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";
50 private static final String OBJECT_TYPE_TRANSLATION = "Translation";
51 private static final String PARENT = "Parent";
52 private static final String OBJECT_TYPE_TRANSCRIPT = "Transcript";
53 private static final String ID = "id";
54 private static final String OBJECT_TYPE_GENE = "Gene";
55 private static final String OBJECT_TYPE = "object_type";
58 * keep track of last identifier retrieved to break loops
60 private String lastId;
63 * Default constructor (to use rest.ensembl.org)
65 public EnsemblLookup()
71 * Constructor given the target domain to fetch data from
75 public EnsemblLookup(String d)
81 public String getDbName()
87 public AlignmentI getSequenceRecords(String queries) throws Exception
93 protected URL getUrl(List<String> ids) throws MalformedURLException
95 String identifier = ids.get(0);
96 return getUrl(identifier, null);
100 * Gets the url for lookup of the given identifier, optionally with objectType
101 * also specified in the request
107 protected URL getUrl(String identifier, String objectType)
109 String url = getDomain() + "/lookup/id/" + identifier
111 if (objectType != null)
113 url += "&" + OBJECT_TYPE + "=" + objectType;
119 } catch (MalformedURLException e)
126 protected boolean useGetRequest()
132 protected String getRequestMimeType(boolean multipleIds)
134 return "application/json";
138 protected String getResponseMimeType()
140 return "application/json";
144 * Returns the gene id related to the given identifier (which may be for a
145 * gene, transcript or protein)
150 public String getGeneId(String identifier)
152 return parseGeneId(getResult(identifier, null));
156 * Calls the Ensembl lookup REST endpoint and retrieves the 'species' for the
157 * given identifier, or null if not found
162 public String getSpecies(String identifier)
164 String species = null;
165 JSONObject json = getResult(identifier, null);
168 Object o = json.get(SPECIES);
171 species = o.toString();
178 * Calls the /lookup/id rest service and returns the response as a JSONObject,
179 * or null if any error
186 protected JSONObject getResult(String identifier, String objectType)
188 List<String> ids = Arrays.asList(new String[] { identifier });
190 BufferedReader br = null;
194 URL url = getUrl(identifier, objectType);
196 if (identifier.equals(lastId))
198 System.err.println("** Ensembl lookup " + url.toString()
199 + " looping on Parent!");
207 br = getHttpResponse(url, ids);
209 return br == null ? null : (JSONObject) (new JSONParser().parse(br));
210 } catch (IOException | ParseException e)
212 System.err.println("Error parsing " + identifier + " lookup response "
222 } catch (IOException e)
231 * Parses the JSON response and returns the gene identifier, or null if not
232 * found. If the returned object_type is Gene, returns the id, if Transcript
233 * returns the Parent. If it is Translation (peptide identifier), then the
234 * Parent is the transcript identifier, so we redo the search with this value,
235 * specifying that object_type should be Transcript.
240 protected String parseGeneId(JSONObject json)
244 // e.g. lookup failed with 404 not found
248 String geneId = null;
249 String type = json.get(OBJECT_TYPE).toString();
250 if (OBJECT_TYPE_GENE.equalsIgnoreCase(type))
252 // got the gene - just returns its id
253 geneId = json.get(JSON_ID).toString();
255 else if (OBJECT_TYPE_TRANSCRIPT.equalsIgnoreCase(type))
257 // got the transcript - return its (Gene) Parent
258 geneId = json.get(PARENT).toString();
260 else if (OBJECT_TYPE_TRANSLATION.equalsIgnoreCase(type))
262 // got the protein - look up its Parent, restricted to type Transcript
263 String transcriptId = json.get(PARENT).toString();
264 geneId = parseGeneId(getResult(transcriptId, OBJECT_TYPE_TRANSCRIPT));
271 * Calls the /lookup/id rest service for the given id, and if successful,
272 * parses and returns the gene's chromosomal coordinates
277 public GeneLociI getGeneLoci(String geneId)
279 return parseGeneLoci(getResult(geneId, OBJECT_TYPE_GENE));
283 * Parses the /lookup/id response for species, asssembly_name,
284 * seq_region_name, start, end and returns an object that wraps them, or null
290 GeneLociI parseGeneLoci(JSONObject json)
299 final String species = json.get("species").toString();
300 final String assembly = json.get("assembly_name").toString();
301 final String chromosome = json.get("seq_region_name").toString();
302 String strand = json.get("strand").toString();
303 int start = Integer.parseInt(json.get("start").toString());
304 int end = Integer.parseInt(json.get("end").toString());
305 int fromEnd = end - start + 1;
306 boolean reverseStrand = "-1".equals(strand);
307 int toStart = reverseStrand ? end : start;
308 int toEnd = reverseStrand ? start : end;
309 List<int[]> fromRange = Collections.singletonList(new int[] { 1,
311 List<int[]> toRange = Collections.singletonList(new int[] { toStart,
313 final MapList map = new MapList(fromRange, toRange, 1, 1);
314 return new GeneLociI()
318 public String getSpeciesId()
320 return species == null ? "" : species;
324 public String getAssemblyId()
330 public String getChromosomeId()
336 public MapList getMap()
341 } catch (NullPointerException | NumberFormatException e)
343 Cache.log.error("Error looking up gene loci: " + e.getMessage());