public void DetermineExonicEffect(ITranscript transcript, IInterval variant, IMappedPosition position,
int coveredCdnaStart, int coveredCdnaEnd, int coveredCdsStart, int coveredCdsEnd, string altAllele,
bool startCodonInsertionWithNoImpact)
{
HasExonOverlap = position.ExonStart != -1 || position.ExonEnd != -1;
if (transcript.Translation != null)
{
var codingRegion = transcript.Translation.CodingRegion;
AfterCoding = IsAfterCoding(variant.Start, variant.End, transcript.End, codingRegion.End);
BeforeCoding = IsBeforeCoding(variant.Start, variant.End, transcript.Start, codingRegion.Start);
WithinCds = IsWithinCds(coveredCdsStart, coveredCdsEnd, codingRegion, variant);
IsCoding = !startCodonInsertionWithNoImpact && (position.CdsStart != -1 || position.CdsEnd != -1);
}
WithinCdna = IsWithinCdna(coveredCdnaStart, coveredCdnaEnd, transcript.TotalExonLength);
if (coveredCdsStart != -1 && coveredCdsEnd != -1)
{
var varLen = coveredCdsEnd - coveredCdsStart + 1;
var alleleLen = altAllele?.Length ?? 0;
HasFrameShift = position.CdsStart != -1 && position.CdsEnd != -1 && !Codons.IsTriplet(alleleLen - varLen);
}
OverlapWithMicroRna = IsMatureMirnaVariant(position.CdnaStart, position.CdnaEnd, transcript.MicroRnas,
transcript.BioType == BioType.miRNA);
}
private static TranscriptPositionalEffect GetPositionalEffect(ITranscript transcript, ISimpleVariant variant,
IMappedPosition position, string refAminoAcid, string altAminoAcid, int coveredCdnaStart,
int coveredCdnaEnd, int coveredCdsStart, int coveredCdsEnd)
{
bool startCodonInsertionWithNoImpact = variant.Type == VariantType.insertion &&
position.ProteinStart <= 1 &&
altAminoAcid.EndsWith(refAminoAcid);
var positionalEffect = new TranscriptPositionalEffect();
positionalEffect.DetermineIntronicEffect(transcript.TranscriptRegions, variant, variant.Type);
positionalEffect.DetermineExonicEffect(transcript, variant, position, coveredCdnaStart, coveredCdnaEnd,
coveredCdsStart, coveredCdsEnd, variant.AltAllele, startCodonInsertionWithNoImpact);
return(positionalEffect);
}
public AnnotatedTranscript(ITranscript transcript, string referenceAminoAcids, string alternateAminoAcids,
string referenceCodons, string alternateCodons, IMappedPosition mappedPosition, string hgvsCoding,
string hgvsProtein, PredictionScore sift, PredictionScore polyphen,
List <ConsequenceTag> consequences, bool?completeOverlap)
{
Transcript = transcript;
ReferenceAminoAcids = referenceAminoAcids;
AlternateAminoAcids = alternateAminoAcids;
ReferenceCodons = referenceCodons;
AlternateCodons = alternateCodons;
MappedPosition = mappedPosition;
HgvsCoding = hgvsCoding;
HgvsProtein = hgvsProtein;
Sift = sift;
PolyPhen = polyphen;
Consequences = consequences;
CompleteOverlap = completeOverlap;
}
public AnnotatedTranscript(ITranscript transcript, string referenceAminoAcids, string alternateAminoAcids,
string referenceCodons, string alternateCodons, IMappedPosition mappedPosition, string hgvsCoding,
string hgvsProtein, PredictionScore sift, PredictionScore polyphen,
IEnumerable <ConsequenceTag> consequences, IGeneFusionAnnotation geneFusionAnnotation)
{
Transcript = transcript;
ReferenceAminoAcids = referenceAminoAcids;
AlternateAminoAcids = alternateAminoAcids;
ReferenceCodons = referenceCodons;
AlternateCodons = alternateCodons;
MappedPosition = mappedPosition;
HgvsCoding = hgvsCoding;
HgvsProtein = hgvsProtein;
Sift = sift;
PolyPhen = polyphen;
Consequences = consequences;
GeneFusionAnnotation = geneFusionAnnotation;
PluginData = new List <IPluginData>();
}
private static string GetTranscriptRefAllele(IMappedPosition position, ISequence cdnaSequence, ISimpleVariant variant,
bool onReverseStrand)
{
var variantRef = HgvsUtilities.GetTranscriptAllele(variant.RefAllele, onReverseStrand);
if (position == null || cdnaSequence == null)
{
return(variantRef);
}
var start = position.CoveredCdnaStart;
var end = position.CoveredCdnaEnd;
if (start == -1 && end == -1)
{
return(variantRef);
}
if (start != -1 && end != -1 && end < start)
{
Swap.Int(ref start, ref end);
}
return(cdnaSequence.Substring(start - 1, end - start + 1));
}
public static string GetHgvsProteinAnnotation(
ITranscript transcript,
string refAminoAcids,
string altAminoAcids,
string transcriptAltAllele,
IMappedPosition position,
VariantEffect variantEffect,
ISimpleVariant variant,
ISequence refSequence,
string hgvscNotation,
bool isMitochondrial)
{
if (IsHgvspNull(transcriptAltAllele, position.CdsStart, position.CdsEnd, variant, hgvscNotation))
{
return(null);
}
var peptideSeq = transcript.Translation.PeptideSeq;
// Amino acid seq should never go past the stop codon
refAminoAcids = !refAminoAcids.EndsWith(AminoAcids.StopCodon) && refAminoAcids.Contains(AminoAcids.StopCodon)
? refAminoAcids.OptimizedSplit(AminoAcids.StopCodon[0])[0] + AminoAcids.StopCodon
: refAminoAcids;
int proteinStart = position.ProteinStart;
HgvsUtilities.ShiftAndRotateAlleles(ref proteinStart, ref refAminoAcids, ref altAminoAcids, peptideSeq);
var end = proteinStart + refAminoAcids.Length - 1;
var refAbbreviation = AminoAcids.GetAbbreviations(refAminoAcids);
var altAbbreviation = AminoAcids.GetAbbreviations(altAminoAcids);
var proteinId = transcript.Translation.ProteinId.WithVersion;
var proteinChange = GetProteinChange(proteinStart, refAminoAcids, altAminoAcids, peptideSeq, variantEffect);
// ReSharper disable once SwitchStatementMissingSomeCases
switch (proteinChange)
{
case ProteinChange.Substitution:
return(HgvspNotation.GetSubstitutionNotation(proteinId, proteinStart, refAbbreviation, altAbbreviation));
case ProteinChange.Unknown:
return(HgvspNotation.GetUnknownNotation(proteinId, proteinStart, end, refAbbreviation, altAbbreviation));
case ProteinChange.Deletion:
return(HgvspNotation.GetDeletionNotation(proteinId, proteinStart, end, refAbbreviation, variantEffect.IsStopGained()));
case ProteinChange.Duplication:
proteinStart -= altAminoAcids.Length;
return(HgvspNotation.GetDuplicationNotation(proteinId, proteinStart, end, altAbbreviation));
case ProteinChange.Frameshift:
return(GetHgvsFrameshiftNotation(refSequence, position.CdsStart, position.CdsEnd, transcriptAltAllele,
transcript, isMitochondrial, proteinId, proteinStart, end));
case ProteinChange.None:
return(HgvspNotation.GetSilentNotation(hgvscNotation, proteinStart, refAbbreviation, variantEffect.IsStopRetained()));
case ProteinChange.DelIns:
return(HgvspNotation.GetDelInsNotation(proteinId, proteinStart, end, refAbbreviation, altAbbreviation));
case ProteinChange.Insertion:
Swap.Int(ref proteinStart, ref end);
return(HgvspNotation.GetInsertionNotation(proteinId, proteinStart, end, altAbbreviation, peptideSeq));
case ProteinChange.Extension:
var altPeptideSequence = HgvsUtilities.GetAltPeptideSequence(refSequence, position.CdsStart, position.CdsEnd,
transcriptAltAllele, transcript, isMitochondrial);
altAbbreviation = proteinStart <= altPeptideSequence.Length ? AminoAcids.ConvertAminoAcidToAbbreviation(altPeptideSequence[proteinStart - 1]): "Ter";
var countToStop = HgvsUtilities.GetNumAminoAcidsUntilStopCodon(altPeptideSequence, peptideSeq, proteinStart - 1, false);
return(HgvspNotation.GetExtensionNotation(proteinId, proteinStart, refAbbreviation, altAbbreviation, countToStop));
case ProteinChange.StartLost:
return(HgvspNotation.GetStartLostNotation(proteinId, proteinStart, end, refAbbreviation));
}
return(null);
}
private static (PredictionScore Sift, PredictionScore PolyPhen) GetPredictionScores(IMappedPosition position,
string refAminoAcid, string altAminoAcid, IPredictionCache siftCache, IPredictionCache polyphenCache,
int siftIndex, int polyphenIndex)
{
if (!NeedPredictionScore(position.ProteinStart, position.ProteinEnd, refAminoAcid, altAminoAcid) ||
position.ProteinStart == -1)
{
return(null, null);
}
var newAminoAcid = altAminoAcid[0];
var siftScore = GetPredictionScore(position.ProteinStart, newAminoAcid, siftCache, siftIndex);
var polyphenScore = GetPredictionScore(position.ProteinStart, newAminoAcid, polyphenCache, polyphenIndex);
return(siftScore, polyphenScore);
}