[PATCH] Add GenomicRanges.

[Ricardo Wurmus]

Hi Guix,

here’s a first batch of packages imported from Bioconductor.  This patch
set adds the GenomicRanges package along with its dependencies.  They
are all very simple.

Only XVector has a separate build phase to avoid a dependency on
zlibbioc, which is a version of zlib that’s frozen in time and only
provided for systems that don’t have a working version of zlib.

~~ Ricardo

>From 417d3f16b02a7295cf98a7f5fc365d87b06bb659 Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <address@hidden>
Date: Fri, 18 Dec 2015 12:06:55 +0100
Subject: [PATCH 1/6] gnu: Add BiocGenerics.

* gnu/packages/bioinformatics.scm (r-biocgenerics): New variable.
---
 gnu/packages/bioinformatics.scm | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 5d93c52..7215fb9 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -3324,6 +3324,27 @@ use multiple corrections.  Visualization of data can be 
done either by
 barplots or heatmaps.")
     (license license:gpl2+)))
 
+(define-public r-biocgenerics
+  (package
+    (name "r-biocgenerics")
+    (version "0.16.1")
+    (source (origin
+              (method url-fetch)
+              (uri (bioconductor-uri "BiocGenerics" version))
+              (sha256
+               (base32
+                "0f16ryy5f012hvksrwlmm33bcl7lw97i2jvhbnwfwl03j4w7nhc1"))))
+    (properties
+     `((upstream-name . "BiocGenerics")
+       (r-repository . bioconductor)))
+    (build-system r-build-system)
+    (home-page "http://bioconductor.org/packages/BiocGenerics";)
+    (synopsis "S4 generic functions for Bioconductor")
+    (description
+     "This package provides S4 generic functions needed by many Bioconductor
+packages.")
+    (license license:artistic2.0)))
+
 (define-public r-qtl
  (package
   (name "r-qtl")
-- 
2.1.0

>From 08ebe755038bbb4111d4d68192af790b6cd7b1dc Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <address@hidden>
Date: Fri, 18 Dec 2015 12:07:18 +0100
Subject: [PATCH 2/6] gnu: Add S4Vectors.

* gnu/packages/bioinformatics.scm (r-s4vectors): New variable.
---
 gnu/packages/bioinformatics.scm | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 7215fb9..83ba132 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -3345,6 +3345,34 @@ barplots or heatmaps.")
 packages.")
     (license license:artistic2.0)))
 
+(define-public r-s4vectors
+  (package
+    (name "r-s4vectors")
+    (version "0.8.5")
+    (source (origin
+              (method url-fetch)
+              (uri (bioconductor-uri "S4Vectors" version))
+              (sha256
+               (base32
+                "10f4jxwlwsiy7zhb3kgp6anid0d7wkvrrljl80r3nhx38yr24l5k"))))
+    (properties
+     `((upstream-name . "S4Vectors")
+       (r-repository . bioconductor)))
+    (build-system r-build-system)
+    (propagated-inputs
+     `(("r-biocgenerics" ,r-biocgenerics)))
+    (home-page "http://bioconductor.org/packages/S4Vectors";)
+    (synopsis "S4 implementation of vectors and lists")
+    (description
+     "The S4Vectors package defines the @code{Vector} and @code{List} virtual
+classes and a set of generic functions that extend the semantic of ordinary
+vectors and lists in R.  Package developers can easily implement vector-like
+or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
+In addition, a few low-level concrete subclasses of general interest (e.g.
address@hidden, @code{Rle}, and @code{Hits}) are implemented in the
+S4Vectors package itself.")
+    (license license:artistic2.0)))
+
 (define-public r-qtl
  (package
   (name "r-qtl")
-- 
2.1.0

>From ca719b062395d7fa5bc0bdd284a85b6573962f30 Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <address@hidden>
Date: Fri, 18 Dec 2015 12:07:39 +0100
Subject: [PATCH 3/6] gnu: Add IRanges.

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

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 83ba132..1254d83 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -3373,6 +3373,36 @@ In addition, a few low-level concrete subclasses of 
general interest (e.g.
 S4Vectors package itself.")
     (license license:artistic2.0)))
 
+(define-public r-iranges
+  (package
+    (name "r-iranges")
+    (version "2.4.6")
+    (source (origin
+              (method url-fetch)
+              (uri (bioconductor-uri "IRanges" version))
+              (sha256
+               (base32
+                "00x0266sys1fc5ipa639y84p6m6mgspk2xb099vcwmd3w4hypj9d"))))
+    (properties
+     `((upstream-name . "IRanges")
+       (r-repository . bioconductor)))
+    (build-system r-build-system)
+    (propagated-inputs
+     `(("r-biocgenerics" ,r-biocgenerics)
+       ("r-s4vectors" ,r-s4vectors)))
+    (home-page "http://bioconductor.org/packages/IRanges";)
+    (synopsis "Infrastructure for manipulating intervals on sequences")
+    (description
+     "This package provides efficient low-level and highly reusable S4 classes
+for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
+generally, data that can be organized sequentially (formally defined as
address@hidden objects), as well as views on these @code{Vector} objects.
+Efficient list-like classes are also provided for storing big collections of
+instances of the basic classes.  All classes in the package use consistent
+naming and share the same rich and consistent \"Vector API\" as much as
+possible.")
+    (license license:artistic2.0)))
+
 (define-public r-qtl
  (package
   (name "r-qtl")
-- 
2.1.0

>From 6300fdd91356ea73b019dc44455c6422954276de Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <address@hidden>
Date: Fri, 18 Dec 2015 12:07:56 +0100
Subject: [PATCH 4/6] gnu: Add GenomeInfoDb.

* gnu/packages/bioinformatics.scm (r-genomeinfodb): New variable.
---
 gnu/packages/bioinformatics.scm | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 1254d83..9a67c19 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -3403,6 +3403,33 @@ naming and share the same rich and consistent \"Vector 
API\" as much as
 possible.")
     (license license:artistic2.0)))
 
+(define-public r-genomeinfodb
+  (package
+    (name "r-genomeinfodb")
+    (version "1.6.1")
+    (source (origin
+              (method url-fetch)
+              (uri (bioconductor-uri "GenomeInfoDb" version))
+              (sha256
+               (base32
+                "1j2n1v1mrw1fxn7cyffz112pm76wd6gy9q9qwlsfv3brbsqbvdbf"))))
+    (properties
+     `((upstream-name . "GenomeInfoDb")
+       (r-repository . bioconductor)))
+    (build-system r-build-system)
+    (propagated-inputs
+     `(("r-biocgenerics" ,r-biocgenerics)
+       ("r-iranges" ,r-iranges)
+       ("r-s4vectors" ,r-s4vectors)))
+    (home-page "http://bioconductor.org/packages/GenomeInfoDb";)
+    (synopsis "Utilities for manipulating chromosome identifiers")
+    (description
+     "This package contains data and functions that define and allow
+translation between different chromosome sequence naming conventions (e.g.,
+\"chr1\" versus \"1\"), including a function that attempts to place sequence
+names in their natural, rather than lexicographic, order.")
+    (license license:artistic2.0)))
+
 (define-public r-qtl
  (package
   (name "r-qtl")
-- 
2.1.0

>From cca6ffc0843d1043f55177d644e246472ab1a87e Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <address@hidden>
Date: Fri, 18 Dec 2015 12:08:22 +0100
Subject: [PATCH 5/6] gnu: Add XVector.

* gnu/packages/bioinformatics.scm (r-xvector): New variable.
---
 gnu/packages/bioinformatics.scm | 37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 9a67c19..1f00edc 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -3430,6 +3430,43 @@ translation between different chromosome sequence naming 
conventions (e.g.,
 names in their natural, rather than lexicographic, order.")
     (license license:artistic2.0)))
 
+(define-public r-xvector
+  (package
+    (name "r-xvector")
+    (version "0.10.0")
+    (source (origin
+              (method url-fetch)
+              (uri (bioconductor-uri "XVector" version))
+              (sha256
+               (base32
+                "0havwyr6xqk7w0rmbwfj9jq1djz7wzdz7w39adhklwzwz9l4ih3a"))))
+    (properties
+     `((upstream-name . "XVector")
+       (r-repository . bioconductor)))
+    (build-system r-build-system)
+    (arguments
+     `(#:phases
+       (modify-phases %standard-phases
+         (add-after 'unpack 'use-system-zlib
+           (lambda _
+             (substitute* "DESCRIPTION"
+               (("zlibbioc, ") ""))
+             (substitute* "NAMESPACE"
+               (("import\\(zlibbioc\\)") ""))
+             #t)))))
+    (inputs
+     `(("zlib" ,zlib)))
+    (propagated-inputs
+     `(("r-biocgenerics" ,r-biocgenerics)
+       ("r-iranges" ,r-iranges)
+       ("r-s4vectors" ,r-s4vectors)))
+    (home-page "http://bioconductor.org/packages/XVector";)
+    (synopsis "Representation and manpulation of external sequences")
+    (description
+     "This package provides memory efficient S4 classes for storing sequences
+\"externally\" (behind an R external pointer, or on disk).")
+    (license license:artistic2.0)))
+
 (define-public r-qtl
  (package
   (name "r-qtl")
-- 
2.1.0

>From 0cd8314f8163bc332eb2f365ed2beb528f2f245d Mon Sep 17 00:00:00 2001
From: Ricardo Wurmus <address@hidden>
Date: Fri, 18 Dec 2015 12:08:41 +0100
Subject: [PATCH 6/6] gnu: Add GenomicRanges.

* gnu/packages/bioinformatics.scm (r-genomicranges): New variable.
---
 gnu/packages/bioinformatics.scm | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 1f00edc..142b29a 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -3467,6 +3467,34 @@ names in their natural, rather than lexicographic, 
order.")
 \"externally\" (behind an R external pointer, or on disk).")
     (license license:artistic2.0)))
 
+(define-public r-genomicranges
+  (package
+    (name "r-genomicranges")
+    (version "1.22.2")
+    (source (origin
+              (method url-fetch)
+              (uri (bioconductor-uri "GenomicRanges" version))
+              (sha256
+               (base32
+                "1jffvcs0jsi7q4l3pvjj6r73vll80csgkljvhqp0g2ixc43jjng9"))))
+    (properties
+     `((upstream-name . "GenomicRanges")
+       (r-repository . bioconductor)))
+    (build-system r-build-system)
+    (propagated-inputs
+     `(("r-biocgenerics" ,r-biocgenerics)
+       ("r-genomeinfodb" ,r-genomeinfodb)
+       ("r-xvector" ,r-xvector)))
+    (home-page "http://bioconductor.org/packages/GenomicRanges";)
+    (synopsis "Representation and manipulation of genomic intervals")
+    (description
+     "This package provides tools to efficiently represent and manipulate
+genomic annotations and alignments is playing a central role when it comes to
+analyzing high-throughput sequencing data (a.k.a. NGS data).  The
+GenomicRanges package defines general purpose containers for storing and
+manipulating genomic intervals and variables defined along a genome.")
+    (license license:artistic2.0)))
+
 (define-public r-qtl
  (package
   (name "r-qtl")
-- 
2.1.0