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.analysis.AlignmentUtils;
24 import jalview.bin.Cache;
25 import jalview.datamodel.DBRefSource;
26 import jalview.ws.seqfetcher.DbSourceProxyImpl;
28 import com.stevesoft.pat.Regex;
31 * A base class for Ensembl sequence fetchers
35 abstract class EnsemblSequenceFetcher extends DbSourceProxyImpl
37 // domain property lookup key
38 protected static final String ENSEMBL_BASEURL = "ENSEMBL_BASEURL";
40 // domain property default value
41 protected static final String DEFAULT_ENSEMBL_BASEURL = "https://rest.ensembl.org";
44 * accepts ENSG/T/E/P with 11 digits
45 * or ENSMUSP or similar for other species
46 * or CCDSnnnnn.nn with at least 3 digits
48 private static final Regex ACCESSION_REGEX = new Regex(
49 "(ENS([A-Z]{3}|)[GTEP]{1}[0-9]{11}$)" + "|"
50 + "(CCDS[0-9.]{3,}$)");
52 protected static final String OBJECT_TYPE_TRANSLATION = "Translation";
54 protected static final String OBJECT_TYPE_TRANSCRIPT = "Transcript";
56 protected static final String OBJECT_TYPE_GENE = "Gene";
58 protected static final String PARENT = "Parent";
60 protected static final String JSON_ID = AlignmentUtils.VARIANT_ID; // "id";
62 protected static final String OBJECT_TYPE = "object_type";
65 * possible values for the 'feature' parameter of the /overlap REST service
66 * @see http://rest.ensembl.org/documentation/info/overlap_id
68 protected enum EnsemblFeatureType
70 gene, transcript, cds, exon, repeat, simple, misc, variation,
71 somatic_variation, structural_variation, somatic_structural_variation,
72 constrained, regulatory
75 private String domain;
80 public EnsemblSequenceFetcher()
83 * the default domain names may be overridden in .jalview_properties;
84 * this allows an easy change from http to https in future if needed
86 domain = Cache.getDefault(ENSEMBL_BASEURL,
87 DEFAULT_ENSEMBL_BASEURL).trim();
91 public String getDbSource()
93 // NB ensure Uniprot xrefs are canonicalised from "Ensembl" to "ENSEMBL"
94 return DBRefSource.ENSEMBL;
98 public String getAccessionSeparator()
104 * Ensembl accession are ENST + 11 digits for human transcript, ENSG for human
105 * gene. Other species insert 3 letters e.g. ENSMUST..., ENSMUSG...
107 * @see http://www.ensembl.org/Help/View?id=151
110 public Regex getAccessionValidator()
112 return ACCESSION_REGEX;
116 public boolean isValidReference(String accession)
118 return getAccessionValidator().search(accession);
128 * Default test query is a transcript
131 public String getTestQuery()
133 // has CDS on reverse strand:
134 return "ENST00000288602";
135 // ENST00000461457 // forward strand
139 public boolean isDnaCoding()
145 * Returns the domain name to query e.g. http://rest.ensembl.org
149 protected String getDomain()
154 protected void setDomain(String d)
156 domain = d == null ? null : d.trim();