From 53131eab2d97a5a2ce43b6f0c7fe47536dbcca84 Mon Sep 17 00:00:00 2001 From: Ricardo Wurmus Date: Thu, 14 Jun 2018 13:50:21 +0200 Subject: gnu: Add minimap2. * gnu/packages/bioinformatics.scm (minimap2): New variable. --- gnu/packages/bioinformatics.scm | 59 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) (limited to 'gnu/packages') diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm index 56fae09d93..a210319243 100644 --- a/gnu/packages/bioinformatics.scm +++ b/gnu/packages/bioinformatics.scm @@ -13247,3 +13247,62 @@ (define-public sjcount junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This version does count multisplits.") (license license:gpl3+)))) + +(define-public minimap2 + (package + (name "minimap2") + (version "2.10") + (source + (origin + (method url-fetch) + (uri (string-append "https://github.com/lh3/minimap2/" + "releases/download/v" version "/" + "minimap2-" version ".tar.bz2")) + (sha256 + (base32 + "080w9066irkbhbyr4nmf19pzkdd2s4v31hpzlajgq2y0drr6zcsj")))) + (build-system gnu-build-system) + (arguments + `(#:tests? #f ; there are none + #:make-flags + (list "CC=gcc" + (let ((system ,(or (%current-target-system) + (%current-system)))) + (cond + ((string-prefix? "x86_64" system) + "all") + ((or (string-prefix? "armhf" system) + (string-prefix? "aarch64" system)) + "arm_neon=1") + (_ "sse2only=1")))) + #:phases + (modify-phases %standard-phases + (delete 'configure) + (replace 'install + (lambda* (#:key outputs #:allow-other-keys) + (let* ((out (assoc-ref outputs "out")) + (bin (string-append out "/bin")) + (man (string-append out "/share/man/man1"))) + (install-file "minimap2" bin) + (mkdir-p man) + (install-file "minimap2.1" man)) + #t))))) + (inputs + `(("zlib" ,zlib))) + (home-page "https://lh3.github.io/minimap2/") + (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences") + (description "Minimap2 is a versatile sequence alignment program that +aligns DNA or mRNA sequences against a large reference database. Typical use +cases include: + +@enumerate +@item mapping PacBio or Oxford Nanopore genomic reads to the human genome; +@item finding overlaps between long reads with error rate up to ~15%; +@item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA + reads against a reference genome; +@item aligning Illumina single- or paired-end reads; +@item assembly-to-assembly alignment; +@item full-genome alignment between two closely related species with + divergence below ~15%. +@end enumerate\n") + (license license:expat))) -- cgit v1.2.3