spec name to spec
-      inherit sources;
-
-      # The "pkgs" (evaluated nixpkgs) to use for e.g. non-builtin fetchers
-      inherit pkgs;
-    };
-
-in
-mkSources (mkConfig {}) // { __functor = _: settings: mkSources (mkConfig settings); }

shell.nix

@@ -1,15 +1,29 @@
-{ sources ? import ./nix/sources.nix, pkgs ? import sources.nixpkgs { } }:
+{ pkgs ? import <nixpkgs> { } }:
 
 with pkgs;
 
-mkShell {
+let
-  buildInputs = [
+  CuReSim = stdenv.mkDerivation rec {
-    R
+    name = "CuReSim";
-    rPackages.immuneSIM
+    version = "1.3";
-    rPackages.Biostrings
+    src = fetchzip { url =
-    jdk
+        "http://www.pegase-biosciences.com/wp-content/uploads/2015/08/${name}${version}.zip";
-    # Develoment tools
+      sha256 = "1hvlpgy4haqgqq52mkxhcl9i1fx67kgwi6f1mijvqzk0xff77hkp";
-    rPackages.languageserver
+      stripRoot = true;
-    rPackages.lintr
+      extraPostFetch = ''
-  ];
+        chmod go-w $out
+      '';
+    };
+
+    nativeBuildInputs = [ makeWrapper ];
+
+    installPhase = ''
+      mkdir -pv $out/share/java $out/bin
+      cp -r ${src} $out/share/java/${name}
+      makeWrapper ${jre}/bin/java $out/bin/CuReSim --add-flags "-jar $out/share/java/${name}/${name}.jar"
+    '';
+  };
+in mkShell {
+  buildInputs =
+    [ R rPackages.immuneSIM rPackages.Biostrings rPackages.stringr CuReSim ];
 }

src/alignment.r

@@ -0,0 +1,153 @@
+library(Biostrings)
+library(parallel)
+
+#' Import and process the TCR and VJ sequences
+#'
+#' @param file A file path with the sequences after applying a read simulator
+#' @return A \code{list} with the TCR sequences and VJ sequences
+parse_data <- function(file) {
+  reversed_sequences <- Biostrings::readQualityScaledDNAStringSet(file)
+  sequences <- Biostrings::reverseComplement(reversed_sequences)
+  vj_segments <- union(
+    readRDS("data/v_segments.rds"),
+    readRDS("data/j_segments_phe.rds")
+  )
+  return(list(sequences, vj_segments))
+}
+
+#' Extracts the VJ metadata from the sequences read identifier
+#'
+#' @param metadata The read identifier of a sequence
+#' @return A \code{list} with the V and J gene identifier
+parse_metadata <- function(metadata) {
+  id_elements <- unlist(strsplit(metadata, split = " "))
+  v_identifier <- id_elements[2]
+  j_identifier <- id_elements[3]
+  return(list(v_id = v_identifier, j_id = j_identifier))
+}
+
+#' Fetches the sequence that matches the VJ gene identifier
+#'
+#' @param names The names of the VJ sequences
+#' @param vdj_segments A \code{DNAStringSet} containing the VJ sequences
+#' @param id The read identifier of a sequence
+#' @return A \code{character} containing the gene sequence
+match_id_sequence <- function(names, vdj_segments, id) {
+  matches <- grep(names, pattern = id)
+  if(id == "TRBJ2-2"){
+    row <- matches[2]
+  } else {
+    row <- matches[1]
+  }
+  return(as.character(vdj_segments[row]))
+}
+
+#' Gets the V and J sequences for a particular read identifier
+#'
+#' @param metadata The read identifier of a sequence
+#' @param names The names of the VJ sequences
+#' @param vdj_segments A \code{DNAStringSet} containing the VJ sequences
+#' @return A \code{list} with the V and J sequences
+get_vj_sequence <- function(metadata, names, vdj_segments) {
+  identifiers <- parse_metadata(metadata)
+  v_sequence <- match_id_sequence(names, vdj_segments, id = identifiers["v_id"])
+  j_sequence <- match_id_sequence(names, vdj_segments, id = identifiers["j_id"])
+  return(list(v_seq = v_sequence, j_seq = j_sequence))
+}
+
+#' Obtains the VJ sequences for all the TCR sequences
+#'
+#' @param sequences A \code{QualityScaledDNAStringSet} with the TCR sequences
+#' @param vdj_segments A \code{DNAStringSet} containing the VJ sequences
+#' @return A \code{data.frame} with the V and J sequences
+fetch_vj_sequences <- function(sequences, vdj_segments) {
+  vj_sequences <- sapply(names(sequences),
+    names(vdj_segments),
+    vdj_segments,
+    FUN = get_vj_sequence
+  )
+  results <- data.frame(t(vj_sequences))
+  return(results)
+}
+
+#' Perform a pairwise alignment of a sequence with the canonical V or J sequence
+#'
+#' @param sequence A \code{DNAString} containing the TCR sequences
+#' @param vdj_segment A \code{DNAString} containing the V or J sequence
+#' @return A \code{PairwiseAlignments}
+align_sequence <- function(sequence, vdj_segment) {
+  return(Biostrings::pairwiseAlignment(
+    subject = sequence,
+    pattern = vdj_segment,
+    type = "global-local",
+    gapOpening = 1
+  ))
+}
+
+#' Computes the coordinate shift of the Cysteine due to indels
+#'
+#' @param insertion An \code{IRanges} containing the insertions
+#' @param deletion An \code{IRanges} containing the deletions
+#' @param cys A \code{list} with the Cysteine coordinates
+#' @param alignment A \code{PairwiseAlignments}
+#' @return A \code{list} with the delta of the Cysteine coordinates
+handle_indels <- function(insertion, deletion, cys, alignment) {
+  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$start + ins_start])) +
+    nchar(stringr::str_extract(alignedSubject(alignment), "^-*"))
+  return(list("start" = ins_start - gaps, "end" = ins_end - gaps))
+}
+
+#' Find the coordinates of the first Cysteine of the HVR
+#'
+#' @param alignment A \code{PairwiseAlignments}
+#' @return A \code{list} with the Cysteine coordinates
+get_cys_coordinates <- function(alignment) {
+  cys <- list("start" = 310, "end" = 312)
+  insertion <- unlist(Biostrings::insertion(alignment))
+  deletion <- unlist(Biostrings::deletion(alignment))
+  delta_coordinates <- handle_indels(insertion, deletion, cys, alignment)
+  read_start <- unlist(start(Biostrings::Views(alignment)))
+  cys_start <- cys$start + delta_coordinates$start + read_start - 1
+  cys_end <- cys$end + delta_coordinates$end + read_start
+  return(list("start" = cys_start, "end" = cys_end))
+}
+
+#' Delimit the hypervariable region (HVR) for each TCR sequence
+#'
+#' @param sequences A \code{QualityScaledDNAStringSet} with the TCR sequences
+#' @param vdj_segments A \code{DNAStringSet} containing the VJ sequences
+#' @param cores Number of cores to apply multiprocessing
+#' @return A \code{QualityScaledDNAStringSet} containing the HVR
+get_hvr_sequences <- function(sequences, vdj_segments, cores = detectCores()) {
+  df <- fetch_vj_sequences(sequences, vdj_segments)
+  v_alignment <- parallel::mcmapply(sequences,
+    df$v_seq,
+    FUN = align_sequence,
+    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$end) + 1)
+  j_alignment <- parallel::mcmapply(remaining,
+    df$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 <- get_hvr_sequences(sequences = data[[1]], vdj_segments = data[[2]])
+Biostrings::writeXStringSet(hvr, "data/curesim-HVR.fastq", format = "fastq")

src/repertoire.r

@@ -1,55 +1,57 @@
 library(immuneSIM)
 library(Biostrings)
 
-generate_repertoires <- function(number_of_sequences) {
+#' Generate the beta chain of a human T-cell receptor (TCR)
-  a_chain <- immuneSIM(
+#'
+#' @param number_of_sequences Number of different sequences to generate
+#' @return A \code{data.frame} with the sequences, V and J genes and CDR3
+generate_repertoire <- function(number_of_sequences) {
+  return(immuneSIM(
     number_of_seqs = number_of_sequences,
     species = "hs",
     receptor = "tr",
-    chain = "a",
+    chain = "b"
-    verbose = TRUE
+  ))
+}
+
+#' Saves the sequences and CDR3 to FASTQ files
+#'
+#' @param data A \code{data.frame} with the preprocessed TCR sequences and CDR3
+save_data <- function(data) {
+  Biostrings::writeXStringSet(data$sequence,
+    "data/sequence.fastq",
+    format = "fastq"
   )
-  b_chain <- immuneSIM(
+  Biostrings::writeXStringSet(data$junction, "data/HVR.fastq", format = "fastq")
-    number_of_seqs = number_of_sequences,
-    species = "hs",
-    receptor = "tr",
-    chain = "b",
-    verbose = TRUE
-  )
-  return(list("a_chain" = a_chain, "b_chain" = b_chain))
 }
 
-process_chain <- function(repertoire) {
+#' Applies the reverse complement and amplifies the number of sequences
-  sequences <- as.character(repertoire$sequence)
+#'
-  counts <- as.integer(repertoire$counts)
+#' @param data A \code{data.frame} containing the TCR sequences and CDR3
-  reads <- Biostrings::DNAStringSet(rep(sequences, counts))
+#' @param reads Number of times to amplify each sequence
-  names(reads) <- seq_len(length(reads))
+#' @return A \code{data.frame} with reverse complement sequences and VJ metadata
-  reverse_complement <- Biostrings::reverseComplement(reads)
+process_data <- function(data, reads) {
-  return(reverse_complement)
+  dna_sequence <- Biostrings::DNAStringSet(data$sequence)
+  data$sequence <- Biostrings::reverseComplement(dna_sequence)
+  names(data$sequence) <- paste(rownames(data), data$v_call, data$j_call, " ")
+  data$junction <- Biostrings::DNAStringSet(data$junction)
+  names(data$junction) <- rownames(data)
+  amplified_data <- data[rep(seq_len(nrow(data)), reads), ]
+  return(amplified_data)
 }
 
-preprocess_data <- function(repertoires) {
+#' Checks the number of command line arguments and captures them
-  filtered_repertoires <- lapply(repertoires, process_chain)
+#'
-  names(filtered_repertoires) <- names(repertoires)
+#' @return A \code{vector} containing the command line arguments
-  return(filtered_repertoires)
+parse_cli_arguments <- function() {
-}
+  args <- commandArgs(trailingOnly = TRUE)
-
+  if (length(args) != 2) {
-save_data <- function(repertoires) {
+    stop("usage: repertoire.r <number of sequences> <number of reads>")
-  for (chain in names(repertoires)) {
-    file_name <- paste("data/", chain, ".fastq", sep = "")
-    Biostrings::writeXStringSet(repertoires[[chain]], file_name, format = "fastq")
   }
+  return(args)
 }
 
-parse_cli_arguments <- function(args) {
+args <- parse_cli_arguments()
-  if (length(args) != 1) {
+repertoire <- generate_repertoire(number_of_sequences = as.integer(args[1]))
-    stop("usage: repertoire.r <number of sequences>")
+data <- process_data(data = repertoire, reads = args[2])
-  }
+save_data(data)
-  return(as.integer(args[1]))
-}
-
-args <- commandArgs(trailingOnly = TRUE)
-number_of_sequences <- parse_cli_arguments(args)
-sim_repertoire <- generate_repertoires(number_of_sequences)
-processed_data <- preprocess_data(sim_repertoire)
-save_data(processed_data)