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;
39 import org.json.simple.JSONArray;
40 import org.json.simple.JSONObject;
41 import org.json.simple.parser.JSONParser;
42 import org.json.simple.parser.ParseException;
45 * A client for fetching and processing Ensembl feature data in GFF format by
46 * calling the overlap REST service
49 * @see http://rest.ensembl.org/documentation/info/overlap_id
51 class EnsemblFeatures extends EnsemblRestClient
54 * The default features to retrieve from Ensembl
55 * can override in getSequenceRecords parameter
57 private EnsemblFeatureType[] featuresWanted = { EnsemblFeatureType.cds,
58 EnsemblFeatureType.exon, EnsemblFeatureType.variation };
61 * Default constructor (to use rest.ensembl.org)
63 public EnsemblFeatures()
69 public String getDbName()
71 return "ENSEMBL (features)";
75 * Makes a query to the REST overlap endpoint for the given sequence
76 * identifier. This returns an 'alignment' consisting of one 'dummy sequence'
77 * (the genomic sequence for which overlap features are returned by the
78 * service). This sequence will have on it sequence features which are the
79 * real information of interest, such as CDS regions or sequence variations.
82 public AlignmentI getSequenceRecords(String query) throws IOException
84 // TODO: use a vararg String... for getSequenceRecords instead?
85 List<String> queries = new ArrayList<>();
87 BufferedReader fp = getSequenceReader(queries);
93 SequenceI seq = parseFeaturesJson(fp);
94 return new Alignment(new SequenceI[] { seq });
98 * Parses the JSON response into Jalview sequence features and attaches them
104 private SequenceI parseFeaturesJson(BufferedReader br)
106 SequenceI seq = new Sequence("Dummy", "");
108 JSONParser jp = new JSONParser();
111 JSONArray responses = (JSONArray) jp.parse(br);
112 Iterator rvals = responses.iterator();
113 while (rvals.hasNext())
117 JSONObject obj = (JSONObject) rvals.next();
118 String type = obj.get("feature_type").toString();
119 int start = Integer.parseInt(obj.get("start").toString());
120 int end = Integer.parseInt(obj.get("end").toString());
121 String source = obj.get("source").toString();
122 String strand = obj.get("strand").toString();
123 String alleles = JSONUtils
124 .arrayToList((JSONArray) obj.get("alleles"));
125 String clinSig = JSONUtils
127 (JSONArray) obj.get("clinical_significance"));
130 * convert 'variation' to 'sequence_variant', and 'cds' to 'CDS'
131 * so as to have a valid SO term for the feature type
132 * ('gene', 'exon', 'transcript' don't need any conversion)
134 if ("variation".equals(type))
136 type = SequenceOntologyI.SEQUENCE_VARIANT;
138 else if (SequenceOntologyI.CDS.equalsIgnoreCase((type)))
140 type = SequenceOntologyI.CDS;
143 String desc = getFirstNotNull(obj, "alleles", "external_name",
145 SequenceFeature sf = new SequenceFeature(type, desc, start, end,
147 sf.setStrand("1".equals(strand) ? "+" : "-");
148 setFeatureAttribute(sf, obj, "id");
149 setFeatureAttribute(sf, obj, "Parent");
150 setFeatureAttribute(sf, obj, "consequence_type");
151 sf.setValue("alleles", alleles);
152 sf.setValue("clinical_significance", clinSig);
154 seq.addSequenceFeature(sf);
155 } catch (Throwable t)
157 // ignore - keep trying other features
160 } catch (ParseException | IOException e)
169 * Returns the first non-null attribute found (if any) as a string, formatted
170 * suitably for display as feature description or tooltip. Answers null if
171 * none of the attribute keys is present.
177 protected String getFirstNotNull(JSONObject obj, String... keys)
181 for (String key : keys)
183 Object val = obj.get(key);
186 String s = val instanceof JSONArray
187 ? JSONUtils.arrayToList((JSONArray) val)
199 * A helper method that reads the 'key' entry in the JSON object, and if not
200 * null, sets its string value as an attribute on the sequence feature
206 protected void setFeatureAttribute(SequenceFeature sf, JSONObject obj,
209 Object object = obj.get(key);
212 sf.setValue(key, object.toString());
217 * Returns a URL for the REST overlap endpoint
223 protected URL getUrl(List<String> ids) throws MalformedURLException
225 StringBuffer urlstring = new StringBuffer(128);
226 urlstring.append(getDomain()).append("/overlap/id/").append(ids.get(0));
228 // @see https://github.com/Ensembl/ensembl-rest/wiki/Output-formats
229 urlstring.append("?content-type=" + getResponseMimeType());
232 * specify object_type=gene in case is shared by transcript and/or protein;
233 * currently only fetching features for gene sequences;
234 * refactor in future if needed to fetch for transcripts
236 urlstring.append("&").append(OBJECT_TYPE).append("=")
237 .append(OBJECT_TYPE_GENE);
240 * specify features to retrieve
241 * @see http://rest.ensembl.org/documentation/info/overlap_id
242 * could make the list a configurable entry in .jalview_properties
244 for (EnsemblFeatureType feature : featuresWanted)
246 urlstring.append("&feature=").append(feature.name());
249 return new URL(urlstring.toString());
253 protected boolean useGetRequest()
259 * Returns the MIME type for GFF3. For GET requests the Content-type header
260 * describes the required encoding of the response.
263 protected String getRequestMimeType()
265 return "application/json";
269 * Returns the MIME type wanted for the response
272 protected String getResponseMimeType()
274 return "application/json";
278 * Overloaded method that allows a list of features to retrieve to be
284 * @throws IOException
286 protected AlignmentI getSequenceRecords(String accId,
287 EnsemblFeatureType[] features) throws IOException
289 featuresWanted = features;
290 return getSequenceRecords(accId);