@Test
public void onePerChromosome() {
StingSAMIterator iter = ArtificialSAMUtils.mappedReadIterator(1, 100, 1);
int count = 0;
while (iter.hasNext()) {
SAMRecord rec = iter.next();
assertEquals(Integer.valueOf(count), rec.getReferenceIndex());
count++;
}
assertEquals(count, 100 * 1);
}
@Test
public void basicUnmappedIteratorTest() {
StingSAMIterator iter = ArtificialSAMUtils.mappedAndUnmappedReadIterator(1, 100, 100, 1000);
int count = 0;
for (int x = 0; x < (100 * 100); x++) {
if (!iter.hasNext()) {
fail("we didn't get the expected number of reads");
}
SAMRecord rec = iter.next();
assertTrue(rec.getReferenceIndex() >= 0);
count++;
}
assertEquals(100 * 100, count);
// now we should have 1000 unmapped reads
count = 0;
while (iter.hasNext()) {
SAMRecord rec = iter.next();
assertTrue(rec.getReferenceIndex() < 0);
count++;
}
assertEquals(count, 1000);
}
private void collectReadData(final SAMRecord record, final ReferenceSequence ref) {
metrics.TOTAL_READS++;
readLengthHistogram.increment(record.getReadBases().length);
if (!record.getReadFailsVendorQualityCheckFlag()) {
metrics.PF_READS++;
if (isNoiseRead(record)) metrics.PF_NOISE_READS++;
if (record.getReadUnmappedFlag()) {
// If the read is unmapped see if it's adapter sequence
final byte[] readBases = record.getReadBases();
if (!(record instanceof BAMRecord)) StringUtil.toUpperCase(readBases);
if (isAdapterSequence(readBases)) {
this.adapterReads++;
}
} else if (doRefMetrics) {
metrics.PF_READS_ALIGNED++;
if (!record.getReadNegativeStrandFlag()) numPositiveStrand++;
if (record.getReadPairedFlag() && !record.getMateUnmappedFlag()) {
metrics.READS_ALIGNED_IN_PAIRS++;
// Check that both ends have mapq > minimum
final Integer mateMq = record.getIntegerAttribute("MQ");
if (mateMq == null
|| mateMq >= MAPPING_QUALITY_THRESOLD
&& record.getMappingQuality() >= MAPPING_QUALITY_THRESOLD) {
++this.chimerasDenominator;
// With both reads mapped we can see if this pair is chimeric
if (Math.abs(record.getInferredInsertSize()) > maxInsertSize
|| !record.getReferenceIndex().equals(record.getMateReferenceIndex())) {
++this.chimeras;
}
}
}
}
}
}
@Override
public int doWork(String[] args) {
File refFile = null;
com.github.lindenb.jvarkit.util.cli.GetOpt getopt =
new com.github.lindenb.jvarkit.util.cli.GetOpt();
int c;
while ((c = getopt.getopt(args, "hvL:r:")) != -1) {
switch (c) {
case 'h':
printUsage();
return 0;
case 'v':
System.out.println(getVersion());
return 0;
case 'L':
getLogger().setLevel(java.util.logging.Level.parse(getopt.getOptArg()));
break;
case 'r':
refFile = new File(getopt.getOptArg());
break;
case ':':
System.err.println("Missing argument for option -" + getopt.getOptOpt());
return -1;
default:
System.err.println("Unknown option -" + getopt.getOptOpt());
return -1;
}
}
if (refFile == null) {
error("Undefined REF file");
return -1;
}
File bamFile = null;
if (getopt.getOptInd() + 1 != args.length) {
info("reading from stdin.");
} else {
bamFile = new File(args[getopt.getOptInd()]);
}
IndexedFastaSequenceFile indexedFastaSequenceFile = null;
SAMFileReader samFileReader = null;
try {
GenomicSequence genomicSequence = null;
indexedFastaSequenceFile = new IndexedFastaSequenceFile(refFile);
SAMFileReader.setDefaultValidationStringency(ValidationStringency.SILENT);
samFileReader = null;
if (bamFile == null) {
samFileReader = new SAMFileReader(System.in);
} else {
samFileReader = new SAMFileReader(bamFile);
}
XMLOutputFactory xmlfactory = XMLOutputFactory.newInstance();
XMLStreamWriter w = xmlfactory.createXMLStreamWriter(System.out, "UTF-8");
w.writeStartDocument("UTF-8", "1.0");
w.writeStartElement("sam");
w.writeComment(getProgramCommandLine());
w.writeAttribute("ref", (bamFile == null ? "stdin" : bamFile.getPath()));
w.writeAttribute("bam", args[1]);
SAMRecordIterator iter = samFileReader.iterator();
while (iter.hasNext()) {
SAMRecord rec = iter.next();
final byte readbases[] = rec.getReadBases();
w.writeStartElement("read");
w.writeStartElement("name");
w.writeCharacters(rec.getReadName());
w.writeEndElement();
w.writeStartElement("sequence");
w.writeCharacters(new String(readbases));
w.writeEndElement();
w.writeStartElement("flags");
w.writeAttribute("paired", String.valueOf(rec.getReadPairedFlag()));
w.writeAttribute(
"failsVendorQual", String.valueOf(rec.getReadFailsVendorQualityCheckFlag()));
w.writeAttribute("mapped", String.valueOf(!rec.getReadUnmappedFlag()));
w.writeAttribute("strand", (rec.getReadNegativeStrandFlag() ? "-" : "+"));
if (rec.getReadPairedFlag()) {
w.writeAttribute("mate-mapped", String.valueOf(!rec.getMateUnmappedFlag()));
w.writeAttribute("mate-strand", (rec.getMateNegativeStrandFlag() ? "-" : "+"));
w.writeAttribute("proper-pair", String.valueOf(rec.getProperPairFlag()));
}
w.writeCharacters(String.valueOf(rec.getFlags()));
w.writeEndElement();
if (!rec.getReadUnmappedFlag()) {
w.writeStartElement("qual");
w.writeCharacters(String.valueOf(rec.getMappingQuality()));
w.writeEndElement();
w.writeStartElement("chrom");
w.writeAttribute("index", String.valueOf(rec.getReferenceIndex()));
w.writeCharacters(rec.getReferenceName());
w.writeEndElement();
w.writeStartElement("pos");
w.writeCharacters(String.valueOf(rec.getAlignmentStart()));
w.writeEndElement();
w.writeStartElement("cigar");
w.writeCharacters(rec.getCigarString());
w.writeEndElement();
}
if (!rec.getMateUnmappedFlag()) {
w.writeStartElement("mate-chrom");
w.writeAttribute("index", String.valueOf(rec.getMateReferenceIndex()));
w.writeCharacters(rec.getMateReferenceName());
w.writeEndElement();
w.writeStartElement("mate-pos");
w.writeCharacters(String.valueOf(rec.getMateAlignmentStart()));
w.writeEndElement();
}
if (!rec.getReadUnmappedFlag()) {
if (genomicSequence == null
|| genomicSequence.getChrom().equals(rec.getReferenceName())) {
genomicSequence = new GenomicSequence(indexedFastaSequenceFile, rec.getReferenceName());
}
w.writeStartElement("align");
int readIndex = 0;
int refIndex = rec.getAlignmentStart();
for (final CigarElement e : rec.getCigar().getCigarElements()) {
switch (e.getOperator()) {
case H:
break; // ignore hard clips
case P:
break; // ignore pads
case I: // cont.
case S:
{
final int length = e.getLength();
for (int i = 0; i < length; ++i) {
w.writeEmptyElement(e.getOperator().name());
w.writeAttribute("read-index", String.valueOf(readIndex + 1));
if (readIndex >= 0 && readIndex < readbases.length) {
w.writeAttribute("read-base", String.valueOf((char) (readbases[readIndex])));
}
readIndex++;
}
break;
}
case N: // cont. -- reference skip
case D:
{
final int length = e.getLength();
for (int i = 0; i < length; ++i) {
w.writeEmptyElement(e.getOperator().name());
w.writeAttribute("ref-index", String.valueOf(refIndex));
if (refIndex >= 1 && refIndex <= genomicSequence.length()) {
w.writeAttribute(
"ref-base", String.valueOf(genomicSequence.charAt(refIndex - 1)));
}
refIndex++;
}
break;
}
case M:
case EQ:
case X:
{
final int length = e.getLength();
for (int i = 0; i < length; ++i) {
w.writeEmptyElement(e.getOperator().name());
char baseRead = '\0';
if (readIndex >= 0 && readIndex < readbases.length) {
baseRead = (char) (rec.getReadBases()[readIndex]);
w.writeAttribute("read-index", String.valueOf(readIndex + 1));
w.writeAttribute("read-base", String.valueOf(baseRead));
}
w.writeAttribute("ref-index", String.valueOf(refIndex));
if (refIndex >= 1 && refIndex <= genomicSequence.length()) {
char baseRef = genomicSequence.charAt(refIndex - 1);
w.writeAttribute("ref-base", String.valueOf(baseRef));
if (Character.toUpperCase(baseRef) != Character.toUpperCase(baseRead)) {
w.writeAttribute("mismatch", "true");
}
}
refIndex++;
readIndex++;
}
break;
}
default:
throw new IllegalStateException(
"Case statement didn't deal with cigar op: " + e.getOperator());
}
}
}
w.writeEndElement();
w.writeEndElement();
iter.close();
w.writeEndElement();
}
w.writeEndElement();
w.writeEndDocument();
w.flush();
w.close();
} catch (Exception err) {
error(err);
return -1;
} finally {
CloserUtil.close(samFileReader);
CloserUtil.close(indexedFastaSequenceFile);
}
return 0;
}