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.UniprotEntry;
32 import jalview.datamodel.UniprotFile;
33 import jalview.ws.ebi.EBIFetchClient;
34 import jalview.ws.seqfetcher.DbSourceProxyImpl;
37 import java.io.FileReader;
38 import java.io.Reader;
40 import java.util.ArrayList;
41 import java.util.Vector;
43 import org.exolab.castor.mapping.Mapping;
44 import org.exolab.castor.xml.Unmarshaller;
46 import com.stevesoft.pat.Regex;
52 public class Uniprot extends DbSourceProxyImpl
54 private static final String BAR_DELIMITER = "|";
57 * Castor mapping loaded from uniprot_mapping.xml
59 private static Mapping map;
72 * @see jalview.ws.DbSourceProxy#getAccessionSeparator()
75 public String getAccessionSeparator()
83 * @see jalview.ws.DbSourceProxy#getAccessionValidator()
86 public Regex getAccessionValidator()
88 return new Regex("([A-Z]+[0-9]+[A-Z0-9]+|[A-Z0-9]+_[A-Z0-9]+)");
94 * @see jalview.ws.DbSourceProxy#getDbSource()
97 public String getDbSource()
99 return DBRefSource.UNIPROT;
105 * @see jalview.ws.DbSourceProxy#getDbVersion()
108 public String getDbVersion()
110 return "0"; // we really don't know what version we're on.
114 * Reads a file containing the reply to the EBI Fetch Uniprot data query,
115 * unmarshals it to a UniprotFile object, and returns the list of UniprotEntry
116 * data models (mapped from <entry> elements)
121 public Vector<UniprotEntry> getUniprotEntries(Reader fileReader)
123 UniprotFile uni = new UniprotFile();
128 // 1. Load the mapping information from the file
129 map = new Mapping(uni.getClass().getClassLoader());
130 URL url = getClass().getResource("/uniprot_mapping.xml");
131 map.loadMapping(url);
134 // 2. Unmarshal the data
135 Unmarshaller unmar = new Unmarshaller(uni);
136 unmar.setIgnoreExtraElements(true);
137 unmar.setMapping(map);
138 if (fileReader != null)
140 uni = (UniprotFile) unmar.unmarshal(fileReader);
142 } catch (Exception e)
144 System.out.println("Error getUniprotEntries() " + e);
147 return uni.getUniprotEntries();
153 * @see jalview.ws.DbSourceProxy#getSequenceRecords(java.lang.String[])
156 public AlignmentI getSequenceRecords(String queries) throws Exception
161 queries = queries.toUpperCase().replaceAll(
162 "(UNIPROT\\|?|UNIPROT_|UNIREF\\d+_|UNIREF\\d+\\|?)", "");
163 AlignmentI al = null;
164 EBIFetchClient ebi = new EBIFetchClient();
165 // uniprotxml parameter required since december 2007
166 // uniprotkb dbname changed introduced december 2008
167 File file = ebi.fetchDataAsFile("uniprotkb:" + queries, "uniprotxml",
169 Vector<UniprotEntry> entries = getUniprotEntries(
170 new FileReader(file));
174 ArrayList<SequenceI> seqs = new ArrayList<SequenceI>();
175 for (UniprotEntry entry : entries)
177 seqs.add(uniprotEntryToSequenceI(entry));
179 al = new Alignment(seqs.toArray(new SequenceI[0]));
184 } catch (Exception e)
195 * @return SequenceI instance created from the UniprotEntry instance
197 public SequenceI uniprotEntryToSequenceI(UniprotEntry entry)
199 String id = getUniprotEntryId(entry);
200 SequenceI sequence = new Sequence(id,
201 entry.getUniprotSequence().getContent());
202 sequence.setDescription(getUniprotEntryDescription(entry));
204 final String dbVersion = getDbVersion();
205 ArrayList<DBRefEntry> dbRefs = new ArrayList<DBRefEntry>();
206 for (String accessionId : entry.getAccession())
208 DBRefEntry dbRef = new DBRefEntry(DBRefSource.UNIPROT, dbVersion,
211 // mark dbRef as a primary reference for this sequence
215 Vector<PDBEntry> onlyPdbEntries = new Vector<PDBEntry>();
216 for (PDBEntry pdb : entry.getDbReference())
218 DBRefEntry dbr = new DBRefEntry();
219 dbr.setSource(pdb.getType());
220 dbr.setAccessionId(pdb.getId());
221 dbr.setVersion(DBRefSource.UNIPROT + ":" + dbVersion);
223 if ("PDB".equals(pdb.getType()))
225 onlyPdbEntries.addElement(pdb);
227 if ("EMBL".equals(pdb.getType()))
229 // look for a CDS reference and add it, too.
230 String cdsId = (String) pdb.getProperty("protein sequence ID");
231 if (cdsId != null && cdsId.trim().length() > 0)
234 String[] vrs = cdsId.split("\\.");
235 dbr = new DBRefEntry(DBRefSource.EMBLCDS, vrs.length > 1 ? vrs[1]
236 : DBRefSource.UNIPROT + ":" + dbVersion, vrs[0]);
240 if ("Ensembl".equals(pdb.getType()))
243 * <dbReference type="Ensembl" id="ENST00000321556">
244 * <molecule id="Q9BXM7-1"/>
245 * <property type="protein sequence ID" value="ENSP00000364204"/>
246 * <property type="gene ID" value="ENSG00000158828"/>
249 String cdsId = (String) pdb.getProperty("protein sequence ID");
250 if (cdsId != null && cdsId.trim().length() > 0)
252 dbr = new DBRefEntry(DBRefSource.ENSEMBL,
253 DBRefSource.UNIPROT + ":" + dbVersion, cdsId.trim());
261 sequence.setPDBId(onlyPdbEntries);
262 if (entry.getFeature() != null)
264 for (SequenceFeature sf : entry.getFeature())
266 sf.setFeatureGroup("Uniprot");
267 sequence.addSequenceFeature(sf);
270 for (DBRefEntry dbr : dbRefs)
272 sequence.addDBRef(dbr);
281 * @return protein name(s) delimited by a white space character
283 public static String getUniprotEntryDescription(UniprotEntry entry)
285 StringBuilder desc = new StringBuilder(32);
286 if (entry.getProtein() != null && entry.getProtein().getName() != null)
288 boolean first = true;
289 for (String nm : entry.getProtein().getName())
299 return desc.toString();
306 * @return The accession id(s) and name(s) delimited by '|'.
308 public static String getUniprotEntryId(UniprotEntry entry)
310 StringBuilder name = new StringBuilder(32);
311 // name.append("UniProt/Swiss-Prot");
312 // use 'canonicalised' name for optimal id matching
313 name.append(DBRefSource.UNIPROT);
314 for (String accessionId : entry.getAccession())
316 name.append(BAR_DELIMITER);
317 name.append(accessionId);
319 for (String n : entry.getName())
321 name.append(BAR_DELIMITER);
324 return name.toString();
330 * @see jalview.ws.DbSourceProxy#isValidReference(java.lang.String)
333 public boolean isValidReference(String accession)
335 // TODO: make the following a standard validator
336 return (accession == null || accession.length() < 2) ? false
337 : getAccessionValidator().search(accession);
341 * return LDHA_CHICK uniprot entry
344 public String getTestQuery()
350 public String getDbName()
352 return "Uniprot"; // getDbSource();