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.ws.dbsources;
23 import jalview.datamodel.Alignment;
24 import jalview.datamodel.AlignmentI;
25 import jalview.datamodel.DBRefEntry;
26 import jalview.datamodel.DBRefSource;
27 import jalview.datamodel.PDBEntry;
28 import jalview.datamodel.Sequence;
29 import jalview.datamodel.SequenceFeature;
30 import jalview.datamodel.SequenceI;
31 import jalview.datamodel.xdb.uniprot.UniprotEntry;
32 import jalview.datamodel.xdb.uniprot.UniprotFeature;
33 import jalview.datamodel.xdb.uniprot.UniprotFile;
34 import jalview.ws.ebi.EBIFetchClient;
35 import jalview.ws.seqfetcher.DbSourceProxyImpl;
38 import java.io.FileReader;
39 import java.io.Reader;
41 import java.util.ArrayList;
42 import java.util.Vector;
44 import org.exolab.castor.mapping.Mapping;
45 import org.exolab.castor.xml.Unmarshaller;
47 import com.stevesoft.pat.Regex;
53 public class Uniprot extends DbSourceProxyImpl
55 private static final String BAR_DELIMITER = "|";
58 * Castor mapping loaded from uniprot_mapping.xml
60 private static Mapping map;
73 * @see jalview.ws.DbSourceProxy#getAccessionSeparator()
76 public String getAccessionSeparator()
84 * @see jalview.ws.DbSourceProxy#getAccessionValidator()
87 public Regex getAccessionValidator()
89 return new Regex("([A-Z]+[0-9]+[A-Z0-9]+|[A-Z0-9]+_[A-Z0-9]+)");
95 * @see jalview.ws.DbSourceProxy#getDbSource()
98 public String getDbSource()
100 return DBRefSource.UNIPROT;
106 * @see jalview.ws.DbSourceProxy#getDbVersion()
109 public String getDbVersion()
111 return "0"; // we really don't know what version we're on.
115 * Reads a file containing the reply to the EBI Fetch Uniprot data query,
116 * unmarshals it to a UniprotFile object, and returns the list of UniprotEntry
117 * data models (mapped from <entry> elements)
122 public Vector<UniprotEntry> getUniprotEntries(Reader fileReader)
124 UniprotFile uni = new UniprotFile();
129 // 1. Load the mapping information from the file
130 map = new Mapping(uni.getClass().getClassLoader());
131 URL url = getClass().getResource("/uniprot_mapping.xml");
132 map.loadMapping(url);
135 // 2. Unmarshal the data
136 Unmarshaller unmar = new Unmarshaller(uni);
137 unmar.setIgnoreExtraElements(true);
138 unmar.setMapping(map);
139 if (fileReader != null)
141 uni = (UniprotFile) unmar.unmarshal(fileReader);
143 } catch (Exception e)
145 System.out.println("Error getUniprotEntries() " + e);
148 return uni.getUniprotEntries();
154 * @see jalview.ws.DbSourceProxy#getSequenceRecords(java.lang.String[])
157 public AlignmentI getSequenceRecords(String queries) throws Exception
162 queries = queries.toUpperCase().replaceAll(
163 "(UNIPROT\\|?|UNIPROT_|UNIREF\\d+_|UNIREF\\d+\\|?)", "");
164 AlignmentI al = null;
165 EBIFetchClient ebi = new EBIFetchClient();
166 // uniprotxml parameter required since december 2007
167 // uniprotkb dbname changed introduced december 2008
168 File file = ebi.fetchDataAsFile("uniprotkb:" + queries, "uniprotxml",
170 Vector<UniprotEntry> entries = getUniprotEntries(
171 new FileReader(file));
175 ArrayList<SequenceI> seqs = new ArrayList<SequenceI>();
176 for (UniprotEntry entry : entries)
178 seqs.add(uniprotEntryToSequenceI(entry));
180 al = new Alignment(seqs.toArray(new SequenceI[0]));
185 } catch (Exception e)
196 * @return SequenceI instance created from the UniprotEntry instance
198 public SequenceI uniprotEntryToSequenceI(UniprotEntry entry)
200 String id = getUniprotEntryId(entry);
201 SequenceI sequence = new Sequence(id,
202 entry.getUniprotSequence().getContent());
203 sequence.setDescription(getUniprotEntryDescription(entry));
205 final String dbVersion = getDbVersion();
206 ArrayList<DBRefEntry> dbRefs = new ArrayList<DBRefEntry>();
207 for (String accessionId : entry.getAccession())
209 DBRefEntry dbRef = new DBRefEntry(DBRefSource.UNIPROT, dbVersion,
212 // mark dbRef as a primary reference for this sequence
216 Vector<PDBEntry> onlyPdbEntries = new Vector<PDBEntry>();
217 for (PDBEntry pdb : entry.getDbReference())
219 DBRefEntry dbr = new DBRefEntry();
220 dbr.setSource(pdb.getType());
221 dbr.setAccessionId(pdb.getId());
222 dbr.setVersion(DBRefSource.UNIPROT + ":" + dbVersion);
224 if ("PDB".equals(pdb.getType()))
226 onlyPdbEntries.addElement(pdb);
228 if ("EMBL".equals(pdb.getType()))
230 // look for a CDS reference and add it, too.
231 String cdsId = (String) pdb.getProperty("protein sequence ID");
232 if (cdsId != null && cdsId.trim().length() > 0)
235 String[] vrs = cdsId.split("\\.");
236 dbr = new DBRefEntry(DBRefSource.EMBLCDS, vrs.length > 1 ? vrs[1]
237 : DBRefSource.UNIPROT + ":" + dbVersion, vrs[0]);
241 if ("Ensembl".equals(pdb.getType()))
244 * <dbReference type="Ensembl" id="ENST00000321556">
245 * <molecule id="Q9BXM7-1"/>
246 * <property type="protein sequence ID" value="ENSP00000364204"/>
247 * <property type="gene ID" value="ENSG00000158828"/>
250 String cdsId = (String) pdb.getProperty("protein sequence ID");
251 if (cdsId != null && cdsId.trim().length() > 0)
253 dbr = new DBRefEntry(DBRefSource.ENSEMBL,
254 DBRefSource.UNIPROT + ":" + dbVersion, cdsId.trim());
261 sequence.setPDBId(onlyPdbEntries);
262 if (entry.getFeature() != null)
264 for (UniprotFeature uf : entry.getFeature())
266 SequenceFeature copy = new SequenceFeature(uf.getType(),
267 uf.getDescription(), uf.getBegin(), uf.getEnd(), "Uniprot");
268 copy.setStatus(uf.getStatus());
269 sequence.addSequenceFeature(copy);
272 for (DBRefEntry dbr : dbRefs)
274 sequence.addDBRef(dbr);
283 * @return protein name(s) delimited by a white space character
285 public static String getUniprotEntryDescription(UniprotEntry entry)
287 StringBuilder desc = new StringBuilder(32);
288 if (entry.getProtein() != null && entry.getProtein().getName() != null)
290 boolean first = true;
291 for (String nm : entry.getProtein().getName())
301 return desc.toString();
308 * @return The accession id(s) and name(s) delimited by '|'.
310 public static String getUniprotEntryId(UniprotEntry entry)
312 StringBuilder name = new StringBuilder(32);
313 // name.append("UniProt/Swiss-Prot");
314 // use 'canonicalised' name for optimal id matching
315 name.append(DBRefSource.UNIPROT);
316 for (String accessionId : entry.getAccession())
318 name.append(BAR_DELIMITER);
319 name.append(accessionId);
321 for (String n : entry.getName())
323 name.append(BAR_DELIMITER);
326 return name.toString();
332 * @see jalview.ws.DbSourceProxy#isValidReference(java.lang.String)
335 public boolean isValidReference(String accession)
337 // TODO: make the following a standard validator
338 return (accession == null || accession.length() < 2) ? false
339 : getAccessionValidator().search(accession);
343 * return LDHA_CHICK uniprot entry
346 public String getTestQuery()
352 public String getDbName()
354 return "Uniprot"; // getDbSource();