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 * Constructor given the target domain to fetch data from
64 public EnsemblLookup(String d)
70 public String getDbName()
76 public AlignmentI getSequenceRecords(String queries) throws Exception
82 protected URL getUrl(List<String> ids) throws MalformedURLException
84 String identifier = ids.get(0);
85 return getUrl(identifier, null);
89 * Gets the url for lookup of the given identifier, optionally with objectType
90 * also specified in the request
96 protected URL getUrl(String identifier, String objectType)
98 String url = getDomain() + "/lookup/id/" + identifier
100 if (objectType != null)
102 url += "&" + OBJECT_TYPE + "=" + objectType;
108 } catch (MalformedURLException e)
115 protected boolean useGetRequest()
121 protected String getRequestMimeType(boolean multipleIds)
123 return "application/json";
127 protected String getResponseMimeType()
129 return "application/json";
133 * Returns the gene id related to the given identifier (which may be for a
134 * gene, transcript or protein)
139 public String getGeneId(String identifier)
141 return getGeneId(identifier, null);
145 * Returns the gene id related to the given identifier (which may be for a
146 * gene, transcript or protein)
152 public String getGeneId(String identifier, String objectType)
154 List<String> ids = Arrays.asList(new String[] { identifier });
156 BufferedReader br = null;
159 URL url = getUrl(identifier, objectType);
162 br = getHttpResponse(url, ids);
164 return br == null ? null : parseResponse(br);
165 } catch (IOException e)
176 } catch (IOException e)
185 * Parses the JSON response and returns the gene identifier, or null if not
186 * found. If the returned object_type is Gene, returns the id, if Transcript
187 * returns the Parent. If it is Translation (peptide identifier), then the
188 * Parent is the transcript identifier, so we redo the search with this value.
192 * @throws IOException
194 protected String parseResponse(BufferedReader br) throws IOException
196 String geneId = null;
197 JSONParser jp = new JSONParser();
200 JSONObject val = (JSONObject) jp.parse(br);
201 String type = val.get(OBJECT_TYPE).toString();
202 if (OBJECT_TYPE_GENE.equalsIgnoreCase(type))
204 // got the gene - just returns its id
205 geneId = val.get(JSON_ID).toString();
207 else if (OBJECT_TYPE_TRANSCRIPT.equalsIgnoreCase(type))
209 // got the transcript - return its (Gene) Parent
210 geneId = val.get(PARENT).toString();
212 else if (OBJECT_TYPE_TRANSLATION.equalsIgnoreCase(type))
214 // got the protein - get its Parent, restricted to type Transcript
215 String transcriptId = val.get(PARENT).toString();
216 geneId = getGeneId(transcriptId, OBJECT_TYPE_TRANSCRIPT);
218 } catch (ParseException e)
226 * Calls the Ensembl lookup REST endpoint and retrieves the 'species' for the
227 * given identifier, or null if not found
232 public String getSpecies(String identifier)
234 String species = null;
235 JSONObject json = getResult(identifier, null);
238 Object o = json.get(SPECIES);
241 species = o.toString();
248 * Calls the /lookup/id rest service and returns the response as a JSONObject,
249 * or null if any error
256 protected JSONObject getResult(String identifier, String objectType)
258 List<String> ids = Arrays.asList(new String[] { identifier });
260 BufferedReader br = null;
263 URL url = getUrl(identifier, objectType);
267 br = getHttpResponse(url, ids);
269 return br == null ? null : (JSONObject) (new JSONParser().parse(br));
270 } catch (IOException | ParseException e)
272 System.err.println("Error parsing " + identifier + " lookup response "
282 } catch (IOException e)
291 * Calls the /lookup/id rest service for the given id, and if successful,
292 * parses and returns the gene's chromosomal coordinates
297 public GeneLociI getGeneLoci(String geneId)
299 return parseGeneLoci(getResult(geneId, OBJECT_TYPE_GENE));
303 * Parses the /lookup/id response for species, asssembly_name,
304 * seq_region_name, start, end and returns an object that wraps them, or null
310 GeneLociI parseGeneLoci(JSONObject json)
319 final String species = json.get("species").toString();
320 final String assembly = json.get("assembly_name").toString();
321 final String chromosome = json.get("seq_region_name").toString();
322 String strand = json.get("strand").toString();
323 int start = Integer.parseInt(json.get("start").toString());
324 int end = Integer.parseInt(json.get("end").toString());
325 int fromEnd = end - start + 1;
326 boolean reverseStrand = "-1".equals(strand);
327 int toStart = reverseStrand ? end : start;
328 int toEnd = reverseStrand ? start : end;
329 List<int[]> fromRange = Collections.singletonList(new int[] { 1,
331 List<int[]> toRange = Collections.singletonList(new int[] { toStart,
333 final MapList map = new MapList(fromRange, toRange, 1, 1);
334 return new GeneLociI()
338 public String getSpeciesId()
340 return species == null ? "" : species;
344 public String getAssemblyId()
350 public String getChromosomeId()
356 public MapList getMap()
361 } catch (NullPointerException | NumberFormatException e)
363 Cache.log.error("Error looking up gene loci: " + e.getMessage());