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 java.io.IOException;
24 import java.net.MalformedURLException;
26 import java.util.ArrayList;
27 import java.util.Collections;
28 import java.util.Iterator;
29 import java.util.List;
32 import org.json.simple.parser.ParseException;
34 import jalview.bin.Cache;
35 import jalview.datamodel.AlignmentI;
36 import jalview.datamodel.DBRefSource;
37 import jalview.datamodel.GeneLociI;
38 import jalview.datamodel.GeneLocus;
39 import jalview.datamodel.Mapping;
40 import jalview.util.MapList;
43 * A client for the Ensembl REST service /map endpoint, to convert from
44 * coordinates of one genome assembly to another.
46 * Note that species and assembly identifiers passed to this class must be valid
47 * in Ensembl. They are not case sensitive.
50 * @see https://rest.ensembl.org/documentation/info/assembly_map
51 * @see https://rest.ensembl.org/info/assembly/human?content-type=text/xml
52 * @see https://rest.ensembl.org/info/species?content-type=text/xml
54 public class EnsemblMap extends EnsemblRestClient
56 private static final String MAPPED = "mapped";
58 private static final String MAPPINGS = "mappings";
60 private static final String CDS = "cds";
62 private static final String CDNA = "cdna";
65 * Default constructor (to use rest.ensembl.org)
73 * Constructor given the target domain to fetch data from
77 public EnsemblMap(String domain)
83 public String getDbName()
85 return DBRefSource.ENSEMBL;
89 public AlignmentI getSequenceRecords(String queries) throws Exception
91 return null; // not used
95 * Constructs a URL of the format <code>
96 * http://rest.ensembl.org/map/human/GRCh38/17:45051610..45109016:1/GRCh37?content-type=application/json
106 * @throws MalformedURLException
108 protected URL getAssemblyMapUrl(String species, String chromosome, String fromRef,
109 String toRef, int startPos, int endPos)
110 throws MalformedURLException
113 * start-end might be reverse strand - present forwards to the service
115 boolean forward = startPos <= endPos;
116 int start = forward ? startPos : endPos;
117 int end = forward ? endPos : startPos;
118 String strand = forward ? "1" : "-1";
119 String url = String.format(
120 "%s/map/%s/%s/%s:%d..%d:%s/%s?content-type=application/json",
121 getDomain(), species, fromRef, chromosome, start, end, strand,
127 protected boolean useGetRequest()
133 protected URL getUrl(List<String> ids) throws MalformedURLException
135 return null; // not used
139 * Calls the REST /map service to get the chromosomal coordinates (start/end)
140 * in 'toRef' that corresponding to the (start/end) queryRange in 'fromRef'
148 * @see http://rest.ensemblgenomes.org/documentation/info/assembly_map
150 public int[] getAssemblyMapping(String species, String chromosome,
151 String fromRef, String toRef, int[] queryRange)
156 url = getAssemblyMapUrl(species, chromosome, fromRef, toRef, queryRange[0],
158 return (parseAssemblyMappingResponse(url));
159 } catch (Throwable t)
161 Cache.log.error("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, MODE_ITERATOR, MAPPINGS);
193 while (rvals.hasNext())
195 // todo check for "mapped"
196 Map<String, Object> val = (Map<String, Object>) rvals.next();
197 Map<String, Object> mapped = (Map<String, Object>) val.get(MAPPED);
198 int start = Integer.parseInt(mapped.get("start").toString());
199 int end = Integer.parseInt(mapped.get("end").toString());
200 String strand = mapped.get("strand").toString();
201 if ("1".equals(strand))
203 result = new int[] { start, end };
207 result = new int[] { end, start };
210 } catch (IOException | ParseException | NumberFormatException e)
218 * Calls the REST /map/cds/id service, and returns a DBRefEntry holding the
219 * returned chromosomal coordinates, or returns null if the call fails
222 * e.g. Ensembl, EnsemblMetazoa
224 * e.g. ENST00000592782, Y55B1AR.1.1
229 public GeneLociI getCdsMapping(String division, String accession,
232 return getIdMapping(division, accession, start, end, CDS);
236 * Calls the REST /map/cdna/id service, and returns a DBRefEntry holding the
237 * returned chromosomal coordinates, or returns null if the call fails
240 * e.g. Ensembl, EnsemblMetazoa
242 * e.g. ENST00000592782, Y55B1AR.1.1
247 public GeneLociI getCdnaMapping(String division, String accession,
250 return getIdMapping(division, accession, start, end, CDNA);
253 GeneLociI getIdMapping(String division, String accession, int start,
254 int end, String cdsOrCdna)
259 String domain = new EnsemblInfo().getDomain(division);
262 url = getIdMapUrl(domain, accession, start, end, cdsOrCdna);
263 return (parseIdMappingResponse(url, accession, domain));
266 } catch (Throwable t)
268 Cache.log.error("Error calling " + url + ": " + t.getMessage());
274 * Constructs a URL to the /map/cds/<id> or /map/cdna/<id> REST service. The
275 * REST call is to either ensembl or ensemblgenomes, as determined from the
276 * division, e.g. Ensembl or EnsemblProtists.
284 * @throws MalformedURLException
286 URL getIdMapUrl(String domain, String accession, int start, int end,
287 String cdsOrCdna) throws MalformedURLException
290 .format("%s/map/%s/%s/%d..%d?include_original_region=1&content-type=application/json",
291 domain, cdsOrCdna, accession, start, end);
296 * Parses the JSON response from the /map/cds/ or /map/cdna REST service. The
302 * {"assembly_name":"TAIR10","end":2501311,"seq_region_name":"1","gap":0,
303 * "strand":-1,"coord_system":"chromosome","rank":0,"start":2501114},
304 * {"assembly_name":"TAIR10","end":2500815,"seq_region_name":"1","gap":0,
305 * "strand":-1,"coord_system":"chromosome","rank":0,"start":2500714}
315 @SuppressWarnings("unchecked")
316 GeneLociI parseIdMappingResponse(URL url, String accession,
322 Iterator<Object> rvals = (Iterator<Object>) getJSON(url, null, -1, MODE_ITERATOR, MAPPINGS);
327 String assembly = null;
328 String chromosome = null;
330 List<int[]> regions = new ArrayList<>();
332 while (rvals.hasNext())
334 Map<String, Object> val = (Map<String, Object>) rvals.next();
335 Map<String, Object> original = (Map<String, Object>) val.get("original");
336 fromEnd = Integer.parseInt(original.get("end").toString());
338 Map<String, Object> mapped = (Map<String, Object>) val.get(MAPPED);
339 int start = Integer.parseInt(mapped.get("start").toString());
340 int end = Integer.parseInt(mapped.get("end").toString());
341 String ass = mapped.get("assembly_name").toString();
342 if (assembly != null && !assembly.equals(ass))
345 .println("EnsemblMap found multiple assemblies - can't resolve");
349 String chr = mapped.get("seq_region_name").toString();
350 if (chromosome != null && !chromosome.equals(chr))
353 .println("EnsemblMap found multiple chromosomes - can't resolve");
357 String strand = mapped.get("strand").toString();
358 if ("-1".equals(strand))
360 regions.add(new int[] { end, start });
364 regions.add(new int[] { start, end });
369 * processed all mapped regions on chromosome, assemble the result,
370 * having first fetched the species id for the accession
372 final String species = new EnsemblLookup(domain)
373 .getSpecies(accession);
374 final String as = assembly;
375 final String chr = chromosome;
376 List<int[]> fromRange = Collections.singletonList(new int[] { 1,
378 Mapping mapping = new Mapping(new MapList(fromRange, regions, 1, 1));
379 return new GeneLocus(species == null ? "" : species, as, chr,
381 } catch (IOException | ParseException | NumberFormatException e)