private static LiteXmlElement ParseXmlElement(XmlTextReader xmlReader)
{
var xmlElement = new LiteXmlElement(xmlReader.Name);
var isEmptyElement = xmlReader.IsEmptyElement;
if (xmlReader.HasAttributes)
{
while (xmlReader.MoveToNextAttribute())
{
xmlElement.Attributes[xmlReader.Name] = xmlReader.Value;
}
}
if (isEmptyElement)
{
return(xmlElement.IsEmpty()? null: xmlElement);
}
while (xmlReader.Read())
{
//we will read till an end tag is observed
switch (xmlReader.NodeType)
{
case XmlNodeType.Element: // The node is an element.
var child = ParseXmlElement(xmlReader);
if (child != null)
{
xmlElement.Children.Add(child);
}
break;
case XmlNodeType.Text:
if (!string.IsNullOrEmpty(xmlReader.Value))
{
xmlElement.StringValues.Add(xmlReader.Value);
}
break;
case XmlNodeType.EndElement: //Display the end of the element.
if (xmlReader.Name == xmlElement.Name)
{
return(xmlElement.IsEmpty()? null: xmlElement);
}
Console.WriteLine("WARNING!! encountered unexpected endElement tag:" + xmlReader.Name);
break;
}
}
return(null);
}
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);
}