2 * Jalview - A Sequence Alignment Editor and Viewer (Version 2.7)
3 * Copyright (C) 2011 J Procter, AM Waterhouse, J Engelhardt, LM Lui, G Barton, M Clamp, S Searle
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 of the License, or (at your option) any later version.
11 * Jalview is distributed in the hope that it will be useful, but
12 * WITHOUT ANY WARRANTY; without even the implied warranty
13 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
14 * PURPOSE. See the GNU General Public License for more details.
16 * You should have received a copy of the GNU General Public License along with Jalview. If not, see <http://www.gnu.org/licenses/>.
20 * JalviewX / Vamsas Project
21 * JPred.seq.concise reader
28 import javax.xml.parsers.ParserConfigurationException;
30 import org.xml.sax.SAXException;
32 import fr.orsay.lri.varna.exceptions.ExceptionFileFormatOrSyntax;
33 import fr.orsay.lri.varna.exceptions.ExceptionLoadingFailed;
34 import fr.orsay.lri.varna.exceptions.ExceptionPermissionDenied;
36 import jalview.datamodel.*;
39 * Parser for the JPred/JNet concise format. This is a series of CSV lines, each
40 * line is either a sequence (QUERY), a sequence profile (align;), or jnet
41 * prediction annotation (anything else). Automagic translation happens for
42 * annotation called 'JNETPRED' (translated to Secondary Structure Prediction),
43 * or 'JNETCONF' (translates to 'Prediction Confidence'). Numeric scores are
44 * differentiated from symbolic by being parseable into a float vector. They are
45 * put in Scores. Symscores gets the others. JNetAnnotationMaker translates the
46 * data parsed by this object into annotation on an alignment. It is
47 * automatically called but can be used to transfer the annotation onto a
48 * sequence in another alignment (and insert gaps where necessary)
53 public class JPredFile extends AlignFile
59 Hashtable Scores; // Hash of names and score vectors
61 Hashtable Symscores; // indexes of symbol annotation properties in sequenceI
65 private int QuerySeqPosition;
68 * Creates a new JPredFile object.
77 * @throws SAXException
78 * @throws ParserConfigurationException
79 * @throws ExceptionFileFormatOrSyntax
80 * @throws ExceptionLoadingFailed
81 * @throws ExceptionPermissionDenied
83 public JPredFile(String inFile, String type) throws IOException, ExceptionFileFormatOrSyntax, ParserConfigurationException, SAXException, ExceptionPermissionDenied, ExceptionLoadingFailed
88 public JPredFile(FileParse source) throws IOException, ExceptionFileFormatOrSyntax, ParserConfigurationException, SAXException, ExceptionPermissionDenied, ExceptionLoadingFailed
96 * @param QuerySeqPosition
99 public void setQuerySeqPosition(int QuerySeqPosition)
101 this.QuerySeqPosition = QuerySeqPosition;
107 * @return DOCUMENT ME!
109 public int getQuerySeqPosition()
111 return QuerySeqPosition;
117 * @return DOCUMENT ME!
119 public Hashtable getScores()
127 * @return DOCUMENT ME!
129 public Hashtable getSymscores()
137 public void initData()
140 Scores = new Hashtable();
146 * parse a JPred concise file into a sequence-alignment like object.
148 public void parse() throws IOException
150 // JBPNote log.System.out.println("all read in ");
152 QuerySeqPosition = -1;
155 Vector seq_entries = new Vector();
156 Vector ids = new Vector();
157 Hashtable Symscores = new Hashtable();
159 while ((line = nextLine()) != null)
161 // Concise format allows no comments or non comma-formatted data
162 StringTokenizer str = new StringTokenizer(line, ":");
165 if (!str.hasMoreTokens())
170 id = str.nextToken();
172 String seqsym = str.nextToken();
173 StringTokenizer symbols = new StringTokenizer(seqsym, ",");
175 // decide if we have more than just alphanumeric symbols
176 int numSymbols = symbols.countTokens();
183 if (seqsym.length() != (2 * numSymbols))
185 // Set of scalars for some property
186 if (Scores.containsKey(id))
190 while (Scores.containsKey(id + "_" + i))
198 Vector scores = new Vector();
200 // Typecheck from first entry
202 String ascore = "dead";
206 // store elements as floats...
207 while (symbols.hasMoreTokens())
209 ascore = symbols.nextToken();
211 Float score = new Float(ascore);
212 scores.addElement((Object) score);
215 Scores.put(id, scores);
216 } catch (Exception e)
218 // or just keep them as strings
221 for (int j = 0; j < i; j++)
224 (Object) ((Float) scores.elementAt(j)).toString(), j);
227 scores.addElement((Object) ascore);
229 while (symbols.hasMoreTokens())
231 ascore = symbols.nextToken();
232 scores.addElement((Object) ascore);
235 Scores.put(id, scores);
238 else if (id.equals("jnetconf"))
240 // log.debug System.out.println("here");
241 id = "Prediction Confidence";
242 this.conf = new Vector(numSymbols);
244 for (int i = 0; i < numSymbols; i++)
246 conf.setElementAt(symbols.nextToken(), i);
251 // Sequence or a prediction string (rendered as sequence)
252 StringBuffer newseq = new StringBuffer();
254 for (int i = 0; i < numSymbols; i++)
256 newseq.append(symbols.nextToken());
259 if (id.indexOf(";") > -1)
261 seq_entries.addElement(newseq);
264 String name = id.substring(id.indexOf(";") + 1);
266 while (ids.lastIndexOf(name) > -1)
268 name = id.substring(id.indexOf(";") + 1) + "_" + ++i;
271 if (QuerySeqPosition == -1)
272 QuerySeqPosition = ids.size();
273 ids.addElement(name);
278 if (id.equals("JNETPRED"))
280 id = "Predicted Secondary Structure";
283 seq_entries.addElement(newseq.toString());
285 Symscores.put((Object) id, (Object) new Integer(ids.size() - 1));
290 * leave it to the parser user to actually check this. if (noSeqs < 1) {
291 * throw new IOException( "JpredFile Parser: No sequence in the
295 maxLength = seq_entries.elementAt(0).toString().length();
297 for (int i = 0; i < ids.size(); i++)
299 // Add all sequence like objects
300 Sequence newSeq = new Sequence(ids.elementAt(i).toString(),
301 seq_entries.elementAt(i).toString(), 1, seq_entries
302 .elementAt(i).toString().length());
304 if (maxLength != seq_entries.elementAt(i).toString().length())
306 throw new IOException("JPredConcise: Entry ("
307 + ids.elementAt(i).toString()
308 + ") has an unexpected number of columns");
311 if ((newSeq.getName().startsWith("QUERY") || newSeq.getName()
312 .startsWith("align;")) && (QuerySeqPosition == -1))
314 QuerySeqPosition = seqs.size();
317 seqs.addElement(newSeq);
319 if (seqs.size() > 0 && QuerySeqPosition > -1)
321 // try to make annotation for a prediction only input (default if no
322 // alignment is given and prediction contains a QUERY or align;sequence_id
324 Alignment tal = new Alignment(this.getSeqsAsArray());
327 JnetAnnotationMaker.add_annotation(this, tal, QuerySeqPosition,
329 } catch (Exception e)
332 IOException ex = new IOException(
333 "Couldn't parse concise annotation for prediction profile.\n"
335 e.printStackTrace(); // java 1.1 does not have :
336 // ex.setStackTrace(e.getStackTrace());
339 this.annotations = new Vector();
340 AlignmentAnnotation[] aan = tal.getAlignmentAnnotation();
341 for (int aai = 0; aan != null && aai < aan.length; aai++)
343 annotations.addElement(aan[aai]);
353 public String print()
355 return "Not Supported";
363 * @throws SAXException
364 * @throws ParserConfigurationException
365 * @throws ExceptionFileFormatOrSyntax
366 * @throws ExceptionLoadingFailed
367 * @throws ExceptionPermissionDenied
369 public static void main(String[] args) throws ExceptionFileFormatOrSyntax, ParserConfigurationException, SAXException, ExceptionPermissionDenied, ExceptionLoadingFailed
373 JPredFile blc = new JPredFile(args[0], "File");
375 for (int i = 0; i < blc.seqs.size(); i++)
377 System.out.println(((Sequence) blc.seqs.elementAt(i)).getName()
379 + ((Sequence) blc.seqs.elementAt(i)).getSequenceAsString()
382 } catch (java.io.IOException e)
384 System.err.println("Exception " + e);
385 // e.printStackTrace(); not java 1.1 compatible!
389 Vector annotSeqs = null;
394 public void removeNonSequences()
396 if (annotSeqs != null)
400 annotSeqs = new Vector();
401 Vector newseqs = new Vector();
404 for (; i < QuerySeqPosition; i++)
406 annotSeqs.addElement(seqs.elementAt(i));
408 // check that no stray annotations have been added at the end.
410 SequenceI sq = (SequenceI) seqs.elementAt(j - 1);
411 if (sq.getName().toUpperCase().startsWith("JPRED"))
413 annotSeqs.addElement(sq);
414 seqs.removeElementAt(--j);
419 newseqs.addElement(seqs.elementAt(i));
422 seqs.removeAllElements();
428 * StringBuffer out = new StringBuffer();
430 * out.append("START PRED\n"); for (int i = 0; i < s[0].sequence.length(); i++)
431 * { out.append(s[0].sequence.substring(i, i + 1) + " ");
432 * out.append(s[1].sequence.substring(i, i + 1) + " ");
433 * out.append(s[1].score[0].elementAt(i) + " ");
434 * out.append(s[1].score[1].elementAt(i) + " ");
435 * out.append(s[1].score[2].elementAt(i) + " ");
436 * out.append(s[1].score[3].elementAt(i) + " ");
438 * out.append("\n"); } out.append("END PRED\n"); return out.toString(); }
440 * public static void main(String[] args) { try { BLCFile blc = new
441 * BLCFile(args[0], "File"); DrawableSequence[] s = new
442 * DrawableSequence[blc.seqs.size()]; for (int i = 0; i < blc.seqs.size(); i++)
443 * { s[i] = new DrawableSequence( (Sequence) blc.seqs.elementAt(i)); } String
444 * out = BLCFile.print(s);
446 * AlignFrame af = new AlignFrame(null, s); af.resize(700, 500); af.show();
447 * System.out.println(out); } catch (java.io.IOException e) {
448 * System.out.println("Exception " + e); } } }