X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fext%2Fensembl%2FEnsemblCdna.java;h=e01ad17eaee377a850713e5af6e8fd47582859f1;hb=bc18effe68ba80213a6d03ca7e6175adc6be71d6;hp=467fc6dda824d93a494c4c564a316fae59e3c505;hpb=e24933a537e0f640c75d4685c468615872bc77fc;p=jalview.git diff --git a/src/jalview/ext/ensembl/EnsemblCdna.java b/src/jalview/ext/ensembl/EnsemblCdna.java index 467fc6d..e01ad17 100644 --- a/src/jalview/ext/ensembl/EnsemblCdna.java +++ b/src/jalview/ext/ensembl/EnsemblCdna.java @@ -1,13 +1,42 @@ +/* + * 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.SequenceOntologyFactory; +import jalview.datamodel.SequenceI; import jalview.io.gff.SequenceOntologyI; +import java.util.ArrayList; import java.util.List; import com.stevesoft.pat.Regex; +/** + * A client to fetch CDNA sequence from Ensembl (i.e. that part of the genomic + * sequence that is transcribed to RNA, but not necessarily translated to + * protein) + * + * @author gmcarstairs + * + */ public class EnsemblCdna extends EnsemblSeqProxy { /* @@ -17,7 +46,7 @@ public class EnsemblCdna extends EnsemblSeqProxy */ private static final Regex ACCESSION_REGEX = new Regex( "(ENS([A-Z]{3}|)[TG][0-9]{11}$)" + "|" + "(CCDS[0-9.]{3,}$)"); - + /* * fetch exon features on genomic sequence (to identify the cdna regions) * and cds and variation features (to retain) @@ -26,11 +55,24 @@ public class EnsemblCdna extends EnsemblSeqProxy EnsemblFeatureType.exon, EnsemblFeatureType.cds, EnsemblFeatureType.variation }; + /** + * Default constructor (to use rest.ensembl.org) + */ public EnsemblCdna() { super(); } + /** + * Constructor given the target domain to fetch data from + * + * @param d + */ + public EnsemblCdna(String d) + { + super(d); + } + @Override public String getDbName() { @@ -70,31 +112,37 @@ public class EnsemblCdna extends EnsemblSeqProxy } /** - * Answers true if the sequence feature type is 'exon' (or a subtype of exon - * 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 'exon' (or a + * subtype of exon 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 (SequenceOntologyFactory.getInstance().isA(sf.getType(), - SequenceOntologyI.EXON)) + List result = new ArrayList<>(); + List sfs = seq.getFeatures() + .getFeaturesByOntology(SequenceOntologyI.EXON); + 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; } + /** + * Parameter object_type=Transcaript added to ensure cdna and not peptide is + * returned (JAL-2529) + */ @Override - protected List getCrossReferenceDatabases() + protected String getObjectType() { - return super.getCrossReferenceDatabases(); - // 30/01/16 also found Vega_transcript, OTTT, ENS_LRG_transcript, UCSC, - // HGNC_trans_name, RefSeq_mRNA, RefSeq_mRNA_predicted + return OBJECT_TYPE_TRANSCRIPT; } }