Use adam-core-spark2_2.12:0.28.0

broadinstitute · Sep 17, 2019 · 560963b · 560963b
1 parent 4180c0d
commit 560963b
Show file tree

Hide file tree

Showing 6 changed files with 21 additions and 17 deletions.
diff --git a/build.gradle b/build.gradle
@@ -281,7 +281,7 @@ dependencies {
     compile 'com.thoughtworks.paranamer:paranamer:2.8'
 
     compile 'org.bdgenomics.bdg-formats:bdg-formats:0.5.0'
-    compile('org.bdgenomics.adam:adam-core-spark2_2.11:0.20.0') {
+    compile('org.bdgenomics.adam:adam-core-spark2_2.12:0.28.0') {
         exclude group: 'org.slf4j'
         exclude group: 'org.apache.hadoop'
         exclude group: 'org.scala-lang'

diff --git a/src/main/java/org/broadinstitute/hellbender/engine/spark/datasources/ReadsSparkSink.java b/src/main/java/org/broadinstitute/hellbender/engine/spark/datasources/ReadsSparkSink.java
@@ -13,7 +13,7 @@
 import org.apache.spark.api.java.JavaRDD;
 import org.apache.spark.api.java.JavaSparkContext;
 import org.apache.spark.broadcast.Broadcast;
-import org.bdgenomics.adam.models.RecordGroupDictionary;
+import org.bdgenomics.adam.models.ReadGroupDictionary;
 import org.bdgenomics.adam.models.SequenceDictionary;
 import org.bdgenomics.formats.avro.AlignmentRecord;
 import org.broadinstitute.hellbender.exceptions.GATKException;
@@ -157,7 +157,7 @@ private static void writeReadsADAM(
             final JavaSparkContext ctx, final String outputFile, final JavaRDD<SAMRecord> reads,
             final SAMFileHeader header) throws IOException {
         final SequenceDictionary seqDict = SequenceDictionary.fromSAMSequenceDictionary(header.getSequenceDictionary());
-        final RecordGroupDictionary readGroups = RecordGroupDictionary.fromSAMHeader(header);
+        final ReadGroupDictionary readGroups = ReadGroupDictionary.fromSAMHeader(header);
         final JavaPairRDD<Void, AlignmentRecord> rddAlignmentRecords =
                 reads.map(read -> {
                     read.setHeaderStrict(header);

diff --git a/...va/org/broadinstitute/hellbender/engine/spark/datasources/ReferenceTwoBitSparkSource.java b/...va/org/broadinstitute/hellbender/engine/spark/datasources/ReferenceTwoBitSparkSource.java
@@ -6,15 +6,19 @@
 import org.bdgenomics.adam.models.ReferenceRegion;
 import org.bdgenomics.adam.util.TwoBitFile;
 import org.bdgenomics.adam.util.TwoBitRecord;
+import org.bdgenomics.formats.avro.Strand;
 import org.bdgenomics.utils.io.ByteAccess;
 import org.broadinstitute.hellbender.utils.SimpleInterval;
 import org.broadinstitute.hellbender.utils.Utils;
 import org.broadinstitute.hellbender.utils.gcs.BucketUtils;
 import org.broadinstitute.hellbender.utils.reference.ReferenceBases;
+import scala.Tuple2;
 import scala.collection.JavaConversions;
+import scala.collection.immutable.IndexedSeq;
 
 import java.io.IOException;
 import java.io.Serializable;
+import java.util.LinkedHashMap;
 import java.util.List;
 import java.util.Map;
 import java.util.stream.Collectors;
@@ -39,7 +43,10 @@ public ReferenceTwoBitSparkSource( String referenceURL) throws IOException {
         byte[] bytes = ByteStreams.toByteArray(BucketUtils.openFile(this.referenceURL));
         ByteAccess byteAccess = new DirectFullByteArrayByteAccess(bytes);
         this.twoBitFile = new TwoBitFile(byteAccess);
-        this.twoBitSeqEntries = JavaConversions.mapAsJavaMap(twoBitFile.seqRecords());
+        this.twoBitSeqEntries = new LinkedHashMap<>();
+        for (Tuple2<String, TwoBitRecord> pair: JavaConversions.seqAsJavaList(twoBitFile.seqRecords())) {
+            twoBitSeqEntries.put(pair._1, pair._2);
+        }
     }
 
     /**
@@ -74,7 +81,7 @@ private static ReferenceRegion simpleIntervalToReferenceRegion(SimpleInterval in
         String contig = interval.getContig();
         long start = interval.getGA4GHStart();
         long end = interval.getGA4GHEnd();
-        return new ReferenceRegion(contig, start, end, null);
+        return new ReferenceRegion(contig, start, end, Strand.UNKNOWN);
     }
 
     private SimpleInterval cropIntervalAtContigEnd( final SimpleInterval interval ) {

diff --git a/...in/java/org/broadinstitute/hellbender/utils/read/BDGAlignmentRecordToGATKReadAdapter.java b/...in/java/org/broadinstitute/hellbender/utils/read/BDGAlignmentRecordToGATKReadAdapter.java
@@ -3,8 +3,7 @@
 import htsjdk.samtools.SAMFileHeader;
 import htsjdk.samtools.SAMRecord;
 import org.bdgenomics.adam.converters.AlignmentRecordConverter;
-import org.bdgenomics.adam.models.RecordGroupDictionary;
-import org.bdgenomics.adam.models.SAMFileHeaderWritable;
+import org.bdgenomics.adam.models.ReadGroupDictionary;
 import org.bdgenomics.formats.avro.AlignmentRecord;
 
 /**
@@ -30,8 +29,8 @@ public final class BDGAlignmentRecordToGATKReadAdapter extends SAMRecordToGATKRe
     private final AlignmentRecord alignmentRecord;
 
     public BDGAlignmentRecordToGATKReadAdapter(final AlignmentRecord alignmentRecord, final SAMFileHeader header) {
-        super(new AlignmentRecordConverter().convert(alignmentRecord, SAMFileHeaderWritable.apply(header),
-                RecordGroupDictionary.fromSAMHeader(header)));
+        super(new AlignmentRecordConverter().convert(alignmentRecord, header,
+                ReadGroupDictionary.fromSAMHeader(header)));
         this.alignmentRecord = alignmentRecord;
     }
 

diff --git a/.../java/org/broadinstitute/hellbender/utils/read/GATKReadToBDGAlignmentRecordConverter.java b/.../java/org/broadinstitute/hellbender/utils/read/GATKReadToBDGAlignmentRecordConverter.java
@@ -5,7 +5,7 @@
 import org.bdgenomics.formats.avro.AlignmentRecord;
 import org.bdgenomics.adam.converters.SAMRecordConverter;
 import org.bdgenomics.adam.models.SequenceDictionary;
-import org.bdgenomics.adam.models.RecordGroupDictionary;
+import org.bdgenomics.adam.models.ReadGroupDictionary;
 
 /**
  * Converts a GATKRead to a BDG AlignmentRecord
@@ -15,27 +15,27 @@ public class GATKReadToBDGAlignmentRecordConverter {
 
     private SAMFileHeader header;
     private SequenceDictionary dict;
-    private RecordGroupDictionary readGroups;
+    private ReadGroupDictionary readGroups;
 
     public GATKReadToBDGAlignmentRecordConverter(SAMFileHeader header) {
         this.header = header;
         this.dict = SequenceDictionary.fromSAMSequenceDictionary(header.getSequenceDictionary());
-        this.readGroups = RecordGroupDictionary.fromSAMHeader(header);
+        this.readGroups = ReadGroupDictionary.fromSAMHeader(header);
     }
 
     public static AlignmentRecord convert( final GATKRead gatkRead, final SAMFileHeader header ) {
         SequenceDictionary dict = SequenceDictionary.fromSAMSequenceDictionary(header.getSequenceDictionary());
-        RecordGroupDictionary readGroups = RecordGroupDictionary.fromSAMHeader(header);
+        ReadGroupDictionary readGroups = ReadGroupDictionary.fromSAMHeader(header);
         return GATKReadToBDGAlignmentRecordConverter.convert(gatkRead, header, dict, readGroups);
     }
 
     public static AlignmentRecord convert(
-            final GATKRead gatkRead, final SAMFileHeader header, final SequenceDictionary dict, final RecordGroupDictionary readGroups ) {
+            final GATKRead gatkRead, final SAMFileHeader header, final SequenceDictionary dict, final ReadGroupDictionary readGroups ) {
         return converter.convert(gatkRead.convertToSAMRecord(header));
     }
 
     public static AlignmentRecord convert(
-            final SAMRecord sam, final SequenceDictionary dict, final RecordGroupDictionary readGroups ) {
+            final SAMRecord sam, final SequenceDictionary dict, final ReadGroupDictionary readGroups ) {
         return converter.convert(sam);
     }
 }
diff --git a/src/test/java/org/broadinstitute/hellbender/utils/read/GATKReadAdaptersUnitTest.java b/src/test/java/org/broadinstitute/hellbender/utils/read/GATKReadAdaptersUnitTest.java
@@ -55,8 +55,6 @@ public Object[][] readPairsForToString() {
 
     private static GATKRead basicReadBackedByADAMRecord(final SAMRecord sam) {
         final AlignmentRecord record = new AlignmentRecord();
-        record.setContigName(sam.getContig());
-        record.setRecordGroupSample(sam.getReadGroup().getSample());
         record.setReadName(sam.getReadName());
         record.setSequence(new String(sam.getReadBases()));
         record.setStart((long)sam.getAlignmentStart()-1); //ADAM records are 0-based