X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fdatamodel%2FAlignment.java;h=64b79b7416d1381b1cb921bcef718354f36f41c7;hb=482e093c4670a813c9eec254990178b209e32dbc;hp=00d1be8ce452ddae2132c82a52afcc684a5efadb;hpb=f14d234620501b7b5024a9f98e94c520641e7a09;p=jalview.git diff --git a/src/jalview/datamodel/Alignment.java b/src/jalview/datamodel/Alignment.java index 00d1be8..64b79b7 100755 --- a/src/jalview/datamodel/Alignment.java +++ b/src/jalview/datamodel/Alignment.java @@ -1,834 +1,1129 @@ -/* - * Jalview - A Sequence Alignment Editor and Viewer - * Copyright (C) 2005 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.datamodel; - -import jalview.analysis.*; - -import jalview.util.*; - -import java.util.*; - -/** Data structure to hold and manipulate a multiple sequence alignment - */ -public class Alignment implements AlignmentI -{ - protected Alignment dataset; - protected Vector sequences; - protected Vector groups = new Vector(); - protected Vector superGroup = new Vector(); - protected char gapCharacter = '-'; - protected int type = NUCLEOTIDE; - public static final int PROTEIN = 0; - public static final int NUCLEOTIDE = 1; - - /** DOCUMENT ME!! */ - public AlignmentAnnotation[] annotations; - - HiddenSequences hiddenSequences = new HiddenSequences(this); - - - /** Make an alignment from an array of Sequences. - * - * @param sequences - */ - public Alignment(SequenceI[] seqs) - { - int i=0; - - if( jalview.util.Comparison.isNucleotide(seqs)) - type = NUCLEOTIDE; - else - type = PROTEIN; - - sequences = new Vector(); - - for (i = 0; i < seqs.length; i++) - { - sequences.addElement(seqs[i]); - - if(seqs[i].getDatasetSequence()!=null - && seqs[i].getDatasetSequence().getAnnotation()!=null) - { - - for(int a=0; a i) - { - /* MC Should move this to a method somewhere */ - if (!jalview.util.Comparison.isGap(current.getCharAt(i))) - { - delete = false; - } - } - } - - if (delete) - { - deleteColumns(i, i); - iSize--; - i--; - } - } - } - - /** Removes a range of columns (start to end inclusive). - * - * @param start Start column in the alignment - * @param end End column in the alignment - */ - public void deleteColumns(int start, int end) - { - deleteColumns(0, getHeight() - 1, start, end); - } - - /** - * DOCUMENT ME! - * - * @param seq1 DOCUMENT ME! - * @param seq2 DOCUMENT ME! - * @param start DOCUMENT ME! - * @param end DOCUMENT ME! - */ - public void deleteColumns(int seq1, int seq2, int start, int end) - { - for (int i = 0; i <= (end - start); i++) - { - for (int j = seq1; j <= seq2; j++) - { - getSequenceAt(j).deleteCharAt(start); - } - } - } - - /** - * DOCUMENT ME! - * - * @param i DOCUMENT ME! - */ - public void trimLeft(int i) - { - int j, jSize = getHeight(); - for (j = 0; j < jSize; j++) - { - SequenceI s = getSequenceAt(j); - int newstart = s.findPosition(i); - - if(i>s.getLength()) - { - sequences.removeElement(s); - j--; - jSize--; - } - else - { - s.setStart(newstart); - s.setSequence(s.getSequence().substring(i)); - } - } - } - - /** - * DOCUMENT ME! - * - * @param i DOCUMENT ME! - */ - public void trimRight(int i) - { - for (int j = 0; j < getHeight(); j++) - { - SequenceI s = getSequenceAt(j); - int newend = s.findPosition(i); - - s.setEnd(newend); - if(s.getLength()>i) - s.setSequence(s.getSequence().substring(0, i + 1)); - } - } - - /** - * DOCUMENT ME! - * - * @param s DOCUMENT ME! - */ - public void deleteSequence(SequenceI s) - { - for (int i = 0; i < getHeight(); i++) - { - if (getSequenceAt(i) == s) - { - deleteSequence(i); - } - } - } - - /** - * DOCUMENT ME! - * - * @param i DOCUMENT ME! - */ - public void deleteSequence(int i) - { - sequences.removeElementAt(i); - } - - /** - * DOCUMENT ME! - * - * @param threshold DOCUMENT ME! - * @param sel DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public Vector removeRedundancy(float threshold, Vector sel) - { - Vector del = new Vector(); - - for (int i = 1; i < sel.size(); i++) - { - for (int j = 0; j < i; j++) - { - // Only do the comparison if either have not been deleted - if (!del.contains((SequenceI) sel.elementAt(i)) || - !del.contains((SequenceI) sel.elementAt(j))) - { - // use PID instead of Comparison (which is really not pleasant) - float pid = Comparison.PID((SequenceI) sel.elementAt(j), - (SequenceI) sel.elementAt(i)); - - if (pid >= threshold) - { - // Delete the shortest one - if (((SequenceI) sel.elementAt(j)).getSequence().length() > ((SequenceI) sel - .elementAt( - i)).getSequence().length()) - { - del.addElement(sel.elementAt(i)); - } - else - { - del.addElement(sel.elementAt(i)); - } - } - } - } - } - - // Now delete the sequences - for (int i = 0; i < del.size(); i++) - { - deleteSequence((SequenceI) del.elementAt(i)); - } - - return del; - } - - /** */ - public SequenceGroup findGroup(int i) - { - return findGroup(getSequenceAt(i)); - } - - /** */ - public SequenceGroup findGroup(SequenceI s) - { - for (int i = 0; i < this.groups.size(); i++) - { - SequenceGroup sg = (SequenceGroup) groups.elementAt(i); - - if (sg.sequences.contains(s)) - { - return sg; - } - } - - return null; - } - - /** - * DOCUMENT ME! - * - * @param s DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public SequenceGroup[] findAllGroups(SequenceI s) - { - Vector temp = new Vector(); - - int gSize = groups.size(); - for (int i = 0; i < gSize; i++) - { - SequenceGroup sg = (SequenceGroup) groups.elementAt(i); - if(sg==null || sg.sequences==null) - { - this.deleteGroup(sg); - gSize--; - continue; - } - - if (sg.sequences.contains(s)) - { - temp.addElement(sg); - } - } - - SequenceGroup[] ret = new SequenceGroup[temp.size()]; - - for (int i = 0; i < temp.size(); i++) - { - ret[i] = (SequenceGroup) temp.elementAt(i); - } - - return ret; - } - - - - /** */ - public void addGroup(SequenceGroup sg) - { - if (!groups.contains(sg)) - { - groups.addElement(sg); - } - } - - /** - * DOCUMENT ME! - */ - public void deleteAllGroups() - { - groups.removeAllElements(); - superGroup.removeAllElements(); - - int i = 0; - - while (i < sequences.size()) - { - SequenceI s = getSequenceAt(i); - s.setColor(java.awt.Color.white); - i++; - } - } - - /** */ - public void deleteGroup(SequenceGroup g) - { - if (groups.contains(g)) - { - groups.removeElement(g); - } - } - - /** */ - public SequenceI findName(String name) - { - int i = 0; - - while (i < sequences.size()) - { - if (getSequenceAt(i).getName().equals(name)) - { - return getSequenceAt(i); - } - - i++; - } - - return null; - } - - - /** */ - public int findIndex(SequenceI s) - { - int i = 0; - - while (i < sequences.size()) - { - if (s == getSequenceAt(i)) - { - return i; - } - - i++; - } - - return -1; - } - - /** - * DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public int getHeight() - { - return sequences.size(); - } - - /** - * DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public int getWidth() - { - int maxLength = -1; - - for (int i = 0; i < sequences.size(); i++) - { - if (getSequenceAt(i).getLength() > maxLength) - { - maxLength = getSequenceAt(i).getLength(); - } - } - - return maxLength; - } - - /** - * DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public int getMaxIdLength() - { - int max = 0; - int i = 0; - - while (i < sequences.size()) - { - SequenceI seq = getSequenceAt(i); - String tmp = seq.getName() + "/" + seq.getStart() + "-" + - seq.getEnd(); - - if (tmp.length() > max) - { - max = tmp.length(); - } - - i++; - } - - return max; - } - - /** - * DOCUMENT ME! - * - * @param gc DOCUMENT ME! - */ - public void setGapCharacter(char gc) - { - gapCharacter = gc; - - for (int i = 0; i < sequences.size(); i++) - { - Sequence seq = (Sequence) sequences.elementAt(i); - seq.sequence = seq.sequence.replace('.', gc); - seq.sequence = seq.sequence.replace('-', gc); - seq.sequence = seq.sequence.replace(' ', gc); - } - } - - /** - * DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public char getGapCharacter() - { - return gapCharacter; - } - - /** - * DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public Vector getAAFrequency() - { - return AAFrequency.calculate(sequences, 0, getWidth()); - } - - /** - * DOCUMENT ME! - * - * @return DOCUMENT ME! - */ - public boolean isAligned() - { - int width = getWidth(); - - for (int i = 0; i < sequences.size(); i++) - { - if (getSequenceAt(i).getLength() != width) - { - return false; - } - } - - return true; - } - - /** - * DOCUMENT ME! - * - * @param aa DOCUMENT ME! - */ - public void deleteAnnotation(AlignmentAnnotation aa) - { - int aSize = 1; - - if (annotations != null) - { - aSize = annotations.length; - } - - AlignmentAnnotation[] temp = new AlignmentAnnotation[aSize - 1]; - - int tIndex = 0; - - for (int i = 0; i < aSize; i++) - { - if (annotations[i] == aa) - { - continue; - } - - temp[tIndex] = annotations[i]; - tIndex++; - } - - annotations = temp; - } - - /** - * - * @param aa AlignmentAnnotation - * @param seqRef The sequence to associate this annotation with - * @return The adjusted AlignmentAnnotation, with dataset sequence and annotation added - */ - public AlignmentAnnotation addAnnotation(AlignmentAnnotation aa, SequenceI seqRef) - { - if(seqRef!=null) - { - //We can only add Annotations to the dataset sequences - if(seqRef.getDatasetSequence()==null) - { - setDataset(null); - } - - AlignmentAnnotation [] old = seqRef.getDatasetSequence().getAnnotation(); - - //First check if this is a new annotation or not. If it is new, - //we must add the annotation to the dataset - boolean newAnnotation = true; - if(seqRef.getDatasetSequence().getAnnotation()!=null) - { - for(int a=0; a 0) - copy = new AlignmentAnnotation( - aa.label, aa.description, aa.annotations, aa.graphMin, - aa.graphMax, aa.graph - ); - else - copy = new AlignmentAnnotation( - aa.label, aa.description, aa.annotations - ); - - copy.datasetAnnotation = aa; - - addAnnotation(copy); - - copy.sequenceRef = seqRef; - - return copy; - } - else - { - addAnnotation(aa); - return aa; - } - } - - public void adjustSequenceAnnotations() - { - if(annotations!=null) - { - for (int a = 0; a < annotations.length; a++) - { - if (annotations[a].sequenceRef != null) - { - annotations[a].adjustForAlignment(); - } - } - } - } - - /** - * DOCUMENT ME! - * - * @param aa DOCUMENT ME! - */ - public void addAnnotation(AlignmentAnnotation aa) - { - int aSize = 1; - if (annotations != null) - { - aSize = annotations.length + 1; - } - - AlignmentAnnotation[] temp = new AlignmentAnnotation[aSize]; - - temp[aSize-1] = aa; - - int i = 0; - - if (aSize > 1) - { - for (i = 0; i < (aSize-1); i++) - { - temp[i] = annotations[i]; - } - } - - annotations = temp; - } - - public void setAnnotationIndex(AlignmentAnnotation aa, int index) - { - if(aa==null || annotations==null || annotations.length-1