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.seqfetcher.DbSourceProxyImpl;
36 import java.io.InputStream;
37 import java.io.InputStreamReader;
38 import java.io.Reader;
40 import java.net.URLConnection;
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;
166 String downloadstring = "http://www.uniprot.org/uniprot/" + queries
169 URLConnection urlconn = null;
171 url = new URL(downloadstring);
172 urlconn = url.openConnection();
173 InputStream istr = urlconn.getInputStream();
174 Vector<UniprotEntry> entries = getUniprotEntries(
175 new InputStreamReader(istr, "UTF-8"));
179 ArrayList<SequenceI> seqs = new ArrayList<>();
180 for (UniprotEntry entry : entries)
182 seqs.add(uniprotEntryToSequenceI(entry));
184 al = new Alignment(seqs.toArray(new SequenceI[0]));
189 } catch (Exception e)
202 * @return SequenceI instance created from the UniprotEntry instance
204 public SequenceI uniprotEntryToSequenceI(UniprotEntry entry)
206 String id = getUniprotEntryId(entry);
207 SequenceI sequence = new Sequence(id,
208 entry.getUniprotSequence().getContent());
209 sequence.setDescription(getUniprotEntryDescription(entry));
211 final String dbVersion = getDbVersion();
212 ArrayList<DBRefEntry> dbRefs = new ArrayList<>();
213 for (String accessionId : entry.getAccession())
215 DBRefEntry dbRef = new DBRefEntry(DBRefSource.UNIPROT, dbVersion,
218 // mark dbRef as a primary reference for this sequence
222 Vector<PDBEntry> onlyPdbEntries = new Vector<>();
223 for (PDBEntry pdb : entry.getDbReference())
225 DBRefEntry dbr = new DBRefEntry();
226 dbr.setSource(pdb.getType());
227 dbr.setAccessionId(pdb.getId());
228 dbr.setVersion(DBRefSource.UNIPROT + ":" + dbVersion);
230 if ("PDB".equals(pdb.getType()))
232 onlyPdbEntries.addElement(pdb);
234 if ("EMBL".equals(pdb.getType()))
236 // look for a CDS reference and add it, too.
237 String cdsId = (String) pdb.getProperty("protein sequence ID");
238 if (cdsId != null && cdsId.trim().length() > 0)
241 String[] vrs = cdsId.split("\\.");
242 dbr = new DBRefEntry(DBRefSource.EMBLCDS, vrs.length > 1 ? vrs[1]
243 : DBRefSource.UNIPROT + ":" + dbVersion, vrs[0]);
247 if ("Ensembl".equals(pdb.getType()))
250 * <dbReference type="Ensembl" id="ENST00000321556">
251 * <molecule id="Q9BXM7-1"/>
252 * <property type="protein sequence ID" value="ENSP00000364204"/>
253 * <property type="gene ID" value="ENSG00000158828"/>
256 String cdsId = (String) pdb.getProperty("protein sequence ID");
257 if (cdsId != null && cdsId.trim().length() > 0)
259 dbr = new DBRefEntry(DBRefSource.ENSEMBL,
260 DBRefSource.UNIPROT + ":" + dbVersion, cdsId.trim());
267 sequence.setPDBId(onlyPdbEntries);
268 if (entry.getFeature() != null)
270 for (UniprotFeature uf : entry.getFeature())
272 SequenceFeature copy = new SequenceFeature(uf.getType(),
273 uf.getDescription(), uf.getBegin(), uf.getEnd(), "Uniprot");
274 copy.setStatus(uf.getStatus());
275 sequence.addSequenceFeature(copy);
278 for (DBRefEntry dbr : dbRefs)
280 sequence.addDBRef(dbr);
289 * @return protein name(s) delimited by a white space character
291 public static String getUniprotEntryDescription(UniprotEntry entry)
293 StringBuilder desc = new StringBuilder(32);
294 if (entry.getProtein() != null && entry.getProtein().getName() != null)
296 boolean first = true;
297 for (String nm : entry.getProtein().getName())
307 return desc.toString();
314 * @return The accession id(s) and name(s) delimited by '|'.
316 public static String getUniprotEntryId(UniprotEntry entry)
318 StringBuilder name = new StringBuilder(32);
319 // name.append("UniProt/Swiss-Prot");
320 // use 'canonicalised' name for optimal id matching
321 name.append(DBRefSource.UNIPROT);
322 for (String accessionId : entry.getAccession())
324 name.append(BAR_DELIMITER);
325 name.append(accessionId);
327 for (String n : entry.getName())
329 name.append(BAR_DELIMITER);
332 return name.toString();
338 * @see jalview.ws.DbSourceProxy#isValidReference(java.lang.String)
341 public boolean isValidReference(String accession)
343 // TODO: make the following a standard validator
344 return (accession == null || accession.length() < 2) ? false
345 : getAccessionValidator().search(accession);
349 * return LDHA_CHICK uniprot entry
352 public String getTestQuery()
358 public String getDbName()
360 return "Uniprot"; // getDbSource();