+/*
+ * Jalview - A Sequence Alignment Editor and Viewer (Version 2.9.0b1)
+ * Copyright (C) 2015 The Jalview Authors
+ *
+ * This file is part of Jalview.
+ *
+ * Jalview is free software: you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, either version 3
+ * of the License, or (at your option) any later version.
+ *
+ * Jalview is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
+ * PURPOSE. See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
/**
* PredFile.java
* JalviewX / Vamsas Project
*/
package jalview.io;
-import jalview.datamodel.*;
-import jalview.util.*;
+import jalview.datamodel.Alignment;
+import jalview.datamodel.AlignmentAnnotation;
+import jalview.datamodel.Sequence;
+import jalview.datamodel.SequenceI;
+import jalview.util.MessageManager;
-import java.io.*;
-import java.util.*;
+import java.io.IOException;
+import java.util.Hashtable;
+import java.util.StringTokenizer;
+import java.util.Vector;
-public class JPredFile
- extends AlignFile
+/**
+ * Parser for the JPred/JNet concise format. This is a series of CSV lines, each
+ * line is either a sequence (QUERY), a sequence profile (align;), or jnet
+ * prediction annotation (anything else). Automagic translation happens for
+ * annotation called 'JNETPRED' (translated to Secondary Structure Prediction),
+ * or 'JNETCONF' (translates to 'Prediction Confidence'). Numeric scores are
+ * differentiated from symbolic by being parseable into a float vector. They are
+ * put in Scores. Symscores gets the others. JNetAnnotationMaker translates the
+ * data parsed by this object into annotation on an alignment. It is
+ * automatically called but can be used to transfer the annotation onto a
+ * sequence in another alignment (and insert gaps where necessary)
+ *
+ * @author jprocter
+ * @version $Revision$
+ */
+public class JPredFile extends AlignFile
{
Vector ids;
+
Vector conf;
+
Hashtable Scores; // Hash of names and score vectors
- public JPredFile(String inStr)
+ Hashtable Symscores; // indexes of symbol annotation properties in sequenceI
+
+ // vector
+
+ private int QuerySeqPosition;
+
+ /**
+ * Creates a new JPredFile object.
+ *
+ * @param inFile
+ * DOCUMENT ME!
+ * @param type
+ * DOCUMENT ME!
+ *
+ * @throws IOException
+ * DOCUMENT ME!
+ */
+ public JPredFile(String inFile, String type) throws IOException
{
- super(inStr);
+ super(inFile, type);
}
- public void initData()
+ public JPredFile(FileParse source) throws IOException
{
+ super(source);
+ }
- super.initData();
- Scores = new Hashtable();
+ /**
+ * DOCUMENT ME!
+ *
+ * @param QuerySeqPosition
+ * DOCUMENT ME!
+ */
+ public void setQuerySeqPosition(int QuerySeqPosition)
+ {
+ this.QuerySeqPosition = QuerySeqPosition;
}
- public JPredFile(String inFile, String type)
- throws IOException
+ /**
+ * DOCUMENT ME!
+ *
+ * @return DOCUMENT ME!
+ */
+ public int getQuerySeqPosition()
{
+ return QuerySeqPosition;
+ }
- super(inFile, type);
+ /**
+ * DOCUMENT ME!
+ *
+ * @return DOCUMENT ME!
+ */
+ public Hashtable getScores()
+ {
+ return Scores;
}
/**
- * parse a JPred concise file into a sequence-alignment like object.
+ * DOCUMENT ME!
+ *
+ * @return DOCUMENT ME!
*/
+ public Hashtable getSymscores()
+ {
+ return Symscores;
+ }
- public void parse()
- throws IOException
+ /**
+ * DOCUMENT ME!
+ */
+ public void initData()
{
+ super.initData();
+ Scores = new Hashtable();
+ ids = null;
+ conf = null;
+ }
+ /**
+ * parse a JPred concise file into a sequence-alignment like object.
+ */
+ public void parse() throws IOException
+ {
+ // JBPNote log.System.out.println("all read in ");
String line;
-
+ QuerySeqPosition = -1;
noSeqs = 0;
+
Vector seq_entries = new Vector();
Vector ids = new Vector();
+ Hashtable Symscores = new Hashtable();
- while ( (line = nextLine()) != null)
+ while ((line = nextLine()) != null)
{
// Concise format allows no comments or non comma-formatted data
StringTokenizer str = new StringTokenizer(line, ":");
String id = "";
- String seq = "";
- if (str.hasMoreTokens())
+
+ if (!str.hasMoreTokens())
{
- id = str.nextToken();
- String seqsym = str.nextToken();
- StringTokenizer symbols = new StringTokenizer(seqsym, ",");
- // decide if we have more than just alphanumeric symbols
- int numSymbols = symbols.countTokens();
- if (seq.length() != (2 * numSymbols))
+ continue;
+ }
+
+ id = str.nextToken();
+
+ String seqsym = str.nextToken();
+ StringTokenizer symbols = new StringTokenizer(seqsym, ",");
+
+ // decide if we have more than just alphanumeric symbols
+ int numSymbols = symbols.countTokens();
+
+ if (numSymbols == 0)
+ {
+ continue;
+ }
+
+ if (seqsym.length() != (2 * numSymbols))
+ {
+ // Set of scalars for some property
+ if (Scores.containsKey(id))
+ {
+ int i = 1;
+
+ while (Scores.containsKey(id + "_" + i))
+ {
+ i++;
+ }
+
+ id = id + "_" + i;
+ }
+
+ Vector scores = new Vector();
+
+ // Typecheck from first entry
+ int i = 0;
+ String ascore = "dead";
+
+ try
{
- // Set of scalars for some property
- if (Scores.containsKey(id))
+ // store elements as floats...
+ while (symbols.hasMoreTokens())
{
- int i = 1;
- while (Scores.containsKey(id + "_" + i))
- {
- i++;
- }
- id = id + "_" + i;
+ ascore = symbols.nextToken();
+
+ Float score = new Float(ascore);
+ scores.addElement((Object) score);
}
- Vector scores = new Vector(numSymbols);
- // Typecheck from first entry
- int i = 0;
- String ascore = symbols.nextToken();
- try
+
+ Scores.put(id, scores);
+ } catch (Exception e)
+ {
+ // or just keep them as strings
+ i = scores.size();
+
+ for (int j = 0; j < i; j++)
{
- // store elements as floats...
- do
- {
- Float score = new Float(ascore);
- scores.set(i, (Object) score);
- ascore = symbols.nextToken();
- }
- while (++i < numSymbols);
+ scores.setElementAt(
+ (Object) ((Float) scores.elementAt(j)).toString(), j);
}
- catch (Exception e)
+
+ scores.addElement((Object) ascore);
+
+ while (symbols.hasMoreTokens())
{
- // or just keep them as strings
- for (int j = 0; j < i; j++)
- {
- scores.set(j,
- (Object)
- ( (Float) scores.get(j)).toString());
- }
- do
- {
- scores.set(i, ascore);
- ascore = symbols.nextToken();
- }
- while (++i < numSymbols);
+ ascore = symbols.nextToken();
+ scores.addElement((Object) ascore);
}
+
Scores.put(id, scores);
}
- else
+ }
+ else if (id.equals("jnetconf"))
+ {
+ // log.debug System.out.println("here");
+ id = "Prediction Confidence";
+ this.conf = new Vector(numSymbols);
+
+ for (int i = 0; i < numSymbols; i++)
{
- if (id.equals("jnetconf"))
+ conf.setElementAt(symbols.nextToken(), i);
+ }
+ }
+ else
+ {
+ // Sequence or a prediction string (rendered as sequence)
+ StringBuffer newseq = new StringBuffer();
+
+ for (int i = 0; i < numSymbols; i++)
+ {
+ newseq.append(symbols.nextToken());
+ }
+
+ if (id.indexOf(";") > -1)
+ {
+ seq_entries.addElement(newseq);
+
+ int i = 1;
+ String name = id.substring(id.indexOf(";") + 1);
+
+ while (ids.lastIndexOf(name) > -1)
{
- id = "Prediction Confidence";
- this.conf = new Vector(numSymbols);
- for (int i = 0; i < numSymbols; i++)
- {
- conf.set(i, (Object) symbols.nextToken());
- }
+ name = id.substring(id.indexOf(";") + 1) + "_" + ++i;
}
- else
+
+ if (QuerySeqPosition == -1)
+ QuerySeqPosition = ids.size();
+ ids.addElement(name);
+ noSeqs++;
+ }
+ else
+ {
+ if (id.equals("JNETPRED"))
{
- // Sequence or a prediction string (rendered as sequence)
-
- StringBuffer newseq = new StringBuffer();
- for (int i = 0; i < numSymbols; i++)
- {
- newseq.append(symbols.nextToken());
- }
- if (id.indexOf(";") > -1)
- {
- seq_entries.addElement(newseq);
- ids.addElement(id.substring(id.indexOf(";")));
- noSeqs++;
- }
- else
- {
- if (id.equals("JNETPRED"))
- {
- id = "Predicted Secondary Structure";
- }
- seq_entries.addElement(newseq);
- ids.addElement(id);
- }
+ id = "Predicted Secondary Structure";
}
- }
+ seq_entries.addElement(newseq.toString());
+ ids.addElement(id);
+ Symscores.put((Object) id, (Object) new Integer(ids.size() - 1));
+ }
}
}
+ /*
+ * leave it to the parser user to actually check this. if (noSeqs < 1) {
+ * throw new IOException( "JpredFile Parser: No sequence in the
+ * prediction!"); }
+ */
- if (noSeqs < 1)
- {
- throw new IOException("JpredFile Parser: No sequence in the prediction!");
- }
maxLength = seq_entries.elementAt(0).toString().length();
+
for (int i = 0; i < ids.size(); i++)
{
// Add all sequence like objects
-
Sequence newSeq = new Sequence(ids.elementAt(i).toString(),
- seq_entries.elementAt(i).toString(), 1,
- seq_entries.elementAt(i).toString().length());
- if (!isValidProteinSequence(newSeq.getSequence()))
+ seq_entries.elementAt(i).toString(), 1, seq_entries
+ .elementAt(i).toString().length());
+
+ if (maxLength != seq_entries.elementAt(i).toString().length())
{
- throw new IOException("JPredConcise: Not a valid protein sequence - ("
- + ids.elementAt(i).toString() + ")");
+ throw new IOException(
+ MessageManager
+ .formatMessage(
+ "exception.jpredconcide_entry_has_unexpected_number_of_columns",
+ new String[] { ids.elementAt(i).toString() }));
}
- if (maxLength != seq_entries.elementAt(i).toString().length())
+ if ((newSeq.getName().startsWith("QUERY") || newSeq.getName()
+ .startsWith("align;")) && (QuerySeqPosition == -1))
{
- throw new IOException("JPredConcise: Entry (" +
- ids.elementAt(i).toString()
- + ") has an unexpected number of columns");
+ QuerySeqPosition = seqs.size();
}
- seqs.addElement(newSeq);
+ seqs.addElement(newSeq);
+ }
+ if (seqs.size() > 0 && QuerySeqPosition > -1)
+ {
+ // try to make annotation for a prediction only input (default if no
+ // alignment is given and prediction contains a QUERY or align;sequence_id
+ // line)
+ Alignment tal = new Alignment(this.getSeqsAsArray());
+ try
+ {
+ JnetAnnotationMaker.add_annotation(this, tal, QuerySeqPosition,
+ true);
+ } catch (Exception e)
+ {
+ tal = null;
+ IOException ex = new IOException(
+ MessageManager
+ .formatMessage(
+ "exception.couldnt_parse_concise_annotation_for_prediction",
+ new String[] { e.getMessage() }));
+ e.printStackTrace(); // java 1.1 does not have :
+ // ex.setStackTrace(e.getStackTrace());
+ throw ex;
+ }
+ this.annotations = new Vector();
+ AlignmentAnnotation[] aan = tal.getAlignmentAnnotation();
+ for (int aai = 0; aan != null && aai < aan.length; aai++)
+ {
+ annotations.addElement(aan[aai]);
+ }
}
}
/**
* print
- *
+ *
* @return String
*/
-
public String print()
{
return "Not Supported";
}
-}
-/*
-StringBuffer out = new StringBuffer();
-out.append("START PRED\n");
-for (int i = 0; i < s[0].sequence.length(); i++)
-{
- out.append(s[0].sequence.substring(i, i + 1) + " ");
- out.append(s[1].sequence.substring(i, i + 1) + " ");
- out.append(s[1].score[0].elementAt(i) + " ");
- out.append(s[1].score[1].elementAt(i) + " ");
- out.append(s[1].score[2].elementAt(i) + " ");
- out.append(s[1].score[3].elementAt(i) + " ");
-
- out.append("\n");
-}
-out.append("END PRED\n");
-return out.toString();
-}
-
- public static void main(String[] args)
-{
- try
+ /**
+ * DOCUMENT ME!
+ *
+ * @param args
+ * DOCUMENT ME!
+ */
+ public static void main(String[] args)
{
- BLCFile blc = new BLCFile(args[0], "File");
- DrawableSequence[] s = new DrawableSequence[blc.seqs.size()];
- for (int i = 0; i < blc.seqs.size(); i++)
+ try
{
- s[i] = new DrawableSequence( (Sequence) blc.seqs.elementAt(i));
- }
- String out = BLCFile.print(s);
+ JPredFile blc = new JPredFile(args[0], "File");
- AlignFrame af = new AlignFrame(null, s);
- af.resize(700, 500);
- af.show();
- System.out.println(out);
+ for (int i = 0; i < blc.seqs.size(); i++)
+ {
+ System.out.println(((Sequence) blc.seqs.elementAt(i)).getName()
+ + "\n"
+ + ((Sequence) blc.seqs.elementAt(i)).getSequenceAsString()
+ + "\n");
+ }
+ } catch (java.io.IOException e)
+ {
+ System.err.println("Exception " + e);
+ // e.printStackTrace(); not java 1.1 compatible!
+ }
}
- catch (java.io.IOException e)
+
+ Vector annotSeqs = null;
+
+ /**
+ * removeNonSequences
+ */
+ public void removeNonSequences()
{
- System.out.println("Exception " + e);
+ if (annotSeqs != null)
+ {
+ return;
+ }
+ annotSeqs = new Vector();
+ Vector newseqs = new Vector();
+ int i = 0;
+ int j = seqs.size();
+ for (; i < QuerySeqPosition; i++)
+ {
+ annotSeqs.addElement(seqs.elementAt(i));
+ }
+ // check that no stray annotations have been added at the end.
+ {
+ SequenceI sq = (SequenceI) seqs.elementAt(j - 1);
+ if (sq.getName().toUpperCase().startsWith("JPRED"))
+ {
+ annotSeqs.addElement(sq);
+ seqs.removeElementAt(--j);
+ }
+ }
+ for (; i < j; i++)
+ {
+ newseqs.addElement(seqs.elementAt(i));
+ }
+
+ seqs.removeAllElements();
+ seqs = newseqs;
}
}
-}
-*/
+/*
+ * StringBuffer out = new StringBuffer();
+ *
+ * out.append("START PRED\n"); for (int i = 0; i < s[0].sequence.length(); i++)
+ * { out.append(s[0].sequence.substring(i, i + 1) + " ");
+ * out.append(s[1].sequence.substring(i, i + 1) + " ");
+ * out.append(s[1].score[0].elementAt(i) + " ");
+ * out.append(s[1].score[1].elementAt(i) + " ");
+ * out.append(s[1].score[2].elementAt(i) + " ");
+ * out.append(s[1].score[3].elementAt(i) + " ");
+ *
+ * out.append("\n"); } out.append("END PRED\n"); return out.toString(); }
+ *
+ * public static void main(String[] args) { try { BLCFile blc = new
+ * BLCFile(args[0], "File"); DrawableSequence[] s = new
+ * DrawableSequence[blc.seqs.size()]; for (int i = 0; i < blc.seqs.size(); i++)
+ * { s[i] = new DrawableSequence( (Sequence) blc.seqs.elementAt(i)); } String
+ * out = BLCFile.print(s);
+ *
+ * AlignFrame af = new AlignFrame(null, s); af.resize(700, 500); af.show();
+ * System.out.println(out); } catch (java.io.IOException e) {
+ * System.out.println("Exception " + e); } } }
+ */