1 package jalview.ext.ensembl;
3 import jalview.datamodel.AlignmentI;
4 import jalview.datamodel.DBRefSource;
5 import jalview.datamodel.GeneLociI;
6 import jalview.util.MapList;
8 import java.io.BufferedReader;
9 import java.io.IOException;
10 import java.net.MalformedURLException;
12 import java.util.ArrayList;
13 import java.util.Collections;
14 import java.util.Iterator;
15 import java.util.List;
17 import org.json.simple.JSONArray;
18 import org.json.simple.JSONObject;
19 import org.json.simple.parser.JSONParser;
20 import org.json.simple.parser.ParseException;
22 public class EnsemblMap extends EnsemblRestClient
24 private static final String MAPPED = "mapped";
26 private static final String MAPPINGS = "mappings";
28 private static final String CDS = "cds";
30 private static final String CDNA = "cdna";
33 * Default constructor (to use rest.ensembl.org)
41 * Constructor given the target domain to fetch data from
45 public EnsemblMap(String domain)
51 public String getDbName()
53 return DBRefSource.ENSEMBL;
57 public AlignmentI getSequenceRecords(String queries) throws Exception
59 return null; // not used
63 * Constructs a URL of the format <code>
64 * http://rest.ensembl.org/map/human/GRCh38/17:45051610..45109016:1/GRCh37?content-type=application/json
74 * @throws MalformedURLException
76 protected URL getAssemblyMapUrl(String species, String chromosome, String fromRef,
77 String toRef, int startPos, int endPos)
78 throws MalformedURLException
81 * start-end might be reverse strand - present forwards to the service
83 boolean forward = startPos <= endPos;
84 int start = forward ? startPos : endPos;
85 int end = forward ? endPos : startPos;
86 String strand = forward ? "1" : "-1";
87 String url = String.format(
88 "%s/map/%s/%s/%s:%d..%d:%s/%s?content-type=application/json",
89 getDomain(), species, fromRef, chromosome, start, end, strand,
95 protected boolean useGetRequest()
101 protected URL getUrl(List<String> ids) throws MalformedURLException
103 return null; // not used
107 * Calls the REST /map service to get the chromosomal coordinates (start/end)
108 * in 'toRef' that corresponding to the (start/end) queryRange in 'fromRef'
116 * @see http://rest.ensemblgenomes.org/documentation/info/assembly_map
118 public int[] getAssemblyMapping(String species, String chromosome,
119 String fromRef, String toRef, int[] queryRange)
122 BufferedReader br = null;
126 url = getAssemblyMapUrl(species, chromosome, fromRef, toRef, queryRange[0],
128 br = getHttpResponse(url, null);
129 return (parseAssemblyMappingResponse(br));
130 } catch (Throwable t)
132 System.out.println("Error calling " + url + ": " + t.getMessage());
141 } catch (IOException e)
150 * Parses the JSON response from the /map/<species>/ REST service. The
151 * format is (with some fields omitted)
156 * "original": {"end":45109016,"start":45051610},
157 * "mapped" : {"end":43186384,"start":43128978}
164 protected int[] parseAssemblyMappingResponse(BufferedReader br)
167 JSONParser jp = new JSONParser();
171 JSONObject parsed = (JSONObject) jp.parse(br);
172 JSONArray mappings = (JSONArray) parsed.get(MAPPINGS);
174 Iterator rvals = mappings.iterator();
175 while (rvals.hasNext())
177 // todo check for "mapped"
178 JSONObject val = (JSONObject) rvals.next();
179 JSONObject mapped = (JSONObject) val.get(MAPPED);
180 int start = Integer.parseInt(mapped.get("start").toString());
181 int end = Integer.parseInt(mapped.get("end").toString());
182 String strand = mapped.get("strand").toString();
183 if ("1".equals(strand))
185 result = new int[] { start, end };
189 result = new int[] { end, start };
192 } catch (IOException | ParseException | NumberFormatException e)
200 * Calls the REST /map/cds/id service, and returns a DBRefEntry holding the
201 * returned chromosomal coordinates, or returns null if the call fails
204 * e.g. Ensembl, EnsemblMetazoa
206 * e.g. ENST00000592782, Y55B1AR.1.1
211 public GeneLociI getCdsMapping(String division, String accession,
214 return getIdMapping(division, accession, start, end, CDS);
218 * Calls the REST /map/cdna/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 getCdnaMapping(String division, String accession,
232 return getIdMapping(division, accession, start, end, CDNA);
235 GeneLociI getIdMapping(String division, String accession, int start,
236 int end, String cdsOrCdna)
239 BufferedReader br = null;
243 String domain = new EnsemblInfo().getDomain(division);
246 url = getIdMapUrl(domain, accession, start, end, cdsOrCdna);
247 br = getHttpResponse(url, null);
250 return (parseIdMappingResponse(br, accession, domain));
254 } catch (Throwable t)
256 System.out.println("Error calling " + url + ": " + t.getMessage());
265 } catch (IOException e)
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 GeneLociI parseIdMappingResponse(BufferedReader br, String accession,
318 JSONParser jp = new JSONParser();
322 JSONObject parsed = (JSONObject) jp.parse(br);
323 JSONArray mappings = (JSONArray) parsed.get(MAPPINGS);
325 Iterator rvals = mappings.iterator();
326 String assembly = null;
327 String chromosome = null;
329 List<int[]> regions = new ArrayList<>();
331 while (rvals.hasNext())
333 JSONObject val = (JSONObject) rvals.next();
334 JSONObject original = (JSONObject) val.get("original");
335 fromEnd = Integer.parseInt(original.get("end").toString());
337 JSONObject mapped = (JSONObject) val.get(MAPPED);
338 int start = Integer.parseInt(mapped.get("start").toString());
339 int end = Integer.parseInt(mapped.get("end").toString());
340 String ass = mapped.get("assembly_name").toString();
341 if (assembly != null && !assembly.equals(ass))
344 .println("EnsemblMap found multiple assemblies - can't resolve");
348 String chr = mapped.get("seq_region_name").toString();
349 if (chromosome != null && !chromosome.equals(chr))
352 .println("EnsemblMap found multiple chromosomes - can't resolve");
356 String strand = mapped.get("strand").toString();
357 if ("-1".equals(strand))
359 regions.add(new int[] { end, start });
363 regions.add(new int[] { start, end });
368 * processed all mapped regions on chromosome, assemble the result,
369 * having first fetched the species id for the accession
371 final String species = new EnsemblLookup(domain)
372 .getSpecies(accession);
373 final String as = assembly;
374 final String chr = chromosome;
375 List<int[]> fromRange = Collections.singletonList(new int[] { 1,
377 final MapList map = new MapList(fromRange, regions, 1, 1);
378 return new GeneLociI()
382 public String getSpeciesId()
384 return species == null ? "" : species;
388 public String getAssemblyId()
394 public String getChromosomeId()
400 public MapList getMap()
405 } catch (IOException | ParseException | NumberFormatException e)