public void GetAlleleBlockToSampleHaplotype_AlleleBlock_WithInternalRefPositions_SplitIfOutOfRange()
{
var genotypeBlock1 = new GenotypeBlock(new[] { "1|2", "0/0", "0|0", "1/1" }.Select(Genotype.GetGenotype).ToArray());
var genotypeBlock2 = new GenotypeBlock(new[] { "1/1", "0|0", "1|1" }.Select(Genotype.GetGenotype).ToArray());
var genotypeBlock3 = new GenotypeBlock(new[] { "1|2", "0|0", "1|1" }.Select(Genotype.GetGenotype).ToArray(), 1);
var genotypeToSample =
new Dictionary <GenotypeBlock, List <int> >
{
{ genotypeBlock1, new List <int> {
0
} },
{ genotypeBlock2, new List <int> {
1
} },
{ genotypeBlock3, new List <int> {
2
} }
};
var indexOfUnsupportedVars = Enumerable.Repeat(new HashSet <int>(), genotypeBlock1.Genotypes.Length).ToArray();
var starts = new[] { 100, 102, 103, 104 };
var functionBlockRanges = starts.Select(x => x + 2).ToList();
var alleleBlockToSampleHaplotype = AlleleBlock.GetAlleleBlockToSampleHaplotype(genotypeToSample,
indexOfUnsupportedVars, starts, functionBlockRanges, out _);
var expectedBlock1 = new AlleleBlock(1, new[] { 1, 0, 1 }, 0, 0);
var expectedBlock2 = new AlleleBlock(1, new[] { 2, 0, 1 }, 0, 0);
Assert.True(alleleBlockToSampleHaplotype.ContainsKey(expectedBlock1));
Assert.True(alleleBlockToSampleHaplotype[expectedBlock1].SequenceEqual(new[] { new SampleHaplotype(2, 0) }));
Assert.True(alleleBlockToSampleHaplotype.ContainsKey(expectedBlock2));
Assert.True(alleleBlockToSampleHaplotype[expectedBlock2].SequenceEqual(new[] { new SampleHaplotype(2, 1) }));
}
public static GenotypeBlock CreateWithGenotypes(int posIndex, string[] genotypeIndexes)
{
var blockInfo = new GenotypeBlock(posIndex, genotypeIndexes.Length);
blockInfo.AddAlleleIndexes(genotypeIndexes);
return(blockInfo);
}
public void GetAlleleBlockToSampleHaplotype_AwareOfTrimmedRefPositions()
{
var genotypeBlock1 = new GenotypeBlock(new[] { "0|0", "1|1", "1|1", "0|0" }.Select(Genotype.GetGenotype).ToArray());
var genotypeBlock2 = new GenotypeBlock(new[] { "0|0", "1|1", "1|1" }.Select(Genotype.GetGenotype).ToArray());
var genotypeBlock3 = new GenotypeBlock(new[] { "1|1", "1|1", "0|0" }.Select(Genotype.GetGenotype).ToArray(), 1);
var genotypeBlock4 = new GenotypeBlock(new[] { "1|1", "1|1" }.Select(Genotype.GetGenotype).ToArray(), 1);
var genotypeToSample =
new Dictionary <GenotypeBlock, List <int> >
{
{ genotypeBlock1, new List <int> {
0
} },
{ genotypeBlock2, new List <int> {
1
} },
{ genotypeBlock3, new List <int> {
2
} },
{ genotypeBlock4, new List <int> {
3
} }
};
var indexOfUnsupportedVars = Enumerable.Repeat(new HashSet <int>(), 4).ToArray();
var starts = Enumerable.Range(100, 4).ToArray();
var functionBlockRanges = starts.Select(x => x + 2).ToList();
var alleleBlockToSampleHaplotype = AlleleBlock.GetAlleleBlockToSampleHaplotype(genotypeToSample,
indexOfUnsupportedVars, starts, functionBlockRanges, out _);
var expectedBlock1 = new AlleleBlock(1, new[] { 1, 1 }, 1, 1);
var expectedBlock2 = new AlleleBlock(1, new[] { 1, 1 }, 1, 0);
var expectedBlock3 = new AlleleBlock(1, new[] { 1, 1 }, 0, 1);
var expectedBlock4 = new AlleleBlock(1, new[] { 1, 1 }, 0, 0);
Assert.True(alleleBlockToSampleHaplotype.ContainsKey(expectedBlock1));
Assert.True(alleleBlockToSampleHaplotype[expectedBlock1]
.SequenceEqual(new[] { new SampleHaplotype(0, 0), new SampleHaplotype(0, 1) }));
Assert.True(alleleBlockToSampleHaplotype.ContainsKey(expectedBlock2));
Assert.True(alleleBlockToSampleHaplotype[expectedBlock2]
.SequenceEqual(new[] { new SampleHaplotype(1, 0), new SampleHaplotype(1, 1) }));
Assert.True(alleleBlockToSampleHaplotype.ContainsKey(expectedBlock3));
Assert.True(alleleBlockToSampleHaplotype[expectedBlock3]
.SequenceEqual(new[] { new SampleHaplotype(2, 0), new SampleHaplotype(2, 1) }));
Assert.True(alleleBlockToSampleHaplotype.ContainsKey(expectedBlock4));
Assert.True(alleleBlockToSampleHaplotype[expectedBlock4]
.SequenceEqual(new[] { new SampleHaplotype(3, 0), new SampleHaplotype(3, 1) }));
}
public void GetAlleleBlockToSampleHaplotype_AlleleBlock_OneAlleleIsRef_EachTime()
{
var genotypeBlock1 = new GenotypeBlock(new[] { "1|0", "0|1", "1|0", "0|1" }.Select(Genotype.GetGenotype).ToArray());
var genotypeBlock2 = new GenotypeBlock(new[] { "1/1", "0|1", "1|0" }.Select(Genotype.GetGenotype).ToArray(), 1);
var genotypeBlock3 = new GenotypeBlock(new[] { "0|0", "1|0", "0|1", "0|0" }.Select(Genotype.GetGenotype).ToArray());
var genotypeBlock4 = new GenotypeBlock(new[] { "0|1", "1|0", "1|0" }.Select(Genotype.GetGenotype).ToArray());
var genotypeToSample =
new Dictionary <GenotypeBlock, List <int> >
{
{ genotypeBlock1, new List <int> {
0
} },
{ genotypeBlock2, new List <int> {
1
} },
{ genotypeBlock3, new List <int> {
2
} },
{ genotypeBlock4, new List <int> {
3
} }
};
var indexOfUnsupportedVars = Enumerable.Repeat(new HashSet <int>(), genotypeBlock1.Genotypes.Length).ToArray();
var starts = new[] { 100, 101, 102, 104 };
var functionBlockRanges = starts.Select(x => x + 2).ToList();
var alleleBlockToSampleHaplotype = AlleleBlock.GetAlleleBlockToSampleHaplotype(genotypeToSample,
indexOfUnsupportedVars, starts, functionBlockRanges, out _);
var expectedBlock1 = new AlleleBlock(0, new[] { 1, 0, 1 }, 0, 0);
var expectedBlock2 = new AlleleBlock(0, new[] { 0, 1, 0 }, 0, 0);
var expectedBlock3 = new AlleleBlock(1, new[] { 1, 0 }, 0, 0);
var expectedBlock4 = new AlleleBlock(1, new[] { 1, 1 }, 0, 0);
var expectedBlock5 = new AlleleBlock(1, new[] { 0, 0 }, 0, 0);
Assert.True(alleleBlockToSampleHaplotype.ContainsKey(expectedBlock1));
Assert.True(alleleBlockToSampleHaplotype[expectedBlock1].SequenceEqual(new[] { new SampleHaplotype(0, 0) }));
Assert.True(alleleBlockToSampleHaplotype.ContainsKey(expectedBlock2));
Assert.True(alleleBlockToSampleHaplotype[expectedBlock2].SequenceEqual(new[] { new SampleHaplotype(0, 1) }));
Assert.True(alleleBlockToSampleHaplotype.ContainsKey(expectedBlock3));
Assert.True(alleleBlockToSampleHaplotype[expectedBlock3].SequenceEqual(new[] { new SampleHaplotype(1, 0) }));
Assert.True(alleleBlockToSampleHaplotype.ContainsKey(expectedBlock4));
Assert.True(alleleBlockToSampleHaplotype[expectedBlock4].SequenceEqual(new[] { new SampleHaplotype(1, 1), new SampleHaplotype(3, 0) }));
Assert.True(alleleBlockToSampleHaplotype.ContainsKey(expectedBlock5));
Assert.True(alleleBlockToSampleHaplotype[expectedBlock5].SequenceEqual(new[] { new SampleHaplotype(3, 1) }));
}
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 Merge_AsExpected()
{
var genotypeBlock1 = new GenotypeBlock(new[] { "1|0", "1|1", "1|1" }.Select(Genotype.GetGenotype).ToArray());
var genotypeBlock2 = new GenotypeBlock(new[] { "0|0", "1|0", "1|1" }.Select(Genotype.GetGenotype).ToArray());
var genotypeToSample =
new Dictionary <GenotypeBlock, List <int> >
{
{ genotypeBlock1, new List <int> {
0
} },
{ genotypeBlock2, new List <int> {
1
} }
};
var indexOfUnsupportedVars = Enumerable.Repeat(new HashSet <int>(), 3).ToArray();
var starts = Enumerable.Range(100, 3).ToArray();
var functionBlockRanges = starts.Select(x => x + 2).ToList();
var alleleBlockToSampleHaplotype = AlleleBlock.GetAlleleBlockToSampleHaplotype(genotypeToSample,
indexOfUnsupportedVars, starts, functionBlockRanges, out var alleleBlockGraph);
var mergedAlleleBlockToSampleHaplotype =
AlleleBlockMerger.Merge(alleleBlockToSampleHaplotype, alleleBlockGraph);
var expectedBlock1 = new AlleleBlock(0, new[] { 1, 1, 1 }, -1, -1);
var expectedBlock2 = new AlleleBlock(0, new[] { 0, 1, 1 }, -1, -1);
var expectedBlock3 = new AlleleBlock(0, new[] { 0, 0, 1 }, -1, -1);
Assert.True(mergedAlleleBlockToSampleHaplotype.ContainsKey(expectedBlock1));
Assert.True(mergedAlleleBlockToSampleHaplotype[expectedBlock1]
.SequenceEqual(new[] { new SampleHaplotype(0, 0) }));
Assert.True(mergedAlleleBlockToSampleHaplotype.ContainsKey(expectedBlock2));
Assert.True(mergedAlleleBlockToSampleHaplotype[expectedBlock2]
.SequenceEqual(new[] { new SampleHaplotype(0, 1), new SampleHaplotype(1, 0) }));
Assert.True(mergedAlleleBlockToSampleHaplotype.ContainsKey(expectedBlock3));
Assert.True(mergedAlleleBlockToSampleHaplotype[expectedBlock3]
.SequenceEqual(new[] { new SampleHaplotype(1, 1) }));
}
