/*
- * Jalview - A Sequence Alignment Editor and Viewer (Version 2.7)
- * Copyright (C) 2011 J Procter, AM Waterhouse, J Engelhardt, LM Lui, G Barton, M Clamp, S Searle
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ 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.
- *
+ * 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/>.
+ * 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.
*/
package jalview.analysis;
-import java.util.*;
-
-import java.awt.*;
-
-import jalview.datamodel.*;
-import jalview.schemes.*;
-import jalview.util.*;
+import jalview.datamodel.AlignmentAnnotation;
+import jalview.datamodel.AlignmentI;
+import jalview.datamodel.Mapping;
+import jalview.datamodel.Sequence;
+import jalview.datamodel.SequenceI;
+import jalview.schemes.ResidueProperties;
+import jalview.schemes.ScoreMatrix;
+import jalview.util.Comparison;
+import jalview.util.Format;
+import jalview.util.MapList;
+import jalview.util.MessageManager;
+
+import java.awt.Color;
+import java.awt.Graphics;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.List;
+import java.util.StringTokenizer;
/**
*
}
/**
- * DOCUMENT ME!
+ *
+ * @return aligned instance of Seq 1
+ */
+ public SequenceI getAlignedSeq1()
+ {
+ SequenceI alSeq1 = new Sequence(s1.getName(), getAStr1());
+ alSeq1.setStart(s1.getStart() + getSeq1Start() - 1);
+ alSeq1.setEnd(s1.getStart() + getSeq1End() - 1);
+ alSeq1.setDatasetSequence(s1.getDatasetSequence() == null ? s1 : s1
+ .getDatasetSequence());
+ return alSeq1;
+ }
+
+ /**
+ *
+ * @return aligned instance of Seq 2
+ */
+ public SequenceI getAlignedSeq2()
+ {
+ SequenceI alSeq2 = new Sequence(s2.getName(), getAStr2());
+ alSeq2.setStart(s2.getStart() + getSeq2Start() - 1);
+ alSeq2.setEnd(s2.getStart() + getSeq2End() - 1);
+ alSeq2.setDatasetSequence(s2.getDatasetSequence() == null ? s2 : s2
+ .getDatasetSequence());
+ return alSeq2;
+ }
+
+ /**
+ * Construct score matrix for sequences with standard DNA or PEPTIDE matrix
*
* @param s1
- * DOCUMENT ME!
+ * - sequence 1
* @param string1
- * - string to align for sequence1
+ * - string to use for s1
* @param s2
- * sequence 2
+ * - sequence 2
* @param string2
- * - string to align for sequence2
+ * - string to use for s2
* @param type
* DNA or PEPTIDE
*/
SeqInit(string1, string2);
}
+ /**
+ * Construct score matrix for sequences with custom substitution matrix
+ *
+ * @param s1
+ * - sequence 1
+ * @param string1
+ * - string to use for s1
+ * @param s2
+ * - sequence 2
+ * @param string2
+ * - string to use for s2
+ * @param scoreMatrix
+ * - substitution matrix to use for alignment
+ */
public void SeqInit(SequenceI s1, String string1, SequenceI s2,
String string2, ScoreMatrix scoreMatrix)
{
else
{
output.append("Wrong type = dna or pep only");
- throw new Error("Unknown Type " + type2
- + " - dna or pep are the only allowed values.");
+ throw new Error(MessageManager.formatMessage("error.unknown_type_dna_or_pep", new String[]{type2}));
}
}
output = output.append("\n\n");
}
- pid = pid / (float) (aseq1.length - count) * 100;
+ pid = pid / (aseq1.length - count) * 100;
output = output.append(new Format("Percentage ID = %2.2f\n\n")
.form(pid));
}
/**
+ * Compute a globally optimal needleman and wunsch alignment between two
+ * sequences
+ *
+ * @param s1
+ * @param s2
+ * @param type
+ * AlignSeq.DNA or AlignSeq.PEP
+ */
+ public static AlignSeq doGlobalNWAlignment(SequenceI s1, SequenceI s2,
+ String type)
+ {
+ AlignSeq as = new AlignSeq(s1, s2, type);
+
+ as.calcScoreMatrix();
+ as.traceAlignment();
+ return as;
+ }
+
+ /**
+ *
+ * @return mapping from positions in S1 to corresponding positions in S2
+ */
+ public jalview.datamodel.Mapping getMappingFromS1(boolean allowmismatch)
+ {
+ ArrayList<Integer> as1 = new ArrayList<Integer>(), as2 = new ArrayList<Integer>();
+ int pdbpos = s2.getStart() + getSeq2Start() - 2;
+ int alignpos = s1.getStart() + getSeq1Start() - 2;
+ int lp2 = pdbpos - 3, lp1 = alignpos - 3;
+ boolean lastmatch = false;
+ // and now trace the alignment onto the atom set.
+ for (int i = 0; i < astr1.length(); i++)
+ {
+ char c1 = astr1.charAt(i), c2 = astr2.charAt(i);
+ if (c1 != '-')
+ {
+ alignpos++;
+ }
+
+ if (c2 != '-')
+ {
+ pdbpos++;
+ }
+
+ if (allowmismatch || c1 == c2)
+ {
+ // extend mapping interval
+ if (lp1 + 1 != alignpos || lp2 + 1 != pdbpos)
+ {
+ as1.add(Integer.valueOf(alignpos));
+ as2.add(Integer.valueOf(pdbpos));
+ }
+ lastmatch = true;
+ lp1 = alignpos;
+ lp2 = pdbpos;
+ }
+ else
+ {
+ // extend mapping interval
+ if (lastmatch)
+ {
+ as1.add(Integer.valueOf(lp1));
+ as2.add(Integer.valueOf(lp2));
+ }
+ lastmatch = false;
+ }
+ }
+ // construct range pairs
+
+ int[] mapseq1 = new int[as1.size() + (lastmatch ? 1 : 0)], mapseq2 = new int[as2
+ .size() + (lastmatch ? 1 : 0)];
+ int i = 0;
+ for (Integer ip : as1)
+ {
+ mapseq1[i++] = ip;
+ }
+ ;
+ i = 0;
+ for (Integer ip : as2)
+ {
+ mapseq2[i++] = ip;
+ }
+ ;
+ if (lastmatch)
+ {
+ mapseq1[mapseq1.length - 1] = alignpos;
+ mapseq2[mapseq2.length - 1] = pdbpos;
+ }
+ MapList map = new MapList(mapseq1, mapseq2, 1, 1);
+
+ jalview.datamodel.Mapping mapping = new Mapping(map);
+ mapping.setTo(s2);
+ return mapping;
+ }
+
+ /**
+ * matches ochains against al and populates seqs with the best match between
+ * each ochain and the set in al
+ *
+ * @param ochains
+ * @param al
+ * @param dnaOrProtein
+ * @param removeOldAnnots
+ * when true, old annotation is cleared before new annotation
+ * transferred
+ * @return List<List<SequenceI> originals, List<SequenceI> replacement,
+ * List<AlignSeq> alignment between each>
+ */
+ public static List<List<? extends Object>> replaceMatchingSeqsWith(
+ List<SequenceI> seqs, List<AlignmentAnnotation> annotations,
+ List<SequenceI> ochains,
+ AlignmentI al, String dnaOrProtein, boolean removeOldAnnots)
+ {
+ List<SequenceI> orig = new ArrayList<SequenceI>(), repl = new ArrayList<SequenceI>();
+ List<AlignSeq> aligs = new ArrayList<AlignSeq>();
+ if (al != null && al.getHeight() > 0)
+ {
+ ArrayList<SequenceI> matches = new ArrayList<SequenceI>();
+ ArrayList<AlignSeq> aligns = new ArrayList<AlignSeq>();
+
+ for (SequenceI sq : ochains)
+ {
+ SequenceI bestm = null;
+ AlignSeq bestaseq = null;
+ int bestscore = 0;
+ for (SequenceI msq : al.getSequences())
+ {
+ AlignSeq aseq = doGlobalNWAlignment(msq, sq,
+ dnaOrProtein);
+ if (bestm == null || aseq.getMaxScore() > bestscore)
+ {
+ bestscore = aseq.getMaxScore();
+ bestaseq = aseq;
+ bestm = msq;
+ }
+ }
+ System.out.println("Best Score for " + (matches.size() + 1) + " :"
+ + bestscore);
+ matches.add(bestm);
+ aligns.add(bestaseq);
+ al.deleteSequence(bestm);
+ }
+ for (int p = 0, pSize = seqs.size(); p < pSize; p++)
+ {
+ SequenceI sq, sp = seqs.get(p);
+ int q;
+ if ((q = ochains.indexOf(sp)) > -1)
+ {
+ seqs.set(p, sq = matches.get(q));
+ orig.add(sp);
+ repl.add(sq);
+ sq.setName(sp.getName());
+ sq.setDescription(sp.getDescription());
+ Mapping sp2sq;
+ sq.transferAnnotation(sp, sp2sq = aligns.get(q).getMappingFromS1(false));
+ aligs.add(aligns.get(q));
+ int inspos = -1;
+ for (int ap = 0; ap < annotations.size();)
+ {
+ if (annotations.get(ap).sequenceRef == sp)
+ {
+ if (inspos == -1)
+ {
+ inspos = ap;
+ }
+ if (removeOldAnnots) {
+ annotations.remove(ap);
+ } else {
+ AlignmentAnnotation alan = annotations.remove(ap);
+ alan.liftOver(sq, sp2sq);
+ alan.setSequenceRef(sq);
+ sq.addAlignmentAnnotation(alan);
+ }
+ }
+ else
+ {
+ ap++;
+ }
+ }
+ if (sq.getAnnotation() != null && sq.getAnnotation().length > 0)
+ {
+ annotations.addAll(inspos == -1 ? annotations.size() : inspos,
+ Arrays.asList(sq.getAnnotation()));
+ }
+ }
+ }
+ }
+ return Arrays.asList(orig, repl, aligs);
+ }
+
+ /**
* compute the PID vector used by the redundancy filter.
*
* @param originalSequences