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 ) );
478 if ( !n.getNodeData().isHasTaxonomy() ) {
479 n.getNodeData().setTaxonomy( new Taxonomy() );
481 n.getNodeData().getTaxonomy().setIdentifier( new Identifier( name ) );
489 static double addPhylogenyDistances( final double a, final double b ) {
490 if ( ( a >= 0.0 ) && ( b >= 0.0 ) ) {
493 else if ( a >= 0.0 ) {
496 else if ( b >= 0.0 ) {
499 return PhylogenyDataUtil.BRANCH_LENGTH_DEFAULT;
502 // Helper for getUltraParalogousNodes( PhylogenyNode ).
503 public static boolean areAllChildrenDuplications( final PhylogenyNode n ) {
504 if ( n.isExternal() ) {
508 if ( n.isDuplication() ) {
510 for( final PhylogenyNode desc : n.getDescendants() ) {
511 if ( !areAllChildrenDuplications( desc ) ) {
523 public static int calculateDepth( final PhylogenyNode node ) {
524 PhylogenyNode n = node;
526 while ( !n.isRoot() ) {
533 public static double calculateDistanceToRoot( final PhylogenyNode node ) {
534 PhylogenyNode n = node;
536 while ( !n.isRoot() ) {
537 if ( n.getDistanceToParent() > 0.0 ) {
538 d += n.getDistanceToParent();
545 public static short calculateMaxBranchesToLeaf( final PhylogenyNode node ) {
546 if ( node.isExternal() ) {
550 for( PhylogenyNode d : node.getAllExternalDescendants() ) {
552 while ( d != node ) {
553 if ( d.isCollapse() ) {
568 public static int calculateMaxDepth( final Phylogeny phy ) {
570 for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) {
571 final PhylogenyNode node = iter.next();
572 final int steps = calculateDepth( node );
580 public static double calculateMaxDistanceToRoot( final Phylogeny phy ) {
582 for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) {
583 final PhylogenyNode node = iter.next();
584 final double d = calculateDistanceToRoot( node );
592 public static DescriptiveStatistics calculatNumberOfDescendantsPerNodeStatistics( final Phylogeny phy ) {
593 final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
594 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
595 final PhylogenyNode n = iter.next();
596 if ( !n.isExternal() ) {
597 stats.addValue( n.getNumberOfDescendants() );
603 public static DescriptiveStatistics calculatBranchLengthStatistics( final Phylogeny phy ) {
604 final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
605 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
606 final PhylogenyNode n = iter.next();
607 if ( !n.isRoot() && ( n.getDistanceToParent() >= 0.0 ) ) {
608 stats.addValue( n.getDistanceToParent() );
614 public static List<DescriptiveStatistics> calculatConfidenceStatistics( final Phylogeny phy ) {
615 final List<DescriptiveStatistics> stats = new ArrayList<DescriptiveStatistics>();
616 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
617 final PhylogenyNode n = iter.next();
618 if ( !n.isExternal() && !n.isRoot() ) {
619 if ( n.getBranchData().isHasConfidences() ) {
620 for( int i = 0; i < n.getBranchData().getConfidences().size(); ++i ) {
621 final Confidence c = n.getBranchData().getConfidences().get( i );
622 if ( ( i > ( stats.size() - 1 ) ) || ( stats.get( i ) == null ) ) {
623 stats.add( i, new BasicDescriptiveStatistics() );
625 if ( !ForesterUtil.isEmpty( c.getType() ) ) {
626 if ( !ForesterUtil.isEmpty( stats.get( i ).getDescription() ) ) {
627 if ( !stats.get( i ).getDescription().equalsIgnoreCase( c.getType() ) ) {
628 throw new IllegalArgumentException( "support values in node [" + n.toString()
629 + "] appear inconsistently ordered" );
632 stats.get( i ).setDescription( c.getType() );
634 stats.get( i ).addValue( ( ( c != null ) && ( c.getValue() >= 0 ) ) ? c.getValue() : 0 );
643 * Returns the set of distinct taxonomies of
644 * all external nodes of node.
645 * If at least one the external nodes has no taxonomy,
649 public static Set<Taxonomy> obtainDistinctTaxonomies( final PhylogenyNode node ) {
650 final List<PhylogenyNode> descs = node.getAllExternalDescendants();
651 final Set<Taxonomy> tax_set = new HashSet<Taxonomy>();
652 for( final PhylogenyNode n : descs ) {
653 if ( !n.getNodeData().isHasTaxonomy() || n.getNodeData().getTaxonomy().isEmpty() ) {
656 tax_set.add( n.getNodeData().getTaxonomy() );
662 * Returns a map of distinct taxonomies of
663 * all external nodes of node.
664 * If at least one of the external nodes has no taxonomy,
668 public static SortedMap<Taxonomy, Integer> obtainDistinctTaxonomyCounts( final PhylogenyNode node ) {
669 final List<PhylogenyNode> descs = node.getAllExternalDescendants();
670 final SortedMap<Taxonomy, Integer> tax_map = new TreeMap<Taxonomy, Integer>();
671 for( final PhylogenyNode n : descs ) {
672 if ( !n.getNodeData().isHasTaxonomy() || n.getNodeData().getTaxonomy().isEmpty() ) {
675 final Taxonomy t = n.getNodeData().getTaxonomy();
676 if ( tax_map.containsKey( t ) ) {
677 tax_map.put( t, tax_map.get( t ) + 1 );
686 public static int calculateNumberOfExternalNodesWithoutTaxonomy( final PhylogenyNode node ) {
687 final List<PhylogenyNode> descs = node.getAllExternalDescendants();
689 for( final PhylogenyNode n : descs ) {
690 if ( !n.getNodeData().isHasTaxonomy() || n.getNodeData().getTaxonomy().isEmpty() ) {
698 * Deep copies the phylogeny originating from this node.
700 static PhylogenyNode copySubTree( final PhylogenyNode source ) {
701 if ( source == null ) {
705 final PhylogenyNode newnode = source.copyNodeData();
706 if ( !source.isExternal() ) {
707 for( int i = 0; i < source.getNumberOfDescendants(); ++i ) {
708 newnode.setChildNode( i, PhylogenyMethods.copySubTree( source.getChildNode( i ) ) );
716 * Shallow copies the phylogeny originating from this node.
718 static PhylogenyNode copySubTreeShallow( final PhylogenyNode source ) {
719 if ( source == null ) {
723 final PhylogenyNode newnode = source.copyNodeDataShallow();
724 if ( !source.isExternal() ) {
725 for( int i = 0; i < source.getNumberOfDescendants(); ++i ) {
726 newnode.setChildNode( i, PhylogenyMethods.copySubTreeShallow( source.getChildNode( i ) ) );
733 public static void deleteExternalNodesNegativeSelection( final Set<Integer> to_delete, final Phylogeny phy ) {
735 for( final Integer id : to_delete ) {
736 phy.deleteSubtree( phy.getNode( id ), true );
741 public static void deleteExternalNodesNegativeSelection( final String[] node_names_to_delete, final Phylogeny p )
742 throws IllegalArgumentException {
743 for( int i = 0; i < node_names_to_delete.length; ++i ) {
744 if ( ForesterUtil.isEmpty( node_names_to_delete[ i ] ) ) {
747 List<PhylogenyNode> nodes = null;
748 nodes = p.getNodes( node_names_to_delete[ i ] );
749 final Iterator<PhylogenyNode> it = nodes.iterator();
750 while ( it.hasNext() ) {
751 final PhylogenyNode n = it.next();
752 if ( !n.isExternal() ) {
753 throw new IllegalArgumentException( "attempt to delete non-external node \""
754 + node_names_to_delete[ i ] + "\"" );
756 p.deleteSubtree( n, true );
761 public static void deleteExternalNodesPositiveSelection( final Set<Taxonomy> species_to_keep, final Phylogeny phy ) {
762 // final Set<Integer> to_delete = new HashSet<Integer>();
763 for( final PhylogenyNodeIterator it = phy.iteratorExternalForward(); it.hasNext(); ) {
764 final PhylogenyNode n = it.next();
765 if ( n.getNodeData().isHasTaxonomy() ) {
766 if ( !species_to_keep.contains( n.getNodeData().getTaxonomy() ) ) {
767 //to_delete.add( n.getNodeId() );
768 phy.deleteSubtree( n, true );
772 throw new IllegalArgumentException( "node " + n.getId() + " has no taxonomic data" );
776 phy.externalNodesHaveChanged();
777 // deleteExternalNodesNegativeSelection( to_delete, phy );
780 public static List<String> deleteExternalNodesPositiveSelection( final String[] node_names_to_keep,
781 final Phylogeny p ) {
782 final PhylogenyNodeIterator it = p.iteratorExternalForward();
783 final String[] to_delete = new String[ p.getNumberOfExternalNodes() ];
785 Arrays.sort( node_names_to_keep );
786 while ( it.hasNext() ) {
787 final String curent_name = it.next().getName();
788 if ( Arrays.binarySearch( node_names_to_keep, curent_name ) < 0 ) {
789 to_delete[ i++ ] = curent_name;
792 PhylogenyMethods.deleteExternalNodesNegativeSelection( to_delete, p );
793 final List<String> deleted = new ArrayList<String>();
794 for( final String n : to_delete ) {
795 if ( !ForesterUtil.isEmpty( n ) ) {
802 public static List<PhylogenyNode> getAllDescendants( final PhylogenyNode node ) {
803 final List<PhylogenyNode> descs = new ArrayList<PhylogenyNode>();
804 final Set<Integer> encountered = new HashSet<Integer>();
805 if ( !node.isExternal() ) {
806 final List<PhylogenyNode> exts = node.getAllExternalDescendants();
807 for( PhylogenyNode current : exts ) {
808 descs.add( current );
809 while ( current != node ) {
810 current = current.getParent();
811 if ( encountered.contains( current.getId() ) ) {
814 descs.add( current );
815 encountered.add( current.getId() );
829 public static Color getBranchColorValue( final PhylogenyNode node ) {
830 if ( node.getBranchData().getBranchColor() == null ) {
833 return node.getBranchData().getBranchColor().getValue();
839 public static double getBranchWidthValue( final PhylogenyNode node ) {
840 if ( !node.getBranchData().isHasBranchWidth() ) {
841 return BranchWidth.BRANCH_WIDTH_DEFAULT_VALUE;
843 return node.getBranchData().getBranchWidth().getValue();
849 public static double getConfidenceValue( final PhylogenyNode node ) {
850 if ( !node.getBranchData().isHasConfidences() ) {
851 return Confidence.CONFIDENCE_DEFAULT_VALUE;
853 return node.getBranchData().getConfidence( 0 ).getValue();
859 public static double[] getConfidenceValuesAsArray( final PhylogenyNode node ) {
860 if ( !node.getBranchData().isHasConfidences() ) {
861 return new double[ 0 ];
863 final double[] values = new double[ node.getBranchData().getConfidences().size() ];
865 for( final Confidence c : node.getBranchData().getConfidences() ) {
866 values[ i++ ] = c.getValue();
872 * Calculates the distance between PhylogenyNodes n1 and n2.
873 * PRECONDITION: n1 is a descendant of n2.
878 * @return distance between n1 and n2
880 private static double getDistance( PhylogenyNode n1, final PhylogenyNode n2 ) {
883 if ( n1.getDistanceToParent() > 0.0 ) {
884 d += n1.getDistanceToParent();
892 * Returns taxonomy t if all external descendants have
893 * the same taxonomy t, null otherwise.
896 public static Taxonomy getExternalDescendantsTaxonomy( final PhylogenyNode node ) {
897 final List<PhylogenyNode> descs = node.getAllExternalDescendants();
899 for( final PhylogenyNode n : descs ) {
900 if ( !n.getNodeData().isHasTaxonomy() || n.getNodeData().getTaxonomy().isEmpty() ) {
903 else if ( tax == null ) {
904 tax = n.getNodeData().getTaxonomy();
906 else if ( n.getNodeData().getTaxonomy().isEmpty() || !tax.isEqual( n.getNodeData().getTaxonomy() ) ) {
913 public static PhylogenyNode getFurthestDescendant( final PhylogenyNode node ) {
914 final List<PhylogenyNode> children = node.getAllExternalDescendants();
915 PhylogenyNode farthest = null;
916 double longest = -Double.MAX_VALUE;
917 for( final PhylogenyNode child : children ) {
918 if ( PhylogenyMethods.getDistance( child, node ) > longest ) {
920 longest = PhylogenyMethods.getDistance( child, node );
926 public static PhylogenyMethods getInstance() {
927 if ( PhylogenyMethods._instance == null ) {
928 PhylogenyMethods._instance = new PhylogenyMethods();
930 return PhylogenyMethods._instance;
934 * Returns the largest confidence value found on phy.
936 static public double getMaximumConfidenceValue( final Phylogeny phy ) {
937 double max = -Double.MAX_VALUE;
938 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
939 final double s = PhylogenyMethods.getConfidenceValue( iter.next() );
940 if ( ( s != Confidence.CONFIDENCE_DEFAULT_VALUE ) && ( s > max ) ) {
947 static public int getMinimumDescendentsPerInternalNodes( final Phylogeny phy ) {
948 int min = Integer.MAX_VALUE;
951 for( final PhylogenyNodeIterator it = phy.iteratorPreorder(); it.hasNext(); ) {
953 if ( n.isInternal() ) {
954 d = n.getNumberOfDescendants();
964 * Convenience method for display purposes.
965 * Not intended for algorithms.
967 public static String getSpecies( final PhylogenyNode node ) {
968 if ( !node.getNodeData().isHasTaxonomy() ) {
971 if ( !ForesterUtil.isEmpty( node.getNodeData().getTaxonomy().getTaxonomyCode() ) ) {
972 return node.getNodeData().getTaxonomy().getTaxonomyCode();
974 else if ( !ForesterUtil.isEmpty( node.getNodeData().getTaxonomy().getScientificName() ) ) {
975 return node.getNodeData().getTaxonomy().getScientificName();
978 return node.getNodeData().getTaxonomy().getCommonName();
983 * Returns all Nodes which are connected to external PhylogenyNode n of this
984 * Phylogeny by a path containing only speciation events. We call these
985 * "super orthologs". Nodes are returned as Vector of references to Nodes.
987 * PRECONDITION: This tree must be binary and rooted, and speciation -
988 * duplication need to be assigned for each of its internal Nodes.
990 * Returns null if this Phylogeny is empty or if n is internal.
992 * external PhylogenyNode whose strictly speciation related Nodes
994 * @return Vector of references to all strictly speciation related Nodes of
995 * PhylogenyNode n of this Phylogeny, null if this Phylogeny is
996 * empty or if n is internal
998 public static List<PhylogenyNode> getSuperOrthologousNodes( final PhylogenyNode n ) {
1000 PhylogenyNode node = n, deepest = null;
1001 final List<PhylogenyNode> v = new ArrayList<PhylogenyNode>();
1002 if ( !node.isExternal() ) {
1005 while ( !node.isRoot() && !node.getParent().isDuplication() ) {
1006 node = node.getParent();
1009 deepest.setIndicatorsToZero();
1011 if ( !node.isExternal() ) {
1012 if ( node.getIndicator() == 0 ) {
1013 node.setIndicator( ( byte ) 1 );
1014 if ( !node.isDuplication() ) {
1015 node = node.getChildNode1();
1018 if ( node.getIndicator() == 1 ) {
1019 node.setIndicator( ( byte ) 2 );
1020 if ( !node.isDuplication() ) {
1021 node = node.getChildNode2();
1024 if ( ( node != deepest ) && ( node.getIndicator() == 2 ) ) {
1025 node = node.getParent();
1032 if ( node != deepest ) {
1033 node = node.getParent();
1036 node.setIndicator( ( byte ) 2 );
1039 } while ( ( node != deepest ) || ( deepest.getIndicator() != 2 ) );
1044 * Convenience method for display purposes.
1045 * Not intended for algorithms.
1047 public static String getTaxonomyIdentifier( final PhylogenyNode node ) {
1048 if ( !node.getNodeData().isHasTaxonomy() || ( node.getNodeData().getTaxonomy().getIdentifier() == null ) ) {
1051 return node.getNodeData().getTaxonomy().getIdentifier().getValue();
1055 * Returns all Nodes which are connected to external PhylogenyNode n of this
1056 * Phylogeny by a path containing, and leading to, only duplication events.
1057 * We call these "ultra paralogs". Nodes are returned as Vector of
1058 * references to Nodes.
1060 * PRECONDITION: This tree must be binary and rooted, and speciation -
1061 * duplication need to be assigned for each of its internal Nodes.
1063 * Returns null if this Phylogeny is empty or if n is internal.
1065 * (Last modified: 10/06/01)
1068 * external PhylogenyNode whose ultra paralogs are to be returned
1069 * @return Vector of references to all ultra paralogs of PhylogenyNode n of
1070 * this Phylogeny, null if this Phylogeny is empty or if n is
1073 public static List<PhylogenyNode> getUltraParalogousNodes( final PhylogenyNode n ) {
1075 PhylogenyNode node = n;
1076 if ( !node.isExternal() ) {
1079 while ( !node.isRoot() && node.getParent().isDuplication() && areAllChildrenDuplications( node.getParent() ) ) {
1080 node = node.getParent();
1082 final List<PhylogenyNode> nodes = node.getAllExternalDescendants();
1087 public static String inferCommonPartOfScientificNameOfDescendants( final PhylogenyNode node ) {
1088 final List<PhylogenyNode> descs = node.getDescendants();
1090 for( final PhylogenyNode n : descs ) {
1091 if ( !n.getNodeData().isHasTaxonomy()
1092 || ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
1095 else if ( sn == null ) {
1096 sn = n.getNodeData().getTaxonomy().getScientificName().trim();
1099 String sn_current = n.getNodeData().getTaxonomy().getScientificName().trim();
1100 if ( !sn.equals( sn_current ) ) {
1101 boolean overlap = false;
1102 while ( ( sn.indexOf( ' ' ) >= 0 ) || ( sn_current.indexOf( ' ' ) >= 0 ) ) {
1103 if ( ForesterUtil.countChars( sn, ' ' ) > ForesterUtil.countChars( sn_current, ' ' ) ) {
1104 sn = sn.substring( 0, sn.lastIndexOf( ' ' ) ).trim();
1107 sn_current = sn_current.substring( 0, sn_current.lastIndexOf( ' ' ) ).trim();
1109 if ( sn.equals( sn_current ) ) {
1123 public static boolean isHasExternalDescendant( final PhylogenyNode node ) {
1124 for( int i = 0; i < node.getNumberOfDescendants(); ++i ) {
1125 if ( node.getChildNode( i ).isExternal() ) {
1133 * This is case insensitive.
1136 public synchronized static boolean isTaxonomyHasIdentifierOfGivenProvider( final Taxonomy tax,
1137 final String[] providers ) {
1138 if ( ( tax.getIdentifier() != null ) && !ForesterUtil.isEmpty( tax.getIdentifier().getProvider() ) ) {
1139 final String my_tax_prov = tax.getIdentifier().getProvider();
1140 for( final String provider : providers ) {
1141 if ( provider.equalsIgnoreCase( my_tax_prov ) ) {
1152 private static boolean match( final String s,
1154 final boolean case_sensitive,
1155 final boolean partial ) {
1156 if ( ForesterUtil.isEmpty( s ) || ForesterUtil.isEmpty( query ) ) {
1159 String my_s = s.trim();
1160 String my_query = query.trim();
1161 if ( !case_sensitive ) {
1162 my_s = my_s.toLowerCase();
1163 my_query = my_query.toLowerCase();
1166 return my_s.indexOf( my_query ) >= 0;
1169 return my_s.equals( my_query );
1173 public static void midpointRoot( final Phylogeny phylogeny ) {
1174 if ( phylogeny.getNumberOfExternalNodes() < 2 ) {
1177 final PhylogenyMethods methods = getInstance();
1178 final double farthest_d = methods.calculateFurthestDistance( phylogeny );
1179 final PhylogenyNode f1 = methods.getFarthestNode1();
1180 final PhylogenyNode f2 = methods.getFarthestNode2();
1181 if ( farthest_d <= 0.0 ) {
1184 double x = farthest_d / 2.0;
1185 PhylogenyNode n = f1;
1186 if ( PhylogenyMethods.getDistance( f1, phylogeny.getRoot() ) < PhylogenyMethods.getDistance( f2, phylogeny
1190 while ( ( x > n.getDistanceToParent() ) && !n.isRoot() ) {
1191 x -= ( n.getDistanceToParent() > 0 ? n.getDistanceToParent() : 0 );
1194 phylogeny.reRoot( n, x );
1195 phylogeny.recalculateNumberOfExternalDescendants( true );
1196 final PhylogenyNode a = getFurthestDescendant( phylogeny.getRoot().getChildNode1() );
1197 final PhylogenyNode b = getFurthestDescendant( phylogeny.getRoot().getChildNode2() );
1198 final double da = getDistance( a, phylogeny.getRoot() );
1199 final double db = getDistance( b, phylogeny.getRoot() );
1200 if ( Math.abs( da - db ) > 0.000001 ) {
1201 throw new FailedConditionCheckException( "this should not have happened: midpoint rooting failed: da="
1202 + da + ", db=" + db + ", diff=" + Math.abs( da - db ) );
1206 public static void normalizeBootstrapValues( final Phylogeny phylogeny,
1207 final double max_bootstrap_value,
1208 final double max_normalized_value ) {
1209 for( final PhylogenyNodeIterator iter = phylogeny.iteratorPreorder(); iter.hasNext(); ) {
1210 final PhylogenyNode node = iter.next();
1211 if ( node.isInternal() ) {
1212 final double confidence = getConfidenceValue( node );
1213 if ( confidence != Confidence.CONFIDENCE_DEFAULT_VALUE ) {
1214 if ( confidence >= max_bootstrap_value ) {
1215 setBootstrapConfidence( node, max_normalized_value );
1218 setBootstrapConfidence( node, ( confidence * max_normalized_value ) / max_bootstrap_value );
1225 public static List<PhylogenyNode> obtainAllNodesAsList( final Phylogeny phy ) {
1226 final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
1227 if ( phy.isEmpty() ) {
1230 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
1231 nodes.add( iter.next() );
1236 public static void postorderBranchColorAveragingExternalNodeBased( final Phylogeny p ) {
1237 for( final PhylogenyNodeIterator iter = p.iteratorPostorder(); iter.hasNext(); ) {
1238 final PhylogenyNode node = iter.next();
1243 if ( node.isInternal() ) {
1244 for( final PhylogenyNodeIterator iterator = node.iterateChildNodesForward(); iterator.hasNext(); ) {
1245 final PhylogenyNode child_node = iterator.next();
1246 final Color child_color = getBranchColorValue( child_node );
1247 if ( child_color != null ) {
1249 red += child_color.getRed();
1250 green += child_color.getGreen();
1251 blue += child_color.getBlue();
1254 setBranchColorValue( node,
1255 new Color( ForesterUtil.roundToInt( red / n ),
1256 ForesterUtil.roundToInt( green / n ),
1257 ForesterUtil.roundToInt( blue / n ) ) );
1262 public static void removeNode( final PhylogenyNode remove_me, final Phylogeny phylogeny ) {
1263 if ( remove_me.isRoot() ) {
1264 throw new IllegalArgumentException( "ill advised attempt to remove root node" );
1266 if ( remove_me.isExternal() ) {
1267 phylogeny.deleteSubtree( remove_me, false );
1270 final PhylogenyNode parent = remove_me.getParent();
1271 final List<PhylogenyNode> descs = remove_me.getDescendants();
1272 parent.removeChildNode( remove_me );
1273 for( final PhylogenyNode desc : descs ) {
1274 parent.addAsChild( desc );
1275 desc.setDistanceToParent( addPhylogenyDistances( remove_me.getDistanceToParent(),
1276 desc.getDistanceToParent() ) );
1278 remove_me.setParent( null );
1279 phylogeny.setIdHash( null );
1280 phylogeny.externalNodesHaveChanged();
1284 public static List<PhylogenyNode> searchData( final String query,
1285 final Phylogeny phy,
1286 final boolean case_sensitive,
1287 final boolean partial ) {
1288 final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
1289 if ( phy.isEmpty() || ( query == null ) ) {
1292 if ( ForesterUtil.isEmpty( query ) ) {
1295 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
1296 final PhylogenyNode node = iter.next();
1297 boolean match = false;
1298 if ( match( node.getName(), query, case_sensitive, partial ) ) {
1301 else if ( node.getNodeData().isHasTaxonomy()
1302 && match( node.getNodeData().getTaxonomy().getTaxonomyCode(), query, case_sensitive, partial ) ) {
1305 else if ( node.getNodeData().isHasTaxonomy()
1306 && match( node.getNodeData().getTaxonomy().getCommonName(), query, case_sensitive, partial ) ) {
1309 else if ( node.getNodeData().isHasTaxonomy()
1310 && match( node.getNodeData().getTaxonomy().getScientificName(), query, case_sensitive, partial ) ) {
1313 else if ( node.getNodeData().isHasTaxonomy()
1314 && ( node.getNodeData().getTaxonomy().getIdentifier() != null )
1315 && match( node.getNodeData().getTaxonomy().getIdentifier().getValue(),
1321 else if ( node.getNodeData().isHasTaxonomy() && !node.getNodeData().getTaxonomy().getSynonyms().isEmpty() ) {
1322 final List<String> syns = node.getNodeData().getTaxonomy().getSynonyms();
1323 I: for( final String syn : syns ) {
1324 if ( match( syn, query, case_sensitive, partial ) ) {
1330 if ( !match && node.getNodeData().isHasSequence()
1331 && match( node.getNodeData().getSequence().getName(), query, case_sensitive, partial ) ) {
1334 if ( !match && node.getNodeData().isHasSequence()
1335 && match( node.getNodeData().getSequence().getSymbol(), query, case_sensitive, partial ) ) {
1339 && node.getNodeData().isHasSequence()
1340 && ( node.getNodeData().getSequence().getAccession() != null )
1341 && match( node.getNodeData().getSequence().getAccession().getValue(),
1347 if ( !match && node.getNodeData().isHasSequence()
1348 && ( node.getNodeData().getSequence().getDomainArchitecture() != null ) ) {
1349 final DomainArchitecture da = node.getNodeData().getSequence().getDomainArchitecture();
1350 I: for( int i = 0; i < da.getNumberOfDomains(); ++i ) {
1351 if ( match( da.getDomain( i ).getName(), query, case_sensitive, partial ) ) {
1357 if ( !match && ( node.getNodeData().getBinaryCharacters() != null ) ) {
1358 Iterator<String> it = node.getNodeData().getBinaryCharacters().getPresentCharacters().iterator();
1359 I: while ( it.hasNext() ) {
1360 if ( match( it.next(), query, case_sensitive, partial ) ) {
1365 it = node.getNodeData().getBinaryCharacters().getGainedCharacters().iterator();
1366 I: while ( it.hasNext() ) {
1367 if ( match( it.next(), query, case_sensitive, partial ) ) {
1380 public static List<PhylogenyNode> searchDataLogicalAnd( final String[] queries,
1381 final Phylogeny phy,
1382 final boolean case_sensitive,
1383 final boolean partial ) {
1384 final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
1385 if ( phy.isEmpty() || ( queries == null ) || ( queries.length < 1 ) ) {
1388 for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
1389 final PhylogenyNode node = iter.next();
1390 boolean all_matched = true;
1391 for( final String query : queries ) {
1392 boolean match = false;
1393 if ( ForesterUtil.isEmpty( query ) ) {
1396 if ( match( node.getName(), query, case_sensitive, partial ) ) {
1399 else if ( node.getNodeData().isHasTaxonomy()
1400 && match( node.getNodeData().getTaxonomy().getTaxonomyCode(), query, case_sensitive, partial ) ) {
1403 else if ( node.getNodeData().isHasTaxonomy()
1404 && match( node.getNodeData().getTaxonomy().getCommonName(), query, case_sensitive, partial ) ) {
1407 else if ( node.getNodeData().isHasTaxonomy()
1408 && match( node.getNodeData().getTaxonomy().getScientificName(), query, case_sensitive, partial ) ) {
1411 else if ( node.getNodeData().isHasTaxonomy()
1412 && ( node.getNodeData().getTaxonomy().getIdentifier() != null )
1413 && match( node.getNodeData().getTaxonomy().getIdentifier().getValue(),
1419 else if ( node.getNodeData().isHasTaxonomy()
1420 && !node.getNodeData().getTaxonomy().getSynonyms().isEmpty() ) {
1421 final List<String> syns = node.getNodeData().getTaxonomy().getSynonyms();
1422 I: for( final String syn : syns ) {
1423 if ( match( syn, query, case_sensitive, partial ) ) {
1429 if ( !match && node.getNodeData().isHasSequence()
1430 && match( node.getNodeData().getSequence().getName(), query, case_sensitive, partial ) ) {
1433 if ( !match && node.getNodeData().isHasSequence()
1434 && match( node.getNodeData().getSequence().getSymbol(), query, case_sensitive, partial ) ) {
1438 && node.getNodeData().isHasSequence()
1439 && ( node.getNodeData().getSequence().getAccession() != null )
1440 && match( node.getNodeData().getSequence().getAccession().getValue(),
1446 if ( !match && node.getNodeData().isHasSequence()
1447 && ( node.getNodeData().getSequence().getDomainArchitecture() != null ) ) {
1448 final DomainArchitecture da = node.getNodeData().getSequence().getDomainArchitecture();
1449 I: for( int i = 0; i < da.getNumberOfDomains(); ++i ) {
1450 if ( match( da.getDomain( i ).getName(), query, case_sensitive, partial ) ) {
1456 if ( !match && ( node.getNodeData().getBinaryCharacters() != null ) ) {
1457 Iterator<String> it = node.getNodeData().getBinaryCharacters().getPresentCharacters().iterator();
1458 I: while ( it.hasNext() ) {
1459 if ( match( it.next(), query, case_sensitive, partial ) ) {
1464 it = node.getNodeData().getBinaryCharacters().getGainedCharacters().iterator();
1465 I: while ( it.hasNext() ) {
1466 if ( match( it.next(), query, case_sensitive, partial ) ) {
1471 // final String[] bcp_ary = node.getNodeData().getBinaryCharacters()
1472 // .getPresentCharactersAsStringArray();
1473 // I: for( final String bc : bcp_ary ) {
1474 // if ( match( bc, query, case_sensitive, partial ) ) {
1479 // final String[] bcg_ary = node.getNodeData().getBinaryCharacters()
1480 // .getGainedCharactersAsStringArray();
1481 // I: for( final String bc : bcg_ary ) {
1482 // if ( match( bc, query, case_sensitive, partial ) ) {
1489 all_matched = false;
1493 if ( all_matched ) {
1501 * Convenience method.
1502 * Sets value for the first confidence value (created if not present, values overwritten otherwise).
1504 public static void setBootstrapConfidence( final PhylogenyNode node, final double bootstrap_confidence_value ) {
1505 setConfidence( node, bootstrap_confidence_value, "bootstrap" );
1508 public static void setBranchColorValue( final PhylogenyNode node, final Color color ) {
1509 if ( node.getBranchData().getBranchColor() == null ) {
1510 node.getBranchData().setBranchColor( new BranchColor() );
1512 node.getBranchData().getBranchColor().setValue( color );
1516 * Convenience method
1518 public static void setBranchWidthValue( final PhylogenyNode node, final double branch_width_value ) {
1519 node.getBranchData().setBranchWidth( new BranchWidth( branch_width_value ) );
1523 * Convenience method.
1524 * Sets value for the first confidence value (created if not present, values overwritten otherwise).
1526 public static void setConfidence( final PhylogenyNode node, final double confidence_value ) {
1527 setConfidence( node, confidence_value, "" );
1531 * Convenience method.
1532 * Sets value for the first confidence value (created if not present, values overwritten otherwise).
1534 public static void setConfidence( final PhylogenyNode node, final double confidence_value, final String type ) {
1535 Confidence c = null;
1536 if ( node.getBranchData().getNumberOfConfidences() > 0 ) {
1537 c = node.getBranchData().getConfidence( 0 );
1540 c = new Confidence();
1541 node.getBranchData().addConfidence( c );
1544 c.setValue( confidence_value );
1547 public static void setScientificName( final PhylogenyNode node, final String scientific_name ) {
1548 if ( !node.getNodeData().isHasTaxonomy() ) {
1549 node.getNodeData().setTaxonomy( new Taxonomy() );
1551 node.getNodeData().getTaxonomy().setScientificName( scientific_name );
1555 * Convenience method to set the taxonomy code of a phylogeny node.
1559 * @param taxonomy_code
1561 public static void setTaxonomyCode( final PhylogenyNode node, final String taxonomy_code ) {
1562 if ( !node.getNodeData().isHasTaxonomy() ) {
1563 node.getNodeData().setTaxonomy( new Taxonomy() );
1565 node.getNodeData().getTaxonomy().setTaxonomyCode( taxonomy_code );
1569 * Removes from Phylogeny to_be_stripped all external Nodes which are
1570 * associated with a species NOT found in Phylogeny reference.
1573 * a reference Phylogeny
1574 * @param to_be_stripped
1575 * Phylogeny to be stripped
1576 * @return number of external nodes removed from to_be_stripped
1578 public static int taxonomyBasedDeletionOfExternalNodes( final Phylogeny reference, final Phylogeny to_be_stripped ) {
1579 final Set<String> ref_ext_taxo = new HashSet<String>();
1580 final ArrayList<PhylogenyNode> nodes_to_delete = new ArrayList<PhylogenyNode>();
1581 for( final PhylogenyNodeIterator it = reference.iteratorExternalForward(); it.hasNext(); ) {
1582 ref_ext_taxo.add( getSpecies( it.next() ) );
1584 for( final PhylogenyNodeIterator it = to_be_stripped.iteratorExternalForward(); it.hasNext(); ) {
1585 final PhylogenyNode n = it.next();
1586 if ( !ref_ext_taxo.contains( getSpecies( n ) ) ) {
1587 nodes_to_delete.add( n );
1590 for( final PhylogenyNode phylogenyNode : nodes_to_delete ) {
1591 to_be_stripped.deleteSubtree( phylogenyNode, true );
1593 return nodes_to_delete.size();
1597 * Arranges the order of childern for each node of this Phylogeny in such a
1598 * way that either the branch with more children is on top (right) or on
1599 * bottom (left), dependent on the value of boolean order.
1602 * decides in which direction to order
1605 public static void orderAppearance( final PhylogenyNode n,
1606 final boolean order,
1607 final boolean order_ext_alphabetically,
1608 final DESCENDANT_SORT_PRIORITY pri ) {
1609 if ( n.isExternal() ) {
1613 PhylogenyNode temp = null;
1614 if ( ( n.getNumberOfDescendants() == 2 )
1615 && ( n.getChildNode1().getNumberOfExternalNodes() != n.getChildNode2().getNumberOfExternalNodes() )
1616 && ( ( n.getChildNode1().getNumberOfExternalNodes() < n.getChildNode2().getNumberOfExternalNodes() ) == order ) ) {
1617 temp = n.getChildNode1();
1618 n.setChild1( n.getChildNode2() );
1619 n.setChild2( temp );
1621 else if ( order_ext_alphabetically ) {
1622 boolean all_ext = true;
1623 for( final PhylogenyNode i : n.getDescendants() ) {
1624 if ( !i.isExternal() ) {
1630 PhylogenyMethods.sortNodeDescendents( n, pri );
1633 for( int i = 0; i < n.getNumberOfDescendants(); ++i ) {
1634 orderAppearance( n.getChildNode( i ), order, order_ext_alphabetically, pri );
1639 public static enum PhylogenyNodeField {
1642 TAXONOMY_SCIENTIFIC_NAME,
1643 TAXONOMY_COMMON_NAME,
1646 TAXONOMY_ID_UNIPROT_1,
1647 TAXONOMY_ID_UNIPROT_2,
1651 public static enum TAXONOMY_EXTRACTION {
1652 NO, YES, PFAM_STYLE_ONLY;
1655 public static enum DESCENDANT_SORT_PRIORITY {
1656 TAXONOMY, SEQUENCE, NODE_NAME;