public SnpEffAnnotation(string annotation)
{
bool isSnpEffAnnotation = annotation.StartsWith("ANN=") || annotation.StartsWith("EFF=");
Annotation = isSnpEffAnnotation ? annotation.Substring(4) : annotation;
if (!isSnpEffAnnotation)
{
return;
}
string[] a = Annotation.Split('|');
Allele = a[0];
Effects = a[1].Split('&');
PutativeImpact = a[2];
GeneName = a[3];
GeneID = a[4];
FeatureType = a[5];
FeatureID = a[6];
TranscriptBiotype = a[7];
if (a[8].Split('/').Length > 0 && int.TryParse(a[8].Split('/')[0], out int x))
{
ExonIntronRank = x;
}
if (a[8].Split('/').Length > 1 && int.TryParse(a[8].Split('/')[1], out int y))
{
ExonIntronTotal = y;
}
HGVSNotationDnaLevel = a[9];
HGVSNotationProteinLevel = a[10];
if (a[11].Split('/').Length > 0 && int.TryParse(a[11].Split('/')[0], out x))
{
OneBasedTranscriptCDNAPosition = x;
}
if (a[11].Split('/').Length > 1 && int.TryParse(a[11].Split('/')[1], out y))
{
TranscriptCDNALength = y;
}
if (a[12].Split('/').Length > 0 && int.TryParse(a[12].Split('/')[0], out x))
{
OneBasedCodingDomainSequencePosition = x;
}
if (a[12].Split('/').Length > 1 && int.TryParse(a[12].Split('/')[1], out y))
{
CodingDomainSequenceLengthIncludingStopCodon = y;
}
if (a[13].Split('/').Length > 0 && int.TryParse(a[13].Split('/')[0], out x))
{
OneBasedProteinPosition = x;
}
if (a[13].Split('/').Length > 1 && int.TryParse(a[13].Split('/')[1], out y))
{
ProteinLength = y;
}
if (int.TryParse(a[14], out y))
{
DistanceToFeature = y;
}
Warnings = a[15].Split('&');
Missense = Effects.Any(eff => eff == "missense_variant");
Synonymous = !Effects.Any(eff => NonSynonymousVariations.Contains(eff));
FrameshiftVariant = Effects.Contains("frameshift_variant");
BadTranscript = Warnings.Any(w => BadTranscriptWarnings.Contains(w));
}
public SnpEffAnnotation(Variant variant, string annotation)
{
Variant = variant;
Annotation = annotation;
string[] a = annotation.Split('|');
Allele = a[0];
Effects = a[1].Split('&');
PutativeImpact = a[2];
GeneName = a[3];
GeneID = a[4];
FeatureType = a[5];
FeatureID = a[6];
TranscriptBiotype = a[7];
if (a[8].Split('/').Length > 0 && int.TryParse(a[8].Split('/')[0], out int x))
{
ExonIntronRank = x;
}
if (a[8].Split('/').Length > 1 && int.TryParse(a[8].Split('/')[1], out int y))
{
ExonIntronTotal = y;
}
HGVSNotationDnaLevel = a[9];
HGVSNotationProteinLevel = a[10];
if (a[11].Split('/').Length > 0 && int.TryParse(a[11].Split('/')[0], out x))
{
OneBasedTranscriptCDNAPosition = x;
}
if (a[11].Split('/').Length > 1 && int.TryParse(a[11].Split('/')[1], out y))
{
TranscriptCDNALength = y;
}
if (a[12].Split('/').Length > 0 && int.TryParse(a[12].Split('/')[0], out x))
{
OneBasedCodingDomainSequencePosition = x;
}
if (a[12].Split('/').Length > 1 && int.TryParse(a[12].Split('/')[1], out y))
{
CodingDomainSequenceLengthIncludingStopCodon = y;
}
if (a[13].Split('/').Length > 0 && int.TryParse(a[13].Split('/')[0], out x))
{
OneBasedProteinPosition = x;
}
if (a[13].Split('/').Length > 1 && int.TryParse(a[13].Split('/')[1], out y))
{
ProteinLength = y;
}
if (int.TryParse(a[14], out y))
{
DistanceToFeature = y;
}
Warnings = a[15].Split('&');
if (HGVSNotationProteinLevel != null)
{
GroupCollection hgvsProteinMatch = HGVSProteinRegex.Match(HGVSNotationProteinLevel).Groups;
if (hgvsProteinMatch.Count > 2)
{
ReferenceAminoAcid = ProteogenomicsUtility.amino_acids_3to1[hgvsProteinMatch[2].Value];
}
if (hgvsProteinMatch.Count > 3 && int.TryParse(hgvsProteinMatch[3].Value, out int location))
{
AminoAcidLocation = location;
}
if (hgvsProteinMatch.Count > 4)
{
AlternateAminoAcid = ProteogenomicsUtility.amino_acids_3to1[hgvsProteinMatch[4].Value];
}
}
Missense = Effects.Any(eff => eff == "missense_variant");
Synonymous = !Effects.Any(eff => NonSynonymousVariations.Contains(eff));
FrameshiftVariant = Effects.Contains("frameshift_variant");
BadTranscript = Warnings.Any(w => BadTranscriptWarnings.Contains(w));
}
