zzh
/
gatk-3.8
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Intermediate checkin, just to fix null pointer exception that happened when merging implementation with latest VCF4 decoder - field ORIGINAL_ALLELE_LIST in vc shouldn't be written in infoFields structure since this won't be output to file and there is no legal structure under this key. 

Base encoding for complex events is still brittle and most probably still has issues, fixes upcoming.
 


git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@3671 348d0f76-0448-11de-a6fe-93d51630548a
This commit is contained in:
delangel 2010-06-29 20:57:09 +00:00
parent baf9479c35
commit e3fb4d5c70
1 changed files with 53 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

56
java/src/org/broadinstitute/sting/utils/genotype/vcf/VCFWriter.java
View File

@ -246,21 +246,68 @@ public class VCFWriter {
alleleMap.put(Allele.NO_CALL, new VCFGenotypeEncoding(VCFGenotypeRecord.EMPTY_ALLELE)); // convenience for lookup
List<VCFGenotypeEncoding> vcfAltAlleles = new ArrayList<VCFGenotypeEncoding>();
int refIndex=0, numTrailingBases = 0, numPaddingBases = 0;
String paddingBases = new String("");
String trailingBases = new String("");
ArrayList<Allele> originalAlleles = (ArrayList)vc.getAttribute("ORIGINAL_ALLELE_LIST");
boolean isComplexEvent = false;
if (referenceBases.length()>1) {
// complex event: by VCF 4.0, reference from previous position is included.
position--;
isComplexEvent = true;
}
// search for reference allele and find trailing and padding at the end.
if (originalAlleles != null) {
Allele originalReferenceAllele = null;
for (refIndex=0; refIndex < originalAlleles.size(); refIndex++) {
originalReferenceAllele = originalAlleles.get(refIndex);
if (originalReferenceAllele.isReference())
break;
}
if (originalReferenceAllele == null)
throw new IllegalStateException("At least one Allele must be reference");
for ( Allele a : vc.getAlleles() ) {
if (a.isNonReference())
continue;
String refString = new String(a.getBases());
String originalRef = new String(originalReferenceAllele.getBases());
numTrailingBases = originalRef.indexOf(refString);
numPaddingBases = originalRef.length()-refString.length()-numTrailingBases;
if (numTrailingBases > 0) {
position -= numTrailingBases;
trailingBases = originalRef.substring(0,numTrailingBases);
}
if (numPaddingBases > 0)
paddingBases = originalRef.substring(refString.length(),originalRef.length()-1);
}
} else {
// no original Allele information:
if (isComplexEvent)
position--;
}
for ( Allele a : vc.getAlleles() ) {
VCFGenotypeEncoding encoding;
String alleleString = new String(a.getBases());
if (isComplexEvent) {// vc.getType() == VariantContext.Type.MIXED ) {
if ( isComplexEvent ) {
// Mixed variants (e.g. microsatellites) have the reference before the event included
String s = new String(refBases)+alleleString;
String s;
if (numTrailingBases > 0) {
s = trailingBases+alleleString+paddingBases;
} else {
s = new String(refBases)+alleleString;
}
encoding = new VCFGenotypeEncoding(s, true);
if (a.isReference())
referenceString = s;
@ -378,7 +425,10 @@ public class VCFWriter {
if ( key.equals("ID") )
continue;
//TODO - fixme
// Original alleles are not for reporting but only for internal bookkeeping
if (key.equals("ORIGINAL_ALLELE_LIST"))
continue;
String outputValue = formatVCFField(key, elt.getValue());
if ( outputValue != null )
infoFields.put(key, outputValue);