.gitignore

+*.o

.gitmodules

+[submodule "samtools"]
+	path = samtools
+	url = https://github.com/samtools/samtools.git

DInDel.cpp

@@ -24,7 +24,7 @@
 #include <boost/math/special_functions/digamma.hpp>
 #include <seqan/align.h>
 #include <seqan/graph_align.h>
-#include "foreach.hpp"
+#include <boost/foreach.hpp>
 #include "bam.h"
 #include "DInDel.hpp"
 #include "Haplotype.hpp"

Faster.cpp

@@ -35,7 +35,7 @@
 #include "Haplotype.hpp"
 #include "Faster.hpp"
 #include "Utils.hpp"
-#include "foreach.hpp"
+#include <boost/foreach.hpp>
 using namespace std;
 const int DEBUGS=0;
 

GetCandidates.cpp

@@ -22,7 +22,7 @@
 #include <fstream>
 #include <string>
 #include "MyBam.hpp"
-#include "foreach.hpp"
+#include <boost/foreach.hpp>
 #include "ObservationModelSeqAn.hpp"
 #include "GetCandidates.hpp"
 #include "Variant.hpp"
@@ -32,7 +32,6 @@
 #include "Fasta.hpp"
 #include "StringHash.hpp"
 #include <set>
-#include "foreach.hpp"
 using namespace std;
 
 int GetCandidatesFromCIGAR::getIndelFromCIGARFetchFunc(const bam1_t *b, void *data)

Haplotype.hpp

@@ -23,7 +23,7 @@
 #include <vector>
 #include "Variant.hpp"
 #include "MLAlignment.hpp"
-#include "foreach.hpp"
+#include <boost/foreach.hpp>
 #include <ext/hash_map>
 #include <set>
 //#include "Fast.hpp"

HaplotypeDistribution.hpp

@@ -27,7 +27,7 @@
 #include "bam.h"
 #include "Haplotype.hpp"
 #include "HapBlock.hpp"
-#include "foreach.hpp"
+#include <boost/foreach.hpp>
 #include "VariantFile.hpp"
 using namespace std;
 

Makefile

-SAMTOOLDIR=/nfs/users/nfs_c/caa/source/samtools/
-SEQANDIR=seqan_library/
+PREFIX=/usr
+BINDIR=$(PREFIX)/bin
+SHAREDIR=$(PREFIX)/share
+SAMTOOLSDIR=samtools
+SEQANDIR=seqan_library
+DINDEL=dindel$(SUFFIX)
 
 CPPFLAGS=-DNDEBUG -D_IOLIB=2 -DMINREADS=2 -DDINDEL
-CXXFLAGS= -I$(SAMTOOLDIR) -I$(SEQANDIR) -I./  -Wno-deprecated  -O3 
-LDFLAGS= -L$(SAMTOOLDIR)  -lbam -lz -lboost_program_options -static 
+CXXFLAGS=-I$(SAMTOOLSDIR) -I$(SEQANDIR) -I./ -Wno-deprecated  -O3 
+LDFLAGS=$(SAMTOOLSDIR)/libbam.a -lz -lboost_program_options -lpthread
 
 SRCSDINDEL=DInDel.cpp HapBlock.cpp HaplotypeDistribution.cpp ObservationModelFB.cpp GetCandidates.cpp Faster.cpp
 OBJSDINDEL=$(SRCSDINDEL:%.cpp=%.o)
 
-dindel:$(OBJSDINDEL) Read.hpp DInDel.hpp HapBlock.hpp Haplotype.hpp HaplotypeDistribution.hpp MyBam.hpp GetCandidates.hpp Variant.hpp Fasta.hpp OutputData.hpp MLAlignment.hpp ObservationModelSeqAn.hpp VariantFile.hpp ReadIndelErrorModel.hpp Library.hpp Faster.hpp
+all: $(DINDEL)
+
+$(DINDEL):$(OBJSDINDEL) Read.hpp DInDel.hpp HapBlock.hpp Haplotype.hpp HaplotypeDistribution.hpp MyBam.hpp GetCandidates.hpp Variant.hpp Fasta.hpp OutputData.hpp MLAlignment.hpp ObservationModelSeqAn.hpp VariantFile.hpp ReadIndelErrorModel.hpp Library.hpp Faster.hpp
 	$(CXX) -o $@ $(CXXFLAGS) $(DINDELFLAGS) $(OBJSDINDEL) $(LDFLAGS) 
 
 clean:
-	rm -f $(OBJSDINDEL) $(OBJSCOMPAREVARIANTS)  $(OBJSMAKEGLF)
+	rm -f $(OBJSDINDEL) $(DINDEL)
+
+DESTBINDIR=$(DESTDIR)$(BINDIR)
+DESTSHAREDIR=$(DESTDIR)$(SHAREDIR)/$(DINDEL)
+
+install: all
+	install -d $(DESTBINDIR) $(DESTSHAREDIR)
+	install $(DINDEL) $(DESTBINDIR)
+	cp -dr --no-preserve=ownership python/* $(DESTSHAREDIR)/

OutputData.hpp

@@ -25,7 +25,7 @@
 #include "StringHash.hpp"
 #include <string>
 #include <iostream>
-#include "foreach.hpp"
+#include <boost/foreach.hpp>
 using namespace std;
 using namespace boost;
 

README

-The source code for Dindel itself is released under GPL3.
-
-In the directory you will find parts of the Boost library (www.boost.org), and
-parts of the Seqan library (www.seqan.de). You will still need to install a copy
-of the Boost library in order for the program_options to compile. The parts of
-the Boost library included in Dindel are there to make it compatible with old
-versions of Boost which didn't have 'foreach.hpp' for instance. The Seqan
-library is included as Dindel uses its Needleman-Wunsch algorithm to align
-candidate haplotypes to the reference sequence.
-
-You will need to download the source code for SAMtools in order to compile
-Dindel. The path to the SAMtools source files can be specified in the Makefile.
-
-If all libraries are in place, simply type "make" at the command line to compile
-Dindel.

README.md

+# dindel-tgi
+
+This is a fork of [dindel-1.01](https://www.sanger.ac.uk/resources/software/dindel/)
+by [The Genome Institute at Washington University](http://genome.wustl.edu).
+It is licensed under the [GNU GPLv3](http://www.gnu.org/copyleft/gpl.html).
+
+[Dindel](https://www.sanger.ac.uk/resources/software/dindel/) was originally
+developed by Cornelis Albers together with Gerton Lunter ([Wellcome Trust Centre for Human Genetics, University of Oxford](http://www.well.ox.ac.uk/home))
+and Richard Durbin ([Wellcome Trust Sanger Institute](https://www.sanger.ac.uk)).  
+
+> Dindel is a program for calling small indels from short-read sequence data
+('next generation sequence data'). It is currently designed to handle only
+Illumina data.
+> 
+> Dindel takes BAM files with mapped Illumina read data and enables researchers
+to detect small indels and produce a VCF file of all the variant calls. It has
+been written in C++ and can be used on Linux-based and Mac computers (it has
+not been tested on Windows operating systems).
+>
+> ---
+>
+> Dindel requires a BAM file containing the read-alignments as input. It then
+extracts candidate indels from the BAM file, and realigns the reads to
+candidate haplotypes consisting of these candidate indels in windows of ~120
+bp. If there is sufficient evidence for an alternative haplotype to the
+reference, it will call an indel.
+>
+> Dindel can test candidate indels discovered with other methods, for instance
+longer deletions found by split-read methods or indels obtained through
+assembly methods. Dindel will then realign both mapped and unmapped reads to
+see if the candidate indel is supported by the reads.
+>
+> Dindel produces a [VCF file](http://vcftools.sourceforge.net/) with the indel
+calls. Genotype likelihoods can be obtained from intermediate files generated
+by Dindel.
+>
+> There is basic support for outputting a realigned BAM file for each
+realignment-window. These realigned BAM files can be used to call SNPs near
+(candidate) indels.
+
+You can find more information, including a [manual](ftp://ftp.sanger.ac.uk/pub/resources/software/dindel/manual-1.01.pdf)
+and the original [source tarball](ftp://ftp.sanger.ac.uk/pub/resources/software/dindel/source_code/dindel-1.01-src.tar.gz),
+on the Wellcome Trust Sanger Institute's [Dindel page](https://www.sanger.ac.uk/resources/software/dindel/).
+You may also be interested in the *Genome Research* 2010 article **Dindel:
+Accurate indel calls from short-read data** (DOI: [10.1101/gr.112326.110](http://dx.doi.org/10.1101%2Fgr.112326.110)).
+
+This fork currently contains a patch to allow sequence data that includes the
+`0x800` flag (supplementary alignment) from newer versions of the [SAM](http://samtools.github.io)
+specification. It also removes the included copy of Boost and adds [samtools-0.1.19](https://github.com/samtools/samtools/tree/0.1.19)
+as a submodule.
+
+## Compiling
+
+This software depends on [Boost](http://www.boost.org), which should probably
+be installed using your packager manager of choice.
+
+This software also depends on [SAMtools](http://samtools.github.io) for SAM
+format support, and [SeqAn](http://www.seqan.de) for aligning candidate
+haplotypes to the reference sequence with the Needleman-Wunsch algorithm. Both
+of these dependencies are included in this repo.
+
+If libboost is installed and the samtools submodule is in place, you
+should be able to compile the `dindel` binary using `make`.
+
+## Packaging
+
+Install dependencies, clone the repository, and run `dpkg-buildpackage`:
+
+```
+$ sudo apt-get update
+$ sudo apt-get install debhelper git-core libboost-dev libboost-program-options-dev libncurses5-dev
+$ git clone https://github.com/genome/dindel-tgi.git dindel-tgi1.01-wu1-1.01-wu1
+$ cd dindel-tgi1.01-wu1-1.01-wu1
+$ git checkout 1.01-wu1-3
+$ dpkg-buildpackage
+```

Read.hpp

@@ -381,7 +381,7 @@ public:
 	{
 		FetchReadData *ptr=(FetchReadData *) data;
 
-		if (!( (b->core.flag & BAM_FDUP) || (b->core.flag & BAM_FQCFAIL) )) {
+		if (!( (b->core.flag & BAM_FDUP) || (b->core.flag & BAM_FQCFAIL) || (b->core.flag & 0x800) )) {
 			try {
 				ptr->reads->push_back(Read(b, *(ptr->libraries), ptr->poolID, (*(ptr->myBams))[ptr->poolID]->bh));
 				ptr->numReads++;

StringHash.hpp

@@ -25,7 +25,7 @@
 #include <ext/hash_map>
 #include <string>
 #include <iostream>
-#include "foreach.hpp"
+#include <boost/foreach.hpp>
 using namespace std;
 using namespace boost;
 using __gnu_cxx::hash;

debian/README.source

@@ -16,3 +16,16 @@ dindel for Debian
 
  -- Steffen Moeller <moeller@debian.org>  Fri, 18 Mar 2016 14:52:14 +0100
 
+
+The source of dindel was moved from Google code to Github:
+
+   https://github.com/genome-vendor/dindel
+
+This was forked to
+
+   https://github.com/genome/dindel-tgi
+
+and received a patch that sounds promising.  Thus this fork is packaged
+now in the Debian package.
+
+ -- Andreas Tille <tille@debian.org>  Mon, 13 Aug 2018 13:41:27 +0200

debian/changelog

-dindel (1.01+dfsg-5) UNRELEASED; urgency=medium
+dindel (1.01-wu1-3+dfsg-1) unstable; urgency=medium
 
+  [ Steffen Moeller ]
   * [debian/upstream/metadata] Added registry ref to
     OMICtools, bio.tools, RRID
 
- -- Steffen Moeller <moeller@debian.org>  Fri, 21 Jul 2017 12:56:45 +0200
+  [ Andreas Tille ]
+  * New upstream version
+  * Package dindel-tgi since this seems to be actively maintained
+    and contains some sensible enhancement.
+  * debhelper 11
+  * Point Vcs fields to salsa.debian.org
+  * Standards-Version: 4.2.0
+  * Update copyright
+
+ -- Andreas Tille <tille@debian.org>  Mon, 13 Aug 2018 14:03:51 +0200
 
 dindel (1.01+dfsg-4) unstable; urgency=medium
 

debian/compat

-9
+11

debian/control

@@ -5,16 +5,16 @@ Uploaders: Animesh Sharma <sharma.animesh@gmail.com>,
            Andreas Tille <tille@debian.org>
 Section: science
 Priority: optional
-Build-Depends: debhelper (>= 9),
+Build-Depends: debhelper (>= 11~),
                seqan-dev (>= 1.4.1),
                libbam-dev,
                libboost-program-options-dev,
                libboost-math-dev,
                zlib1g-dev
-Standards-Version: 3.9.8
-Vcs-Browser: https://anonscm.debian.org/cgit/debian-med/dindel.git
-Vcs-Git: https://anonscm.debian.org/git/debian-med/dindel.git
-Homepage: https://sites.google.com/site/keesalbers/soft/dindel
+Standards-Version: 4.2.0
+Vcs-Browser: https://salsa.debian.org/med-team/dindel
+Vcs-Git: https://salsa.debian.org/med-team/dindel.git
+Homepage: https://github.com/genome/dindel-tgi
 
 Package: dindel
 Architecture: any

debian/copyright

@@ -6,47 +6,16 @@ Files-Excluded: boost
                 seqan_library
 
 Files: *
-Copyright: 2010 Cornelis A. Albers
-                Sanger Center, Cambridge, UK
+Copyright: 2010-2014 Cornelis A. Albers;
+                     Sanger Center, Cambridge, UK;
+                     The McDonnell Genome Institute
 License: GPL-3
 
-Files: digamma.hpp
-Copyright: 2006 John Maddock
-License: Boost
-
-Files: foreach.hpp
-Copyright: 2004 Eric Niebler.
-License: Boost
-
 Files: debian/*
-Copyright: 2016 Animesh Sharma <sharma.animesh@gmail.com>
+Copyright: 2016-2018 Animesh Sharma <sharma.animesh@gmail.com>
                      Andreas Tille <tille@debian.org>
 License: GPL-3
 
-License: Boost
- Permission is hereby granted, free of charge, to any person or
- organization obtaining a copy of the software and accompanying
- documentation covered by this license (the "Software") to use, reproduce,
- display, distribute, execute, and transmit the Software, and to prepare
- derivative works of the Software, and to permit third-parties to whom
- the Software is furnished to do so, all subject to the following:
- .
- The copyright notices in the Software and this entire statement,
- including the above license grant, this restriction and the following
- disclaimer, must be included in all copies of the Software, in whole or
- in part, and all derivative works of the Software, unless such copies
- or derivative works are solely in the form of machine-executable object
- code generated by a source language processor.
- .
- THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
- OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, TITLE AND
- NON-INFRINGEMENT. IN NO EVENT SHALL THE COPYRIGHT HOLDERS OR ANYONE
- DISTRIBUTING THE SOFTWARE BE LIABLE FOR ANY DAMAGES OR OTHER LIABILITY,
- WHETHER IN CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- SOFTWARE.
-
 License: GPL-3
  This package is free software; you can redistribute it and/or modify
  it under the terms of the GNU General Public License as published by

debian/docs

-README
+README*