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_BASEURL = "ENSEMBL_BASEURL";
39 protected static final String ENSEMBL_GENOMES_BASEURL = "ENSEMBL_GENOMES_BASEURL";
41 // domain properties default values:
42 protected static final String DEFAULT_ENSEMBL_BASEURL = "http://rest.ensembl.org";
44 protected static final String DEFAULT_ENSEMBL_GENOMES_BASEURL = "http://rest.ensemblgenomes.org";
47 * accepts ENSG/T/E/P with 11 digits
48 * or ENSMUSP or similar for other species
49 * or CCDSnnnnn.nn with at least 3 digits
51 private static final Regex ACCESSION_REGEX = new Regex(
52 "(ENS([A-Z]{3}|)[GTEP]{1}[0-9]{11}$)" + "|"
53 + "(CCDS[0-9.]{3,}$)");
55 protected final String ensemblGenomesDomain;
57 protected final String ensemblDomain;
60 * possible values for the 'feature' parameter of the /overlap REST service
61 * @see http://rest.ensembl.org/documentation/info/overlap_id
63 protected enum EnsemblFeatureType
65 gene, transcript, cds, exon, repeat, simple, misc, variation,
66 somatic_variation, structural_variation, somatic_structural_variation,
67 constrained, regulatory
70 private String domain;
75 public EnsemblSequenceFetcher()
78 * the default domain names may be overridden in .jalview_properties;
79 * this allows an easy change from http to https in future if needed
81 ensemblDomain = Cache.getDefault(ENSEMBL_BASEURL,
82 DEFAULT_ENSEMBL_BASEURL);
83 ensemblGenomesDomain = Cache.getDefault(ENSEMBL_GENOMES_BASEURL,
84 DEFAULT_ENSEMBL_GENOMES_BASEURL);
85 domain = ensemblDomain;
89 public String getDbSource()
91 // NB ensure Uniprot xrefs are canonicalised from "Ensembl" to "ENSEMBL"
92 if (ensemblGenomesDomain.equals(getDomain()))
94 return DBRefSource.ENSEMBLGENOMES;
96 return DBRefSource.ENSEMBL;
100 public String getAccessionSeparator()
106 * Ensembl accession are ENST + 11 digits for human transcript, ENSG for human
107 * gene. Other species insert 3 letters e.g. ENSMUST..., ENSMUSG...
109 * @see http://www.ensembl.org/Help/View?id=151
112 public Regex getAccessionValidator()
114 return ACCESSION_REGEX;
118 public boolean isValidReference(String accession)
120 return getAccessionValidator().search(accession);
130 * Default test query is a transcript
133 public String getTestQuery()
135 // has CDS on reverse strand:
136 return "ENST00000288602";
137 // ENST00000461457 // forward strand
141 public boolean isDnaCoding()
147 * Returns the domain name to query e.g. http://rest.ensembl.org or
148 * http://rest.ensemblgenomes.org
152 protected String getDomain()
157 protected void setDomain(String d)