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.analysis;
23 import jalview.datamodel.AlignmentAnnotation;
24 import jalview.datamodel.HiddenMarkovModel;
25 import jalview.datamodel.PDBEntry;
26 import jalview.datamodel.Sequence;
27 import jalview.datamodel.SequenceFeature;
28 import jalview.datamodel.SequenceI;
30 import java.util.Enumeration;
31 import java.util.Hashtable;
32 import java.util.List;
33 import java.util.Vector;
35 public class SeqsetUtils
39 * Store essential properties of a sequence in a hashtable for later recovery
40 * Keys are Name, Start, End, SeqFeatures, PdbId, HMM
46 public static Hashtable SeqCharacterHash(SequenceI seq)
48 Hashtable sqinfo = new Hashtable();
49 sqinfo.put("Name", seq.getName());
50 sqinfo.put("Start", Integer.valueOf(seq.getStart()));
51 sqinfo.put("End", Integer.valueOf(seq.getEnd()));
52 if (seq.getDescription() != null)
54 sqinfo.put("Description", seq.getDescription());
57 Vector<SequenceFeature> sfeat = new Vector<>();
58 List<SequenceFeature> sfs = seq.getFeatures().getAllFeatures();
61 if (seq.getDatasetSequence() == null)
63 sqinfo.put("SeqFeatures", sfeat);
65 (seq.getAllPDBEntries() != null) ? seq.getAllPDBEntries()
66 : new Vector<PDBEntry>());
70 sqinfo.put("datasetSequence",
71 (seq.getDatasetSequence() != null) ? seq.getDatasetSequence()
72 : new Sequence("THISISAPLACEHOLDER", ""));
74 if (seq.hasHMMProfile())
76 sqinfo.put("HMM", seq.getHMM());
79 if (seq.getAnnotation("Search Scores") != null)
81 sqinfo.put("Score", seq.getAnnotation("Search Scores"));
88 * Recover essential properties of a sequence from a hashtable TODO: replace
89 * these methods with something more elegant.
95 * @return boolean true if name was not updated from sqinfo Name entry
97 public static boolean SeqCharacterUnhash(SequenceI sq, Hashtable sqinfo)
99 boolean namePresent = true;
104 String oldname = (String) sqinfo.get("Name");
105 Integer start = (Integer) sqinfo.get("Start");
106 Integer end = (Integer) sqinfo.get("End");
107 Vector<SequenceFeature> sfeatures = (Vector<SequenceFeature>) sqinfo
109 Vector<PDBEntry> pdbid = (Vector<PDBEntry>) sqinfo.get("PdbId");
110 String description = (String) sqinfo.get("Description");
111 Sequence seqds = (Sequence) sqinfo.get("datasetSequence");
112 HiddenMarkovModel hmm = (HiddenMarkovModel) sqinfo.get("HMM");
113 AlignmentAnnotation[] scores = (AlignmentAnnotation[]) sqinfo
124 if (pdbid != null && pdbid.size() > 0)
129 if ((start != null) && (end != null))
131 sq.setStart(start.intValue());
132 sq.setEnd(end.intValue());
135 if (sfeatures != null && !sfeatures.isEmpty())
137 sq.setSequenceFeatures(sfeatures);
139 if (description != null)
141 sq.setDescription(description);
143 if ((seqds != null) && !(seqds.getName().equals("THISISAPLACEHOLDER")
144 && seqds.getLength() == 0))
146 if (sfeatures != null)
149 "Implementation error: setting dataset sequence for a sequence which has sequence features.\n\tDataset sequence features will not be visible.");
151 sq.setDatasetSequence(seqds);
156 sq.setHMM(new HiddenMarkovModel(hmm, sq));
161 for (AlignmentAnnotation score : scores)
163 sq.addAlignmentAnnotation(score);
170 * Form of the unique name used in uniquify for the i'th sequence in an
171 * ordered vector of sequences.
177 public static String unique_name(int i)
179 return new String("Sequence" + i);
183 * Generates a hash of SeqCharacterHash properties for each sequence in a
184 * sequence set, and optionally renames the sequences to an unambiguous 'safe'
190 * boolean set this to rename each of the sequences to its
191 * unique_name(index) name
192 * @return Hashtable to be passed to
193 * @see deuniquify to recover original names (and properties) for renamed
196 public static Hashtable uniquify(SequenceI[] sequences,
199 // Generate a safely named sequence set and a hash to recover the sequence
201 Hashtable map = new Hashtable();
202 // String[] un_names = new String[sequences.length];
204 for (int i = 0; i < sequences.length; i++)
206 String safename = unique_name(i);
207 map.put(safename, SeqCharacterHash(sequences[i]));
211 sequences[i].setName(safename);
219 * recover unsafe sequence names and original properties for a sequence set
220 * using a map generated by
222 * @see uniquify(sequences,true)
229 public static boolean deuniquify(Hashtable map, SequenceI[] sequences)
231 return deuniquify(map, sequences, true);
235 * recover unsafe sequence names and original properties for a sequence set
236 * using a map generated by
238 * @see uniquify(sequences,true)
244 * when false, don't complain about sequences without any data in the
248 public static boolean deuniquify(Hashtable map, SequenceI[] sequences,
251 jalview.analysis.SequenceIdMatcher matcher = new SequenceIdMatcher(
253 SequenceI msq = null;
254 Enumeration keys = map.keys();
255 Vector unmatched = new Vector();
256 for (int i = 0, j = sequences.length; i < j; i++)
258 unmatched.addElement(sequences[i]);
260 while (keys.hasMoreElements())
262 Object key = keys.nextElement();
263 if (key instanceof String)
265 if ((msq = matcher.findIdMatch((String) key)) != null)
267 Hashtable sqinfo = (Hashtable) map.get(key);
268 unmatched.removeElement(msq);
269 SeqCharacterUnhash(msq, sqinfo);
275 System.err.println("Can't find '" + ((String) key)
276 + "' in uniquified alignment");
281 if (unmatched.size() > 0 && !quiet)
283 System.err.println("Did not find matches for :");
284 for (Enumeration i = unmatched.elements(); i
285 .hasMoreElements(); System.out
286 .println(((SequenceI) i.nextElement()).getName()))
297 * returns a subset of the sequenceI seuqences, including only those that
298 * contain at least one residue.
302 * @return SequenceI[]
304 public static SequenceI[] getNonEmptySequenceSet(SequenceI[] sequences)
306 // Identify first row of alignment with residues for prediction
307 boolean ungapped[] = new boolean[sequences.length];
309 for (int i = 0, j = sequences.length; i < j; i++)
311 String tempseq = jalview.analysis.AlignSeq.extractGaps(
312 jalview.util.Comparison.GapChars,
313 sequences[i].getSequenceAsString());
315 if (tempseq.length() == 0)
327 return null; // no minimal set
329 // compose minimal set
330 SequenceI[] mset = new SequenceI[msflen];
331 for (int i = 0, j = sequences.length, k = 0; i < j; i++)
335 mset[k++] = sequences[i];