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.BufferedReader;
29 import java.io.IOException;
30 import java.net.MalformedURLException;
32 import java.util.Arrays;
33 import java.util.Collections;
34 import java.util.List;
36 import org.json.simple.JSONObject;
37 import org.json.simple.parser.JSONParser;
38 import org.json.simple.parser.ParseException;
41 * A client for the Ensembl /lookup REST endpoint, used to find the gene
42 * identifier given a gene, transcript or protein identifier, or to extract the
43 * species or chromosomal coordinates from the same service response
47 public class EnsemblLookup extends EnsemblRestClient
49 private static final String SPECIES = "species";
52 * Default constructor (to use rest.ensembl.org)
54 public EnsemblLookup()
60 public String getDbName()
66 public AlignmentI getSequenceRecords(String queries) throws Exception
72 protected URL getUrl(List<String> ids) throws MalformedURLException
74 String identifier = ids.get(0);
75 return getUrl(identifier, null);
79 * Gets the url for lookup of the given identifier, optionally with objectType
80 * also specified in the request
86 protected URL getUrl(String identifier, String objectType)
88 String url = getDomain() + "/lookup/id/" + identifier
90 if (objectType != null)
92 url += "&" + OBJECT_TYPE + "=" + objectType;
98 } catch (MalformedURLException e)
105 protected boolean useGetRequest()
111 * Returns the gene id related to the given identifier (which may be for a
112 * gene, transcript or protein), or null if none is found
117 public String getGeneId(String identifier)
119 return getGeneId(identifier, null);
123 * Returns the gene id related to the given identifier (which may be for a
124 * gene, transcript or protein), or null if none is found
130 public String getGeneId(String identifier, String objectType)
132 return parseGeneId(getResult(identifier, objectType));
136 * Parses the JSON response and returns the gene identifier, or null if not
137 * found. If the returned object_type is Gene, returns the id, if Transcript
138 * returns the Parent. If it is Translation (peptide identifier), then the
139 * Parent is the transcript identifier, so we redo the search with this value.
144 protected String parseGeneId(JSONObject val)
150 String geneId = null;
151 String type = val.get(OBJECT_TYPE).toString();
152 if (OBJECT_TYPE_GENE.equalsIgnoreCase(type))
154 // got the gene - just returns its id
155 geneId = val.get(JSON_ID).toString();
157 else if (OBJECT_TYPE_TRANSCRIPT.equalsIgnoreCase(type))
159 // got the transcript - return its (Gene) Parent
160 geneId = val.get(PARENT).toString();
162 else if (OBJECT_TYPE_TRANSLATION.equalsIgnoreCase(type))
164 // got the protein - get its Parent, restricted to type Transcript
165 String transcriptId = val.get(PARENT).toString();
166 geneId = getGeneId(transcriptId, OBJECT_TYPE_TRANSCRIPT);
173 * Calls the Ensembl lookup REST endpoint and retrieves the 'species' for the
174 * given identifier, or null if not found
179 public String getSpecies(String identifier)
181 String species = null;
182 JSONObject json = getResult(identifier, null);
185 Object o = json.get(SPECIES);
188 species = o.toString();
195 * Calls the /lookup/id rest service and returns the response as a JSONObject,
196 * or null if any error
203 protected JSONObject getResult(String identifier, String objectType)
205 List<String> ids = Arrays.asList(new String[] { identifier });
207 BufferedReader br = null;
210 URL url = getUrl(identifier, objectType);
214 br = getHttpResponse(url, ids);
216 return br == null ? null : (JSONObject) (new JSONParser().parse(br));
217 } catch (IOException | ParseException e)
219 System.err.println("Error parsing " + identifier + " lookup response "
229 } catch (IOException e)
238 * Calls the /lookup/id rest service for the given id, and if successful,
239 * parses and returns the gene's chromosomal coordinates
244 public GeneLociI getGeneLoci(String geneId)
246 return parseGeneLoci(getResult(geneId, OBJECT_TYPE_GENE));
250 * Parses the /lookup/id response for species, asssembly_name,
251 * seq_region_name, start, end and returns an object that wraps them, or null
257 GeneLociI parseGeneLoci(JSONObject json)
266 final String species = json.get("species").toString();
267 final String assembly = json.get("assembly_name").toString();
268 final String chromosome = json.get("seq_region_name").toString();
269 String strand = json.get("strand").toString();
270 int start = Integer.parseInt(json.get("start").toString());
271 int end = Integer.parseInt(json.get("end").toString());
272 int fromEnd = end - start + 1;
273 boolean reverseStrand = "-1".equals(strand);
274 int toStart = reverseStrand ? end : start;
275 int toEnd = reverseStrand ? start : end;
276 List<int[]> fromRange = Collections.singletonList(new int[] { 1,
278 List<int[]> toRange = Collections.singletonList(new int[] { toStart,
280 final MapList map = new MapList(fromRange, toRange, 1, 1);
281 return new GeneLociI()
285 public String getSpeciesId()
287 return species == null ? "" : species;
291 public String getAssemblyId()
297 public String getChromosomeId()
303 public MapList getMap()
308 } catch (NullPointerException | NumberFormatException e)
310 Cache.log.error("Error looking up gene loci: " + e.getMessage());