Makefile

 all: vcflib/Makefile log
 	cd src && $(MAKE)
 
+wbamtools: vcflib/Makefile log
+	cd src && $(MAKE) -f Makefile.bamtools
+
 log: src/version_git.h
 	wget -q http://hypervolu.me/freebayes/build/$(shell cat src/version_git.h | grep v | cut -f 3 -d\  | sed s/\"//g) &
 

README.md

@@ -93,7 +93,6 @@ Luckily, if you have access to https:// on port 443, then you can use this
 ## Compilation
 
 FreeBayes requires g++ and the standard C and C++ development libraries.
-Additionally, cmake is required for building the BamTools API.
 
     make
 
@@ -106,6 +105,12 @@ accomplished via
 
     sudo make install
 
+Note that the freebayes-parallel script and the programs on which it depends are
+not installed by this command.
+
+Users can optionally build with [BamTools](https://github.com/pezmaster31/bamtools) instead of [SeqLib](https://github.com/walaj/SeqLib). Building with BamTools requires CMake.
+
+    make wbamtools
 
 ## Usage
 
@@ -179,7 +184,7 @@ Note that any of the above examples can be made parallel by using the
 scripts/freebayes-parallel script.  If you find freebayes to be slow, you
 should probably be running it in parallel using this script to run on a single
 host, or generating a series of scripts, one per region, and run them on a
-cluster.
+cluster. Be aware that the freebayes-parallel script contains calls to other programs  using relative paths from the scripts subdirectory; the easiest way to ensure a successful run is to invoke the freebayes-parallel script from within the scripts subdirectory.
 
 
 ## Calling variants: from fastq to VCF
@@ -404,7 +409,7 @@ As freebayes is haplotype-based, left-alignment is necessary only for the
 determination of candidate polymorphic loci.  Once such loci are determined, 
 haplotype observations are extracted from reads where:
 
-1. putative variants lie within `--haplotype-window` bases of each other 
+1. putative variants lie within `--haplotype-length` bases of each other 
 (default 3bp),
 2. the reference sequence has repeats (e.g. microsatellites or STRs are called 
 as one haplotype),
@@ -444,7 +449,7 @@ detection window.  We can then use these as "basis alleles" for the observation
 of haplotypes, considering all other putative variants supported by the 
 alignment to be sequencing errors:
 
-    freebayes -f ref.fa --haplotype-window 500 \
+    freebayes -f ref.fa --haplotype-length 500 \
         --haplotype-basis-alleles vars.vcf aln.bam >haps.vcf
 
 These steps should allow us to read long haplotypes directly from input data 
@@ -454,7 +459,7 @@ The high error rate means that beyond a small window each read will contain a
 completely different literal haplotype.  To a point, this property improves our 
 signal to noise ratio and can effectively filter out sequencing errors at the 
 point of the input filters, but it also decreases the effective observation 
-depth will prevent the generation of any calls if a long `--haplotype-window` 
+depth will prevent the generation of any calls if a long `--haplotype-length` 
 is combined with high a sequencing error rate.
 
 

debian/changelog

+freebayes (1.2.0-1) UNRELEASED; urgency=medium
+
+  * New upstream version
+  * Point Vcs fields to salsa.debian.org
+  * Standards-Version: 4.1.4
+
+ -- Andreas Tille <tille@debian.org>  Thu, 26 Apr 2018 15:30:48 +0200
+
 freebayes (1.1.0-2) unstable; urgency=medium
 
   * Versioned Build-Depends: libseqlib-dev (>= 1.1.1+dfsg-4) to include all

debian/control

@@ -17,9 +17,9 @@ Build-Depends: debhelper (>= 11~),
                samtools,
                parallel,
                libvcflib-tools (>= 1.0.0~rc1+dfsg1-6)
-Standards-Version: 4.1.3
-Vcs-Browser: https://anonscm.debian.org/cgit/debian-med/freebayes.git
-Vcs-Git: https://anonscm.debian.org/git/debian-med/freebayes.git
+Standards-Version: 4.1.4
+Vcs-Browser: https://salsa.debian.org/med-team/freebayes
+Vcs-Git: https://salsa.debian.org/med-team/freebayes.git
 Homepage: https://github.com/ekg/freebayes
 
 Package: freebayes

paper/main.blg

-This is BibTeX, Version 0.99d (TeX Live 2015/dev/Debian)
+This is BibTeX, Version 0.99d (TeX Live 2015/Debian)
 Capacity: max_strings=35307, hash_size=35307, hash_prime=30011
 The top-level auxiliary file: main.aux
 The style file: genome_research.bst

src/Allele.cpp

@@ -180,6 +180,7 @@ const short Allele::currentQuality(void) const {
             return quality;
             break;
     }
+    return 0;
 }
 
 const long double Allele::lncurrentQuality(void) const {
@@ -332,19 +333,19 @@ string stringForAlleles(vector<Allele> &alleles) {
     return out.str();
 }
 
-string json(vector<Allele*> &alleles) {
+string tojson(vector<Allele*> &alleles) {
     stringstream out;
     vector<Allele*>::iterator a = alleles.begin();
-    out << "[" << (*a)->json(); ++a;
+    out << "[" << (*a)->tojson(); ++a;
     for (; a != alleles.end(); ++a)
-        out << "," << (*a)->json();
+        out << "," << (*a)->tojson();
     out << "]";
     return out.str();
 }
 
-string json(Allele*& allele) { return allele->json(); }
+string tojson(Allele*& allele) { return allele->tojson(); }
 
-string Allele::json(void) {
+string Allele::tojson(void) {
     stringstream out;
     if (!genotypeAllele) {
         out << "{\"id\":\"" << readID << "\""
@@ -1415,9 +1416,9 @@ int referenceLengthFromCigar(string& cigar) {
         case 'M':
         case 'X':
         case 'D':
-        case 'N':
             r += c->first;
             break;
+        case 'N':
         case 'I':
         default:
             break;
@@ -1434,9 +1435,9 @@ int Allele::referenceLengthFromCigar(void) {
         case 'M':
         case 'X':
         case 'D':
-        case 'N':
             r += c->first;
             break;
+        case 'N':
         case 'I':
         default:
             break;
@@ -1448,30 +1449,21 @@ int Allele::referenceLengthFromCigar(void) {
 
 // combines the two alleles into a complex variant, updates important data
 void Allele::mergeAllele(const Allele& newAllele, AlleleType newType) {
-    //cout << stringForAllele(*this) << endl << stringForAllele(newAllele) << endl;
+    //cerr << stringForAllele(*this) << endl << stringForAllele(newAllele) << endl;
     type = newType;
     alternateSequence += newAllele.alternateSequence;
     length += newAllele.length; // hmmm
     basesRight = newAllele.basesRight;
     baseQualities.insert(baseQualities.end(), newAllele.baseQualities.begin(), newAllele.baseQualities.end());
     currentBase = base();
-    // XXX note that we don't add Q values for intermingled gaps in combined alleles
-    if (newAllele.type != ALLELE_REFERENCE) {
-        quality = min(newAllele.quality, quality);
-        lnquality = max(newAllele.lnquality, lnquality);
-        //quality = minQuality(baseQualities);
-        //lnquality = log(quality);
-    } else {
     quality = averageQuality(baseQualities);
-        lnquality = log(quality);
+    lnquality = phred2ln(quality);
     basesRight += newAllele.referenceLength;
-    }
     if (newAllele.type != ALLELE_REFERENCE) {
         repeatRightBoundary = newAllele.repeatRightBoundary;
     }
     cigar = mergeCigar(cigar, newAllele.cigar);
     referenceLength = referenceLengthFromCigar();
-    //cout << stringForAllele(*this) << endl << endl;
 }
 
 void Allele::squash(void) {

src/Allele.h

@@ -96,10 +96,10 @@ class Allele {
     friend ostream &operator<<(ostream &out, Allele &a);
     friend ostream &operator<<(ostream &out, Allele* &a);
 
-    friend string json(vector<Allele*> &alleles, long int &position);
-    friend string json(vector<Allele*> &alleles);
-    friend string json(Allele &allele, long int &position);
-    friend string json(Allele* &allele);
+    friend string tojson(vector<Allele*> &alleles, long int &position);
+    friend string tojson(vector<Allele*> &alleles);
+    friend string tojson(Allele &allele, long int &position);
+    friend string tojson(Allele* &allele);
 
 public:
 
@@ -262,7 +262,7 @@ public:
                                     //  this is used to update cached data in the allele prior to presenting the allele for analysis
                                     //  for the current base, just use allele.currentBase
 
-    string json(void);
+    string tojson(void);
     unsigned int getLengthOnReference(void);
     int referenceLengthFromCigar(void);
 

src/AlleleParser.h

@@ -77,6 +77,7 @@ public:
     void addAllele(Allele allele, bool mergeComplex = true,
                    int maxComplexGap = 0, bool boundIndels = false);
     bool fitHaplotype(int pos, int haplotypeLength, Allele*& aptr, bool allowPartials = false);
+    void clumpAlleles(bool mergeComplex = true, int maxComplexGap = 0, bool boundIndels = false);
 
 };
 
@@ -249,7 +250,7 @@ public:
     void removeNonOverlappingAlleles(vector<Allele*>& alleles,
                                      int haplotypeLength = 1,
                                      bool getAllAllelesInHaplotype = false);
-    void removePreviousAlleles(vector<Allele*>& alleles);
+    void removePreviousAlleles(vector<Allele*>& alleles, long int position);
     void removeFilteredAlleles(vector<Allele*>& alleles);
     void removeDuplicateAlleles(Samples& samples, map<string, vector<Allele*> >& alleleGroups,
                                 int allowedAlleleTypes, int haplotypeLength, Allele& refallele);

src/CNV.cpp

@@ -6,8 +6,22 @@ bool CNVMap::load(string const& filename) {
     if (cnvFile.is_open()) {
         while (getline (cnvFile, line)) {
             vector<string> fields = split(line, " \t");
+            if (fields.size() == 2) {
+                const string& sample = fields.at(0);
+                int ploidy = atoi(fields.at(1).c_str());
+                setSamplePloidy(sample, ploidy);
+            } else if (fields.size() == 5) {
                 // note conversion between 1 and 0 based
-            setPloidy(fields.at(3), fields.at(0), atol(fields.at(1).c_str()), atol(fields.at(2).c_str()), atoi(fields.at(4).c_str()));
+                const string& sample = fields.at(3);
+                const string& seq = fields.at(0);
+                long int start = atol(fields.at(1).c_str());
+                long int end = atol(fields.at(2).c_str());
+                int ploidy = atoi(fields.at(4).c_str());
+                setPloidy(sample, seq, start, end, ploidy);
+            } else {
+                cerr << "error [freebayes::CNVMap] could not parse CNVmap line " << line << endl;
+                exit(1);
+            }
         }
     } else {
         return false;
@@ -19,24 +33,30 @@ void CNVMap::setDefaultPloidy(int defploidy) {
     defaultPloidy = defploidy;
 }
 
+void CNVMap::setSamplePloidy(const string& sample, int ploidy) {
+    samplePloidy[sample] = ploidy;
+}
+
 void CNVMap::setPloidy(string const& sample, string const& seq, long int start, long int end, int ploidy) {
     sampleSeqCNV[sample][seq][make_pair(start, end)] = ploidy;
 }
 
 int CNVMap::ploidy(string const& sample, string const& seq, long int position) {
 
+    int basePloidy = (samplePloidy.find(sample) != samplePloidy.end()) ? samplePloidy[sample] : defaultPloidy;
+
     if (sampleSeqCNV.empty()) {
-        return defaultPloidy;
+        return basePloidy;
     }
 
     SampleSeqCNVMap::iterator scnv = sampleSeqCNV.find(sample);
 
     if (scnv == sampleSeqCNV.end()) {
-        return defaultPloidy;
+        return basePloidy;
     } else {
         map<string, map<pair<long int, long int>, int> >::iterator c = scnv->second.find(seq);
         if (c == scnv->second.end()) {
-            return defaultPloidy;
+            return basePloidy;
         } else {
             map<pair<long int, long int>, int>& cnvs = c->second;
             for (map<pair<long int, long int>, int>::iterator i = cnvs.begin(); i != cnvs.end(); ++i) {
@@ -50,7 +70,7 @@ int CNVMap::ploidy(string const& sample, string const& seq, long int position) {
                     break;
                 }
             }
-            return defaultPloidy;
+            return basePloidy;
         }
     }
 

src/CNV.h

@@ -19,6 +19,7 @@ class CNVMap {
 public:
     CNVMap(void) : defaultPloidy(2) { }
     void setDefaultPloidy(int defploidy);
+    void setSamplePloidy(const string& sample, int ploidy);
     bool load(string const& filename);
     int ploidy(string const& sample, string const& seq, long int position);
     void setPloidy(string const& sample, string const& seq, long int start, long int end, int ploidy);
@@ -27,6 +28,7 @@ private:
     // note: this map is stored as 0-based, end position exclusive
     SampleSeqCNVMap sampleSeqCNV;
     int defaultPloidy;
+    map<string, int> samplePloidy;
 
 };
 

src/DataLikelihood.cpp

 #include "DataLikelihood.h"
 #include "multichoose.h"
 #include "multipermute.h"
-
+#include "Logging.h"
 
 long double
 probObservedAllelesGivenGenotype(
         Sample& sample,
         Genotype& genotype,
-        double dependenceFactor,
-        bool useMapQ,
         Bias& observationBias,
-        bool standardGLs,
         vector<Allele>& genotypeAlleles,
         Contamination& contaminations,
-        map<string, double>& freqs
+        map<string, double>& freqs,
+        Parameters& parameters
     ) {
 
-    //cerr << "P(" << genotype << " given" << endl <<  sample;
+    DEBUG2("P(" << genotype << " given" << endl <<  sample);
 
     int observationCount = sample.observationCount();
     vector<long double> alleleProbs = genotype.alleleProbabilities(observationBias);
@@ -26,12 +24,12 @@ probObservedAllelesGivenGenotype(
     long double prodQout = 0;  // the probability that the reads not in the genotype are all wrong
     long double prodSample = 0;
     
-    if (standardGLs) {
+    if (parameters.standardGLs) {
         for (Sample::iterator s = sample.begin(); s != sample.end(); ++s) {
             const string& base = s->first;
             if (!genotype.containsAllele(base)) {
                 vector<Allele*>& alleles = s->second;
-                if (useMapQ) {
+                if (parameters.useMappingQuality) {
                     for (vector<Allele*>::iterator a = alleles.begin(); a != alleles.end(); ++a) {
                         // take the lesser of mapping quality and base quality (in log space)
                         prodQout += max((*a)->lnquality, (*a)->lnmapQuality);
@@ -71,7 +69,7 @@ probObservedAllelesGivenGenotype(
                     }
                 }
                 Allele& obs = **a;
-                //cerr << "observation: " << obs << endl;
+                DEBUG2("observation: " << obs);
                 long double probi = 0;
                 ContaminationEstimate& contamination = contaminations.of(obs.readGroupID);
                 double scale = 1;
@@ -86,10 +84,12 @@ probObservedAllelesGivenGenotype(
                             cerr << "partial " << *a << " has empty reverse" << endl;
                             exit(1);
                         }
-                        //cerr << "partial " << *a << " supports potentially " << sample.reversePartials[*a].size() << " alleles : " << endl;
-                        //for (set<Allele*>::iterator m = sample.reversePartials[*a].begin();
-                        //m != sample.reversePartials[*a].end(); ++m) cerr << **m << " ";
-                        //cerr << endl;
+
+                        DEBUG2("partial " << *a << " supports potentially " << sample.reversePartials[*a].size() << " alleles : ");
+                        for (set<Allele*>::iterator m = sample.reversePartials[*a].begin();
+                             m != sample.reversePartials[*a].end(); ++m)
+                            DEBUG2(**m << " ");
+
                         scale = (double)1/(double)sample.reversePartials[*a].size();
                         qual *= scale;
                     }
@@ -143,10 +143,10 @@ probObservedAllelesGivenGenotype(
     }
 
     // read dependence factor, asymptotically downgrade quality values of
-    // successive reads to dependenceFactor * quality
-    if (standardGLs) {
+    // successive reads to parameters.RDF * quality
+    if (parameters.standardGLs) {
         if (countOut > 1) {
-            prodQout *= (1 + (countOut - 1) * dependenceFactor) / countOut;
+            prodQout *= (1 + (countOut - 1) * parameters.RDF) / countOut;
         }
 
         if (sum(observationCounts) == 0) {
@@ -158,7 +158,7 @@ probObservedAllelesGivenGenotype(
         }
     } else {
         if (countOut > 1) {
-            prodQout *= (1 + (countOut - 1) * dependenceFactor) / countOut;
+            prodQout *= (1 + (countOut - 1) * parameters.RDF) / countOut;
         }
         long double probObsGivenGt = prodQout + prodSample;
         return isinf(probObsGivenGt) ? 0 : probObsGivenGt;
@@ -171,13 +171,11 @@ vector<pair<Genotype*, long double> >
 probObservedAllelesGivenGenotypes(
         Sample& sample,
         vector<Genotype*>& genotypes,
-        double dependenceFactor,
-        bool useMapQ,
         Bias& observationBias,
-        bool standardGLs,
         vector<Allele>& genotypeAlleles,
         Contamination& contaminations,
-        map<string, double>& freqs
+        map<string, double>& freqs,
+        Parameters& parameters
     ) {
     vector<pair<Genotype*, long double> > results;
     for (vector<Genotype*>::iterator g = genotypes.begin(); g != genotypes.end(); ++g) {
@@ -187,13 +185,11 @@ probObservedAllelesGivenGenotypes(
                   probObservedAllelesGivenGenotype(
                       sample,
                       **g,
-                      dependenceFactor,
-                      useMapQ,
                       observationBias,
-                      standardGLs,
                       genotypeAlleles,
                       contaminations,
-                      freqs)));
+                      freqs,
+                      parameters)));
     }
     return results;
 }
@@ -252,21 +248,18 @@ calculateSampleDataLikelihoods(
         }
 
         vector<pair<Genotype*, long double> > probs
-            = probObservedAllelesGivenGenotypes(sample, genotypesWithObs,
-                                                parameters.RDF, parameters.useMappingQuality,
-                                                observationBias, parameters.standardGLs,
+            = probObservedAllelesGivenGenotypes(sample,
+                                                genotypesWithObs,
+                                                observationBias,
                                                 genotypeAlleles,
                                                 contaminationEstimates,
-                                                estimatedAlleleFrequencies);
+                                                estimatedAlleleFrequencies,
+                                                parameters);
             
-#ifdef VERBOSE_DEBUG
-        if (parameters.debug2) {
         for (vector<pair<Genotype*, long double> >::iterator p = probs.begin(); p != probs.end(); ++p) {
-                cerr << parser->currentSequenceName << "," << (long unsigned int) parser->currentPosition + 1 << ","
-                     << sampleName << ",likelihood," << *(p->first) << "," << p->second << endl;
-            }
+            DEBUG2(parser->currentSequenceName << "," << (long unsigned int) parser->currentPosition + 1 << ","
+                   << sampleName << ",likelihood," << *(p->first) << "," << p->second);
         }
-#endif
 
         Result& sampleData = results[sampleName];
         sampleData.name = sampleName;

src/DataLikelihood.h

@@ -26,25 +26,21 @@ long double
 probObservedAllelesGivenGenotype(
         Sample& sample,
         Genotype& genotype,
-        double dependenceFactor,
-        bool useMapQ,
         Bias& observationBias,
-        bool standardGLs,
         vector<Allele>& genotypeAlleles,
         Contamination& contaminations,
-        map<string, double>& freqs);
+        map<string, double>& freqs,
+        Parameters& parameters);
 
 vector<pair<Genotype*, long double> >
 probObservedAllelesGivenGenotypes(
         Sample& sample,
         vector<Genotype*>& genotypes,
-        double dependenceFactor,
-        bool useMapQ,
         Bias& observationBias,
-        bool standardGLs,
         vector<Allele>& genotypeAlleles,
         Contamination& contaminations,
-        map<string, double>& freqs);
+        map<string, double>& freqs,
+        Parameters& parameters);
 
 void
 calculateSampleDataLikelihoods(

src/Fasta.cpp

@@ -87,6 +87,7 @@ ostream& operator<<(ostream& output, FastaIndex& fastaIndex) {
     for( vector<FastaIndexEntry>::iterator fit = sortedIndex.begin(); fit != sortedIndex.end(); ++fit) {
         output << *fit << endl;
     }
+    return output;
 }
 
 void FastaIndex::indexReference(string refname) {

src/LargeFileSupport.h

@@ -4,6 +4,10 @@
 #define ftell64(a)     _ftelli64(a)
 #define fseek64(a,b,c) _fseeki64(a,b,c)
 typedef __int64 off_type;
+#elif defined(__CYGWIN__)
+#define ftell64(a)     ftell(a)
+#define fseek64(a,b,c) fseek(a,b,c)
+typedef __int64_t off_type;
 #elif defined(__APPLE__)
 #define ftell64(a)     ftello(a)
 #define fseek64(a,b,c) fseeko(a,b,c)

src/LeftAlign.h

@@ -94,7 +94,7 @@ using namespace BamTools;
 #define CIGTYPE Type()
 #define ADDCIGAR add
 #define CIGOP SeqLib::CigarField
-#define FILLREADGROUP(rg, align) (rg) = (align).GetZTag("RG")
+#define FILLREADGROUP(rg, align) (align).GetZTag("RG", rg)
 #define GETHEADERTEXT HeaderConcat()
 #include "SeqLib/BamReader.h"
 #include "SeqLib/BamWriter.h"

src/Logging.h

+#ifndef LOGGING_H
+#define LOGGING_H
+
+// helper debugging macros to improve code readability
+#define DEBUG(msg) \
+    if (parameters.debug) { cerr << msg << endl; }
+
+// lower-priority messages, enabled with "make debug"
+#ifdef VERBOSE_DEBUG
+#define DEBUG2(msg) \
+    if (parameters.debug2) { cerr << msg << endl; }
+#else
+#define DEBUG2(msg)
+#endif
+
+// must-see error messages
+#define ERROR(msg) \
+    cerr << "ERROR(freebayes): " << msg << endl;
+
+// must-see warning messages
+#define WARNING(msg) \
+    cerr << "WARNING(freebayes): " << msg << endl;
+
+#endif

src/Makefile

@@ -5,41 +5,46 @@
 ################################################################################
 
 # Compiler
-CXX=g++
+CXX=g++ ${CXXFLAGS}
 C=gcc
 
+export CXXFLAGS
+export C
+export CC
+export CXX
+export LDFLAGS
+export LIBFLAGS
+
 # Compiler flags
+
 CFLAGS=-O3 -D_FILE_OFFSET_BITS=64 -g
 #CFLAGS=-O3 -static -D VERBOSE_DEBUG  # enables verbose debugging via --debug2
 
-BAMTOOLS_ROOT=../bamtools
 SEQLIB_ROOT=../SeqLib
 VCFLIB_ROOT=../vcflib
 TABIX_ROOT=$(VCFLIB_ROOT)/tabixpp
-HTSLIB_ROOT=$(TABIX_ROOT)/htslib
+HTSLIB_ROOT=$(SEQLIB_ROOT)/htslib
 
-LIBS = -lz -lm -lpthread
-INCLUDE = -I../ttmath -I$(BAMTOOLS_ROOT)/src/ -I$(VCFLIB_ROOT)/src/ -I$(TABIX_ROOT)/ -I$(VCFLIB_ROOT)/smithwaterman/ -I$(VCFLIB_ROOT)/multichoose/ -I$(VCFLIB_ROOT)/filevercmp/ -I$(HTSLIB_ROOT) -I$(SEQLIB_ROOT) -I$(SEQLIB_ROOT)/htslib
+LIBS = -lz -llzma -lbz2 -lm -lpthread
+INCLUDE = -I../src -I../ttmath -I$(VCFLIB_ROOT)/src/ -I$(VCFLIB_ROOT)/smithwaterman/ -I$(VCFLIB_ROOT)/multichoose/ -I$(VCFLIB_ROOT)/filevercmp/ -I$(VCFLIB_ROOT)/fastahack/ -I$(HTSLIB_ROOT) -I$(SEQLIB_ROOT) 
+#INCLUDE = -I../ttmath -I$(BAMTOOLS_ROOT)/src/ -I$(VCFLIB_ROOT)/src/ -I$(TABIX_ROOT)/ -I$(VCFLIB_ROOT)/smithwaterman/ -I$(VCFLIB_ROOT)/multichoose/ -I$(VCFLIB_ROOT)/filevercmp/ -I$(VCFLIB_ROOT)/fastahack/ -I$(HTSLIB_ROOT) -I$(SEQLIB_ROOT) -I$(SEQLIB_ROOT)/htslib
 
 all: autoversion ../bin/freebayes ../bin/bamleftalign
 
 static:
-	$(MAKE) CFLAGS="$(CFLAGS) -static" all
+	$(MAKE) CXXFLAGS="$(CXXFLAGS) -static" all
 
 debug:
-	$(MAKE) CFLAGS="$(CFLAGS) -D VERBOSE_DEBUG -g -rdynamic" all
+	$(MAKE) CXXFLAGS="$(CXXFLAGS) -D VERBOSE_DEBUG -g -rdynamic" all
 
 profiling:
 	$(MAKE) CFLAGS="$(CFLAGS) -g" all
 
 gprof:
-	$(MAKE) CFLAGS="$(CFLAGS) -pg" all
+	$(MAKE) CXXFLAGS="$(CXXFLAGS) -pg" all
 
 .PHONY: all static debug profiling gprof
 
-# builds bamtools static lib, and copies into root
-$(BAMTOOLS_ROOT)/lib/libbamtools.a:
-	cd $(BAMTOOLS_ROOT) && mkdir -p build && cd build && cmake .. && $(MAKE)
 $(HTSLIB_ROOT)/libhts.a:
 	cd $(HTSLIB_ROOT) && make
 
@@ -71,14 +76,12 @@ OBJECTS=BedReader.o \
 		NonCall.o \
 		SegfaultHandler.o \
 		../vcflib/tabixpp/tabix.o \
-		../vcflib/tabixpp/htslib/bgzf.o \
 		../vcflib/smithwaterman/SmithWatermanGotoh.o \
 		../vcflib/smithwaterman/disorder.cpp \
 		../vcflib/smithwaterman/LeftAlign.o \
 		../vcflib/smithwaterman/Repeats.o \
 		../vcflib/smithwaterman/IndelAllele.o \
 		Variant.o \
-		$(BAMTOOLS_ROOT)/lib/libbamtools.a \
 		$(SEQLIB_ROOT)/src/libseqlib.a	\
 		$(SEQLIB_ROOT)/bwa/libbwa.a	\
 		$(SEQLIB_ROOT)/fermi-lite/libfml.a	\
@@ -88,115 +91,114 @@ HEADERS=multichoose.h version_git.h
 
 # executables
 
-freebayes ../bin/freebayes: freebayes.o $(OBJECTS) $(HEADERS)
-	$(CXX) $(CFLAGS) $(INCLUDE) freebayes.o $(OBJECTS) -o ../bin/freebayes $(LIBS)
+freebayes ../bin/freebayes: freebayes.o $(OBJECTS) $(HEADERS) $(seqlib)
+	$(CXX) $(CXXFLAGS) $(INCLUDE) freebayes.o $(OBJECTS) -o ../bin/freebayes $(LIBS)
 
-alleles ../bin/alleles: alleles.o $(OBJECTS) $(HEADERS)
-	$(CXX) $(CFLAGS) $(INCLUDE) alleles.o $(OBJECTS) -o ../bin/alleles $(LIBS)
+alleles ../bin/alleles: alleles.o $(OBJECTS) $(HEADERS) $(seqlib)
+	$(CXX) $(CXXFLAGS) $(INCLUDE) alleles.o $(OBJECTS) -o ../bin/alleles $(LIBS)
 
-dummy ../bin/dummy: dummy.o $(OBJECTS) $(HEADERS)
-	$(CXX) $(CFLAGS) $(INCLUDE) dummy.o $(OBJECTS) -o ../bin/dummy $(LIBS)
+dummy ../bin/dummy: dummy.o $(OBJECTS) $(HEADERS) $(seqlib)
+	$(CXX) $(CXXFLAGS) $(INCLUDE) dummy.o $(OBJECTS) -o ../bin/dummy $(LIBS)
 
-bamleftalign ../bin/bamleftalign: $(BAMTOOLS_ROOT)/lib/libbamtools.a $(SEQLIB_ROOT)/src/libseqlib.a $(SEQLIB_ROOT)/htslib/libhts.a bamleftalign.o Fasta.o LeftAlign.o IndelAllele.o split.o
-	$(CXX) $(CFLAGS) $(INCLUDE) bamleftalign.o Fasta.o Utility.o LeftAlign.o IndelAllele.o split.o $(BAMTOOLS_ROOT)/lib/libbamtools.a $(SEQLIB_ROOT)/src/libseqlib.a $(SEQLIB_ROOT)/htslib/libhts.a -o ../bin/bamleftalign $(LIBS)
+bamleftalign ../bin/bamleftalign: $(SEQLIB_ROOT)/src/libseqlib.a $(HTSLIB_ROOT)/libhts.a bamleftalign.o Fasta.o LeftAlign.o IndelAllele.o split.o
+	$(CXX) $(CXXFLAGS) $(INCLUDE) bamleftalign.o $(OBJECTS) -o ../bin/bamleftalign $(LIBS)
 
-bamfiltertech ../bin/bamfiltertech: $(BAMTOOLS_ROOT)/lib/libbamtools.a $(SEQLIB_ROOT)/src/libseqlib.a $(SEQLIB_ROOT)/htslib/libhts.a bamfiltertech.o $(OBJECTS) $(HEADERS)
-	$(CXX) $(CFLAGS) $(INCLUDE) bamfiltertech.o $(OBJECTS) -o ../bin/bamfiltertech $(LIBS)
+bamfiltertech ../bin/bamfiltertech: $(SEQLIB_ROOT)/src/libseqlib.a $(HTSLIB_ROOT)/libhts.a bamfiltertech.o $(OBJECTS) $(HEADERS)
+	$(CXX) $(CXXFLAGS) $(INCLUDE) bamfiltertech.o $(OBJECTS) -o ../bin/bamfiltertech $(LIBS)
 
 
 # objects
 
 Fasta.o: Fasta.cpp Utility.o
-	$(CXX) $(CFLAGS) $(INCLUDE) -c Fasta.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c Fasta.cpp
 
 alleles.o: alleles.cpp AlleleParser.o Allele.o
-	$(CXX) $(CFLAGS) $(INCLUDE) -c alleles.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c alleles.cpp
 
 dummy.o: dummy.cpp AlleleParser.o Allele.o
-	$(CXX) $(CFLAGS) $(INCLUDE) -c dummy.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c dummy.cpp
 
-freebayes.o: freebayes.cpp TryCatch.h $(HTSLIB_ROOT)/libhts.a $(BAMTOOLS_ROOT)/lib/libbamtools.a
-	$(CXX) $(CFLAGS) $(INCLUDE) -c freebayes.cpp
+freebayes.o: freebayes.cpp TryCatch.h $(HTSLIB_ROOT)/libhts.a ../vcflib/tabixpp/tabix.o
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c freebayes.cpp
 
 fastlz.o: fastlz.c fastlz.h
 	$(C) $(CFLAGS) $(INCLUDE) -c fastlz.c	
 
 Parameters.o: Parameters.cpp Parameters.h Version.h
-	$(CXX) $(CFLAGS) $(INCLUDE) -c Parameters.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c Parameters.cpp
 
 Allele.o: Allele.cpp Allele.h multichoose.h Genotype.h
-	$(CXX) $(CFLAGS) $(INCLUDE) -c Allele.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c Allele.cpp
 
 Sample.o: Sample.cpp Sample.h
-	$(CXX) $(CFLAGS) $(INCLUDE) -c Sample.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c Sample.cpp
 
 Genotype.o: Genotype.cpp Genotype.h Allele.h multipermute.h
-	$(CXX) $(CFLAGS) $(INCLUDE) -c Genotype.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c Genotype.cpp
 
 Ewens.o: Ewens.cpp Ewens.h
-	$(CXX) $(CFLAGS) $(INCLUDE) -c Ewens.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c Ewens.cpp
 
-AlleleParser.o: AlleleParser.cpp AlleleParser.h multichoose.h Parameters.h $(BAMTOOLS_ROOT)/lib/libbamtools.a $(HTSLIB_ROOT)/libhts.a
-	$(CXX) $(CFLAGS) $(INCLUDE) -c AlleleParser.cpp
+AlleleParser.o: AlleleParser.cpp AlleleParser.h multichoose.h Parameters.h $(HTSLIB_ROOT)/libhts.a
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c AlleleParser.cpp
 
 Utility.o: Utility.cpp Utility.h Sum.h Product.h
-	$(CXX) $(CFLAGS) $(INCLUDE) -c Utility.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c Utility.cpp
 
 SegfaultHandler.o: SegfaultHandler.cpp SegfaultHandler.h
-	$(CXX) $(CFLAGS) $(INCLUDE) -c SegfaultHandler.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c SegfaultHandler.cpp
 
 Dirichlet.o: Dirichlet.h Dirichlet.cpp Sum.h Product.h
-	$(CXX) $(CFLAGS) $(INCLUDE) -c Dirichlet.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c Dirichlet.cpp
 
 Multinomial.o: Multinomial.h Multinomial.cpp Sum.h Product.h Utility.h
-	$(CXX) $(CFLAGS) $(INCLUDE) -c Multinomial.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c Multinomial.cpp
 
 DataLikelihood.o: DataLikelihood.cpp DataLikelihood.h Sum.h Product.h
-	$(CXX) $(CFLAGS) $(INCLUDE) -c DataLikelihood.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c DataLikelihood.cpp
 
 Marginals.o: Marginals.cpp Marginals.h
-	$(CXX) $(CFLAGS) $(INCLUDE) -c Marginals.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c Marginals.cpp
 
 ResultData.o: ResultData.cpp ResultData.h Result.h Result.cpp Allele.h Utility.h Genotype.h AlleleParser.h Version.h
-	$(CXX) $(CFLAGS) $(INCLUDE) -c ResultData.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c ResultData.cpp
 
 Result.o: Result.cpp Result.h
-	$(CXX) $(CFLAGS) $(INCLUDE) -c Result.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c Result.cpp
 
 NonCall.o: NonCall.cpp NonCall.h
-	$(CXX) $(CFLAGS) $(INCLUDE) -c NonCall.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c NonCall.cpp
 
 BedReader.o: BedReader.cpp BedReader.h
-	$(CXX) $(CFLAGS) $(INCLUDE) -c BedReader.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c BedReader.cpp
 
 CNV.o: CNV.cpp CNV.h
-	$(CXX) $(CFLAGS) $(INCLUDE) -c CNV.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c CNV.cpp
 
 Bias.o: Bias.cpp Bias.h
-	$(CXX) $(CFLAGS) $(INCLUDE) -c Bias.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c Bias.cpp
 
 split.o: split.h split.cpp
-	$(CXX) $(CFLAGS) $(INCLUDE) -c split.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c split.cpp
 
 bamleftalign.o: bamleftalign.cpp LeftAlign.cpp
-	$(CXX) $(CFLAGS) $(INCLUDE) -c bamleftalign.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c bamleftalign.cpp
 
 bamfiltertech.o: bamfiltertech.cpp
-	$(CXX) $(CFLAGS) $(INCLUDE) -c bamfiltertech.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c bamfiltertech.cpp
 
-LeftAlign.o: LeftAlign.h LeftAlign.cpp $(BAMTOOLS_ROOT)/lib/libbamtools.a $(HTSLIB_ROOT)/libhts.a
-	$(CXX) $(CFLAGS) $(INCLUDE) -c LeftAlign.cpp
+LeftAlign.o: LeftAlign.h LeftAlign.cpp $(HTSLIB_ROOT)/libhts.a
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c LeftAlign.cpp
 
 IndelAllele.o: IndelAllele.cpp IndelAllele.h
-	$(CXX) $(CFLAGS) $(INCLUDE) -c IndelAllele.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c IndelAllele.cpp
 
 Variant.o: $(VCFLIB_ROOT)/src/Variant.h $(VCFLIB_ROOT)/src/Variant.cpp
-	$(CXX) $(CFLAGS) $(INCLUDE) -c $(VCFLIB_ROOT)/src/Variant.cpp
+	$(CXX) $(CXXFLAGS) $(INCLUDE) -c $(VCFLIB_ROOT)/src/Variant.cpp
+#	$(CXX) -std=c++11 $(CFLAGS) $(INCLUDE) -c $(VCFLIB_ROOT)/src/Variant.cpp
 
 ../vcflib/tabixpp/tabix.o:
-	cd $(TABIX_ROOT)/ && make
-../vcflib/tabixpp/htslib/bgzf.o: ../vcflib/tabixpp/htslib/bgzf.c ../vcflib/tabixpp/htslib/htslib/bgzf.h
-	cd ../vcflib/tabixpp && $(MAKE)
+	cd $(TABIX_ROOT)/ && $(MAKE) && cp tabix.hpp ../../src/
 
 ../vcflib/smithwaterman/SmithWatermanGotoh.o: ../vcflib/smithwaterman/SmithWatermanGotoh.h ../vcflib/smithwaterman/SmithWatermanGotoh.cpp
 	cd ../vcflib/smithwaterman && $(MAKE)
@@ -274,7 +276,6 @@ autoversion:
 
 
 clean:
-	rm -rf *.o *.cgh *~ freebayes alleles ../bin/freebayes ../bin/alleles ../vcflib/*.o ../vcflib/tabixpp/*.{o,a}
-	cd $(BAMTOOLS_ROOT)/build && make clean
-	cd ../vcflib/smithwaterman && make clean
-
+	rm -rf *.o *.cgh *~ freebayes alleles ../bin/freebayes ../bin/alleles ../vcflib/*.o ../vcflib/tabixpp/*.{o,a} tabix.hpp
+	if [ -d $(BAMTOOLS_ROOT)/build ]; then make -C $(BAMTOOLS_ROOT)/build clean; fi
+	make -C $(VCFLIB_ROOT)/smithwaterman clean

src/Makefile.bamtools

+################################################################################
+# Makefile for FreeBayes
+# Erik Garrison, 2010
+# Boston College
+################################################################################
+
+# Compiler
+CXX=g++
+C=gcc
+
+# Compiler flags
+CFLAGS=-O3 -D_FILE_OFFSET_BITS=64 -g
+#CFLAGS=-O3 -static -D VERBOSE_DEBUG  # enables verbose debugging via --debug2
+
+BAMTOOLS_ROOT=../bamtools
+VCFLIB_ROOT=../vcflib
+TABIX_ROOT=$(VCFLIB_ROOT)/tabixpp
+HTSLIB_ROOT=$(TABIX_ROOT)/htslib
+
+LIBS = -lz -lm -lpthread
+INCLUDE = -I../ttmath -I$(BAMTOOLS_ROOT)/src/ -I$(VCFLIB_ROOT)/src/ -I$(TABIX_ROOT)/ -I$(VCFLIB_ROOT)/smithwaterman/ -I$(VCFLIB_ROOT)/multichoose/ -I$(VCFLIB_ROOT)/filevercmp/ -I$(HTSLIB_ROOT) -DHAVE_BAMTOOLS=1
+
+all: autoversion ../bin/freebayes ../bin/bamleftalign
+
+static:
+	$(MAKE) CFLAGS="$(CFLAGS) -static" all
+
+debug:
+	$(MAKE) CFLAGS="$(CFLAGS) -D VERBOSE_DEBUG -g -rdynamic" all
+
+profiling:
+	$(MAKE) CFLAGS="$(CFLAGS) -g" all
+
+gprof:
+	$(MAKE) CFLAGS="$(CFLAGS) -pg" all
+
+.PHONY: all static debug profiling gprof
+
+# builds bamtools static lib, and copies into root
+$(BAMTOOLS_ROOT)/lib/libbamtools.a:
+	cd $(BAMTOOLS_ROOT) && mkdir -p build && cd build && cmake .. && $(MAKE)
+$(HTSLIB_ROOT)/libhts.a:
+	cd $(HTSLIB_ROOT) && make
+
+OBJECTS=BedReader.o \
+		CNV.o \
+		fastlz.o \
+		Fasta.o \
+		Parameters.o \
+		Allele.o \
+		Sample.o \
+		Result.o \
+		AlleleParser.o \
+		Utility.o \
+		Genotype.o \
+		DataLikelihood.o \
+		Multinomial.o \
+		Ewens.o \
+		ResultData.o \
+		Dirichlet.o \
+		Marginals.o \
+		split.o \
+		LeftAlign.o \
+		IndelAllele.o \
+		Bias.o \
+		Contamination.o \
+		NonCall.o \
+		SegfaultHandler.o \
+		../vcflib/tabixpp/tabix.o \
+		../vcflib/tabixpp/htslib/bgzf.o \
+		../vcflib/smithwaterman/SmithWatermanGotoh.o \
+		../vcflib/smithwaterman/disorder.cpp \
+		../vcflib/smithwaterman/LeftAlign.o \
+		../vcflib/smithwaterman/Repeats.o \
+		../vcflib/smithwaterman/IndelAllele.o \
+		Variant.o \
+		$(BAMTOOLS_ROOT)/lib/libbamtools.a \
+		$(TABIX_ROOT)/htslib/libhts.a
+
+HEADERS=multichoose.h version_git.h
+
+# executables
+
+freebayes ../bin/freebayes: freebayes.o $(OBJECTS) $(HEADERS)
+	$(CXX) $(CFLAGS) $(INCLUDE) freebayes.o $(OBJECTS) -o ../bin/freebayes $(LIBS)
+
+alleles ../bin/alleles: alleles.o $(OBJECTS) $(HEADERS)
+	$(CXX) $(CFLAGS) $(INCLUDE) alleles.o $(OBJECTS) -o ../bin/alleles $(LIBS)
+
+dummy ../bin/dummy: dummy.o $(OBJECTS) $(HEADERS)
+	$(CXX) $(CFLAGS) $(INCLUDE) dummy.o $(OBJECTS) -o ../bin/dummy $(LIBS)
+
+bamleftalign ../bin/bamleftalign: $(BAMTOOLS_ROOT)/lib/libbamtools.a bamleftalign.o Fasta.o LeftAlign.o IndelAllele.o split.o
+	$(CXX) $(CFLAGS) $(INCLUDE) bamleftalign.o Fasta.o Utility.o LeftAlign.o IndelAllele.o split.o $(BAMTOOLS_ROOT)/lib/libbamtools.a -o ../bin/bamleftalign $(LIBS)
+
+bamfiltertech ../bin/bamfiltertech: $(BAMTOOLS_ROOT)/lib/libbamtools.a bamfiltertech.o $(OBJECTS) $(HEADERS)
+	$(CXX) $(CFLAGS) $(INCLUDE) bamfiltertech.o $(OBJECTS) -o ../bin/bamfiltertech $(LIBS)
+
+
+# objects
+
+Fasta.o: Fasta.cpp Utility.o
+	$(CXX) $(CFLAGS) $(INCLUDE) -c Fasta.cpp
+
+alleles.o: alleles.cpp AlleleParser.o Allele.o
+	$(CXX) $(CFLAGS) $(INCLUDE) -c alleles.cpp
+
+dummy.o: dummy.cpp AlleleParser.o Allele.o
+	$(CXX) $(CFLAGS) $(INCLUDE) -c dummy.cpp
+
+freebayes.o: freebayes.cpp TryCatch.h $(HTSLIB_ROOT)/libhts.a $(BAMTOOLS_ROOT)/lib/libbamtools.a
+	$(CXX) $(CFLAGS) $(INCLUDE) -c freebayes.cpp
+
+fastlz.o: fastlz.c fastlz.h
+	$(C) $(CFLAGS) $(INCLUDE) -c fastlz.c	
+
+Parameters.o: Parameters.cpp Parameters.h Version.h
+	$(CXX) $(CFLAGS) $(INCLUDE) -c Parameters.cpp
+
+Allele.o: Allele.cpp Allele.h multichoose.h Genotype.h
+	$(CXX) $(CFLAGS) $(INCLUDE) -c Allele.cpp
+
+Sample.o: Sample.cpp Sample.h
+	$(CXX) $(CFLAGS) $(INCLUDE) -c Sample.cpp
+
+Genotype.o: Genotype.cpp Genotype.h Allele.h multipermute.h
+	$(CXX) $(CFLAGS) $(INCLUDE) -c Genotype.cpp
+
+Ewens.o: Ewens.cpp Ewens.h
+	$(CXX) $(CFLAGS) $(INCLUDE) -c Ewens.cpp
+
+AlleleParser.o: AlleleParser.cpp AlleleParser.h multichoose.h Parameters.h $(BAMTOOLS_ROOT)/lib/libbamtools.a $(HTSLIB_ROOT)/libhts.a
+	$(CXX) $(CFLAGS) $(INCLUDE) -c AlleleParser.cpp
+
+Utility.o: Utility.cpp Utility.h Sum.h Product.h
+	$(CXX) $(CFLAGS) $(INCLUDE) -c Utility.cpp
+
+SegfaultHandler.o: SegfaultHandler.cpp SegfaultHandler.h
+	$(CXX) $(CFLAGS) $(INCLUDE) -c SegfaultHandler.cpp
+
+Dirichlet.o: Dirichlet.h Dirichlet.cpp Sum.h Product.h
+	$(CXX) $(CFLAGS) $(INCLUDE) -c Dirichlet.cpp
+
+Multinomial.o: Multinomial.h Multinomial.cpp Sum.h Product.h Utility.h
+	$(CXX) $(CFLAGS) $(INCLUDE) -c Multinomial.cpp
+
+DataLikelihood.o: DataLikelihood.cpp DataLikelihood.h Sum.h Product.h
+	$(CXX) $(CFLAGS) $(INCLUDE) -c DataLikelihood.cpp
+
+Marginals.o: Marginals.cpp Marginals.h
+	$(CXX) $(CFLAGS) $(INCLUDE) -c Marginals.cpp
+
+ResultData.o: ResultData.cpp ResultData.h Result.h Result.cpp Allele.h Utility.h Genotype.h AlleleParser.h Version.h
+	$(CXX) $(CFLAGS) $(INCLUDE) -c ResultData.cpp
+
+Result.o: Result.cpp Result.h
+	$(CXX) $(CFLAGS) $(INCLUDE) -c Result.cpp
+
+NonCall.o: NonCall.cpp NonCall.h
+	$(CXX) $(CFLAGS) $(INCLUDE) -c NonCall.cpp
+
+BedReader.o: BedReader.cpp BedReader.h
+	$(CXX) $(CFLAGS) $(INCLUDE) -c BedReader.cpp
+
+CNV.o: CNV.cpp CNV.h
+	$(CXX) $(CFLAGS) $(INCLUDE) -c CNV.cpp
+
+Bias.o: Bias.cpp Bias.h
+	$(CXX) $(CFLAGS) $(INCLUDE) -c Bias.cpp
+
+split.o: split.h split.cpp
+	$(CXX) $(CFLAGS) $(INCLUDE) -c split.cpp
+
+bamleftalign.o: bamleftalign.cpp LeftAlign.cpp
+	$(CXX) $(CFLAGS) $(INCLUDE) -c bamleftalign.cpp
+
+bamfiltertech.o: bamfiltertech.cpp
+	$(CXX) $(CFLAGS) $(INCLUDE) -c bamfiltertech.cpp
+
+LeftAlign.o: LeftAlign.h LeftAlign.cpp $(BAMTOOLS_ROOT)/lib/libbamtools.a $(HTSLIB_ROOT)/libhts.a
+	$(CXX) $(CFLAGS) $(INCLUDE) -c LeftAlign.cpp
+
+IndelAllele.o: IndelAllele.cpp IndelAllele.h
+	$(CXX) $(CFLAGS) $(INCLUDE) -c IndelAllele.cpp
+
+Variant.o: $(VCFLIB_ROOT)/src/Variant.h $(VCFLIB_ROOT)/src/Variant.cpp
+	$(CXX) $(CFLAGS) $(INCLUDE) -c $(VCFLIB_ROOT)/src/Variant.cpp
+
+../vcflib/tabixpp/tabix.o:
+	cd $(TABIX_ROOT)/ && make
+../vcflib/tabixpp/htslib/bgzf.o: ../vcflib/tabixpp/htslib/bgzf.c ../vcflib/tabixpp/htslib/htslib/bgzf.h
+	cd ../vcflib/tabixpp && $(MAKE)
+
+../vcflib/smithwaterman/SmithWatermanGotoh.o: ../vcflib/smithwaterman/SmithWatermanGotoh.h ../vcflib/smithwaterman/SmithWatermanGotoh.cpp
+	cd ../vcflib/smithwaterman && $(MAKE)
+
+
+VERSION_FILE=./version_git.h
+RELEASED_VERSION_FILE=./version_release.txt
+
+
+## versioning system from BedTools
+##
+## For freebayes developers (not users):
+## When you want to release (and tag) a new version, run:
+##   $ make setversion VERSION=v2.17.2
+## This will:
+##   1. Update the "/src/utils/version/version_release.txt" file
+##   2. Commit the file
+##   3. Git-Tag the commit with the latest version
+##
+.PHONY: setversion
+setversion:
+    ifeq "$(VERSION)" ""
+		$(error please set VERSION variable to the new version (e.g "make setversion VERSION=v2.17.2"))
+    endif
+		@echo "# This file was auto-generated by running \"make setversion VERSION=$(VERSION)\"" > "$(RELEASED_VERSION_FILE)"
+		@echo "# on $$(date) ." >> "$(RELEASED_VERSION_FILE)"
+		@echo "# Please do not edit or commit this file manually." >> "$(RELEASED_VERSION_FILE)"
+		@echo "#" >> "$(RELEASED_VERSION_FILE)"
+		@echo "$(VERSION)" >> $(RELEASED_VERSION_FILE)
+		@git add $(RELEASED_VERSION_FILE)
+		@git commit -q -m "Setting Release-Version $(VERSION)"
+		@git tag "$(VERSION)"
+		@echo "Version updated to $(VERSION)."
+		@echo ""
+		@echo "Don't forget to push the commits AND the tags:"
+		@echo "  git push --all --tags"
+		@echo ""
+
+
+## Automatic version detection
+##
+## What's going on here?
+## 1. If there's a ".git" repository - use the version from the repository.
+##    ignore any released-version file. git repository is authorative.
+##
+## 2, If there's no ".git" repository,
+##    get the "released" version number from the release-version file.
+##
+## 3. Compare the detected version (from steps 1,2) to the current string
+##    in ./src/utils/version/version_git.h .
+##    If they differ, update the header file - will cause a recompilation
+##    of version.o .
+##
+.PHONY: autoversion
+autoversion:
+	@( \
+	if [ -d "../.git" ] && which git > /dev/null ; then \
+		DETECTED_VERSION=$$(git describe --always --tags --dirty) ; \
+	else \
+		DETECTED_VERSION=$$(grep -v "^#" "$(RELEASED_VERSION_FILE)") ; \
+	fi ; \
+	\
+	CURRENT_VERSION="" ; \
+	[ -e "$(VERSION_FILE)" ] && CURRENT_VERSION=$$(grep "define VERSION_GIT " "$(VERSION_FILE)" | cut -f3 -d" " | sed 's/"//g') ; \
+	\
+	echo "DETECTED_VERSION = $$DETECTED_VERSION" ; \
+	echo "CURRENT_VERSION  = $$CURRENT_VERSION" ; \
+	if [ "$${DETECTED_VERSION}" != "$${CURRENT_VERSION}" ] ; then \
+		echo "Updating version file." ; \
+		echo "#ifndef VERSION_GIT_H" > $(VERSION_FILE) ; \
+		echo "#define VERSION_GIT_H" >> $(VERSION_FILE) ; \
+		echo "#define VERSION_GIT \"$${DETECTED_VERSION}\"" >> $(VERSION_FILE) ; \
+		echo "#endif /* VERSION_GIT_H */" >> $(VERSION_FILE) ; \
+	fi )
+
+
+clean:
+	rm -rf *.o *.cgh *~ freebayes alleles ../bin/freebayes ../bin/alleles ../vcflib/*.o ../vcflib/tabixpp/*.{o,a}
+	cd $(BAMTOOLS_ROOT)/build && make clean
+	cd ../vcflib/smithwaterman && make clean
+

src/Parameters.cpp

@@ -125,7 +125,9 @@ void Parameters::usage(char** argv) {
         << "                   will then be partitioned on the basis of the populations." << endl
         << "   -A --cnv-map FILE" << endl
         << "                   Read a copy number map from the BED file FILE, which has" << endl
-        << "                   the format:" << endl
+        << "                   either a sample-level ploidy:" << endl
+        << "                      sample name, copy number" << endl
+        << "                   or a region-specific format:" << endl
         << "                      reference sequence, start, end, sample name, copy number" << endl
         << "                   ... for each region in each sample which does not have the" << endl
         << "                   default copy number as set by --ploidy." << endl
@@ -202,13 +204,13 @@ void Parameters::usage(char** argv) {
         << "   -E --max-complex-gap N" << endl
         << "      --haplotype-length N" << endl
         << "                   Allow haplotype calls with contiguous embedded matches of up" << endl
-        << "                   to this length.  (default: 3)" << endl
+        << "                   to this length. Set N=-1 to disable clumping. (default: 3)" << endl
         << "   --min-repeat-size N" << endl
         << "                   When assembling observations across repeats, require the total repeat" << endl
         << "                   length at least this many bp.  (default: 5)" << endl
         << "   --min-repeat-entropy N" << endl
         << "                   To detect interrupted repeats, build across sequence until it has" << endl
-        << "                   entropy > N bits per bp.  (default: 0, off)" << endl
+        << "                   entropy > N bits per bp. Set to 0 to turn off. (default: 1)" << endl
         << "   --no-partial-observations" << endl
         << "                   Exclude observations which do not fully span the dynamically-determined" << endl
         << "                   detection window.  (default, use all observations, dividing partial" << endl
@@ -259,7 +261,7 @@ void Parameters::usage(char** argv) {
         << "   -F --min-alternate-fraction N" << endl
         << "                   Require at least this fraction of observations supporting" << endl
         << "                   an alternate allele within a single individual in the" << endl
-        << "                   in order to evaluate the position.  default: 0.2" << endl
+        << "                   in order to evaluate the position.  default: 0.05" << endl
         << "   -C --min-alternate-count N" << endl
         << "                   Require at least this count of observations supporting" << endl
         << "                   an alternate allele within a single individual in order" << endl
@@ -404,7 +406,7 @@ Parameters::Parameters(int argc, char** argv) {
     maxComplexGap = 3;
     //maxHaplotypeLength = 100;
     minRepeatSize = 5;
-    minRepeatEntropy = 0;
+    minRepeatEntropy = 1;
     usePartialObservations = true;
     pooledDiscrete = false;                 // -J --pooled
     pooledContinuous = false;
@@ -451,7 +453,7 @@ Parameters::Parameters(int argc, char** argv) {
     TB = 3;
     posteriorIntegrationDepth = 0;
     calculateMarginals = false;
-    minAltFraction = 0.2;  // require 20% of reads from sample to be supporting the same alternate to consider
+    minAltFraction = 0.05;  // require 5% of reads from sample to be supporting the same alternate to consider
     minAltCount = 2; // require 2 reads in same sample call
     minAltTotal = 1;
     minAltQSum = 0;
@@ -785,7 +787,7 @@ Parameters::Parameters(int argc, char** argv) {
             // -m --min-mapping-quality
         case 'm':
             if (!convert(optarg, MQL0)) {
-                cerr << "could not parse min-base-quality" << endl;
+                cerr << "could not parse min-mapping-quality" << endl;
                 exit(1);
             }
             break;