private bool ValidateReference(string chromosome, int pos, string refAllele)
{
var refIndex = _compressedSequence.Renamer.GetReferenceIndex(chromosome);
if (refIndex == ChromosomeRenamer.UnknownReferenceIndex)
{
return(false);
}
_dataFileManager.LoadReference(refIndex, () => { });
return(_compressedSequence.Substring(pos - 1, refAllele.Length) == refAllele);
}
public PianoVariant Annotate(IVariant variant)
{
if (variant == null)
{
return(null);
}
var variantFeature = new VariantFeature(variant as VcfVariant, _renamer, _vid);
// load the reference sequence
_dataFileManager.LoadReference(variantFeature.ReferenceIndex, () => {});
// handle ref no-calls and assign the alternate alleles
variantFeature.AssignAlternateAlleles();
// annotate the variant
_pianoVariant = new PianoVariant(variantFeature);
Annotate(variantFeature);
_performanceMetrics.Increment();
return(_pianoVariant);
}
private void CreateVcf(StreamWriter writer, Transcript transcript)
{
var geneSymbol = transcript.Gene.Symbol;
if (!transcript.IsCanonical && _processedGeneSet.Contains(geneSymbol))
{
return;
}
if (transcript.Translation == null)
{
return;
}
_processedGeneSet.Add(geneSymbol);
_dataFileManager.LoadReference(transcript.ReferenceIndex, () => {});
var position = (transcript.Translation.CodingRegion.GenomicStart + transcript.Translation.CodingRegion.GenomicEnd) / 2;
var refAllele = _compressedSequence.Substring(position - 1, 1);
var altAllele = _nucleotides.First(nuceleotide => nuceleotide != refAllele);
writer.WriteLine($"{_renamer.UcscReferenceNames[transcript.ReferenceIndex]}\t{position}\t.\t{refAllele}\t{altAllele}\t.\t.\t.");
}
private List <ClinVarItem> ExtractClinVarItems(LiteXmlElement xmlElement)
{
ClearClinvarFields();
if (xmlElement == null)
{
return(null);
}
if (xmlElement.IsEmpty())
{
return(null);
}
foreach (var child in xmlElement.Children)
{
switch (child.Name)
{
case "ReferenceClinVarAssertion":
ParseRefClinVarAssertion(child);
break;
case "ClinVarAssertion":
ParseScv(child);
break;
}
}
if (_recordStatus != "current")
{
Console.WriteLine($"record status not current: {_recordStatus} for {_id}");
return(null);
}
var clinvarList = new List <ClinVarItem>();
foreach (var variant in _variantList)
{
// in order to match the VCF, we leave out the ones that do not have dbsnp id
if (variant.DbSnp == null)
{
continue;
}
if (!InputFileParserUtilities.IsDesiredChromosome(variant.Chromosome, _compressedSequence.Renamer))
{
continue;
}
if (variant.VariantType == "Microsatellite")
{
continue;
}
var refIndex = _compressedSequence.Renamer.GetReferenceIndex(variant.Chromosome);
if (refIndex == ChromosomeRenamer.UnknownReferenceIndex)
{
throw new GeneralException($"Could not find the reference index for: {variant.Chromosome}");
}
_dataFileManager.LoadReference(refIndex, () => {});
ClinvarVariant shiftedVariant = variant;
//some entries do not have ref allele in the xml file. For those, we extract them from our ref sequence
if (variant.ReferenceAllele == null && variant.VariantType == "Deletion")
{
shiftedVariant = GenerateRefAllele(variant, _compressedSequence);
}
if (variant.AltAllele == null && variant.VariantType == "Duplication")
{
shiftedVariant = GenerateAltAllele(variant, _compressedSequence);
}
//left align the variant
shiftedVariant = LeftShift(shiftedVariant);
if (variant.ReferenceAllele == null && variant.VariantType == "Indel" && variant.AltAllele != null)
{
shiftedVariant = GenerateRefAllele(variant, _compressedSequence);
}
_pubMedIds.Sort();
if (string.IsNullOrEmpty(shiftedVariant.ReferenceAllele) && string.IsNullOrEmpty(shiftedVariant.AltAllele))
{
continue;
}
clinvarList.Add(
new ClinVarItem(shiftedVariant.Chromosome,
shiftedVariant.Start,
_alleleOrigins.Distinct().ToList(),
shiftedVariant.AltAllele ?? "",
_id,
_reviewStatus,
_medGenIDs.Distinct().ToList(),
_omimIDs.Distinct().ToList(),
_orphanetIDs.Distinct().ToList(),
_prefPhenotypes.Count > 0? _prefPhenotypes.Distinct().ToList(): _altPhenotypes.Distinct().ToList(),
shiftedVariant.ReferenceAllele ?? "",
_significance,
_pubMedIds.Distinct().ToList(),
_lastUpdatedDate));
}
return(clinvarList.Count > 0 ? clinvarList: null);
}
private SupplementaryPositionCreator GetNextSupplementaryAnnotation()
{
// no more active iterators left
if (_iSupplementaryDataItemList.Count == 0 && _additionalItemsList.Count == 0)
{
return(null);
}
var minSupplementaryDataItem = CurrentMinSupplementaryDataItem();
if (minSupplementaryDataItem == null)
{
return(null); //nothing more to retun. All enumerators are empty.
}
var sa = new SupplementaryAnnotationPosition(minSupplementaryDataItem.Start);
var saCreator = new SupplementaryPositionCreator(sa)
{
RefSeqName = minSupplementaryDataItem.Chromosome
};
string refSequence = null;
if (_currentRefName == null || !_currentRefName.Equals(saCreator.RefSeqName))
{
CloseCurrentSaWriter();
_currentRefName = saCreator.RefSeqName;
var refIndex = _renamer.GetReferenceIndex(_currentRefName);
if (refIndex == ChromosomeRenamer.UnknownReferenceIndex)
{
throw new GeneralException($"Could not find the reference index for: {_currentRefName}");
}
_dataFileManager.LoadReference(refIndex, () => {});
OpenNewSaWriter();
}
if (_compressedSequence != null)
{
refSequence = _compressedSequence.Substring(sa.ReferencePosition - 1, ReferenceWindowSize);
}
// list of data items to be removed and added
var deleteList = new List <IEnumerator <SupplementaryDataItem> >();
foreach (var iDataEnumerator in _iSupplementaryDataItemList)
{
// only using items at the same location as minSuppDataItem
if (!iDataEnumerator.Current.Equals(minSupplementaryDataItem))
{
continue;
}
if (iDataEnumerator.Current.IsInterval)
{
var suppInterval = iDataEnumerator.Current.GetSupplementaryInterval(_renamer);
_supplementaryIntervalList.Add(suppInterval);
}
else
{
var additionalSuppData = iDataEnumerator.Current.SetSupplementaryAnnotations(saCreator, refSequence);
if (additionalSuppData != null)
{
_additionalItemsList.Add(additionalSuppData);
}
}
// adding empty enumerators to deleteList
if (!iDataEnumerator.MoveNext())
{
deleteList.Add(iDataEnumerator);
}
}
// add annotations from additional items if applicable.
AddAdditionalItems(minSupplementaryDataItem, saCreator);
// removing lists that are empty and therfore should be removed from the list of enumerators
_iSupplementaryDataItemList.RemoveAll(x => deleteList.Contains(x));
return(saCreator);
}
