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.Alignment;
24 import jalview.datamodel.AlignmentI;
25 import jalview.datamodel.Sequence;
26 import jalview.datamodel.SequenceFeature;
27 import jalview.datamodel.SequenceI;
28 import jalview.io.gff.SequenceOntologyI;
29 import jalview.util.JSONUtils;
31 import java.io.IOException;
32 import java.net.MalformedURLException;
34 import java.util.ArrayList;
35 import java.util.Iterator;
36 import java.util.List;
39 import org.json.simple.parser.ParseException;
42 * A client for fetching and processing Ensembl feature data in GFF format by
43 * calling the overlap REST service
46 * @see http://rest.ensembl.org/documentation/info/overlap_id
48 class EnsemblFeatures extends EnsemblRestClient
51 * The default features to retrieve from Ensembl
52 * can override in getSequenceRecords parameter
54 private EnsemblFeatureType[] featuresWanted = { EnsemblFeatureType.cds,
55 EnsemblFeatureType.exon, EnsemblFeatureType.variation };
58 * Default constructor (to use rest.ensembl.org)
60 public EnsemblFeatures()
66 * Constructor given the target domain to fetch data from
70 public EnsemblFeatures(String d)
76 public String getDbName()
78 return "ENSEMBL (features)";
82 * Makes a query to the REST overlap endpoint for the given sequence
83 * identifier. This returns an 'alignment' consisting of one 'dummy sequence'
84 * (the genomic sequence for which overlap features are returned by the
85 * service). This sequence will have on it sequence features which are the
86 * real information of interest, such as CDS regions or sequence variations.
89 public AlignmentI getSequenceRecords(String query) throws IOException
91 // TODO: use a vararg String... for getSequenceRecords instead?
93 List<String> queries = new ArrayList<>();
95 SequenceI seq = parseFeaturesJson(queries);
96 return new Alignment(new SequenceI[] { seq });
100 * Parses the JSON response into Jalview sequence features and attaches them
101 * to a dummy sequence
106 @SuppressWarnings("unchecked")
107 private SequenceI parseFeaturesJson(List<String> queries)
109 SequenceI seq = new Sequence("Dummy", "");
112 Iterator<Object> rvals = (Iterator<Object>) getJSON(null, queries, -1, MODE_ITERATOR, null);
117 while (rvals.hasNext())
121 Map<String, Object> obj = (Map<String, Object>) rvals.next();
122 String type = obj.get("feature_type").toString();
123 int start = Integer.parseInt(obj.get("start").toString());
124 int end = Integer.parseInt(obj.get("end").toString());
125 String source = obj.get("source").toString();
126 String strand = obj.get("strand").toString();
127 String alleles = JSONUtils
128 .arrayToStringList((List<Object>) obj.get("alleles"));
129 String clinSig = JSONUtils
131 (List<Object>) obj.get("clinical_significance"));
134 * convert 'variation' to 'sequence_variant', and 'cds' to 'CDS'
135 * so as to have a valid SO term for the feature type
136 * ('gene', 'exon', 'transcript' don't need any conversion)
138 if ("variation".equals(type))
140 type = SequenceOntologyI.SEQUENCE_VARIANT;
142 else if (SequenceOntologyI.CDS.equalsIgnoreCase((type)))
144 type = SequenceOntologyI.CDS;
147 String desc = getFirstNotNull(obj, "alleles", "external_name",
149 SequenceFeature sf = new SequenceFeature(type, desc, start, end,
151 sf.setStrand("1".equals(strand) ? "+" : "-");
152 setFeatureAttribute(sf, obj, "id");
153 setFeatureAttribute(sf, obj, "Parent");
154 setFeatureAttribute(sf, obj, "consequence_type");
155 sf.setValue("alleles", alleles);
156 sf.setValue("clinical_significance", clinSig);
158 seq.addSequenceFeature(sf);
160 } catch (Throwable t)
162 // ignore - keep trying other features
165 } catch (ParseException | IOException e)
175 * Returns the first non-null attribute found (if any) as a string, formatted
176 * suitably for display as feature description or tooltip. Answers null if
177 * none of the attribute keys is present.
183 @SuppressWarnings("unchecked")
184 protected String getFirstNotNull(Map<String, Object> obj, String... keys)
186 for (String key : keys)
188 Object val = obj.get(key);
191 String s = val instanceof List<?>
192 ? JSONUtils.arrayToStringList((List<Object>) val)
204 * A helper method that reads the 'key' entry in the JSON object, and if not
205 * null, sets its string value as an attribute on the sequence feature
211 protected void setFeatureAttribute(SequenceFeature sf, Map<String, Object> obj,
214 Object object = obj.get(key);
217 sf.setValue(key, object.toString());
222 * Returns a URL for the REST overlap endpoint
228 protected URL getUrl(List<String> ids) throws MalformedURLException
230 StringBuffer urlstring = new StringBuffer(128);
231 urlstring.append(getDomain()).append("/overlap/id/").append(ids.get(0));
233 // @see https://github.com/Ensembl/ensembl-rest/wiki/Output-formats
234 urlstring.append("?content-type=" + getResponseMimeType());
237 * specify object_type=gene in case is shared by transcript and/or protein;
238 * currently only fetching features for gene sequences;
239 * refactor in future if needed to fetch for transcripts
241 urlstring.append("&").append(OBJECT_TYPE).append("=")
242 .append(OBJECT_TYPE_GENE);
245 * specify features to retrieve
246 * @see http://rest.ensembl.org/documentation/info/overlap_id
247 * could make the list a configurable entry in .jalview_properties
249 for (EnsemblFeatureType feature : featuresWanted)
251 urlstring.append("&feature=").append(feature.name());
254 return new URL(urlstring.toString());
258 protected boolean useGetRequest()
264 * Returns the MIME type for GFF3. For GET requests the Content-type header
265 * describes the required encoding of the response.
268 protected String getRequestMimeType()
270 return "application/json";
274 * Returns the MIME type wanted for the response
277 protected String getResponseMimeType()
279 return "application/json";
283 * Overloaded method that allows a list of features to retrieve to be
289 * @throws IOException
291 protected AlignmentI getSequenceRecords(String accId,
292 EnsemblFeatureType[] features) throws IOException
294 featuresWanted = features;
295 return getSequenceRecords(accId);