private static final String DEFAULT_SPECIES = "homo_sapiens";
/**
- * A class to model the mapping from sequence to VCF coordinates. Cases include
+ * A class to model the mapping from sequence to VCF coordinates. Cases
+ * include
* <ul>
* <li>a direct 1:1 mapping where the sequence is one of the VCF contigs</li>
- * <li>a mapping of sequence to chromosomal coordinates, where sequence and VCF
- * use the same reference assembly</li>
- * <li>a modified mapping of sequence to chromosomal coordinates, where sequence
- * and VCF use different reference assembles</li>
+ * <li>a mapping of sequence to chromosomal coordinates, where sequence and
+ * VCF use the same reference assembly</li>
+ * <li>a modified mapping of sequence to chromosomal coordinates, where
+ * sequence and VCF use different reference assembles</li>
* </ul>
*/
class VCFMap
private static final String VCF_SPECIES = "VCF_SPECIES"; // default is human
- private static final String DEFAULT_REFERENCE = "grch37"; // fallback default is human GRCh37
+ private static final String DEFAULT_REFERENCE = "grch37"; // fallback default
+ // is human GRCh37
/*
* keys to fields of VEP CSQ consequence data
* see https://www.ensembl.org/info/docs/tools/vep/vep_formats.html
*/
private static final String CSQ_CONSEQUENCE_KEY = "Consequence";
+
private static final String CSQ_ALLELE_KEY = "Allele";
- private static final String CSQ_ALLELE_NUM_KEY = "ALLELE_NUM"; // 0 (ref), 1...
+
+ private static final String CSQ_ALLELE_NUM_KEY = "ALLELE_NUM"; // 0 (ref),
+ // 1...
+
private static final String CSQ_FEATURE_KEY = "Feature"; // Ensembl stable id
/*
* see http://www.ensembl.org/info/docs/tools/vep/vep_formats.html
*/
private int csqConsequenceFieldIndex = -1;
+
private int csqAlleleFieldIndex = -1;
+
private int csqAlleleNumberFieldIndex = -1;
+
private int csqFeatureFieldIndex = -1;
// todo the same fields for SnpEff ANN data if wanted
*/
public SequenceI loadVCFContig(String contig)
{
- VCFHeaderLine headerLine = header.getOtherHeaderLine(VCFHeader.REFERENCE_KEY);
+ VCFHeaderLine headerLine = header
+ .getOtherHeaderLine(VCFHeader.REFERENCE_KEY);
if (headerLine == null)
{
Console.error("VCF reference header not found");
/**
* Attempts to determine and save the species and genome assembly version to
- * which the VCF data applies. This may be done by parsing the {@code reference}
- * header line, configured in a property file, or (potentially) confirmed
- * interactively by the user.
+ * which the VCF data applies. This may be done by parsing the
+ * {@code reference} header line, configured in a property file, or
+ * (potentially) confirmed interactively by the user.
* <p>
* The saved values should be identifiers valid for Ensembl's REST service
* {@code map} endpoint, so they can be used (if necessary) to retrieve the
{
try
{
- patterns.add(Pattern.compile(token.toUpperCase(Locale.ROOT)));
+ patterns.add(Pattern.compile(token.toUpperCase(Locale.ROOT)));
} catch (PatternSyntaxException e)
{
System.err.println("Invalid pattern ignored: " + token);
}
/**
- * Tries to add overlapping variants read from a VCF file to the given sequence,
- * and returns the number of variant features added
+ * Tries to add overlapping variants read from a VCF file to the given
+ * sequence, and returns the number of variant features added
*
* @param seq
* @return
vcfAssembly);
if (newRange == null)
{
- Console.error(
- String.format("Failed to map %s:%s:%s:%d:%d to %s", species,
- chromosome, seqRef, range[0], range[1],
- vcfAssembly));
+ Console.error(String.format("Failed to map %s:%s:%s:%d:%d to %s",
+ species, chromosome, seqRef, range[0], range[1],
+ vcfAssembly));
continue;
}
else
* RuntimeException throwable by htsjdk
*/
String msg = String.format("Error reading VCF for %s:%d-%d: %s ",
- map.chromosome, vcfStart, vcfEnd,e.getLocalizedMessage());
+ map.chromosome, vcfStart, vcfEnd, e.getLocalizedMessage());
Console.error(msg);
}
}
/**
* Inspects one allele and attempts to add a variant feature for it to the
* sequence. The additional data associated with this allele is extracted to
- * store in the feature's key-value map. Answers the number of features added (0
- * or 1).
+ * store in the feature's key-value map. Answers the number of features added
+ * (0 or 1).
*
* @param seq
* @param variant
* pick out the consequence data (if any) that is for the current allele
* and feature (transcript) that matches the current sequence
*/
- String consequence = getConsequenceForAlleleAndFeature(variant, CSQ_FIELD,
- altAlleleIndex, csqAlleleFieldIndex,
- csqAlleleNumberFieldIndex, seq.getName().toLowerCase(Locale.ROOT),
- csqFeatureFieldIndex);
+ String consequence = getConsequenceForAlleleAndFeature(variant,
+ CSQ_FIELD, altAlleleIndex, csqAlleleFieldIndex,
+ csqAlleleNumberFieldIndex,
+ seq.getName().toLowerCase(Locale.ROOT), csqFeatureFieldIndex);
/*
* pick out the ontology term for the consequence type
/**
* Answers the VCF FILTER value for the variant - or an approximation to it.
* This field is either PASS, or a semi-colon separated list of filters not
- * passed. htsjdk saves filters as a HashSet, so the order when reassembled into
- * a list may be different.
+ * passed. htsjdk saves filters as a HashSet, so the order when reassembled
+ * into a list may be different.
*
* @param variant
* @return
}
/**
- * Determines the Sequence Ontology term to use for the variant feature type in
- * Jalview. The default is 'sequence_variant', but a more specific term is used
- * if:
+ * Determines the Sequence Ontology term to use for the variant feature type
+ * in Jalview. The default is 'sequence_variant', but a more specific term is
+ * used if:
* <ul>
* <li>VEP (or SnpEff) Consequence annotation is included in the VCF</li>
* <li>sequence id can be matched to VEP Feature (or SnpEff Feature_ID)</li>
*/
private String getConsequenceForAlleleAndFeature(VariantContext variant,
String vcfInfoId, int altAlleleIndex, int alleleFieldIndex,
- int alleleNumberFieldIndex,
- String seqName, int featureFieldIndex)
+ int alleleNumberFieldIndex, String seqName, int featureFieldIndex)
{
if (alleleFieldIndex == -1 || featureFieldIndex == -1)
{
if (csqFields.length > featureFieldIndex)
{
String featureIdentifier = csqFields[featureFieldIndex];
- if (featureIdentifier.length() > 4
- && seqName.indexOf(featureIdentifier.toLowerCase(Locale.ROOT)) > -1)
+ if (featureIdentifier.length() > 4 && seqName
+ .indexOf(featureIdentifier.toLowerCase(Locale.ROOT)) > -1)
{
/*
* feature (transcript) matched - now check for allele match
}
/**
- * Answers true for '.', null, or an empty value, or if the INFO type is String.
- * If the INFO type is Integer or Float, answers false if the value is not in
- * valid format.
+ * Answers true for '.', null, or an empty value, or if the INFO type is
+ * String. If the INFO type is Integer or Float, answers false if the value is
+ * not in valid format.
*
* @param variant
* @param infoId
* @param toRef
* @return
*/
- protected int[] findSubsumedRangeMapping(int[] queryRange, String chromosome,
- String species, String fromRef, String toRef)
+ protected int[] findSubsumedRangeMapping(int[] queryRange,
+ String chromosome, String species, String fromRef, String toRef)
{
String key = makeRangesKey(chromosome, species, fromRef, toRef);
if (assemblyMappings.containsKey(key))
*/
int offset = queryRange[0] - fromRange[0];
int mappedRangeFrom = toRange[0] + offset;
- int mappedRangeTo = mappedRangeFrom + (queryRange[1] - queryRange[0]);
+ int mappedRangeTo = mappedRangeFrom
+ + (queryRange[1] - queryRange[0]);
return new int[] { mappedRangeFrom, mappedRangeTo };
}
}
SequenceI targetSequence, MapList mapping)
{
int[] mappedRange = mapping.locateInTo(sf.getBegin(), sf.getEnd());
-
+
if (mappedRange != null)
{
String group = sf.getFeatureGroup();
protected static String makeRangesKey(String chromosome, String species,
String fromRef, String toRef)
{
- return species + EXCL + chromosome + EXCL + fromRef + EXCL
- + toRef;
+ return species + EXCL + chromosome + EXCL + fromRef + EXCL + toRef;
}
}