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.datamodel.SequenceI;
25 import jalview.io.gff.SequenceOntologyI;
26 import jalview.util.Platform;
28 import java.util.ArrayList;
29 import java.util.List;
31 import com.stevesoft.pat.Regex;
34 * A client to fetch CDNA sequence from Ensembl (i.e. that part of the genomic
35 * sequence that is transcribed to RNA, but not necessarily translated to
41 public class EnsemblCdna extends EnsemblSeqProxy
44 * accepts ENST or ENSTG with 11 digits
45 * or ENSMUST or similar for other species
46 * or CCDSnnnnn.nn with at least 3 digits
48 private static final Regex ACCESSION_REGEX = Platform.newRegex(
49 "(ENS([A-Z]{3}|)[TG][0-9]{11}$)" + "|" + "(CCDS[0-9.]{3,}$)");
52 * fetch exon features on genomic sequence (to identify the cdna regions)
53 * and cds and variation features (to retain)
55 private static final EnsemblFeatureType[] FEATURES_TO_FETCH = {
56 EnsemblFeatureType.exon, EnsemblFeatureType.cds,
57 EnsemblFeatureType.variation };
60 * Default constructor (to use rest.ensembl.org)
68 * Constructor given the target domain to fetch data from
72 public EnsemblCdna(String d)
78 public String getDbName()
80 return "ENSEMBL (CDNA)";
84 protected EnsemblSeqType getSourceEnsemblType()
86 return EnsemblSeqType.CDNA;
90 public Regex getAccessionValidator()
92 return ACCESSION_REGEX;
96 protected EnsemblFeatureType[] getFeaturesToFetch()
98 return FEATURES_TO_FETCH;
102 * Answers true unless the feature type is 'transcript' (or a sub-type in the
103 * Sequence Ontology).
106 protected boolean retainFeature(SequenceFeature sf, String accessionId)
108 if (isTranscript(sf.getType()))
112 return featureMayBelong(sf, accessionId);
116 * Answers a list of sequence features (if any) whose type is 'exon' (or a
117 * subtype of exon in the Sequence Ontology), and whose Parent is the
118 * transcript we are retrieving
121 protected List<SequenceFeature> getIdentifyingFeatures(SequenceI seq,
124 List<SequenceFeature> result = new ArrayList<>();
125 List<SequenceFeature> sfs = seq.getFeatures()
126 .getFeaturesByOntology(SequenceOntologyI.EXON);
127 for (SequenceFeature sf : sfs)
129 String parentFeature = (String) sf.getValue(PARENT);
130 if (accId.equals(parentFeature))
140 * Parameter object_type=Transcaript added to ensure cdna and not peptide is
141 * returned (JAL-2529)
144 protected String getObjectType()
146 return OBJECT_TYPE_TRANSCRIPT;