Skip to content
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

VCF Tranche filtering in java #4800

Merged
merged 3 commits into from
Jun 21, 2018
Merged

VCF Tranche filtering in java #4800

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1f732a5
tranche filtering in java
lucidtronix May 22, 2018
26175ad
cleanup
lucidtronix Jun 20, 2018
c88dbde
fix tests
lucidtronix Jun 21, 2018
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
2 changes: 1 addition & 1 deletion src/main/java/org/broadinstitute/hellbender/tools/walkers/vqsr/CNNVariantTrain.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,7 +103,7 @@ protected void onStartup() {

@Override
protected Object doWork() {
final Resource pythonScriptResource = new Resource("training.py", FilterVariantTranches.class);
final Resource pythonScriptResource = new Resource("training.py", CNNVariantTrain.class);
List<String> arguments = new ArrayList<>(Arrays.asList(
"--data_dir", inputTensorDir,
"--output_dir", outputDir,
Expand Down
2 changes: 1 addition & 1 deletion src/main/java/org/broadinstitute/hellbender/tools/walkers/vqsr/CNNVariantWriteTensors.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -121,7 +121,7 @@ protected void onStartup() {

@Override
protected Object doWork() {
final Resource pythonScriptResource = new Resource("training.py", FilterVariantTranches.class);
final Resource pythonScriptResource = new Resource("training.py", CNNVariantWriteTensors.class);
List<String> arguments = new ArrayList<>(Arrays.asList(
"--reference_fasta", reference,
"--input_vcf", inputVcf,
Expand Down
284 changes: 161 additions & 123 deletions src/main/java/org/broadinstitute/hellbender/tools/walkers/vqsr/FilterVariantTranches.java
View file
Open in desktop

Large diffs are not rendered by default.

124 changes: 0 additions & 124 deletions src/main/resources/org/broadinstitute/hellbender/tools/walkers/vqsr/tranches.py
View file
Open in desktop

This file was deleted.

5 changes: 2 additions & 3 deletions src/test/java/org/broadinstitute/hellbender/tools/walkers/vqsr/CNNVariantPipelineTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -95,11 +95,10 @@ public void testTranches() {
args.add("FilterVariantTranches")
.addArgument(StandardArgumentDefinitions.VARIANT_LONG_NAME, trancheVCF)
.addArgument(StandardArgumentDefinitions.OUTPUT_LONG_NAME, outputVCF.getAbsolutePath())
.addArgument("snp-truth-vcf", snpTruthVCF)
.addArgument("indel-truth-vcf", indelTruthVCF)
.addArgument("resource", snpTruthVCF)
.addArgument("resource", indelTruthVCF)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This test doesn't really need to be assigned to the python group anymore.

.addArgument("tranche", "99.0")
.addArgument("tranche", "95.0")
.addArgument("max-sites", "2000")
.addArgument("info-key", "VQSLOD");

new Main().instanceMain(args.getArgsArray());
Expand Down
104 changes: 104 additions & 0 deletions ...rg/broadinstitute/hellbender/tools/walkers/vqsr/FilterVariantTranchesIntegrationTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,104 @@
package org.broadinstitute.hellbender.tools.walkers.vqsr;

import org.broadinstitute.hellbender.CommandLineProgramTest;
import org.broadinstitute.hellbender.utils.test.ArgumentsBuilder;
import org.broadinstitute.hellbender.utils.test.IntegrationTestSpec;
import org.broadinstitute.hellbender.cmdline.StandardArgumentDefinitions;

import org.testng.annotations.Test;

import java.util.Arrays;
import java.io.IOException;

public class FilterVariantTranchesIntegrationTest extends CommandLineProgramTest {


/**
* Run the tool on a small test VCF.
*/
@Test
public void testTrancheFiltering() throws IOException {
final String trancheVCF = largeFileTestDir + "VQSR/g94982_20_1m_10m_python_2dcnn.vcf.gz";
final String indelTruthVCF = largeFileTestDir + "VQSR/ALL.wgs.indels_mills_devine_hg19_leftAligned_collapsed_double_hit.sites.20.1M-10M.vcf";
final String snpTruthVCF = largeFileTestDir + "VQSR/Omni25_sites_1525_samples.b37.20.1M-10M.vcf";

final ArgumentsBuilder argsBuilder = new ArgumentsBuilder();
argsBuilder.addArgument(StandardArgumentDefinitions.VARIANT_LONG_NAME, trancheVCF)
.addArgument(StandardArgumentDefinitions.OUTPUT_LONG_NAME, "%s")
.addArgument("resource", snpTruthVCF)
.addArgument("resource", indelTruthVCF)
.addArgument("tranche", "99.0")
.addArgument("info-key", "MIX_SMALL_2D_W_DROPOUT")
.addArgument(StandardArgumentDefinitions.ADD_OUTPUT_VCF_COMMANDLINE, "false");

final IntegrationTestSpec spec = new IntegrationTestSpec(argsBuilder.toString(),
Arrays.asList(largeFileTestDir + "VQSR/expected/g94982_20_1m_10m_tranched_99.vcf"));
spec.executeTest("testTrancheFiltering", this);

}

@Test
public void testTrancheFilteringDuplicate() throws IOException {
final String trancheVCF = largeFileTestDir + "VQSR/g94982_20_1m_10m_python_2dcnn.vcf.gz";
final String indelTruthVCF = largeFileTestDir + "VQSR/ALL.wgs.indels_mills_devine_hg19_leftAligned_collapsed_double_hit.sites.20.1M-10M.vcf";
final String snpTruthVCF = largeFileTestDir + "VQSR/Omni25_sites_1525_samples.b37.20.1M-10M.vcf";

final ArgumentsBuilder argsBuilder = new ArgumentsBuilder();
argsBuilder.addArgument(StandardArgumentDefinitions.VARIANT_LONG_NAME, trancheVCF)
.addArgument(StandardArgumentDefinitions.OUTPUT_LONG_NAME, "%s")
.addArgument("resource", snpTruthVCF)
.addArgument("resource", indelTruthVCF)
.addArgument("tranche", "99.0")
.addArgument("tranche", "99.0")
.addArgument("info-key", "MIX_SMALL_2D_W_DROPOUT")
.addArgument(StandardArgumentDefinitions.ADD_OUTPUT_VCF_COMMANDLINE, "false");

final IntegrationTestSpec spec = new IntegrationTestSpec(argsBuilder.toString(),
Arrays.asList(largeFileTestDir + "VQSR/expected/g94982_20_1m_10m_tranched_99.vcf"));
spec.executeTest("testTrancheFilteringDuplicate", this);
}

@Test
public void testTrancheFilteringTranches() throws IOException {
final String trancheVCF = largeFileTestDir + "VQSR/g94982_20_1m_10m_python_2dcnn.vcf.gz";
final String indelTruthVCF = largeFileTestDir + "VQSR/ALL.wgs.indels_mills_devine_hg19_leftAligned_collapsed_double_hit.sites.20.1M-10M.vcf";
final String snpTruthVCF = largeFileTestDir + "VQSR/Omni25_sites_1525_samples.b37.20.1M-10M.vcf";

final ArgumentsBuilder argsBuilder = new ArgumentsBuilder();
argsBuilder.addArgument(StandardArgumentDefinitions.VARIANT_LONG_NAME, trancheVCF)
.addArgument(StandardArgumentDefinitions.OUTPUT_LONG_NAME, "%s")
.addArgument("resource", snpTruthVCF)
.addArgument("resource", indelTruthVCF)
.addArgument("tranche", "95.0")
.addArgument("tranche", "99.0")
.addArgument("tranche", "99.9")
.addArgument("info-key", "MIX_SMALL_2D_W_DROPOUT")
.addArgument(StandardArgumentDefinitions.ADD_OUTPUT_VCF_COMMANDLINE, "false");

final IntegrationTestSpec spec = new IntegrationTestSpec(argsBuilder.toString(),
Arrays.asList(largeFileTestDir + "VQSR/expected/g94982_20_1m_10m_tranched_95_99_99.9.vcf"));
spec.executeTest("testTrancheFilteringTranches", this);
}

@Test
public void testTrancheFilteringTranchesOrder() throws IOException {
final String trancheVCF = largeFileTestDir + "VQSR/g94982_20_1m_10m_python_2dcnn.vcf.gz";
final String indelTruthVCF = largeFileTestDir + "VQSR/ALL.wgs.indels_mills_devine_hg19_leftAligned_collapsed_double_hit.sites.20.1M-10M.vcf";
final String snpTruthVCF = largeFileTestDir + "VQSR/Omni25_sites_1525_samples.b37.20.1M-10M.vcf";
final ArgumentsBuilder argsBuilder = new ArgumentsBuilder();
argsBuilder.addArgument(StandardArgumentDefinitions.VARIANT_LONG_NAME, trancheVCF)
.addArgument(StandardArgumentDefinitions.OUTPUT_LONG_NAME, "%s")
.addArgument("resource", snpTruthVCF)
.addArgument("resource", indelTruthVCF)
.addArgument("tranche", "99.9")
.addArgument("tranche", "95.0")
.addArgument("tranche", "99.0")
.addArgument("info-key", "MIX_SMALL_2D_W_DROPOUT")
.addArgument(StandardArgumentDefinitions.ADD_OUTPUT_VCF_COMMANDLINE, "false");

final IntegrationTestSpec spec = new IntegrationTestSpec(argsBuilder.toString(),
Arrays.asList(largeFileTestDir + "VQSR/expected/g94982_20_1m_10m_tranched_95_99_99.9.vcf"));
spec.executeTest("testTrancheFilteringTranchesOrder", this);
}

}
3 changes: 3 additions & 0 deletions src/test/resources/large/VQSR/expected/g94982_20_1m_10m_tranched_95_99_99.9.vcf
View file
Open in desktop
Git LFS file not shown
3 changes: 3 additions & 0 deletions src/test/resources/large/VQSR/expected/g94982_20_1m_10m_tranched_99.vcf
View file
Open in desktop
Git LFS file not shown
3 changes: 3 additions & 0 deletions src/test/resources/large/VQSR/g94982_20_1m_10m_python_2dcnn.vcf.gz
View file
Open in desktop
Git LFS file not shown
3 changes: 3 additions & 0 deletions src/test/resources/large/VQSR/g94982_20_1m_10m_python_2dcnn.vcf.gz.tbi
View file
Open in desktop
Git LFS file not shown