public void GenerateVcfStrings_IncludeHeaders()
{
if (MiscUtils.IsRunningAnyLinux)
{
return; // currently failing on linux :(
}
var parser = VcfVariantParserSettings.Create(ImmutableList.Create(SampleName));
var variants = VcfVariant.TryParse(Bnd1, parser).FollowedBy(VcfVariant.TryParse(Bnd2, parser)).EnumerateSuccesses().ToList();
var wittyerVariant = WittyerBndInternal.Create(variants[0],
variants[0].ToTryOfGenotypedVcfVariant(VariantNormalizer.TrimCommonBases).GetOrThrow().Samples.Values.First(),
WittyerType.IntraChromosomeBreakend, new List <uint>(), uint.MinValue, null, variants[1]);
var headerLines = WittyerVcfWriter.GenerateVcfStrings(
WittyerResult.Create(VcfHeader.CreateBuilder(VcfVersion.FourPointOne).Build(), SampleName,
variants.Select(v => v.Contig).Distinct().ToList(), false,
new Dictionary <WittyerType, IReadOnlyList <IWittyerVariant> >(),
new Dictionary <WittyerType, IReadOnlyList <IWittyerBnd> >
{
{ WittyerType.IntraChromosomeBreakend, new List <IWittyerBnd> {
wittyerVariant
} }
}, new List <IVcfVariant>()), null, null)
.TakeWhile(line => line.StartsWith(VcfConstants.Header.Prefix)).ToList();
// 11 = VcfVersion, WHO, WHAT, WHERE, WHY, WIT, WIN, WOW, date, version, column names
Assert.Equal(11, headerLines.Count);
}
public void OverlapWorks_DupDel([NotNull] string truthVar, [NotNull] string queryVar, string type, bool isTp)
{
const string sampleName = "blah";
var vcfVariantParserSettings = VcfVariantParserSettings.Create(new List <string> {
sampleName
});
var baseVariant = VcfVariant.TryParse(truthVar, vcfVariantParserSettings).GetOrThrow();
const bool isCrossTypeOn = true;
var wittyerType = WittyerType.Parse(type);
var inputSpecs = InputSpec.GenerateCustomInputSpecs(!isCrossTypeOn, new[] { wittyerType }, percentDistance: PercentDistance).ToDictionary(s => s.VariantType, s => s);
var bndSet = new Dictionary <IGeneralBnd, IVcfVariant>();
var errorList = new List <string>();
var truthV = (IMutableWittyerSimpleVariant)WittyerVcfReader.CreateVariant(baseVariant, baseVariant.Samples.First().Value, true, sampleName,
inputSpecs, bndSet, errorList, isCrossTypeOn);
baseVariant = VcfVariant.TryParse(queryVar, vcfVariantParserSettings).GetOrThrow();
var queryV = (IMutableWittyerVariant)WittyerVcfReader.CreateVariant(baseVariant, baseVariant.Samples.First().Value, false, sampleName,
inputSpecs, bndSet, errorList, isCrossTypeOn);
var tree = TruthForest.Create(sampleName, VcfHeader.CreateBuilder(VcfVersion.FourPointOne).Build());
tree.AddTarget(truthV);
OverlappingUtils.DoOverlapping(tree.VariantTrees, queryV, OverlappingUtils.IsVariantAlleleMatch, isCrossTypeOn, true);
queryV.Finalize(WitDecision.FalsePositive, EvaluationMode.CrossTypeAndSimpleCounting, null);
truthV.Finalize(WitDecision.FalseNegative, EvaluationMode.CrossTypeAndSimpleCounting, null);
Assert.Equal(isTp ? WitDecision.TruePositive : WitDecision.FalsePositive, queryV.Sample.Wit);
Assert.Equal(isTp ? WitDecision.TruePositive : WitDecision.FalseNegative, truthV.Sample.Wit);
}
internal static IEnumerable <IBasicMetaLine> MergeMetaLines([NotNull] this IVcfHeader truthHeader,
[CanBeNull] string cmdLine, [NotNull] IVcfHeader queryHeader)
{
var truthMetaLines = truthHeader.ColumnMetaInfoLines;
var queryMetaLines = queryHeader.ColumnMetaInfoLines;
var altLines = MergeMetaInfoLines(truthMetaLines.AltLines, Alt, queryMetaLines.AltLines);
var filterLines = MergeMetaInfoLines(truthMetaLines.FilterLines, Filter, queryMetaLines.FilterLines);
var contigLines = MergeContigLines(queryMetaLines.ContigLines, truthMetaLines.ContigLines);
var infoLines = MergeTypedMetaLines(truthMetaLines.InfoLines, Info, queryMetaLines.InfoLines);
var sampleFormatLines =
MergeTypedMetaLines(truthMetaLines.SampleFormatLines, SampleFormat, queryMetaLines.SampleFormatLines);
var sampleMetaLines = MergeTypedMetaLines(truthMetaLines.SampleMetaLines, Meta, queryMetaLines.SampleMetaLines);
var builder = VcfHeader.CreateBuilder(truthHeader.Version)
.AddSampleColumn(DefaultTruthSampleName).AddSampleColumn(DefaultQuerySampleName);
truthHeader.ReferenceGenome.DoOnSuccess(r => builder.SetReference(r));
foreach (var line in altLines.Concat(filterLines).Concat(contigLines).Concat(sampleMetaLines)
.Concat(GenerateWittyerLines(infoLines, sampleFormatLines, cmdLine)))
{
yield return(line);
}
}
public void MergeHeaderWorks()
{
string GetPrefix(string line)
=> line.Split(new[] { VcfConstants.Header.MetaInfoLines.KeyValueDelimiter[0] }, 4)
.Where(it => it.Length > 2).Skip(2).FirstOrDefault();
var queryHeader = VcfHeader
.TryCreate(Path.Combine("Resources", "VcfHeaders", "query.wit-141.vcf").ToFileInfo()).GetOrThrow();
var truthHeader = VcfHeader
.TryCreate(Path.Combine("Resources", "VcfHeaders", "truth.wit-141.vcf").ToFileInfo()).GetOrThrow();
var vcfLines = truthHeader.MergedWith(queryHeader, SamplePair.Default, null).ToList();
var merged = VcfHeader.TryCreate(vcfLines)
.GetOrThrow();
MultiAssert.True(
merged.ColumnMetaInfoLines.SampleFormatLines.ContainsKey(WittyerConstants.WittyerMetaInfoLineKeys
.What));
MultiAssert.True(
merged.ColumnMetaInfoLines.SampleFormatLines.ContainsKey(WittyerConstants.WittyerMetaInfoLineKeys
.Why));
MultiAssert.True(
merged.ColumnMetaInfoLines.SampleFormatLines.ContainsKey(WittyerConstants.WittyerMetaInfoLineKeys
.Wit));
MultiAssert.True(
merged.ColumnMetaInfoLines.InfoLines.ContainsKey(WittyerConstants.WittyerMetaInfoLineKeys
.Who));
MultiAssert.True(
merged.ColumnMetaInfoLines.InfoLines.ContainsKey(WittyerConstants.WittyerMetaInfoLineKeys
.Where));
MultiAssert.True(
merged.ColumnMetaInfoLines.InfoLines.ContainsKey(WittyerConstants.WittyerMetaInfoLineKeys
.Win));
MultiAssert.True(
merged.ColumnMetaInfoLines.InfoLines.ContainsKey(WittyerConstants.WittyerMetaInfoLineKeys
.Wow));
// 1 different because of date in
// ##bcftools_viewCommand=view -h /home/hking/manta_2by250_sv_dragen/manta_2by250_sv_dragen.sv.vcf.gz; Date=Fri Jul 19 07:39:26 2019
var diffs = queryHeader.Select(GetPrefix).Where(it => it != null).ToImmutableHashSet()
.Except(merged.Select(GetPrefix).Where(it => it != null));
MultiAssert.True(diffs.Count == 1);
// 1 different because of date in
// ##bcftools_viewCommand=view -h NA12878_pbmm_v1.0.0_pbsv_v2.2.0_hg38_20190430_witty_format.vcf.gz; Date=Fri Jul 19 07:38:56 2019
diffs = truthHeader.Select(GetPrefix).Where(it => it != null).ToImmutableHashSet()
.Except(merged.Select(GetPrefix).Where(it => it != null));
MultiAssert.True(diffs.Count == 1);
MultiAssert.AssertAll();
}
public void ComparerWorks()
{
if (MiscUtils.IsRunningAnyLinux)
{
return; // currently failing on linux :(
}
IReadOnlyList <IContigInfo> CreateHeader(string fileName) => VcfHeader
.TryCreate(Path.Combine("Resources", "VcfHeaders", fileName).ToFileInfo()).GetOrThrow()
.ColumnMetaInfoLines.ContigLines.Select(kvp => kvp.Value.Contig).ToReadOnlyList();
var comparer = WittyerVcfWriter.CreateComparer(CreateHeader("query.vcf.gz"), CreateHeader("truth.vcf.gz"));
var parser = VcfVariantParserSettings.Create(ImmutableList.Create(SampleName));
var bnd1 = VcfVariant.TryParse(Bnd1, parser).GetOrThrow();
var bnd2 = VcfVariant.TryParse(Bnd2, parser).GetOrThrow();
Assert.True(comparer.Compare(bnd1, bnd2) < 0);
}
internal static IEnumerable <string> MergedWith([NotNull] this IVcfHeader truthHeader,
[NotNull] IVcfHeader queryHeader, [NotNull] ISamplePair pair, [CanBeNull] string cmdLine)
{
var mergedMetaLines = truthHeader.MergeMetaLines(cmdLine, queryHeader);
return(ToWittyBuilder()
.AddSampleMetaInfo(truthHeader, pair, queryHeader, mergedMetaLines)
.Build().ToStrings());
VcfHeader.Builder ToWittyBuilder()
{
var builder = VcfHeader.CreateBuilder(truthHeader.Version)
.AddSampleColumn(DefaultTruthSampleName).AddSampleColumn(DefaultQuerySampleName);
truthHeader.ReferenceGenome.DoOnSuccess(r => builder.SetReference(r));
return(builder);
}
}
