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.
23 import jalview.datamodel.DBRefEntry;
24 import jalview.datamodel.DBRefSource;
25 import jalview.datamodel.PDBEntry;
26 import jalview.datamodel.SequenceI;
28 import java.util.ArrayList;
29 import java.util.HashMap;
30 import java.util.HashSet;
31 import java.util.Hashtable;
32 import java.util.List;
36 import com.stevesoft.pat.Regex;
39 * Utilities for handling DBRef objects and their collections.
41 public class DBRefUtils
44 * lookup from lower-case form of a name to its canonical (standardised) form
46 private static Map<String, String> canonicalSourceNameLookup = new HashMap<String, String>();
48 private static Map<String, String> dasCoordinateSystemsLookup = new HashMap<String, String>();
52 // TODO load these from a resource file?
53 canonicalSourceNameLookup.put("uniprotkb/swiss-prot",
55 canonicalSourceNameLookup.put("uniprotkb/trembl", DBRefSource.UNIPROT);
57 // Ensembl values for dbname in xref REST service:
58 canonicalSourceNameLookup.put("uniprot/sptrembl", DBRefSource.UNIPROT);
59 canonicalSourceNameLookup.put("uniprot/swissprot", DBRefSource.UNIPROT);
61 canonicalSourceNameLookup.put("pdb", DBRefSource.PDB);
62 canonicalSourceNameLookup.put("ensembl", DBRefSource.ENSEMBL);
63 // Ensembl Gn and Tr are for Ensembl genomic and transcript IDs as served
65 canonicalSourceNameLookup.put("ensembl-tr", DBRefSource.ENSEMBL);
66 canonicalSourceNameLookup.put("ensembl-gn", DBRefSource.ENSEMBL);
68 // Make sure we have lowercase entries for all canonical string lookups
69 Set<String> keys = canonicalSourceNameLookup.keySet();
72 canonicalSourceNameLookup.put(k.toLowerCase(),
73 canonicalSourceNameLookup.get(k));
76 dasCoordinateSystemsLookup.put("pdbresnum", DBRefSource.PDB);
77 dasCoordinateSystemsLookup.put("uniprot", DBRefSource.UNIPROT);
78 dasCoordinateSystemsLookup.put("embl", DBRefSource.EMBL);
79 // dasCoordinateSystemsLookup.put("embl", DBRefSource.EMBLCDS);
83 * Returns those DBRefEntry objects whose source identifier (once converted to
84 * Jalview's canonical form) is in the list of sources to search for. Returns
85 * null if no matches found.
88 * DBRefEntry objects to search
90 * array of sources to select
93 public static DBRefEntry[] selectRefs(DBRefEntry[] dbrefs,
96 if (dbrefs == null || sources == null)
100 HashSet<String> srcs = new HashSet<String>();
101 for (String src : sources)
106 List<DBRefEntry> res = new ArrayList<DBRefEntry>();
107 for (DBRefEntry dbr : dbrefs)
109 String source = getCanonicalName(dbr.getSource());
110 if (srcs.contains(source))
118 DBRefEntry[] reply = new DBRefEntry[res.size()];
119 return res.toArray(reply);
125 * isDasCoordinateSystem
131 * @return boolean true if Source DBRefEntry is compatible with DAS
132 * CoordinateSystem name
135 public static boolean isDasCoordinateSystem(String string,
136 DBRefEntry dBRefEntry)
138 if (string == null || dBRefEntry == null)
142 String coordsys = dasCoordinateSystemsLookup.get(string.toLowerCase());
143 return coordsys == null ? false : coordsys.equals(dBRefEntry
148 * look up source in an internal list of database reference sources and return
149 * the canonical jalview name for the source, or the original string if it has
153 * @return canonical jalview source (one of jalview.datamodel.DBRefSource.*)
156 public static String getCanonicalName(String source)
162 String canonical = canonicalSourceNameLookup.get(source.toLowerCase());
163 return canonical == null ? source : canonical;
167 * Returns a (possibly empty) list of those references that match the given
168 * entry. Currently uses a comparator which matches if
170 * <li>database sources are the same</li>
171 * <li>accession ids are the same</li>
172 * <li>both have no mapping, or the mappings are the same</li>
176 * Set of references to search
181 public static List<DBRefEntry> searchRefs(DBRefEntry[] ref,
184 return searchRefs(ref, entry,
185 matchDbAndIdAndEitherMapOrEquivalentMapList);
189 * Returns a list of those references that match the given accession id
191 * <li>database sources are the same</li>
192 * <li>accession ids are the same</li>
193 * <li>both have no mapping, or the mappings are the same</li>
197 * Set of references to search
199 * accession id to match
202 public static List<DBRefEntry> searchRefs(DBRefEntry[] refs, String accId)
204 return searchRefs(refs, new DBRefEntry("", "", accId), matchId);
208 * Returns a (possibly empty) list of those references that match the given
209 * entry, according to the given comparator.
212 * an array of database references to search
214 * an entry to compare against
218 static List<DBRefEntry> searchRefs(DBRefEntry[] refs, DBRefEntry entry,
219 DbRefComp comparator)
221 List<DBRefEntry> rfs = new ArrayList<DBRefEntry>();
222 if (refs == null || entry == null)
226 for (int i = 0; i < refs.length; i++)
228 if (comparator.matches(entry, refs[i]))
238 public boolean matches(DBRefEntry refa, DBRefEntry refb);
242 * match on all non-null fields in refa
244 // TODO unused - remove?
245 public static DbRefComp matchNonNullonA = new DbRefComp()
248 public boolean matches(DBRefEntry refa, DBRefEntry refb)
250 if (refa.getSource() == null
251 || refb.getSource().equals(refa.getSource()))
253 if (refa.getVersion() == null
254 || refb.getVersion().equals(refa.getVersion()))
256 if (refa.getAccessionId() == null
257 || refb.getAccessionId().equals(refa.getAccessionId()))
259 if (refa.getMap() == null
260 || (refb.getMap() != null && refb.getMap().equals(
273 * either field is null or field matches for all of source, version, accession
276 // TODO unused - remove?
277 public static DbRefComp matchEitherNonNull = new DbRefComp()
280 public boolean matches(DBRefEntry refa, DBRefEntry refb)
282 if (nullOrEqual(refa.getSource(), refb.getSource())
283 && nullOrEqual(refa.getVersion(), refb.getVersion())
284 && nullOrEqual(refa.getAccessionId(), refb.getAccessionId())
285 && nullOrEqual(refa.getMap(), refb.getMap()))
294 * accession ID and DB must be identical. Version is ignored. Map is either
295 * not defined or is a match (or is compatible?)
297 // TODO unused - remove?
298 public static DbRefComp matchDbAndIdAndEitherMap = new DbRefComp()
301 public boolean matches(DBRefEntry refa, DBRefEntry refb)
303 if (refa.getSource() != null && refb.getSource() != null
304 && refb.getSource().equals(refa.getSource()))
306 // We dont care about version
307 if (refa.getAccessionId() != null && refb.getAccessionId() != null
308 // FIXME should be && not || here?
309 || refb.getAccessionId().equals(refa.getAccessionId()))
311 if ((refa.getMap() == null || refb.getMap() == null)
312 || (refa.getMap() != null && refb.getMap() != null && refb
313 .getMap().equals(refa.getMap())))
324 * accession ID and DB must be identical. Version is ignored. No map on either
325 * or map but no maplist on either or maplist of map on a is the complement of
326 * maplist of map on b.
328 // TODO unused - remove?
329 public static DbRefComp matchDbAndIdAndComplementaryMapList = new DbRefComp()
332 public boolean matches(DBRefEntry refa, DBRefEntry refb)
334 if (refa.getSource() != null && refb.getSource() != null
335 && refb.getSource().equals(refa.getSource()))
337 // We dont care about version
338 if (refa.getAccessionId() != null && refb.getAccessionId() != null
339 || refb.getAccessionId().equals(refa.getAccessionId()))
341 if ((refa.getMap() == null && refb.getMap() == null)
342 || (refa.getMap() != null && refb.getMap() != null))
344 if ((refb.getMap().getMap() == null && refa.getMap().getMap() == null)
345 || (refb.getMap().getMap() != null
346 && refa.getMap().getMap() != null && refb
347 .getMap().getMap().getInverse()
348 .equals(refa.getMap().getMap())))
360 * accession ID and DB must be identical. Version is ignored. No map on both
361 * or or map but no maplist on either or maplist of map on a is equivalent to
362 * the maplist of map on b.
364 // TODO unused - remove?
365 public static DbRefComp matchDbAndIdAndEquivalentMapList = new DbRefComp()
368 public boolean matches(DBRefEntry refa, DBRefEntry refb)
370 if (refa.getSource() != null && refb.getSource() != null
371 && refb.getSource().equals(refa.getSource()))
373 // We dont care about version
374 // if ((refa.getVersion()==null || refb.getVersion()==null)
375 // || refb.getVersion().equals(refa.getVersion()))
377 if (refa.getAccessionId() != null && refb.getAccessionId() != null
378 || refb.getAccessionId().equals(refa.getAccessionId()))
380 if (refa.getMap() == null && refb.getMap() == null)
384 if (refa.getMap() != null
385 && refb.getMap() != null
386 && ((refb.getMap().getMap() == null && refa.getMap()
387 .getMap() == null) || (refb.getMap().getMap() != null
388 && refa.getMap().getMap() != null && refb
389 .getMap().getMap().equals(refa.getMap().getMap()))))
400 * accession ID and DB must be identical, or null on a. Version is ignored. No
401 * map on either or map but no maplist on either or maplist of map on a is
402 * equivalent to the maplist of map on b.
404 public static DbRefComp matchDbAndIdAndEitherMapOrEquivalentMapList = new DbRefComp()
407 public boolean matches(DBRefEntry refa, DBRefEntry refb)
409 if (refa.getSource() != null && refb.getSource() != null
410 && refb.getSource().equals(refa.getSource()))
412 // We dont care about version
414 if (refa.getAccessionId() == null
415 || refa.getAccessionId().equals(refb.getAccessionId()))
417 if (refa.getMap() == null || refb.getMap() == null)
421 if ((refa.getMap() != null && refb.getMap() != null)
422 && (refb.getMap().getMap() == null && refa.getMap()
424 || (refb.getMap().getMap() != null
425 && refa.getMap().getMap() != null && (refb
426 .getMap().getMap().equals(refa.getMap().getMap()))))
437 * accession ID only must be identical.
439 public static DbRefComp matchId = new DbRefComp()
442 public boolean matches(DBRefEntry refa, DBRefEntry refb)
444 if (refa.getAccessionId() != null && refb.getAccessionId() != null
445 && refb.getAccessionId().equals(refa.getAccessionId()))
454 * Parses a DBRefEntry and adds it to the sequence, also a PDBEntry if the
457 * Used by file parsers to generate DBRefs from annotation within file (eg
464 * where to annotate with reference
465 * @return parsed version of entry that was added to seq (if any)
467 public static DBRefEntry parseToDbRef(SequenceI seq, String dbname,
468 String version, String acn)
470 DBRefEntry ref = null;
473 String locsrc = DBRefUtils.getCanonicalName(dbname);
474 if (locsrc.equals(DBRefSource.PDB))
477 * Check for PFAM style stockhom PDB accession id citation e.g.
480 Regex r = new com.stevesoft.pat.Regex(
481 "([0-9][0-9A-Za-z]{3})\\s*(.?)\\s*;\\s*([0-9]+)-([0-9]+)");
482 if (r.search(acn.trim()))
484 String pdbid = r.stringMatched(1);
485 String chaincode = r.stringMatched(2);
486 if (chaincode == null)
490 // String mapstart = r.stringMatched(3);
491 // String mapend = r.stringMatched(4);
492 if (chaincode.equals(" "))
496 // construct pdb ref.
497 ref = new DBRefEntry(locsrc, version, pdbid + chaincode);
498 PDBEntry pdbr = new PDBEntry();
500 pdbr.setType(PDBEntry.Type.PDB);
501 pdbr.setProperty(new Hashtable());
502 pdbr.setChainCode(chaincode);
503 // pdbr.getProperty().put("CHAIN", chaincode);
508 System.err.println("Malformed PDB DR line:" + acn);
514 ref = new DBRefEntry(locsrc, version, acn);
525 * Returns true if either object is null, or they are equal
531 public static boolean nullOrEqual(Object o1, Object o2)
533 if (o1 == null || o2 == null)
537 return (o1 == null ? o2.equals(o1) : o1.equals(o2));
541 * Selects just the DNA or protein references from a set of references
544 * if true, select references to 'standard' DNA databases, else to
545 * 'standard' peptide databases
547 * a set of references to select from
550 public static DBRefEntry[] selectDbRefs(boolean selectDna,
553 return selectRefs(refs, selectDna ? DBRefSource.DNACODINGDBS
554 : DBRefSource.PROTEINDBS);
555 // could attempt to find other cross
556 // refs here - ie PDB xrefs
557 // (not dna, not protein seq)
561 * Returns the (possibly empty) list of those supplied dbrefs which have the
562 * specified source database, with a case-insensitive match of source name
568 public static List<DBRefEntry> searchRefsForSource(DBRefEntry[] dbRefs,
571 List<DBRefEntry> matches = new ArrayList<DBRefEntry>();
572 if (dbRefs != null && source != null)
574 for (DBRefEntry dbref : dbRefs)
576 if (source.equalsIgnoreCase(dbref.getSource()))