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

Added argument to ValidationAmplicons to only output valid sequences - useful for not having to post-filter or grep resulting files before delivering downstream

This commit is contained in:
Guillermo del Angel 2012-03-04 10:24:29 -05:00
parent 69611af7d3
commit 3b5a7c34d7
1 changed files with 16 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
public/java/src/org/broadinstitute/sting/gatk/walkers/validation/ValidationAmplicons.java
View File

@ -110,6 +110,13 @@ public class ValidationAmplicons extends RodWalker<Integer,Integer> {
@Argument(doc="Lower case SNPs rather than replacing with 'N'",fullName="lowerCaseSNPs",required=false)
boolean lowerCaseSNPs = false;
/**
* If onlyOutputValidAmplicons is true, the output fasta file will contain only valid sequences.
* Useful for producing delivery-ready files.
*/
@Argument(doc="Only output valid sequences.",fullName="onlyOutputValidAmplicons",required=false)
boolean onlyOutputValidAmplicons = false;
/**
* BWA single-end alignment is used as a primer specificity proxy. Low-complexity regions (that don't align back to themselves as a best hit) are lowercased.
* This changes the size of the k-mer used for alignment.
@ -486,14 +493,16 @@ public class ValidationAmplicons extends RodWalker<Integer,Integer> {
valid = "Valid";
}
String seqIdentity = sequence.toString().replace('n', 'N').replace('i', 'I').replace('d', 'D');
if (!sequenomOutput)
out.printf(">%s %s %s%n%s%n", allelePos != null ? allelePos.toString() : "multiple", valid, probeName, seqIdentity);
else {
seqIdentity = seqIdentity.replace("*",""); // identifier < 20 letters long, no * in ref allele, one line per record
probeName = probeName.replace("amplicon_","a");
out.printf("%s_%s %s%n", allelePos != null ? allelePos.toString() : "multiple", probeName, seqIdentity);
if (!onlyOutputValidAmplicons || !sequenceInvalid) {
String seqIdentity = sequence.toString().replace('n', 'N').replace('i', 'I').replace('d', 'D');
if (!sequenomOutput)
out.printf(">%s %s %s%n%s%n", allelePos != null ? allelePos.toString() : "multiple", valid, probeName, seqIdentity);
else {
seqIdentity = seqIdentity.replace("*",""); // identifier < 20 letters long, no * in ref allele, one line per record
probeName = probeName.replace("amplicon_","a");
out.printf("%s_%s %s%n", allelePos != null ? allelePos.toString() : "multiple", probeName, seqIdentity);
}
}
}
}