* Data model for one entry returned from an EMBL query, as marshalled by a
* Castor binding file
*
- * For example:
- * http://www.ebi.ac.uk/ena/data/view/J03321&display=xml
+ * For example: http://www.ebi.ac.uk/ena/data/view/J03321&display=xml
*
* @see embl_mapping.xml
*/
retrievedref.setMap(new Mapping(null, new int[] { 1, dna.getLength() },
new int[] { 1, dna.getLength() }, 1, 1));
-
/*
* transform EMBL Database refs to canonical form
*/
if (qname.equals("translation"))
{
// remove all spaces (precompiled String.replaceAll(" ", ""))
- translation = SPACE_PATTERN.matcher(q.getValues()[0]).replaceAll("");
+ translation = SPACE_PATTERN.matcher(q.getValues()[0]).replaceAll(
+ "");
}
else if (qname.equals("protein_id"))
{
/*
* add cds features to dna sequence
*/
- for (int xint = 0; exons != null && xint < exons.length; xint += 2)
+ String cds = feature.getName(); // "CDS"
+ for (int xint = 0; exons != null && xint < exons.length - 1; xint += 2)
{
- SequenceFeature sf = makeCdsFeature(exons, xint, proteinName,
- proteinId, vals, codonStart);
- sf.setType(feature.getName()); // "CDS"
+ int exonStart = exons[xint];
+ int exonEnd = exons[xint + 1];
+ int begin = Math.min(exonStart, exonEnd);
+ int end = Math.max(exonStart, exonEnd);
+ int exonNumber = xint / 2 + 1;
+ String desc = String.format("Exon %d for protein '%s' EMBLCDS:%s",
+ exonNumber, proteinName, proteinId);
+
+ SequenceFeature sf = makeCdsFeature(cds, desc, begin, end,
+ sourceDb, vals);
+
sf.setEnaLocation(feature.getLocation());
- sf.setFeatureGroup(sourceDb);
+ boolean forwardStrand = exonStart <= exonEnd;
+ sf.setStrand(forwardStrand ? "+" : "-");
+ sf.setPhase(String.valueOf(codonStart - 1));
+ sf.setValue(FeatureProperties.EXONPOS, exonNumber);
+ sf.setValue(FeatureProperties.EXONPRODUCT, proteinName);
+
dna.addSequenceFeature(sf);
}
}
*/
String source = DBRefUtils.getCanonicalName(ref.getSource());
ref.setSource(source);
- DBRefEntry proteinDbRef = new DBRefEntry(ref.getSource(), ref.getVersion(), ref
- .getAccessionId());
+ DBRefEntry proteinDbRef = new DBRefEntry(ref.getSource(),
+ ref.getVersion(), ref.getAccessionId());
if (source.equals(DBRefSource.UNIPROT))
{
String proteinSeqName = DBRefSource.UNIPROT + "|"
+ ref.getAccessionId();
- if (dnaToProteinMapping != null && dnaToProteinMapping.getTo() != null)
+ if (dnaToProteinMapping != null
+ && dnaToProteinMapping.getTo() != null)
{
if (mappingUsed)
{
/**
* Helper method to construct a SequenceFeature for one cds range
*
- * @param exons
- * array of cds [start, end, ...] positions
- * @param exonStartIndex
- * offset into the exons array
- * @param proteinName
- * @param proteinAccessionId
+ * @param type
+ * feature type ("CDS")
+ * @param desc
+ * description
+ * @param begin
+ * start position
+ * @param end
+ * end position
+ * @param group
+ * feature group
* @param vals
* map of 'miscellaneous values' for feature
- * @param codonStart
- * codon start position for CDS (1/2/3, normally 1)
* @return
*/
- protected SequenceFeature makeCdsFeature(int[] exons, int exonStartIndex,
- String proteinName, String proteinAccessionId,
- Map<String, String> vals, int codonStart)
- {
- int exonNumber = exonStartIndex / 2 + 1;
- SequenceFeature sf = new SequenceFeature();
- sf.setBegin(Math.min(exons[exonStartIndex], exons[exonStartIndex + 1]));
- sf.setEnd(Math.max(exons[exonStartIndex], exons[exonStartIndex + 1]));
- sf.setDescription(String.format("Exon %d for protein '%s' EMBLCDS:%s",
- exonNumber, proteinName, proteinAccessionId));
- sf.setPhase(String.valueOf(codonStart - 1));
- sf.setStrand(exons[exonStartIndex] <= exons[exonStartIndex + 1] ? "+"
- : "-");
- sf.setValue(FeatureProperties.EXONPOS, exonNumber);
- sf.setValue(FeatureProperties.EXONPRODUCT, proteinName);
+ protected SequenceFeature makeCdsFeature(String type, String desc,
+ int begin, int end, String group, Map<String, String> vals)
+ {
+ SequenceFeature sf = new SequenceFeature(type, desc, begin, end, group);
+
if (!vals.isEmpty())
{
StringBuilder sb = new StringBuilder();