/// <summary>
/// returns a JSON object given a vcf line (no annotation is performed)
/// </summary>
internal static UnifiedJson GetJson(string vcfLine, ChromosomeRenamer renamer)
{
var variantFeature = VcfUtilities.GetVariant(vcfLine, renamer);
var json = new UnifiedJson(variantFeature);
json.AddVariantData(variantFeature);
return(json);
}
private static void WriteOmim(IAnnotationSource annotator, UnifiedJsonWriter unifiedJsonWriter)
{
var omimAnnotations = new List <string>();
annotator.AddGeneLevelAnnotation(omimAnnotations);
var annotionOutput = UnifiedJson.GetGeneAnnotation(omimAnnotations, "omim");
unifiedJsonWriter.Write(annotionOutput);
}
/// <summary>
/// constructor
/// </summary>
public UnifiedJsonWriter(StreamWriter writer, string creationTime, string vepDataVersion, IEnumerable <IDataSourceVersion> iDataSourceVersions, string genomeAssembly, string[] sampleNames)
{
_writer = writer;
_writer.NewLine = "\n";
var dataSourceVersions = iDataSourceVersions?.Select(iDataSourceVersion => iDataSourceVersion as DataSourceVersion).ToList();
// write the header
_writer.Write(UnifiedJson.GetHeader(NirvanaAnnotationSource.GetVersion(), creationTime, genomeAssembly,
JsonCommon.SchemaVersion, vepDataVersion, dataSourceVersions, sampleNames));
}
private static void ExtractCsqs(UnifiedJson unifiedJson, List <CsqEntry> csqs)
{
foreach (var jsonVariant in unifiedJson.AnnotatedAlternateAlleles)
{
csqs.AddRange(
jsonVariant.EnsemblTranscripts.Where(transcript => transcript.IsCanonical == "true")
.Select(transcript => new CsqEntry
{
Allele = jsonVariant.GenotypeIndex.ToString(),
Canonical = transcript.IsCanonical,
Feature = transcript.TranscriptID,
FeatureType = CsqCommon.TranscriptFeatureType,
Symbol = transcript.Hgnc,
Consequence = transcript.Consequence == null ? null : string.Join("&", transcript.Consequence)
}));
csqs.AddRange(from transcript in jsonVariant.RefSeqTranscripts
where transcript.IsCanonical == "true"
select new CsqEntry
{
Allele = jsonVariant.GenotypeIndex.ToString(),
Canonical = transcript.IsCanonical,
Feature = transcript.TranscriptID,
FeatureType = CsqCommon.TranscriptFeatureType,
Symbol = transcript.Hgnc,
Consequence = transcript.Consequence == null ? null : string.Join("&", transcript.Consequence)
});
csqs.AddRange(jsonVariant.RegulatoryRegions.Select(regulatoryRegion => new CsqEntry
{
Allele = jsonVariant.GenotypeIndex.ToString(),
Consequence = string.Join("&", regulatoryRegion.Consequence),
Feature = regulatoryRegion.ID,
FeatureType = CsqCommon.RegulatoryFeatureType
}));
}
}
private static void ExtractInfo(UnifiedJson unifiedJson, VcfField infoEntries)
{
var alleleFreq1000G = new VcfInfoKeyValue("AF1000G");
var ancestralAllele = new VcfInfoKeyValue("AA");
var clinVar = new VcfInfoKeyValue("clinvar");
var cosmic = new VcfInfoKeyValue("cosmic");
var evs = new VcfInfoKeyValue("EVS");
var globalMinorAllele = new VcfInfoKeyValue("GMAF");
var phyloP = new VcfInfoKeyValue("phyloP");
foreach (var jsonVariant in unifiedJson.AnnotatedAlternateAlleles)
{
if (jsonVariant.IsReferenceMinor)
{
infoEntries.Add("RefMinor");
}
phyloP.Add(jsonVariant.PhylopScore);
ancestralAllele.Add(jsonVariant.AncestralAllele);
foreach (var cosmicEntry in jsonVariant.CosmicEntries)
{
if (cosmicEntry.ID == null)
{
continue;
}
if (cosmicEntry.SaAltAllele != jsonVariant.SaAltAllele)
{
continue;
}
cosmic.Add(jsonVariant.GenotypeIndex.ToString(CultureInfo.InvariantCulture) + '|' + cosmicEntry.ID);
}
foreach (var clinVarEntry in jsonVariant.ClinVarEntries)
{
if (clinVarEntry.Significance == null)
{
continue;
}
if (clinVarEntry.SaAltAllele != jsonVariant.SaAltAllele)
{
continue;
}
clinVar.Add(jsonVariant.GenotypeIndex.ToString(CultureInfo.InvariantCulture) + '|' + RemoveWhiteSpaceAndComma(clinVarEntry.Significance));
}
if (jsonVariant.GlobalMinorAllele != null || jsonVariant.GlobalMinorAlleleFrequency != null)
{
globalMinorAllele.Add(jsonVariant.GlobalMinorAllele + '|' + jsonVariant.GlobalMinorAlleleFrequency);
}
else
{
// for multi allelic variants, we need to add a . for the entries that do not have a Global minor allele.
globalMinorAllele.Add(null);
}
alleleFreq1000G.Add(jsonVariant.AlleleFrequencyAll);
if (jsonVariant.EvsAlleleFrequencyAll != null || jsonVariant.EvsCoverage != null || jsonVariant.EvsSamples != null)
{
evs.Add(jsonVariant.EvsAlleleFrequencyAll + '|' + jsonVariant.EvsCoverage + '|' + jsonVariant.EvsSamples);
}
else
{
evs.Add(null);
}
}
infoEntries.Add(ancestralAllele.GetString());
infoEntries.Add(globalMinorAllele.GetString());
infoEntries.Add(alleleFreq1000G.GetString());
infoEntries.Add(evs.GetString());
infoEntries.Add(phyloP.GetString());
infoEntries.Add(cosmic.GetString());
infoEntries.Add(clinVar.GetString());
}
