2 * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
3 * Copyright (C) $$Year-Rel$$ The Jalview Authors
5 * This file is part of Jalview.
7 * Jalview is free software: you can redistribute it and/or
8 * modify it under the terms of the GNU General Public License
9 * as published by the Free Software Foundation, either version 3
10 * of the License, or (at your option) any later version.
12 * Jalview is distributed in the hope that it will be useful, but
13 * WITHOUT ANY WARRANTY; without even the implied warranty
14 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
15 * PURPOSE. See the GNU General Public License for more details.
17 * You should have received a copy of the GNU General Public License
18 * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
19 * The Jalview Authors are detailed in the 'AUTHORS' file.
21 package jalview.ext.ensembl;
23 import jalview.datamodel.SequenceFeature;
24 import jalview.io.gff.SequenceOntologyFactory;
25 import jalview.io.gff.SequenceOntologyI;
27 import java.util.HashMap;
30 import com.stevesoft.pat.Regex;
33 * A client to fetch CDNA sequence from Ensembl (i.e. that part of the genomic
34 * sequence that is transcribed to RNA, but not necessarily translated to
40 public class EnsemblCdna extends EnsemblSeqProxy
43 * accepts ENST or ENSTG with 11 digits
44 * or ENSMUST or similar for other species
45 * or CCDSnnnnn.nn with at least 3 digits
47 private static final Regex ACCESSION_REGEX = new Regex(
48 "(ENS([A-Z]{3}|)[TG][0-9]{11}$)" + "|" + "(CCDS[0-9.]{3,}$)");
50 private static Map<String, String> params = new HashMap<String, String>();
54 params.put("object_type", "transcript");
58 * fetch exon features on genomic sequence (to identify the cdna regions)
59 * and cds and variation features (to retain)
61 private static final EnsemblFeatureType[] FEATURES_TO_FETCH = {
62 EnsemblFeatureType.exon, EnsemblFeatureType.cds,
63 EnsemblFeatureType.variation };
66 * Default constructor (to use rest.ensembl.org)
74 * Constructor given the target domain to fetch data from
78 public EnsemblCdna(String d)
84 public String getDbName()
86 return "ENSEMBL (CDNA)";
90 protected EnsemblSeqType getSourceEnsemblType()
92 return EnsemblSeqType.CDNA;
96 public Regex getAccessionValidator()
98 return ACCESSION_REGEX;
102 protected EnsemblFeatureType[] getFeaturesToFetch()
104 return FEATURES_TO_FETCH;
108 * Answers true unless the feature type is 'transcript' (or a sub-type in the
109 * Sequence Ontology).
112 protected boolean retainFeature(SequenceFeature sf, String accessionId)
114 if (isTranscript(sf.getType()))
118 return featureMayBelong(sf, accessionId);
122 * Answers true if the sequence feature type is 'exon' (or a subtype of exon
123 * in the Sequence Ontology), and the Parent of the feature is the transcript
127 protected boolean identifiesSequence(SequenceFeature sf, String accId)
129 if (SequenceOntologyFactory.getInstance().isA(sf.getType(),
130 SequenceOntologyI.EXON))
132 String parentFeature = (String) sf.getValue(PARENT);
133 if (("transcript:" + accId).equals(parentFeature))
142 * Parameter object_type=cdna added to ensure cdna and not peptide is returned
146 protected Map<String, String> getAdditionalParameters()