private static ExitCodes ProgramExecution()
{
var logger = new ConsoleLogger();
var bundle = DataBundle.GetDataBundle(_inputReferencePath, _inputPrefix);
int numRefSeqs = bundle.SequenceReader.NumRefSeqs;
var chromosome = ReferenceNameUtilities.GetChromosome(bundle.SequenceReader.RefNameToChromosome, _referenceName);
bundle.Load(chromosome);
string outputStub = GetOutputStub(chromosome, bundle.Source);
var interval = new ChromosomeInterval(chromosome, _referencePosition, _referenceEndPosition);
var transcripts = GetTranscripts(logger, bundle, interval);
var sift = GetPredictionStaging(logger, "SIFT", transcripts, chromosome, bundle.SiftPredictions, bundle.SiftReader, x => x.SiftIndex, numRefSeqs);
var polyphen = GetPredictionStaging(logger, "PolyPhen", transcripts, chromosome, bundle.PolyPhenPredictions, bundle.PolyPhenReader, x => x.PolyPhenIndex, numRefSeqs);
string referenceBases = GetReferenceBases(logger, bundle.SequenceReader, interval);
var regulatoryRegionIntervalArrays = GetRegulatoryRegionIntervalArrays(logger, bundle.TranscriptCache, interval, numRefSeqs);
var transcriptIntervalArrays = PredictionUtilities.UpdateTranscripts(transcripts, bundle.SiftPredictions,
sift.Predictions, bundle.PolyPhenPredictions, polyphen.Predictions, numRefSeqs);
var transcriptStaging = GetTranscriptStaging(bundle.TranscriptCacheData.Header, transcriptIntervalArrays, regulatoryRegionIntervalArrays);
WriteCache(logger, FileUtilities.GetCreateStream(CacheConstants.TranscriptPath(outputStub)), transcriptStaging, "transcript");
WriteCache(logger, FileUtilities.GetCreateStream(CacheConstants.SiftPath(outputStub)), sift.Staging, "SIFT");
WriteCache(logger, FileUtilities.GetCreateStream(CacheConstants.PolyPhenPath(outputStub)), polyphen.Staging, "PolyPhen");
WriteReference(logger, CacheConstants.BasesPath(outputStub), bundle.SequenceReader, chromosome,
referenceBases, interval.Start);
return(ExitCodes.Success);
}
public void CreateFromSymbolicAllele_Duplication()
{
var interval = new ChromosomeInterval(ChromosomeUtilities.Chr1, 37820921, 38404543);
BreakEndAdjacency[] adjacencies = BreakEndUtilities.CreateFromSymbolicAllele(interval, VariantType.tandem_duplication);
Assert.NotNull(adjacencies);
Assert.Equal(2, adjacencies.Length);
var observed = adjacencies[0];
Assert.Equal(ChromosomeUtilities.Chr1.EnsemblName, observed.Origin.Chromosome.EnsemblName);
Assert.Equal(38404543, observed.Origin.Position);
Assert.False(observed.Origin.OnReverseStrand);
Assert.Equal(ChromosomeUtilities.Chr1.EnsemblName, observed.Partner.Chromosome.EnsemblName);
Assert.Equal(37820920, observed.Partner.Position);
Assert.False(observed.Partner.OnReverseStrand);
var observed2 = adjacencies[1];
Assert.Equal(ChromosomeUtilities.Chr1.EnsemblName, observed2.Origin.Chromosome.EnsemblName);
Assert.Equal(37820920, observed2.Origin.Position);
Assert.True(observed2.Origin.OnReverseStrand);
Assert.Equal(ChromosomeUtilities.Chr1.EnsemblName, observed2.Partner.Chromosome.EnsemblName);
Assert.Equal(38404543, observed2.Partner.Position);
Assert.True(observed2.Partner.OnReverseStrand);
}
public void CreateFromSymbolicAllele_Deletion()
{
var interval = new ChromosomeInterval(ChromosomeUtilities.Chr1, 1594584, 1660503);
BreakEndAdjacency[] adjacencies = BreakEndUtilities.CreateFromSymbolicAllele(interval, VariantType.deletion);
Assert.NotNull(adjacencies);
Assert.Equal(2, adjacencies.Length);
var observed = adjacencies[0];
Assert.Equal(ChromosomeUtilities.Chr1.EnsemblName, observed.Origin.Chromosome.EnsemblName);
Assert.Equal(1594583, observed.Origin.Position);
Assert.False(observed.Origin.OnReverseStrand);
Assert.Equal(ChromosomeUtilities.Chr1.EnsemblName, observed.Partner.Chromosome.EnsemblName);
Assert.Equal(1660504, observed.Partner.Position);
Assert.False(observed.Partner.OnReverseStrand);
var observed2 = adjacencies[1];
Assert.Equal(ChromosomeUtilities.Chr1.EnsemblName, observed2.Origin.Chromosome.EnsemblName);
Assert.Equal(1660504, observed2.Origin.Position);
Assert.True(observed2.Origin.OnReverseStrand);
Assert.Equal(ChromosomeUtilities.Chr1.EnsemblName, observed2.Partner.Chromosome.EnsemblName);
Assert.Equal(1594583, observed2.Partner.Position);
Assert.True(observed2.Partner.OnReverseStrand);
}
public void CreateFromSymbolicAllele_Inversion()
{
var interval = new ChromosomeInterval(ChromosomeUtilities.Chr1, 63989116, 64291267);
BreakEndAdjacency[] adjacencies = BreakEndUtilities.CreateFromSymbolicAllele(interval, VariantType.inversion);
Assert.NotNull(adjacencies);
Assert.Equal(2, adjacencies.Length);
var observed = adjacencies[0];
Assert.Equal(ChromosomeUtilities.Chr1.EnsemblName, observed.Origin.Chromosome.EnsemblName);
Assert.Equal(63989115, observed.Origin.Position);
Assert.False(observed.Origin.OnReverseStrand);
Assert.Equal(ChromosomeUtilities.Chr1.EnsemblName, observed.Partner.Chromosome.EnsemblName);
Assert.Equal(64291267, observed.Partner.Position);
Assert.True(observed.Partner.OnReverseStrand);
var observed2 = adjacencies[1];
Assert.Equal(ChromosomeUtilities.Chr1.EnsemblName, observed2.Origin.Chromosome.EnsemblName);
Assert.Equal(64291268, observed2.Origin.Position);
Assert.True(observed2.Origin.OnReverseStrand);
Assert.Equal(ChromosomeUtilities.Chr1.EnsemblName, observed2.Partner.Chromosome.EnsemblName);
Assert.Equal(63989116, observed2.Partner.Position);
Assert.False(observed2.Partner.OnReverseStrand);
}
public void GetOverlappingFlankingTranscripts_NoOverlaps()
{
var interval = new ChromosomeInterval(ChromosomeUtilities.Chr11, 5000, 5001);
ITranscript[] overlappingTranscripts = _cache.TranscriptIntervalForest.GetAllFlankingValues(interval);
Assert.Null(overlappingTranscripts);
}
public void CreateFromSymbolicAllele_UnhandledVariantType_ReturnNull()
{
var interval = new ChromosomeInterval(ChromosomeUtilities.Chr1, 63989116, 64291267);
BreakEndAdjacency[] adjacencies = BreakEndUtilities.CreateFromSymbolicAllele(interval, VariantType.complex_structural_alteration);
Assert.Null(adjacencies);
}
public void GetOverlappingFlankingTranscripts_TwoOverlaps()
{
var interval = new ChromosomeInterval(ChromosomeUtilities.Chr1, 100, 200);
ITranscript[] overlappingTranscripts = _cache.TranscriptIntervalForest.GetAllFlankingValues(interval);
Assert.NotNull(overlappingTranscripts);
Assert.Equal(2, overlappingTranscripts.Length);
}
public void GetOverlapFractions_ReturnNulls_BreakEnd()
{
var saInterval = new ChromosomeInterval(ChromosomeUtilities.Chr1, 2, 1);
var variant = new SimpleVariant(ChromosomeUtilities.Chr1, 1, 2, null, null, VariantType.translocation_breakend);
var(reciprocalOverlap, annotationOverlap) = SuppIntervalUtilities.GetOverlapFractions(saInterval, variant);
Assert.Null(reciprocalOverlap);
Assert.Null(annotationOverlap);
}
public void GetOverlapFractions_ReturnNulls_DifferentChroms()
{
var saInterval = new ChromosomeInterval(ChromosomeUtilities.Chr1, 1, 2);
var variant = new SimpleVariant(ChromosomeUtilities.Chr2, 1, 2, null, null, VariantType.deletion);
var(reciprocalOverlap, annotationOverlap) = SuppIntervalUtilities.GetOverlapFractions(saInterval, variant);
Assert.Null(reciprocalOverlap);
Assert.Null(annotationOverlap);
}
public void ChromosomeInterval_Setup()
{
const int expectedStart = 100;
const int expectedEnd = 200;
var observedInterval = new ChromosomeInterval(ChromosomeUtilities.Chr1, 100, 200);
Assert.Equal(ChromosomeUtilities.Chr1, observedInterval.Chromosome);
Assert.Equal(expectedStart, observedInterval.Start);
Assert.Equal(expectedEnd, observedInterval.End);
}
public void ChromosomeInterval_Setup()
{
var expectedChromosome = new Chromosome("chr1", "1", 0);
const int expectedStart = 100;
const int expectedEnd = 200;
var observedInterval = new ChromosomeInterval(expectedChromosome, 100, 200);
Assert.Equal(expectedChromosome, observedInterval.Chromosome);
Assert.Equal(expectedStart, observedInterval.Start);
Assert.Equal(expectedEnd, observedInterval.End);
}
public void GetOverlapFractions_NotNull_AsExpected(int varStart, int varEnd, int saStart, int saEnd, double expectedReciprocalOverlap, double expecedAnnotationOverlap)
{
var saInterval = new ChromosomeInterval(ChromosomeUtilities.Chr1, saStart, saEnd);
var variant = new SimpleVariant(ChromosomeUtilities.Chr1, varStart, varEnd, null, null, VariantType.deletion);
var(reciprocalOverlap, annotationOverlap) = SuppIntervalUtilities.GetOverlapFractions(saInterval, variant);
Assert.NotNull(reciprocalOverlap);
Assert.NotNull(annotationOverlap);
Assert.Equal(expectedReciprocalOverlap, reciprocalOverlap.Value, 5);
Assert.Equal(expecedAnnotationOverlap, annotationOverlap.Value, 5);
}
private static (ushort RefIndex, Interval <RepeatExpansionPhenotype> Interval) GetPhenotype(string line, IDictionary <string, IChromosome> refNameToChromosome)
{
string[] cols = line.OptimizedSplit('\t');
if (cols.Length < MinNumberOfColumns)
{
throw new InvalidDataException($"Expected at least {MinNumberOfColumns} columns in the STR data file, but found only {cols.Length}.");
}
string chromosomeString = cols[ChromIndex];
int start = int.Parse(cols[StartIndex]);
int end = int.Parse(cols[EndIndex]);
string phenotype = cols[PhenotypeIndex];
string omimId = cols[OmimIndex];
int[] repeatNumbers = cols[RepeatNumbersIndex].Split(',').Select(int.Parse).ToArray();
int[] alleleCounts = cols[AlleleCountsIndex].Split(',').Select(int.Parse).ToArray();
string[] classifications = cols[CategoriesIndex].Split(',').ToArray();
Interval[] classificationRanges = cols[CategoryRangesIndex].Split(',').Select(GetInterval).ToArray();
if (repeatNumbers.Length != alleleCounts.Length)
{
throw new InvalidDataException($"Inconsistent number of repeat numbers ({repeatNumbers.Length}) vs. allele counts ({alleleCounts.Length})");
}
if (classifications.Length != classificationRanges.Length)
{
throw new InvalidDataException($"Inconsistent number of values of classifications ({classifications.Length}) vs. classification ranges ({classificationRanges.Length})");
}
var chromosome = ReferenceNameUtilities.GetChromosome(refNameToChromosome, chromosomeString);
var chromosomeInterval = new ChromosomeInterval(chromosome, start, end);
double[] percentiles = PercentileUtilities.ComputePercentiles(repeatNumbers.Length, alleleCounts);
var rePhenotype = new RepeatExpansionPhenotype(chromosomeInterval, phenotype, omimId, repeatNumbers, percentiles, classifications, classificationRanges);
return(chromosome.Index, new Interval <RepeatExpansionPhenotype>(start, end, rePhenotype));
}
public MatcherTests()
{
var repeatNumbers = new[] { 7, 8, 9 };
double[] percentiles = { 0, 1, 1.5 };
var classificationRanges = new[] { new Interval(0, 27) };
var classifications = new[] { "Normal" };
var aInterval = new ChromosomeInterval(ChromosomeUtilities.Chr1, 100, 200);
var aPhenotype = new RepeatExpansionPhenotype(aInterval, "A", null, repeatNumbers, percentiles, classifications, classificationRanges);
var chr1Phenotypes = new Interval <RepeatExpansionPhenotype> [1];
chr1Phenotypes[0] = new Interval <RepeatExpansionPhenotype>(aInterval.Start, aInterval.End, aPhenotype);
var intervalArrays = new IntervalArray <RepeatExpansionPhenotype> [1];
intervalArrays[ChromosomeUtilities.Chr1.Index] = new IntervalArray <RepeatExpansionPhenotype>(chr1Phenotypes);
var phenotypeForest = new IntervalForest <RepeatExpansionPhenotype>(intervalArrays);
_matcher = new Matcher(phenotypeForest);
}
