Skip to content

fix(ENGKNOW-2566): gor improve csvcc and gtgen to handle genotypes values outside 0 1 2 3 #63

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
gmagnu merged 4 commits into from
Jul 29, 2025
Merged

fix(ENGKNOW-2566): gor improve csvcc and gtgen to handle genotypes values outside 0 1 2 3 #63

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ca80aad
feat(ENGKNOW-2566): support for more GT values
gorfather Jun 26, 2025
3df010a
feat(ENGKNOW-2566): support for more GT values
gorfather Jun 26, 2025
515dad6
Merge branch 'main' of github.com:gorpipe/gor into ENGKNOW-2566-gor-i…
gorfather Jul 29, 2025
8578c40
feat(ENGKNOW-2566): support for more GT values
gorfather Jul 29, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions gortools/src/main/scala/gorsat/Analysis/GtGenAnalysis.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,7 +61,7 @@ object GtGenAnalysis {
sh.buckValueCols(i).setLength(buckSize)
var j = 0
while (j < buckSize) {
sh.buckValueCols(i).setCharAt(j, '3') // Missing
sh.buckValueCols(i).setCharAt(j, '#') // Missing
j += 1
}
i += 1
Expand Down Expand Up @@ -180,7 +180,7 @@ object GtGenAnalysis {
if (!useGroup) groupMap += (-1 -> singleGroupHolder)

def set_coverage(lSeg: CovSEGinfo, rSeg: CovSEGinfo): Unit = {
if (lSeg.values.charAt(rSeg.buckPos) =='4') lSeg.values.setCharAt(rSeg.buckPos, '0')
if (lSeg.values.charAt(rSeg.buckPos) =='#') lSeg.values.setCharAt(rSeg.buckPos, '0')
}

def nested_process(lr: Row, next_lr: Row): Unit = {
Expand Down Expand Up @@ -291,7 +291,7 @@ object GtGenAnalysis {
}

//#######
super.process(RowObj(s"${lr.colsSlice(0, bucketCol+1)}\t${lSeg.values.toString() }"))
super.process(RowObj(s"${lr.colsSlice(0, bucketCol+1)}\t${lSeg.values.toString().replace('#','3') }"))

if ((lr.chr == lastLeftChr && maxLeftStop < leftStop) || lr.chr != lastLeftChr) maxLeftStop = leftStop
lastLeftChr = lr.chr
Expand Down
15 changes: 15 additions & 0 deletions gortools/src/test/java/gorsat/gtgen/UTestGTGen.java
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
package gorsat.gtgen;

import gorsat.TestUtils;
import org.junit.Assert;
import org.junit.Test;

Expand Down Expand Up @@ -232,4 +233,18 @@ public void test_getAn() {
gtGen.setPrior(0.01, 1000);
Assert.assertEquals(1001, gtGen.getAn());
}

@Test
public void testGTGENunknown() {
TestUtils.runGorPipe("""
create #vars# = gorrow chr1,1 | calc ref 'A,A' | calc alt 'C,C' | calc GT '1,1' | calc pn 'pn1,pn2' | split ref,alt,gt,pn;
create #goodcov# = gorrow chr1,0,3 | calc pn 'pn1,pn2' | split pn;
create #bucket# = nor [#vars#] | select pn | calc bucket 'b1';

gor [#vars#] | gtgen -gc ref,alt [#bucket#] [#goodcov#] | throwif values != '11'
| merge <(gor [#vars#] | where pn != 'pn2' | gtgen -gc ref,alt [#bucket#] [#goodcov#] | throwif values != '10')
| merge <(gor [#vars#] | where pn != 'pn2' | gtgen -gc ref,alt [#bucket#] <(gor [#goodcov#] | where pn != 'pn2') | throwif values != '13')
""" );
}

}
Loading