/// <summary>
/// Get the last coding exon
/// </summary>
/// <returns></returns>
public Exon GetLastCodingExon()
{
List <CDS> cds = CdsSortedStrand;
if (cds.Count == 0)
{
return(null);
}
if (LastCodingExon == null)
{
// Get transcription start position
long cend = IsStrandPlus() ? cds.Last().OneBasedEnd : cds.Last().OneBasedStart;
// Pick exon intersecting cdsStart (TSS)
foreach (Exon exon in ExonsSortedStrand)
{
if (exon.Intersects(cend))
{
LastCodingExon = exon;
}
}
// Sanity check
if (LastCodingExon == null)
{
throw new ArgumentException("Error: Cannot find first coding exon for transcript:\n" + this);
}
}
return(LastCodingExon);
}
/// <summary>
/// Analyze insertions in this transcript. Add changeEffect to 'changeEffect'
/// </summary>
/// <param name="exon"></param>
/// <returns></returns>
protected override bool ChangeCodon(Exon exon)
{
string netChange = Variant.NetChange(Transcript.IsStrandMinus());
CodonsReference = CodonsRef();
CodonsAlternate = CodonsAlt();
EffectType effType;
if (netChange.Length % CODON_SIZE != 0)
{
/**
* Length not multiple of CODON_SIZE => FRAME_SHIFT
* E.g. :
* Original: AAA CCC GGG AAA CCC GGG AAA CCC GGG
* Insert 'TT' pos 0: TTA AAC CCG GGA AAC CCG GGA AAC CCG GG
* Insert 'TT' pos 1: ATT AAC CCG GGA AAC CCG GGA AAC CCG GG
* Insert 'TT' pos 2: AAT TAC CCG GGA AAC CCG GGA AAC CCG GG
*/
effType = EffectType.FRAME_SHIFT;
}
else if (CodonStartIndex == 0)
{
/**
* Length multiple of CODON_SIZE and insertion happens at codon boundary => CODON_INSERTION
* E.g. :
* Original: AAA CCC GGG AAA CCC GGG AAA CCC GGG
* Insert 'TTT' pos 0: TTT AAA CCC GGG AAA CCC GGG AAA CCC GGG
*/
effType = EffectType.CODON_INSERTION;
}
else
{
/**
* Length multiple of CODON_SIZE and insertion does not happen at codon boundary => CODON_CHANGE_PLUS_CODON_INSERTION
* E.g. :
* Original: AAA CCC GGG AAA CCC GGG AAA CCC GGG
* Insert 'TTT' pos 1: ATT TAA CCC GGG AAA CCC GGG AAA CCC GGG
* Insert 'TTT' pos 2: AAT TTA CCC GGG AAA CCC GGG AAA CCC GGG
*/
if (CodonsAlternate.ToUpper(CultureInfo.InvariantCulture).StartsWith(CodonsReference.ToUpper(CultureInfo.InvariantCulture)))
{
/**
* May be the inserted base are equal to the old ones.
* E.g.
* Original: AAA CCC GGG AAA CCC GGG AAA CCC GGG
* Insert 'AAA' pos 1: AAA AAA CCC GGG AAA CCC GGG AAA CCC GGG
*/
effType = EffectType.CODON_INSERTION;
}
else
{
effType = EffectType.CODON_CHANGE_PLUS_CODON_INSERTION;
}
}
Effect(exon, effType, false);
return(true);
}
/// <summary>
/// Get the simplest string describing the effect (this is mostly used for testcases)
/// </summary>
/// <param name="shortFormat"></param>
/// <returns></returns>
public string ToStringSimple(bool shortFormat)
{
string transcriptId = "";
Transcript tr = GetTranscript();
if (tr != null)
{
transcriptId = tr.ID;
}
string exonId = "";
Exon exon = GetExon();
//if (exon != null) exonId = exon.getId();
string eff = Effect(shortFormat, true, true, false, false);
if (eff != "")
{
return(eff);
}
if (exonId != "")
{
return(exonId);
}
if (transcriptId != "")
{
return(transcriptId);
}
return("NO EFFECT");
}
/// <summary>
/// Create UTR regions for this transcript
/// </summary>
public List <UTR> CreateUTRs()
{
if (CodingDomainSequences.Count == 0)
{
return(UTRs);
}
List <Interval> missing = Exons.OfType <Interval>().ToList();
foreach (Interval interval in UTRs.Concat(CodingDomainSequences.OfType <Interval>().ToList()))
{
missing = missing.SelectMany(i => i.Minus(interval)).ToList();
}
long codingMin = CodingDomainSequences.Select(c => c.OneBasedStart).Min();
long codingMax = CodingDomainSequences.Select(c => c.OneBasedEnd).Max();
foreach (Interval interval in missing)
{
Exon x = FindExon(interval);
if (x == null)
{
throw new ArgumentException("Cannot find exon for UTR: " + interval.ToString());
}
UTR toAdd = null;
if (IsStrandPlus())
{
if (interval.OneBasedEnd <= codingMin)
{
toAdd = new UTR5Prime(x, x.ChromosomeID, x.Source, x.Strand, interval.OneBasedStart, interval.OneBasedEnd);
}
else if (interval.OneBasedStart >= codingMax)
{
toAdd = new UTR3Prime(x, x.ChromosomeID, x.Source, x.Strand, interval.OneBasedStart, interval.OneBasedEnd);
}
}
else
{
if (interval.OneBasedStart >= codingMax)
{
toAdd = new UTR5Prime(x, x.ChromosomeID, x.Source, x.Strand, interval.OneBasedStart, interval.OneBasedEnd);
}
else if (interval.OneBasedEnd <= codingMin)
{
toAdd = new UTR3Prime(x, x.ChromosomeID, x.Source, x.Strand, interval.OneBasedStart, interval.OneBasedEnd);
}
}
// OK?
if (toAdd != null)
{
UTRs.Add(toAdd);
}
}
return(UTRs);
}
/// <summary>
/// Find base at genomic coordinate 'pos'
/// </summary>
/// <param name="pos"></param>
/// <returns></returns>
public ISequence BaseAt(int pos)
{
CalcCdsStartEnd();
Exon ex = FindExon(pos);
if (ex == null)
{
return(null);
}
return(ex.basesAt(pos - ex.OneBasedStart, 1));
}
/// <summary>
/// Analyze SNPs in this transcript. Add changeEffect to 'changeEffect'
/// </summary>
/// <param name="exon"></param>
/// <returns></returns>
protected override bool ChangeCodon(Exon exon)
{
// Get old and new codons
CodonsReference = CodonsRef();
CodonsAlternate = CodonsAlt();
// Use a generic low priority variant, this allows 'AdditionalEffects' to override it
Effect(exon, EffectType.CODON_CHANGE, true);
if (CodonsReference == "")
{
VariantEffects.AddErrorWarning(Variant, ErrorWarningType.ERROR_MISSING_CDS_SEQUENCE);
}
return(true);
}
public string getSequence()
{
// Create UTR sequence
StringBuilder sb = new StringBuilder();
foreach (UTR5Prime utr in get5primeUtrs())
{
Exon ex = (Exon)utr.Parent;
ISequence utrSeq = ex.Sequence;
if (utr.Length() < utrSeq.Count)
{
utrSeq = utrSeq.GetSubSequence(0, utr.Length());
} // UTR5' may stop before end of exon
sb.Append(SequenceExtensions.ConvertToString(utrSeq));
}
return(sb.ToString());
}
/// <summary>
/// Set marker. Add some warnings if the marker relates to incomplete transcripts
/// </summary>
/// <param name="marker"></param>
public void SetMarker(Interval marker)
{
Marker = marker;
Transcript transcript = GetTranscript();
if (transcript != null)
{
// Transcript level errors or warnings
AddErrorWarningInfo(transcript.sanityCheck(Variant));
// Exon level errors or warnings
Exon exon = GetExon();
if (exon != null)
{
AddErrorWarningInfo(exon.SanityCheck(Variant));
}
}
}
public List <Intron> CreateIntrons()
{
Exon previous = null;
foreach (Exon x in Exons)
{
if (previous == null)
{
previous = x;
continue;
}
Intron intron = new Intron(this, x.ChromosomeID, x.Source, x.Strand, previous.OneBasedEnd + 1, x.OneBasedStart - 1);
if (intron.Length() > 0)
{
Introns.Add(intron);
}
}
return(Introns);
}
private static MetadataListItem <List <string> > CDSFeatureMetadata(CDS cds, Exon exon)
{
string cdsAttributes = exon.GetGtfAttributes() + " protein_id \"" + (cds.Parent as Transcript).ProteinID + "\";";
var feature = new MetadataListItem <List <string> >(cds.FeatureType, cdsAttributes);
feature.SubItems["source"] = new List <string> {
cds.Source.ToString()
};
feature.SubItems["start"] = new List <string> {
cds.OneBasedStart.ToString()
};
feature.SubItems["end"] = new List <string> {
cds.OneBasedEnd.ToString()
};
if (cds.Strand != ".")
{
feature.SubItems["strand"] = new List <string> {
cds.Strand.ToString()
};
} // might take in features without strand later on
return(feature);
}
/// <summary>
/// Corrrects coordinates of end of coding sequence based on coding sequence length
/// </summary>
/// <param name="codingSequenceLength"></param>
/// <returns></returns>
public UTR3Prime EndFrameCorrection(long codingSequenceLength)
{
long endFrame = codingSequenceLength % 3;
if (endFrame <= 0)
{
return(null);
} // nothing to do
// First exon is not zero? => Create a UTR5 prime to compensate
Exon parent = (FindParent(typeof(Transcript)) as Transcript).GetLastCodingExon();
UTR3Prime utr3 = null;
if (IsStrandPlus())
{
long start = OneBasedEnd - (endFrame - 1);
utr3 = new UTR3Prime(parent, parent.ChromosomeID, parent.Source, parent.Strand, start, OneBasedEnd);
}
else
{
long end = OneBasedStart + (endFrame - 1);
utr3 = new UTR3Prime(parent, parent.ChromosomeID, parent.Source, parent.Strand, OneBasedStart, end);
}
// correct start or end coordinates
if (IsStrandPlus())
{
OneBasedEnd -= endFrame;
}
else
{
OneBasedStart += endFrame;
}
return(utr3);
}
public List <MetadataListItem <List <string> > > GetFeatures()
{
var features = new List <MetadataListItem <List <string> > >();
var geneMetadata = GetGtfFeatureMetadata();
features.Add(geneMetadata);
List <Interval> exonsAndCds = Exons.OfType <Interval>().Concat(CodingDomainSequences).OrderBy(t => t.OneBasedStart).ToList(); // exons before cds; exons should come up first after stable sorting
Exon currentExon = null;
foreach (Interval xc in exonsAndCds)
{
Exon x = xc as Exon;
if (x != null)
{
currentExon = x;
features.Add(x.GetGtfFeatureMetadata());
}
else
{
features.Add(CDSFeatureMetadata(xc as CDS, currentExon));
}
}
return(features);
}
/// <summary>
/// Corrrects coordinates of end of coding sequence based on coding sequence length
/// </summary>
/// <param name="codingSequenceLength"></param>
/// <returns></returns>
public UTR5Prime StartFrameCorrection()
{
if (StartFrame <= 0)
{
return(null);
} // nothing to do
// First exon is not zero? => Create a UTR5 prime to compensate
Exon parent = (FindParent(typeof(Transcript)) as Transcript).GetLastCodingExon();
UTR5Prime utr5 = null;
if (IsStrandPlus())
{
long end = OneBasedStart + (StartFrame - 1);
utr5 = new UTR5Prime(parent, parent.Source, parent.ChromosomeID, parent.Strand, OneBasedStart, end, null);
}
else
{
long start = OneBasedEnd - (StartFrame - 1);
utr5 = new UTR5Prime(parent, parent.Source, parent.ChromosomeID, parent.Strand, start, OneBasedEnd, null);
}
// correct start or end coordinates
if (IsStrandPlus())
{
OneBasedStart += StartFrame;
}
else
{
OneBasedEnd -= StartFrame;
}
StartFrame = 0;
return(utr5);
}
protected UTR(Exon parent, string chromID, string source, string strand, long oneBasedStart, long oneBasedEnd)
: base(parent, chromID, source, strand, oneBasedStart, oneBasedEnd)
{
}
protected UTR(Exon parent, string chromID, string source, string strand, long oneBasedStart, long oneBasedEnd, HashSet <Variant> variants)
: base(parent, chromID, source, strand, oneBasedStart, oneBasedEnd, variants)
{
}
/// <summary>
/// Processes a feature from a GFF3 gene model file.
/// </summary>
/// <param name="feature"></param>
/// <param name="oneBasedStart"></param>
/// <param name="oneBasedEnd"></param>
/// <param name="chrom"></param>
/// <param name="attributes"></param>
public void ProcessGff3Feature(MetadataListItem <List <string> > feature, long oneBasedStart, long oneBasedEnd, Chromosome chrom, Dictionary <string, string> attributes)
{
bool hasGeneId = attributes.TryGetValue("gene_id", out string geneId);
bool hasTranscriptId = attributes.TryGetValue("transcript_id", out string transcriptId);
bool hasExonId = attributes.TryGetValue("exon_id", out string exonId);
bool hasProteinId = attributes.TryGetValue("protein_id", out string proteinId);
bool hasSource = feature.SubItems.TryGetValue("source", out List <string> sourceish); // false if empty ("." in GFF format)
bool hasStrand = feature.SubItems.TryGetValue("strand", out List <string> strandish); // false if empty ("." in GFF format)
bool hasFrame = feature.SubItems.TryGetValue("frame", out List <string> framey); // false if empty ("." in GFF format)
string source = hasSource ? sourceish[0] : "";
if (!hasStrand)
{
return;
} // strand is a required to do anything in this program
string strand = strandish[0];
int frame = 0;
if (hasFrame)
{
int.TryParse(framey[0], out frame);
}
if (hasGeneId && (currentGene == null || hasGeneId && geneId != currentGene.ID))
{
currentGene = new Gene(geneId, chrom, source, strand, oneBasedStart, oneBasedEnd, feature);
Genes.Add(currentGene);
GenomeForest.Add(currentGene);
}
if (hasTranscriptId && (currentTranscript == null || hasTranscriptId && transcriptId != currentTranscript.ID))
{
if (currentTranscript != null)
{
Transcript.SetRegions(currentTranscript);
currentTranscript.FrameCorrection();
}
currentTranscript = new Transcript(transcriptId, currentGene, source, strand, oneBasedStart, oneBasedEnd, null, null, feature);
currentGene.Transcripts.Add(currentTranscript);
GenomeForest.Add(currentTranscript);
}
if (hasExonId)
{
ISequence exon_dna = chrom.Sequence.GetSubSequence(oneBasedStart - 1, oneBasedEnd - oneBasedStart + 1);
Exon exon = new Exon(currentTranscript, currentTranscript.IsStrandPlus() ? exon_dna : exon_dna.GetReverseComplementedSequence(),
source, oneBasedStart, oneBasedEnd, chrom == null ? "" : chrom.ChromosomeID, strand, null, feature);
if (exon.Length() > 0)
{
currentTranscript.Exons.Add(exon);
}
}
else if (hasProteinId)
{
CDS cds = new CDS(currentTranscript, chrom.Sequence.ID, source, strand, oneBasedStart, oneBasedEnd, null, frame);
if (cds.Length() > 0)
{
currentTranscript.CodingDomainSequences.Add(cds);
currentTranscript.ProteinID = proteinId;
}
}
else // nothing to do
{
}
}
/// <summary>
/// Processes a feature from a GTF gene model file.
/// </summary>
/// <param name="feature"></param>
/// <param name="oneBasedStart"></param>
/// <param name="oneBasedEnd"></param>
/// <param name="chrom"></param>
/// <param name="attributes"></param>
public void ProcessGtfFeature(MetadataListItem <List <string> > feature, long oneBasedStart, long oneBasedEnd, Chromosome chrom, Dictionary <string, string> attributes)
{
bool hasGeneId = attributes.TryGetValue("gene_id", out string geneId);
bool hasTranscriptId = attributes.TryGetValue("transcript_id", out string transcriptId);
bool hasProteinId = attributes.TryGetValue("protein_id", out string proteinId);
bool hasExonId = attributes.TryGetValue("exon_id", out string exonId);
bool hasSource = feature.SubItems.TryGetValue("source", out List <string> sourceish);
bool hasStrand = feature.SubItems.TryGetValue("strand", out List <string> strandish);
bool hasFrame = feature.SubItems.TryGetValue("frame", out List <string> framey);
string source = hasSource ? sourceish[0] : "";
if (!hasStrand)
{
return;
} // strand is a required to do anything in this program
string strand = strandish[0];
int frame = 0;
if (hasFrame)
{
int.TryParse(framey[0], out frame);
}
// Trim prefixes from the IDs
string genePrefix = "gene:";
string transcriptPrefix = "transcript:";
if (hasGeneId && geneId.StartsWith(genePrefix))
{
string newGeneId = geneId.Substring(genePrefix.Length);
feature.FreeText.Replace(geneId, newGeneId);
geneId = newGeneId;
}
if (hasTranscriptId && transcriptId.StartsWith(transcriptPrefix))
{
string newTranscriptId = transcriptId.Substring(transcriptPrefix.Length);
feature.FreeText.Replace(transcriptId, newTranscriptId);
transcriptId = newTranscriptId;
}
if (hasProteinId && proteinId.StartsWith(transcriptPrefix))
{
proteinId = proteinId.Substring(transcriptPrefix.Length); // transcript id is used for protein id sometimes
}
// Catch the transcript features before they go by if available, i.e. if the file doesn't just have exons
if (feature.Key == "transcript" && (currentTranscript == null || hasTranscriptId && transcriptId != currentTranscript.ID))
{
if (currentGene == null || hasGeneId && geneId != currentGene.ID)
{
currentGene = new Gene(geneId, chrom, source, strand, oneBasedStart, oneBasedEnd, feature);
Genes.Add(currentGene);
GenomeForest.Add(currentGene);
}
currentTranscript = new Transcript(transcriptId, currentGene, source, strand, oneBasedStart, oneBasedEnd, null, null, feature);
currentGene.Transcripts.Add(currentTranscript);
GenomeForest.Add(currentTranscript);
}
if (feature.Key == "exon" || feature.Key == "CDS")
{
if (currentGene == null || hasGeneId && geneId != currentGene.ID)
{
currentGene = new Gene(geneId, chrom, source, strand, oneBasedStart, oneBasedEnd, feature);
Genes.Add(currentGene);
GenomeForest.Add(currentGene);
}
if (currentTranscript == null || hasTranscriptId && transcriptId != currentTranscript.ID)
{
if (currentTranscript != null)
{
Transcript.SetRegions(currentTranscript);
currentTranscript.FrameCorrection();
}
currentTranscript = new Transcript(transcriptId, currentGene, source, strand, oneBasedStart, oneBasedEnd, null, null, feature);
currentGene.Transcripts.Add(currentTranscript);
GenomeForest.Add(currentTranscript);
}
if (feature.Key == "exon")
{
ISequence exon_dna = chrom.Sequence.GetSubSequence(oneBasedStart - 1, oneBasedEnd - oneBasedStart + 1);
Exon exon = new Exon(currentTranscript, currentTranscript.IsStrandPlus() ? exon_dna : exon_dna.GetReverseComplementedSequence(),
source, oneBasedStart, oneBasedEnd, chrom.Sequence.ID, strand, null, feature);
if (exon.Length() > 0)
{
currentTranscript.Exons.Add(exon);
}
}
else if (feature.Key == "CDS")
{
CDS cds = new CDS(currentTranscript, chrom.Sequence.ID, source, strand, oneBasedStart, oneBasedEnd, null, frame);
if (hasProteinId)
{
currentTranscript.ProteinID = proteinId;
}
if (cds.Length() > 0)
{
currentTranscript.CodingDomainSequences.Add(cds);
}
}
else
{ // nothing to do
}
}
}
/// <summary>
/// Calculate the effect on an exon
/// </summary>
/// <param name="exon"></param>
/// <returns></returns>
protected virtual bool ChangeCodon(Exon exon)
{
throw new InvalidOperationException("Unimplemented method codonChangeSingle() for\n\t\tVariant type : " + Variant.GetType().Name + "\n\t\tClass : " + GetType().Name + "\n\t\tVariant : " + Variant);
}
public UTR3Prime(Exon parent, string chromID, string source, string strand, long oneBasedStart, long oneBasedEnd)
: base(parent, chromID, source, strand, oneBasedStart, oneBasedEnd)
{
}
public string ToString(bool useSeqOntology, bool useHgvs)
{
// Get data to show
string geneId = "", geneName = "", transcriptId = "", exonId = "", customId = "";
string bioType = null;
int exonRank = -1;
if (Marker != null)
{
// Gene Id, name and biotype
Gene gene = GetGene();
Transcript tr = GetTranscript();
// CDS size info
if (gene != null)
{
geneId = gene.ID;
//geneName = gene.getGeneName();
//bioType = (getBiotype() == null ? "" : getBiotype().ToString());
}
// Update trId
if (tr != null)
{
transcriptId = tr.ID;
}
// Exon rank information
Exon exon = GetExon();
//if (exon != null)
//{
// exonId = exon.ID;
// exonRank = exon.getRank();
//}
// Regulation
//if (isRegulation()) bioType = ((Regulation)marker).getRegulationType();
}
// Add seqChage's ID
//if (!variant.getId() == "") customId += variant.getId();
// Add custom markers
//if (marker != null && marker is Custom) customId += (customId == "" ? "" : ";") + marker.getId();
// CDS length
long cdsSize = GetCdsLength();
string error = String.Join(",", Error);
string warning = String.Join(",", Warning);
string errWarn = error + (error == "" ? "" : "|") + warning;
//string aaChange = "";
//if (useHgvs) aaChange = getHgvs();
//else aaChange = ((aaRef.Length + aaAlt.Length) > 0 ? aaRef + "/" + aaAlt : "");
string aaChange = ((ReferenceAA.Length + AlternateAA.Length) > 0 ? ReferenceAA + "/" + AlternateAA : "");
return(errWarn //
+ "\t" + geneId //
+ "\t" + geneName //
+ "\t" + bioType //
+ "\t" + transcriptId //
+ "\t" + exonId //
+ "\t" + (exonRank >= 0 ? exonRank.ToString() : "") //
+ "\t" + Effect(false, false, false, useSeqOntology, false) //
+ "\t" + aaChange //
+ "\t" + ((CodonsRef.Length + CodonsAlt.Length) > 0 ? CodonsRef + "/" + CodonsAlt : "") //
+ "\t" + (CodonNum >= 0 ? (CodonNum + 1).ToString() : "") //
//+ "\t" + (codonDegeneracy >= 0 ? codonDegeneracy + "" : "") //
+ "\t" + (cdsSize >= 0 ? cdsSize.ToString() : "") //
+ "\t" + (CodonsAroundOld.Length > 0 ? CodonsAroundOld + " / " + CodonsAroundNew : "") //
+ "\t" + (AroundOldAAs.Length > 0 ? AroundOldAAs + " / " + AroundNewAAs : "") //
+ "\t" + customId //
);
}
/// <summary>
/// Find a CDS that matches exactly the exon
/// </summary>
/// <param name="exon"></param>
/// <returns></returns>
public CDS FindCds(Exon exon)
{
return(CodingDomainSequences.FirstOrDefault(c => exon.Includes(c)));
}
/// <summary>
/// Analyze deletions in this transcript.
/// </summary>
/// <param name="exon"></param>
/// <returns></returns>
protected override bool ChangeCodon(Exon exon)
{
// Is there any net effect?
if (NetCodingSequenceChange == "")
{
return(false);
}
EffectType effType;
if (Variant.Includes(exon))
{
/**
* An exon has been entirely removed
*/
CodonsReference = "";
CodonsAlternate = "";
CodonStartNumber = -1;
CodonStartIndex = -1;
effType = EffectType.EXON_DELETED;
}
else if (NetCodingSequenceChange.Length % CODON_SIZE != 0)
{
/**
* Length not multiple of CODON_SIZE => FRAME_SHIFT
* E.g. :
* Original: AAA CCC GGG AAA CCC GGG AAA CCC GGG
* Delete 'AA' pos 0: ACC CGG GAA ACC CGG GAA ACC CGG G
* Delete 'AA' pos 1: ACC CGG GAA ACC CGG GAA ACC CGG G
* Delete 'AC' pos 2: AAC CGG GAA ACC CGG GAA ACC CGG G
*/
CodonsReference = CodonsRef();
CodonsAlternate = "";
effType = EffectType.FRAME_SHIFT;
}
else if (CodonStartIndex == 0)
{
/**
* Length multiple of CODON_SIZE and insertion happens at codon boundary => CODON_DELETION
* E.g. :
* Original: AAA CCC GGG AAA CCC GGG AAA CCC GGG
* Delete 'AAA' pos 0: CCC GGG AAA CCC GGG AAA CCC GGG
*/
CodonsReference = CodonsRef();
CodonsAlternate = "";
effType = EffectType.CODON_DELETION;
}
else
{
/**
* Length multiple of CODON_SIZE and insertion does not happen at codon boundary => CODON_CHANGE_PLUS_CODON_DELETION
* E.g. :
* Original: AAA CCC GGG AAA CCC GGG AAA CCC GGG
* Delete 'AAC' pos 1: ACC GGG AAA CCC GGG AAA CCC GGG
* Delete 'ACC' pos 2: AAC GGG AAA CCC GGG AAA CCC GGG
*/
CodonsReference = CodonsRef();
CodonsAlternate = CodonsAlt();
if (CodonsAlternate == "" || CodonsReference.StartsWith(CodonsAlternate))
{
/**
* Note: It might happen that the last codon of the exon was deleted.
* In this case there is no 'CODON_CHANGE'
* E.g.
* Original: AAA CCC GGG AAA CCC GGG AAA CCC GGG
* Delete 'GGG' pos 24: ACC CCC GGG AAA CCC GGG AAA CCC
*
* Note2: It may also be the case that the deleted bases are equal to the following ones.
* E.g.
* Original: ACG TCG TCC GGG AAA CCC GGG AAA CCC GGG
* Delete 'CGT' pos 1: ACG TCC GGG AAA CCC GGG AAA CCC GGG
*/
effType = EffectType.CODON_DELETION;
}
else
{
effType = EffectType.CODON_CHANGE_PLUS_CODON_DELETION;
}
}
Effect(exon, effType, false);
return(true);
}
public UTR3Prime(Exon parent, string chromID, string source, string strand, long oneBasedStart, long oneBasedEnd, HashSet <Variant> variants)
: base(parent, chromID, source, strand, oneBasedStart, oneBasedEnd, variants)
{
}
/// <summary>
/// Copy an exon
/// </summary>
/// <param name="x"></param>
public Exon(Exon x)
: this(x.Parent as Transcript, x.Sequence, x.Source, x.OneBasedStart, x.OneBasedEnd, x.ChromosomeID, x.Strand, x.FeatureMetadata)
{
}