From 95da30390282c778bcd8058d0ddbaaaec22da1bb Mon Sep 17 00:00:00 2001 From: Alexis Praga Date: Tue, 9 Aug 2022 15:16:46 +0200 Subject: [PATCH] gatk : init at 4.2.6.1 GATK is the industry standard for genetics analysis, more precisely for identifying SNPs and indels in germline DNA and RNAseq data . This package does not ship the Spark version. Apply suggestions from code review Co-authored-by: Sandro --- maintainers/maintainer-list.nix | 6 +++ .../science/biology/gatk/default.nix | 38 +++++++++++++++++++ pkgs/top-level/all-packages.nix | 2 + 3 files changed, 46 insertions(+) create mode 100644 pkgs/applications/science/biology/gatk/default.nix diff --git a/maintainers/maintainer-list.nix b/maintainers/maintainer-list.nix index ea6c70d8c6db..599c8e450157 100644 --- a/maintainers/maintainer-list.nix +++ b/maintainers/maintainer-list.nix @@ -983,6 +983,12 @@ fingerprint = "BF8B F725 DA30 E53E 7F11 4ED8 AAA5 0652 F047 9205"; }]; }; + apraga = { + email = "alexis.praga@proton.me"; + github = "apraga"; + githubId = 914687; + name = "Alexis Praga"; + }; ar1a = { email = "aria@ar1as.space"; github = "ar1a"; diff --git a/pkgs/applications/science/biology/gatk/default.nix b/pkgs/applications/science/biology/gatk/default.nix new file mode 100644 index 000000000000..c0818b8336df --- /dev/null +++ b/pkgs/applications/science/biology/gatk/default.nix @@ -0,0 +1,38 @@ +{ lib, stdenv, fetchzip }: + +stdenv.mkDerivation rec { + pname = "gatk"; + version = "4.2.6.1"; + src = fetchzip { + url = "https://github.com/broadinstitute/gatk/releases/download/${version}/gatk-${version}.zip"; + sha256 = "0hjlsl7fxf3ankyjidqhwxc70gjh6z4lnjzw6b5fldzb0qvgfvy8"; + }; + + installPhase = '' + mkdir -p $out/bin + install -m755 -D $src/gatk $out/bin/ + install -m755 -D $src/gatk-package-${version}-local.jar $out/bin/ + ''; + + meta = with lib; { + homepage = "https://gatk.broadinstitute.org/hc/en-us"; + description = "A wide variety of tools with a primary focus on variant discovery and genotyping." ; + license = licenses.asl20; + sourceProvenance = with lib.sourceTypes; [ binaryBytecode ] ; + maintainers = with maintainers; [ apraga ]; + longDescription = '' + The GATK is the industry standard for identifying SNPs and indels in germline + DNA and RNAseq data. Its scope is now expanding to include somatic short variant + calling, and to tackle copy number (CNV) and structural variation (SV). In + addition to the variant callers themselves, the GATK also includes many + utilities to perform related tasks such as processing and quality control of + high-throughput sequencing data, and bundles the popular Picard toolkit. + + These tools were primarily designed to process exomes and whole genomes + generated with Illumina sequencing technology, but they can be adapted to handle + a variety of other technologies and experimental designs. And although it was + originally developed for human genetics, the GATK has since evolved to handle + genome data from any organism, with any level of ploidy. + ''; + }; +} diff --git a/pkgs/top-level/all-packages.nix b/pkgs/top-level/all-packages.nix index db628a413506..4dffc6d9e8f2 100644 --- a/pkgs/top-level/all-packages.nix +++ b/pkgs/top-level/all-packages.nix @@ -6460,6 +6460,8 @@ with pkgs; gawkInteractive = gawk.override { interactive = true; }; + gatk = callPackage ../applications/science/biology/gatk {} ; + gbdfed = callPackage ../tools/misc/gbdfed { gtk = gtk2-x11; };