Merge branch 'release/v2.0.4'

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "repseqio"]
+	path = repseqio
+	url = https://github.com/repseqio/repseqio.git

.travis.yml

@@ -0,0 +1,23 @@
+language: java
+
+sudo: false
+
+git:
+  submodules: false
+
+before_install:
+  - sed -i 's/git@github.com:/https:\/\/github.com\//' .gitmodules
+  - git submodule update --init --recursive
+  - rm -rf ./repseqio/.cache
+  - mv .cache ./repseqio/.cache
+  - cd repseqio/milib && mvn clean install -DskipTests -B && cd ..
+  - mvn clean install -DskipTests -B && cd ..
+  - mv ./repseqio/.cache .cache
+
+jdk:
+  - openjdk7
+
+cache:
+  directories:
+  - $HOME/.m2
+  - .cache

CHANGELOG

@@ -1,4 +1,12 @@
 
+MiXCR 2.0.4 ( 4 Feb 2017)
+========================
+
+-- Fix for NPE in `-nMutations ...` `-aaMutations ...`
+-- Correct visualization of D gene P segments in exportAlignmentsPretty
+-- minor: Fix for error in export when fields are given in the file
+
+
 MiXCR 2.0.3 (26 Dec 2016)
 ========================
 

README.md

@@ -1,3 +1,5 @@
+[![Build Status](https://travis-ci.org/milaboratory/mixcr.svg)](https://travis-ci.org/milaboratory/mixcr)
+
 ## Overview
 
 MiXCR is a universal software for fast and accurate analysis of raw T- or B- cell receptor repertoire sequencing data.
@@ -42,6 +44,27 @@ For more details see documentation.
 
 Detailed documentation can be found at https://mixcr.readthedocs.io/
 
+## Build
+
+Dependancy:
+
+- Maven 3 (https://maven.apache.org/)
+
+To build MiXCR from source:
+
+- Refresh git submodules
+
+  ```
+  git submodule update --init --recursive
+  ```
+
+- Run build script. First build may take several minuties to download sequences for built-in V/D/J/C gene libraries from NCBI.
+
+  ```
+  ./build.sh
+  ```
+
+
 ## License
 
 Copyright (c) 2014-2015, Bolotin Dmitry, Chudakov Dmitry, Shugay Mikhail

build.sh

@@ -0,0 +1,83 @@
+#!/bin/bash
+
+# Linux readlink -f alternative for Mac OS X
+function readlinkUniversal() {
+    targetFile=$1
+
+    cd `dirname $targetFile`
+    targetFile=`basename $targetFile`
+
+    # iterate down a (possible) chain of symlinks
+    while [ -L "$targetFile" ]
+    do
+        targetFile=`readlink $targetFile`
+        cd `dirname $targetFile`
+        targetFile=`basename $targetFile`
+    done
+
+    # compute the canonicalized name by finding the physical path 
+    # for the directory we're in and appending the target file.
+    phys_dir=`pwd -P`
+    result=$phys_dir/$targetFile
+    echo $result
+}
+
+os=`uname`
+delta=100
+
+dir=""
+
+case $os in
+    Darwin)
+        dir=$(dirname "$(readlinkUniversal "$0")")
+    ;;
+    Linux)
+        dir="$(dirname "$(readlink -f "$0")")"
+    ;;
+    FreeBSD)
+        dir=$(dirname "$(readlinkUniversal "$0")")    
+    ;;
+    *)
+       echo "Unknown OS."
+       exit 1
+    ;;
+esac
+
+if [[ ! -f ${dir}/repseqio/milib/pom.xml ]];
+then
+  echo "Please init git submodules. Try:"
+  echo "git submodule update --init --recursive"
+  exit 1
+fi
+
+function error_exit {
+    echo -e "$1"
+    exit "${2:-1}"
+}
+
+GREEN='\033[0;32m'
+RED='\033[0;31m'
+NC='\033[0m' # No Color
+
+echo "Building MiLib."
+cd ${dir}/repseqio/milib
+mvn clean install -DskipTests -B || error_exit "${RED}Problem building MiLib!${NC}" 1
+
+echo "Building RepSeq.IO util/lib"
+cd ${dir}/repseqio
+mvn clean install -DskipTests -B || error_exit "${RED}Problem building RepSeq.IO util!${NC}" 1
+
+echo "Building MiXCR."
+cd ${dir}
+mvn clean install -DskipTests -B || error_exit "${RED}Problem building MiXCR util!${NC}" 1
+
+echo -e "${GREEN}Build successfull!${NC}"
+echo "The following is the output of \"mixcr -v\" command:"
+${dir}/mixcr -v || error_exit "${RED}Something went wrong!${NC}" 1
+echo -e "${GREEN}Everything seems OK!${NC}"
+echo ""
+echo "Add mixcr script from this folder to your PATH variable or add symlink to your bin folder."
+echo ""
+echo "MiXCR is free for Academic use. For commertial use please contact licensing@milaboratory.com ."
+echo ""
+echo "If you discover bugs or have any questions, contact us at https://github.com/milaboratory/mixcr/issues ."

pom.xml

@@ -32,7 +32,7 @@
 
     <groupId>com.milaboratory</groupId>
     <artifactId>mixcr</artifactId>
-    <version>2.0.3</version>
+    <version>2.0.4</version>
     <packaging>jar</packaging>
     <name>MiXCR</name>
 
@@ -44,14 +44,14 @@
 
     <properties>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
-        <milib.version>1.7</milib.version>
+        <milib.version>1.7.1</milib.version>
     </properties>
 
     <dependencies>
         <dependency>
             <groupId>io.repseq</groupId>
             <artifactId>repseqio</artifactId>
-            <version>1.2.4</version>
+            <version>1.2.6</version>
         </dependency>
 
         <dependency>

src/main/java/com/milaboratory/mixcr/basictypes/VDJCAlignmentsFormatter.java

@@ -113,6 +113,20 @@ public boolean accept(SequencePartitioning object) {
             return object.isAvailable(ReferencePoint.VEnd) && object.getPosition(ReferencePoint.VEnd) != object.getPosition(ReferencePoint.VEndTrimmed);
         }
     };
+    public static final Filter<SequencePartitioning> IsDPLeft = new Filter<SequencePartitioning>() {
+        @Override
+        public boolean accept(SequencePartitioning object) {
+            return object.isAvailable(ReferencePoint.DBegin) && object.getPosition(ReferencePoint.DBegin) != object.getPosition(ReferencePoint.DBeginTrimmed);
+        }
+    };
+    public static final Filter<SequencePartitioning> IsDPRight = new Filter<SequencePartitioning>() {
+        @Override
+        public boolean accept(SequencePartitioning object) {
+            return object.isAvailable(ReferencePoint.DEnd) && object.getPosition(ReferencePoint.DEnd) != object.getPosition(ReferencePoint.DEndTrimmed);
+        }
+    };
+    public static final Filter<SequencePartitioning> NotDPLeft = FilterUtil.not(IsDPLeft);
+    public static final Filter<SequencePartitioning> NotDPRight = FilterUtil.not(IsDPRight);
     public static final Filter<SequencePartitioning> NotVP = FilterUtil.not(IsVP);
 
 
@@ -130,8 +144,15 @@ public boolean accept(SequencePartitioning object) {
             pd(ReferencePoint.VEndTrimmed, "V>", -1, NotVP),
             pd(ReferencePoint.VEnd, "V><VP", IsVP),
             pd(ReferencePoint.VEndTrimmed, "VP>", -1, IsVP),
-            pd(ReferencePoint.DBeginTrimmed, "<D"),
-            pd(ReferencePoint.DEndTrimmed, "D>", -1),
+
+            pd(ReferencePoint.DBeginTrimmed, "<D", NotDPLeft),
+            pd(ReferencePoint.DBegin, "DP><D", IsDPLeft),
+            pd(ReferencePoint.DBeginTrimmed, "<DP", IsDPLeft),
+
+            pd(ReferencePoint.DEndTrimmed, "D>", -1, NotDPRight),
+            pd(ReferencePoint.DEnd, "D><DP", IsDPRight),
+            pd(ReferencePoint.DEndTrimmed, "DP>", IsDPRight),
+
             pd(ReferencePoint.JBeginTrimmed, "<J"),
             pd(ReferencePoint.CDR3End, "CDR3><FR4"),
             pd(ReferencePoint.FR4End, "FR4>", -1),

src/main/java/com/milaboratory/mixcr/cli/ActionExportParameters.java

@@ -195,6 +195,7 @@ public static ArrayList<FieldExtractor> parseFile(OutputMode outputMode, Class c
             String line;
             while ((line = reader.readLine()) != null) {
                 line = line.trim();
+                line = line.replace("\"", "");
                 if (!line.isEmpty())
                     options.addAll(Arrays.asList(line.split(" ")));
             }

src/main/java/com/milaboratory/mixcr/export/FeatureExtractors.java

@@ -8,10 +8,7 @@
 import com.milaboratory.core.sequence.TranslationParameters;
 import com.milaboratory.mixcr.basictypes.VDJCHit;
 import com.milaboratory.mixcr.basictypes.VDJCObject;
-import io.repseq.core.GeneFeature;
-import io.repseq.core.GeneType;
-import io.repseq.core.ReferencePoints;
-import io.repseq.core.VDJCGene;
+import io.repseq.core.*;
 
 import static com.milaboratory.mixcr.export.FieldExtractors.NULL;
 
@@ -32,7 +29,10 @@ static abstract class WithHeader extends FieldWithParameters<VDJCObject, GeneFea
 
         void validate(GeneFeature[] features) {
             if (features.length == 2 && !features[1].contains(features[0]))
-                throw new IllegalArgumentException(String.format("%s: Base feature %s does not contain relative feature %s", command, features[1], features[0]));
+                throw new IllegalArgumentException(String.format("%s: Base feature %s does not contain relative feature %s",
+                        command, GeneFeature.encode(features[1]), GeneFeature.encode(features[0])));
+
+            //todo bigfeature nofloating bounds
         }
 
         private String header0(String[] prefixes, GeneFeature[] features) {
@@ -88,43 +88,91 @@ static abstract class MutationsExtractor extends WithHeader {
             super(command, description, nArgs, hPrefix, sPrefix);
         }
 
+        @Override
+        void validate(GeneFeature[] features) {
+            super.validate(features);
+            for (GeneFeature feature : features)
+                if (feature.getGeneType() == null)
+                    throw new IllegalArgumentException(String.format("%s: Gene feature %s covers several gene types " +
+                            "(not possible to select corresponding alignment)", command, GeneFeature.encode(feature)));
+        }
+
         @Override
         protected String extractValue(VDJCObject object, GeneFeature[] parameters) {
             GeneFeature smallGeneFeature = parameters[0];
             GeneFeature bigGeneFeature = parameters[parameters.length - 1];
 
             GeneType geneType = bigGeneFeature.getGeneType();
+            assert geneType != null;
+
             VDJCHit hit = object.getBestHit(geneType);
 
             if (hit == null)
                 return "-";
 
             GeneFeature alignedFeature = hit.getAlignedFeature();
-            if (!alignedFeature.contains(smallGeneFeature))
-                return "-";
+//            if (!alignedFeature.contains(smallGeneFeature))
+//                return "-";
 
             VDJCGene gene = hit.getGene();
-            ReferencePoints partitioning = gene.getPartitioning();
-            if (!partitioning.isAvailable(bigGeneFeature))
+            ReferencePoints germlinePartitioning = gene.getPartitioning();
+            if (!germlinePartitioning.isAvailable(bigGeneFeature))
                 return "-";
 
-            Range smallTargetRage = partitioning.getRelativeRange(alignedFeature, smallGeneFeature);
+            Range smallTargetRage = germlinePartitioning.getRelativeRange(alignedFeature, smallGeneFeature);
+            if (smallTargetRage == null)
+                for (int i = 0; i < object.numberOfTargets(); i++) {
+                    SequencePartitioning pt = object.getPartitionedTarget(i).getPartitioning();
+                    Range range = pt.getRange(smallGeneFeature);
+                    if (range == null)
+                        continue;
+                    Alignment<NucleotideSequence> alignment = object.getBestHit(geneType).getAlignment(i);
+                    smallTargetRage = alignment.convertToSeq1Range(range);
+                    if (smallTargetRage != null)
+                        break;
+                }
+
+            if (smallTargetRage == null)
+                return "-";
 
-            for (int i = 0; i < hit.numberOfTargets(); i++) {
+            GeneFeature intersectionBigAligned = GeneFeature.intersectionStrict(bigGeneFeature, alignedFeature);
+
+            for (int i = 0; i < hit.numberOfTargets(); ++i) {
                 Alignment<NucleotideSequence> alignment = hit.getAlignment(i);
 
                 if (alignment == null || !alignment.getSequence1Range().contains(smallTargetRage))
                     continue;
 
-                Mutations<NucleotideSequence> mutations = alignment.getAbsoluteMutations().extractRelativeMutationsForRange(smallTargetRage);
+                Mutations<NucleotideSequence> mutations;
                 if (parameters.length == 2) {
-                    int shift = partitioning.getRelativePosition(bigGeneFeature, smallGeneFeature.getFirstPoint());
-                    if (shift < 0)
+                    mutations = alignment.getAbsoluteMutations().extractAbsoluteMutationsForRange(smallTargetRage);
+
+                    ReferencePoint baIntersectionBegin = intersectionBigAligned.getFirstPoint();
+
+                    int referencePosition = germlinePartitioning.getRelativePosition(alignedFeature, baIntersectionBegin);
+                    int bigFeaturePosition = germlinePartitioning.getRelativePosition(bigGeneFeature, baIntersectionBegin);
+
+                    if (bigFeaturePosition < 0 || referencePosition < 0)
                         continue;
+
+                    int shift = bigFeaturePosition - referencePosition;
+
+                    if (shift < 0)
+                        mutations = mutations.getRange(Mutations.pabs(mutations.firstMutationWithPosition(-shift)), mutations.size());
+
                     mutations = mutations.move(shift);
-                }
 
-                return convert(mutations, gene.getFeature(bigGeneFeature), object.getFeature(smallGeneFeature).getSequence(), partitioning.getTranslationParameters(bigGeneFeature));
+//                    int shift = germlinePartitioning.getRelativePosition(bigGeneFeature, smallGeneFeature.getFirstPoint());
+//                    if (shift < 0)
+//                        continue;
+//                    mutations = mutations.move(shift);
+//                    mutations = mutations.extractRelativeMutationsForRange(bigRange);
+//                    if (mutations == null)
+//                        continue;
+                } else
+                    mutations = alignment.getAbsoluteMutations().extractRelativeMutationsForRange(smallTargetRage);
+
+                return convert(mutations, gene.getFeature(bigGeneFeature), object.getFeature(smallGeneFeature).getSequence(), germlinePartitioning.getTranslationParameters(bigGeneFeature));
             }
             return "-";
         }

src/test/java/com/milaboratory/mixcr/export/FieldExtractorsTest.java

@@ -31,6 +31,7 @@
 import com.milaboratory.mixcr.basictypes.Clone;
 import com.milaboratory.mixcr.basictypes.VDJCAlignments;
 import com.milaboratory.mixcr.basictypes.VDJCObject;
+import com.milaboratory.mixcr.cli.Main;
 import com.milaboratory.mixcr.cli.Util;
 import io.repseq.core.GeneType;
 import org.junit.Ignore;

src/test/java/com/milaboratory/mixcr/partialassembler/PartialAlignmentsAssemblerTest.java

@@ -8,7 +8,6 @@
 import com.milaboratory.core.sequence.SequenceBuilder;
 import com.milaboratory.core.sequence.SequenceQuality;
 import com.milaboratory.mixcr.basictypes.*;
-import com.milaboratory.mixcr.cli.ReportHelper;
 import com.milaboratory.mixcr.util.RunMiXCR;
 import com.milaboratory.mixcr.vdjaligners.VDJCAlignerParameters;
 import com.milaboratory.mixcr.vdjaligners.VDJCParametersPresets;
@@ -214,9 +213,8 @@ public static TestResult processData(PairedRead[] data, InputTestData input) thr
         params.alignerParameters.setAllowPartialAlignments(true);
 
         final RunMiXCR.AlignResult inputAlignments = RunMiXCR.align(params);
-        inputAlignments.report.writeReport(new ReportHelper(System.out));
-        System.out.println("\n");
-
+        //inputAlignments.report.writeReport(new ReportHelper(System.out));
+        //System.out.println("\n");
 
         for (VDJCAlignments al : inputAlignments.alignments) {
             for (GeneType gt : GeneType.VJC_REFERENCE) {
@@ -250,8 +248,8 @@ public static TestResult processData(PairedRead[] data, InputTestData input) thr
             try (final VDJCAlignmentsReader reader = inputAlignments.resultReader()) {
                 assembler.searchOverlaps(reader);
             }
-            assembler.writeReport(new ReportHelper(System.out));
-            System.out.println("\n");
+            //assembler.writeReport(new ReportHelper(System.out));
+            //System.out.println("\n");
         }