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.AlignmentI;
25 import jalview.datamodel.GeneLociI;
26 import jalview.util.MapList;
28 import java.io.IOException;
29 import java.net.MalformedURLException;
31 import java.util.Arrays;
32 import java.util.Collections;
33 import java.util.List;
36 import org.json.simple.parser.ParseException;
39 * A client for the Ensembl /lookup REST endpoint, used to find the gene
40 * identifier given a gene, transcript or protein identifier, or to extract the
41 * species or chromosomal coordinates from the same service response
45 public class EnsemblLookup extends EnsemblRestClient
47 private static final String SPECIES = "species";
50 * Default constructor (to use rest.ensembl.org)
52 public EnsemblLookup()
58 * Constructor given the target domain to fetch data from
62 public EnsemblLookup(String d)
68 public String getDbName()
74 public AlignmentI getSequenceRecords(String queries) throws Exception
80 protected URL getUrl(List<String> ids) throws MalformedURLException
82 String identifier = ids.get(0);
83 return getUrl(identifier, null);
87 * Gets the url for lookup of the given identifier, optionally with objectType
88 * also specified in the request
94 protected URL getUrl(String identifier, String objectType)
96 String url = getDomain() + "/lookup/id/" + identifier
98 if (objectType != null)
100 url += "&" + OBJECT_TYPE + "=" + objectType;
106 } catch (MalformedURLException e)
113 protected boolean useGetRequest()
119 * Returns the gene id related to the given identifier (which may be for a
120 * gene, transcript or protein), or null if none is found
125 public String getGeneId(String identifier)
127 return getGeneId(identifier, null);
131 * Returns the gene id related to the given identifier (which may be for a
132 * gene, transcript or protein), or null if none is found
138 public String getGeneId(String identifier, String objectType)
140 return parseGeneId(getResult(identifier, objectType));
144 * Parses the JSON response and returns the gene identifier, or null if not
145 * found. If the returned object_type is Gene, returns the id, if Transcript
146 * returns the Parent. If it is Translation (peptide identifier), then the
147 * Parent is the transcript identifier, so we redo the search with this value.
152 protected String parseGeneId(Map<String, Object> val)
158 String geneId = null;
159 String type = val.get(OBJECT_TYPE).toString();
160 if (OBJECT_TYPE_GENE.equalsIgnoreCase(type))
162 // got the gene - just returns its id
163 geneId = val.get(JSON_ID).toString();
165 else if (OBJECT_TYPE_TRANSCRIPT.equalsIgnoreCase(type))
167 // got the transcript - return its (Gene) Parent
168 geneId = val.get(PARENT).toString();
170 else if (OBJECT_TYPE_TRANSLATION.equalsIgnoreCase(type))
172 // got the protein - get its Parent, restricted to type Transcript
173 String transcriptId = val.get(PARENT).toString();
174 geneId = getGeneId(transcriptId, OBJECT_TYPE_TRANSCRIPT);
181 * Calls the Ensembl lookup REST endpoint and retrieves the 'species' for the
182 * given identifier, or null if not found
187 public String getSpecies(String identifier)
189 String species = null;
190 Map<String, Object> json = getResult(identifier, null);
193 Object o = json.get(SPECIES);
196 species = o.toString();
203 * Calls the /lookup/id rest service and returns the response as a Map<String, Object>,
204 * or null if any error
211 @SuppressWarnings("unchecked")
212 protected Map<String, Object> getResult(String identifier, String objectType)
214 List<String> ids = Arrays.asList(new String[] { identifier });
218 return (Map<String, Object>) getJSON(getUrl(identifier, objectType), ids, -1, MODE_MAP, null);
220 catch (IOException | ParseException e)
222 System.err.println("Error parsing " + identifier + " lookup response "
229 * Calls the /lookup/id rest service for the given id, and if successful,
230 * parses and returns the gene's chromosomal coordinates
235 public GeneLociI getGeneLoci(String geneId)
237 return parseGeneLoci(getResult(geneId, OBJECT_TYPE_GENE));
241 * Parses the /lookup/id response for species, asssembly_name,
242 * seq_region_name, start, end and returns an object that wraps them, or null
248 GeneLociI parseGeneLoci(Map<String, Object> json)
257 final String species = json.get("species").toString();
258 final String assembly = json.get("assembly_name").toString();
259 final String chromosome = json.get("seq_region_name").toString();
260 String strand = json.get("strand").toString();
261 int start = Integer.parseInt(json.get("start").toString());
262 int end = Integer.parseInt(json.get("end").toString());
263 int fromEnd = end - start + 1;
264 boolean reverseStrand = "-1".equals(strand);
265 int toStart = reverseStrand ? end : start;
266 int toEnd = reverseStrand ? start : end;
267 List<int[]> fromRange = Collections.singletonList(new int[] { 1,
269 List<int[]> toRange = Collections.singletonList(new int[] { toStart,
271 final MapList map = new MapList(fromRange, toRange, 1, 1);
272 return new GeneLociI()
276 public String getSpeciesId()
278 return species == null ? "" : species;
282 public String getAssemblyId()
288 public String getChromosomeId()
294 public MapList getMap()
299 } catch (NullPointerException | NumberFormatException e)
301 Cache.log.error("Error looking up gene loci: " + e.getMessage());