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.BufferedReader;
32 import java.io.IOException;
33 import java.net.MalformedURLException;
35 import java.util.ArrayList;
36 import java.util.Iterator;
37 import java.util.List;
40 import org.json.simple.parser.ParseException;
43 * A client for fetching and processing Ensembl feature data in GFF format by
44 * calling the overlap REST service
47 * @see http://rest.ensembl.org/documentation/info/overlap_id
49 class EnsemblFeatures extends EnsemblRestClient
52 * The default features to retrieve from Ensembl
53 * can override in getSequenceRecords parameter
55 private EnsemblFeatureType[] featuresWanted = { EnsemblFeatureType.cds,
56 EnsemblFeatureType.exon, EnsemblFeatureType.variation };
59 * Default constructor (to use rest.ensembl.org)
61 public EnsemblFeatures()
67 * Constructor given the target domain to fetch data from
71 public EnsemblFeatures(String d)
77 public String getDbName()
79 return "ENSEMBL (features)";
83 * Makes a query to the REST overlap endpoint for the given sequence
84 * identifier. This returns an 'alignment' consisting of one 'dummy sequence'
85 * (the genomic sequence for which overlap features are returned by the
86 * service). This sequence will have on it sequence features which are the
87 * real information of interest, such as CDS regions or sequence variations.
90 public AlignmentI getSequenceRecords(String query) throws IOException
92 // TODO: use a vararg String... for getSequenceRecords instead?
93 List<String> queries = new ArrayList<>();
95 SequenceI seq = parseFeaturesJson(queries);
98 return new Alignment(new SequenceI[] { seq });
102 * Parses the JSON response into Jalview sequence features and attaches them
103 * to a dummy sequence
108 @SuppressWarnings("unchecked")
109 private SequenceI parseFeaturesJson(List<String> queries)
113 SequenceI seq = new Sequence("Dummy", "");
118 Iterator<Object> rvals = (Iterator<Object>) getJSON(null, queries, -1, MODE_ITERATOR, null);
121 while (rvals.hasNext())
125 Map<String, Object> obj = (Map<String, Object>) rvals.next();
126 String type = obj.get("feature_type").toString();
127 int start = Integer.parseInt(obj.get("start").toString());
128 int end = Integer.parseInt(obj.get("end").toString());
129 String source = obj.get("source").toString();
130 String strand = obj.get("strand").toString();
131 String alleles = JSONUtils
132 .arrayToStringList((List<Object>) obj.get("alleles"));
133 String clinSig = JSONUtils
135 (List<Object>) obj.get("clinical_significance"));
138 * convert 'variation' to 'sequence_variant', and 'cds' to 'CDS'
139 * so as to have a valid SO term for the feature type
140 * ('gene', 'exon', 'transcript' don't need any conversion)
142 if ("variation".equals(type))
144 type = SequenceOntologyI.SEQUENCE_VARIANT;
146 else if (SequenceOntologyI.CDS.equalsIgnoreCase((type)))
148 type = SequenceOntologyI.CDS;
151 String desc = getFirstNotNull(obj, "alleles", "external_name",
153 SequenceFeature sf = new SequenceFeature(type, desc, start, end,
155 sf.setStrand("1".equals(strand) ? "+" : "-");
156 setFeatureAttribute(sf, obj, "id");
157 setFeatureAttribute(sf, obj, "Parent");
158 setFeatureAttribute(sf, obj, "consequence_type");
159 sf.setValue("alleles", alleles);
160 sf.setValue("clinical_significance", clinSig);
162 seq.addSequenceFeature(sf);
163 } catch (Throwable t)
165 // ignore - keep trying other features
168 } catch (ParseException | IOException e)
179 * Returns the first non-null attribute found (if any) as a string
185 protected String getFirstNotNull(Map<String, Object> obj, String... keys)
189 for (String key : keys)
191 Object val = obj.get(key);
194 String s = val.toString();
205 * A helper method that reads the 'key' entry in the JSON object, and if not
206 * null, sets its string value as an attribute on the sequence feature
212 protected void setFeatureAttribute(SequenceFeature sf, Map<String, Object> obj,
215 Object object = obj.get(key);
218 sf.setValue(key, object.toString());
223 * Returns a URL for the REST overlap endpoint
229 protected URL getUrl(List<String> ids) throws MalformedURLException
231 StringBuffer urlstring = new StringBuffer(128);
232 urlstring.append(getDomain()).append("/overlap/id/").append(ids.get(0));
234 // @see https://github.com/Ensembl/ensembl-rest/wiki/Output-formats
235 urlstring.append("?content-type=" + getResponseMimeType());
238 * specify object_type=gene in case is shared by transcript and/or protein;
239 * currently only fetching features for gene sequences;
240 * refactor in future if needed to fetch for transcripts
242 urlstring.append("&").append(OBJECT_TYPE).append("=")
243 .append(OBJECT_TYPE_GENE);
246 * specify features to retrieve
247 * @see http://rest.ensembl.org/documentation/info/overlap_id
248 * could make the list a configurable entry in .jalview_properties
250 for (EnsemblFeatureType feature : featuresWanted)
252 urlstring.append("&feature=").append(feature.name());
255 return new URL(urlstring.toString());
259 protected boolean useGetRequest()
265 * Returns the MIME type for GFF3. For GET requests the Content-type header
266 * describes the required encoding of the response.
269 protected String getRequestMimeType()
271 return "application/json";
275 * Returns the MIME type wanted for the response
278 protected String getResponseMimeType()
280 return "application/json";
284 * Overloaded method that allows a list of features to retrieve to be
290 * @throws IOException
292 protected AlignmentI getSequenceRecords(String accId,
293 EnsemblFeatureType[] features) throws IOException
295 featuresWanted = features;
296 return getSequenceRecords(accId);