X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fext%2Fensembl%2FEnsemblCds.java;h=f397412fb8a2857bd8b5c5b0468b7057f9b11d57;hb=57738a1f3c19b1c3a00bd3ac5108f8cd0af32f99;hp=58cf8fa572a39369af797f29b29c0f3d7bfc3a38;hpb=f9b80711054b61e8c2257488a1637e15616cb9c9;p=jalview.git diff --git a/src/jalview/ext/ensembl/EnsemblCds.java b/src/jalview/ext/ensembl/EnsemblCds.java index 58cf8fa..f397412 100644 --- a/src/jalview/ext/ensembl/EnsemblCds.java +++ b/src/jalview/ext/ensembl/EnsemblCds.java @@ -1,25 +1,71 @@ +/* + * 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 . + * 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() { @@ -47,32 +93,49 @@ public class EnsemblCds extends EnsemblSeqProxy @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; } - return super.retainFeature(sf, accessionId); + return featureMayBelong(sf, accessionId); } /** - * 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 getIdentifyingFeatures(SequenceI seq, + String accId) { - if (SequenceOntology.getInstance().isA(sf.getType(), - SequenceOntology.CDS)) + List result = new ArrayList<>(); + List 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 getCdsRanges(SequenceI dnaSeq) + { + int len = dnaSeq.getLength(); + List ranges = new ArrayList<>(); + ranges.add(new int[] { 1, len }); + return ranges; } }