From 3d558ed2093c9d85699945ff70271f0be119b434 Mon Sep 17 00:00:00 2001 From: jprocter Date: Tue, 24 Oct 2006 08:11:22 +0000 Subject: [PATCH] fixes bug reported by Christopher Tan (help@jalview.org) - preservation of sequence description in aligned sequences. --- src/jalview/analysis/SeqsetUtils.java | 448 +++++++++++++++++---------------- 1 file changed, 226 insertions(+), 222 deletions(-) diff --git a/src/jalview/analysis/SeqsetUtils.java b/src/jalview/analysis/SeqsetUtils.java index 908d4e5..885305a 100755 --- a/src/jalview/analysis/SeqsetUtils.java +++ b/src/jalview/analysis/SeqsetUtils.java @@ -1,222 +1,226 @@ -/* - * Jalview - A Sequence Alignment Editor and Viewer - * Copyright (C) 2006 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle - * - * This program 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 2 - * of the License, or (at your option) any later version. - * - * This program 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 this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA - */ -package jalview.analysis; - -import java.util.*; - -import jalview.datamodel.*; - -/** - *

Title:

- * - *

Description:

- * - *

Copyright: Copyright (c) 2004

- * - *

Company: Dundee University

- * - * @author not attributable - * @version 1.0 - */ -public class SeqsetUtils -{ - - /** - * Store essential properties of a sequence in a hashtable for later recovery - * Keys are Name, Start, End, SeqFeatures, PdbId - * @param seq SequenceI - * @return Hashtable - */ - public static Hashtable SeqCharacterHash(SequenceI seq) - { - Hashtable sqinfo = new Hashtable(); - sqinfo.put("Name", seq.getName()); - sqinfo.put("Start", new Integer(seq.getStart())); - sqinfo.put("End", new Integer(seq.getEnd())); - Vector sfeat = new Vector(); - jalview.datamodel.SequenceFeature[] sfarray=seq.getSequenceFeatures(); - if (sfarray!=null && sfarray.length>0) { - for (int i=0;i0) - { - sq.setPDBId(pdbid); - } - - if ( (start != null) && (end != null)) - { - sq.setStart(start.intValue()); - sq.setEnd(end.intValue()); - } - - if ((sfeatures != null) && (sfeatures.size()>0)) - { - SequenceFeature[] sfarray = (SequenceFeature[]) sfeatures.toArray(); - sq.setSequenceFeatures(sfarray); - } - - if ((seqds!=null) && !(seqds.getName().equals("THISISAPLACEHOLDER") && seqds.getLength()==0)) { - sq.setDatasetSequence(seqds); - } - - return namePresent; - } - - /** - * Form of the unique name used in uniquify for the i'th sequence in an ordered vector of sequences. - * @param i int - * @return String - */ - public static String unique_name(int i) - { - return new String("Sequence" + i); - } - - /** - * Generates a hash of SeqCharacterHash properties for each sequence - * in a sequence set, and optionally renames the sequences to an - * unambiguous 'safe' name. - * @param sequences SequenceI[] - * @param write_names boolean set this to rename each of the sequences to its unique_name(index) name - * @return Hashtable to be passed to @see deuniquify to recover original names (and properties) for renamed sequences - */ - public static Hashtable uniquify(SequenceI[] sequences, boolean write_names) - { - // Generate a safely named sequence set and a hash to recover the sequence names - Hashtable map = new Hashtable(); - //String[] un_names = new String[sequences.length]; - - for (int i = 0; i < sequences.length; i++) - { - String safename = unique_name(i); - map.put(safename, SeqCharacterHash(sequences[i])); - - if (write_names) - { - sequences[i].setName(safename); - } - } - - - return map; - } - /** - * recover unsafe sequence names and original properties for a sequence - * set using a map generated by @see uniquify(sequences,true) - * @param map Hashtable - * @param sequences SequenceI[] - * @return boolean - */ - public static boolean deuniquify(Hashtable map, SequenceI[] sequences) - { - jalview.analysis.SequenceIdMatcher matcher = new SequenceIdMatcher(sequences); - SequenceI msq = null; - Enumeration keys = map.keys(); - Vector unmatched = new Vector(); - for (int i=0, j=sequences.length; i0) { - System.err.println("Did not find matches for :"); - for (Enumeration i = unmatched.elements(); i.hasMoreElements(); System.out.println(((SequenceI) i.nextElement()).getName())) - ; - return false; - } - - return true; - } - /** - * returns a subset of the sequenceI seuqences, - * including only those that contain at least one residue. - * @param sequences SequenceI[] - * @return SequenceI[] - */ - public static SequenceI[] getNonEmptySequenceSet(SequenceI[] sequences) { - // Identify first row of alignment with residues for prediction - boolean ungapped[] = new boolean[sequences.length]; - int msflen=0; - for (int i=0,j=sequences.length; iTitle:

+ * + *

Description:

+ * + *

Copyright: Copyright (c) 2004

+ * + *

Company: Dundee University

+ * + * @author not attributable + * @version 1.0 + */ +public class SeqsetUtils +{ + + /** + * Store essential properties of a sequence in a hashtable for later recovery + * Keys are Name, Start, End, SeqFeatures, PdbId + * @param seq SequenceI + * @return Hashtable + */ + public static Hashtable SeqCharacterHash(SequenceI seq) + { + Hashtable sqinfo = new Hashtable(); + sqinfo.put("Name", seq.getName()); + sqinfo.put("Start", new Integer(seq.getStart())); + sqinfo.put("End", new Integer(seq.getEnd())); + if (seq.getDescription()!=null) + sqinfo.put("Description", seq.getDescription()); + Vector sfeat = new Vector(); + jalview.datamodel.SequenceFeature[] sfarray=seq.getSequenceFeatures(); + if (sfarray!=null && sfarray.length>0) { + for (int i=0;i0) + { + sq.setPDBId(pdbid); + } + + if ( (start != null) && (end != null)) + { + sq.setStart(start.intValue()); + sq.setEnd(end.intValue()); + } + + if ((sfeatures != null) && (sfeatures.size()>0)) + { + SequenceFeature[] sfarray = (SequenceFeature[]) sfeatures.toArray(); + sq.setSequenceFeatures(sfarray); + } + if (description!=null) + sq.setDescription(description); + if ((seqds!=null) && !(seqds.getName().equals("THISISAPLACEHOLDER") && seqds.getLength()==0)) { + sq.setDatasetSequence(seqds); + } + + return namePresent; + } + + /** + * Form of the unique name used in uniquify for the i'th sequence in an ordered vector of sequences. + * @param i int + * @return String + */ + public static String unique_name(int i) + { + return new String("Sequence" + i); + } + + /** + * Generates a hash of SeqCharacterHash properties for each sequence + * in a sequence set, and optionally renames the sequences to an + * unambiguous 'safe' name. + * @param sequences SequenceI[] + * @param write_names boolean set this to rename each of the sequences to its unique_name(index) name + * @return Hashtable to be passed to @see deuniquify to recover original names (and properties) for renamed sequences + */ + public static Hashtable uniquify(SequenceI[] sequences, boolean write_names) + { + // Generate a safely named sequence set and a hash to recover the sequence names + Hashtable map = new Hashtable(); + //String[] un_names = new String[sequences.length]; + + for (int i = 0; i < sequences.length; i++) + { + String safename = unique_name(i); + map.put(safename, SeqCharacterHash(sequences[i])); + + if (write_names) + { + sequences[i].setName(safename); + } + } + + + return map; + } + /** + * recover unsafe sequence names and original properties for a sequence + * set using a map generated by @see uniquify(sequences,true) + * @param map Hashtable + * @param sequences SequenceI[] + * @return boolean + */ + public static boolean deuniquify(Hashtable map, SequenceI[] sequences) + { + jalview.analysis.SequenceIdMatcher matcher = new SequenceIdMatcher(sequences); + SequenceI msq = null; + Enumeration keys = map.keys(); + Vector unmatched = new Vector(); + for (int i=0, j=sequences.length; i0) { + System.err.println("Did not find matches for :"); + for (Enumeration i = unmatched.elements(); i.hasMoreElements(); System.out.println(((SequenceI) i.nextElement()).getName())) + ; + return false; + } + + return true; + } + /** + * returns a subset of the sequenceI seuqences, + * including only those that contain at least one residue. + * @param sequences SequenceI[] + * @return SequenceI[] + */ + public static SequenceI[] getNonEmptySequenceSet(SequenceI[] sequences) { + // Identify first row of alignment with residues for prediction + boolean ungapped[] = new boolean[sequences.length]; + int msflen=0; + for (int i=0,j=sequences.length; i