gnu: Add preseq.

* gnu/packages/bioinformatics.scm (preseq): New variable.
* gnu/packages/patches/preseq-1.0.2-install-to-PREFIX.patch: New file.
* gnu/packages/patches/preseq-1.0.2-link-with-libbam.patch: New file.
* gnu-system.am (dist_patch_DATA): Add them.

3 files changed, 126 insertions, 0 deletions

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index f6349cfb8f..2b7f78be34 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -2087,6 +2087,62 @@ subsequent visualization, annotation and storage of results.")
     ;; LGPLv2.1+
     (license (list license:gpl2 license:lgpl2.1+))))
 
+(define-public preseq
+  (package
+    (name "preseq")
+    (version "1.0.2")
+    (source (origin
+              (method url-fetch)
+              (uri
+               (string-append "http://smithlabresearch.org/downloads/preseq-"
+                              version ".tar.bz2"))
+              (sha256
+               (base32 "0r7sw07p6nv8ygvc17gd78lisbw5336v3vhs86b5wv8mw3pwqksc"))
+              (patches (list (search-patch "preseq-1.0.2-install-to-PREFIX.patch")
+                             (search-patch "preseq-1.0.2-link-with-libbam.patch")))
+              (modules '((guix build utils)))
+              (snippet
+               ;; Remove bundled samtools.
+               '(delete-file-recursively "preseq-master/samtools"))))
+    (build-system gnu-build-system)
+    (arguments
+     `(#:tests? #f ;no "check" target
+       #:phases
+       (modify-phases %standard-phases
+         (add-after
+          'unpack 'enter-dir
+          (lambda _
+            (chdir "preseq-master")
+            #t))
+         (add-after
+          'unpack 'use-samtools-headers
+          (lambda _
+            (substitute* '("smithlab_cpp/SAM.cpp"
+                           "smithlab_cpp/SAM.hpp")
+              (("sam.h") "samtools/sam.h"))
+            #t))
+         (delete 'configure))
+       #:make-flags (list (string-append "PREFIX="
+                                         (assoc-ref %outputs "out"))
+                          (string-append "LIBBAM="
+                                         (assoc-ref %build-inputs "samtools")
+                                         "/lib/libbam.a"))))
+    (inputs
+     `(("gsl" ,gsl)
+       ("samtools" ,samtools-0.1)
+       ("zlib" ,zlib)))
+    (home-page "http://smithlabresearch.org/software/preseq/")
+    (synopsis "Program for analyzing library complexity")
+    (description
+     "The preseq package is aimed at predicting and estimating the complexity
+of a genomic sequencing library, equivalent to predicting and estimating the
+number of redundant reads from a given sequencing depth and how many will be
+expected from additional sequencing using an initial sequencing experiment.
+The estimates can then be used to examine the utility of further sequencing,
+optimize the sequencing depth, or to screen multiple libraries to avoid low
+complexity samples.")
+    (license license:gpl3+)))
+
 (define-public sra-tools
   (package
     (name "sra-tools")
diff --git a/gnu/packages/patches/preseq-1.0.2-install-to-PREFIX.patch b/gnu/packages/patches/preseq-1.0.2-install-to-PREFIX.patch
new file mode 100644
index 0000000000..f8318ae0f5
--- /dev/null
+++ b/gnu/packages/patches/preseq-1.0.2-install-to-PREFIX.patch
@@ -0,0 +1,37 @@
+This patch has been submitted upstream: https://github.com/smithlabcode/preseq/pull/15
+
+From 65387b0d766e6c06a15cf8d8f9183d9a4ba644bb Mon Sep 17 00:00:00 2001
+From: Ricardo Wurmus <ricardo.wurmus@mdc-berlin.de>
+Date: Thu, 25 Jun 2015 15:01:53 +0200
+Subject: [PATCH] Install to PREFIX
+
+---
+ Makefile | 8 ++++++--
+ 1 file changed, 6 insertions(+), 2 deletions(-)
+
+diff --git a/Makefile b/Makefile
+index 4d0367a..e334f2f 100644
+--- a/preseq-master/Makefile
++++ b/preseq-master/Makefile
+@@ -22,6 +22,10 @@ ifndef ROOT
+ ROOT = $(shell pwd)
+ endif
+ 
++ifndef PREFIX
++PREFIX = $(ROOT)
++endif
++
+ ifndef SMITHLAB_CPP
+ SMITHLAB_CPP=$(ROOT)/smithlab_cpp/
+ endif
+@@ -91,8 +95,8 @@ endif
+ 	$(CXX) $(CXXFLAGS) -o $@ $^ $(INCLUDEARGS) $(LIBS)
+ 
+ install: $(PROGS)
+-	@mkdir -p $(ROOT)/bin
+-	@install -m 755 $(PROGS) $(ROOT)/bin
++	@mkdir -p $(PREFIX)/bin
++	@install -m 755 $(PROGS) $(PREFIX)/bin
+ 
+ clean:
+ 	@-rm -f $(PROGS) *.o *~
diff --git a/gnu/packages/patches/preseq-1.0.2-link-with-libbam.patch b/gnu/packages/patches/preseq-1.0.2-link-with-libbam.patch
new file mode 100644
index 0000000000..035a3b1fe4
--- /dev/null
+++ b/gnu/packages/patches/preseq-1.0.2-link-with-libbam.patch
@@ -0,0 +1,33 @@
+This patch has been submitted upstream: https://github.com/smithlabcode/preseq/pull/15
+
+From a937a54d56e8a6ff06237471e568154d1fa5f267 Mon Sep 17 00:00:00 2001
+From: Ricardo Wurmus <ricardo.wurmus@mdc-berlin.de>
+Date: Thu, 25 Jun 2015 15:02:35 +0200
+Subject: [PATCH] Link with libbam.a if provided via LIBBAM
+
+---
+ Makefile | 7 +++++++
+ 1 file changed, 7 insertions(+)
+
+diff --git a/Makefile b/Makefile
+index e334f2f..de310e4 100644
+--- a/preseq-master/Makefile
++++ b/preseq-master/Makefile
+@@ -83,10 +83,17 @@ $(PROGS): $(addprefix $(SMITHLAB_CPP)/, \
+ preseq: continued_fraction.o load_data_for_complexity.o moment_sequence.o
+ 
+ ifdef SAMTOOLS_DIR
++ifdef LIBBAM
++LIBS += -pthread
++bam2mr preseq: $(addprefix $(SMITHLAB_CPP)/, SAM.o) \
++        $(LIBBAM)
++else
+ bam2mr preseq: $(addprefix $(SMITHLAB_CPP)/, SAM.o) \
+         $(addprefix $(SAMTOOLS_DIR)/, sam.o bam.o bam_import.o bam_pileup.o \
+         faidx.o bam_aux.o kstring.o knetfile.o sam_header.o razf.o bgzf.o)
+ endif
++endif # SAMTOOLS_DIR
++
+ 
+ %.o: %.cpp %.hpp
+ 	$(CXX) $(CXXFLAGS) -c -o $@ $< $(INCLUDEARGS)