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.bin.Cache;
24 import jalview.datamodel.DBRefSource;
25 import jalview.ws.seqfetcher.DbSourceProxyImpl;
27 import com.stevesoft.pat.Regex;
30 * A base class for Ensembl sequence fetchers
34 abstract class EnsemblSequenceFetcher extends DbSourceProxyImpl
36 // domain properties lookup keys:
37 protected static final String ENSEMBL_DOMAIN = "ENSEMBL_DOMAIN";
38 protected static final String ENSEMBL_GENOMES_DOMAIN = "ENSEMBL_GENOMES_DOMAIN";
40 // domain properties default values:
41 protected static final String DEFAULT_ENSEMBL_DOMAIN = "http://rest.ensembl.org";
42 protected static final String DEFAULT_ENSEMBL_GENOMES_DOMAIN = "http://rest.ensemblgenomes.org";
45 * accepts ENSG/T/E/P with 11 digits
46 * or ENSMUSP or similar for other species
47 * or CCDSnnnnn.nn with at least 3 digits
49 private static final Regex ACCESSION_REGEX = new Regex(
50 "(ENS([A-Z]{3}|)[GTEP]{1}[0-9]{11}$)" + "|"
51 + "(CCDS[0-9.]{3,}$)");
53 protected final String ensemblGenomesDomain;
55 protected final String ensemblDomain;
58 * possible values for the 'feature' parameter of the /overlap REST service
59 * @see http://rest.ensembl.org/documentation/info/overlap_id
61 protected enum EnsemblFeatureType
63 gene, transcript, cds, exon, repeat, simple, misc, variation,
64 somatic_variation, structural_variation, somatic_structural_variation,
65 constrained, regulatory
68 private String domain;
73 public EnsemblSequenceFetcher()
76 * the default domain names may be overridden in .jalview_properties;
77 * this allows an easy change from http to https in future if needed
79 ensemblDomain = Cache.getDefault(ENSEMBL_DOMAIN, DEFAULT_ENSEMBL_DOMAIN);
80 ensemblGenomesDomain = Cache.getDefault(ENSEMBL_GENOMES_DOMAIN,
81 DEFAULT_ENSEMBL_GENOMES_DOMAIN);
82 domain = ensemblDomain;
86 public String getDbSource()
88 // NB ensure Uniprot xrefs are canonicalised from "Ensembl" to "ENSEMBL"
89 if (ensemblGenomesDomain.equals(getDomain()))
91 return DBRefSource.ENSEMBLGENOMES;
93 return DBRefSource.ENSEMBL;
97 public String getAccessionSeparator()
103 * Ensembl accession are ENST + 11 digits for human transcript, ENSG for human
104 * gene. Other species insert 3 letters e.g. ENSMUST..., ENSMUSG...
106 * @see http://www.ensembl.org/Help/View?id=151
109 public Regex getAccessionValidator()
111 return ACCESSION_REGEX;
115 public boolean isValidReference(String accession)
117 return getAccessionValidator().search(accession);
127 * Default test query is a transcript
130 public String getTestQuery()
132 // has CDS on reverse strand:
133 return "ENST00000288602";
134 // ENST00000461457 // forward strand
138 public boolean isDnaCoding()
144 * Returns the domain name to query e.g. http://rest.ensembl.org or
145 * http://rest.ensemblgenomes.org
149 protected String getDomain()
154 protected void setDomain(String d)