Bump nixpkgs revision

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

@@ -1,56 +0,0 @@
-* 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
-
-- [[https://github.com/GreiffLab/immuneSIM/][immuneSIM]]: in silico generation of human and mouse BCR and TCR repertoires
-- [[http://www.pegase-biosciences.com/curesim-a-customized-read-simulator/][CuReSim]]: read simulator that mimics Ion Torrent sequencing
-
-** 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 |

nix/sources.json

@@ -17,10 +17,10 @@
         "homepage": "",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "a565a2165ab6e195d7c105a8416b8f4b4d0349a4",
+        "rev": "359e6542e1d41eb18df55c82bdb08bf738fae2cf",
-        "sha256": "1x90qm533lh8xh172rqfcj3pwg8imyx650xgr41rqppmm6fli4w1",
+        "sha256": "05v28njaas9l26ibc6vy6imvy7grbkli32bmv0n32x6x9cf68gf9",
         "type": "tarball",
-        "url": "https://github.com/NixOS/nixpkgs/archive/a565a2165ab6e195d7c105a8416b8f4b4d0349a4.tar.gz",
+        "url": "https://github.com/NixOS/nixpkgs/archive/359e6542e1d41eb18df55c82bdb08bf738fae2cf.tar.gz",
         "url_template": "https://github.com/<owner>/<repo>/archive/<rev>.tar.gz"
     }
 }

src/alignment.r

@@ -34,7 +34,11 @@ parse_metadata <- function(metadata) {
 #' @return A \code{character} containing the gene sequence
 match_id_sequence <- function(names, vdj_segments, id) {
   matches <- grep(names, pattern = id)
-  row <- matches[1]
+  if(id == "TRBJ2-2"){
+    row <- matches[2]
+  } else {
+    row <- matches[1]
+  }
   return(as.character(vdj_segments[row]))
 }
 
@@ -106,8 +110,9 @@ get_cys_coordinates <- function(alignment) {
   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
+  read_start <- unlist(start(Biostrings::Views(alignment)))
-  cys_end <- cys$end + delta_coordinates$end
+  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))
 }
 
@@ -126,7 +131,7 @@ get_hvr_sequences <- function(sequences, vdj_segments, cores = detectCores()) {
   )
   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$end))
+  remaining <- Biostrings::subseq(sequences, start = unlist(cys_df$end) + 1)
   j_alignment <- parallel::mcmapply(remaining,
     df$j_seq,
     FUN = align_sequence,
@@ -145,4 +150,4 @@ get_hvr_sequences <- function(sequences, vdj_segments, cores = detectCores()) {
 
 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")
+Biostrings::writeXStringSet(hvr, "data/curesim-HVR.fastq", format = "fastq")