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.datamodel.GeneLocus;
27 import jalview.datamodel.Mapping;
28 import jalview.util.MapList;
30 import java.io.BufferedReader;
31 import java.io.IOException;
32 import java.net.MalformedURLException;
34 import java.util.Arrays;
35 import java.util.Collections;
36 import java.util.List;
38 import org.json.simple.JSONObject;
39 import org.json.simple.parser.JSONParser;
40 import org.json.simple.parser.ParseException;
43 * A client for the Ensembl /lookup REST endpoint, used to find the gene
44 * identifier given a gene, transcript or protein identifier, or to extract the
45 * species or chromosomal coordinates from the same service response
49 public class EnsemblLookup extends EnsemblRestClient
51 private static final String SPECIES = "species";
54 * Default constructor (to use rest.ensembl.org)
56 public EnsemblLookup()
62 * Constructor given the target domain to fetch data from
66 public EnsemblLookup(String d)
72 public String getDbName()
78 public AlignmentI getSequenceRecords(String queries) throws Exception
84 protected URL getUrl(List<String> ids) throws MalformedURLException
86 String identifier = ids.get(0);
87 return getUrl(identifier, null);
91 * Gets the url for lookup of the given identifier, optionally with objectType
92 * also specified in the request
98 protected URL getUrl(String identifier, String objectType)
100 String url = getDomain() + "/lookup/id/" + identifier
102 if (objectType != null)
104 url += "&" + OBJECT_TYPE + "=" + objectType;
110 } catch (MalformedURLException e)
117 protected boolean useGetRequest()
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
129 public String getGeneId(String identifier)
131 return getGeneId(identifier, null);
135 * Returns the gene id related to the given identifier (which may be for a
136 * gene, transcript or protein), or null if none is found
142 public String getGeneId(String identifier, String objectType)
144 return parseGeneId(getResult(identifier, objectType));
148 * Parses the JSON response and returns the gene identifier, or null if not
149 * found. If the returned object_type is Gene, returns the id, if Transcript
150 * returns the Parent. If it is Translation (peptide identifier), then the
151 * Parent is the transcript identifier, so we redo the search with this value.
156 protected String parseGeneId(JSONObject val)
162 String geneId = null;
163 String type = val.get(OBJECT_TYPE).toString();
164 if (OBJECT_TYPE_GENE.equalsIgnoreCase(type))
166 // got the gene - just returns its id
167 geneId = val.get(JSON_ID).toString();
169 else if (OBJECT_TYPE_TRANSCRIPT.equalsIgnoreCase(type))
171 // got the transcript - return its (Gene) Parent
172 geneId = val.get(PARENT).toString();
174 else if (OBJECT_TYPE_TRANSLATION.equalsIgnoreCase(type))
176 // got the protein - get its Parent, restricted to type Transcript
177 String transcriptId = val.get(PARENT).toString();
178 geneId = getGeneId(transcriptId, OBJECT_TYPE_TRANSCRIPT);
185 * Calls the Ensembl lookup REST endpoint and retrieves the 'species' for the
186 * given identifier, or null if not found
191 public String getSpecies(String identifier)
193 String species = null;
194 JSONObject json = getResult(identifier, null);
197 Object o = json.get(SPECIES);
200 species = o.toString();
207 * Calls the /lookup/id rest service and returns the response as a JSONObject,
208 * or null if any error
215 protected JSONObject getResult(String identifier, String objectType)
217 List<String> ids = Arrays.asList(new String[] { identifier });
219 BufferedReader br = null;
222 URL url = getUrl(identifier, objectType);
226 br = getHttpResponse(url, ids);
228 return br == null ? null : (JSONObject) (new JSONParser().parse(br));
229 } catch (IOException | ParseException e)
231 System.err.println("Error parsing " + identifier + " lookup response "
241 } catch (IOException e)
250 * Calls the /lookup/id rest service for the given id, and if successful,
251 * parses and returns the gene's chromosomal coordinates
256 public GeneLociI getGeneLoci(String geneId)
258 return parseGeneLoci(getResult(geneId, OBJECT_TYPE_GENE));
262 * Parses the /lookup/id response for species, asssembly_name,
263 * seq_region_name, start, end and returns an object that wraps them, or null
269 GeneLociI parseGeneLoci(JSONObject json)
278 final String species = json.get("species").toString();
279 final String assembly = json.get("assembly_name").toString();
280 final String chromosome = json.get("seq_region_name").toString();
281 String strand = json.get("strand").toString();
282 int start = Integer.parseInt(json.get("start").toString());
283 int end = Integer.parseInt(json.get("end").toString());
284 int fromEnd = end - start + 1;
285 boolean reverseStrand = "-1".equals(strand);
286 int toStart = reverseStrand ? end : start;
287 int toEnd = reverseStrand ? start : end;
288 List<int[]> fromRange = Collections.singletonList(new int[] { 1,
290 List<int[]> toRange = Collections.singletonList(new int[] { toStart,
292 final Mapping map = new Mapping(
293 new MapList(fromRange, toRange, 1, 1));
294 return new GeneLocus(species == null ? "" : species, assembly,
296 } catch (NullPointerException | NumberFormatException e)
298 Cache.log.error("Error looking up gene loci: " + e.getMessage());