From c5173d74d67b786c36dd53930c5d4fe4805cf3e9 Mon Sep 17 00:00:00 2001
From: Roel Janssen <roel@gnu.org>
Date: Thu, 12 Jan 2017 10:02:57 +0100
Subject: gnu: Add r-txdb-mmusculus-ucsc-mm10-knowngene.

* gnu/packages/bioinformatics.scm (r-txdb-mmusculus-ucsc-mm10-knowngene): New variable.
---
 gnu/packages/bioinformatics.scm | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 14daf59c92..d82b6c093c 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -7100,6 +7100,41 @@ (define-public r-bsgenome-mmusculus-ucsc-mm10
 in Biostrings objects.")
     (license license:artistic2.0)))
 
+(define-public r-txdb-mmusculus-ucsc-mm10-knowngene
+  (package
+    (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
+    (version "3.4.0")
+    (source (origin
+              (method url-fetch)
+              ;; We cannot use bioconductor-uri here because this tarball is
+              ;; located under "data/annotation/" instead of "bioc/".
+              (uri (string-append "http://www.bioconductor.org/packages/"
+                                  "release/data/annotation/src/contrib/"
+                                  "TxDb.Mmusculus.UCSC.mm10.knownGene_"
+                                  version ".tar.gz"))
+              (sha256
+               (base32
+                "08gava9wsvpcqz51k2sni3pj03n5155v32d9riqbf305nbirqbkb"))))
+    (properties
+     `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
+    (build-system r-build-system)
+    ;; As this package provides little more than a very large data file it
+    ;; doesn't make sense to build substitutes.
+    (arguments `(#:substitutable? #f))
+    (propagated-inputs
+     `(("r-bsgenome" ,r-bsgenome)
+       ("r-genomicfeatures" ,r-genomicfeatures)
+       ("r-annotationdbi" ,r-annotationdbi)))
+    (home-page
+     "http://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
+    (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
+    (description
+     "This package loads a TxDb object, which is an R interface to
+prefabricated databases contained in this package.  This package provides
+the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
+based on the knownGene track.")
+    (license license:artistic2.0)))
+
 (define-public r-bsgenome-celegans-ucsc-ce6
   (package
     (name "r-bsgenome-celegans-ucsc-ce6")
-- 
cgit v1.2.3


From dd42a330d1301fd34f36dada9d142006165abaef Mon Sep 17 00:00:00 2001
From: Raoul Jean Pierre Bonnal <ilpuccio.febo@gmail.com>
Date: Fri, 13 Jan 2017 20:38:25 +0100
Subject: gnu: Add r-sva.

* gnu/packages/bioinformatics.scm (r-sva): New variable.
---
 gnu/packages/bioinformatics.scm | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index d82b6c093c..4b9cd22f86 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -7995,3 +7995,29 @@ (define-public r-copywriter
 CopywriteR constitutes a widely applicable alternative to available copy
 number detection tools.")
     (license license:gpl2)))
+
+(define-public r-sva
+  (package
+    (name "r-sva")
+    (version "3.22.0")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (bioconductor-uri "sva" version))
+       (sha256
+        (base32
+         "1wc1fjm6dzlsqqagm43y57w8jh8nsh0r0m8z1p6ximcb5gxqh7hn"))))
+    (build-system r-build-system)
+    (propagated-inputs
+     `(("r-genefilter" ,r-genefilter)))
+    (home-page "http://bioconductor.org/packages/sva")
+    (synopsis "Surrogate variable analysis")
+    (description
+     "This package contains functions for removing batch effects and other
+unwanted variation in high-throughput experiment.  It also contains functions
+for identifying and building surrogate variables for high-dimensional data
+sets.  Surrogate variables are covariates constructed directly from
+high-dimensional data like gene expression/RNA sequencing/methylation/brain
+imaging data that can be used in subsequent analyses to adjust for unknown,
+unmodeled, or latent sources of noise.")
+    (license license:artistic2.0)))
-- 
cgit v1.2.3


From b91cfa22e1b9f3e5d3a62ee65ee71a6e708b9b53 Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <rekado@elephly.net>
Date: Mon, 16 Jan 2017 23:14:13 +0100
Subject: gnu: Add r-centipede.

* gnu/packages/bioinformatics.scm (r-centipede): New variable.
---
 gnu/packages/bioinformatics.scm | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 4b9cd22f86..b14b7d4caf 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -5159,6 +5159,30 @@ (define-public infernal
     (supported-systems '("i686-linux" "x86_64-linux"))
     (license license:bsd-3)))
 
+(define-public r-centipede
+  (package
+    (name "r-centipede")
+    (version "1.2")
+    (source (origin
+              (method url-fetch)
+              (uri (string-append "http://download.r-forge.r-project.org/"
+                                  "src/contrib/CENTIPEDE_" version ".tar.gz"))
+              (sha256
+               (base32
+                "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
+    (build-system r-build-system)
+    (home-page "http://centipede.uchicago.edu/")
+    (synopsis "Predict transcription factor binding sites")
+    (description
+     "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
+of the genome that are bound by particular transcription factors.  It starts
+by identifying a set of candidate binding sites, and then aims to classify the
+sites according to whether each site is bound or not bound by a transcription
+factor.  CENTIPEDE is an unsupervised learning algorithm that discriminates
+between two different types of motif instances using as much relevant
+information as possible.")
+    (license (list license:gpl2+ license:gpl3+))))
+
 (define-public r-vegan
   (package
     (name "r-vegan")
-- 
cgit v1.2.3


From e84efc50d7156706fbf6fc86065371b67f929289 Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <rekado@elephly.net>
Date: Mon, 16 Jan 2017 11:49:32 +0100
Subject: gnu: Add hisat2.

* gnu/packages/bioinformatics.scm (hisat2): New variable.
---
 gnu/packages/bioinformatics.scm | 63 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index b14b7d4caf..b3aedec63f 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -2722,6 +2722,69 @@ (define-public hisat
 particular, reads spanning multiple exons.")
     (license license:gpl3+)))
 
+(define-public hisat2
+  (package
+    (name "hisat2")
+    (version "2.0.5")
+    (source
+     (origin
+       (method url-fetch)
+       ;; FIXME: a better source URL is
+       ;; (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
+       ;;                "/downloads/hisat2-" version "-source.zip")
+       ;; with hash "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"
+       ;; but it is currently unavailable.
+       (uri "https://github.com/infphilo/hisat2/archive/cba6e8cb.tar.gz")
+       (file-name (string-append name "-" version ".tar.gz"))
+       (sha256
+        (base32
+         "1mf2hdsyv7cd97xm9mp9a4qws02yrj95y6w6f6cdwnq0klp81r50"))))
+    (build-system gnu-build-system)
+    (arguments
+     `(#:tests? #f                      ; no check target
+       #:make-flags (list "CC=gcc" "CXX=g++" "allall")
+       #:modules ((guix build gnu-build-system)
+                  (guix build utils)
+                  (srfi srfi-26))
+       #:phases
+       (modify-phases %standard-phases
+         (add-after 'unpack 'make-deterministic
+           (lambda _
+             (substitute* "Makefile"
+               (("`date`") "0"))
+             #t))
+         (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/hisat2/")))
+               (for-each
+                (cut install-file <> bin)
+                (find-files "."
+                            "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
+               (mkdir-p doc)
+               (install-file "doc/manual.inc.html" doc))
+             #t)))))
+    (native-inputs
+     `(("unzip" ,unzip)                 ; needed for archive from ftp
+       ("perl" ,perl)
+       ("pandoc" ,ghc-pandoc)))         ; for documentation
+    (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
+    (synopsis "Graph-based alignment of genomic sequencing reads")
+    (description "HISAT2 is a fast and sensitive alignment program for mapping
+next-generation sequencing reads (both DNA and RNA) to a population of human
+genomes (as well as to a single reference genome).  In addition to using one
+global @dfn{graph FM} (GFM) index that represents a population of human
+genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
+the whole genome.  These small indexes, combined with several alignment
+strategies, enable rapid and accurate alignment of sequencing reads.  This new
+indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
+    ;; HISAT2 contains files from Bowtie2, which is released under
+    ;; GPLv2 or later.  The HISAT2 source files are released under
+    ;; GPLv3 or later.
+    (license license:gpl3+)))
+
 (define-public hmmer
   (package
     (name "hmmer")
-- 
cgit v1.2.3


From 769fc6bb18d311bafa47e9666d35db2cb594e8ab Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <rekado@elephly.net>
Date: Mon, 16 Jan 2017 11:56:00 +0100
Subject: gnu: Add ribodiff.

* gnu/packages/bioinformatics.scm (ribodiff): New variable.
---
 gnu/packages/bioinformatics.scm | 41 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index b3aedec63f..cd64d34390 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -468,6 +468,47 @@ (define-public ribotaper
 provides the Ribotaper pipeline.")
     (license license:gpl3+)))
 
+(define-public ribodiff
+  (package
+    (name "ribodiff")
+    (version "0.2.2")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (string-append "https://github.com/ratschlab/RiboDiff/"
+                           "archive/v" version ".tar.gz"))
+       (file-name (string-append name "-" version ".tar.gz"))
+       (sha256
+        (base32
+         "0wpbwmfv05wdjxv7ikm664f7s7p7cqr8jnw99zrda0q67rl50aaj"))))
+    (build-system python-build-system)
+    (arguments
+     `(#:python ,python-2
+       #:phases
+       (modify-phases %standard-phases
+         ;; Generate an installable executable script wrapper.
+         (add-after 'unpack 'patch-setup.py
+           (lambda _
+             (substitute* "setup.py"
+               (("^(.*)packages=.*" line prefix)
+                (string-append line "\n"
+                               prefix "scripts=['scripts/TE.py'],\n")))
+             #t)))))
+    (inputs
+     `(("python-numpy" ,python2-numpy)
+       ("python-matplotlib" ,python2-matplotlib)
+       ("python-scipy" ,python2-scipy)
+       ("python-statsmodels" ,python2-statsmodels)))
+    (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
+    (synopsis "Detect translation efficiency changes from ribosome footprints")
+    (description "RiboDiff is a statistical tool that detects the protein
+translational efficiency change from Ribo-Seq (ribosome footprinting) and
+RNA-Seq data.  It uses a generalized linear model to detect genes showing
+difference in translational profile taking mRNA abundance into account.  It
+facilitates us to decipher the translational regulation that behave
+independently with transcriptional regulation.")
+    (license license:gpl3+)))
+
 (define-public bioawk
   (package
     (name "bioawk")
-- 
cgit v1.2.3


From fb1e528ef1edca46ba4152b88356266944982ebe Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <rekado@elephly.net>
Date: Mon, 16 Jan 2017 11:59:24 +0100
Subject: gnu: Add r-seqminer.

* gnu/packages/bioinformatics.scm (r-seqminer): New variable.
---
 gnu/packages/bioinformatics.scm | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index cd64d34390..28a0da80e8 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -8149,3 +8149,25 @@ (define-public r-sva
 imaging data that can be used in subsequent analyses to adjust for unknown,
 unmodeled, or latent sources of noise.")
     (license license:artistic2.0)))
+
+(define-public r-seqminer
+  (package
+    (name "r-seqminer")
+    (version "5.3")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (cran-uri "seqminer" version))
+       (sha256
+        (base32
+         "0y0gc5lws3hdxasjb84m532ics6imb7qg9sl1zy62h503jh4j9gw"))))
+    (build-system r-build-system)
+    (inputs
+     `(("zlib" ,zlib)))
+    (home-page "http://seqminer.genomic.codes")
+    (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
+    (description
+     "This package provides tools to integrate nucleotide sequencing
+data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
+    ;; Any version of the GPL is acceptable
+    (license (list license:gpl2+ license:gpl3+))))
-- 
cgit v1.2.3


From 1f40e73cb52293d0ff429703136235398129887f Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <rekado@elephly.net>
Date: Mon, 16 Jan 2017 11:59:41 +0100
Subject: gnu: Add r-raremetals2.

* gnu/packages/bioinformatics.scm (r-raremetals2): New variable.
---
 gnu/packages/bioinformatics.scm | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 28a0da80e8..743e8fdce9 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -8171,3 +8171,34 @@ (define-public r-seqminer
 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
     ;; Any version of the GPL is acceptable
     (license (list license:gpl2+ license:gpl3+))))
+
+(define-public r-raremetals2
+  (package
+    (name "r-raremetals2")
+    (version "0.1")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (string-append "http://genome.sph.umich.edu/w/images/"
+                           "b/b7/RareMETALS2_" version ".tar.gz"))
+       (sha256
+        (base32
+         "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
+    (properties `((upstream-name . "RareMETALS2")))
+    (build-system r-build-system)
+    (propagated-inputs
+     `(("r-seqminer" ,r-seqminer)
+       ("r-mvtnorm" ,r-mvtnorm)
+       ("r-compquadform" ,r-compquadform)
+       ("r-getopt" ,r-getopt)))
+    (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
+    (synopsis "Analyze gene-level association tests for binary trait")
+    (description
+     "The R package rareMETALS2 is an extension of the R package rareMETALS.
+It was designed to meta-analyze gene-level association tests for binary trait.
+While rareMETALS offers a near-complete solution for meta-analysis of
+gene-level tests for quantitative trait, it does not offer the optimal
+solution for binary trait.  The package rareMETALS2 offers improved features
+for analyzing gene-level association tests in meta-analyses for binary
+trait.")
+    (license license:gpl3)))
-- 
cgit v1.2.3


From 0e7d058e4482d8653778915d2ae4941f0ba20a67 Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <rekado@elephly.net>
Date: Mon, 16 Jan 2017 12:01:20 +0100
Subject: gnu: Add r-maldiquant.

* gnu/packages/bioinformatics.scm (r-maldiquant): New variable.
---
 gnu/packages/bioinformatics.scm | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 743e8fdce9..74948ec556 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -8202,3 +8202,29 @@ (define-public r-raremetals2
 for analyzing gene-level association tests in meta-analyses for binary
 trait.")
     (license license:gpl3)))
+
+(define-public r-maldiquant
+  (package
+    (name "r-maldiquant")
+    (version "1.16")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (cran-uri "MALDIquant" version))
+       (sha256
+        (base32
+         "067xbmy10mpsvmv77g62chd7wwhdhcfn5hmp5fisbnz2h5rq0q60"))))
+    (properties `((upstream-name . "MALDIquant")))
+    (build-system r-build-system)
+    (home-page "http://cran.r-project.org/web/packages/MALDIquant")
+    (synopsis "Quantitative analysis of mass spectrometry data")
+    (description
+     "This package provides a complete analysis pipeline for matrix-assisted
+laser desorption/ionization-time-of-flight (MALDI-TOF) and other
+two-dimensional mass spectrometry data.  In addition to commonly used plotting
+and processing methods it includes distinctive features, namely baseline
+subtraction methods such as morphological filters (TopHat) or the
+statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
+alignment using warping functions, handling of replicated measurements as well
+as allowing spectra with different resolutions.")
+    (license license:gpl3+)))
-- 
cgit v1.2.3


From ae2621743010ae498dbafa0a0e8b3b21f5826130 Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <rekado@elephly.net>
Date: Mon, 16 Jan 2017 12:02:18 +0100
Subject: gnu: Add r-protgenerics.

* gnu/packages/bioinformatics.scm (r-protgenerics): New variable.
---
 gnu/packages/bioinformatics.scm | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 74948ec556..4a1bd01965 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -8228,3 +8228,23 @@ (define-public r-maldiquant
 alignment using warping functions, handling of replicated measurements as well
 as allowing spectra with different resolutions.")
     (license license:gpl3+)))
+
+(define-public r-protgenerics
+  (package
+    (name "r-protgenerics")
+    (version "1.6.0")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (bioconductor-uri "ProtGenerics" version))
+       (sha256
+        (base32
+         "0hb3vrrvfx6lcfalmjxm8dmigfmi5nba0pzjfgsrzd35c8mbfc6f"))))
+    (properties `((upstream-name . "ProtGenerics")))
+    (build-system r-build-system)
+    (home-page "https://github.com/lgatto/ProtGenerics")
+    (synopsis "S4 generic functions for proteomics infrastructure")
+    (description
+     "This package provides S4 generic functions needed by Bioconductor
+proteomics packages.")
+    (license license:artistic2.0)))
-- 
cgit v1.2.3


From 71676a1f4c8d14239936c07113c5cd2a37770aa0 Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <rekado@elephly.net>
Date: Mon, 16 Jan 2017 12:18:12 +0100
Subject: gnu: Add r-mzr.

* gnu/packages/bioinformatics.scm (r-mzr): New variable.
---
 gnu/packages/bioinformatics.scm | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 4a1bd01965..51660026eb 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -8248,3 +8248,35 @@ (define-public r-protgenerics
      "This package provides S4 generic functions needed by Bioconductor
 proteomics packages.")
     (license license:artistic2.0)))
+
+(define-public r-mzr
+  (package
+    (name "r-mzr")
+    (version "2.8.1")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (bioconductor-uri "mzR" version))
+       (sha256
+        (base32
+         "0ipmhg6l3pf648rdx5g2ha7l5ppd3cja6afxhdw76x8ga3633x0r"))))
+    (properties `((upstream-name . "mzR")))
+    (build-system r-build-system)
+    (inputs
+     `(("netcdf" ,netcdf)))
+    (propagated-inputs
+     `(("r-biobase" ,r-biobase)
+       ("r-biocgenerics" ,r-biocgenerics)
+       ("r-protgenerics" ,r-protgenerics)
+       ("r-rcpp" ,r-rcpp)
+       ("r-zlibbioc" ,r-zlibbioc)))
+    (home-page "https://github.com/sneumann/mzR/")
+    (synopsis "Parser for mass spectrometry data files")
+    (description
+     "The mzR package provides a unified API to the common file formats and
+parsers available for mass spectrometry data.  It comes with a wrapper for the
+ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
+The package contains the original code written by the ISB, and a subset of the
+proteowizard library for mzML and mzIdentML.  The netCDF reading code has
+previously been used in XCMS.")
+    (license license:artistic2.0)))
-- 
cgit v1.2.3


From 5c9d15055f501868a72148619b5a6db7debd20b8 Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <rekado@elephly.net>
Date: Mon, 16 Jan 2017 12:18:30 +0100
Subject: gnu: Add r-affyio.

* gnu/packages/bioinformatics.scm (r-affyio): New variable.
---
 gnu/packages/bioinformatics.scm | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 51660026eb..6cc808c6a7 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -8280,3 +8280,27 @@ (define-public r-mzr
 proteowizard library for mzML and mzIdentML.  The netCDF reading code has
 previously been used in XCMS.")
     (license license:artistic2.0)))
+
+(define-public r-affyio
+  (package
+    (name "r-affyio")
+    (version "1.44.0")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (bioconductor-uri "affyio" version))
+       (sha256
+        (base32
+         "1svsl4mpk06xm505pap913x69ywks99262krag8y4ygpllj7dfyy"))))
+    (build-system r-build-system)
+    (propagated-inputs
+     `(("r-zlibbioc" ,r-zlibbioc)))
+    (inputs
+     `(("zlib" ,zlib)))
+    (home-page "https://github.com/bmbolstad/affyio")
+    (synopsis "Tools for parsing Affymetrix data files")
+    (description
+     "This package provides routines for parsing Affymetrix data files based
+upon file format information.  The primary focus is on accessing the CEL and
+CDF file formats.")
+    (license license:lgpl2.0+)))
-- 
cgit v1.2.3


From 05c7e5fb76cf8ebc271595cf3e363e3b8678d7e0 Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <rekado@elephly.net>
Date: Mon, 16 Jan 2017 12:18:51 +0100
Subject: gnu: Add r-affy.

* gnu/packages/bioinformatics.scm (r-affy): New variable.
---
 gnu/packages/bioinformatics.scm | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 6cc808c6a7..9e073843e2 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -8304,3 +8304,29 @@ (define-public r-affyio
 upon file format information.  The primary focus is on accessing the CEL and
 CDF file formats.")
     (license license:lgpl2.0+)))
+
+(define-public r-affy
+  (package
+    (name "r-affy")
+    (version "1.52.0")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (bioconductor-uri "affy" version))
+       (sha256
+        (base32
+         "1snq71ligf0wvaxa6zfrl13ydw0zfhspmhdyfk8q3ba3np4cz344"))))
+    (build-system r-build-system)
+    (propagated-inputs
+     `(("r-affyio" ,r-affyio)
+       ("r-biobase" ,r-biobase)
+       ("r-biocgenerics" ,r-biocgenerics)
+       ("r-biocinstaller" ,r-biocinstaller)
+       ("r-preprocesscore" ,r-preprocesscore)
+       ("r-zlibbioc" ,r-zlibbioc)))
+    (home-page "http://bioconductor.org/packages/affy")
+    (synopsis "Methods for affymetrix oligonucleotide arrays")
+    (description
+     "This package contains functions for exploratory oligonucleotide array
+analysis.")
+    (license license:lgpl2.0+)))
-- 
cgit v1.2.3


From 7c08afaf7bd86c543d46a1d3157a8a57bfed8af4 Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <rekado@elephly.net>
Date: Mon, 16 Jan 2017 12:19:09 +0100
Subject: gnu: Add r-vsn.

* gnu/packages/bioinformatics.scm (r-vsn): New variable.
---
 gnu/packages/bioinformatics.scm | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 9e073843e2..82a60dae05 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -8330,3 +8330,36 @@ (define-public r-affy
      "This package contains functions for exploratory oligonucleotide array
 analysis.")
     (license license:lgpl2.0+)))
+
+(define-public r-vsn
+  (package
+    (name "r-vsn")
+    (version "3.42.3")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (bioconductor-uri "vsn" version))
+       (sha256
+        (base32
+         "0mgl0azys2g90simf8wx6jdwd7gyg3m4pf12n6w6507jixm2cg97"))))
+    (build-system r-build-system)
+    (propagated-inputs
+     `(("r-affy" ,r-affy)
+       ("r-biobase" ,r-biobase)
+       ("r-ggplot2" ,r-ggplot2)
+       ("r-limma" ,r-limma)))
+    (home-page "http://bioconductor.org/packages/release/bioc/html/vsn.html")
+    (synopsis "Variance stabilization and calibration for microarray data")
+    (description
+     "The package implements a method for normalising microarray intensities,
+and works for single- and multiple-color arrays.  It can also be used for data
+from other technologies, as long as they have similar format.  The method uses
+a robust variant of the maximum-likelihood estimator for an
+additive-multiplicative error model and affine calibration.  The model
+incorporates data calibration step (a.k.a.  normalization), a model for the
+dependence of the variance on the mean intensity and a variance stabilizing
+data transformation.  Differences between transformed intensities are
+analogous to \"normalized log-ratios\".  However, in contrast to the latter,
+their variance is independent of the mean, and they are usually more sensitive
+and specific in detecting differential transcription.")
+    (license license:artistic2.0)))
-- 
cgit v1.2.3


From 4aa7d592f18c690106b604029a884c0654795189 Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <rekado@elephly.net>
Date: Mon, 16 Jan 2017 12:19:28 +0100
Subject: gnu: Add r-mzid.

* gnu/packages/bioinformatics.scm (r-mzid): New variable.
---
 gnu/packages/bioinformatics.scm | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 82a60dae05..4952bbe339 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -8363,3 +8363,33 @@ (define-public r-vsn
 their variance is independent of the mean, and they are usually more sensitive
 and specific in detecting differential transcription.")
     (license license:artistic2.0)))
+
+(define-public r-mzid
+  (package
+    (name "r-mzid")
+    (version "1.12.0")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (bioconductor-uri "mzID" version))
+       (sha256
+        (base32
+         "1zn896cpfvqp1qmq5c4vcj933hb8rxwb6gkck1wqvr7393rpqy1q"))))
+    (properties `((upstream-name . "mzID")))
+    (build-system r-build-system)
+    (propagated-inputs
+     `(("r-doparallel" ,r-doparallel)
+       ("r-foreach" ,r-foreach)
+       ("r-iterators" ,r-iterators)
+       ("r-plyr" ,r-plyr)
+       ("r-protgenerics" ,r-protgenerics)
+       ("r-rcpp" ,r-rcpp)
+       ("r-xml" ,r-xml)))
+    (home-page "http://bioconductor.org/packages/mzID")
+    (synopsis "Parser for mzIdentML files")
+    (description
+     "This package provides a parser for mzIdentML files implemented using the
+XML package.  The parser tries to be general and able to handle all types of
+mzIdentML files with the drawback of having less pretty output than a vendor
+specific parser.")
+    (license license:gpl2+)))
-- 
cgit v1.2.3


From 6a67e181ac5fcf0fc19a5b4a247e1680e112d3ca Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <rekado@elephly.net>
Date: Mon, 16 Jan 2017 12:21:05 +0100
Subject: gnu: Add r-pcamethods.

* gnu/packages/bioinformatics.scm (r-pcamethods): New variable.
---
 gnu/packages/bioinformatics.scm | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 4952bbe339..bc7b0be1a5 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -8393,3 +8393,32 @@ (define-public r-mzid
 mzIdentML files with the drawback of having less pretty output than a vendor
 specific parser.")
     (license license:gpl2+)))
+
+(define-public r-pcamethods
+  (package
+    (name "r-pcamethods")
+    (version "1.66.0")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (bioconductor-uri "pcaMethods" version))
+       (sha256
+        (base32
+         "18mawhxw57pgpn87qha4mwki24gqja7wpqha8q496476vyap11xw"))))
+    (properties `((upstream-name . "pcaMethods")))
+    (build-system r-build-system)
+    (propagated-inputs
+     `(("r-biobase" ,r-biobase)
+       ("r-biocgenerics" ,r-biocgenerics)
+       ("r-rcpp" ,r-rcpp)))
+    (home-page "https://github.com/hredestig/pcamethods")
+    (synopsis "Collection of PCA methods")
+    (description
+     "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
+Inverse Non-Linear PCA and the conventional SVD PCA.  A cluster based method
+for missing value estimation is included for comparison.  BPCA, PPCA and
+NipalsPCA may be used to perform PCA on incomplete data as well as for
+accurate missing value estimation.  A set of methods for printing and plotting
+the results is also provided.  All PCA methods make use of the same data
+structure (pcaRes) to provide a common interface to the PCA results.")
+    (license license:gpl3+)))
-- 
cgit v1.2.3


From 11879284cbbcc045029f328b7a20a4af4796cb2c Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <rekado@elephly.net>
Date: Mon, 16 Jan 2017 12:21:21 +0100
Subject: gnu: Add r-msnbase.

* gnu/packages/bioinformatics.scm (r-msnbase): New variable.
---
 gnu/packages/bioinformatics.scm | 41 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index bc7b0be1a5..abe5c92949 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -8422,3 +8422,44 @@ (define-public r-pcamethods
 the results is also provided.  All PCA methods make use of the same data
 structure (pcaRes) to provide a common interface to the PCA results.")
     (license license:gpl3+)))
+
+(define-public r-msnbase
+  (package
+    (name "r-msnbase")
+    (version "2.0.2")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (bioconductor-uri "MSnbase" version))
+       (sha256
+        (base32
+         "0jjjs29dcwsjaxzfqxy98ycpg3rwxzzchkj77my3cjgdc00sm66n"))))
+    (properties `((upstream-name . "MSnbase")))
+    (build-system r-build-system)
+    (propagated-inputs
+     `(("r-affy" ,r-affy)
+       ("r-biobase" ,r-biobase)
+       ("r-biocgenerics" ,r-biocgenerics)
+       ("r-biocparallel" ,r-biocparallel)
+       ("r-digest" ,r-digest)
+       ("r-ggplot2" ,r-ggplot2)
+       ("r-impute" ,r-impute)
+       ("r-iranges" ,r-iranges)
+       ("r-maldiquant" ,r-maldiquant)
+       ("r-mzid" ,r-mzid)
+       ("r-mzr" ,r-mzr)
+       ("r-pcamethods" ,r-pcamethods)
+       ("r-plyr" ,r-plyr)
+       ("r-preprocesscore" ,r-preprocesscore)
+       ("r-protgenerics" ,r-protgenerics)
+       ("r-rcpp" ,r-rcpp)
+       ("r-reshape2" ,r-reshape2)
+       ("r-s4vectors" ,r-s4vectors)
+       ("r-vsn" ,r-vsn)
+       ("r-xml" ,r-xml)))
+    (home-page "https://github.com/lgatto/MSnbase")
+    (synopsis "Base functions and classes for MS-based proteomics")
+    (description
+     "This package provides basic plotting, data manipulation and processing
+of MS-based proteomics data.")
+    (license license:artistic2.0)))
-- 
cgit v1.2.3


From 66da3a9f319293f42906117388814b98ddb71b79 Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <rekado@elephly.net>
Date: Mon, 16 Jan 2017 12:21:38 +0100
Subject: gnu: Add r-msnid.

* gnu/packages/bioinformatics.scm (r-msnid): New variable.
---
 gnu/packages/bioinformatics.scm | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index abe5c92949..c60bedce43 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -8463,3 +8463,42 @@ (define-public r-msnbase
      "This package provides basic plotting, data manipulation and processing
 of MS-based proteomics data.")
     (license license:artistic2.0)))
+
+(define-public r-msnid
+  (package
+    (name "r-msnid")
+    (version "1.8.0")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (bioconductor-uri "MSnID" version))
+       (sha256
+        (base32
+         "0fkk3za39cxi0jyxmagmycjdslr2xf6vg3ylz14jyffqi0blw9d5"))))
+    (properties `((upstream-name . "MSnID")))
+    (build-system r-build-system)
+    (propagated-inputs
+     `(("r-biobase" ,r-biobase)
+       ("r-data-table" ,r-data-table)
+       ("r-doparallel" ,r-doparallel)
+       ("r-dplyr" ,r-dplyr)
+       ("r-foreach" ,r-foreach)
+       ("r-iterators" ,r-iterators)
+       ("r-msnbase" ,r-msnbase)
+       ("r-mzid" ,r-mzid)
+       ("r-mzr" ,r-mzr)
+       ("r-protgenerics" ,r-protgenerics)
+       ("r-r-cache" ,r-r-cache)
+       ("r-rcpp" ,r-rcpp)
+       ("r-reshape2" ,r-reshape2)))
+    (home-page "http://bioconductor.org/packages/MSnID")
+    (synopsis "Utilities for LC-MSn proteomics identifications")
+    (description
+     "This package extracts MS/MS ID data from mzIdentML (leveraging the mzID
+package) or text files.  After collating the search results from multiple
+datasets it assesses their identification quality and optimize filtering
+criteria to achieve the maximum number of identifications while not exceeding
+a specified false discovery rate.  It also contains a number of utilities to
+explore the MS/MS results and assess missed and irregular enzymatic cleavages,
+mass measurement accuracy, etc.")
+    (license license:artistic2.0)))
-- 
cgit v1.2.3


From 1778ea740e052a9a31151b2746d3bcce199ec3b4 Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <rekado@elephly.net>
Date: Wed, 18 Jan 2017 16:00:43 +0100
Subject: gnu: multiqc: Add python-nose to inputs.

* gnu/packages/bioinformatics.scm (multiqc)[propagated-inputs]: Add
python-nose.
---
 gnu/packages/bioinformatics.scm | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index c60bedce43..0a77ccfdf9 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -8024,7 +8024,9 @@ (define-public multiqc
        ("python-pyyaml" ,python-pyyaml)
        ("python-click" ,python-click)
        ("python-matplotlib" ,python-matplotlib)
-       ("python-numpy" ,python-numpy)))
+       ("python-numpy" ,python-numpy)
+       ;; MultQC checks for the presence of nose at runtime.
+       ("python-nose" ,python-nose)))
     (home-page "http://multiqc.info")
     (synopsis "Aggregate bioinformatics analysis reports")
     (description
-- 
cgit v1.2.3


From e614d6398ab2b90a3d025fe559fa49a4f7b56cba Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <rekado@elephly.net>
Date: Fri, 20 Jan 2017 15:28:50 +0100
Subject: gnu: r-msnbase: Expand abbreviation in description.

* gnu/packages/bioinformatics.scm (r-msnbase)[description]: Expand "MS"
to "mass spectrometry".
---
 gnu/packages/bioinformatics.scm | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 0a77ccfdf9..f8a4ed7e5d 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -8463,7 +8463,7 @@ (define-public r-msnbase
     (synopsis "Base functions and classes for MS-based proteomics")
     (description
      "This package provides basic plotting, data manipulation and processing
-of MS-based proteomics data.")
+of mass spectrometry based proteomics data.")
     (license license:artistic2.0)))
 
 (define-public r-msnid
-- 
cgit v1.2.3


From 2923f3e5b9b4ce0f355fc6d1f7a688e918c95dda Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <rekado@elephly.net>
Date: Fri, 20 Jan 2017 15:29:50 +0100
Subject: gnu: r-msnid: Expand abbreviation in description.

* gnu/packages/bioinformatics.scm (r-msnid)[description]: Expand "MS/MS"
to "tandem mass spectrometry".
---
 gnu/packages/bioinformatics.scm | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index f8a4ed7e5d..64c40c729f 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -8496,11 +8496,11 @@ (define-public r-msnid
     (home-page "http://bioconductor.org/packages/MSnID")
     (synopsis "Utilities for LC-MSn proteomics identifications")
     (description
-     "This package extracts MS/MS ID data from mzIdentML (leveraging the mzID
-package) or text files.  After collating the search results from multiple
-datasets it assesses their identification quality and optimize filtering
-criteria to achieve the maximum number of identifications while not exceeding
-a specified false discovery rate.  It also contains a number of utilities to
-explore the MS/MS results and assess missed and irregular enzymatic cleavages,
-mass measurement accuracy, etc.")
+     "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
+from mzIdentML (leveraging the mzID package) or text files.  After collating
+the search results from multiple datasets it assesses their identification
+quality and optimize filtering criteria to achieve the maximum number of
+identifications while not exceeding a specified false discovery rate.  It also
+contains a number of utilities to explore the MS/MS results and assess missed
+and irregular enzymatic cleavages, mass measurement accuracy, etc.")
     (license license:artistic2.0)))
-- 
cgit v1.2.3


From cda0f9a4a91e69c0d3468138ba2bf16f12dd471e Mon Sep 17 00:00:00 2001
From: Ben Woodcroft <donttrustben@gmail.com>
Date: Sat, 21 Jan 2017 17:28:11 +1000
Subject: gnu: diamond: Update to 0.8.34.

* gnu/packages/bioinformatics.scm (diamond): Update to 0.8.34.
---
 gnu/packages/bioinformatics.scm | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 64c40c729f..1209eafcff 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -2047,7 +2047,7 @@ (define-public deeptools
 (define-public diamond
   (package
     (name "diamond")
-    (version "0.8.31")
+    (version "0.8.34")
     (source (origin
               (method url-fetch)
               (uri (string-append
@@ -2056,7 +2056,7 @@ (define-public diamond
               (file-name (string-append name "-" version ".tar.gz"))
               (sha256
                (base32
-                "0nh79f4rpgq8vmlga743r7vd0z0ik6spy34f7vfq0v9lcmvfr7xq"))))
+                "0jvr34g346gbz7z1zb9bs0vplivm9p4cxk0lbzklvdpa7g236p39"))))
     (build-system cmake-build-system)
     (arguments
      '(#:tests? #f ; no "check" target
-- 
cgit v1.2.3


From c0dee46c85c9ae9f9b40f83f693f666fdd3e5d28 Mon Sep 17 00:00:00 2001
From: Ben Woodcroft <donttrustben@gmail.com>
Date: Sat, 21 Jan 2017 18:17:16 +1000
Subject: gnu: r-vegan: Update to 2.4-2.

* gnu/packages/bioinformatics.scm (r-vegan): Update to 2.4-2.
---
 gnu/packages/bioinformatics.scm | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'gnu/packages/bioinformatics.scm')

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 1209eafcff..3bf352193c 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -5290,14 +5290,14 @@ (define-public r-centipede
 (define-public r-vegan
   (package
     (name "r-vegan")
-    (version "2.4-1")
+    (version "2.4-2")
     (source
      (origin
        (method url-fetch)
        (uri (cran-uri "vegan" version))
        (sha256
         (base32
-         "0i0c7rc0nzgbysd1nlxzxd2rvy75qcnw3yc7nggzqjzzj5d7yzsd"))))
+         "12wf64izrpq9z3ix7mgm5421mq0xsm8dw5qblvcrz452nfhjf5w9"))))
     (build-system r-build-system)
     (arguments
      `(#:phases
-- 
cgit v1.2.3