@Test
public void testFilteredCounts() {
final GenomeAnalysisEngine engine = new GenomeAnalysisEngine();
engine.setGenomeLocParser(genomeLocParser);
final Collection<SAMReaderID> samFiles = new ArrayList<>();
final SAMReaderID readerID = new SAMReaderID(testBAM, new Tags());
samFiles.add(readerID);
final List<ReadFilter> filters = new ArrayList<>();
filters.add(new EveryTenthReadFilter());
final SAMDataSource dataSource =
new SAMDataSource(
samFiles,
new ThreadAllocation(),
null,
genomeLocParser,
false,
SAMFileReader.ValidationStringency.STRICT,
null,
null,
new ValidationExclusion(),
filters,
new ArrayList<ReadTransformer>(),
false,
(byte) 30,
false,
true);
engine.setReadsDataSource(dataSource);
final TraverseReadsNano traverseReadsNano = new TraverseReadsNano(1);
final DummyReadWalker walker = new DummyReadWalker();
traverseReadsNano.initialize(engine, walker, null);
for (final Shard shard : dataSource.createShardIteratorOverAllReads(new ReadShardBalancer())) {
final ReadShardDataProvider dataProvider =
new ReadShardDataProvider(
shard,
engine.getGenomeLocParser(),
dataSource.seek(shard),
reference,
new ArrayList<ReferenceOrderedDataSource>());
traverseReadsNano.traverse(walker, dataProvider, 0);
dataProvider.close();
}
Assert.assertEquals(
(long)
engine
.getCumulativeMetrics()
.getCountsByFilter()
.get(EveryTenthReadFilter.class.getSimpleName()),
contigs.size() * numReadsPerContig / 10);
}
@BeforeClass
private void init() throws IOException {
reference = new CachingIndexedFastaSequenceFile(new File(b37KGReference));
dictionary = reference.getSequenceDictionary();
genomeLocParser = new GenomeLocParser(dictionary);
header = ArtificialSAMUtils.createDefaultReadGroup(new SAMFileHeader(), "test", "test");
header.setSequenceDictionary(dictionary);
header.setSortOrder(SAMFileHeader.SortOrder.coordinate);
readGroup = new GATKSAMReadGroupRecord(header.getReadGroup("test"));
final List<GATKSAMRecord> reads = new ArrayList<>();
for (final String contig : contigs) {
for (int i = 1; i <= numReadsPerContig; i++) {
reads.add(buildSAMRecord("read" + contig + "_" + i, contig, i));
}
}
createBAM(reads);
}
@Test
public void testCountsFromActiveRegionTraversal() {
final GenomeAnalysisEngine engine = new GenomeAnalysisEngine();
engine.setGenomeLocParser(genomeLocParser);
final Collection<SAMReaderID> samFiles = new ArrayList<>();
final SAMReaderID readerID = new SAMReaderID(testBAM, new Tags());
samFiles.add(readerID);
final SAMDataSource dataSource =
new SAMDataSource(
samFiles,
new ThreadAllocation(),
null,
genomeLocParser,
false,
SAMFileReader.ValidationStringency.STRICT,
null,
null,
new ValidationExclusion(),
new ArrayList<ReadFilter>(),
new ArrayList<ReadTransformer>(),
false,
(byte) 30,
false,
true);
engine.setReadsDataSource(dataSource);
final Set<String> samples = SampleUtils.getSAMFileSamples(dataSource.getHeader());
final List<GenomeLoc> intervals = new ArrayList<>(contigs.size());
for (final String contig : contigs)
intervals.add(genomeLocParser.createGenomeLoc(contig, 1, numReadsPerContig));
final TraverseActiveRegions traverseActiveRegions = new TraverseActiveRegions();
final DummyActiveRegionWalker walker = new DummyActiveRegionWalker();
traverseActiveRegions.initialize(engine, walker, null);
for (final Shard shard :
dataSource.createShardIteratorOverIntervals(
new GenomeLocSortedSet(genomeLocParser, intervals), new ActiveRegionShardBalancer())) {
final WindowMaker windowMaker =
new WindowMaker(
shard, genomeLocParser, dataSource.seek(shard), shard.getGenomeLocs(), samples);
for (WindowMaker.WindowMakerIterator window : windowMaker) {
final LocusShardDataProvider dataProvider =
new LocusShardDataProvider(
shard,
shard.getReadProperties(),
genomeLocParser,
window.getLocus(),
window,
reference,
new ArrayList<ReferenceOrderedDataSource>());
traverseActiveRegions.traverse(walker, dataProvider, 0);
dataProvider.close();
}
windowMaker.close();
}
Assert.assertEquals(
engine.getCumulativeMetrics().getNumReadsSeen(), contigs.size() * numReadsPerContig);
Assert.assertEquals(
engine.getCumulativeMetrics().getNumIterations(), contigs.size() * numReadsPerContig);
}