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.bin.Cache;
24 import jalview.datamodel.Alignment;
25 import jalview.datamodel.AlignmentI;
26 import jalview.datamodel.DBRefEntry;
27 import jalview.datamodel.DBRefSource;
28 import jalview.datamodel.PDBEntry;
29 import jalview.datamodel.Sequence;
30 import jalview.datamodel.SequenceFeature;
31 import jalview.datamodel.SequenceI;
32 import jalview.schemes.ResidueProperties;
33 import jalview.util.StringUtils;
34 import jalview.ws.seqfetcher.DbSourceProxyImpl;
35 import jalview.xml.binding.uniprot.DbReferenceType;
36 import jalview.xml.binding.uniprot.Entry;
37 import jalview.xml.binding.uniprot.FeatureType;
38 import jalview.xml.binding.uniprot.LocationType;
39 import jalview.xml.binding.uniprot.PositionType;
40 import jalview.xml.binding.uniprot.PropertyType;
42 import java.io.InputStream;
44 import java.net.URLConnection;
45 import java.util.ArrayList;
46 import java.util.List;
47 import java.util.Vector;
49 import javax.xml.bind.JAXBContext;
50 import javax.xml.bind.JAXBException;
51 import javax.xml.stream.FactoryConfigurationError;
52 import javax.xml.stream.XMLInputFactory;
53 import javax.xml.stream.XMLStreamException;
54 import javax.xml.stream.XMLStreamReader;
56 import com.stevesoft.pat.Regex;
59 * This class queries the Uniprot database for sequence data, unmarshals the
60 * returned XML, and converts it to Jalview Sequence records (including attached
61 * database references and sequence features)
66 public class Uniprot extends DbSourceProxyImpl
68 private static final String DEFAULT_UNIPROT_DOMAIN = "https://www.uniprot.org";
70 private static final String BAR_DELIMITER = "|";
80 private String getDomain()
82 return Cache.getDefault("UNIPROT_DOMAIN", DEFAULT_UNIPROT_DOMAIN);
88 * @see jalview.ws.DbSourceProxy#getAccessionSeparator()
91 public String getAccessionSeparator()
99 * @see jalview.ws.DbSourceProxy#getAccessionValidator()
102 public Regex getAccessionValidator()
104 return new Regex("([A-Z]+[0-9]+[A-Z0-9]+|[A-Z0-9]+_[A-Z0-9]+)");
110 * @see jalview.ws.DbSourceProxy#getDbSource()
113 public String getDbSource()
115 return DBRefSource.UNIPROT;
121 * @see jalview.ws.DbSourceProxy#getDbVersion()
124 public String getDbVersion()
126 return "0"; // we really don't know what version we're on.
132 * @see jalview.ws.DbSourceProxy#getSequenceRecords(java.lang.String[])
135 public AlignmentI getSequenceRecords(String queries) throws Exception
140 queries = queries.toUpperCase().replaceAll(
141 "(UNIPROT\\|?|UNIPROT_|UNIREF\\d+_|UNIREF\\d+\\|?)", "");
142 AlignmentI al = null;
144 String downloadstring = getDomain() + "/uniprot/" + queries
147 URL url = new URL(downloadstring);
148 URLConnection urlconn = url.openConnection();
149 InputStream istr = urlconn.getInputStream();
150 List<Entry> entries = getUniprotEntries(istr);
153 List<SequenceI> seqs = new ArrayList<>();
154 for (Entry entry : entries)
156 seqs.add(uniprotEntryToSequence(entry));
158 al = new Alignment(seqs.toArray(new SequenceI[seqs.size()]));
163 } catch (Exception e)
173 * Converts an Entry object (bound from Uniprot XML) to a Jalview Sequence
178 SequenceI uniprotEntryToSequence(Entry entry)
180 String id = getUniprotEntryId(entry);
182 * Sequence should not include any whitespace, but JAXB leaves these in
184 String seqString = entry.getSequence().getValue().replaceAll("\\s*",
187 SequenceI sequence = new Sequence(id,
189 sequence.setDescription(getUniprotEntryDescription(entry));
192 * add a 'self' DBRefEntry for each accession
194 final String dbVersion = getDbVersion();
195 List<DBRefEntry> dbRefs = new ArrayList<>();
196 for (String accessionId : entry.getAccession())
198 DBRefEntry dbRef = new DBRefEntry(DBRefSource.UNIPROT, dbVersion,
204 * add a DBRefEntry for each dbReference element in the XML;
205 * also add a PDBEntry if type="PDB";
206 * also add an EMBLCDS dbref if protein sequence id is given
207 * also add an Ensembl dbref " " " " " "
209 Vector<PDBEntry> pdbRefs = new Vector<>();
210 for (DbReferenceType dbref : entry.getDbReference())
212 String type = dbref.getType();
213 DBRefEntry dbr = new DBRefEntry(type,
214 DBRefSource.UNIPROT + ":" + dbVersion, dbref.getId());
216 if ("PDB".equals(type))
218 pdbRefs.add(new PDBEntry(dbr));
220 if ("EMBL".equals(type))
223 * e.g. Uniprot accession Q9BXM7 has
224 * <dbReference type="EMBL" id="M19359">
225 * <property type="protein sequence ID" value="AAA40981.1"/>
226 * <property type="molecule type" value="Genomic_DNA"/>
229 String cdsId = getProperty(dbref.getProperty(),
230 "protein sequence ID");
231 if (cdsId != null && cdsId.trim().length() > 0)
234 String[] vrs = cdsId.split("\\.");
235 String version = vrs.length > 1 ? vrs[1]
236 : DBRefSource.UNIPROT + ":" + dbVersion;
237 dbr = new DBRefEntry(DBRefSource.EMBLCDS, version, vrs[0]);
241 if ("Ensembl".equals(type))
244 * e.g. Uniprot accession Q9BXM7 has
245 * <dbReference type="Ensembl" id="ENST00000321556">
246 * <molecule id="Q9BXM7-1"/>
247 * <property type="protein sequence ID" value="ENSP00000364204"/>
248 * <property type="gene ID" value="ENSG00000158828"/>
251 String cdsId = getProperty(dbref.getProperty(),
252 "protein sequence ID");
253 if (cdsId != null && cdsId.trim().length() > 0)
255 dbr = new DBRefEntry(DBRefSource.ENSEMBL,
256 DBRefSource.UNIPROT + ":" + dbVersion, cdsId.trim());
263 * create features; they have either begin and end, or position, in XML
265 sequence.setPDBId(pdbRefs);
266 if (entry.getFeature() != null)
268 for (FeatureType uf : entry.getFeature())
270 LocationType location = uf.getLocation();
273 if (location.getPosition() != null)
275 start = location.getPosition().getPosition().intValue();
280 start = location.getBegin().getPosition().intValue();
281 end = location.getEnd().getPosition().intValue();
283 SequenceFeature sf = new SequenceFeature(uf.getType(),
284 getDescription(uf), start, end, "Uniprot");
285 sf.setStatus(uf.getStatus());
286 sequence.addSequenceFeature(sf);
289 for (DBRefEntry dbr : dbRefs)
291 sequence.addDBRef(dbr);
297 * A helper method that builds a sequence feature description
302 static String getDescription(FeatureType feature)
304 String orig = feature.getOriginal();
305 List<String> variants = feature.getVariation();
306 StringBuilder sb = new StringBuilder();
309 * append variant in standard format if present
311 * multiple variants are split over lines using <br>
313 boolean asHtml = false;
314 if (orig != null && !orig.isEmpty() && variants != null
315 && !variants.isEmpty())
318 for (String var : variants)
320 // TODO proper HGVS nomenclature for delins structural variations
321 // http://varnomen.hgvs.org/recommendations/protein/variant/delins/
322 // for now we are pragmatic - any orig/variant sequence longer than
323 // three characters is shown with single-character notation rather than
324 // three-letter notation
326 if (orig.length() < 4)
328 for (int c = 0, clen = orig.length(); c < clen; c++)
330 char origchar = orig.charAt(c);
331 String orig3 = ResidueProperties.aa2Triplet.get("" + origchar);
332 sb.append(orig3 == null ? origchar
333 : StringUtils.toSentenceCase(orig3));
341 LocationType location = feature.getLocation();
342 PositionType start = location.getPosition() == null
343 ? location.getBegin()
344 : location.getPosition();
345 sb.append(Integer.toString(start.getPosition().intValue()));
347 if (var.length() < 4)
349 for (int c = 0, clen = var.length(); c < clen; c++)
351 char varchar = var.charAt(c);
352 String var3 = ResidueProperties.aa2Triplet.get("" + varchar);
354 sb.append(var3 != null ? StringUtils.toSentenceCase(var3)
362 if (++p != variants.size())
364 sb.append("<br/> ");
373 String description = feature.getDescription();
374 if (description != null)
376 sb.append(description);
380 sb.insert(0, "<html>");
381 sb.append("</html>");
384 return sb.toString();
388 * A helper method that searches the list of properties for one with the given
389 * key, and if found returns the property value, else returns null
395 static String getProperty(List<PropertyType> properties, String key)
398 if (properties != null)
400 for (PropertyType prop : properties)
402 if (key.equals(prop.getType()))
404 value = prop.getValue();
413 * Extracts xml element entry/protein/recommendedName/fullName
418 static String getUniprotEntryDescription(Entry entry)
421 if (entry.getProtein() != null
422 && entry.getProtein().getRecommendedName() != null)
424 // fullName is mandatory if recommendedName is present
425 desc = entry.getProtein().getRecommendedName().getFullName()
432 * Constructs a sequence id by concatenating all entry/name elements with '|'
438 static String getUniprotEntryId(Entry entry)
440 StringBuilder name = new StringBuilder(32);
441 for (String n : entry.getName())
443 if (name.length() > 0)
445 name.append(BAR_DELIMITER);
449 return name.toString();
455 * @see jalview.ws.DbSourceProxy#isValidReference(java.lang.String)
458 public boolean isValidReference(String accession)
460 // TODO: make the following a standard validator
461 return (accession == null || accession.length() < 2) ? false
462 : getAccessionValidator().search(accession);
466 * return LDHA_CHICK uniprot entry
469 public String getTestQuery()
475 public String getDbName()
477 return "Uniprot"; // getDbSource();
487 * Reads the reply to the EBI Fetch Uniprot data query, unmarshals it to an
488 * Uniprot object, and returns the enclosed Entry objects, or null on any
494 public List<Entry> getUniprotEntries(InputStream is)
496 List<Entry> entries = null;
499 JAXBContext jc = JAXBContext
500 .newInstance("jalview.xml.binding.uniprot");
501 XMLStreamReader streamReader = XMLInputFactory.newInstance()
502 .createXMLStreamReader(is);
503 javax.xml.bind.Unmarshaller um = jc.createUnmarshaller();
504 jalview.xml.binding.uniprot.Uniprot uniprot = (jalview.xml.binding.uniprot.Uniprot) um.unmarshal(streamReader);
505 if (uniprot != null && !uniprot.getEntry().isEmpty())
507 entries = uniprot.getEntry();
509 } catch (JAXBException | XMLStreamException
510 | FactoryConfigurationError e)