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.DBRefSource;
24 import jalview.ws.seqfetcher.DbSourceProxyImpl;
26 import com.stevesoft.pat.Regex;
29 * A base class for Ensembl sequence fetchers
33 abstract class EnsemblSequenceFetcher extends DbSourceProxyImpl
36 * accepts ENSG/T/E/P with 11 digits
37 * or ENSMUSP or similar for other species
38 * or CCDSnnnnn.nn with at least 3 digits
40 private static final Regex ACCESSION_REGEX = new Regex(
41 "(ENS([A-Z]{3}|)[GTEP]{1}[0-9]{11}$)" + "|"
42 + "(CCDS[0-9.]{3,}$)");
44 protected static final String ENSEMBL_GENOMES_REST = "http://rest.ensemblgenomes.org";
46 protected static final String ENSEMBL_REST = "http://rest.ensembl.org";
48 protected static final String OBJECT_TYPE_TRANSLATION = "Translation";
50 protected static final String OBJECT_TYPE_TRANSCRIPT = "Transcript";
52 protected static final String OBJECT_TYPE_GENE = "Gene";
54 protected static final String PARENT = "Parent";
56 protected static final String ID = "id";
58 protected static final String OBJECT_TYPE = "object_type";
61 * possible values for the 'feature' parameter of the /overlap REST service
62 * @see http://rest.ensembl.org/documentation/info/overlap_id
64 protected enum EnsemblFeatureType
66 gene, transcript, cds, exon, repeat, simple, misc, variation,
67 somatic_variation, structural_variation, somatic_structural_variation,
68 constrained, regulatory
71 private String domain = ENSEMBL_REST;
74 public String getDbSource()
76 // NB ensure Uniprot xrefs are canonicalised from "Ensembl" to "ENSEMBL"
77 if (ENSEMBL_GENOMES_REST.equals(getDomain()))
79 return DBRefSource.ENSEMBLGENOMES;
81 return DBRefSource.ENSEMBL;
85 public String getAccessionSeparator()
91 * Ensembl accession are ENST + 11 digits for human transcript, ENSG for human
92 * gene. Other species insert 3 letters e.g. ENSMUST..., ENSMUSG...
94 * @see http://www.ensembl.org/Help/View?id=151
97 public Regex getAccessionValidator()
99 return ACCESSION_REGEX;
103 public boolean isValidReference(String accession)
105 return getAccessionValidator().search(accession);
115 * Default test query is a transcript
118 public String getTestQuery()
120 // has CDS on reverse strand:
121 return "ENST00000288602";
122 // ENST00000461457 // forward strand
126 public boolean isDnaCoding()
132 * Returns the domain name to query e.g. http://rest.ensembl.org or
133 * http://rest.ensemblgenomes.org
137 protected String getDomain()
142 protected void setDomain(String d)