2 // FORESTER -- software libraries and applications
3 // for evolutionary biology research and applications.
5 // Copyright (C) 2008-2009 Christian M. Zmasek
6 // Copyright (C) 2008-2009 Burnham Institute for Medical Research
9 // This library is free software; you can redistribute it and/or
10 // modify it under the terms of the GNU Lesser General Public
11 // License as published by the Free Software Foundation; either
12 // version 2.1 of the License, or (at your option) any later version.
14 // This library is distributed in the hope that it will be useful,
15 // but WITHOUT ANY WARRANTY; without even the implied warranty of
16 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17 // Lesser General Public License for more details.
19 // You should have received a copy of the GNU Lesser General Public
20 // License along with this library; if not, write to the Free Software
21 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
23 // Contact: phylosoft @ gmail . com
24 // WWW: www.phylosoft.org/forester
26 package org.forester.phylogeny;
28 import java.awt.Color;
30 import java.io.IOException;
31 import java.util.ArrayList;
32 import java.util.Arrays;
33 import java.util.Collections;
34 import java.util.Comparator;
35 import java.util.HashSet;
36 import java.util.Iterator;
37 import java.util.List;
39 import java.util.SortedMap;
40 import java.util.TreeMap;
42 import org.forester.io.parsers.PhylogenyParser;
43 import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException;
44 import org.forester.io.parsers.phyloxml.PhyloXmlUtil;
45 import org.forester.io.parsers.util.PhylogenyParserException;
46 import org.forester.phylogeny.data.BranchColor;
47 import org.forester.phylogeny.data.BranchWidth;
48 import org.forester.phylogeny.data.Confidence;
49 import org.forester.phylogeny.data.DomainArchitecture;
50 import org.forester.phylogeny.data.Identifier;
51 import org.forester.phylogeny.data.PhylogenyDataUtil;
52 import org.forester.phylogeny.data.Sequence;
53 import org.forester.phylogeny.data.Taxonomy;
54 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
55 import org.forester.phylogeny.factories.PhylogenyFactory;
56 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
57 import org.forester.util.BasicDescriptiveStatistics;
58 import org.forester.util.DescriptiveStatistics;
59 import org.forester.util.FailedConditionCheckException;
60 import org.forester.util.ForesterUtil;
62 public class PhylogenyMethods {
64 private static PhylogenyMethods _instance = null;
65 private final Set<Integer> _temp_hash_set = new HashSet<Integer>();
66 private PhylogenyNode _farthest_1 = null;
67 private PhylogenyNode _farthest_2 = null;
69 private PhylogenyMethods() {
70 // Hidden constructor.
74 * Calculates the distance between PhylogenyNodes node1 and node2.
79 * @return distance between node1 and node2
81 public double calculateDistance( final PhylogenyNode node1, final PhylogenyNode node2 ) {
82 final PhylogenyNode lca = obtainLCA( node1, node2 );
83 final PhylogenyNode n1 = node1;
84 final PhylogenyNode n2 = node2;
85 return ( PhylogenyMethods.getDistance( n1, lca ) + PhylogenyMethods.getDistance( n2, lca ) );
88 public double calculateFurthestDistance( final Phylogeny phylogeny ) {
89 if ( phylogeny.getNumberOfExternalNodes() < 2 ) {
94 PhylogenyNode node_1 = null;
95 PhylogenyNode node_2 = null;
96 double farthest_d = -Double.MAX_VALUE;
97 final PhylogenyMethods methods = PhylogenyMethods.getInstance();
98 final List<PhylogenyNode> ext_nodes = phylogeny.getRoot().getAllExternalDescendants();
99 for( int i = 1; i < ext_nodes.size(); ++i ) {
100 for( int j = 0; j < i; ++j ) {
101 final double d = methods.calculateDistance( ext_nodes.get( i ), ext_nodes.get( j ) );
103 throw new RuntimeException( "distance cannot be negative" );
105 if ( d > farthest_d ) {
107 node_1 = ext_nodes.get( i );
108 node_2 = ext_nodes.get( j );
112 _farthest_1 = node_1;
113 _farthest_2 = node_2;
118 public Object clone() throws CloneNotSupportedException {
119 throw new CloneNotSupportedException();
122 public PhylogenyNode getFarthestNode1() {
126 public PhylogenyNode getFarthestNode2() {
131 * Returns the LCA of PhylogenyNodes node1 and node2.
136 * @return LCA of node1 and node2
138 public PhylogenyNode obtainLCA( final PhylogenyNode node1, final PhylogenyNode node2 ) {
139 _temp_hash_set.clear();
140 PhylogenyNode n1 = node1;
141 PhylogenyNode n2 = node2;
142 _temp_hash_set.add( n1.getId() );
143 while ( !n1.isRoot() ) {
145 _temp_hash_set.add( n1.getId() );
147 while ( !_temp_hash_set.contains( n2.getId() ) && !n2.isRoot() ) {
150 if ( !_temp_hash_set.contains( n2.getId() ) ) {
151 throw new IllegalArgumentException( "attempt to get LCA of two nodes which do not share a common root" );
157 * Returns all orthologs of the external PhylogenyNode n of this Phylogeny.
158 * Orthologs are returned as List of node references.
160 * PRECONDITION: This tree must be binary and rooted, and speciation -
161 * duplication need to be assigned for each of its internal Nodes.
163 * Returns null if this Phylogeny is empty or if n is internal.
165 * external PhylogenyNode whose orthologs are to be returned
166 * @return Vector of references to all orthologous Nodes of PhylogenyNode n
167 * of this Phylogeny, null if this Phylogeny is empty or if n is
170 public List<PhylogenyNode> getOrthologousNodes( final Phylogeny phy, final PhylogenyNode node ) {
171 final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
172 final PhylogenyNodeIterator it = phy.iteratorExternalForward();
173 while ( it.hasNext() ) {
174 final PhylogenyNode temp_node = it.next();
175 if ( ( temp_node != node ) && isAreOrthologous( node, temp_node ) ) {
176 nodes.add( temp_node );
182 public boolean isAreOrthologous( final PhylogenyNode node1, final PhylogenyNode node2 ) {
183 return !obtainLCA( node1, node2 ).isDuplication();
186 public final static Phylogeny[] readPhylogenies( final PhylogenyParser parser, final File file ) throws IOException {
187 final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
188 final Phylogeny[] trees = factory.create( file, parser );
189 if ( ( trees == null ) || ( trees.length == 0 ) ) {
190 throw new PhylogenyParserException( "Unable to parse phylogeny from file: " + file );
195 public final static Phylogeny[] readPhylogenies( final PhylogenyParser parser, final List<File> files )
197 final List<Phylogeny> tree_list = new ArrayList<Phylogeny>();
198 for( final File file : files ) {
199 final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
200 final Phylogeny[] trees = factory.create( file, parser );
201 if ( ( trees == null ) || ( trees.length == 0 ) ) {
202 throw new PhylogenyParserException( "Unable to parse phylogeny from file: " + file );
204 tree_list.addAll( Arrays.asList( trees ) );
206 return tree_list.toArray( new Phylogeny[ tree_list.size() ] );
209 final static public void transferInternalNodeNamesToConfidence( final Phylogeny phy ) {
210 final PhylogenyNodeIterator it = phy.iteratorPostorder();
211 while ( it.hasNext() ) {
212 final PhylogenyNode n = it.next();
213 if ( !n.isExternal() && !n.getBranchData().isHasConfidences() ) {
214 if ( !ForesterUtil.isEmpty( n.getName() ) ) {
217 d = Double.parseDouble( n.getName() );
219 catch ( final Exception e ) {
223 n.getBranchData().addConfidence( new Confidence( d, "" ) );
231 final static public void transferInternalNamesToBootstrapSupport( final Phylogeny phy ) {
232 final PhylogenyNodeIterator it = phy.iteratorPostorder();
233 while ( it.hasNext() ) {
234 final PhylogenyNode n = it.next();
235 if ( !n.isExternal() && !ForesterUtil.isEmpty( n.getName() ) ) {
238 value = Double.parseDouble( n.getName() );
240 catch ( final NumberFormatException e ) {
241 throw new IllegalArgumentException( "failed to parse number from [" + n.getName() + "]: "
242 + e.getLocalizedMessage() );
244 if ( value >= 0.0 ) {
245 n.getBranchData().addConfidence( new Confidence( value, "bootstrap" ) );
252 final static public void sortNodeDescendents( final PhylogenyNode node, final DESCENDANT_SORT_PRIORITY pri ) {
253 class PhylogenyNodeSortTaxonomyPriority implements Comparator<PhylogenyNode> {
256 public int compare( final PhylogenyNode n1, final PhylogenyNode n2 ) {
257 if ( n1.getNodeData().isHasTaxonomy() && n2.getNodeData().isHasTaxonomy() ) {
258 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getScientificName() ) )
259 && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getScientificName() ) ) ) {
260 return n1.getNodeData().getTaxonomy().getScientificName().toLowerCase()
261 .compareTo( n2.getNodeData().getTaxonomy().getScientificName().toLowerCase() );
263 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getTaxonomyCode() ) )
264 && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getTaxonomyCode() ) ) ) {
265 return n1.getNodeData().getTaxonomy().getTaxonomyCode()
266 .compareTo( n2.getNodeData().getTaxonomy().getTaxonomyCode() );
268 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getCommonName() ) )
269 && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getCommonName() ) ) ) {
270 return n1.getNodeData().getTaxonomy().getCommonName().toLowerCase()
271 .compareTo( n2.getNodeData().getTaxonomy().getCommonName().toLowerCase() );
274 if ( n1.getNodeData().isHasSequence() && n2.getNodeData().isHasSequence() ) {
275 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getName() ) )
276 && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getName() ) ) ) {
277 return n1.getNodeData().getSequence().getName().toLowerCase()
278 .compareTo( n2.getNodeData().getSequence().getName().toLowerCase() );
280 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getSymbol() ) )
281 && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getSymbol() ) ) ) {
282 return n1.getNodeData().getSequence().getSymbol()
283 .compareTo( n2.getNodeData().getSequence().getSymbol() );
285 if ( ( n1.getNodeData().getSequence().getAccession() != null )
286 && ( n2.getNodeData().getSequence().getAccession() != null )
287 && !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getAccession().getValue() )
288 && !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getAccession().getValue() ) ) {
289 return n1.getNodeData().getSequence().getAccession().getValue()
290 .compareTo( n2.getNodeData().getSequence().getAccession().getValue() );
293 if ( ( !ForesterUtil.isEmpty( n1.getName() ) ) && ( !ForesterUtil.isEmpty( n2.getName() ) ) ) {
294 return n1.getName().toLowerCase().compareTo( n2.getName().toLowerCase() );
299 class PhylogenyNodeSortSequencePriority implements Comparator<PhylogenyNode> {
302 public int compare( final PhylogenyNode n1, final PhylogenyNode n2 ) {
303 if ( n1.getNodeData().isHasSequence() && n2.getNodeData().isHasSequence() ) {
304 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getName() ) )
305 && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getName() ) ) ) {
306 return n1.getNodeData().getSequence().getName().toLowerCase()
307 .compareTo( n2.getNodeData().getSequence().getName().toLowerCase() );
309 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getSymbol() ) )
310 && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getSymbol() ) ) ) {
311 return n1.getNodeData().getSequence().getSymbol()
312 .compareTo( n2.getNodeData().getSequence().getSymbol() );
314 if ( ( n1.getNodeData().getSequence().getAccession() != null )
315 && ( n2.getNodeData().getSequence().getAccession() != null )
316 && !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getAccession().getValue() )
317 && !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getAccession().getValue() ) ) {
318 return n1.getNodeData().getSequence().getAccession().getValue()
319 .compareTo( n2.getNodeData().getSequence().getAccession().getValue() );
322 if ( n1.getNodeData().isHasTaxonomy() && n2.getNodeData().isHasTaxonomy() ) {
323 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getScientificName() ) )
324 && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getScientificName() ) ) ) {
325 return n1.getNodeData().getTaxonomy().getScientificName().toLowerCase()
326 .compareTo( n2.getNodeData().getTaxonomy().getScientificName().toLowerCase() );
328 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getTaxonomyCode() ) )
329 && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getTaxonomyCode() ) ) ) {
330 return n1.getNodeData().getTaxonomy().getTaxonomyCode()
331 .compareTo( n2.getNodeData().getTaxonomy().getTaxonomyCode() );
333 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getCommonName() ) )
334 && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getCommonName() ) ) ) {
335 return n1.getNodeData().getTaxonomy().getCommonName().toLowerCase()
336 .compareTo( n2.getNodeData().getTaxonomy().getCommonName().toLowerCase() );
339 if ( ( !ForesterUtil.isEmpty( n1.getName() ) ) && ( !ForesterUtil.isEmpty( n2.getName() ) ) ) {
340 return n1.getName().toLowerCase().compareTo( n2.getName().toLowerCase() );
345 class PhylogenyNodeSortNodeNamePriority implements Comparator<PhylogenyNode> {
348 public int compare( final PhylogenyNode n1, final PhylogenyNode n2 ) {
349 if ( ( !ForesterUtil.isEmpty( n1.getName() ) ) && ( !ForesterUtil.isEmpty( n2.getName() ) ) ) {
350 return n1.getName().toLowerCase().compareTo( n2.getName().toLowerCase() );
352 if ( n1.getNodeData().isHasTaxonomy() && n2.getNodeData().isHasTaxonomy() ) {
353 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getScientificName() ) )
354 && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getScientificName() ) ) ) {
355 return n1.getNodeData().getTaxonomy().getScientificName().toLowerCase()
356 .compareTo( n2.getNodeData().getTaxonomy().getScientificName().toLowerCase() );
358 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getTaxonomyCode() ) )
359 && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getTaxonomyCode() ) ) ) {
360 return n1.getNodeData().getTaxonomy().getTaxonomyCode()
361 .compareTo( n2.getNodeData().getTaxonomy().getTaxonomyCode() );
363 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getCommonName() ) )
364 && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getCommonName() ) ) ) {
365 return n1.getNodeData().getTaxonomy().getCommonName().toLowerCase()
366 .compareTo( n2.getNodeData().getTaxonomy().getCommonName().toLowerCase() );
369 if ( n1.getNodeData().isHasSequence() && n2.getNodeData().isHasSequence() ) {
370 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getName() ) )
371 && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getName() ) ) ) {
372 return n1.getNodeData().getSequence().getName().toLowerCase()
373 .compareTo( n2.getNodeData().getSequence().getName().toLowerCase() );
375 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getSymbol() ) )
376 && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getSymbol() ) ) ) {
377 return n1.getNodeData().getSequence().getSymbol()
378 .compareTo( n2.getNodeData().getSequence().getSymbol() );
380 if ( ( n1.getNodeData().getSequence().getAccession() != null )
381 && ( n2.getNodeData().getSequence().getAccession() != null )
382 && !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getAccession().getValue() )
383 && !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getAccession().getValue() ) ) {
384 return n1.getNodeData().getSequence().getAccession().getValue()
385 .compareTo( n2.getNodeData().getSequence().getAccession().getValue() );
391 Comparator<PhylogenyNode> c;
394 c = new PhylogenyNodeSortSequencePriority();
397 c = new PhylogenyNodeSortNodeNamePriority();
400 c = new PhylogenyNodeSortTaxonomyPriority();
402 final List<PhylogenyNode> descs = node.getDescendants();
403 Collections.sort( descs, c );
405 for( final PhylogenyNode desc : descs ) {
406 node.setChildNode( i++, desc );
410 final static public void transferNodeNameToField( final Phylogeny phy,
411 final PhylogenyMethods.PhylogenyNodeField field,
412 final boolean external_only ) throws PhyloXmlDataFormatException {
413 final PhylogenyNodeIterator it = phy.iteratorPostorder();
414 while ( it.hasNext() ) {
415 final PhylogenyNode n = it.next();
416 if ( external_only && n.isInternal() ) {
419 final String name = n.getName().trim();
420 if ( !ForesterUtil.isEmpty( name ) ) {
424 setTaxonomyCode( n, name );
426 case TAXONOMY_SCIENTIFIC_NAME:
428 if ( !n.getNodeData().isHasTaxonomy() ) {
429 n.getNodeData().setTaxonomy( new Taxonomy() );
431 n.getNodeData().getTaxonomy().setScientificName( name );
433 case TAXONOMY_COMMON_NAME:
435 if ( !n.getNodeData().isHasTaxonomy() ) {
436 n.getNodeData().setTaxonomy( new Taxonomy() );
438 n.getNodeData().getTaxonomy().setCommonName( name );
440 case SEQUENCE_SYMBOL:
442 if ( !n.getNodeData().isHasSequence() ) {
443 n.getNodeData().setSequence( new Sequence() );
445 n.getNodeData().getSequence().setSymbol( name );
449 if ( !n.getNodeData().isHasSequence() ) {
450 n.getNodeData().setSequence( new Sequence() );
452 n.getNodeData().getSequence().setName( name );
454 case TAXONOMY_ID_UNIPROT_1: {
455 if ( !n.getNodeData().isHasTaxonomy() ) {
456 n.getNodeData().setTaxonomy( new Taxonomy() );
459 final int i = name.indexOf( '_' );
461 id = name.substring( 0, i );
466 n.getNodeData().getTaxonomy()
467 .setIdentifier( new Identifier( id, PhyloXmlUtil.UNIPROT_TAX_PROVIDER ) );
470 case TAXONOMY_ID_UNIPROT_2: {
471 if ( !n.getNodeData().isHasTaxonomy() ) {
472 n.getNodeData().setTaxonomy( new Taxonomy() );
475 final int i = name.indexOf( '_' );
477 id = name.substring( i + 1, name.length() );
482 n.getNodeData().getTaxonomy()
483 .setIdentifier( new Identifier( id, PhyloXmlUtil.UNIPROT_TAX_PROVIDER ) );
487 if ( !n.getNodeData().isHasTaxonomy() ) {
488 n.getNodeData().setTaxonomy( new Taxonomy() );
490 n.getNodeData().getTaxonomy().setIdentifier( new Identifier( name ) );
498 static double addPhylogenyDistances( final double a, final double b ) {
499 if ( ( a >= 0.0 ) && ( b >= 0.0 ) ) {
502 else if ( a >= 0.0 ) {
505 else if ( b >= 0.0 ) {
508 return PhylogenyDataUtil.BRANCH_LENGTH_DEFAULT;
511 // Helper for getUltraParalogousNodes( PhylogenyNode ).
512 public static boolean areAllChildrenDuplications( final PhylogenyNode n ) {
513 if ( n.isExternal() ) {
517 if ( n.isDuplication() ) {
519 for( final PhylogenyNode desc : n.getDescendants() ) {
520 if ( !areAllChildrenDuplications( desc ) ) {
532 public static int calculateDepth( final PhylogenyNode node ) {
533 PhylogenyNode n = node;
535 while ( !n.isRoot() ) {
542 public static double calculateDistanceToRoot( final PhylogenyNode node ) {
543 PhylogenyNode n = node;
545 while ( !n.isRoot() ) {
546 if ( n.getDistanceToParent() > 0.0 ) {
547 d += n.getDistanceToParent();
554 public static short calculateMaxBranchesToLeaf( final PhylogenyNode node ) {
555 if ( node.isExternal() ) {
559 for( PhylogenyNode d : node.getAllExternalDescendants() ) {
561 while ( d != node ) {
562 if ( d.isCollapse() ) {
577 public static int calculateMaxDepth( final Phylogeny phy ) {
579 for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) {
580 final PhylogenyNode node = iter.next();
581 final int steps = calculateDepth( node );
589 public static double calculateMaxDistanceToRoot( final Phylogeny phy ) {
591 for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) {
592 final PhylogenyNode node = iter.next();
593 final double d = calculateDistanceToRoot( node );
601 public static DescriptiveStatistics calculatNumberOfDescendantsPerNodeStatistics( final Phylogeny phy ) {
602 final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
603 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
604 final PhylogenyNode n = iter.next();
605 if ( !n.isExternal() ) {
606 stats.addValue( n.getNumberOfDescendants() );
612 public static DescriptiveStatistics calculatBranchLengthStatistics( final Phylogeny phy ) {
613 final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
614 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
615 final PhylogenyNode n = iter.next();
616 if ( !n.isRoot() && ( n.getDistanceToParent() >= 0.0 ) ) {
617 stats.addValue( n.getDistanceToParent() );
623 public static List<DescriptiveStatistics> calculatConfidenceStatistics( final Phylogeny phy ) {
624 final List<DescriptiveStatistics> stats = new ArrayList<DescriptiveStatistics>();
625 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
626 final PhylogenyNode n = iter.next();
627 if ( !n.isExternal() && !n.isRoot() ) {
628 if ( n.getBranchData().isHasConfidences() ) {
629 for( int i = 0; i < n.getBranchData().getConfidences().size(); ++i ) {
630 final Confidence c = n.getBranchData().getConfidences().get( i );
631 if ( ( i > ( stats.size() - 1 ) ) || ( stats.get( i ) == null ) ) {
632 stats.add( i, new BasicDescriptiveStatistics() );
634 if ( !ForesterUtil.isEmpty( c.getType() ) ) {
635 if ( !ForesterUtil.isEmpty( stats.get( i ).getDescription() ) ) {
636 if ( !stats.get( i ).getDescription().equalsIgnoreCase( c.getType() ) ) {
637 throw new IllegalArgumentException( "support values in node [" + n.toString()
638 + "] appear inconsistently ordered" );
641 stats.get( i ).setDescription( c.getType() );
643 stats.get( i ).addValue( ( ( c != null ) && ( c.getValue() >= 0 ) ) ? c.getValue() : 0 );
652 * Returns the set of distinct taxonomies of
653 * all external nodes of node.
654 * If at least one the external nodes has no taxonomy,
658 public static Set<Taxonomy> obtainDistinctTaxonomies( final PhylogenyNode node ) {
659 final List<PhylogenyNode> descs = node.getAllExternalDescendants();
660 final Set<Taxonomy> tax_set = new HashSet<Taxonomy>();
661 for( final PhylogenyNode n : descs ) {
662 if ( !n.getNodeData().isHasTaxonomy() || n.getNodeData().getTaxonomy().isEmpty() ) {
665 tax_set.add( n.getNodeData().getTaxonomy() );
671 * Returns a map of distinct taxonomies of
672 * all external nodes of node.
673 * If at least one of the external nodes has no taxonomy,
677 public static SortedMap<Taxonomy, Integer> obtainDistinctTaxonomyCounts( final PhylogenyNode node ) {
678 final List<PhylogenyNode> descs = node.getAllExternalDescendants();
679 final SortedMap<Taxonomy, Integer> tax_map = new TreeMap<Taxonomy, Integer>();
680 for( final PhylogenyNode n : descs ) {
681 if ( !n.getNodeData().isHasTaxonomy() || n.getNodeData().getTaxonomy().isEmpty() ) {
684 final Taxonomy t = n.getNodeData().getTaxonomy();
685 if ( tax_map.containsKey( t ) ) {
686 tax_map.put( t, tax_map.get( t ) + 1 );
695 public static int calculateNumberOfExternalNodesWithoutTaxonomy( final PhylogenyNode node ) {
696 final List<PhylogenyNode> descs = node.getAllExternalDescendants();
698 for( final PhylogenyNode n : descs ) {
699 if ( !n.getNodeData().isHasTaxonomy() || n.getNodeData().getTaxonomy().isEmpty() ) {
707 * Deep copies the phylogeny originating from this node.
709 static PhylogenyNode copySubTree( final PhylogenyNode source ) {
710 if ( source == null ) {
714 final PhylogenyNode newnode = source.copyNodeData();
715 if ( !source.isExternal() ) {
716 for( int i = 0; i < source.getNumberOfDescendants(); ++i ) {
717 newnode.setChildNode( i, PhylogenyMethods.copySubTree( source.getChildNode( i ) ) );
725 * Shallow copies the phylogeny originating from this node.
727 static PhylogenyNode copySubTreeShallow( final PhylogenyNode source ) {
728 if ( source == null ) {
732 final PhylogenyNode newnode = source.copyNodeDataShallow();
733 if ( !source.isExternal() ) {
734 for( int i = 0; i < source.getNumberOfDescendants(); ++i ) {
735 newnode.setChildNode( i, PhylogenyMethods.copySubTreeShallow( source.getChildNode( i ) ) );
742 public static void deleteExternalNodesNegativeSelection( final Set<Integer> to_delete, final Phylogeny phy ) {
744 for( final Integer id : to_delete ) {
745 phy.deleteSubtree( phy.getNode( id ), true );
750 public static void deleteExternalNodesNegativeSelection( final String[] node_names_to_delete, final Phylogeny p )
751 throws IllegalArgumentException {
752 for( int i = 0; i < node_names_to_delete.length; ++i ) {
753 if ( ForesterUtil.isEmpty( node_names_to_delete[ i ] ) ) {
756 List<PhylogenyNode> nodes = null;
757 nodes = p.getNodes( node_names_to_delete[ i ] );
758 final Iterator<PhylogenyNode> it = nodes.iterator();
759 while ( it.hasNext() ) {
760 final PhylogenyNode n = it.next();
761 if ( !n.isExternal() ) {
762 throw new IllegalArgumentException( "attempt to delete non-external node \""
763 + node_names_to_delete[ i ] + "\"" );
765 p.deleteSubtree( n, true );
770 public static void deleteExternalNodesPositiveSelection( final Set<Taxonomy> species_to_keep, final Phylogeny phy ) {
771 // final Set<Integer> to_delete = new HashSet<Integer>();
772 for( final PhylogenyNodeIterator it = phy.iteratorExternalForward(); it.hasNext(); ) {
773 final PhylogenyNode n = it.next();
774 if ( n.getNodeData().isHasTaxonomy() ) {
775 if ( !species_to_keep.contains( n.getNodeData().getTaxonomy() ) ) {
776 //to_delete.add( n.getNodeId() );
777 phy.deleteSubtree( n, true );
781 throw new IllegalArgumentException( "node " + n.getId() + " has no taxonomic data" );
785 phy.externalNodesHaveChanged();
786 // deleteExternalNodesNegativeSelection( to_delete, phy );
789 public static List<String> deleteExternalNodesPositiveSelection( final String[] node_names_to_keep,
790 final Phylogeny p ) {
791 final PhylogenyNodeIterator it = p.iteratorExternalForward();
792 final String[] to_delete = new String[ p.getNumberOfExternalNodes() ];
794 Arrays.sort( node_names_to_keep );
795 while ( it.hasNext() ) {
796 final String curent_name = it.next().getName();
797 if ( Arrays.binarySearch( node_names_to_keep, curent_name ) < 0 ) {
798 to_delete[ i++ ] = curent_name;
801 PhylogenyMethods.deleteExternalNodesNegativeSelection( to_delete, p );
802 final List<String> deleted = new ArrayList<String>();
803 for( final String n : to_delete ) {
804 if ( !ForesterUtil.isEmpty( n ) ) {
811 public static List<PhylogenyNode> getAllDescendants( final PhylogenyNode node ) {
812 final List<PhylogenyNode> descs = new ArrayList<PhylogenyNode>();
813 final Set<Integer> encountered = new HashSet<Integer>();
814 if ( !node.isExternal() ) {
815 final List<PhylogenyNode> exts = node.getAllExternalDescendants();
816 for( PhylogenyNode current : exts ) {
817 descs.add( current );
818 while ( current != node ) {
819 current = current.getParent();
820 if ( encountered.contains( current.getId() ) ) {
823 descs.add( current );
824 encountered.add( current.getId() );
838 public static Color getBranchColorValue( final PhylogenyNode node ) {
839 if ( node.getBranchData().getBranchColor() == null ) {
842 return node.getBranchData().getBranchColor().getValue();
848 public static double getBranchWidthValue( final PhylogenyNode node ) {
849 if ( !node.getBranchData().isHasBranchWidth() ) {
850 return BranchWidth.BRANCH_WIDTH_DEFAULT_VALUE;
852 return node.getBranchData().getBranchWidth().getValue();
858 public static double getConfidenceValue( final PhylogenyNode node ) {
859 if ( !node.getBranchData().isHasConfidences() ) {
860 return Confidence.CONFIDENCE_DEFAULT_VALUE;
862 return node.getBranchData().getConfidence( 0 ).getValue();
868 public static double[] getConfidenceValuesAsArray( final PhylogenyNode node ) {
869 if ( !node.getBranchData().isHasConfidences() ) {
870 return new double[ 0 ];
872 final double[] values = new double[ node.getBranchData().getConfidences().size() ];
874 for( final Confidence c : node.getBranchData().getConfidences() ) {
875 values[ i++ ] = c.getValue();
881 * Calculates the distance between PhylogenyNodes n1 and n2.
882 * PRECONDITION: n1 is a descendant of n2.
887 * @return distance between n1 and n2
889 private static double getDistance( PhylogenyNode n1, final PhylogenyNode n2 ) {
892 if ( n1.getDistanceToParent() > 0.0 ) {
893 d += n1.getDistanceToParent();
901 * Returns taxonomy t if all external descendants have
902 * the same taxonomy t, null otherwise.
905 public static Taxonomy getExternalDescendantsTaxonomy( final PhylogenyNode node ) {
906 final List<PhylogenyNode> descs = node.getAllExternalDescendants();
908 for( final PhylogenyNode n : descs ) {
909 if ( !n.getNodeData().isHasTaxonomy() || n.getNodeData().getTaxonomy().isEmpty() ) {
912 else if ( tax == null ) {
913 tax = n.getNodeData().getTaxonomy();
915 else if ( n.getNodeData().getTaxonomy().isEmpty() || !tax.isEqual( n.getNodeData().getTaxonomy() ) ) {
922 public static PhylogenyNode getFurthestDescendant( final PhylogenyNode node ) {
923 final List<PhylogenyNode> children = node.getAllExternalDescendants();
924 PhylogenyNode farthest = null;
925 double longest = -Double.MAX_VALUE;
926 for( final PhylogenyNode child : children ) {
927 if ( PhylogenyMethods.getDistance( child, node ) > longest ) {
929 longest = PhylogenyMethods.getDistance( child, node );
935 public static PhylogenyMethods getInstance() {
936 if ( PhylogenyMethods._instance == null ) {
937 PhylogenyMethods._instance = new PhylogenyMethods();
939 return PhylogenyMethods._instance;
943 * Returns the largest confidence value found on phy.
945 static public double getMaximumConfidenceValue( final Phylogeny phy ) {
946 double max = -Double.MAX_VALUE;
947 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
948 final double s = PhylogenyMethods.getConfidenceValue( iter.next() );
949 if ( ( s != Confidence.CONFIDENCE_DEFAULT_VALUE ) && ( s > max ) ) {
956 static public int getMinimumDescendentsPerInternalNodes( final Phylogeny phy ) {
957 int min = Integer.MAX_VALUE;
960 for( final PhylogenyNodeIterator it = phy.iteratorPreorder(); it.hasNext(); ) {
962 if ( n.isInternal() ) {
963 d = n.getNumberOfDescendants();
973 * Convenience method for display purposes.
974 * Not intended for algorithms.
976 public static String getSpecies( final PhylogenyNode node ) {
977 if ( !node.getNodeData().isHasTaxonomy() ) {
980 else if ( !ForesterUtil.isEmpty( node.getNodeData().getTaxonomy().getScientificName() ) ) {
981 return node.getNodeData().getTaxonomy().getScientificName();
983 if ( !ForesterUtil.isEmpty( node.getNodeData().getTaxonomy().getTaxonomyCode() ) ) {
984 return node.getNodeData().getTaxonomy().getTaxonomyCode();
987 return node.getNodeData().getTaxonomy().getCommonName();
992 * Returns all Nodes which are connected to external PhylogenyNode n of this
993 * Phylogeny by a path containing only speciation events. We call these
994 * "super orthologs". Nodes are returned as Vector of references to Nodes.
996 * PRECONDITION: This tree must be binary and rooted, and speciation -
997 * duplication need to be assigned for each of its internal Nodes.
999 * Returns null if this Phylogeny is empty or if n is internal.
1001 * external PhylogenyNode whose strictly speciation related Nodes
1002 * are to be returned
1003 * @return Vector of references to all strictly speciation related Nodes of
1004 * PhylogenyNode n of this Phylogeny, null if this Phylogeny is
1005 * empty or if n is internal
1007 public static List<PhylogenyNode> getSuperOrthologousNodes( final PhylogenyNode n ) {
1009 PhylogenyNode node = n, deepest = null;
1010 final List<PhylogenyNode> v = new ArrayList<PhylogenyNode>();
1011 if ( !node.isExternal() ) {
1014 while ( !node.isRoot() && !node.getParent().isDuplication() ) {
1015 node = node.getParent();
1018 deepest.setIndicatorsToZero();
1020 if ( !node.isExternal() ) {
1021 if ( node.getIndicator() == 0 ) {
1022 node.setIndicator( ( byte ) 1 );
1023 if ( !node.isDuplication() ) {
1024 node = node.getChildNode1();
1027 if ( node.getIndicator() == 1 ) {
1028 node.setIndicator( ( byte ) 2 );
1029 if ( !node.isDuplication() ) {
1030 node = node.getChildNode2();
1033 if ( ( node != deepest ) && ( node.getIndicator() == 2 ) ) {
1034 node = node.getParent();
1041 if ( node != deepest ) {
1042 node = node.getParent();
1045 node.setIndicator( ( byte ) 2 );
1048 } while ( ( node != deepest ) || ( deepest.getIndicator() != 2 ) );
1053 * Convenience method for display purposes.
1054 * Not intended for algorithms.
1056 public static String getTaxonomyIdentifier( final PhylogenyNode node ) {
1057 if ( !node.getNodeData().isHasTaxonomy() || ( node.getNodeData().getTaxonomy().getIdentifier() == null ) ) {
1060 return node.getNodeData().getTaxonomy().getIdentifier().getValue();
1064 * Returns all Nodes which are connected to external PhylogenyNode n of this
1065 * Phylogeny by a path containing, and leading to, only duplication events.
1066 * We call these "ultra paralogs". Nodes are returned as Vector of
1067 * references to Nodes.
1069 * PRECONDITION: This tree must be binary and rooted, and speciation -
1070 * duplication need to be assigned for each of its internal Nodes.
1072 * Returns null if this Phylogeny is empty or if n is internal.
1074 * (Last modified: 10/06/01)
1077 * external PhylogenyNode whose ultra paralogs are to be returned
1078 * @return Vector of references to all ultra paralogs of PhylogenyNode n of
1079 * this Phylogeny, null if this Phylogeny is empty or if n is
1082 public static List<PhylogenyNode> getUltraParalogousNodes( final PhylogenyNode n ) {
1084 PhylogenyNode node = n;
1085 if ( !node.isExternal() ) {
1088 while ( !node.isRoot() && node.getParent().isDuplication() && areAllChildrenDuplications( node.getParent() ) ) {
1089 node = node.getParent();
1091 final List<PhylogenyNode> nodes = node.getAllExternalDescendants();
1096 public static String inferCommonPartOfScientificNameOfDescendants( final PhylogenyNode node ) {
1097 final List<PhylogenyNode> descs = node.getDescendants();
1099 for( final PhylogenyNode n : descs ) {
1100 if ( !n.getNodeData().isHasTaxonomy()
1101 || ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
1104 else if ( sn == null ) {
1105 sn = n.getNodeData().getTaxonomy().getScientificName().trim();
1108 String sn_current = n.getNodeData().getTaxonomy().getScientificName().trim();
1109 if ( !sn.equals( sn_current ) ) {
1110 boolean overlap = false;
1111 while ( ( sn.indexOf( ' ' ) >= 0 ) || ( sn_current.indexOf( ' ' ) >= 0 ) ) {
1112 if ( ForesterUtil.countChars( sn, ' ' ) > ForesterUtil.countChars( sn_current, ' ' ) ) {
1113 sn = sn.substring( 0, sn.lastIndexOf( ' ' ) ).trim();
1116 sn_current = sn_current.substring( 0, sn_current.lastIndexOf( ' ' ) ).trim();
1118 if ( sn.equals( sn_current ) ) {
1132 public static boolean isHasExternalDescendant( final PhylogenyNode node ) {
1133 for( int i = 0; i < node.getNumberOfDescendants(); ++i ) {
1134 if ( node.getChildNode( i ).isExternal() ) {
1142 * This is case insensitive.
1145 public synchronized static boolean isTaxonomyHasIdentifierOfGivenProvider( final Taxonomy tax,
1146 final String[] providers ) {
1147 if ( ( tax.getIdentifier() != null ) && !ForesterUtil.isEmpty( tax.getIdentifier().getProvider() ) ) {
1148 final String my_tax_prov = tax.getIdentifier().getProvider();
1149 for( final String provider : providers ) {
1150 if ( provider.equalsIgnoreCase( my_tax_prov ) ) {
1161 private static boolean match( final String s,
1163 final boolean case_sensitive,
1164 final boolean partial ) {
1165 if ( ForesterUtil.isEmpty( s ) || ForesterUtil.isEmpty( query ) ) {
1168 String my_s = s.trim();
1169 String my_query = query.trim();
1170 if ( !case_sensitive ) {
1171 my_s = my_s.toLowerCase();
1172 my_query = my_query.toLowerCase();
1175 return my_s.indexOf( my_query ) >= 0;
1178 return my_s.equals( my_query );
1182 public static void midpointRoot( final Phylogeny phylogeny ) {
1183 if ( phylogeny.getNumberOfExternalNodes() < 2 ) {
1186 final PhylogenyMethods methods = getInstance();
1187 final double farthest_d = methods.calculateFurthestDistance( phylogeny );
1188 final PhylogenyNode f1 = methods.getFarthestNode1();
1189 final PhylogenyNode f2 = methods.getFarthestNode2();
1190 if ( farthest_d <= 0.0 ) {
1193 double x = farthest_d / 2.0;
1194 PhylogenyNode n = f1;
1195 if ( PhylogenyMethods.getDistance( f1, phylogeny.getRoot() ) < PhylogenyMethods.getDistance( f2, phylogeny
1199 while ( ( x > n.getDistanceToParent() ) && !n.isRoot() ) {
1200 x -= ( n.getDistanceToParent() > 0 ? n.getDistanceToParent() : 0 );
1203 phylogeny.reRoot( n, x );
1204 phylogeny.recalculateNumberOfExternalDescendants( true );
1205 final PhylogenyNode a = getFurthestDescendant( phylogeny.getRoot().getChildNode1() );
1206 final PhylogenyNode b = getFurthestDescendant( phylogeny.getRoot().getChildNode2() );
1207 final double da = getDistance( a, phylogeny.getRoot() );
1208 final double db = getDistance( b, phylogeny.getRoot() );
1209 if ( Math.abs( da - db ) > 0.000001 ) {
1210 throw new FailedConditionCheckException( "this should not have happened: midpoint rooting failed: da="
1211 + da + ", db=" + db + ", diff=" + Math.abs( da - db ) );
1215 public static void normalizeBootstrapValues( final Phylogeny phylogeny,
1216 final double max_bootstrap_value,
1217 final double max_normalized_value ) {
1218 for( final PhylogenyNodeIterator iter = phylogeny.iteratorPreorder(); iter.hasNext(); ) {
1219 final PhylogenyNode node = iter.next();
1220 if ( node.isInternal() ) {
1221 final double confidence = getConfidenceValue( node );
1222 if ( confidence != Confidence.CONFIDENCE_DEFAULT_VALUE ) {
1223 if ( confidence >= max_bootstrap_value ) {
1224 setBootstrapConfidence( node, max_normalized_value );
1227 setBootstrapConfidence( node, ( confidence * max_normalized_value ) / max_bootstrap_value );
1234 public static List<PhylogenyNode> obtainAllNodesAsList( final Phylogeny phy ) {
1235 final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
1236 if ( phy.isEmpty() ) {
1239 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
1240 nodes.add( iter.next() );
1245 public static void postorderBranchColorAveragingExternalNodeBased( final Phylogeny p ) {
1246 for( final PhylogenyNodeIterator iter = p.iteratorPostorder(); iter.hasNext(); ) {
1247 final PhylogenyNode node = iter.next();
1252 if ( node.isInternal() ) {
1253 //for( final PhylogenyNodeIterator iterator = node.iterateChildNodesForward(); iterator.hasNext(); ) {
1254 for( int i = 0; i < node.getNumberOfDescendants(); ++i ) {
1255 final PhylogenyNode child_node = node.getChildNode( i );
1256 final Color child_color = getBranchColorValue( child_node );
1257 if ( child_color != null ) {
1259 red += child_color.getRed();
1260 green += child_color.getGreen();
1261 blue += child_color.getBlue();
1264 setBranchColorValue( node,
1265 new Color( ForesterUtil.roundToInt( red / n ),
1266 ForesterUtil.roundToInt( green / n ),
1267 ForesterUtil.roundToInt( blue / n ) ) );
1272 public static void removeNode( final PhylogenyNode remove_me, final Phylogeny phylogeny ) {
1273 if ( remove_me.isRoot() ) {
1274 throw new IllegalArgumentException( "ill advised attempt to remove root node" );
1276 if ( remove_me.isExternal() ) {
1277 phylogeny.deleteSubtree( remove_me, false );
1280 final PhylogenyNode parent = remove_me.getParent();
1281 final List<PhylogenyNode> descs = remove_me.getDescendants();
1282 parent.removeChildNode( remove_me );
1283 for( final PhylogenyNode desc : descs ) {
1284 parent.addAsChild( desc );
1285 desc.setDistanceToParent( addPhylogenyDistances( remove_me.getDistanceToParent(),
1286 desc.getDistanceToParent() ) );
1288 remove_me.setParent( null );
1289 phylogeny.setIdHash( null );
1290 phylogeny.externalNodesHaveChanged();
1294 public static List<PhylogenyNode> searchData( final String query,
1295 final Phylogeny phy,
1296 final boolean case_sensitive,
1297 final boolean partial ) {
1298 final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
1299 if ( phy.isEmpty() || ( query == null ) ) {
1302 if ( ForesterUtil.isEmpty( query ) ) {
1305 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
1306 final PhylogenyNode node = iter.next();
1307 boolean match = false;
1308 if ( match( node.getName(), query, case_sensitive, partial ) ) {
1311 else if ( node.getNodeData().isHasTaxonomy()
1312 && match( node.getNodeData().getTaxonomy().getTaxonomyCode(), query, case_sensitive, partial ) ) {
1315 else if ( node.getNodeData().isHasTaxonomy()
1316 && match( node.getNodeData().getTaxonomy().getCommonName(), query, case_sensitive, partial ) ) {
1319 else if ( node.getNodeData().isHasTaxonomy()
1320 && match( node.getNodeData().getTaxonomy().getScientificName(), query, case_sensitive, partial ) ) {
1323 else if ( node.getNodeData().isHasTaxonomy()
1324 && ( node.getNodeData().getTaxonomy().getIdentifier() != null )
1325 && match( node.getNodeData().getTaxonomy().getIdentifier().getValue(),
1331 else if ( node.getNodeData().isHasTaxonomy() && !node.getNodeData().getTaxonomy().getSynonyms().isEmpty() ) {
1332 final List<String> syns = node.getNodeData().getTaxonomy().getSynonyms();
1333 I: for( final String syn : syns ) {
1334 if ( match( syn, query, case_sensitive, partial ) ) {
1340 if ( !match && node.getNodeData().isHasSequence()
1341 && match( node.getNodeData().getSequence().getName(), query, case_sensitive, partial ) ) {
1344 if ( !match && node.getNodeData().isHasSequence()
1345 && match( node.getNodeData().getSequence().getSymbol(), query, case_sensitive, partial ) ) {
1349 && node.getNodeData().isHasSequence()
1350 && ( node.getNodeData().getSequence().getAccession() != null )
1351 && match( node.getNodeData().getSequence().getAccession().getValue(),
1357 if ( !match && node.getNodeData().isHasSequence()
1358 && ( node.getNodeData().getSequence().getDomainArchitecture() != null ) ) {
1359 final DomainArchitecture da = node.getNodeData().getSequence().getDomainArchitecture();
1360 I: for( int i = 0; i < da.getNumberOfDomains(); ++i ) {
1361 if ( match( da.getDomain( i ).getName(), query, case_sensitive, partial ) ) {
1367 if ( !match && ( node.getNodeData().getBinaryCharacters() != null ) ) {
1368 Iterator<String> it = node.getNodeData().getBinaryCharacters().getPresentCharacters().iterator();
1369 I: while ( it.hasNext() ) {
1370 if ( match( it.next(), query, case_sensitive, partial ) ) {
1375 it = node.getNodeData().getBinaryCharacters().getGainedCharacters().iterator();
1376 I: while ( it.hasNext() ) {
1377 if ( match( it.next(), query, case_sensitive, partial ) ) {
1390 public static List<PhylogenyNode> searchDataLogicalAnd( final String[] queries,
1391 final Phylogeny phy,
1392 final boolean case_sensitive,
1393 final boolean partial ) {
1394 final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
1395 if ( phy.isEmpty() || ( queries == null ) || ( queries.length < 1 ) ) {
1398 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
1399 final PhylogenyNode node = iter.next();
1400 boolean all_matched = true;
1401 for( final String query : queries ) {
1402 boolean match = false;
1403 if ( ForesterUtil.isEmpty( query ) ) {
1406 if ( match( node.getName(), query, case_sensitive, partial ) ) {
1409 else if ( node.getNodeData().isHasTaxonomy()
1410 && match( node.getNodeData().getTaxonomy().getTaxonomyCode(), query, case_sensitive, partial ) ) {
1413 else if ( node.getNodeData().isHasTaxonomy()
1414 && match( node.getNodeData().getTaxonomy().getCommonName(), query, case_sensitive, partial ) ) {
1417 else if ( node.getNodeData().isHasTaxonomy()
1418 && match( node.getNodeData().getTaxonomy().getScientificName(), query, case_sensitive, partial ) ) {
1421 else if ( node.getNodeData().isHasTaxonomy()
1422 && ( node.getNodeData().getTaxonomy().getIdentifier() != null )
1423 && match( node.getNodeData().getTaxonomy().getIdentifier().getValue(),
1429 else if ( node.getNodeData().isHasTaxonomy()
1430 && !node.getNodeData().getTaxonomy().getSynonyms().isEmpty() ) {
1431 final List<String> syns = node.getNodeData().getTaxonomy().getSynonyms();
1432 I: for( final String syn : syns ) {
1433 if ( match( syn, query, case_sensitive, partial ) ) {
1439 if ( !match && node.getNodeData().isHasSequence()
1440 && match( node.getNodeData().getSequence().getName(), query, case_sensitive, partial ) ) {
1443 if ( !match && node.getNodeData().isHasSequence()
1444 && match( node.getNodeData().getSequence().getSymbol(), query, case_sensitive, partial ) ) {
1448 && node.getNodeData().isHasSequence()
1449 && ( node.getNodeData().getSequence().getAccession() != null )
1450 && match( node.getNodeData().getSequence().getAccession().getValue(),
1456 if ( !match && node.getNodeData().isHasSequence()
1457 && ( node.getNodeData().getSequence().getDomainArchitecture() != null ) ) {
1458 final DomainArchitecture da = node.getNodeData().getSequence().getDomainArchitecture();
1459 I: for( int i = 0; i < da.getNumberOfDomains(); ++i ) {
1460 if ( match( da.getDomain( i ).getName(), query, case_sensitive, partial ) ) {
1466 if ( !match && ( node.getNodeData().getBinaryCharacters() != null ) ) {
1467 Iterator<String> it = node.getNodeData().getBinaryCharacters().getPresentCharacters().iterator();
1468 I: while ( it.hasNext() ) {
1469 if ( match( it.next(), query, case_sensitive, partial ) ) {
1474 it = node.getNodeData().getBinaryCharacters().getGainedCharacters().iterator();
1475 I: while ( it.hasNext() ) {
1476 if ( match( it.next(), query, case_sensitive, partial ) ) {
1481 // final String[] bcp_ary = node.getNodeData().getBinaryCharacters()
1482 // .getPresentCharactersAsStringArray();
1483 // I: for( final String bc : bcp_ary ) {
1484 // if ( match( bc, query, case_sensitive, partial ) ) {
1489 // final String[] bcg_ary = node.getNodeData().getBinaryCharacters()
1490 // .getGainedCharactersAsStringArray();
1491 // I: for( final String bc : bcg_ary ) {
1492 // if ( match( bc, query, case_sensitive, partial ) ) {
1499 all_matched = false;
1503 if ( all_matched ) {
1511 * Convenience method.
1512 * Sets value for the first confidence value (created if not present, values overwritten otherwise).
1514 public static void setBootstrapConfidence( final PhylogenyNode node, final double bootstrap_confidence_value ) {
1515 setConfidence( node, bootstrap_confidence_value, "bootstrap" );
1518 public static void setBranchColorValue( final PhylogenyNode node, final Color color ) {
1519 if ( node.getBranchData().getBranchColor() == null ) {
1520 node.getBranchData().setBranchColor( new BranchColor() );
1522 node.getBranchData().getBranchColor().setValue( color );
1526 * Convenience method
1528 public static void setBranchWidthValue( final PhylogenyNode node, final double branch_width_value ) {
1529 node.getBranchData().setBranchWidth( new BranchWidth( branch_width_value ) );
1533 * Convenience method.
1534 * Sets value for the first confidence value (created if not present, values overwritten otherwise).
1536 public static void setConfidence( final PhylogenyNode node, final double confidence_value ) {
1537 setConfidence( node, confidence_value, "" );
1541 * Convenience method.
1542 * Sets value for the first confidence value (created if not present, values overwritten otherwise).
1544 public static void setConfidence( final PhylogenyNode node, final double confidence_value, final String type ) {
1545 Confidence c = null;
1546 if ( node.getBranchData().getNumberOfConfidences() > 0 ) {
1547 c = node.getBranchData().getConfidence( 0 );
1550 c = new Confidence();
1551 node.getBranchData().addConfidence( c );
1554 c.setValue( confidence_value );
1557 public static void setScientificName( final PhylogenyNode node, final String scientific_name ) {
1558 if ( !node.getNodeData().isHasTaxonomy() ) {
1559 node.getNodeData().setTaxonomy( new Taxonomy() );
1561 node.getNodeData().getTaxonomy().setScientificName( scientific_name );
1565 * Convenience method to set the taxonomy code of a phylogeny node.
1569 * @param taxonomy_code
1570 * @throws PhyloXmlDataFormatException
1572 public static void setTaxonomyCode( final PhylogenyNode node, final String taxonomy_code )
1573 throws PhyloXmlDataFormatException {
1574 if ( !node.getNodeData().isHasTaxonomy() ) {
1575 node.getNodeData().setTaxonomy( new Taxonomy() );
1577 node.getNodeData().getTaxonomy().setTaxonomyCode( taxonomy_code );
1581 * Removes from Phylogeny to_be_stripped all external Nodes which are
1582 * associated with a species NOT found in Phylogeny reference.
1585 * a reference Phylogeny
1586 * @param to_be_stripped
1587 * Phylogeny to be stripped
1588 * @return number of external nodes removed from to_be_stripped
1590 public static int taxonomyBasedDeletionOfExternalNodes( final Phylogeny reference, final Phylogeny to_be_stripped ) {
1591 final Set<String> ref_ext_taxo = new HashSet<String>();
1592 final ArrayList<PhylogenyNode> nodes_to_delete = new ArrayList<PhylogenyNode>();
1593 for( final PhylogenyNodeIterator it = reference.iteratorExternalForward(); it.hasNext(); ) {
1594 ref_ext_taxo.add( getSpecies( it.next() ) );
1596 for( final PhylogenyNodeIterator it = to_be_stripped.iteratorExternalForward(); it.hasNext(); ) {
1597 final PhylogenyNode n = it.next();
1598 if ( !ref_ext_taxo.contains( getSpecies( n ) ) ) {
1599 nodes_to_delete.add( n );
1602 for( final PhylogenyNode phylogenyNode : nodes_to_delete ) {
1603 to_be_stripped.deleteSubtree( phylogenyNode, true );
1605 return nodes_to_delete.size();
1609 * Arranges the order of childern for each node of this Phylogeny in such a
1610 * way that either the branch with more children is on top (right) or on
1611 * bottom (left), dependent on the value of boolean order.
1614 * decides in which direction to order
1617 public static void orderAppearance( final PhylogenyNode n,
1618 final boolean order,
1619 final boolean order_ext_alphabetically,
1620 final DESCENDANT_SORT_PRIORITY pri ) {
1621 if ( n.isExternal() ) {
1625 PhylogenyNode temp = null;
1626 if ( ( n.getNumberOfDescendants() == 2 )
1627 && ( n.getChildNode1().getNumberOfExternalNodes() != n.getChildNode2().getNumberOfExternalNodes() )
1628 && ( ( n.getChildNode1().getNumberOfExternalNodes() < n.getChildNode2().getNumberOfExternalNodes() ) == order ) ) {
1629 temp = n.getChildNode1();
1630 n.setChild1( n.getChildNode2() );
1631 n.setChild2( temp );
1633 else if ( order_ext_alphabetically ) {
1634 boolean all_ext = true;
1635 for( final PhylogenyNode i : n.getDescendants() ) {
1636 if ( !i.isExternal() ) {
1642 PhylogenyMethods.sortNodeDescendents( n, pri );
1645 for( int i = 0; i < n.getNumberOfDescendants(); ++i ) {
1646 orderAppearance( n.getChildNode( i ), order, order_ext_alphabetically, pri );
1651 public static enum PhylogenyNodeField {
1654 TAXONOMY_SCIENTIFIC_NAME,
1655 TAXONOMY_COMMON_NAME,
1658 TAXONOMY_ID_UNIPROT_1,
1659 TAXONOMY_ID_UNIPROT_2,
1663 public static enum TAXONOMY_EXTRACTION {
1664 NO, YES, PFAM_STYLE_ONLY;
1667 public static enum DESCENDANT_SORT_PRIORITY {
1668 TAXONOMY, SEQUENCE, NODE_NAME;