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.PhyloXmlUtil;
44 import org.forester.io.parsers.util.PhylogenyParserException;
45 import org.forester.phylogeny.data.BranchColor;
46 import org.forester.phylogeny.data.BranchWidth;
47 import org.forester.phylogeny.data.Confidence;
48 import org.forester.phylogeny.data.DomainArchitecture;
49 import org.forester.phylogeny.data.Identifier;
50 import org.forester.phylogeny.data.PhylogenyDataUtil;
51 import org.forester.phylogeny.data.Sequence;
52 import org.forester.phylogeny.data.Taxonomy;
53 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
54 import org.forester.phylogeny.factories.PhylogenyFactory;
55 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
56 import org.forester.util.BasicDescriptiveStatistics;
57 import org.forester.util.DescriptiveStatistics;
58 import org.forester.util.FailedConditionCheckException;
59 import org.forester.util.ForesterUtil;
61 public class PhylogenyMethods {
63 private static PhylogenyMethods _instance = null;
64 private final Set<Integer> _temp_hash_set = new HashSet<Integer>();
65 private PhylogenyNode _farthest_1 = null;
66 private PhylogenyNode _farthest_2 = null;
68 private PhylogenyMethods() {
69 // Hidden constructor.
73 * Calculates the distance between PhylogenyNodes node1 and node2.
78 * @return distance between node1 and node2
80 public double calculateDistance( final PhylogenyNode node1, final PhylogenyNode node2 ) {
81 final PhylogenyNode lca = obtainLCA( node1, node2 );
82 final PhylogenyNode n1 = node1;
83 final PhylogenyNode n2 = node2;
84 return ( PhylogenyMethods.getDistance( n1, lca ) + PhylogenyMethods.getDistance( n2, lca ) );
87 public double calculateFurthestDistance( final Phylogeny phylogeny ) {
88 if ( phylogeny.getNumberOfExternalNodes() < 2 ) {
93 PhylogenyNode node_1 = null;
94 PhylogenyNode node_2 = null;
95 double farthest_d = -Double.MAX_VALUE;
96 final PhylogenyMethods methods = PhylogenyMethods.getInstance();
97 final List<PhylogenyNode> ext_nodes = phylogeny.getRoot().getAllExternalDescendants();
98 for( int i = 1; i < ext_nodes.size(); ++i ) {
99 for( int j = 0; j < i; ++j ) {
100 final double d = methods.calculateDistance( ext_nodes.get( i ), ext_nodes.get( j ) );
102 throw new RuntimeException( "distance cannot be negative" );
104 if ( d > farthest_d ) {
106 node_1 = ext_nodes.get( i );
107 node_2 = ext_nodes.get( j );
111 _farthest_1 = node_1;
112 _farthest_2 = node_2;
117 public Object clone() throws CloneNotSupportedException {
118 throw new CloneNotSupportedException();
121 public PhylogenyNode getFarthestNode1() {
125 public PhylogenyNode getFarthestNode2() {
130 * Returns the LCA of PhylogenyNodes node1 and node2.
135 * @return LCA of node1 and node2
137 public PhylogenyNode obtainLCA( final PhylogenyNode node1, final PhylogenyNode node2 ) {
138 _temp_hash_set.clear();
139 PhylogenyNode n1 = node1;
140 PhylogenyNode n2 = node2;
141 _temp_hash_set.add( n1.getId() );
142 while ( !n1.isRoot() ) {
144 _temp_hash_set.add( n1.getId() );
146 while ( !_temp_hash_set.contains( n2.getId() ) && !n2.isRoot() ) {
149 if ( !_temp_hash_set.contains( n2.getId() ) ) {
150 throw new IllegalArgumentException( "attempt to get LCA of two nodes which do not share a common root" );
156 * Returns all orthologs of the external PhylogenyNode n of this Phylogeny.
157 * Orthologs are returned as List of node references.
159 * PRECONDITION: This tree must be binary and rooted, and speciation -
160 * duplication need to be assigned for each of its internal Nodes.
162 * Returns null if this Phylogeny is empty or if n is internal.
164 * external PhylogenyNode whose orthologs are to be returned
165 * @return Vector of references to all orthologous Nodes of PhylogenyNode n
166 * of this Phylogeny, null if this Phylogeny is empty or if n is
169 public List<PhylogenyNode> getOrthologousNodes( final Phylogeny phy, final PhylogenyNode node ) {
170 final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
171 final PhylogenyNodeIterator it = phy.iteratorExternalForward();
172 while ( it.hasNext() ) {
173 final PhylogenyNode temp_node = it.next();
174 if ( ( temp_node != node ) && isAreOrthologous( node, temp_node ) ) {
175 nodes.add( temp_node );
181 public boolean isAreOrthologous( final PhylogenyNode node1, final PhylogenyNode node2 ) {
182 return !obtainLCA( node1, node2 ).isDuplication();
185 public final static Phylogeny[] readPhylogenies( final PhylogenyParser parser, final File file ) throws IOException {
186 final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
187 final Phylogeny[] trees = factory.create( file, parser );
188 if ( ( trees == null ) || ( trees.length == 0 ) ) {
189 throw new PhylogenyParserException( "Unable to parse phylogeny from file: " + file );
194 final static public void transferInternalNodeNamesToConfidence( final Phylogeny phy ) {
195 final PhylogenyNodeIterator it = phy.iteratorPostorder();
196 while ( it.hasNext() ) {
197 final PhylogenyNode n = it.next();
198 if ( !n.isExternal() && !n.getBranchData().isHasConfidences() ) {
199 if ( !ForesterUtil.isEmpty( n.getName() ) ) {
202 d = Double.parseDouble( n.getName() );
204 catch ( final Exception e ) {
208 n.getBranchData().addConfidence( new Confidence( d, "" ) );
216 final static public void transferInternalNamesToBootstrapSupport( final Phylogeny phy ) {
217 final PhylogenyNodeIterator it = phy.iteratorPostorder();
218 while ( it.hasNext() ) {
219 final PhylogenyNode n = it.next();
220 if ( !n.isExternal() && !ForesterUtil.isEmpty( n.getName() ) ) {
223 value = Double.parseDouble( n.getName() );
225 catch ( final NumberFormatException e ) {
226 throw new IllegalArgumentException( "failed to parse number from [" + n.getName() + "]: "
227 + e.getLocalizedMessage() );
229 if ( value >= 0.0 ) {
230 n.getBranchData().addConfidence( new Confidence( value, "bootstrap" ) );
237 final static public void sortNodeDescendents( final PhylogenyNode node, final DESCENDANT_SORT_PRIORITY pri ) {
238 class PhylogenyNodeSortTaxonomyPriority implements Comparator<PhylogenyNode> {
241 public int compare( final PhylogenyNode n1, final PhylogenyNode n2 ) {
242 if ( n1.getNodeData().isHasTaxonomy() && n2.getNodeData().isHasTaxonomy() ) {
243 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getScientificName() ) )
244 && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getScientificName() ) ) ) {
245 return n1.getNodeData().getTaxonomy().getScientificName().toLowerCase()
246 .compareTo( n2.getNodeData().getTaxonomy().getScientificName().toLowerCase() );
248 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getTaxonomyCode() ) )
249 && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getTaxonomyCode() ) ) ) {
250 return n1.getNodeData().getTaxonomy().getTaxonomyCode()
251 .compareTo( n2.getNodeData().getTaxonomy().getTaxonomyCode() );
253 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getCommonName() ) )
254 && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getCommonName() ) ) ) {
255 return n1.getNodeData().getTaxonomy().getCommonName().toLowerCase()
256 .compareTo( n2.getNodeData().getTaxonomy().getCommonName().toLowerCase() );
259 if ( n1.getNodeData().isHasSequence() && n2.getNodeData().isHasSequence() ) {
260 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getName() ) )
261 && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getName() ) ) ) {
262 return n1.getNodeData().getSequence().getName().toLowerCase()
263 .compareTo( n2.getNodeData().getSequence().getName().toLowerCase() );
265 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getSymbol() ) )
266 && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getSymbol() ) ) ) {
267 return n1.getNodeData().getSequence().getSymbol()
268 .compareTo( n2.getNodeData().getSequence().getSymbol() );
270 if ( ( n1.getNodeData().getSequence().getAccession() != null )
271 && ( n2.getNodeData().getSequence().getAccession() != null )
272 && !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getAccession().getValue() )
273 && !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getAccession().getValue() ) ) {
274 return n1.getNodeData().getSequence().getAccession().getValue()
275 .compareTo( n2.getNodeData().getSequence().getAccession().getValue() );
278 if ( ( !ForesterUtil.isEmpty( n1.getName() ) ) && ( !ForesterUtil.isEmpty( n2.getName() ) ) ) {
279 return n1.getName().toLowerCase().compareTo( n2.getName().toLowerCase() );
284 class PhylogenyNodeSortSequencePriority implements Comparator<PhylogenyNode> {
287 public int compare( final PhylogenyNode n1, final PhylogenyNode n2 ) {
288 if ( n1.getNodeData().isHasSequence() && n2.getNodeData().isHasSequence() ) {
289 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getName() ) )
290 && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getName() ) ) ) {
291 return n1.getNodeData().getSequence().getName().toLowerCase()
292 .compareTo( n2.getNodeData().getSequence().getName().toLowerCase() );
294 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getSymbol() ) )
295 && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getSymbol() ) ) ) {
296 return n1.getNodeData().getSequence().getSymbol()
297 .compareTo( n2.getNodeData().getSequence().getSymbol() );
299 if ( ( n1.getNodeData().getSequence().getAccession() != null )
300 && ( n2.getNodeData().getSequence().getAccession() != null )
301 && !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getAccession().getValue() )
302 && !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getAccession().getValue() ) ) {
303 return n1.getNodeData().getSequence().getAccession().getValue()
304 .compareTo( n2.getNodeData().getSequence().getAccession().getValue() );
307 if ( n1.getNodeData().isHasTaxonomy() && n2.getNodeData().isHasTaxonomy() ) {
308 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getScientificName() ) )
309 && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getScientificName() ) ) ) {
310 return n1.getNodeData().getTaxonomy().getScientificName().toLowerCase()
311 .compareTo( n2.getNodeData().getTaxonomy().getScientificName().toLowerCase() );
313 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getTaxonomyCode() ) )
314 && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getTaxonomyCode() ) ) ) {
315 return n1.getNodeData().getTaxonomy().getTaxonomyCode()
316 .compareTo( n2.getNodeData().getTaxonomy().getTaxonomyCode() );
318 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getCommonName() ) )
319 && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getCommonName() ) ) ) {
320 return n1.getNodeData().getTaxonomy().getCommonName().toLowerCase()
321 .compareTo( n2.getNodeData().getTaxonomy().getCommonName().toLowerCase() );
324 if ( ( !ForesterUtil.isEmpty( n1.getName() ) ) && ( !ForesterUtil.isEmpty( n2.getName() ) ) ) {
325 return n1.getName().toLowerCase().compareTo( n2.getName().toLowerCase() );
330 class PhylogenyNodeSortNodeNamePriority implements Comparator<PhylogenyNode> {
333 public int compare( final PhylogenyNode n1, final PhylogenyNode n2 ) {
334 if ( ( !ForesterUtil.isEmpty( n1.getName() ) ) && ( !ForesterUtil.isEmpty( n2.getName() ) ) ) {
335 return n1.getName().toLowerCase().compareTo( n2.getName().toLowerCase() );
337 if ( n1.getNodeData().isHasTaxonomy() && n2.getNodeData().isHasTaxonomy() ) {
338 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getScientificName() ) )
339 && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getScientificName() ) ) ) {
340 return n1.getNodeData().getTaxonomy().getScientificName().toLowerCase()
341 .compareTo( n2.getNodeData().getTaxonomy().getScientificName().toLowerCase() );
343 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getTaxonomyCode() ) )
344 && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getTaxonomyCode() ) ) ) {
345 return n1.getNodeData().getTaxonomy().getTaxonomyCode()
346 .compareTo( n2.getNodeData().getTaxonomy().getTaxonomyCode() );
348 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getCommonName() ) )
349 && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getCommonName() ) ) ) {
350 return n1.getNodeData().getTaxonomy().getCommonName().toLowerCase()
351 .compareTo( n2.getNodeData().getTaxonomy().getCommonName().toLowerCase() );
354 if ( n1.getNodeData().isHasSequence() && n2.getNodeData().isHasSequence() ) {
355 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getName() ) )
356 && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getName() ) ) ) {
357 return n1.getNodeData().getSequence().getName().toLowerCase()
358 .compareTo( n2.getNodeData().getSequence().getName().toLowerCase() );
360 if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getSymbol() ) )
361 && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getSymbol() ) ) ) {
362 return n1.getNodeData().getSequence().getSymbol()
363 .compareTo( n2.getNodeData().getSequence().getSymbol() );
365 if ( ( n1.getNodeData().getSequence().getAccession() != null )
366 && ( n2.getNodeData().getSequence().getAccession() != null )
367 && !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getAccession().getValue() )
368 && !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getAccession().getValue() ) ) {
369 return n1.getNodeData().getSequence().getAccession().getValue()
370 .compareTo( n2.getNodeData().getSequence().getAccession().getValue() );
376 Comparator<PhylogenyNode> c;
379 c = new PhylogenyNodeSortSequencePriority();
382 c = new PhylogenyNodeSortNodeNamePriority();
385 c = new PhylogenyNodeSortTaxonomyPriority();
387 final List<PhylogenyNode> descs = node.getDescendants();
388 Collections.sort( descs, c );
390 for( final PhylogenyNode desc : descs ) {
391 node.setChildNode( i++, desc );
395 final static public void transferNodeNameToField( final Phylogeny phy,
396 final PhylogenyMethods.PhylogenyNodeField field ) {
397 final PhylogenyNodeIterator it = phy.iteratorPostorder();
398 while ( it.hasNext() ) {
399 final PhylogenyNode n = it.next();
400 final String name = n.getName().trim();
401 if ( !ForesterUtil.isEmpty( name ) ) {
405 // if ( name.length() > 5 ) {
407 // if ( !n.getNodeData().isHasTaxonomy() ) {
408 // n.getNodeData().setTaxonomy( new Taxonomy() );
410 // n.getNodeData().getTaxonomy().setScientificName( name );
415 setTaxonomyCode( n, name );
417 case TAXONOMY_SCIENTIFIC_NAME:
419 if ( !n.getNodeData().isHasTaxonomy() ) {
420 n.getNodeData().setTaxonomy( new Taxonomy() );
422 n.getNodeData().getTaxonomy().setScientificName( name );
424 case TAXONOMY_COMMON_NAME:
426 if ( !n.getNodeData().isHasTaxonomy() ) {
427 n.getNodeData().setTaxonomy( new Taxonomy() );
429 n.getNodeData().getTaxonomy().setCommonName( name );
431 case SEQUENCE_SYMBOL:
433 if ( !n.getNodeData().isHasSequence() ) {
434 n.getNodeData().setSequence( new Sequence() );
436 n.getNodeData().getSequence().setSymbol( name );
440 if ( !n.getNodeData().isHasSequence() ) {
441 n.getNodeData().setSequence( new Sequence() );
443 n.getNodeData().getSequence().setName( name );
445 case TAXONOMY_ID_UNIPROT_1: {
446 if ( !n.getNodeData().isHasTaxonomy() ) {
447 n.getNodeData().setTaxonomy( new Taxonomy() );
450 final int i = name.indexOf( '_' );
452 id = name.substring( 0, i );
457 n.getNodeData().getTaxonomy()
458 .setIdentifier( new Identifier( id, PhyloXmlUtil.UNIPROT_TAX_PROVIDER ) );
461 case TAXONOMY_ID_UNIPROT_2: {
462 if ( !n.getNodeData().isHasTaxonomy() ) {
463 n.getNodeData().setTaxonomy( new Taxonomy() );
466 final int i = name.indexOf( '_' );
468 id = name.substring( i + 1, name.length() );
473 n.getNodeData().getTaxonomy()
474 .setIdentifier( new Identifier( id, PhyloXmlUtil.UNIPROT_TAX_PROVIDER ) );
482 static double addPhylogenyDistances( final double a, final double b ) {
483 if ( ( a >= 0.0 ) && ( b >= 0.0 ) ) {
486 else if ( a >= 0.0 ) {
489 else if ( b >= 0.0 ) {
492 return PhylogenyDataUtil.BRANCH_LENGTH_DEFAULT;
495 // Helper for getUltraParalogousNodes( PhylogenyNode ).
496 public static boolean areAllChildrenDuplications( final PhylogenyNode n ) {
497 if ( n.isExternal() ) {
501 if ( n.isDuplication() ) {
503 for( final PhylogenyNode desc : n.getDescendants() ) {
504 if ( !areAllChildrenDuplications( desc ) ) {
516 public static int calculateDepth( final PhylogenyNode node ) {
517 PhylogenyNode n = node;
519 while ( !n.isRoot() ) {
526 public static double calculateDistanceToRoot( final PhylogenyNode node ) {
527 PhylogenyNode n = node;
529 while ( !n.isRoot() ) {
530 if ( n.getDistanceToParent() > 0.0 ) {
531 d += n.getDistanceToParent();
538 public static short calculateMaxBranchesToLeaf( final PhylogenyNode node ) {
539 if ( node.isExternal() ) {
543 for( PhylogenyNode d : node.getAllExternalDescendants() ) {
545 while ( d != node ) {
546 if ( d.isCollapse() ) {
561 public static int calculateMaxDepth( final Phylogeny phy ) {
563 for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) {
564 final PhylogenyNode node = iter.next();
565 final int steps = calculateDepth( node );
573 public static double calculateMaxDistanceToRoot( final Phylogeny phy ) {
575 for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) {
576 final PhylogenyNode node = iter.next();
577 final double d = calculateDistanceToRoot( node );
585 public static DescriptiveStatistics calculatNumberOfDescendantsPerNodeStatistics( final Phylogeny phy ) {
586 final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
587 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
588 final PhylogenyNode n = iter.next();
589 if ( !n.isExternal() ) {
590 stats.addValue( n.getNumberOfDescendants() );
596 public static DescriptiveStatistics calculatBranchLengthStatistics( final Phylogeny phy ) {
597 final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
598 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
599 final PhylogenyNode n = iter.next();
600 if ( !n.isRoot() && ( n.getDistanceToParent() >= 0.0 ) ) {
601 stats.addValue( n.getDistanceToParent() );
607 public static List<DescriptiveStatistics> calculatConfidenceStatistics( final Phylogeny phy ) {
608 final List<DescriptiveStatistics> stats = new ArrayList<DescriptiveStatistics>();
609 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
610 final PhylogenyNode n = iter.next();
611 if ( !n.isExternal() && !n.isRoot() ) {
612 if ( n.getBranchData().isHasConfidences() ) {
613 for( int i = 0; i < n.getBranchData().getConfidences().size(); ++i ) {
614 final Confidence c = n.getBranchData().getConfidences().get( i );
615 if ( ( i > ( stats.size() - 1 ) ) || ( stats.get( i ) == null ) ) {
616 stats.add( i, new BasicDescriptiveStatistics() );
618 if ( !ForesterUtil.isEmpty( c.getType() ) ) {
619 if ( !ForesterUtil.isEmpty( stats.get( i ).getDescription() ) ) {
620 if ( !stats.get( i ).getDescription().equalsIgnoreCase( c.getType() ) ) {
621 throw new IllegalArgumentException( "support values in node [" + n.toString()
622 + "] appear inconsistently ordered" );
625 stats.get( i ).setDescription( c.getType() );
627 stats.get( i ).addValue( ( ( c != null ) && ( c.getValue() >= 0 ) ) ? c.getValue() : 0 );
636 * Returns the set of distinct taxonomies of
637 * all external nodes of node.
638 * If at least one the external nodes has no taxonomy,
642 public static Set<Taxonomy> obtainDistinctTaxonomies( final PhylogenyNode node ) {
643 final List<PhylogenyNode> descs = node.getAllExternalDescendants();
644 final Set<Taxonomy> tax_set = new HashSet<Taxonomy>();
645 for( final PhylogenyNode n : descs ) {
646 if ( !n.getNodeData().isHasTaxonomy() || n.getNodeData().getTaxonomy().isEmpty() ) {
649 tax_set.add( n.getNodeData().getTaxonomy() );
655 * Returns a map of distinct taxonomies of
656 * all external nodes of node.
657 * If at least one of the external nodes has no taxonomy,
661 public static SortedMap<Taxonomy, Integer> obtainDistinctTaxonomyCounts( final PhylogenyNode node ) {
662 final List<PhylogenyNode> descs = node.getAllExternalDescendants();
663 final SortedMap<Taxonomy, Integer> tax_map = new TreeMap<Taxonomy, Integer>();
664 for( final PhylogenyNode n : descs ) {
665 if ( !n.getNodeData().isHasTaxonomy() || n.getNodeData().getTaxonomy().isEmpty() ) {
668 final Taxonomy t = n.getNodeData().getTaxonomy();
669 if ( tax_map.containsKey( t ) ) {
670 tax_map.put( t, tax_map.get( t ) + 1 );
679 public static int calculateNumberOfExternalNodesWithoutTaxonomy( final PhylogenyNode node ) {
680 final List<PhylogenyNode> descs = node.getAllExternalDescendants();
682 for( final PhylogenyNode n : descs ) {
683 if ( !n.getNodeData().isHasTaxonomy() || n.getNodeData().getTaxonomy().isEmpty() ) {
691 * Deep copies the phylogeny originating from this node.
693 static PhylogenyNode copySubTree( final PhylogenyNode source ) {
694 if ( source == null ) {
698 final PhylogenyNode newnode = source.copyNodeData();
699 if ( !source.isExternal() ) {
700 for( int i = 0; i < source.getNumberOfDescendants(); ++i ) {
701 newnode.setChildNode( i, PhylogenyMethods.copySubTree( source.getChildNode( i ) ) );
709 * Shallow copies the phylogeny originating from this node.
711 static PhylogenyNode copySubTreeShallow( final PhylogenyNode source ) {
712 if ( source == null ) {
716 final PhylogenyNode newnode = source.copyNodeDataShallow();
717 if ( !source.isExternal() ) {
718 for( int i = 0; i < source.getNumberOfDescendants(); ++i ) {
719 newnode.setChildNode( i, PhylogenyMethods.copySubTreeShallow( source.getChildNode( i ) ) );
726 public static void deleteExternalNodesNegativeSelection( final Set<Integer> to_delete, final Phylogeny phy ) {
728 for( final Integer id : to_delete ) {
729 phy.deleteSubtree( phy.getNode( id ), true );
734 public static void deleteExternalNodesNegativeSelection( final String[] node_names_to_delete, final Phylogeny p )
735 throws IllegalArgumentException {
736 for( int i = 0; i < node_names_to_delete.length; ++i ) {
737 if ( ForesterUtil.isEmpty( node_names_to_delete[ i ] ) ) {
740 List<PhylogenyNode> nodes = null;
741 nodes = p.getNodes( node_names_to_delete[ i ] );
742 final Iterator<PhylogenyNode> it = nodes.iterator();
743 while ( it.hasNext() ) {
744 final PhylogenyNode n = it.next();
745 if ( !n.isExternal() ) {
746 throw new IllegalArgumentException( "attempt to delete non-external node \""
747 + node_names_to_delete[ i ] + "\"" );
749 p.deleteSubtree( n, true );
754 public static void deleteExternalNodesPositiveSelection( final Set<Taxonomy> species_to_keep, final Phylogeny phy ) {
755 // final Set<Integer> to_delete = new HashSet<Integer>();
756 for( final PhylogenyNodeIterator it = phy.iteratorExternalForward(); it.hasNext(); ) {
757 final PhylogenyNode n = it.next();
758 if ( n.getNodeData().isHasTaxonomy() ) {
759 if ( !species_to_keep.contains( n.getNodeData().getTaxonomy() ) ) {
760 //to_delete.add( n.getNodeId() );
761 phy.deleteSubtree( n, true );
765 throw new IllegalArgumentException( "node " + n.getId() + " has no taxonomic data" );
769 phy.externalNodesHaveChanged();
770 // deleteExternalNodesNegativeSelection( to_delete, phy );
773 public static List<String> deleteExternalNodesPositiveSelection( final String[] node_names_to_keep,
774 final Phylogeny p ) {
775 final PhylogenyNodeIterator it = p.iteratorExternalForward();
776 final String[] to_delete = new String[ p.getNumberOfExternalNodes() ];
778 Arrays.sort( node_names_to_keep );
779 while ( it.hasNext() ) {
780 final String curent_name = it.next().getName();
781 if ( Arrays.binarySearch( node_names_to_keep, curent_name ) < 0 ) {
782 to_delete[ i++ ] = curent_name;
785 PhylogenyMethods.deleteExternalNodesNegativeSelection( to_delete, p );
786 final List<String> deleted = new ArrayList<String>();
787 for( final String n : to_delete ) {
788 if ( !ForesterUtil.isEmpty( n ) ) {
795 public static List<PhylogenyNode> getAllDescendants( final PhylogenyNode node ) {
796 final List<PhylogenyNode> descs = new ArrayList<PhylogenyNode>();
797 final Set<Integer> encountered = new HashSet<Integer>();
798 if ( !node.isExternal() ) {
799 final List<PhylogenyNode> exts = node.getAllExternalDescendants();
800 for( PhylogenyNode current : exts ) {
801 descs.add( current );
802 while ( current != node ) {
803 current = current.getParent();
804 if ( encountered.contains( current.getId() ) ) {
807 descs.add( current );
808 encountered.add( current.getId() );
822 public static Color getBranchColorValue( final PhylogenyNode node ) {
823 if ( node.getBranchData().getBranchColor() == null ) {
826 return node.getBranchData().getBranchColor().getValue();
832 public static double getBranchWidthValue( final PhylogenyNode node ) {
833 if ( !node.getBranchData().isHasBranchWidth() ) {
834 return BranchWidth.BRANCH_WIDTH_DEFAULT_VALUE;
836 return node.getBranchData().getBranchWidth().getValue();
842 public static double getConfidenceValue( final PhylogenyNode node ) {
843 if ( !node.getBranchData().isHasConfidences() ) {
844 return Confidence.CONFIDENCE_DEFAULT_VALUE;
846 return node.getBranchData().getConfidence( 0 ).getValue();
852 public static double[] getConfidenceValuesAsArray( final PhylogenyNode node ) {
853 if ( !node.getBranchData().isHasConfidences() ) {
854 return new double[ 0 ];
856 final double[] values = new double[ node.getBranchData().getConfidences().size() ];
858 for( final Confidence c : node.getBranchData().getConfidences() ) {
859 values[ i++ ] = c.getValue();
865 * Calculates the distance between PhylogenyNodes n1 and n2.
866 * PRECONDITION: n1 is a descendant of n2.
871 * @return distance between n1 and n2
873 private static double getDistance( PhylogenyNode n1, final PhylogenyNode n2 ) {
876 if ( n1.getDistanceToParent() > 0.0 ) {
877 d += n1.getDistanceToParent();
885 * Returns taxonomy t if all external descendants have
886 * the same taxonomy t, null otherwise.
889 public static Taxonomy getExternalDescendantsTaxonomy( final PhylogenyNode node ) {
890 final List<PhylogenyNode> descs = node.getAllExternalDescendants();
892 for( final PhylogenyNode n : descs ) {
893 if ( !n.getNodeData().isHasTaxonomy() || n.getNodeData().getTaxonomy().isEmpty() ) {
896 else if ( tax == null ) {
897 tax = n.getNodeData().getTaxonomy();
899 else if ( n.getNodeData().getTaxonomy().isEmpty() || !tax.isEqual( n.getNodeData().getTaxonomy() ) ) {
906 public static PhylogenyNode getFurthestDescendant( final PhylogenyNode node ) {
907 final List<PhylogenyNode> children = node.getAllExternalDescendants();
908 PhylogenyNode farthest = null;
909 double longest = -Double.MAX_VALUE;
910 for( final PhylogenyNode child : children ) {
911 if ( PhylogenyMethods.getDistance( child, node ) > longest ) {
913 longest = PhylogenyMethods.getDistance( child, node );
919 public static PhylogenyMethods getInstance() {
920 if ( PhylogenyMethods._instance == null ) {
921 PhylogenyMethods._instance = new PhylogenyMethods();
923 return PhylogenyMethods._instance;
927 * Returns the largest confidence value found on phy.
929 static public double getMaximumConfidenceValue( final Phylogeny phy ) {
930 double max = -Double.MAX_VALUE;
931 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
932 final double s = PhylogenyMethods.getConfidenceValue( iter.next() );
933 if ( ( s != Confidence.CONFIDENCE_DEFAULT_VALUE ) && ( s > max ) ) {
940 static public int getMinimumDescendentsPerInternalNodes( final Phylogeny phy ) {
941 int min = Integer.MAX_VALUE;
944 for( final PhylogenyNodeIterator it = phy.iteratorPreorder(); it.hasNext(); ) {
946 if ( n.isInternal() ) {
947 d = n.getNumberOfDescendants();
957 * Convenience method for display purposes.
958 * Not intended for algorithms.
960 public static String getSpecies( final PhylogenyNode node ) {
961 if ( !node.getNodeData().isHasTaxonomy() ) {
964 if ( !ForesterUtil.isEmpty( node.getNodeData().getTaxonomy().getTaxonomyCode() ) ) {
965 return node.getNodeData().getTaxonomy().getTaxonomyCode();
967 else if ( !ForesterUtil.isEmpty( node.getNodeData().getTaxonomy().getScientificName() ) ) {
968 return node.getNodeData().getTaxonomy().getScientificName();
971 return node.getNodeData().getTaxonomy().getCommonName();
976 * Returns all Nodes which are connected to external PhylogenyNode n of this
977 * Phylogeny by a path containing only speciation events. We call these
978 * "super orthologs". Nodes are returned as Vector of references to Nodes.
980 * PRECONDITION: This tree must be binary and rooted, and speciation -
981 * duplication need to be assigned for each of its internal Nodes.
983 * Returns null if this Phylogeny is empty or if n is internal.
985 * external PhylogenyNode whose strictly speciation related Nodes
987 * @return Vector of references to all strictly speciation related Nodes of
988 * PhylogenyNode n of this Phylogeny, null if this Phylogeny is
989 * empty or if n is internal
991 public static List<PhylogenyNode> getSuperOrthologousNodes( final PhylogenyNode n ) {
993 PhylogenyNode node = n, deepest = null;
994 final List<PhylogenyNode> v = new ArrayList<PhylogenyNode>();
995 if ( !node.isExternal() ) {
998 while ( !node.isRoot() && !node.getParent().isDuplication() ) {
999 node = node.getParent();
1002 deepest.setIndicatorsToZero();
1004 if ( !node.isExternal() ) {
1005 if ( node.getIndicator() == 0 ) {
1006 node.setIndicator( ( byte ) 1 );
1007 if ( !node.isDuplication() ) {
1008 node = node.getChildNode1();
1011 if ( node.getIndicator() == 1 ) {
1012 node.setIndicator( ( byte ) 2 );
1013 if ( !node.isDuplication() ) {
1014 node = node.getChildNode2();
1017 if ( ( node != deepest ) && ( node.getIndicator() == 2 ) ) {
1018 node = node.getParent();
1025 if ( node != deepest ) {
1026 node = node.getParent();
1029 node.setIndicator( ( byte ) 2 );
1032 } while ( ( node != deepest ) || ( deepest.getIndicator() != 2 ) );
1037 * Convenience method for display purposes.
1038 * Not intended for algorithms.
1040 public static String getTaxonomyIdentifier( final PhylogenyNode node ) {
1041 if ( !node.getNodeData().isHasTaxonomy() || ( node.getNodeData().getTaxonomy().getIdentifier() == null ) ) {
1044 return node.getNodeData().getTaxonomy().getIdentifier().getValue();
1048 * Returns all Nodes which are connected to external PhylogenyNode n of this
1049 * Phylogeny by a path containing, and leading to, only duplication events.
1050 * We call these "ultra paralogs". Nodes are returned as Vector of
1051 * references to Nodes.
1053 * PRECONDITION: This tree must be binary and rooted, and speciation -
1054 * duplication need to be assigned for each of its internal Nodes.
1056 * Returns null if this Phylogeny is empty or if n is internal.
1058 * (Last modified: 10/06/01)
1061 * external PhylogenyNode whose ultra paralogs are to be returned
1062 * @return Vector of references to all ultra paralogs of PhylogenyNode n of
1063 * this Phylogeny, null if this Phylogeny is empty or if n is
1066 public static List<PhylogenyNode> getUltraParalogousNodes( final PhylogenyNode n ) {
1068 PhylogenyNode node = n;
1069 if ( !node.isExternal() ) {
1072 while ( !node.isRoot() && node.getParent().isDuplication() && areAllChildrenDuplications( node.getParent() ) ) {
1073 node = node.getParent();
1075 final List<PhylogenyNode> nodes = node.getAllExternalDescendants();
1080 public static String inferCommonPartOfScientificNameOfDescendants( final PhylogenyNode node ) {
1081 final List<PhylogenyNode> descs = node.getDescendants();
1083 for( final PhylogenyNode n : descs ) {
1084 if ( !n.getNodeData().isHasTaxonomy()
1085 || ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
1088 else if ( sn == null ) {
1089 sn = n.getNodeData().getTaxonomy().getScientificName().trim();
1092 String sn_current = n.getNodeData().getTaxonomy().getScientificName().trim();
1093 if ( !sn.equals( sn_current ) ) {
1094 boolean overlap = false;
1095 while ( ( sn.indexOf( ' ' ) >= 0 ) || ( sn_current.indexOf( ' ' ) >= 0 ) ) {
1096 if ( ForesterUtil.countChars( sn, ' ' ) > ForesterUtil.countChars( sn_current, ' ' ) ) {
1097 sn = sn.substring( 0, sn.lastIndexOf( ' ' ) ).trim();
1100 sn_current = sn_current.substring( 0, sn_current.lastIndexOf( ' ' ) ).trim();
1102 if ( sn.equals( sn_current ) ) {
1116 public static boolean isHasExternalDescendant( final PhylogenyNode node ) {
1117 for( int i = 0; i < node.getNumberOfDescendants(); ++i ) {
1118 if ( node.getChildNode( i ).isExternal() ) {
1126 * This is case insensitive.
1129 public synchronized static boolean isTaxonomyHasIdentifierOfGivenProvider( final Taxonomy tax,
1130 final String[] providers ) {
1131 if ( ( tax.getIdentifier() != null ) && !ForesterUtil.isEmpty( tax.getIdentifier().getProvider() ) ) {
1132 final String my_tax_prov = tax.getIdentifier().getProvider();
1133 for( final String provider : providers ) {
1134 if ( provider.equalsIgnoreCase( my_tax_prov ) ) {
1145 private static boolean match( final String s,
1147 final boolean case_sensitive,
1148 final boolean partial ) {
1149 if ( ForesterUtil.isEmpty( s ) || ForesterUtil.isEmpty( query ) ) {
1152 String my_s = s.trim();
1153 String my_query = query.trim();
1154 if ( !case_sensitive ) {
1155 my_s = my_s.toLowerCase();
1156 my_query = my_query.toLowerCase();
1159 return my_s.indexOf( my_query ) >= 0;
1162 return my_s.equals( my_query );
1166 public static void midpointRoot( final Phylogeny phylogeny ) {
1167 if ( phylogeny.getNumberOfExternalNodes() < 2 ) {
1170 final PhylogenyMethods methods = getInstance();
1171 final double farthest_d = methods.calculateFurthestDistance( phylogeny );
1172 final PhylogenyNode f1 = methods.getFarthestNode1();
1173 final PhylogenyNode f2 = methods.getFarthestNode2();
1174 if ( farthest_d <= 0.0 ) {
1177 double x = farthest_d / 2.0;
1178 PhylogenyNode n = f1;
1179 if ( PhylogenyMethods.getDistance( f1, phylogeny.getRoot() ) < PhylogenyMethods.getDistance( f2, phylogeny
1183 while ( ( x > n.getDistanceToParent() ) && !n.isRoot() ) {
1184 x -= ( n.getDistanceToParent() > 0 ? n.getDistanceToParent() : 0 );
1187 phylogeny.reRoot( n, x );
1188 phylogeny.recalculateNumberOfExternalDescendants( true );
1189 final PhylogenyNode a = getFurthestDescendant( phylogeny.getRoot().getChildNode1() );
1190 final PhylogenyNode b = getFurthestDescendant( phylogeny.getRoot().getChildNode2() );
1191 final double da = getDistance( a, phylogeny.getRoot() );
1192 final double db = getDistance( b, phylogeny.getRoot() );
1193 if ( Math.abs( da - db ) > 0.000001 ) {
1194 throw new FailedConditionCheckException( "this should not have happened: midpoint rooting failed: da="
1195 + da + ", db=" + db + ", diff=" + Math.abs( da - db ) );
1199 public static void normalizeBootstrapValues( final Phylogeny phylogeny,
1200 final double max_bootstrap_value,
1201 final double max_normalized_value ) {
1202 for( final PhylogenyNodeIterator iter = phylogeny.iteratorPreorder(); iter.hasNext(); ) {
1203 final PhylogenyNode node = iter.next();
1204 if ( node.isInternal() ) {
1205 final double confidence = getConfidenceValue( node );
1206 if ( confidence != Confidence.CONFIDENCE_DEFAULT_VALUE ) {
1207 if ( confidence >= max_bootstrap_value ) {
1208 setBootstrapConfidence( node, max_normalized_value );
1211 setBootstrapConfidence( node, ( confidence * max_normalized_value ) / max_bootstrap_value );
1218 public static List<PhylogenyNode> obtainAllNodesAsList( final Phylogeny phy ) {
1219 final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
1220 if ( phy.isEmpty() ) {
1223 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
1224 nodes.add( iter.next() );
1229 public static void postorderBranchColorAveragingExternalNodeBased( final Phylogeny p ) {
1230 for( final PhylogenyNodeIterator iter = p.iteratorPostorder(); iter.hasNext(); ) {
1231 final PhylogenyNode node = iter.next();
1236 if ( node.isInternal() ) {
1237 for( final PhylogenyNodeIterator iterator = node.iterateChildNodesForward(); iterator.hasNext(); ) {
1238 final PhylogenyNode child_node = iterator.next();
1239 final Color child_color = getBranchColorValue( child_node );
1240 if ( child_color != null ) {
1242 red += child_color.getRed();
1243 green += child_color.getGreen();
1244 blue += child_color.getBlue();
1247 setBranchColorValue( node,
1248 new Color( ForesterUtil.roundToInt( red / n ),
1249 ForesterUtil.roundToInt( green / n ),
1250 ForesterUtil.roundToInt( blue / n ) ) );
1255 public static void removeNode( final PhylogenyNode remove_me, final Phylogeny phylogeny ) {
1256 if ( remove_me.isRoot() ) {
1257 throw new IllegalArgumentException( "ill advised attempt to remove root node" );
1259 if ( remove_me.isExternal() ) {
1260 phylogeny.deleteSubtree( remove_me, false );
1263 final PhylogenyNode parent = remove_me.getParent();
1264 final List<PhylogenyNode> descs = remove_me.getDescendants();
1265 parent.removeChildNode( remove_me );
1266 for( final PhylogenyNode desc : descs ) {
1267 parent.addAsChild( desc );
1268 desc.setDistanceToParent( addPhylogenyDistances( remove_me.getDistanceToParent(),
1269 desc.getDistanceToParent() ) );
1271 remove_me.setParent( null );
1272 phylogeny.setIdHash( null );
1273 phylogeny.externalNodesHaveChanged();
1277 public static List<PhylogenyNode> searchData( final String query,
1278 final Phylogeny phy,
1279 final boolean case_sensitive,
1280 final boolean partial ) {
1281 final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
1282 if ( phy.isEmpty() || ( query == null ) ) {
1285 if ( ForesterUtil.isEmpty( query ) ) {
1288 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
1289 final PhylogenyNode node = iter.next();
1290 boolean match = false;
1291 if ( match( node.getName(), query, case_sensitive, partial ) ) {
1294 else if ( node.getNodeData().isHasTaxonomy()
1295 && match( node.getNodeData().getTaxonomy().getTaxonomyCode(), query, case_sensitive, partial ) ) {
1298 else if ( node.getNodeData().isHasTaxonomy()
1299 && match( node.getNodeData().getTaxonomy().getCommonName(), query, case_sensitive, partial ) ) {
1302 else if ( node.getNodeData().isHasTaxonomy()
1303 && match( node.getNodeData().getTaxonomy().getScientificName(), query, case_sensitive, partial ) ) {
1306 else if ( node.getNodeData().isHasTaxonomy()
1307 && ( node.getNodeData().getTaxonomy().getIdentifier() != null )
1308 && match( node.getNodeData().getTaxonomy().getIdentifier().getValue(),
1314 else if ( node.getNodeData().isHasTaxonomy() && !node.getNodeData().getTaxonomy().getSynonyms().isEmpty() ) {
1315 final List<String> syns = node.getNodeData().getTaxonomy().getSynonyms();
1316 I: for( final String syn : syns ) {
1317 if ( match( syn, query, case_sensitive, partial ) ) {
1323 if ( !match && node.getNodeData().isHasSequence()
1324 && match( node.getNodeData().getSequence().getName(), query, case_sensitive, partial ) ) {
1327 if ( !match && node.getNodeData().isHasSequence()
1328 && match( node.getNodeData().getSequence().getSymbol(), query, case_sensitive, partial ) ) {
1332 && node.getNodeData().isHasSequence()
1333 && ( node.getNodeData().getSequence().getAccession() != null )
1334 && match( node.getNodeData().getSequence().getAccession().getValue(),
1340 if ( !match && node.getNodeData().isHasSequence()
1341 && ( node.getNodeData().getSequence().getDomainArchitecture() != null ) ) {
1342 final DomainArchitecture da = node.getNodeData().getSequence().getDomainArchitecture();
1343 I: for( int i = 0; i < da.getNumberOfDomains(); ++i ) {
1344 if ( match( da.getDomain( i ).getName(), query, case_sensitive, partial ) ) {
1350 if ( !match && ( node.getNodeData().getBinaryCharacters() != null ) ) {
1351 Iterator<String> it = node.getNodeData().getBinaryCharacters().getPresentCharacters().iterator();
1352 I: while ( it.hasNext() ) {
1353 if ( match( it.next(), query, case_sensitive, partial ) ) {
1358 it = node.getNodeData().getBinaryCharacters().getGainedCharacters().iterator();
1359 I: while ( it.hasNext() ) {
1360 if ( match( it.next(), query, case_sensitive, partial ) ) {
1373 public static List<PhylogenyNode> searchDataLogicalAnd( final String[] queries,
1374 final Phylogeny phy,
1375 final boolean case_sensitive,
1376 final boolean partial ) {
1377 final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
1378 if ( phy.isEmpty() || ( queries == null ) || ( queries.length < 1 ) ) {
1381 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
1382 final PhylogenyNode node = iter.next();
1383 boolean all_matched = true;
1384 for( final String query : queries ) {
1385 boolean match = false;
1386 if ( ForesterUtil.isEmpty( query ) ) {
1389 if ( match( node.getName(), query, case_sensitive, partial ) ) {
1392 else if ( node.getNodeData().isHasTaxonomy()
1393 && match( node.getNodeData().getTaxonomy().getTaxonomyCode(), query, case_sensitive, partial ) ) {
1396 else if ( node.getNodeData().isHasTaxonomy()
1397 && match( node.getNodeData().getTaxonomy().getCommonName(), query, case_sensitive, partial ) ) {
1400 else if ( node.getNodeData().isHasTaxonomy()
1401 && match( node.getNodeData().getTaxonomy().getScientificName(), query, case_sensitive, partial ) ) {
1404 else if ( node.getNodeData().isHasTaxonomy()
1405 && ( node.getNodeData().getTaxonomy().getIdentifier() != null )
1406 && match( node.getNodeData().getTaxonomy().getIdentifier().getValue(),
1412 else if ( node.getNodeData().isHasTaxonomy()
1413 && !node.getNodeData().getTaxonomy().getSynonyms().isEmpty() ) {
1414 final List<String> syns = node.getNodeData().getTaxonomy().getSynonyms();
1415 I: for( final String syn : syns ) {
1416 if ( match( syn, query, case_sensitive, partial ) ) {
1422 if ( !match && node.getNodeData().isHasSequence()
1423 && match( node.getNodeData().getSequence().getName(), query, case_sensitive, partial ) ) {
1426 if ( !match && node.getNodeData().isHasSequence()
1427 && match( node.getNodeData().getSequence().getSymbol(), query, case_sensitive, partial ) ) {
1431 && node.getNodeData().isHasSequence()
1432 && ( node.getNodeData().getSequence().getAccession() != null )
1433 && match( node.getNodeData().getSequence().getAccession().getValue(),
1439 if ( !match && node.getNodeData().isHasSequence()
1440 && ( node.getNodeData().getSequence().getDomainArchitecture() != null ) ) {
1441 final DomainArchitecture da = node.getNodeData().getSequence().getDomainArchitecture();
1442 I: for( int i = 0; i < da.getNumberOfDomains(); ++i ) {
1443 if ( match( da.getDomain( i ).getName(), query, case_sensitive, partial ) ) {
1449 if ( !match && ( node.getNodeData().getBinaryCharacters() != null ) ) {
1450 Iterator<String> it = node.getNodeData().getBinaryCharacters().getPresentCharacters().iterator();
1451 I: while ( it.hasNext() ) {
1452 if ( match( it.next(), query, case_sensitive, partial ) ) {
1457 it = node.getNodeData().getBinaryCharacters().getGainedCharacters().iterator();
1458 I: while ( it.hasNext() ) {
1459 if ( match( it.next(), query, case_sensitive, partial ) ) {
1464 // final String[] bcp_ary = node.getNodeData().getBinaryCharacters()
1465 // .getPresentCharactersAsStringArray();
1466 // I: for( final String bc : bcp_ary ) {
1467 // if ( match( bc, query, case_sensitive, partial ) ) {
1472 // final String[] bcg_ary = node.getNodeData().getBinaryCharacters()
1473 // .getGainedCharactersAsStringArray();
1474 // I: for( final String bc : bcg_ary ) {
1475 // if ( match( bc, query, case_sensitive, partial ) ) {
1482 all_matched = false;
1486 if ( all_matched ) {
1494 * Convenience method.
1495 * Sets value for the first confidence value (created if not present, values overwritten otherwise).
1497 public static void setBootstrapConfidence( final PhylogenyNode node, final double bootstrap_confidence_value ) {
1498 setConfidence( node, bootstrap_confidence_value, "bootstrap" );
1501 public static void setBranchColorValue( final PhylogenyNode node, final Color color ) {
1502 if ( node.getBranchData().getBranchColor() == null ) {
1503 node.getBranchData().setBranchColor( new BranchColor() );
1505 node.getBranchData().getBranchColor().setValue( color );
1509 * Convenience method
1511 public static void setBranchWidthValue( final PhylogenyNode node, final double branch_width_value ) {
1512 node.getBranchData().setBranchWidth( new BranchWidth( branch_width_value ) );
1516 * Convenience method.
1517 * Sets value for the first confidence value (created if not present, values overwritten otherwise).
1519 public static void setConfidence( final PhylogenyNode node, final double confidence_value ) {
1520 setConfidence( node, confidence_value, "" );
1524 * Convenience method.
1525 * Sets value for the first confidence value (created if not present, values overwritten otherwise).
1527 public static void setConfidence( final PhylogenyNode node, final double confidence_value, final String type ) {
1528 Confidence c = null;
1529 if ( node.getBranchData().getNumberOfConfidences() > 0 ) {
1530 c = node.getBranchData().getConfidence( 0 );
1533 c = new Confidence();
1534 node.getBranchData().addConfidence( c );
1537 c.setValue( confidence_value );
1540 public static void setScientificName( final PhylogenyNode node, final String scientific_name ) {
1541 if ( !node.getNodeData().isHasTaxonomy() ) {
1542 node.getNodeData().setTaxonomy( new Taxonomy() );
1544 node.getNodeData().getTaxonomy().setScientificName( scientific_name );
1548 * Convenience method to set the taxonomy code of a phylogeny node.
1552 * @param taxonomy_code
1554 public static void setTaxonomyCode( final PhylogenyNode node, final String taxonomy_code ) {
1555 if ( !node.getNodeData().isHasTaxonomy() ) {
1556 node.getNodeData().setTaxonomy( new Taxonomy() );
1558 node.getNodeData().getTaxonomy().setTaxonomyCode( taxonomy_code );
1562 * Removes from Phylogeny to_be_stripped all external Nodes which are
1563 * associated with a species NOT found in Phylogeny reference.
1566 * a reference Phylogeny
1567 * @param to_be_stripped
1568 * Phylogeny to be stripped
1569 * @return number of external nodes removed from to_be_stripped
1571 public static int taxonomyBasedDeletionOfExternalNodes( final Phylogeny reference, final Phylogeny to_be_stripped ) {
1572 final Set<String> ref_ext_taxo = new HashSet<String>();
1573 final ArrayList<PhylogenyNode> nodes_to_delete = new ArrayList<PhylogenyNode>();
1574 for( final PhylogenyNodeIterator it = reference.iteratorExternalForward(); it.hasNext(); ) {
1575 ref_ext_taxo.add( getSpecies( it.next() ) );
1577 for( final PhylogenyNodeIterator it = to_be_stripped.iteratorExternalForward(); it.hasNext(); ) {
1578 final PhylogenyNode n = it.next();
1579 if ( !ref_ext_taxo.contains( getSpecies( n ) ) ) {
1580 nodes_to_delete.add( n );
1583 for( final PhylogenyNode phylogenyNode : nodes_to_delete ) {
1584 to_be_stripped.deleteSubtree( phylogenyNode, true );
1586 return nodes_to_delete.size();
1590 * Arranges the order of childern for each node of this Phylogeny in such a
1591 * way that either the branch with more children is on top (right) or on
1592 * bottom (left), dependent on the value of boolean order.
1595 * decides in which direction to order
1598 public static void orderAppearance( final PhylogenyNode n,
1599 final boolean order,
1600 final boolean order_ext_alphabetically,
1601 final DESCENDANT_SORT_PRIORITY pri ) {
1602 if ( n.isExternal() ) {
1606 PhylogenyNode temp = null;
1607 if ( ( n.getNumberOfDescendants() == 2 )
1608 && ( n.getChildNode1().getNumberOfExternalNodes() != n.getChildNode2().getNumberOfExternalNodes() )
1609 && ( ( n.getChildNode1().getNumberOfExternalNodes() < n.getChildNode2().getNumberOfExternalNodes() ) == order ) ) {
1610 temp = n.getChildNode1();
1611 n.setChild1( n.getChildNode2() );
1612 n.setChild2( temp );
1614 else if ( order_ext_alphabetically ) {
1615 boolean all_ext = true;
1616 for( final PhylogenyNode i : n.getDescendants() ) {
1617 if ( !i.isExternal() ) {
1623 PhylogenyMethods.sortNodeDescendents( n, pri );
1626 for( int i = 0; i < n.getNumberOfDescendants(); ++i ) {
1627 orderAppearance( n.getChildNode( i ), order, order_ext_alphabetically, pri );
1632 public static enum PhylogenyNodeField {
1635 TAXONOMY_SCIENTIFIC_NAME,
1636 TAXONOMY_COMMON_NAME,
1639 TAXONOMY_ID_UNIPROT_1,
1640 TAXONOMY_ID_UNIPROT_2;
1643 public static enum TAXONOMY_EXTRACTION {
1644 NO, YES, PFAM_STYLE_ONLY;
1647 public static enum DESCENDANT_SORT_PRIORITY {
1648 TAXONOMY, SEQUENCE, NODE_NAME;