internal static ISample ExtractSample(string sampleColumn, FormatIndices formatIndices, ISimplePosition simplePosition,
IMitoHeteroplasmyProvider mitoHeteroplasmyProvider, LegacySampleFieldExtractor legacyExtractor = null, bool enableDq = false)
{
// sanity check: make sure we have a format column
if (string.IsNullOrEmpty(sampleColumn))
{
return(Sample.EmptySample);
}
string[] sampleColumns = sampleColumn.OptimizedSplit(':', formatIndices.NumColumns);
if (sampleColumns.Length == 1 && sampleColumns[0] == ".")
{
return(Sample.EmptySample);
}
sampleColumns.NormalizeNulls();
if (legacyExtractor != null)
{
return(legacyExtractor.ExtractSample(sampleColumn));
}
int[] alleleDepths = sampleColumns.GetString(formatIndices.AD).GetIntegers();
float?artifactAdjustedQualityScore = sampleColumns.GetString(formatIndices.AQ).GetFloat();
int? copyNumber = sampleColumns.GetString(formatIndices.CN).GetInteger();
string[] diseaseAffectedStatuses = sampleColumns.GetString(formatIndices.DST).GetStrings();
bool failedFilter = sampleColumns.GetString(formatIndices.FT).GetFailedFilter();
string genotype = sampleColumns.GetString(formatIndices.GT);
int? genotypeQuality = sampleColumns.GetString(formatIndices.GQ).GetInteger();
bool isDeNovo = sampleColumns.GetString(formatIndices.DN).IsDeNovo();
double? deNovoQuality = enableDq? sampleColumns.GetString(formatIndices.DQ).GetDouble():null;
float? likelihoodRatioQualityScore = sampleColumns.GetString(formatIndices.LQ).GetFloat();
int[] pairedEndReadCounts = sampleColumns.GetString(formatIndices.PR).GetIntegers();
int[] repeatUnitCounts = sampleColumns.GetString(formatIndices.REPCN).GetIntegers('/');
int[] splitReadCounts = sampleColumns.GetString(formatIndices.SR).GetIntegers();
int? totalDepth = sampleColumns.GetString(formatIndices.DP).GetInteger();
double?variantFrequency = sampleColumns.GetString(formatIndices.VF).GetDouble();
int? minorHaplotypeCopyNumber = sampleColumns.GetString(formatIndices.MCN).GetInteger();
double?somaticQuality = sampleColumns.GetString(formatIndices.SQ).GetDouble();
int? binCount = sampleColumns.GetString(formatIndices.BC).GetInteger();
double[] variantFrequencies = VariantFrequency.GetVariantFrequencies(variantFrequency, alleleDepths, simplePosition.AltAlleles.Length);
string[] mitoHeteroplasmyPercentiles = mitoHeteroplasmyProvider?.GetVrfPercentiles(simplePosition.Chromosome, simplePosition.Start,
simplePosition.AltAlleles, variantFrequencies)?.Select(x => x?.ToString("0.##") ?? "null").ToArray();
var isLoh = GetLoh(copyNumber, minorHaplotypeCopyNumber, genotype);
var sample = new Sample(alleleDepths, artifactAdjustedQualityScore, copyNumber, diseaseAffectedStatuses,
failedFilter, genotype, genotypeQuality, isDeNovo, deNovoQuality, likelihoodRatioQualityScore, pairedEndReadCounts,
repeatUnitCounts, splitReadCounts, totalDepth, variantFrequencies, minorHaplotypeCopyNumber, somaticQuality, isLoh, mitoHeteroplasmyPercentiles, binCount);
return(sample);
}
internal static ISample ExtractSample(string sampleColumn, FormatIndices formatIndices, int numAltAlleles,
LegacySampleFieldExtractor legacyExtractor = null)
{
// sanity check: make sure we have a format column
if (string.IsNullOrEmpty(sampleColumn))
{
return(Sample.EmptySample);
}
string[] sampleColumns = sampleColumn.OptimizedSplit(':', formatIndices.NumColumns);
if (sampleColumns.Length == 1 && sampleColumns[0] == ".")
{
return(Sample.EmptySample);
}
sampleColumns.NormalizeNulls();
if (legacyExtractor != null)
{
return(legacyExtractor.ExtractSample(sampleColumn));
}
int[] alleleDepths = sampleColumns.GetString(formatIndices.AD).GetIntegers();
float?artifactAdjustedQualityScore = sampleColumns.GetString(formatIndices.AQ).GetFloat();
int? copyNumber = sampleColumns.GetString(formatIndices.CN).GetInteger();
string[] diseaseAffectedStatuses = sampleColumns.GetString(formatIndices.DST).GetStrings();
bool failedFilter = sampleColumns.GetString(formatIndices.FT).GetFailedFilter();
string genotype = sampleColumns.GetString(formatIndices.GT);
int? genotypeQuality = sampleColumns.GetString(formatIndices.GQ).GetInteger();
bool isDeNovo = sampleColumns.GetString(formatIndices.DN).IsDeNovo();
float? likelihoodRatioQualityScore = sampleColumns.GetString(formatIndices.LQ).GetFloat();
int[] pairedEndReadCounts = sampleColumns.GetString(formatIndices.PR).GetIntegers();
int[] repeatUnitCounts = sampleColumns.GetString(formatIndices.REPCN).GetIntegers('/');
int[] splitReadCounts = sampleColumns.GetString(formatIndices.SR).GetIntegers();
int? totalDepth = sampleColumns.GetString(formatIndices.DP).GetInteger();
double?variantFrequency = sampleColumns.GetString(formatIndices.VF).GetDouble();
int? minorHaplotypeCopyNumber = sampleColumns.GetString(formatIndices.MCN).GetInteger();
double?somaticQuality = sampleColumns.GetString(formatIndices.SQ).GetDouble();
double[] variantFrequencies = VariantFrequency.GetVariantFrequencies(variantFrequency, alleleDepths, numAltAlleles);
var isLoh = GetLoh(copyNumber, minorHaplotypeCopyNumber, genotype);
var sample = new Sample(alleleDepths, artifactAdjustedQualityScore, copyNumber, diseaseAffectedStatuses,
failedFilter, genotype, genotypeQuality, isDeNovo, likelihoodRatioQualityScore, pairedEndReadCounts,
repeatUnitCounts, splitReadCounts, totalDepth, variantFrequencies, minorHaplotypeCopyNumber, somaticQuality, isLoh);
return(sample);
}
/// <summary>
/// returns a JsonSample object given the data contained within the sample genotype
/// field.
/// </summary>
private ISample ExtractSample(string sampleColumn)
{
// sanity check: make sure we have a format column
if (_formatIndices == null || string.IsNullOrEmpty(sampleColumn))
{
return(Sample.EmptySample);
}
var sampleColumns = sampleColumn.Split(':');
// handle missing sample columns
if (sampleColumns.Length == 1 && sampleColumns[0] == ".")
{
return(Sample.EmptySample);
}
var sampleFields = new IntermediateSampleFields(_vcfColumns, _formatIndices, sampleColumns);
var alleleDepths = AlleleDepths.GetAlleleDepths(sampleFields);
var failedFilter = FailedFilter.GetFailedFilter(sampleFields);
var genotype = Genotype.GetGenotype(sampleFields);
var genotypeQuality = GenotypeQuality.GetGenotypeQuality(sampleFields);
var totalDepth = TotalDepth.GetTotalDepth(_infoDepth, sampleFields);
var variantFrequencies = VariantFrequency.GetVariantFrequencies(sampleFields);
var splitReadCounts = ReadCounts.GetSplitReadCounts(sampleFields);
var pairEndReadCounts = ReadCounts.GetPairEndReadCounts(sampleFields);
var isLossOfHeterozygosity = sampleFields.MajorChromosomeCount != null && sampleFields.CopyNumber != null &&
sampleFields.MajorChromosomeCount.Value == sampleFields.CopyNumber.Value &&
sampleFields.CopyNumber.Value > 1;
var sample = new Sample(genotype, genotypeQuality, variantFrequencies, totalDepth, alleleDepths, failedFilter,
sampleFields.CopyNumber, isLossOfHeterozygosity, sampleFields.DenovoQuality, splitReadCounts,
pairEndReadCounts, sampleFields.RepeatNumber, sampleFields.RepeatNumberSpan, sampleFields.MAD,
sampleFields.SCH, sampleFields.PLG, sampleFields.PCN, sampleFields.DCS, sampleFields.DID,
sampleFields.DST, sampleFields.PCH, sampleFields.CHC, sampleFields.AQ, sampleFields.LQ);
return(sample);
}