public void VariantGenerator_AsExpected()
{
var mockSequenceProvider = new Mock <ISequenceProvider>();
mockSequenceProvider.SetupGet(x => x.RefNameToChromosome)
.Returns(new Dictionary <string, IChromosome> {
{ "chr1", new Chromosome("chr1", "1", 0) }
});
mockSequenceProvider.SetupGet(x => x.Sequence).Returns(new SimpleSequence("CAGCTGAA"));
var sequenceProvider = mockSequenceProvider.Object;
var position1 = SimplePosition.GetSimplePosition("chr1 2 . A T,G . PASS . GT:PS 0|1:123 2/2:789 0|2:456", sequenceProvider.RefNameToChromosome);
var position2 = SimplePosition.GetSimplePosition("chr1 4 . C A,G . PASS . GT:PS 1|1:301 1|2:789 1|2:456", sequenceProvider.RefNameToChromosome);
var position3 = SimplePosition.GetSimplePosition("chr1 6 . G C . PASS . GT:PS . 1|0:789 0/1:.", sequenceProvider.RefNameToChromosome);
var functionBlockRanges = new List <int> {
4, 6, 8
};
var recomposer = new VariantGenerator(sequenceProvider);
var recomposedPositions = recomposer.Recompose(new List <ISimplePosition> {
position1, position2, position3
}, functionBlockRanges).ToList();
Assert.Equal(2, recomposedPositions.Count);
Assert.Equal("chr1 2 . AGC AGA,GGG . PASS RECOMPOSED GT:PS . . 1|2:456", string.Join("\t", recomposedPositions[0].VcfFields));
Assert.Equal("chr1 2 . AGCTG GGATC,GGGTG . PASS RECOMPOSED GT:PS . 1|2:789 .", string.Join("\t", recomposedPositions[1].VcfFields));
}
public void VariantGenerator_OverlappingDeletionAtTheEnd_Ignored()
{
var mockSequenceProvider = new Mock <ISequenceProvider>();
mockSequenceProvider.SetupGet(x => x.RefNameToChromosome)
.Returns(new Dictionary <string, IChromosome> {
{ "chr1", new Chromosome("chr1", "1", 0) }
});
mockSequenceProvider.SetupGet(x => x.Sequence).Returns(new SimpleSequence("CAGCTGAATCGCGA"));
var sequenceProvider = mockSequenceProvider.Object;
var position1 = AnnotationUtilities.GetSimplePosition("chr1 2 . A T . PASS . GT 0|1 0/0", sequenceProvider.RefNameToChromosome);
var position2 = AnnotationUtilities.GetSimplePosition("chr1 4 . C A . PASS . GT 1|1 0/0", sequenceProvider.RefNameToChromosome);
var position3 = AnnotationUtilities.GetSimplePosition("chr1 4 . CTGAATCGCGA C . PASS . GT 0/0 0|1", sequenceProvider.RefNameToChromosome);
var functionBlockRanges = new List <int> {
4, 6, 6
};
var recomposer = new VariantGenerator(sequenceProvider);
var recomposedPositions = recomposer.Recompose(new List <ISimplePosition> {
position1, position2, position3
}, functionBlockRanges).ToList();
Assert.Single(recomposedPositions);
Assert.Equal("chr1 2 . AGC AGA,TGA . PASS RECOMPOSED GT 1|2 0|0", string.Join("\t", recomposedPositions[0].VcfFields));
}
public void GetPositionsAndRefAltAlleles_AsExpected()
{
var genotypes = new[] { "1|2", "1/1", "0|1", "0/1" };
var genotypeToSample =
new Dictionary <(string, int), List <int> > {
{ (string.Join(";", genotypes), 0), new List <int> {
0
} }
};
var indexOfUnsupportedVars = Enumerable.Repeat(new HashSet <string>(), genotypes.Length).ToArray();
var starts = new[] { 356, 358, 360, 361 };
var functionBlockRanges = new List <int> {
358, 360, 362, 364
};
var alleles = new[] { new[] { "G", "C", "T" }, new[] { "A", "T" }, new[] { "C", "G" }, new[] { "G", "T" } };
var refSequence = "GAATCG";
var alleleIndexBlocksToSample = AlleleIndexBlock.GetAlleleIndexBlockToSampleIndex(genotypeToSample, indexOfUnsupportedVars, starts, functionBlockRanges).ToArray();
var alleleSet = new AlleleSet(null, starts, alleles);
var alleleIndexBlocks = alleleIndexBlocksToSample.Select(x => x.Key).ToArray();
var decomposedPositionIndex = new HashSet <(int, int)>();
var result1 = VariantGenerator.GetPositionsAndRefAltAlleles(alleleIndexBlocks[0], alleleSet, refSequence, starts[0], decomposedPositionIndex);
var result2 = VariantGenerator.GetPositionsAndRefAltAlleles(alleleIndexBlocks[1], alleleSet, refSequence, starts[0], decomposedPositionIndex);
Assert.Equal((356, 360, "GAATC", "CATTC"), result1);
Assert.Equal((356, 360, "GAATC", "TATTG"), result2);
}
public void VariantGenerator_MinGQUsed_DotAndNullIgnored()
{
var mockSequenceProvider = new Mock <ISequenceProvider>();
mockSequenceProvider.SetupGet(x => x.RefNameToChromosome)
.Returns(new Dictionary <string, IChromosome> {
{ "chr1", new Chromosome("chr1", "1", 0) }
});
mockSequenceProvider.SetupGet(x => x.Sequence).Returns(new SimpleSequence("CAGCTGAA"));
var sequenceProvider = mockSequenceProvider.Object;
var position1 = AnnotationUtilities.GetSimplePosition("chr1 2 . A T,G . PASS . GT:PS:GQ 0|1:123:. 2/2:.:14.2 0|2:456:.", sequenceProvider.RefNameToChromosome);
var position2 = AnnotationUtilities.GetSimplePosition("chr1 4 . C A,G . PASS . GT:PS:GQ 1|1:301:. 1|2:.:18 1|2:456:15.6", sequenceProvider.RefNameToChromosome);
var position3 = AnnotationUtilities.GetSimplePosition("chr1 6 . G C . PASS . GT . 1|0 0/1", sequenceProvider.RefNameToChromosome);
var functionBlockRanges = new List <int> {
4, 6, 8
};
var recomposer = new VariantGenerator(sequenceProvider);
var recomposedPositions = recomposer.Recompose(new List <ISimplePosition> {
position1, position2, position3
}, functionBlockRanges).ToList();
Assert.Equal(2, recomposedPositions.Count);
Assert.Equal("chr1 2 . AGC AGA,GGG,TGA . PASS RECOMPOSED GT:GQ:PS 1|3:.:123 . 1|2:15.6:456", string.Join("\t", recomposedPositions[0].VcfFields));
Assert.Equal("chr1 2 . AGCTG GGATC,GGGTG . PASS RECOMPOSED GT:GQ . 1|2:14.2 .", string.Join("\t", recomposedPositions[1].VcfFields));
}
public void VariantGenerator_AllTrailingMissingValuesDroped()
{
var mockSequenceProvider = new Mock <ISequenceProvider>();
mockSequenceProvider.SetupGet(x => x.RefNameToChromosome)
.Returns(new Dictionary <string, IChromosome> {
{ "chr1", new Chromosome("chr1", "1", 0) }
});
mockSequenceProvider.SetupGet(x => x.Sequence).Returns(new SimpleSequence("CAGCTGAA"));
var sequenceProvider = mockSequenceProvider.Object;
var position1 = AnnotationUtilities.GetSimplePosition("chr1 2 . A T,G . PASS . GT:GQ:PS 0|1:.:123 2/2 1|1:17:456", sequenceProvider.RefNameToChromosome);
var position2 = AnnotationUtilities.GetSimplePosition("chr1 4 . C A,G . PASS . GT:GQ:PS ./. 1|2 1|2:15.6:456", sequenceProvider.RefNameToChromosome);
var position3 = AnnotationUtilities.GetSimplePosition("chr1 6 . G C . PASS . GT:GQ:PS ./. 1|0 1|1:13:456", sequenceProvider.RefNameToChromosome);
var functionBlockRanges = new List <int> {
4, 6, 8
};
var recomposer = new VariantGenerator(sequenceProvider);
var recomposedPositions = recomposer.Recompose(new List <ISimplePosition> {
position1, position2, position3
}, functionBlockRanges).ToList();
Assert.Single(recomposedPositions);
Assert.Equal("chr1 2 . AGCTG GGATC,GGGTG,TGATC,TGGTC . PASS RECOMPOSED GT:GQ:PS . 1|2 3|4:13:456", string.Join("\t", recomposedPositions[0].VcfFields));
}
public void VariantGenerator_HomozygousSitesAndPhasedSites_Recomposed()
{
var mockSequenceProvider = new Mock <ISequenceProvider>();
mockSequenceProvider.SetupGet(x => x.RefNameToChromosome)
.Returns(new Dictionary <string, IChromosome> {
{ "chr1", new Chromosome("chr1", "1", 0) }
});
mockSequenceProvider.SetupGet(x => x.Sequence).Returns(new SimpleSequence("CAGCTGAA"));
var sequenceProvider = mockSequenceProvider.Object;
var position1 = AnnotationUtilities.GetSimplePosition("chr1 2 . A T . PASS . GT 1/1 1/1 1/1", sequenceProvider.RefNameToChromosome);
var position2 = AnnotationUtilities.GetSimplePosition("chr1 3 . G A,G 45 PASS . GT:PS 1|1:2 1|2:2 1|2:2", sequenceProvider.RefNameToChromosome);
var position3 = AnnotationUtilities.GetSimplePosition("chr1 4 . C A 45 PASS . GT 1/1 1/1 1/1", sequenceProvider.RefNameToChromosome);
var position4 = AnnotationUtilities.GetSimplePosition("chr1 5 . T A,G 45 PASS . GT:PS 1|1:4 1|2:2 1|2:4", sequenceProvider.RefNameToChromosome);
var position5 = AnnotationUtilities.GetSimplePosition("chr1 6 . G C 30 PASS . GT 1/1 1/1 1/1", sequenceProvider.RefNameToChromosome);
var functionBlockRanges = new List <int> {
4, 5, 6, 7, 8
};
var recomposer = new VariantGenerator(sequenceProvider);
var recomposedPositions = recomposer.Recompose(new List <ISimplePosition> {
position1, position2, position3, position4, position5
}, functionBlockRanges).ToList();
Assert.Equal(3, recomposedPositions.Count);
Assert.Equal("chr1 2 . AGC TAA,TGA 45 PASS RECOMPOSED GT:PS . . 1|2:2", string.Join("\t", recomposedPositions[0].VcfFields));
Assert.Equal("chr1 2 . AGCTG TAAAC,TGAGC 30 PASS RECOMPOSED GT:PS 1|1 1|2:2 .", string.Join("\t", recomposedPositions[1].VcfFields));
Assert.Equal("chr1 4 . CTG AAC,AGC 30 PASS RECOMPOSED GT:PS . . 1|2:4", string.Join("\t", recomposedPositions[2].VcfFields));
}
public void VariantGenerator_FilterTag_PassedMnvOverridesFailedOne()
{
var mockSequenceProvider = new Mock <ISequenceProvider>();
mockSequenceProvider.SetupGet(x => x.RefNameToChromosome)
.Returns(new Dictionary <string, IChromosome> {
{ "chr1", new Chromosome("chr1", "1", 0) }
});
mockSequenceProvider.SetupGet(x => x.Sequence).Returns(new SimpleSequence("CAGCTGAA"));
var sequenceProvider = mockSequenceProvider.Object;
var position1 = AnnotationUtilities.GetSimplePosition("chr1 2 . A T . PASS . GT 0|1 0|1", sequenceProvider.RefNameToChromosome);
var position2 = AnnotationUtilities.GetSimplePosition("chr1 4 . C A . FailedForSomeReason . GT 0|0 0|1", sequenceProvider.RefNameToChromosome);
var position3 = AnnotationUtilities.GetSimplePosition("chr1 6 . G C . PASS . GT 0|1 0|1", sequenceProvider.RefNameToChromosome);
var functionBlockRanges = new List <int> {
6, 8, 10
};
var recomposer = new VariantGenerator(sequenceProvider);
var recomposedPositions = recomposer.Recompose(new List <ISimplePosition> {
position1, position2, position3
}, functionBlockRanges).ToList();
Assert.Single(recomposedPositions);
Assert.Equal("chr1 2 . AGCTG TGATC,TGCTC . PASS RECOMPOSED GT 0|2 0|1", string.Join("\t", recomposedPositions[0].VcfFields));
}
public void VariantGenerator_HomoReferenceGenotype_Output()
{
var mockSequenceProvider = new Mock <ISequenceProvider>();
mockSequenceProvider.SetupGet(x => x.RefNameToChromosome)
.Returns(new Dictionary <string, IChromosome> {
{ "chr1", new Chromosome("chr1", "1", 0) }
});
mockSequenceProvider.SetupGet(x => x.Sequence).Returns(new SimpleSequence("CAGCTGAA"));
var sequenceProvider = mockSequenceProvider.Object;
var position1 = AnnotationUtilities.GetSimplePosition("chr1 1 . C A . PASS . GT:PS 0|1:1584593 0/0:.", sequenceProvider.RefNameToChromosome);
var position2 = AnnotationUtilities.GetSimplePosition("chr1 2 . A C . PASS . GT:PS 0|1:1584593 0/0:.", sequenceProvider.RefNameToChromosome);
var functionBlockRanges = new List <int> {
3, 4
};
var recomposer = new VariantGenerator(sequenceProvider);
var recomposedPositions = recomposer.Recompose(new List <ISimplePosition> {
position1, position2
}, functionBlockRanges).ToList();
Assert.Single(recomposedPositions);
Assert.Equal("chr1 1 . CA AC . PASS RECOMPOSED GT:PS 0|1:1584593 0|0", string.Join("\t", recomposedPositions[0].VcfFields));
}
public void VariantGenerator_SampleColumnCorrectlyProcessed_WhenTrailingMissingValuesDroped()
{
var mockSequenceProvider = new Mock <ISequenceProvider>();
mockSequenceProvider.SetupGet(x => x.RefNameToChromosome)
.Returns(new Dictionary <string, IChromosome> {
{ "chr1", new Chromosome("chr1", "1", 0) }
});
mockSequenceProvider.SetupGet(x => x.Sequence).Returns(new SimpleSequence("CAGCTGAA"));
var sequenceProvider = mockSequenceProvider.Object;
var position1 = SimplePosition.GetSimplePosition("chr1 2 . A T,G . PASS . GT:PS:GQ 0|1:123 2/2:.:14.2 ./.", sequenceProvider.RefNameToChromosome);
var position2 = SimplePosition.GetSimplePosition("chr1 4 . C A,G . PASS . GT:PS:GQ ./. 1|2:.:18 1|2:456:15.6", sequenceProvider.RefNameToChromosome);
var position3 = SimplePosition.GetSimplePosition("chr1 6 . G C . PASS . GT ./. 1|0 ./.", sequenceProvider.RefNameToChromosome);
var functionBlockRanges = new List <int> {
4, 6, 8
};
var recomposer = new VariantGenerator(sequenceProvider);
var recomposedPositions = recomposer.Recompose(new List <ISimplePosition> {
position1, position2, position3
}, functionBlockRanges).ToList();
Assert.Single(recomposedPositions);
Assert.Equal("chr1 2 . AGCTG GGATC,GGGTG . PASS RECOMPOSED GT:GQ . 1|2:14.2 .", string.Join("\t", recomposedPositions[0].VcfFields));
}
public void GenerateOutput_NothingRecomposed_ReturnOriginalVcfFieldList()
{
var mockSequenceProvider = new Mock <ISequenceProvider>();
mockSequenceProvider.SetupGet(x => x.RefNameToChromosome)
.Returns(new Dictionary <string, IChromosome> {
{ "chr1", new Chromosome("chr1", "1", 0) }
});
mockSequenceProvider.SetupGet(x => x.Sequence).Returns(new SimpleSequence("CAGCTGAA"));
var sequenceProvider = mockSequenceProvider.Object;
var variantGenerator = new VariantGenerator(sequenceProvider);
var position1 = AnnotationUtilities.GetSimplePosition("chr1 2 . A T . PASS . GT:PS 0|1:123", sequenceProvider.RefNameToChromosome);
var position2 = AnnotationUtilities.GetSimplePosition("chr1 4 . C G . PASS . GT 0/1", sequenceProvider.RefNameToChromosome);
var position3 = AnnotationUtilities.GetSimplePosition("chr1 6 . G C . PASS . GT 0|1", sequenceProvider.RefNameToChromosome);
var positions = new List <ISimplePosition> {
position1, position2, position3
};
var recomposable = new List <bool> {
true, true, true
};
var functionBlockRanges = new List <int> {
4, 6, 8
};
var bufferedPositions = new BufferedPositions(positions, recomposable, functionBlockRanges);
var positionProcessor = new PositionProcessor(_positionBufferMock.Object, variantGenerator);
var output = positionProcessor.GenerateOutput(bufferedPositions).ToArray();
for (int i = 0; i < output.Length; i++)
{
Assert.True(positions[i].VcfFields.SequenceEqual(output[i].VcfFields));
}
}
public void VariantGenerator_MinQualUsed_DotIgnored()
{
var mockSequenceProvider = new Mock <ISequenceProvider>();
mockSequenceProvider.SetupGet(x => x.RefNameToChromosome)
.Returns(ChromosomeUtilities.RefNameToChromosome);
mockSequenceProvider.SetupGet(x => x.Sequence).Returns(new SimpleSequence("CAGCTGAA"));
var sequenceProvider = mockSequenceProvider.Object;
var position1 = AnnotationUtilities.GetSimplePosition("chr1 2 . A T,G . PASS . GT:PS 0|1:123 2/2:. 0|2:456", sequenceProvider.RefNameToChromosome);
var position2 = AnnotationUtilities.GetSimplePosition("chr1 4 . C A,G 45 PASS . GT:PS 1|1:301 1|2:. 1|2:456", sequenceProvider.RefNameToChromosome);
var position3 = AnnotationUtilities.GetSimplePosition("chr1 6 . G C 30.1 PASS . GT . 1|0 0/1", sequenceProvider.RefNameToChromosome);
var functionBlockRanges = new List <int> {
4, 6, 8
};
var recomposer = new VariantGenerator(sequenceProvider, _vidCreator);
var recomposedPositions = recomposer.Recompose(new List <ISimplePosition> {
position1, position2, position3
}, functionBlockRanges).ToList();
Assert.Equal(2, recomposedPositions.Count);
Assert.Equal("chr1 2 . AGC AGA,GGG,TGA 45 PASS RECOMPOSED GT:PS 1|3:123 . 1|2:456", string.Join("\t", recomposedPositions[0].VcfFields));
Assert.Equal("chr1 2 . AGCTG GGATC,GGGTG 30.1 PASS RECOMPOSED GT . 1|2 .", string.Join("\t", recomposedPositions[1].VcfFields));
}
public void VariantGenerator_ForceGenotype_ConsistentAllele_Recompose()
{
var mockSequenceProvider = new Mock <ISequenceProvider>();
mockSequenceProvider.SetupGet(x => x.RefNameToChromosome)
.Returns(ChromosomeUtilities.RefNameToChromosome);
mockSequenceProvider.SetupGet(x => x.Sequence).Returns(new SimpleSequence("CAGCTGAATCGCGA"));
var sequenceProvider = mockSequenceProvider.Object;
var position1 = AnnotationUtilities.GetSimplePosition("chr1 2 . A T . PASS . GT 1|1 0/0", sequenceProvider.RefNameToChromosome);
var position2 = AnnotationUtilities.GetSimplePosition("chr1 4 . C G . PASS . GT 0|1 0|1", sequenceProvider.RefNameToChromosome);
var position3 = AnnotationUtilities.GetSimplePosition("chr1 4 . C G,A . PASS . GT 0|1 0/0", sequenceProvider.RefNameToChromosome);
var functionBlockRanges = new List <int> {
4, 6, 6
};
var recomposer = new VariantGenerator(sequenceProvider, _vidCreator);
var recomposedPositions = recomposer.Recompose(new List <ISimplePosition> {
position1, position2, position3
}, functionBlockRanges).ToList();
Assert.Single(recomposedPositions);
Assert.Equal("chr1 2 . AGC TGC,TGG . PASS RECOMPOSED GT 1|2 .", string.Join("\t", recomposedPositions[0].VcfFields));
}
public void VariantGenerator_ConflictAltAlleles_AlleleBlockStartInTheMiddle_NoRecompositionNoException()
{
var mockSequenceProvider = new Mock <ISequenceProvider>();
mockSequenceProvider.SetupGet(x => x.RefNameToChromosome)
.Returns(ChromosomeUtilities.RefNameToChromosome);
mockSequenceProvider.SetupGet(x => x.Sequence).Returns(new SimpleSequence("CAGCTGAATCGCGA"));
var sequenceProvider = mockSequenceProvider.Object;
var position1 = AnnotationUtilities.GetSimplePosition("chr1 1 . C T . PASS . GT 0/1 0|1", sequenceProvider.RefNameToChromosome);
var position2 = AnnotationUtilities.GetSimplePosition("chr1 2 . A T . PASS . GT 0/1 0|0", sequenceProvider.RefNameToChromosome);
var position3 = AnnotationUtilities.GetSimplePosition("chr1 4 . C G . PASS . GT 1|1 1|1", sequenceProvider.RefNameToChromosome);
var position4 = AnnotationUtilities.GetSimplePosition("chr1 4 . C A . PASS . GT 1|1 0|1", sequenceProvider.RefNameToChromosome);
var functionBlockRanges = new List <int> {
3, 4, 6, 6
};
var recomposer = new VariantGenerator(sequenceProvider, _vidCreator);
var recomposedPositions = recomposer.Recompose(new List <ISimplePosition> {
position1, position2, position3, position4
}, functionBlockRanges).ToList();
Assert.Empty(recomposedPositions);
}
public void VariantGenerator_RefAllelesAddedToMergeAlleles()
{
var mockSequenceProvider = new Mock <ISequenceProvider>();
mockSequenceProvider.SetupGet(x => x.RefNameToChromosome)
.Returns(new Dictionary <string, IChromosome> {
{ "chr1", new Chromosome("chr1", "1", 0) }
});
mockSequenceProvider.SetupGet(x => x.Sequence).Returns(new SimpleSequence("CAGCTGAACT"));
var sequenceProvider = mockSequenceProvider.Object;
var position1 = AnnotationUtilities.GetSimplePosition("chr1 2 . A T . PASS . GT 0|1 0|0 0|1 0|0", sequenceProvider.RefNameToChromosome);
var position2 = AnnotationUtilities.GetSimplePosition("chr1 4 . C A . PASS . GT 1|1 1|1 1|1 1|1", sequenceProvider.RefNameToChromosome);
var position3 = AnnotationUtilities.GetSimplePosition("chr1 6 . G C . PASS . GT 1|1 1|1 1|1 1|1", sequenceProvider.RefNameToChromosome);
var position4 = AnnotationUtilities.GetSimplePosition("chr1 8 . A G . PASS . GT 0|1 0|1 0|0 0|0", sequenceProvider.RefNameToChromosome);
var functionBlockRanges = new List <int> {
4, 6, 8, 10
};
var recomposer = new VariantGenerator(sequenceProvider);
var recomposedPositions = recomposer.Recompose(new List <ISimplePosition> {
position1, position2, position3, position4
}, functionBlockRanges).ToList();
Assert.Single(recomposedPositions);
Assert.Equal("chr1 2 . AGCTGAA AGATCAA,AGATCAG,TGATCAA,TGATCAG . PASS RECOMPOSED GT 1|4 1|2 1|3 1|1", string.Join("\t", recomposedPositions[0].VcfFields));
}
public void VariantGenerator_FilterTag_DotTreatedAsPass()
{
var mockSequenceProvider = new Mock <ISequenceProvider>();
mockSequenceProvider.SetupGet(x => x.RefNameToChromosome)
.Returns(new Dictionary <string, IChromosome> {
{ "chr1", new Chromosome("chr1", "1", 0) }
});
mockSequenceProvider.SetupGet(x => x.Sequence).Returns(new SimpleSequence("CAGCTGAA"));
var sequenceProvider = mockSequenceProvider.Object;
var position1 = AnnotationUtilities.GetSimplePosition("chr1 2 . A T,G . PASS . GT:PS 0|1:123 2/2:. 0|2:456", sequenceProvider.RefNameToChromosome);
var position2 = AnnotationUtilities.GetSimplePosition("chr1 4 . C A,G . . . GT:PS 1|1:301 1|2:. 1|2:456", sequenceProvider.RefNameToChromosome);
var position3 = AnnotationUtilities.GetSimplePosition("chr1 6 . G C . FailedForSomeReason . GT:PS . 1|0:. 0/1:456", sequenceProvider.RefNameToChromosome);
var functionBlockRanges = new List <int> {
4, 6, 8
};
var recomposer = new VariantGenerator(sequenceProvider);
var recomposedPositions = recomposer.Recompose(new List <ISimplePosition> {
position1, position2, position3
}, functionBlockRanges).ToList();
Assert.Equal(2, recomposedPositions.Count);
Assert.Equal("chr1 2 . AGC AGA,GGG,TGA . PASS RECOMPOSED GT:PS 1|3:123 . 1|2:456", string.Join("\t", recomposedPositions[0].VcfFields));
Assert.Equal("chr1 2 . AGCTG GGATC,GGGTG . FilteredVariantsRecomposed RECOMPOSED GT . 1|2 .", string.Join("\t", recomposedPositions[1].VcfFields));
}
public void GetPositionsAndRefAltAlleles_AsExpected()
{
var genotypeBlock = new GenotypeBlock(new[] { "1|2", "1/1", "0|1", "0/1" }.Select(Genotype.GetGenotype).ToArray());
var genotypeToSample =
new Dictionary <GenotypeBlock, List <int> > {
{ genotypeBlock, new List <int> {
0
} }
};
var indexOfUnsupportedVars = Enumerable.Repeat(new HashSet <int>(), genotypeBlock.Genotypes.Length).ToArray();
var starts = new[] { 356, 358, 360, 361 };
var functionBlockRanges = new List <int> {
358, 360, 362, 364
};
var alleles = new[] { new[] { "G", "C", "T" }, new[] { "A", "T" }, new[] { "C", "G" }, new[] { "G", "T" } };
const string refSequence = "GAATCG";
var alleleBlockToSampleHaplotype = AlleleBlock.GetAlleleBlockToSampleHaplotype(genotypeToSample, indexOfUnsupportedVars, starts, functionBlockRanges, out var alleleBlockGraph);
var mergedAlleleBlockToSampleHaplotype =
AlleleBlockMerger.Merge(alleleBlockToSampleHaplotype, alleleBlockGraph).ToArray();
var alleleSet = new AlleleSet(ChromosomeUtilities.Chr1, starts, alleles);
var alleleBlocks = mergedAlleleBlockToSampleHaplotype.Select(x => x.Key).ToArray();
var sequence = new NSequence();
var result1 = VariantGenerator.GetPositionsAndRefAltAlleles(alleleBlocks[0], alleleSet, refSequence, starts[0], null, sequence, _vidCreator);
var result2 = VariantGenerator.GetPositionsAndRefAltAlleles(alleleBlocks[1], alleleSet, refSequence, starts[0], null, sequence, _vidCreator);
var expectedVarPosIndexes1 = new List <int> {
0, 1
};
var expectedVarPosIndexes2 = new List <int> {
0, 1, 2
};
Assert.Equal((356, 360, "GAATC", "CATTC"), (result1.Start, result1.End, result1.Ref, result1.Alt));
for (var i = 0; i < expectedVarPosIndexes1.Count; i++)
{
Assert.Equal(expectedVarPosIndexes1[i], result1.VarPosIndexesInAlleleBlock[i]);
}
Assert.Equal((356, 360, "GAATC", "TATTG"), (result2.Start, result2.End, result2.Ref, result2.Alt));
for (var i = 0; i < expectedVarPosIndexes2.Count; i++)
{
Assert.Equal(expectedVarPosIndexes2[i], result2.VarPosIndexesInAlleleBlock[i]);
}
}
public void GenerateOutput_Return_OriginalAndRecomposed_VcfFieldList()
{
var mockSequenceProvider = new Mock <ISequenceProvider>();
mockSequenceProvider.SetupGet(x => x.RefNameToChromosome)
.Returns(new Dictionary <string, IChromosome> {
{ "chr1", new Chromosome("chr1", "1", 0) }
});
mockSequenceProvider.SetupGet(x => x.Sequence).Returns(new SimpleSequence("CAGCTGAA"));
var sequenceProvider = mockSequenceProvider.Object;
var variantGenerator = new VariantGenerator(sequenceProvider);
var position1 = AnnotationUtilities.GetSimplePosition("chr1 2 . A T . PASS . GT:PS 0|1:.", sequenceProvider.RefNameToChromosome);
var position2 = AnnotationUtilities.GetSimplePosition("chr1 4 . C G . PASS . GT 1/1", sequenceProvider.RefNameToChromosome);
var position3 = AnnotationUtilities.GetSimplePosition("chr1 6 . G C . PASS . GT 0|1", sequenceProvider.RefNameToChromosome);
var positions = new List <ISimplePosition> {
position1, position2, position3
};
var recomposable = new List <bool> {
true, true, true
};
var functionBlockRanges = new List <int> {
4, 6, 8
};
var bufferedPositions = new BufferedPositions(positions, recomposable, functionBlockRanges);
var positionProcessor = new PositionProcessor(_positionBufferMock.Object, variantGenerator);
var output = positionProcessor.GenerateOutput(bufferedPositions).ToArray();
var expectedOutput = new string[4][];
expectedOutput[0] = position1.VcfFields;
expectedOutput[1] = new[]
{ "chr1", "2", ".", "AGCTG", "AGGTG,TGGTC", ".", "PASS", "RECOMPOSED", "GT", "1|2" };
expectedOutput[2] = position2.VcfFields;
expectedOutput[3] = position3.VcfFields;
for (int i = 0; i < output.Length; i++)
{
Assert.True(expectedOutput[i].SequenceEqual(output[i].VcfFields));
}
}
public void VariantGenerator_NoMnvAfterTrimming_NotRecompose()
{
var mockSequenceProvider = new Mock <ISequenceProvider>();
mockSequenceProvider.SetupGet(x => x.RefNameToChromosome)
.Returns(ChromosomeUtilities.RefNameToChromosome);
mockSequenceProvider.SetupGet(x => x.Sequence).Returns(new SimpleSequence("CAGCTGAA"));
var sequenceProvider = mockSequenceProvider.Object;
var position1 = AnnotationUtilities.GetSimplePosition("chr1 1 . C A . PASS . GT:PS 1|0:1584593 1|1:. 0|1:.", sequenceProvider.RefNameToChromosome);
var position2 = AnnotationUtilities.GetSimplePosition("chr1 2 . A C . PASS . GT:PS 0|1:1584593 0/0:. 0/0:.", sequenceProvider.RefNameToChromosome);
var functionBlockRanges = new List <int> {
3, 4
};
var recomposer = new VariantGenerator(sequenceProvider, _vidCreator);
var recomposedPositions = recomposer.Recompose(new List <ISimplePosition> {
position1, position2
}, functionBlockRanges).ToList();
Assert.Empty(recomposedPositions);
}
public void VariantGenerator_FilterTag_OnlyDecomposedVariantsConsidered()
{
var mockSequenceProvider = new Mock <ISequenceProvider>();
mockSequenceProvider.SetupGet(x => x.RefNameToChromosome)
.Returns(ChromosomeUtilities.RefNameToChromosome);
mockSequenceProvider.SetupGet(x => x.Sequence).Returns(new SimpleSequence("CAGCTGAA"));
var sequenceProvider = mockSequenceProvider.Object;
var position1 = AnnotationUtilities.GetSimplePosition("chr1 2 . A T . PASS . GT 0|1 0/1 0|0", sequenceProvider.RefNameToChromosome);
var position2 = AnnotationUtilities.GetSimplePosition("chr1 4 . C A . FailedForSomeReason . GT 0|0 0/1 0|0", sequenceProvider.RefNameToChromosome);
var position3 = AnnotationUtilities.GetSimplePosition("chr1 6 . G C . PASS . GT 1|1 0/1 0|0", sequenceProvider.RefNameToChromosome);
var functionBlockRanges = new List <int> {
6, 8, 10
};
var recomposer = new VariantGenerator(sequenceProvider, _vidCreator);
var recomposedPositions = recomposer.Recompose(new List <ISimplePosition> {
position1, position2, position3
}, functionBlockRanges).ToList();
Assert.Single(recomposedPositions);
Assert.Equal("chr1 2 . AGCTG AGCTC,TGCTC . PASS RECOMPOSED GT 1|2 . 0|0", string.Join("\t", recomposedPositions[0].VcfFields));
}
public static List <Configuration> buildConfigs(VariabilityModel vm, List <SamplingStrategies> binaryStrategies,
List <ExperimentalDesign> experimentalDesigns)
{
List <Configuration> result = new List <Configuration>();
VariantGenerator vg = new VariantGenerator();
List <List <BinaryOption> > binaryConfigs = new List <List <BinaryOption> >();
List <Dictionary <NumericOption, Double> > numericConfigs = new List <Dictionary <NumericOption, double> >();
foreach (SamplingStrategies strat in binaryStrategies)
{
switch (strat)
{
//Binary sampling heuristics
case SamplingStrategies.ALLBINARY:
binaryConfigs.AddRange(vg.generateAllVariantsFast(vm));
break;
case SamplingStrategies.BINARY_RANDOM:
RandomBinary rb = new RandomBinary(vm);
foreach (Dictionary <string, string> expDesignParamSet in binaryParams.randomBinaryParameters)
{
binaryConfigs.AddRange(rb.getRandomConfigs(expDesignParamSet));
}
break;
case SamplingStrategies.OPTIONWISE:
{
FeatureWise fw = new FeatureWise();
binaryConfigs.AddRange(fw.generateFeatureWiseConfigurations(GlobalState.varModel));
}
break;
//case SamplingStrategies.MINMAX:
// {
// MinMax mm = new MinMax();
// binaryConfigs.AddRange(mm.generateMinMaxConfigurations(GlobalState.varModel));
// }
// break;
case SamplingStrategies.PAIRWISE:
{
PairWise pw = new PairWise();
binaryConfigs.AddRange(pw.generatePairWiseVariants(GlobalState.varModel));
}
break;
case SamplingStrategies.NEGATIVE_OPTIONWISE:
{
NegFeatureWise neg = new NegFeatureWise(); //2nd option: neg.generateNegativeFWAllCombinations(GlobalState.varModel));
binaryConfigs.AddRange(neg.generateNegativeFW(GlobalState.varModel));
}
break;
case SamplingStrategies.T_WISE:
foreach (Dictionary <string, string> ParamSet in binaryParams.tWiseParameters)
{
TWise tw = new TWise();
int t = 3;
foreach (KeyValuePair <String, String> param in ParamSet)
{
if (param.Key.Equals(TWise.PARAMETER_T_NAME))
{
t = Convert.ToInt16(param.Value);
}
binaryConfigs.AddRange(tw.generateT_WiseVariants_new(vm, t));
}
}
break;
}
}
//Experimental designs for numeric options
if (experimentalDesigns.Count != 0)
{
handleDesigns(experimentalDesigns, numericConfigs, vm);
}
foreach (List <BinaryOption> binConfig in binaryConfigs)
{
if (numericConfigs.Count == 0)
{
Configuration c = new Configuration(binConfig);
result.Add(c);
}
foreach (Dictionary <NumericOption, double> numConf in numericConfigs)
{
Configuration c = new Configuration(binConfig, numConf);
result.Add(c);
}
}
if (vm.MixedConstraints.Count == 0)
{
return(result.Distinct().ToList());
}
else
{
List <Configuration> unfilteredList = result.Distinct().ToList();
List <Configuration> filteredConfiguration = new List <Configuration>();
foreach (Configuration toTest in unfilteredList)
{
bool isValid = true;
foreach (MixedConstraint constr in vm.MixedConstraints)
{
if (!constr.requirementsFulfilled(toTest))
{
isValid = false;
}
}
if (isValid)
{
filteredConfiguration.Add(toTest);
}
}
return(filteredConfiguration);
}
}
/// <summary>
/// Returns a set of random binary partial configurations.
/// </summary>
/// <param name="parameters">Parameters for this random sampling. The following paramters are supported:
/// seed = the seed for the random generator (int required)
/// numConfigs = the number of configurations that have to be selected.
/// To be able ot select a number of configurations equal to the number selected by the OW heuristic or
/// the TWise heuristics, two special values can be given for this paramter. To select a number equal to
/// the OW heuristics use "asOW" as value and to select a number equal to a TWise heuristics with a t of X
/// use "asTWX".
/// </param>
/// <returns>A list of random binary partial configuartions.</returns>
public List <List <BinaryOption> > getRandomConfigs(Dictionary <String, String> parameters)
{
configurations.Clear();
int seed = 0;
int numConfigs = varModel.BinaryOptions.Count;
// parse parameters
if (parameters.ContainsKey("numConfigs"))
{
String numConfigsValue = parameters["numConfigs"];
if (!int.TryParse(numConfigsValue, out numConfigs))
{
// special constants as parameter (numConfigs = asOW or asTWX
if (numConfigsValue.Contains("asOW"))
{
FeatureWise fw = new FeatureWise();
numConfigs = fw.generateFeatureWiseConfigsCSP(varModel).Count;
}
else if (numConfigsValue.Contains("asTW"))
{
numConfigsValue = numConfigsValue.Replace("asTW", "").Trim();
int.TryParse(numConfigsValue, out numConfigs);
TWise tw = new TWise();
numConfigs = tw.generateT_WiseVariants_new(varModel, numConfigs).Count;
}
}
}
if (parameters.ContainsKey("seed"))
{
int.TryParse(parameters["seed"], out seed);
}
// build set of all valid binary partial configurations
VariantGenerator vg = new VariantGenerator();
List <List <BinaryOption> > allConfigs = vg.generateAllVariantsFast(varModel);
//repair wrong parameters
if (numConfigs >= allConfigs.Count)
{
if (numConfigs > allConfigs.Count)
{
GlobalState.logError.logLine("Random Sampling: numConfigs to large for variability model. num set to " + allConfigs.Count);
}
configurations = allConfigs;
return(allConfigs);
}
// select random configurations
Random r = new Random(seed);
for (int i = 0; i < numConfigs; i++)
{
List <BinaryOption> selectedConfig = allConfigs[r.Next(allConfigs.Count + 1)];
if (configurations.Contains(selectedConfig))
{
i -= 1;
}
else
{
configurations.Add(selectedConfig);
}
}
return(configurations);
}
public void VariantGenerator_AsExpected()
{
var mockSequenceProvider = new Mock <ISequenceProvider>();
mockSequenceProvider.SetupGet(x => x.RefNameToChromosome)
.Returns(new Dictionary <string, IChromosome> {
{ "chr1", new Chromosome("chr1", "1", 0) }
});
mockSequenceProvider.SetupGet(x => x.Sequence).Returns(new SimpleSequence("CAGCTGAA"));
var sequenceProvider = mockSequenceProvider.Object;
var position1 = AnnotationUtilities.GetSimplePosition("chr1 2 . A T,G . PASS . GT:PS 0|1:123 2/2:789 0|2:456", sequenceProvider.RefNameToChromosome);
var position2 = AnnotationUtilities.GetSimplePosition("chr1 4 . C A,G . PASS . GT:PS 1|1:301 1|2:789 1|2:456", sequenceProvider.RefNameToChromosome);
var position3 = AnnotationUtilities.GetSimplePosition("chr1 6 . G C . PASS . GT:PS . 1|0:789 0/1:.", sequenceProvider.RefNameToChromosome);
var functionBlockRanges = new List <int> {
4, 6, 8
};
var recomposer = new VariantGenerator(sequenceProvider);
var recomposedPositions = recomposer.Recompose(new List <ISimplePosition> {
position1, position2, position3
}, functionBlockRanges).ToList();
Assert.Equal(2, recomposedPositions.Count);
Assert.Equal("chr1 2 . AGC AGA,GGG,TGA . PASS RECOMPOSED GT:PS 1|3:123 . 1|2:456", string.Join("\t", recomposedPositions[0].VcfFields));
Assert.Equal("chr1 2 . AGCTG GGATC,GGGTG . PASS RECOMPOSED GT:PS . 1|2:789 .", string.Join("\t", recomposedPositions[1].VcfFields));
//Check LinkedVids
//SNVs
Assert.Equal(2, position1.LinkedVids.Length);
Assert.Equal(new List <string> {
"1:2:4:TGA"
}, position1.LinkedVids[0]);
position1.LinkedVids[1].Sort();
Assert.Equal(new List <string> {
"1:2:4:GGG", "1:2:6:GGATC", "1:2:6:GGGTG"
}, position1.LinkedVids[1]);
Assert.Equal(2, position2.LinkedVids.Length);
position2.LinkedVids[0].Sort();
Assert.Equal(new List <string> {
"1:2:4:AGA", "1:2:4:TGA", "1:2:6:GGATC"
}, position2.LinkedVids[0]);
position2.LinkedVids[1].Sort();
Assert.Equal(new List <string> {
"1:2:4:GGG", "1:2:6:GGGTG"
}, position2.LinkedVids[1]);
Assert.Single(position3.LinkedVids);
Assert.Equal(new List <string> {
"1:2:6:GGATC"
}, position3.LinkedVids[0]);
//MNVs
Assert.Equal(3, recomposedPositions[0].LinkedVids.Length);
Assert.Equal(new List <string> {
"1:4:A"
}, recomposedPositions[0].LinkedVids[0]);
Assert.Equal(new List <string> {
"1:2:G", "1:4:G"
}, recomposedPositions[0].LinkedVids[1]);
Assert.Equal(new List <string> {
"1:2:T", "1:4:A"
}, recomposedPositions[0].LinkedVids[2]);
Assert.Equal(2, recomposedPositions[1].LinkedVids.Length);
Assert.Equal(new List <string> {
"1:2:G", "1:4:A", "1:6:C"
}, recomposedPositions[1].LinkedVids[0]);
Assert.Equal(new List <string> {
"1:2:G", "1:4:G"
}, recomposedPositions[1].LinkedVids[1]);
}