+/*
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
+ *
+ * This file is part of Jalview.
+ *
+ * Jalview is free software: you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, either version 3
+ * of the License, or (at your option) any later version.
+ *
+ * Jalview is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
+ * PURPOSE. See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
package jalview.ext.ensembl;
import jalview.datamodel.SequenceFeature;
-import jalview.io.gff.SequenceOntology;
+import jalview.datamodel.SequenceI;
+import jalview.io.gff.SequenceOntologyFactory;
+import jalview.io.gff.SequenceOntologyI;
+import java.util.ArrayList;
+import java.util.List;
+
+/**
+ * A client for direct fetching of CDS sequences from Ensembl (i.e. that part of
+ * the genomic sequence that is translated to protein)
+ *
+ * TODO: not currently used as CDS sequences are computed from CDS features on
+ * transcripts - delete this class?
+ *
+ * @author gmcarstairs
+ *
+ */
public class EnsemblCds extends EnsemblSeqProxy
{
/*
* fetch cds features on genomic sequence (to identify the CDS regions)
- * and variation features (to retain)
+ * and exon and variation features (to retain for display)
*/
private static final EnsemblFeatureType[] FEATURES_TO_FETCH = {
- EnsemblFeatureType.cds, EnsemblFeatureType.variation };
+ EnsemblFeatureType.cds, EnsemblFeatureType.exon,
+ EnsemblFeatureType.variation };
/**
- * Constructor
+ * Default constructor (to use rest.ensembl.org)
*/
public EnsemblCds()
{
super();
}
+ /**
+ * Constructor given the target domain to fetch data from
+ *
+ * @param d
+ */
+ public EnsemblCds(String d)
+ {
+ super(d);
+ }
+
@Override
public String getDbName()
{
@Override
protected boolean retainFeature(SequenceFeature sf, String accessionId)
{
- if (SequenceOntology.getInstance().isA(sf.getType(),
- SequenceOntology.CDS))
+ if (SequenceOntologyFactory.getInstance().isA(sf.getType(),
+ SequenceOntologyI.CDS))
{
return false;
}
}
/**
- * Answers true if the sequence feature type is 'CDS' (or a subtype of CDS in
- * the Sequence Ontology), and the Parent of the feature is the transcript we
- * are retrieving
+ * Answers a list of sequence features (if any) whose type is 'CDS' (or a
+ * subtype of CDS in the Sequence Ontology), and whose Parent is the
+ * transcript we are retrieving
*/
@Override
- protected boolean identifiesSequence(SequenceFeature sf, String accId)
+ protected List<SequenceFeature> getIdentifyingFeatures(SequenceI seq,
+ String accId)
{
- if (SequenceOntology.getInstance().isA(sf.getType(),
- SequenceOntology.CDS))
+ List<SequenceFeature> result = new ArrayList<>();
+ List<SequenceFeature> sfs = seq.getFeatures()
+ .getFeaturesByOntology(SequenceOntologyI.CDS);
+ for (SequenceFeature sf : sfs)
{
String parentFeature = (String) sf.getValue(PARENT);
- if (("transcript:" + accId).equals(parentFeature))
+ if ( accId.equals(parentFeature))
{
- return true;
+ result.add(sf);
}
}
- return false;
+ return result;
+ }
+
+ /**
+ * Overrides this method to trivially return a range which is the whole of the
+ * nucleotide sequence. This is both faster than scanning for CDS features,
+ * and also means we don't need to keep CDS features on CDS sequence (where
+ * they are redundant information).
+ */
+ protected List<int[]> getCdsRanges(SequenceI dnaSeq)
+ {
+ int len = dnaSeq.getLength();
+ List<int[]> ranges = new ArrayList<>();
+ ranges.add(new int[] { 1, len });
+ return ranges;
}
}