/**
* Handle UTR joins
*
* @param feature
* @param key
* @param qualifiers
* @return
*/
private Location joinUtrs(Feature feature, Key key, QualifierVector qualifiers) {
Location location = feature.getLocation();
if (key.getKeyString().equals("5'UTR") || key.getKeyString().equals("3'UTR")) {
ChadoCanonicalGene gene = ((GFFStreamFeature) feature).getChadoGene();
String utrName = GeneUtils.getUniqueName(feature);
String transcriptName = gene.getTranscriptFromName(utrName);
List<Feature> utrs;
if (key.getKeyString().equals("5'UTR")) utrs = gene.get5UtrOfTranscript(transcriptName);
else utrs = gene.get3UtrOfTranscript(transcriptName);
if (utrs.size() > 1) {
int start = Integer.MAX_VALUE;
RangeVector ranges = new RangeVector();
for (int i = 0; i < utrs.size(); i++) {
Feature utr = utrs.get(i);
Range range = utr.getLocation().getTotalRange();
if (start > range.getStart()) start = range.getStart();
ranges.add(range);
}
if (start != feature.getLocation().getTotalRange().getStart()) return null;
location = new Location(ranges, feature.getLocation().isComplement());
}
int ntranscripts = gene.getTranscripts().size();
if (ntranscripts == 1) transcriptName = gene.getGeneUniqueName();
qualifiers.setQualifier(new Qualifier("locus_tag", transcriptName));
qualifiers.removeQualifierByName("ID");
}
return location;
}
/**
* Change the stop_codon_redefined_as_selenocysteine SO qualifier to the transl_except EMBL
* qualifier.
*
* @param qualifiers
* @param feature
*/
private void handleSelenocysteine(QualifierVector qualifiers, Feature feature) {
if (!feature.getKey().getKeyString().equals(DatabaseDocument.EXONMODEL)) return;
qualifiers.removeQualifierByName("stop_codon_redefined_as_selenocysteine");
uk.ac.sanger.artemis.Feature f = ((uk.ac.sanger.artemis.Feature) feature.getUserData());
int translatedBasePosion = 0;
String aa = f.getTranslation().toString();
for (int i = 0; i < aa.length(); i++) {
if (AminoAcidSequence.isStopCodon(aa.charAt(i))) {
translatedBasePosion = i * 3;
break;
}
}
FeatureSegmentVector segments = f.getSegments();
int nbases = 0;
int sequenceloc = 0;
for (int i = 0; i < segments.size(); i++) {
int seglen = segments.elementAt(i).getBases().length();
if (nbases + seglen > translatedBasePosion) {
Bases bases = f.getStrand().getBases();
sequenceloc =
segments.elementAt(i).getStart().getPosition() + (translatedBasePosion - nbases);
if (!f.isForwardFeature()) sequenceloc = bases.getComplementPosition(sequenceloc);
}
nbases += seglen;
}
String pos = "";
if (f.isForwardFeature()) pos = sequenceloc + ".." + (sequenceloc + 2);
else pos = "complement(" + (sequenceloc - 2) + ".." + sequenceloc + ")";
qualifiers.add(new Qualifier("transl_except", "(pos:" + pos + ",aa:Sec)"));
}
/**
* If the given feature can be added directly to this Entry, then return it, otherwise create and
* return a new feature of the appropriate type.
*
* @param copy if true then always new a new copy of the Feature.
*/
protected Object makeNativeFeature(final Feature feature, final boolean copy) {
if (!copy
&& (feature instanceof EmblStreamFeature && this instanceof EmblDocumentEntry
|| feature instanceof GenbankStreamFeature && this instanceof GenbankDocumentEntry)) {
return (PublicDBStreamFeature) feature;
} else {
try {
if (feature instanceof GFFStreamFeature) return mapGffToNativeFeature(feature);
else if (this instanceof EmblDocumentEntry) return new EmblStreamFeature(feature);
else return new GenbankStreamFeature(feature);
} catch (NullPointerException npe) {
System.err.println(((uk.ac.sanger.artemis.Feature) feature.getUserData()).getIDString());
throw npe;
}
}
}
/**
* Routine to combine transcript qualifiers and for multiple transcripts create links to the other
* transcripts (other_transcript) and to use the transcript ID.
*
* @param qualifiers
* @param transcript
* @param ntranscripts
* @param chadoGene
*/
private int handleTranscripts(
QualifierVector qualifiers,
Feature transcript,
int ntranscripts,
ChadoCanonicalGene chadoGene) {
QualifierVector transcriptQualifiers = transcript.getQualifiers().copy();
combineQualifiers(qualifiers, transcriptQualifiers, false);
ntranscripts = chadoGene.getTranscripts().size();
if (ntranscripts > 1) {
addNewQualifier(qualifiers, transcriptQualifiers.getQualifierByName("ID"));
List<Feature> transcripts = chadoGene.getTranscripts();
for (int i = 0; i < ntranscripts; i++) {
Feature thisTranscript = (Feature) transcripts.get(i);
String thisTranscriptName = GeneUtils.getUniqueName(thisTranscript);
if (!thisTranscriptName.equals(GeneUtils.getUniqueName(transcript))) {
Qualifier qualifier = new Qualifier("other_transcript", thisTranscriptName);
addNewQualifier(qualifiers, qualifier);
}
}
}
return ntranscripts;
}
/**
* Map GFF features to EMBL/Genbank
*
* @param feature
* @return
*/
private Object mapGffToNativeFeature(final Feature feature) {
if (DATABASE_MAP_KEYS == null) initDatabaseMappings();
Key key = feature.getKey();
QualifierVector qualifiers = feature.getQualifiers().copy();
// ignore if obsolete
if (IGNORE_OBSOLETE_FEATURES) {
Qualifier isObsoleteQualifier = qualifiers.getQualifierByName("isObsolete");
if (isObsoleteQualifier != null) {
String value = (String) isObsoleteQualifier.getValues().get(0);
if (Boolean.parseBoolean(value)) return null;
}
}
key = map(key, qualifiers);
if (getEntryInformation().isValidQualifier((String) DATABASE_QUALIFIERS_TO_REMOVE[0])) {
try {
if (this instanceof EmblDocumentEntry)
return new EmblStreamFeature(key, feature.getLocation(), qualifiers);
else return new GenbankStreamFeature(key, feature.getLocation(), qualifiers);
} catch (InvalidRelationException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
Location location = joinUtrs(feature, key, qualifiers);
if (location == null) return null;
// flatten gene model - combining qualifiers
if (key.getKeyString().equals(DatabaseDocument.EXONMODEL)) {
ChadoCanonicalGene chadoGene = ((GFFStreamFeature) feature).getChadoGene();
final String name = GeneUtils.getUniqueName(feature);
final String transcriptName = chadoGene.getTranscriptFromName(name);
StringVector sv = new StringVector();
sv.add(transcriptName);
final Feature transcript = chadoGene.containsTranscript(sv);
if (transcript != null && GeneUtils.isNonCodingTranscripts(transcript.getKey())) return null;
qualifiers.removeQualifierByName("ID");
int ntranscripts = 0;
// add transcript & protein qualifiers to CDS
try {
final Feature protein = chadoGene.getProteinOfTranscript(transcriptName);
if (protein != null) combineQualifiers(qualifiers, protein.getQualifiers().copy(), false);
if (transcript != null)
ntranscripts = handleTranscripts(qualifiers, transcript, ntranscripts, chadoGene);
} catch (NullPointerException npe) {
}
// add gene qualifiers to CDS
QualifierVector geneQualifiers = chadoGene.getGene().getQualifiers().copy();
// multiple transcripts
if (ntranscripts > 1 && geneQualifiers.getQualifierByName("ID") != null) {
Qualifier newIDQualifier =
new Qualifier(
"shared_id", (String) geneQualifiers.getQualifierByName("ID").getValues().get(0));
addNewQualifier(qualifiers, newIDQualifier);
geneQualifiers.removeQualifierByName("ID");
}
combineQualifiers(qualifiers, geneQualifiers, true);
} else if (GeneUtils.isNonCodingTranscripts(key)) {
// use gene id for non-coding transcripts
ChadoCanonicalGene chadoGene = ((GFFStreamFeature) feature).getChadoGene();
if (chadoGene != null) {
qualifiers.removeQualifierByName("ID");
QualifierVector geneQualifiers = chadoGene.getGene().getQualifiers().copy();
combineQualifiers(qualifiers, geneQualifiers, true);
}
}
try {
for (int i = 0; i < DATABASE_QUALIFIERS_TO_MAP.length; i++) {
if (!getEntryInformation().isValidQualifier(DATABASE_QUALIFIERS_TO_MAP[i][0])) {
changeQualifierName(
qualifiers, DATABASE_QUALIFIERS_TO_MAP[i][0], DATABASE_QUALIFIERS_TO_MAP[i][1]);
}
}
if (qualifiers.getQualifierByName("stop_codon_redefined_as_selenocysteine") != null) {
handleSelenocysteine(qualifiers, feature);
}
for (int i = 0; i < DATABASE_QUALIFIERS_TO_REMOVE.length; i++) {
if (!getEntryInformation().isValidQualifier((String) DATABASE_QUALIFIERS_TO_REMOVE[i]))
qualifiers.removeQualifierByName((String) DATABASE_QUALIFIERS_TO_REMOVE[i]);
}
if (key.getKeyString().equals("polypeptide")) return null;
else if (key.getKeyString().equals("gene")) return null;
else if (key.getKeyString().equals("centromere")) return null;
else if (key.getKeyString().equals("transcript") || key.getKeyString().equals("mRNA"))
return null;
if (this instanceof EmblDocumentEntry)
return new EmblStreamFeature(key, location, qualifiers);
else return new GenbankStreamFeature(key, location, qualifiers);
} catch (InvalidRelationException e) {
e.printStackTrace();
if (feature instanceof DatabaseStreamFeature) return new EmblStreamFeature();
else return new GenbankStreamFeature();
}
}