/// <summary>
/// assigns the reference and alternate codons [TranscriptVariationAllele.pm:259 codon]
/// </summary>
public static void Assign(TranscriptAnnotation ta, Transcript transcript, ICompressedSequence compressedSequence)
{
// sanity check: make sure this is a coding region
if (!(ta.HasValidCdsEnd && ta.HasValidCdsStart))
{
ta.ReferenceCodon = null;
ta.AlternateCodon = null;
return;
}
// calculate necessary coordinates and lengths
int aminoAcidStart = ta.ProteinBegin * 3 - 2;
int aminoAcidEnd = ta.ProteinEnd * 3;
int prefixLen = ta.CodingDnaSequenceBegin - aminoAcidStart;
int suffixLen = aminoAcidEnd - ta.CodingDnaSequenceEnd;
var codingSequence = new CodingSequence(compressedSequence, transcript.Translation.CodingRegion.GenomicStart,
transcript.Translation.CodingRegion.GenomicEnd, transcript.CdnaMaps, transcript.Gene.OnReverseStrand,
transcript.StartExonPhase);
var aminoAcidSeq = codingSequence.Sequence();
int start1 = aminoAcidStart - 1;
int start2 = aminoAcidEnd - suffixLen;
int maxSuffixLen = aminoAcidSeq.Length - start2;
bool atTailEnd = false;
if (suffixLen > maxSuffixLen)
{
suffixLen = maxSuffixLen;
atTailEnd = true;
}
if (start1 < 0)
{
start1 = 0;
}
if (start2 < 0)
{
start2 = 0;
}
if (prefixLen < 0)
{
prefixLen = 0;
}
string prefix = start1 + prefixLen < aminoAcidSeq.Length
? aminoAcidSeq.Substring(start1, prefixLen).ToLower()
: "AAA";
string suffix = suffixLen > 0
? aminoAcidSeq.Substring(start2, suffixLen).ToLower()
: "";
ta.HasFrameShift = false;
ta.ReferenceCodon = GetCodon(ta.TranscriptReferenceAllele, prefix, suffix, ref ta.HasFrameShift, atTailEnd);
ta.AlternateCodon = GetCodon(ta.TranscriptAlternateAllele, prefix, suffix, ref ta.HasFrameShift, atTailEnd);
}
private void LocateExonIntron(Transcript transcript, int pos)
{
var exons = transcript.CdnaMaps;
if (pos < exons.First().GenomicStart || pos > exons.Last().GenomicEnd)
{
return;
}
var startIdx = 0;
while (startIdx < exons.Length)
{
if (pos > exons[startIdx].GenomicEnd)
{
startIdx++;
}
if (pos < exons[startIdx].GenomicStart)
{
Intron = transcript.Gene.OnReverseStrand ? exons.Length - startIdx : startIdx;
return;
}
if (pos <= exons[startIdx].GenomicEnd)
{
Exon = transcript.Gene.OnReverseStrand ? exons.Length - startIdx : startIdx + 1;
return;
}
}
}
private static string MapCdnaPosition(Transcript transcript, int breakendPosition)
{
if (breakendPosition > transcript.End || breakendPosition < transcript.Start)
{
return(null);
}
var startIdx = 0;
var endIdx = transcript.CdnaMaps.Length - 1;
while (startIdx <= endIdx)
{
if (transcript.CdnaMaps[startIdx].GenomicEnd >= breakendPosition)
{
break;
}
startIdx++;
}
var inExon = breakendPosition >= transcript.CdnaMaps[startIdx].GenomicStart;
if (inExon)
{
var pos = ConvertGenomicPosToCodingPos(breakendPosition, transcript.CdnaMaps[startIdx],
transcript.Gene.OnReverseStrand, transcript.Translation.CodingRegion.CdnaStart, transcript.Translation.CodingRegion.CdnaEnd);
return(pos);
}
var distance1 = breakendPosition - transcript.CdnaMaps[startIdx - 1].GenomicEnd;
var distance2 = transcript.CdnaMaps[startIdx].GenomicStart - breakendPosition;
var distance = distance1;
var mappedExonIdx = startIdx - 1;
var mappedExonPos = transcript.CdnaMaps[startIdx - 1].GenomicEnd;
var orientation = transcript.Gene.OnReverseStrand ? '-' : '+';
if (distance1 > distance2)
{
distance = distance2;
mappedExonIdx = startIdx;
mappedExonPos = transcript.CdnaMaps[startIdx].GenomicStart;
orientation = transcript.Gene.OnReverseStrand ? '+' : '-';
}
var exonPos = ConvertGenomicPosToCodingPos(mappedExonPos, transcript.CdnaMaps[mappedExonIdx],
transcript.Gene.OnReverseStrand, transcript.Translation.CodingRegion.CdnaStart, transcript.Translation.CodingRegion.CdnaEnd);
return(exonPos + orientation + distance);
}
public BreakendTranscriptAnnotation(Transcript transcript, int breakendPosition, char isBreakendSuffix)
{
var transcriptId = TranscriptUtilities.GetTranscriptId(transcript);
TranscriptDataSource = transcript.TranscriptSource;
GeneName = transcript.Gene.Symbol;
if (transcript.Translation == null || breakendPosition < transcript.Translation.CodingRegion.GenomicStart || breakendPosition > transcript.Translation.CodingRegion.GenomicEnd)
{
InCodingRegion = false;
return;
}
InCodingRegion = true;
var transcriptCdnaLength = transcript.Translation.CodingRegion.CdnaEnd - transcript.Translation.CodingRegion.CdnaStart + 1;
_referenceName = "chr";
_codingStart = transcript.Translation.CodingRegion.GenomicStart;
_codingEnd = transcript.Translation.CodingRegion.GenomicEnd;
// map cdn position
var complementaryCdnaPosDescription = MapCdnaPosition(transcript, breakendPosition);
LocateExonIntron(transcript, breakendPosition);
var transcriptOrientation = transcript.Gene.OnReverseStrand ? '-' : '+';
ConsistentOrientation = transcriptOrientation == isBreakendSuffix;
if (ConsistentOrientation)
{
HgvsDescription = GeneName + "{" + transcriptId + "}" + ":c." + complementaryCdnaPosDescription + "_" +
transcriptCdnaLength;
}
else
{
HgvsDescription = GeneName + "{" + transcriptId + "}" + ":c." + 1 + "_" + complementaryCdnaPosDescription;
}
}
public bool CheckForDuplicationForAltAlleleWithinTranscript(ICompressedSequence compressedSequence, Transcript transcript)
{
if (VepVariantType != VariantType.insertion)
{
return(false);
}
int altAlleleLen = AlternateAllele.Length;
string compareRegion;
if (transcript.Gene.OnReverseStrand)
{
if (End + altAlleleLen > transcript.End)
{
return(false);
}
compareRegion = compressedSequence.Substring(Start - 1, altAlleleLen);
}
else
{
if (Start - altAlleleLen < transcript.Start)
{
return(false);
}
compareRegion = compressedSequence.Substring(End - altAlleleLen, altAlleleLen);
}
if (compareRegion == AlternateAllele)
{
return(true);
}
return(false);
}