public void FastForward_EnsemblNamingStyle_ChangeReaderStateCorrectly()
{
var annotationRange = new GenomicRange(new GenomicPosition(ChromosomeUtilities.Chr1, 100), new GenomicPosition(ChromosomeUtilities.Chr1, 200));
var vcfFilter = new VcfFilter(annotationRange);
const string firstLineInRange = "1\t100\t.\tC\tT\t165.00\tPASS\tSNVSB=-12.5;SNVHPOL=2\tGT:GQ:GQX:DP:DPF:AD\t0/1:119:35:25:0:8,17";
using (var ms = new MemoryStream())
{
using (var writer = new StreamWriter(ms, Encoding.UTF8, 1024, true))
{
writer.WriteLine("#Header line 1");
writer.WriteLine("#Header line 2");
writer.WriteLine("#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\tMother");
writer.WriteLine("2\t150\t.\tG\tA\t5.00\tLowGQXHetSNP\tSNVSB=0.0;SNVHPOL=2\tGT:GQ:GQX:DP:DPF:AD\t0/1:3:1:1:0:0,1");
writer.WriteLine("1\t90\t.\tT\tC\t1.00\tLowGQXHetSNP\tSNVSB=0.0;SNVHPOL=2\tGT:GQ:GQX:DP:DPF:AD\t0/1:23:9:3:0:2,1");
writer.WriteLine("1\t95\t.\tA\tT\t2.00\tLowGQXHetSNP\tSNVSB=0.0;SNVHPOL=2\tGT:GQ:GQX:DP:DPF:AD\t0/1:23:9:3:0:2,1");
writer.WriteLine(firstLineInRange);
writer.WriteLine("1\t102\t.\tC\tA\t3.00\tLowGQXHetSNP\tSNVSB=0.0;SNVHPOL=5\tGT:GQ:GQX:DP:DPF:AD\t0/1:29:2:2:0:1,1");
}
ms.Position = 0;
using (var reader = new StreamReader(ms))
{
vcfFilter.FastForward(reader);
Assert.Equal(firstLineInRange, vcfFilter.BufferedLine);
}
}
}
public void GetPositions_inRange()
{
var chromosome = new Chromosome("chr1", "1", 0);
var annotationRange = new GenomicRange(new GenomicPosition(chromosome, 10019), new GenomicPosition(chromosome, 10290));
var seqProvider = ParserTestUtils.GetSequenceProvider(10329, "AC", 'A', _chromDict);
var positions = PreLoadUtilities.GetPositions(GetVcfStream(), annotationRange, seqProvider);
Assert.Single(positions);
Assert.Equal(3, positions[Chrom1].Count);
}
public void GetPositions_inRange()
{
var annotationRange = new GenomicRange(new GenomicPosition(ChromosomeUtilities.Chr1, 10019), new GenomicPosition(ChromosomeUtilities.Chr1, 10290));
var seqProvider = ParserTestUtils.GetSequenceProvider(10329, "AC", 'A', ChromosomeUtilities.RefNameToChromosome);
(var positions, _) = PreLoadUtilities.GetPositions(GetVcfStream(), annotationRange, seqProvider, null);
Assert.Single(positions);
Assert.Equal(3, positions[ChromosomeUtilities.Chr1].Count);
}
public void PassedTheEnd_AsExpected()
{
var annotationRange = new GenomicRange(new GenomicPosition(ChromosomeUtilities.Chr1, 100), new GenomicPosition(ChromosomeUtilities.Chr1, 200));
var vcfFilter = new VcfFilter(annotationRange);
Assert.False(vcfFilter.PassedTheEnd(ChromosomeUtilities.Chr1, 150));
Assert.False(vcfFilter.PassedTheEnd(ChromosomeUtilities.Chr1, 200));
Assert.True(vcfFilter.PassedTheEnd(ChromosomeUtilities.Chr1, 201));
Assert.True(vcfFilter.PassedTheEnd(ChromosomeUtilities.Chr2, 150));
}
public void GetVariantPositions(Stream vcfStream, GenomicRange genomicRange)
{
if (vcfStream == null)
{
_variantPositions = null;
return;
}
vcfStream.Position = Tabix.VirtualPosition.From(InputStartVirtualPosition).BlockOffset;
_variantPositions = PreLoadUtilities.GetPositions(vcfStream, genomicRange, SequenceProvider).ToImmutableDictionary();
}
public void PassedTheEnd_AsExpected()
{
var chromosome = new Chromosome("chr1", "1", 0);
var annotationRange = new GenomicRange(new GenomicPosition(chromosome, 100), new GenomicPosition(chromosome, 200));
var vcfFilter = new VcfFilter(annotationRange);
Assert.False(vcfFilter.PassedTheEnd(new Chromosome("chr1", "1", 0), 150));
Assert.False(vcfFilter.PassedTheEnd(new Chromosome("chr1", "1", 0), 200));
Assert.True(vcfFilter.PassedTheEnd(new Chromosome("chr1", "1", 0), 201));
Assert.True(vcfFilter.PassedTheEnd(new Chromosome("chr2", "2", 1), 150));
}
public void GetVariantPositions(Stream vcfStream, GenomicRange genomicRange)
{
if (vcfStream == null)
{
_variantPositions = null;
return;
}
vcfStream.Position = Tabix.VirtualPosition.From(InputStartVirtualPosition).BlockOffset;
int numPositions;
Metrics.SaPositionScan.Start();
(_variantPositions, numPositions) = PreLoadUtilities.GetPositions(vcfStream, genomicRange, SequenceProvider, RefMinorProvider);
Metrics.ShowSaPositionScanLoad(numPositions);
}
public VcfFilter(GenomicRange genomicRange)
{
_genomicRange = genomicRange;
_genomicRangeChecker = new GenomicRangeChecker(genomicRange);
}
public static IDictionary <IChromosome, List <int> > GetPositions(Stream vcfStream, GenomicRange genomicRange, ISequenceProvider sequenceProvider)
{
var benchmark = new Benchmark();
Console.Write("Scanning positions required for SA pre-loading....");
var chromPositions = new Dictionary <IChromosome, List <int> >();
var rangeChecker = new GenomicRangeChecker(genomicRange);
var refNameToChrom = sequenceProvider.RefNameToChromosome;
using (var reader = new StreamReader(vcfStream))
{
string line;
while ((line = reader.ReadLine()) != null)
{
if (!NeedProcessThisLine(refNameToChrom, line, out var splits, out IChromosome iChrom))
{
continue;
}
int position = int.Parse(splits[VcfCommon.PosIndex]);
if (rangeChecker.OutOfRange(iChrom, position))
{
break;
}
string refAllele = splits[VcfCommon.RefIndex];
string altAllele = splits[VcfCommon.AltIndex];
sequenceProvider.LoadChromosome(iChrom);
UpdateChromToPositions(chromPositions, iChrom, position, refAllele, altAllele, sequenceProvider.Sequence);
}
}
int count = SortPositionsAndGetCount(chromPositions);
Console.WriteLine($"{count} positions found in {Benchmark.ToHumanReadable(benchmark.GetElapsedTime())}");
return(chromPositions);
}
public static (ImmutableDictionary <IChromosome, List <int> > PositionsByChromosome, int Count) GetPositions(Stream vcfStream, GenomicRange genomicRange,
ISequenceProvider sequenceProvider, IRefMinorProvider refMinorProvider)
{
var positionsByChromosome = new Dictionary <IChromosome, List <int> >();
var rangeChecker = new GenomicRangeChecker(genomicRange);
var refNameToChrom = sequenceProvider.RefNameToChromosome;
using (var reader = new StreamReader(vcfStream))
{
string line;
string currentReferenceName = "";
IChromosome chromosome = null;
while ((line = reader.ReadLine()) != null)
{
if (line.StartsWith('#'))
{
continue;
}
string[] cols = line.OptimizedSplit('\t');
string referenceName = cols[VcfCommon.ChromIndex];
if (referenceName != currentReferenceName)
{
if (!refNameToChrom.TryGetValue(referenceName, out chromosome))
{
continue;
}
currentReferenceName = referenceName;
}
(int position, bool foundError) = cols[VcfCommon.PosIndex].OptimizedParseInt32();
if (foundError)
{
throw new InvalidDataException($"Unable to convert the VCF position to an integer: {cols[VcfCommon.PosIndex]}");
}
if (rangeChecker.OutOfRange(chromosome, position))
{
break;
}
string refAllele = cols[VcfCommon.RefIndex];
string altAllele = cols[VcfCommon.AltIndex];
if (altAllele == "." && !IsRefMinor(refMinorProvider, chromosome, position))
{
continue;
}
sequenceProvider.LoadChromosome(chromosome);
TryAddPosition(positionsByChromosome, chromosome, position, refAllele, altAllele, sequenceProvider.Sequence);
}
}
int count = SortPositionsAndGetCount(positionsByChromosome);
return(positionsByChromosome.ToImmutableDictionary(), count);
}
public GenomicRangeChecker(GenomicRange genomicRange)
{
_genomicRange = genomicRange;
}