Class |
Line # |
Actions |
|||
---|---|---|---|---|---|
EnsemblLookup | 47 | 60 | 28 |
1 | /* | |
2 | * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$) | |
3 | * Copyright (C) $$Year-Rel$$ The Jalview Authors | |
4 | * | |
5 | * This file is part of Jalview. | |
6 | * | |
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. | |
11 | * | |
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. | |
16 | * | |
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. | |
20 | */ | |
21 | package jalview.ext.ensembl; | |
22 | ||
23 | import jalview.bin.Console; | |
24 | import jalview.datamodel.AlignmentI; | |
25 | import jalview.datamodel.GeneLociI; | |
26 | import jalview.datamodel.GeneLocus; | |
27 | import jalview.datamodel.Mapping; | |
28 | import jalview.util.MapList; | |
29 | ||
30 | import java.io.IOException; | |
31 | import java.net.MalformedURLException; | |
32 | import java.net.URL; | |
33 | import java.util.Arrays; | |
34 | import java.util.Collections; | |
35 | import java.util.List; | |
36 | import java.util.Map; | |
37 | ||
38 | import org.json.simple.parser.ParseException; | |
39 | ||
40 | /** | |
41 | * A client for the Ensembl /lookup REST endpoint, used to find the gene | |
42 | * identifier given a gene, transcript or protein identifier, or to extract the | |
43 | * species or chromosomal coordinates from the same service response | |
44 | * | |
45 | * @author gmcarstairs | |
46 | */ | |
47 | public class EnsemblLookup extends EnsemblRestClient | |
48 | { | |
49 | private static final String SPECIES = "species"; | |
50 | ||
51 | /** | |
52 | * Default constructor (to use rest.ensembl.org) | |
53 | */ | |
54 | 0 | public EnsemblLookup() |
55 | { | |
56 | 0 | super(); |
57 | } | |
58 | ||
59 | /** | |
60 | * Constructor given the target domain to fetch data from | |
61 | * | |
62 | * @param | |
63 | */ | |
64 | 0 | public EnsemblLookup(String d) |
65 | { | |
66 | 0 | super(d); |
67 | } | |
68 | ||
69 | 0 | @Override |
70 | public String getDbName() | |
71 | { | |
72 | 0 | return "ENSEMBL"; |
73 | } | |
74 | ||
75 | 0 | @Override |
76 | public AlignmentI getSequenceRecords(String queries) throws Exception | |
77 | { | |
78 | 0 | return null; |
79 | } | |
80 | ||
81 | 0 | @Override |
82 | protected URL getUrl(List<String> ids) throws MalformedURLException | |
83 | { | |
84 | 0 | String identifier = ids.get(0); |
85 | 0 | return getUrl(identifier, null); |
86 | } | |
87 | ||
88 | /** | |
89 | * Gets the url for lookup of the given identifier, optionally with objectType | |
90 | * also specified in the request | |
91 | * | |
92 | * @param identifier | |
93 | * @param objectType | |
94 | * @return | |
95 | */ | |
96 | 0 | protected URL getUrl(String identifier, String objectType) |
97 | { | |
98 | 0 | String url = getDomain() + "/lookup/id/" + identifier |
99 | + CONTENT_TYPE_JSON; | |
100 | 0 | if (objectType != null) |
101 | { | |
102 | 0 | url += "&" + OBJECT_TYPE + "=" + objectType; |
103 | } | |
104 | ||
105 | 0 | try |
106 | { | |
107 | 0 | return new URL(url); |
108 | } catch (MalformedURLException e) | |
109 | { | |
110 | 0 | return null; |
111 | } | |
112 | } | |
113 | ||
114 | 0 | @Override |
115 | protected boolean useGetRequest() | |
116 | { | |
117 | 0 | return true; |
118 | } | |
119 | ||
120 | /** | |
121 | * Returns the gene id related to the given identifier (which may be for a | |
122 | * gene, transcript or protein), or null if none is found | |
123 | * | |
124 | * @param identifier | |
125 | * @return | |
126 | */ | |
127 | 0 | public String getGeneId(String identifier) |
128 | { | |
129 | 0 | return getGeneId(identifier, null); |
130 | } | |
131 | ||
132 | /** | |
133 | * Returns the gene id related to the given identifier (which may be for a | |
134 | * gene, transcript or protein), or null if none is found | |
135 | * | |
136 | * @param identifier | |
137 | * @param objectType | |
138 | * @return | |
139 | */ | |
140 | 0 | public String getGeneId(String identifier, String objectType) |
141 | { | |
142 | 0 | return parseGeneId(getResult(identifier, objectType)); |
143 | } | |
144 | ||
145 | /** | |
146 | * Parses the JSON response and returns the gene identifier, or null if not | |
147 | * found. If the returned object_type is Gene, returns the id, if Transcript | |
148 | * returns the Parent. If it is Translation (peptide identifier), then the | |
149 | * Parent is the transcript identifier, so we redo the search with this value. | |
150 | * | |
151 | * @param br | |
152 | * @return | |
153 | */ | |
154 | 0 | protected String parseGeneId(Map<String, Object> val) |
155 | { | |
156 | 0 | if (val == null) |
157 | { | |
158 | 0 | return null; |
159 | } | |
160 | 0 | String geneId = null; |
161 | 0 | String type = val.get(OBJECT_TYPE).toString(); |
162 | 0 | if (OBJECT_TYPE_GENE.equalsIgnoreCase(type)) |
163 | { | |
164 | // got the gene - just returns its id | |
165 | 0 | geneId = val.get(JSON_ID).toString(); |
166 | } | |
167 | 0 | else if (OBJECT_TYPE_TRANSCRIPT.equalsIgnoreCase(type)) |
168 | { | |
169 | // got the transcript - return its (Gene) Parent | |
170 | 0 | geneId = val.get(PARENT).toString(); |
171 | } | |
172 | 0 | else if (OBJECT_TYPE_TRANSLATION.equalsIgnoreCase(type)) |
173 | { | |
174 | // got the protein - get its Parent, restricted to type Transcript | |
175 | 0 | String transcriptId = val.get(PARENT).toString(); |
176 | 0 | geneId = getGeneId(transcriptId, OBJECT_TYPE_TRANSCRIPT); |
177 | } | |
178 | ||
179 | 0 | return geneId; |
180 | } | |
181 | ||
182 | /** | |
183 | * Calls the Ensembl lookup REST endpoint and retrieves the 'species' for the | |
184 | * given identifier, or null if not found | |
185 | * | |
186 | * @param identifier | |
187 | * @return | |
188 | */ | |
189 | 0 | public String getSpecies(String identifier) |
190 | { | |
191 | 0 | String species = null; |
192 | 0 | Map<String, Object> json = getResult(identifier, null); |
193 | 0 | if (json != null) |
194 | { | |
195 | 0 | Object o = json.get(SPECIES); |
196 | 0 | if (o != null) |
197 | { | |
198 | 0 | species = o.toString(); |
199 | } | |
200 | } | |
201 | 0 | return species; |
202 | } | |
203 | ||
204 | /** | |
205 | * Calls the /lookup/id rest service and returns the response as a Map<String, | |
206 | * Object>, or null if any error | |
207 | * | |
208 | * @param identifier | |
209 | * @param objectType | |
210 | * (optional) | |
211 | * @return | |
212 | */ | |
213 | 0 | @SuppressWarnings("unchecked") |
214 | protected Map<String, Object> getResult(String identifier, | |
215 | String objectType) | |
216 | { | |
217 | 0 | List<String> ids = Arrays.asList(new String[] { identifier }); |
218 | ||
219 | 0 | try |
220 | { | |
221 | 0 | return (Map<String, Object>) getJSON(getUrl(identifier, objectType), |
222 | ids, -1, MODE_MAP, null); | |
223 | } catch (IOException | ParseException e) | |
224 | { | |
225 | 0 | jalview.bin.Console.errPrintln("Error parsing " + identifier |
226 | + " lookup response " + e.getMessage()); | |
227 | 0 | return null; |
228 | } | |
229 | } | |
230 | ||
231 | /** | |
232 | * Calls the /lookup/id rest service for the given id, and if successful, | |
233 | * parses and returns the gene's chromosomal coordinates | |
234 | * | |
235 | * @param geneId | |
236 | * @return | |
237 | */ | |
238 | 0 | public GeneLociI getGeneLoci(String geneId) |
239 | { | |
240 | 0 | return parseGeneLoci(getResult(geneId, OBJECT_TYPE_GENE)); |
241 | } | |
242 | ||
243 | /** | |
244 | * Parses the /lookup/id response for species, asssembly_name, | |
245 | * seq_region_name, start, end and returns an object that wraps them, or null | |
246 | * if unsuccessful | |
247 | * | |
248 | * @param json | |
249 | * @return | |
250 | */ | |
251 | 0 | GeneLociI parseGeneLoci(Map<String, Object> json) |
252 | { | |
253 | 0 | if (json == null) |
254 | { | |
255 | 0 | return null; |
256 | } | |
257 | ||
258 | 0 | try |
259 | { | |
260 | 0 | final String species = json.get("species").toString(); |
261 | 0 | final String assembly = json.get("assembly_name").toString(); |
262 | 0 | final String chromosome = json.get("seq_region_name").toString(); |
263 | 0 | String strand = json.get("strand").toString(); |
264 | 0 | int start = Integer.parseInt(json.get("start").toString()); |
265 | 0 | int end = Integer.parseInt(json.get("end").toString()); |
266 | 0 | int fromEnd = end - start + 1; |
267 | 0 | boolean reverseStrand = "-1".equals(strand); |
268 | 0 | int toStart = reverseStrand ? end : start; |
269 | 0 | int toEnd = reverseStrand ? start : end; |
270 | 0 | List<int[]> fromRange = Collections |
271 | .singletonList(new int[] | |
272 | { 1, fromEnd }); | |
273 | 0 | List<int[]> toRange = Collections |
274 | .singletonList(new int[] | |
275 | { toStart, toEnd }); | |
276 | 0 | final Mapping map = new Mapping( |
277 | new MapList(fromRange, toRange, 1, 1)); | |
278 | 0 | return new GeneLocus(species == null ? "" : species, assembly, |
279 | chromosome, map); | |
280 | } catch (NullPointerException | NumberFormatException e) | |
281 | { | |
282 | 0 | Console.error("Error looking up gene loci: " + e.getMessage()); |
283 | 0 | e.printStackTrace(); |
284 | } | |
285 | 0 | return null; |
286 | } | |
287 | ||
288 | } |