/// <summary>
/// TODO: Should verify that this only happens once, perhaps also that the samples don't contain things that wouldn't match this,
/// </summary>
/// <param name="filterToApply">Filter to apply.</param>
public void ApplyFilterToAllSNPs(PolymorphismFilter filterToApply)
{
foreach (var root in treeRoot.GetAllChildren())
{
root.Mutations.FilterSites(filterToApply);
}
filtersApplied.Add(filterToApply);
}
public SimpleSample(string id, List <Polymorphism> polys, PolymorphismFilter filter)
{
this.Filter = filter;
this.Id = id;
//TODO: See if the filter was already applied?
this.Polymorphisms = filter.FilterPolys(polys).ToList();
//now calculate weight
this.TotalSampleWeight = Polymorphisms.Sum(x => x.getMutationRate());
}
public HaploTypeReport GetHaplotypeReport(Sequence toBuildReportFor, List <string> dataLines, string id = "Sample")
{
var delts = ReferenceGenome.GetDeltaAlignments(toBuildReportFor).SelectMany(x => x).ToList();
if (delts.Count != 1)
{
return(null);
throw new Exception("Final assembly had no or multiple delta alignments with the reference, whereas only 1 is expected");
}
var delt = delts [0];
var aln = delt.ConvertDeltaToSequences();
dataLines.Add("REF_OFFSET =" + delt.FirstSequenceStart.ToString());
dataLines.Add("ASSEMBLY_OFFSET =" + delt.SecondSequenceStart.ToString());
//dataLines.Add("ALN_SCORE=" + aln.Score.ToString());
var refseq = aln.FirstSequence as Sequence;
dataLines.Add("REF_SEQUENCE = " + refseq.ConvertToString());
var qseq = aln.SecondSequence as Sequence;
dataLines.Add("QUERY_SEQUENCE= " + qseq.ConvertToString());
//now get all polymorphisms, and sort haplotypes
//TODO: Don't call nucmer twice
var AllPolys = GenomeToHaploGrepConverter.FindPolymorphisms(toBuildReportFor);
PolymorphismFilter pf = new PolymorphismFilter();
var sample = new SimpleSample(id, AllPolys, pf);
var comparisons = treeRoot.GetAllChildren().Select(x => new HaplotypeComparison(x, sample)).ToList();
var report = new HaploTypeReport(comparisons, sample);
dataLines.AddRange(report.GetRowReportLines());
var passedFilters = sample.Polymorphisms.ToDictionary(x => x.position);
//noq get list of differences
dataLines.Add("#Data report below, (Note in rCRS positions, accounting for 'N' at position 3107 and in 1 based index)");
List <VariantAnnotation> reporters = new List <VariantAnnotation>()
{
new HaploTypeMatchAnnotation(report.BestHit, passedFilters),
new FrequencyFileAnnotation(), new BigTableAnnotation()
};
var headerLine = String.Join(VariantAnnotation.FIELD_DELIM, reporters.Select(x => x.GetHeaderLine()).ToArray());
dataLines.Add(headerLine);
var infoLines = AllPolys.Select(x => String.Join(VariantAnnotation.FIELD_DELIM, reporters.Select(y => y.GetAnnotation(x)).ToArray()));
dataLines.AddRange(infoLines);
return(report);
}