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.datamodel.AlignmentI;
24 import jalview.datamodel.DBRefSource;
25 import jalview.datamodel.GeneLociI;
26 import jalview.datamodel.GeneLocus;
27 import jalview.datamodel.Mapping;
28 import jalview.util.MapList;
30 import java.io.IOException;
31 import java.net.MalformedURLException;
33 import java.util.ArrayList;
34 import java.util.Collections;
35 import java.util.Iterator;
36 import java.util.List;
39 import org.json.simple.parser.ParseException;
42 * A client for the Ensembl REST service /map endpoint, to convert from
43 * coordinates of one genome assembly to another.
45 * Note that species and assembly identifiers passed to this class must be valid
46 * in Ensembl. They are not case sensitive.
49 * @see https://rest.ensembl.org/documentation/info/assembly_map
50 * @see https://rest.ensembl.org/info/assembly/human?content-type=text/xml
51 * @see https://rest.ensembl.org/info/species?content-type=text/xml
53 public class EnsemblMap extends EnsemblRestClient
55 private static final String MAPPED = "mapped";
57 private static final String MAPPINGS = "mappings";
59 private static final String CDS = "cds";
61 private static final String CDNA = "cdna";
64 * Default constructor (to use rest.ensembl.org)
72 * Constructor given the target domain to fetch data from
76 public EnsemblMap(String domain)
82 public String getDbName()
84 return DBRefSource.ENSEMBL;
88 public AlignmentI getSequenceRecords(String queries) throws Exception
90 return null; // not used
94 * Constructs a URL of the format <code>
95 * http://rest.ensembl.org/map/human/GRCh38/17:45051610..45109016:1/GRCh37?content-type=application/json
105 * @throws MalformedURLException
107 protected URL getAssemblyMapUrl(String species, String chromosome,
108 String fromRef, String toRef, int startPos, int endPos)
109 throws MalformedURLException
112 * start-end might be reverse strand - present forwards to the service
114 boolean forward = startPos <= endPos;
115 int start = forward ? startPos : endPos;
116 int end = forward ? endPos : startPos;
117 String strand = forward ? "1" : "-1";
118 String url = String.format(
119 "%s/map/%s/%s/%s:%d..%d:%s/%s?content-type=application/json",
120 getDomain(), species, fromRef, chromosome, start, end, strand,
126 protected boolean useGetRequest()
132 protected URL getUrl(List<String> ids) throws MalformedURLException
134 return null; // not used
138 * Calls the REST /map service to get the chromosomal coordinates (start/end)
139 * in 'toRef' that corresponding to the (start/end) queryRange in 'fromRef'
147 * @see http://rest.ensemblgenomes.org/documentation/info/assembly_map
149 public int[] getAssemblyMapping(String species, String chromosome,
150 String fromRef, String toRef, int[] queryRange)
155 url = getAssemblyMapUrl(species, chromosome, fromRef, toRef,
156 queryRange[0], queryRange[1]);
157 return (parseAssemblyMappingResponse(url));
158 } catch (Throwable t)
161 .outPrintln("Error calling " + url + ": " + t.getMessage());
167 * Parses the JSON response from the /map/<species>/ REST service. The
168 * format is (with some fields omitted)
173 * "original": {"end":45109016,"start":45051610},
174 * "mapped" : {"end":43186384,"start":43128978}
181 @SuppressWarnings("unchecked")
182 protected int[] parseAssemblyMappingResponse(URL url)
188 Iterator<Object> rvals = (Iterator<Object>) getJSON(url, null, -1,
189 MODE_ITERATOR, MAPPINGS);
194 while (rvals.hasNext())
196 // todo check for "mapped"
197 Map<String, Object> val = (Map<String, Object>) rvals.next();
198 Map<String, Object> mapped = (Map<String, Object>) val.get(MAPPED);
199 int start = Integer.parseInt(mapped.get("start").toString());
200 int end = Integer.parseInt(mapped.get("end").toString());
201 String strand = mapped.get("strand").toString();
202 if ("1".equals(strand))
204 result = new int[] { start, end };
208 result = new int[] { end, start };
211 } catch (IOException | ParseException | NumberFormatException e)
219 * Calls the REST /map/cds/id service, and returns a DBRefEntry holding the
220 * returned chromosomal coordinates, or returns null if the call fails
223 * e.g. Ensembl, EnsemblMetazoa
225 * e.g. ENST00000592782, Y55B1AR.1.1
230 public GeneLociI getCdsMapping(String division, String accession,
233 return getIdMapping(division, accession, start, end, CDS);
237 * Calls the REST /map/cdna/id service, and returns a DBRefEntry holding the
238 * returned chromosomal coordinates, or returns null if the call fails
241 * e.g. Ensembl, EnsemblMetazoa
243 * e.g. ENST00000592782, Y55B1AR.1.1
248 public GeneLociI getCdnaMapping(String division, String accession,
251 return getIdMapping(division, accession, start, end, CDNA);
254 GeneLociI getIdMapping(String division, String accession, int start,
255 int end, String cdsOrCdna)
260 String domain = new EnsemblInfo().getDomain(division);
263 url = getIdMapUrl(domain, accession, start, end, cdsOrCdna);
264 return (parseIdMappingResponse(url, accession, domain));
267 } catch (Throwable t)
270 .outPrintln("Error calling " + url + ": " + t.getMessage());
276 * Constructs a URL to the /map/cds/<id> or /map/cdna/<id> REST service. The
277 * REST call is to either ensembl or ensemblgenomes, as determined from the
278 * division, e.g. Ensembl or EnsemblProtists.
286 * @throws MalformedURLException
288 URL getIdMapUrl(String domain, String accession, int start, int end,
289 String cdsOrCdna) throws MalformedURLException
291 String url = String.format(
292 "%s/map/%s/%s/%d..%d?include_original_region=1&content-type=application/json",
293 domain, cdsOrCdna, accession, start, end);
298 * Parses the JSON response from the /map/cds/ or /map/cdna REST service. The
304 * {"assembly_name":"TAIR10","end":2501311,"seq_region_name":"1","gap":0,
305 * "strand":-1,"coord_system":"chromosome","rank":0,"start":2501114},
306 * {"assembly_name":"TAIR10","end":2500815,"seq_region_name":"1","gap":0,
307 * "strand":-1,"coord_system":"chromosome","rank":0,"start":2500714}
317 @SuppressWarnings("unchecked")
318 GeneLociI parseIdMappingResponse(URL url, String accession, String domain)
323 Iterator<Object> rvals = (Iterator<Object>) getJSON(url, null, -1,
324 MODE_ITERATOR, MAPPINGS);
329 String assembly = null;
330 String chromosome = null;
332 List<int[]> regions = new ArrayList<>();
334 while (rvals.hasNext())
336 Map<String, Object> val = (Map<String, Object>) rvals.next();
337 Map<String, Object> original = (Map<String, Object>) val
339 fromEnd = Integer.parseInt(original.get("end").toString());
341 Map<String, Object> mapped = (Map<String, Object>) val.get(MAPPED);
342 int start = Integer.parseInt(mapped.get("start").toString());
343 int end = Integer.parseInt(mapped.get("end").toString());
344 String ass = mapped.get("assembly_name").toString();
345 if (assembly != null && !assembly.equals(ass))
347 jalview.bin.Console.errPrintln(
348 "EnsemblMap found multiple assemblies - can't resolve");
352 String chr = mapped.get("seq_region_name").toString();
353 if (chromosome != null && !chromosome.equals(chr))
355 jalview.bin.Console.errPrintln(
356 "EnsemblMap found multiple chromosomes - can't resolve");
360 String strand = mapped.get("strand").toString();
361 if ("-1".equals(strand))
363 regions.add(new int[] { end, start });
367 regions.add(new int[] { start, end });
372 * processed all mapped regions on chromosome, assemble the result,
373 * having first fetched the species id for the accession
375 final String species = new EnsemblLookup(domain)
376 .getSpecies(accession);
377 final String as = assembly;
378 final String chr = chromosome;
379 List<int[]> fromRange = Collections
380 .singletonList(new int[]
382 Mapping mapping = new Mapping(new MapList(fromRange, regions, 1, 1));
383 return new GeneLocus(species == null ? "" : species, as, chr,
385 } catch (IOException | ParseException | NumberFormatException e)