01/01: gnu: Add plink.

[Ricardo Wurmus]

rekado pushed a commit to branch master
in repository guix.

commit cc6ed477372f8cb3aeb579fa6a5858179548f9ba
Author: Ricardo Wurmus <address@hidden>
Date:   Thu Jun 25 12:04:05 2015 +0200

    gnu: Add plink.
    
    * gnu/packages/bioinformatics.scm (plink): New variable.
    * gnu/packages/patches/plink-1.07-unclobber-i.patch: New file.
---
 gnu/packages/bioinformatics.scm                   |   53 ++++++++++++++++
 gnu/packages/patches/plink-1.07-unclobber-i.patch |   69 +++++++++++++++++++++
 2 files changed, 122 insertions(+), 0 deletions(-)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 31df219..4eac835 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -1793,6 +1793,59 @@ Databases are stored in a portable image within the file 
system, and can be
 accessed/downloaded on demand across HTTP.")
     (license license:public-domain)))
 
+(define-public plink
+  (package
+    (name "plink")
+    (version "1.07")
+    (source
+     (origin
+       (method url-fetch)
+       (uri (string-append
+             "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-";
+             version "-src.zip"))
+       (sha256
+        (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
+       (patches (list (search-patch "plink-1.07-unclobber-i.patch")))))
+    (build-system gnu-build-system)
+    (arguments
+     '(#:tests? #f ;no "check" target
+       #:make-flags (list (string-append "LIB_LAPACK="
+                                         (assoc-ref %build-inputs "lapack")
+                                         "/lib/liblapack.so")
+                          "WITH_LAPACK=1"
+                          "FORCE_DYNAMIC=1"
+                          ;; disable phoning home
+                          "WITH_WEBCHECK=")
+       #:phases
+       (modify-phases %standard-phases
+         ;; no "configure" script
+         (delete 'configure)
+         (replace 'install
+                  (lambda* (#:key outputs #:allow-other-keys)
+                    (let ((bin (string-append (assoc-ref outputs "out")
+                                              "/bin/")))
+                      (mkdir-p bin)
+                      (copy-file "plink" (string-append bin "plink"))
+                      #t))))))
+    (inputs
+     `(("zlib" ,zlib)
+       ("lapack" ,lapack)))
+    (native-inputs
+     `(("unzip" ,unzip)))
+    (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/";)
+    (synopsis "Whole genome association analysis toolset")
+    (description
+     "PLINK is a whole genome association analysis toolset, designed to
+perform a range of basic, large-scale analyses in a computationally efficient
+manner.  The focus of PLINK is purely on analysis of genotype/phenotype data,
+so there is no support for steps prior to this (e.g. study design and
+planning, generating genotype or CNV calls from raw data).  Through
+integration with gPLINK and Haploview, there is some support for the
+subsequent visualization, annotation and storage of results.")
+    ;; Code is released under GPLv2, except for fisher.h, which is under
+    ;; LGPLv2.1+
+    (license (list license:gpl2 license:lgpl2.1+))))
+
 (define-public sra-tools
   (package
     (name "sra-tools")
diff --git a/gnu/packages/patches/plink-1.07-unclobber-i.patch 
b/gnu/packages/patches/plink-1.07-unclobber-i.patch
new file mode 100644
index 0000000..60cd97b
--- /dev/null
+++ b/gnu/packages/patches/plink-1.07-unclobber-i.patch
@@ -0,0 +1,69 @@
+GCC rightfully complains about redefined variables, as iterator declarations
+appear inside loops with a loop variable of the same name.
+
+This patch has been sent upstream.
+
+--- a/sets.cpp 2015-06-25 11:22:08.252821681 +0200
++++ b/sets.cpp 2015-06-25 11:22:23.239187985 +0200
+@@ -768,11 +768,11 @@
+       //////////////////////////////////////////////
+       // Reset original missing status
+ 
+-      vector<Individual*>::iterator i = PP->sample.begin();
+-      while ( i != PP->sample.end() )
++      vector<Individual*>::iterator it = PP->sample.begin();
++      while ( it != PP->sample.end() )
+       {
+-        (*i)->missing = (*i)->flag;
+-        ++i;
++        (*it)->missing = (*it)->flag;
++        ++it;
+       }
+ 
+       ////////////////////////////////////////////////
+
+--- a/elf.cpp  2009-10-10 18:00:21.000000000 +0200
++++ b/elf.cpp  2015-06-25 11:34:06.136835756 +0200
+@@ -1175,10 +1175,10 @@
+         << setw(8) << gcnt << " "
+         << setw(8) << (double)cnt / (double)gcnt << "\n";
+ 
+-      map<int,int>::iterator i = chr_cnt.begin();
+-      while ( i != chr_cnt.end() )
++      map<int,int>::iterator it = chr_cnt.begin();
++      while ( it != chr_cnt.end() )
+       {
+-        int c = i->first;
++        int c = it->first;
+         int x = chr_cnt.find( c )->second;
+         int y = chr_gcnt.find( c )->second;
+         
+@@ -1189,7 +1189,7 @@
+             << setw(8) << y << " "
+             << setw(8) << (double)x / (double)y << "\n";
+         
+-        ++i;
++        ++it;
+       }
+       
+     }
+
+--- plink-1.07-src/idhelp.cpp  2009-10-10 18:00:22.000000000 +0200
++++ plink-1.07-src/idhelp.cpp.patched  2015-06-25 11:37:39.387204086 +0200
+@@ -772,12 +772,12 @@
+       for (int j = 0 ; j < jointField.size(); j++ )
+       {
+         set<IDField*> & jf = jointField[j];
+-        set<IDField*>::iterator j = jf.begin();
++        set<IDField*>::iterator jit = jf.begin();
+         PP->printLOG(" { ");
+-        while ( j != jf.end() )
++        while ( jit != jf.end() )
+           {
+-            PP->printLOG( (*j)->name + " " );
+-            ++j;
++            PP->printLOG( (*jit)->name + " " );
++            ++jit;
+           }
+         PP->printLOG(" }");
+       }