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.PDBEntry;
24 import jalview.datamodel.Sequence;
25 import jalview.datamodel.SequenceFeature;
26 import jalview.datamodel.SequenceI;
28 import java.util.Enumeration;
29 import java.util.Hashtable;
30 import java.util.List;
31 import java.util.Vector;
33 public class SeqsetUtils
37 * Store essential properties of a sequence in a hashtable for later recovery
38 * Keys are Name, Start, End, SeqFeatures, PdbId
44 public static Hashtable SeqCharacterHash(SequenceI seq)
46 Hashtable sqinfo = new Hashtable();
47 sqinfo.put("Name", seq.getName());
48 sqinfo.put("Start", new Integer(seq.getStart()));
49 sqinfo.put("End", new Integer(seq.getEnd()));
50 if (seq.getDescription() != null)
52 sqinfo.put("Description", seq.getDescription());
55 Vector<SequenceFeature> sfeat = new Vector<SequenceFeature>();
56 List<SequenceFeature> sfs = seq.getFeatures().getAllFeatures();
59 if (seq.getDatasetSequence() == null)
61 sqinfo.put("SeqFeatures", sfeat);
63 (seq.getAllPDBEntries() != null) ? seq.getAllPDBEntries()
64 : new Vector<PDBEntry>());
68 sqinfo.put("datasetSequence",
69 (seq.getDatasetSequence() != null) ? seq.getDatasetSequence()
70 : new Sequence("THISISAPLACEHOLDER", ""));
76 * Recover essential properties of a sequence from a hashtable TODO: replace
77 * these methods with something more elegant.
83 * @return boolean true if name was not updated from sqinfo Name entry
85 public static boolean SeqCharacterUnhash(SequenceI sq, Hashtable sqinfo)
87 boolean namePresent = true;
92 String oldname = (String) sqinfo.get("Name");
93 Integer start = (Integer) sqinfo.get("Start");
94 Integer end = (Integer) sqinfo.get("End");
95 Vector<SequenceFeature> sfeatures = (Vector<SequenceFeature>) sqinfo
97 Vector<PDBEntry> pdbid = (Vector<PDBEntry>) sqinfo.get("PdbId");
98 String description = (String) sqinfo.get("Description");
99 Sequence seqds = (Sequence) sqinfo.get("datasetSequence");
108 if (pdbid != null && pdbid.size() > 0)
113 if ((start != null) && (end != null))
115 sq.setStart(start.intValue());
116 sq.setEnd(end.intValue());
119 if (sfeatures != null && !sfeatures.isEmpty())
121 sq.setSequenceFeatures(sfeatures);
123 if (description != null)
125 sq.setDescription(description);
128 && !(seqds.getName().equals("THISISAPLACEHOLDER") && seqds
131 if (sfeatures != null)
134 .println("Implementation error: setting dataset sequence for a sequence which has sequence features.\n\tDataset sequence features will not be visible.");
136 sq.setDatasetSequence(seqds);
143 * Form of the unique name used in uniquify for the i'th sequence in an
144 * ordered vector of sequences.
150 public static String unique_name(int i)
152 return new String("Sequence" + i);
156 * Generates a hash of SeqCharacterHash properties for each sequence in a
157 * sequence set, and optionally renames the sequences to an unambiguous 'safe'
163 * boolean set this to rename each of the sequences to its
164 * unique_name(index) name
165 * @return Hashtable to be passed to
166 * @see deuniquify to recover original names (and properties) for renamed
169 public static Hashtable uniquify(SequenceI[] sequences,
172 // Generate a safely named sequence set and a hash to recover the sequence
174 Hashtable map = new Hashtable();
175 // String[] un_names = new String[sequences.length];
177 for (int i = 0; i < sequences.length; i++)
179 String safename = unique_name(i);
180 map.put(safename, SeqCharacterHash(sequences[i]));
184 sequences[i].setName(safename);
192 * recover unsafe sequence names and original properties for a sequence set
193 * using a map generated by
195 * @see uniquify(sequences,true)
202 public static boolean deuniquify(Hashtable map, SequenceI[] sequences)
204 return deuniquify(map, sequences, true);
208 * recover unsafe sequence names and original properties for a sequence set
209 * using a map generated by
211 * @see uniquify(sequences,true)
217 * when false, don't complain about sequences without any data in the
221 public static boolean deuniquify(Hashtable map, SequenceI[] sequences,
224 jalview.analysis.SequenceIdMatcher matcher = new SequenceIdMatcher(
226 SequenceI msq = null;
227 Enumeration keys = map.keys();
228 Vector unmatched = new Vector();
229 for (int i = 0, j = sequences.length; i < j; i++)
231 unmatched.addElement(sequences[i]);
233 while (keys.hasMoreElements())
235 Object key = keys.nextElement();
236 if (key instanceof String)
238 if ((msq = matcher.findIdMatch((String) key)) != null)
240 Hashtable sqinfo = (Hashtable) map.get(key);
241 unmatched.removeElement(msq);
242 SeqCharacterUnhash(msq, sqinfo);
248 System.err.println("Can't find '" + ((String) key)
249 + "' in uniquified alignment");
254 if (unmatched.size() > 0 && !quiet)
256 System.err.println("Did not find matches for :");
257 for (Enumeration i = unmatched.elements(); i.hasMoreElements(); System.out
258 .println(((SequenceI) i.nextElement()).getName()))
269 * returns a subset of the sequenceI seuqences, including only those that
270 * contain at least one residue.
274 * @return SequenceI[]
276 public static SequenceI[] getNonEmptySequenceSet(SequenceI[] sequences)
278 // Identify first row of alignment with residues for prediction
279 boolean ungapped[] = new boolean[sequences.length];
281 for (int i = 0, j = sequences.length; i < j; i++)
283 String tempseq = jalview.analysis.AlignSeq.extractGaps(
284 jalview.util.Comparison.GapChars,
285 sequences[i].getSequenceAsString());
287 if (tempseq.length() == 0)
299 return null; // no minimal set
301 // compose minimal set
302 SequenceI[] mset = new SequenceI[msflen];
303 for (int i = 0, j = sequences.length, k = 0; i < j; i++)
307 mset[k++] = sequences[i];