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

Jump to bottom

Restore array output in gCNV WDLs for efficient postprocessing. #5490

Merged
merged 2 commits into from Jan 8, 2019
Merged

Restore array output in gCNV WDLs for efficient postprocessing. #5490

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cc4f379
Added canonicalization of all file paths passed to gCNV python scripts.
samuelklee Sep 10, 2018
08ffd75
Restore array output in gCNV WDLs for efficient postprocessing.
samuelklee Nov 19, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
13 changes: 7 additions & 6 deletions ...in/java/org/broadinstitute/hellbender/tools/copynumber/DetermineGermlineContigPloidy.java
View file
Open in desktop
Expand Up @@ -18,6 +18,7 @@
import org.broadinstitute.hellbender.tools.copynumber.formats.metadata.LocatableMetadata;
import org.broadinstitute.hellbender.tools.copynumber.formats.records.CoveragePerContig;
import org.broadinstitute.hellbender.tools.copynumber.formats.records.SimpleCount;
import org.broadinstitute.hellbender.tools.copynumber.utils.CopyNumberUtils;
import org.broadinstitute.hellbender.utils.SimpleInterval;
import org.broadinstitute.hellbender.utils.Utils;
import org.broadinstitute.hellbender.utils.io.IOUtils;
Expand Down Expand Up @@ -385,20 +386,20 @@ private boolean executeDeterminePloidyAndDepthPythonScript(final File samplesByC
: outputDir + File.separator; //add trailing slash if necessary
//note that the samples x coverage-by-contig table is referred to as "metadata" by gcnvkernel
final List<String> arguments = new ArrayList<>(Arrays.asList(
"--sample_coverage_metadata=" + samplesByCoveragePerContigFile.getAbsolutePath(),
"--output_calls_path=" + outputDirArg + outputPrefix + CALLS_PATH_SUFFIX));
"--sample_coverage_metadata=" + CopyNumberUtils.getCanonicalPath(samplesByCoveragePerContigFile),
"--output_calls_path=" + CopyNumberUtils.getCanonicalPath(outputDirArg + outputPrefix + CALLS_PATH_SUFFIX)));
arguments.addAll(germlineContigPloidyModelArgumentCollection.generatePythonArguments(runMode));
arguments.addAll(germlineContigPloidyHybridADVIArgumentCollection.generatePythonArguments());

final String script;
if (runMode == RunMode.COHORT) {
script = COHORT_DETERMINE_PLOIDY_AND_DEPTH_PYTHON_SCRIPT;
arguments.add("--interval_list=" + intervalsFile.getAbsolutePath());
arguments.add("--contig_ploidy_prior_table=" + inputContigPloidyPriorsFile.getAbsolutePath());
arguments.add("--output_model_path=" + outputDirArg + outputPrefix + MODEL_PATH_SUFFIX);
arguments.add("--interval_list=" + CopyNumberUtils.getCanonicalPath(intervalsFile));
samuelklee marked this conversation as resolved.
Show resolved Hide resolved
arguments.add("--contig_ploidy_prior_table=" + CopyNumberUtils.getCanonicalPath(inputContigPloidyPriorsFile));
arguments.add("--output_model_path=" + CopyNumberUtils.getCanonicalPath(outputDirArg + outputPrefix + MODEL_PATH_SUFFIX));
} else {
script = CASE_DETERMINE_PLOIDY_AND_DEPTH_PYTHON_SCRIPT;
arguments.add("--input_model_path=" + inputModelDir);
arguments.add("--input_model_path=" + CopyNumberUtils.getCanonicalPath(inputModelDir));
}
return executor.executeScript(
new Resource(script, GermlineCNVCaller.class),
Expand Down
15 changes: 8 additions & 7 deletions src/main/java/org/broadinstitute/hellbender/tools/copynumber/GermlineCNVCaller.java
View file
Open in desktop
Expand Up @@ -13,6 +13,7 @@
import org.broadinstitute.hellbender.tools.copynumber.formats.collections.SimpleCountCollection;
import org.broadinstitute.hellbender.tools.copynumber.formats.collections.SimpleIntervalCollection;
import org.broadinstitute.hellbender.tools.copynumber.formats.records.SimpleCount;
import org.broadinstitute.hellbender.tools.copynumber.utils.CopyNumberUtils;
import org.broadinstitute.hellbender.utils.SimpleInterval;
import org.broadinstitute.hellbender.utils.Utils;
import org.broadinstitute.hellbender.utils.io.IOUtils;
Expand Down Expand Up @@ -406,21 +407,21 @@ private boolean executeGermlineCNVCallerPythonScript(final List<File> intervalSu

//add required arguments
final List<String> arguments = new ArrayList<>(Arrays.asList(
"--ploidy_calls_path=" + inputContigPloidyCallsDir,
"--output_calls_path=" + outputDirArg + outputPrefix + CALLS_PATH_SUFFIX,
"--output_tracking_path=" + outputDirArg + outputPrefix + TRACKING_PATH_SUFFIX));
"--ploidy_calls_path=" + CopyNumberUtils.getCanonicalPath(inputContigPloidyCallsDir),
"--output_calls_path=" + CopyNumberUtils.getCanonicalPath(outputDirArg + outputPrefix + CALLS_PATH_SUFFIX),
"--output_tracking_path=" + CopyNumberUtils.getCanonicalPath(outputDirArg + outputPrefix + TRACKING_PATH_SUFFIX)));

//if a model path is given, add it to the argument (both COHORT and CASE modes)
if (inputModelDir != null) {
arguments.add("--input_model_path=" + inputModelDir);
arguments.add("--input_model_path=" + CopyNumberUtils.getCanonicalPath(inputModelDir));
}

final String script;
if (runMode == RunMode.COHORT) {
script = COHORT_DENOISING_CALLING_PYTHON_SCRIPT;
//these are the annotated intervals, if provided
arguments.add("--modeling_interval_list=" + specifiedIntervalsFile.getAbsolutePath());
arguments.add("--output_model_path=" + outputDirArg + outputPrefix + MODEL_PATH_SUFFIX);
arguments.add("--modeling_interval_list=" + CopyNumberUtils.getCanonicalPath(specifiedIntervalsFile));
arguments.add("--output_model_path=" + CopyNumberUtils.getCanonicalPath(outputDirArg + outputPrefix + MODEL_PATH_SUFFIX));
if (inputAnnotatedIntervalsFile != null) {
arguments.add("--enable_explicit_gc_bias_modeling=True");
} else {
Expand All @@ -432,7 +433,7 @@ private boolean executeGermlineCNVCallerPythonScript(final List<File> intervalSu
}

arguments.add("--read_count_tsv_files");
arguments.addAll(intervalSubsetReadCountFiles.stream().map(File::getAbsolutePath).collect(Collectors.toList()));
arguments.addAll(intervalSubsetReadCountFiles.stream().map(CopyNumberUtils::getCanonicalPath).collect(Collectors.toList()));

arguments.addAll(germlineDenoisingModelArgumentCollection.generatePythonArguments(runMode));
arguments.addAll(germlineCallingArgumentCollection.generatePythonArguments(runMode));
Expand Down
34 changes: 34 additions & 0 deletions src/main/java/org/broadinstitute/hellbender/tools/copynumber/utils/CopyNumberUtils.java
View file
Open in desktop
@@ -0,0 +1,34 @@
package org.broadinstitute.hellbender.tools.copynumber.utils;

import org.broadinstitute.hellbender.exceptions.UserException;
import org.broadinstitute.hellbender.utils.Utils;
import org.broadinstitute.hellbender.utils.python.PythonScriptExecutor;

import java.io.File;
import java.io.IOException;

public final class CopyNumberUtils {
private CopyNumberUtils() {}

/**
* File paths that are passed to {@link PythonScriptExecutor} must be canonical (rather than absolute).
* See https://github.com/broadinstitute/gatk/issues/4724.
*/
public static String getCanonicalPath(final File file) {
Utils.nonNull(file);
try {
return file.getCanonicalPath();
} catch (final IOException e) {
throw new UserException.BadInput(String.format("Could not resolve a canonical file path: %s", file));
}
}

/**
* File paths that are passed to {@link PythonScriptExecutor} must be canonical (rather than absolute).
* See https://github.com/broadinstitute/gatk/issues/4724.
*/
public static String getCanonicalPath(final String filename) {
Utils.nonEmpty(filename);
return getCanonicalPath(new File(filename));
}
}