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.

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

ah - use new GT encoding #6822

Merged
merged 4 commits into from
Sep 16, 2020
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
@@ -1,29 +1,51 @@
package org.broadinstitute.hellbender.tools.variantdb;

import htsjdk.samtools.SAMSequenceDictionary;
import htsjdk.variant.variantcontext.Allele;
import htsjdk.variant.variantcontext.VariantContext;
import htsjdk.variant.vcf.*;
import org.apache.commons.lang.StringUtils;
import org.broadinstitute.hellbender.tools.variantdb.arrays.RawArrayTsvCreator;
import org.broadinstitute.hellbender.utils.genotyper.IndexedAlleleList;
import org.broadinstitute.hellbender.utils.variant.GATKVCFConstants;
import org.broadinstitute.hellbender.utils.variant.GATKVCFHeaderLines;

import java.util.ArrayList;
import java.util.HashSet;
import java.util.List;
import java.util.Set;

//TODO rename this or get rid of it. a place holder for now
public class CommonCode {
public static final String NORMX = "NORMX";
public static final String NORMY = "NORMY";
public static final String BAF = "BAF";
public static final String LRR = "LRR";


public static String getGTString(final VariantContext variant) {
Copy link
Contributor

Choose a reason for hiding this comment

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

I'm so surprised this code doesn't exist anywhere? the VCFWriter must be doing (largely) the same thing?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

yes, but it is very embedded in the actual writing of the output and in htsjdk which for some reason i think it's more difficult for us to modify to make it modular.

List<Integer> allele_indices = getGTAlleleIndexes(variant);
if (allele_indices.size() != 2){
throw new IllegalArgumentException("GT doesnt have two alleles");
}
String separator = variant.getGenotype(0).isPhased() ? VCFConstants.PHASED : VCFConstants.UNPHASED;
return StringUtils.join(allele_indices, separator);
}

public static List<Integer> getGTAlleleIndexes(final VariantContext variant) {
IndexedAlleleList<Allele> alleleList = new IndexedAlleleList<>(variant.getAlleles());
ArrayList<Integer> allele_indices = new ArrayList<Integer>();

for (Allele allele : variant.getGenotype(0).getAlleles()) {
allele_indices.add(alleleList.indexOfAllele(allele));
}
return allele_indices;
}

public static VCFHeader generateRawArrayVcfHeader(Set<String> sampleNames, final SAMSequenceDictionary sequenceDictionary) {
final Set<VCFHeaderLine> lines = new HashSet<>();

lines.add(VCFStandardHeaderLines.getFormatLine(VCFConstants.GENOTYPE_KEY));
lines.add(new VCFFormatHeaderLine(NORMX, 1, VCFHeaderLineType.Float, "Normalized X intensity"));
lines.add(new VCFFormatHeaderLine(NORMY, 1, VCFHeaderLineType.Float, "Normalized Y intensity"));
lines.add(new VCFFormatHeaderLine(BAF, 1, VCFHeaderLineType.Float, "B Allele Frequency"));
lines.add(new VCFFormatHeaderLine(LRR, 1, VCFHeaderLineType.Float, "Log R Ratio"));
lines.add(new VCFFormatHeaderLine(RawArrayTsvCreator.NORMX, 1, VCFHeaderLineType.Float, "Normalized X intensity"));
lines.add(new VCFFormatHeaderLine(RawArrayTsvCreator.NORMY, 1, VCFHeaderLineType.Float, "Normalized Y intensity"));
lines.add(new VCFFormatHeaderLine(RawArrayTsvCreator.BAF, 1, VCFHeaderLineType.Float, "B Allele Frequency"));
lines.add(new VCFFormatHeaderLine(RawArrayTsvCreator.LRR, 1, VCFHeaderLineType.Float, "Log R Ratio"));


final VCFHeader header = new VCFHeader(lines, sampleNames);
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -4,8 +4,7 @@ public class IngestConstants {

public static final char SEPARATOR = '\t';
public static final String FILETYPE = ".tsv";
public static final String metadataFilePrefix = "metadata_";
public static final String metadataDirectoryName = "metadata"; // TODO remove
public static final String sampleMetadataFilePrefix = "sample_";
public static final int partitionPerTable = 4000;

}
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,6 @@
import org.broadinstitute.hellbender.engine.ProgressMeter;
import org.broadinstitute.hellbender.engine.ReferenceDataSource;
import org.broadinstitute.hellbender.tools.variantdb.arrays.BasicArrayData.ArrayGenotype;
import org.broadinstitute.hellbender.tools.variantdb.CommonCode;
import org.broadinstitute.hellbender.tools.variantdb.SchemaUtils;
import org.broadinstitute.hellbender.tools.variantdb.arrays.tables.ProbeInfo;
import org.broadinstitute.hellbender.tools.walkers.ReferenceConfidenceVariantContextMerger;
Expand Down Expand Up @@ -375,10 +374,10 @@ private VariantContext createVariantContextFromSampleRecord(final ProbeInfo prob
}
genotypeBuilder.alleles(genotypeAlleles);

genotypeBuilder.attribute(CommonCode.NORMX, formatFloatForVcf(normx));
genotypeBuilder.attribute(CommonCode.NORMY, formatFloatForVcf(normy));
genotypeBuilder.attribute(CommonCode.BAF, formatFloatForVcf(baf));
genotypeBuilder.attribute(CommonCode.LRR, formatFloatForVcf(lrr));
genotypeBuilder.attribute(RawArrayTsvCreator.NORMX, formatFloatForVcf(normx));
genotypeBuilder.attribute(RawArrayTsvCreator.NORMY, formatFloatForVcf(normy));
genotypeBuilder.attribute(RawArrayTsvCreator.BAF, formatFloatForVcf(baf));
genotypeBuilder.attribute(RawArrayTsvCreator.LRR, formatFloatForVcf(lrr));

genotypeBuilder.name(sample);

Expand Down

This file was deleted.

Original file line number Diff line number Diff line change
@@ -0,0 +1,100 @@
package org.broadinstitute.hellbender.tools.variantdb.arrays;

import htsjdk.variant.variantcontext.VariantContext;
import org.broadinstitute.hellbender.tools.variantdb.CommonCode;
import org.broadinstitute.hellbender.tools.variantdb.arrays.tables.ProbeInfo;

import java.util.*;



public enum ArraySampleFieldEnum {
sample_id,
sample_name,


// This where the validation step (required vs not) lives -- fail if there is missing data for a required field
// and just leave it empty if not required

NUM_ASSAYS {
public String getColumnValue(final Map<String, String> metricsMap) {
return metricsMap.get(this.name());
}
},
NUM_NON_FILTERED_ASSAYS{
public String getColumnValue(final Map<String, String> metricsMap) {
return metricsMap.get(this.name());
}
},
NUM_FILTERED_ASSAYS{
public String getColumnValue(final Map<String, String> metricsMap) {
return metricsMap.get(this.name());
}
},
NUM_ZEROED_OUT_ASSAYS{
public String getColumnValue(final Map<String, String> metricsMap) {
return metricsMap.get(this.name());
}
},
NUM_SNPS{
public String getColumnValue(final Map<String, String> metricsMap) {
return metricsMap.get(this.name());
}
},
NUM_INDELS{
public String getColumnValue(final Map<String, String> metricsMap) {
return metricsMap.get(this.name());
}
},
NUM_CALLS{
public String getColumnValue(final Map<String, String> metricsMap) {
return metricsMap.get(this.name());
}
},
NUM_AUTOCALL_CALLS{
public String getColumnValue(final Map<String, String> metricsMap) {
return metricsMap.get(this.name());
}
},
NUM_NO_CALLS{
public String getColumnValue(final Map<String, String> metricsMap) {
return metricsMap.get(this.name());
}
},
NUM_IN_DB_SNP{
public String getColumnValue(final Map<String, String> metricsMap) {
return metricsMap.get(this.name());
}
},
NOVEL_SNPS{
public String getColumnValue(final Map<String, String> metricsMap) {
return metricsMap.get(this.name());
}
},

PCT_DBSNP{
public String getColumnValue(final Map<String, String> metricsMap) {
return metricsMap.get(this.name());
}
},
CALL_RATE{
public String getColumnValue(final Map<String, String> metricsMap) {
return metricsMap.get(this.name());
}
},
AUTOCALL_CALL_RATE{
public String getColumnValue(final Map<String, String> metricsMap) {
return metricsMap.get(this.name());
}
},
NUM_SINGLETONS{
public String getColumnValue(final Map<String, String> metricsMap) {
return metricsMap.get(this.name());
}
};

public String getColumnValue(final Map<String, String> metricsMap) {
throw new IllegalArgumentException("Not implemented");
}

}
Original file line number Diff line number Diff line change
@@ -0,0 +1,110 @@
package org.broadinstitute.hellbender.tools.variantdb.arrays;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.broadinstitute.hellbender.exceptions.UserException;
import org.broadinstitute.hellbender.tools.variantdb.IngestConstants;
import org.broadinstitute.hellbender.utils.tsv.SimpleXSVWriter;

import java.io.*;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import java.util.Map;
import java.util.stream.Collectors;
import java.util.stream.IntStream;

public class ArraySampleTsvCreator {

private static final Logger logger = LogManager.getLogger(ArraySampleTsvCreator.class);

private SimpleXSVWriter sampleMetadataWriter = null;
private Map<String, String> metricsMap;


public ArraySampleTsvCreator(String metricsFilepath) {
if (metricsFilepath != null && !metricsFilepath.isEmpty()) {
BufferedReader reader = null;
try {
String columns = null;
String values = null;
reader = new BufferedReader(new FileReader(metricsFilepath));
String line = reader.readLine();
while (line != null) {
if (!line.startsWith("#") && !line.trim().isEmpty()) {
if (columns == null) {
columns = line;
} else if (values == null) {
values = line;
} else {
// there are more lines than expected - output a warning
logger.warn("more lines than expected in metrics file: " + line);
}
}
line = reader.readLine();
}

List<String> colList = Arrays.asList(columns.split("\t"));
List<String> valList = Arrays.asList(values.split("\t"));
metricsMap = IntStream.range(0, colList.size()).boxed().collect(Collectors.toMap(colList::get, valList::get));

} catch (IOException e) {
throw new RuntimeException("could not read metrics file", e);
}
}
}

public static List<String> getHeaders() {
return Arrays.stream(ArraySampleFieldEnum.values()).map(String::valueOf).collect(Collectors.toList());
}

public void createRow(String sampleName, String sampleId, String tableNumberPrefix, File outputDirectory) {
// if the metadata tsvs don't exist yet -- create them
try {
// Create a metadata file to go into the metadata dir for _this_ sample
// TODO--this should just be one file per sample set?
final File sampleMetadataFileName = new File (outputDirectory, IngestConstants.sampleMetadataFilePrefix + tableNumberPrefix + sampleName + IngestConstants.FILETYPE);
// write header to it
List<String> sampleListHeader = ArraySampleTsvCreator.getHeaders();
sampleMetadataWriter = new SimpleXSVWriter(sampleMetadataFileName.toPath(), IngestConstants.SEPARATOR);
sampleMetadataWriter.setHeaderLine(sampleListHeader);

final List<String> TSVLineToCreateSampleMetadata = createSampleListRow(
sampleName,
sampleId);
sampleMetadataWriter.getNewLineBuilder().setRow(TSVLineToCreateSampleMetadata).write();

} catch (final IOException e) {
throw new UserException("Could not create sample outputs", e);
}

}

private List<String> createSampleListRow(String sampleName, String sampleId) {
List<String> row = new ArrayList<>();
row.add(sampleName);
row.add(sampleId);

for (final ArraySampleFieldEnum fieldEnum : ArraySampleFieldEnum.values()) {
if (fieldEnum != ArraySampleFieldEnum.sample_id && fieldEnum != ArraySampleFieldEnum.sample_name) {
if (metricsMap == null) {
row.add("null");
} else {
row.add(fieldEnum.getColumnValue(metricsMap));
}
}
}
return row;
}

public void closeTool() {
if (sampleMetadataWriter != null) {
try {
sampleMetadataWriter.close();
} catch (final Exception e) {
throw new IllegalArgumentException("Couldn't close array sample writer", e);
}
}

}
}
Loading