diff options
Diffstat (limited to 'gnu/packages/bioinformatics.scm')
| -rw-r--r-- | gnu/packages/bioinformatics.scm | 116 |
1 files changed, 114 insertions, 2 deletions
diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm index 4dd2ee6f92..281bd1f427 100644 --- a/gnu/packages/bioinformatics.scm +++ b/gnu/packages/bioinformatics.scm @@ -579,10 +579,11 @@ confidence to have in an alignment.") (snippet `(begin ;; Remove bundled boost, pigz, zlib, and .git directory - ;; FIXME: also remove bundled sources for google-sparsehash, - ;; murmurhash3, kmc once packaged. + ;; FIXME: also remove bundled sources for murmurhash3 and + ;; kmc once packaged. (delete-file-recursively "boost") (delete-file-recursively "pigz") + (delete-file-recursively "google-sparsehash") (delete-file-recursively "zlib") (delete-file-recursively ".git") #t)))) @@ -632,6 +633,7 @@ confidence to have in an alignment.") (inputs `(("openmpi" ,openmpi) ("boost" ,boost) + ("sparsehash" ,sparsehash) ("pigz" ,pigz) ("zlib" ,zlib))) (supported-systems '("x86_64-linux")) @@ -919,6 +921,54 @@ also includes an interface for tabix.") (define-public python2-pysam (package-with-python2 python-pysam)) +(define-public cd-hit + (package + (name "cd-hit") + (version "4.6.5") + (source (origin + (method url-fetch) + (uri (string-append "https://github.com/weizhongli/cdhit" + "/releases/download/V" version + "/cd-hit-v" version "-2016-0304.tar.gz")) + (sha256 + (base32 + "15db0hq38yyifwqx9b6l34z14jcq576dmjavhj8a426c18lvnhp3")))) + (build-system gnu-build-system) + (arguments + `(#:tests? #f ; there are no tests + #:make-flags + ;; Executables are copied directly to the PREFIX. + (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin")) + #:phases + (modify-phases %standard-phases + ;; No "configure" script + (delete 'configure) + ;; Remove sources of non-determinism + (add-after 'unpack 'be-timeless + (lambda _ + (substitute* "cdhit-utility.c++" + ((" \\(built on \" __DATE__ \"\\)") "")) + (substitute* "cdhit-common.c++" + (("__DATE__") "\"0\"") + (("\", %s, \" __TIME__ \"\\\\n\", date") "")) + #t)) + ;; The "install" target does not create the target directory + (add-before 'install 'create-target-dir + (lambda* (#:key outputs #:allow-other-keys) + (mkdir-p (string-append (assoc-ref outputs "out") "/bin")) + #t))))) + (inputs + `(("perl" ,perl))) + (home-page "http://weizhongli-lab.org/cd-hit/") + (synopsis "Cluster and compare protein or nucleotide sequences") + (description + "CD-HIT is a program for clustering and comparing protein or nucleotide +sequences. CD-HIT is designed to be fast and handle extremely large +databases.") + ;; The manual says: "It can be copied under the GNU General Public License + ;; version 2 (GPLv2)." + (license license:gpl2))) + (define-public clipper (package (name "clipper") @@ -958,6 +1008,46 @@ also includes an interface for tabix.") "CLIPper is a tool to define peaks in CLIP-seq datasets.") (license license:gpl2))) +(define-public codingquarry + (package + (name "codingquarry") + (version "2.0") + (source (origin + (method url-fetch) + (uri (string-append + "mirror://sourceforge/codingquarry/CodingQuarry_v" + version ".tar.gz")) + (sha256 + (base32 + "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i")))) + (build-system gnu-build-system) + (arguments + '(#:tests? #f ; no "check" target + #: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")) + (doc (string-append out "/share/doc/codingquarry"))) + (install-file "INSTRUCTIONS.pdf" doc) + (copy-recursively "QuarryFiles" + (string-append out "/QuarryFiles")) + (install-file "CodingQuarry" bin) + (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))))))) + (inputs `(("openmpi" ,openmpi))) + (native-search-paths + (list (search-path-specification + (variable "QUARRY_PATH") + (files '("QuarryFiles"))))) + (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported + (synopsis "Fungal gene predictor") + (description "CodingQuarry is a highly accurate, self-training GHMM fungal +gene predictor designed to work with assembled, aligned RNA-seq transcripts.") + (home-page "https://sourceforge.net/projects/codingquarry/") + (license license:gpl3+))) + (define-public couger (package (name "couger") @@ -3847,6 +3937,28 @@ barplots or heatmaps.") packages.") (license license:artistic2.0))) +(define-public r-dnacopy + (package + (name "r-dnacopy") + (version "1.44.0") + (source (origin + (method url-fetch) + (uri (bioconductor-uri "DNAcopy" version)) + (sha256 + (base32 + "1c1px4rbr36xx929hp59k7ca9k5ab66qmn8k63fk13278ncm6h66")))) + (properties + `((upstream-name . "DNAcopy"))) + (build-system r-build-system) + (inputs + `(("gfortran" ,gfortran))) + (home-page "https://bioconductor.org/packages/DNAcopy") + (synopsis "Implementation of a circular binary segmentation algorithm") + (description "This package implements the circular binary segmentation (CBS) +algorithm to segment DNA copy number data and identify genomic regions with +abnormal copy number.") + (license license:gpl2+))) + (define-public r-s4vectors (package (name "r-s4vectors") |