return farthest_d;
}
- final public static Event getEventAtLCA( final PhylogenyNode n1, final PhylogenyNode n2 ) {
- return calculateLCA( n1, n2 ).getNodeData().getEvent();
- }
-
@Override
public Object clone() throws CloneNotSupportedException {
throw new CloneNotSupportedException();
return _farthest_2;
}
- final public static void deleteNonOrthologousExternalNodes( final Phylogeny phy, final PhylogenyNode n ) {
- if ( n.isInternal() ) {
- throw new IllegalArgumentException( "node is not external" );
- }
- final ArrayList<PhylogenyNode> to_delete = new ArrayList<PhylogenyNode>();
- for( final PhylogenyNodeIterator it = phy.iteratorExternalForward(); it.hasNext(); ) {
- final PhylogenyNode i = it.next();
- if ( !PhylogenyMethods.getEventAtLCA( n, i ).isSpeciation() ) {
- to_delete.add( i );
+ public static DescriptiveStatistics calculatBranchLengthStatistics( final Phylogeny phy ) {
+ final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
+ for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
+ final PhylogenyNode n = iter.next();
+ if ( !n.isRoot() && ( n.getDistanceToParent() >= 0.0 ) ) {
+ stats.addValue( n.getDistanceToParent() );
}
}
- for( final PhylogenyNode d : to_delete ) {
- phy.deleteSubtree( d, true );
+ return stats;
+ }
+
+ public static List<DescriptiveStatistics> calculatConfidenceStatistics( final Phylogeny phy ) {
+ final List<DescriptiveStatistics> stats = new ArrayList<DescriptiveStatistics>();
+ for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
+ final PhylogenyNode n = iter.next();
+ if ( !n.isExternal() && !n.isRoot() ) {
+ if ( n.getBranchData().isHasConfidences() ) {
+ for( int i = 0; i < n.getBranchData().getConfidences().size(); ++i ) {
+ final Confidence c = n.getBranchData().getConfidences().get( i );
+ if ( ( i > ( stats.size() - 1 ) ) || ( stats.get( i ) == null ) ) {
+ stats.add( i, new BasicDescriptiveStatistics() );
+ }
+ if ( !ForesterUtil.isEmpty( c.getType() ) ) {
+ if ( !ForesterUtil.isEmpty( stats.get( i ).getDescription() ) ) {
+ if ( !stats.get( i ).getDescription().equalsIgnoreCase( c.getType() ) ) {
+ throw new IllegalArgumentException( "support values in node [" + n.toString()
+ + "] appear inconsistently ordered" );
+ }
+ }
+ stats.get( i ).setDescription( c.getType() );
+ }
+ stats.get( i ).addValue( ( ( c != null ) && ( c.getValue() >= 0 ) ) ? c.getValue() : 0 );
+ }
+ }
+ }
}
- phy.clearHashIdToNodeMap();
- phy.externalNodesHaveChanged();
+ return stats;
}
/**
throw new IllegalArgumentException( "illegal attempt to calculate LCA of two nodes which do not share a common root" );
}
- public static final void preOrderReId( final Phylogeny phy ) {
- if ( phy.isEmpty() ) {
- return;
- }
- phy.setIdToNodeMap( null );
- int i = PhylogenyNode.getNodeCount();
- for( final PhylogenyNodeIterator it = phy.iteratorPreorder(); it.hasNext(); ) {
- it.next().setId( i++ );
- }
- PhylogenyNode.setNodeCount( i );
- }
-
/**
* Returns the LCA of PhylogenyNodes node1 and node2.
* Precondition: ids are in pre-order (or level-order).
return node1;
}
- /**
- * Returns all orthologs of the external PhylogenyNode n of this Phylogeny.
- * Orthologs are returned as List of node references.
- * <p>
- * PRECONDITION: This tree must be binary and rooted, and speciation -
- * duplication need to be assigned for each of its internal Nodes.
- * <p>
- * Returns null if this Phylogeny is empty or if n is internal.
- * @param n
- * external PhylogenyNode whose orthologs are to be returned
- * @return Vector of references to all orthologous Nodes of PhylogenyNode n
- * of this Phylogeny, null if this Phylogeny is empty or if n is
- * internal
- */
- public final static List<PhylogenyNode> getOrthologousNodes( final Phylogeny phy, final PhylogenyNode node ) {
- final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
- PhylogenyMethods.preOrderReId( phy );
- final PhylogenyNodeIterator it = phy.iteratorExternalForward();
- while ( it.hasNext() ) {
- final PhylogenyNode temp_node = it.next();
- if ( ( temp_node != node ) && !calculateLCAonTreeWithIdsInPreOrder( node, temp_node ).isDuplication() ) {
- nodes.add( temp_node );
+ public static short calculateMaxBranchesToLeaf( final PhylogenyNode node ) {
+ if ( node.isExternal() ) {
+ return 0;
+ }
+ short max = 0;
+ for( PhylogenyNode d : node.getAllExternalDescendants() ) {
+ short steps = 0;
+ while ( d != node ) {
+ if ( d.isCollapse() ) {
+ steps = 0;
+ }
+ else {
+ steps++;
+ }
+ d = d.getParent();
+ }
+ if ( max < steps ) {
+ max = steps;
}
}
- return nodes;
+ return max;
+ }
+
+ public static int calculateMaxDepth( final Phylogeny phy ) {
+ int max = 0;
+ for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) {
+ final PhylogenyNode node = iter.next();
+ final int steps = node.calculateDepth();
+ if ( steps > max ) {
+ max = steps;
+ }
+ }
+ return max;
+ }
+
+ public static double calculateMaxDistanceToRoot( final Phylogeny phy ) {
+ double max = 0.0;
+ for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) {
+ final PhylogenyNode node = iter.next();
+ final double d = node.calculateDistanceToRoot();
+ if ( d > max ) {
+ max = d;
+ }
+ }
+ return max;
+ }
+
+ public static int calculateNumberOfExternalNodesWithoutTaxonomy( final PhylogenyNode node ) {
+ final List<PhylogenyNode> descs = node.getAllExternalDescendants();
+ int x = 0;
+ for( final PhylogenyNode n : descs ) {
+ if ( !n.getNodeData().isHasTaxonomy() || n.getNodeData().getTaxonomy().isEmpty() ) {
+ x++;
+ }
+ }
+ return x;
+ }
+
+ public static DescriptiveStatistics calculatNumberOfDescendantsPerNodeStatistics( final Phylogeny phy ) {
+ final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
+ for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
+ final PhylogenyNode n = iter.next();
+ if ( !n.isExternal() ) {
+ stats.addValue( n.getNumberOfDescendants() );
+ }
+ }
+ return stats;
+ }
+
+ public static int countNumberOfPolytomies( final Phylogeny phy ) {
+ int count = 0;
+ for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
+ final PhylogenyNode n = iter.next();
+ if ( !n.isExternal() && ( n.getNumberOfDescendants() > 2 ) ) {
+ count++;
+ }
+ }
+ return count;
}
public static final HashMap<String, PhylogenyNode> createNameToExtNodeMap( final Phylogeny phy ) {
return nodes;
}
- public final static Phylogeny[] readPhylogenies( final PhylogenyParser parser, final File file ) throws IOException {
- final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
- final Phylogeny[] trees = factory.create( file, parser );
- if ( ( trees == null ) || ( trees.length == 0 ) ) {
- throw new PhylogenyParserException( "Unable to parse phylogeny from file: " + file );
+ public static void deleteExternalNodesNegativeSelection( final Set<Integer> to_delete, final Phylogeny phy ) {
+ phy.clearHashIdToNodeMap();
+ for( final Integer id : to_delete ) {
+ phy.deleteSubtree( phy.getNode( id ), true );
}
- return trees;
+ phy.clearHashIdToNodeMap();
+ phy.externalNodesHaveChanged();
}
- public final static Phylogeny[] readPhylogenies( final PhylogenyParser parser, final List<File> files )
- throws IOException {
- final List<Phylogeny> tree_list = new ArrayList<Phylogeny>();
- for( final File file : files ) {
- final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
- final Phylogeny[] trees = factory.create( file, parser );
- if ( ( trees == null ) || ( trees.length == 0 ) ) {
- throw new PhylogenyParserException( "Unable to parse phylogeny from file: " + file );
+ public static void deleteExternalNodesNegativeSelection( final String[] node_names_to_delete, final Phylogeny p )
+ throws IllegalArgumentException {
+ for( final String element : node_names_to_delete ) {
+ if ( ForesterUtil.isEmpty( element ) ) {
+ continue;
+ }
+ List<PhylogenyNode> nodes = null;
+ nodes = p.getNodes( element );
+ final Iterator<PhylogenyNode> it = nodes.iterator();
+ while ( it.hasNext() ) {
+ final PhylogenyNode n = it.next();
+ if ( !n.isExternal() ) {
+ throw new IllegalArgumentException( "attempt to delete non-external node \"" + element + "\"" );
+ }
+ p.deleteSubtree( n, true );
}
- tree_list.addAll( Arrays.asList( trees ) );
}
- return tree_list.toArray( new Phylogeny[ tree_list.size() ] );
+ p.clearHashIdToNodeMap();
+ p.externalNodesHaveChanged();
}
- final static public void transferInternalNodeNamesToConfidence( final Phylogeny phy ) {
- final PhylogenyNodeIterator it = phy.iteratorPostorder();
- while ( it.hasNext() ) {
+ public static void deleteExternalNodesPositiveSelection( final Set<Taxonomy> species_to_keep, final Phylogeny phy ) {
+ // final Set<Integer> to_delete = new HashSet<Integer>();
+ for( final PhylogenyNodeIterator it = phy.iteratorExternalForward(); it.hasNext(); ) {
final PhylogenyNode n = it.next();
- if ( !n.isExternal() && !n.getBranchData().isHasConfidences() ) {
- if ( !ForesterUtil.isEmpty( n.getName() ) ) {
- double d = -1.0;
- try {
- d = Double.parseDouble( n.getName() );
- }
- catch ( final Exception e ) {
- d = -1.0;
- }
- if ( d >= 0.0 ) {
- n.getBranchData().addConfidence( new Confidence( d, "" ) );
- n.setName( "" );
- }
+ if ( n.getNodeData().isHasTaxonomy() ) {
+ if ( !species_to_keep.contains( n.getNodeData().getTaxonomy() ) ) {
+ //to_delete.add( n.getNodeId() );
+ phy.deleteSubtree( n, true );
}
}
+ else {
+ throw new IllegalArgumentException( "node " + n.getId() + " has no taxonomic data" );
+ }
}
+ phy.clearHashIdToNodeMap();
+ phy.externalNodesHaveChanged();
}
- final static public void transferInternalNamesToBootstrapSupport( final Phylogeny phy ) {
- final PhylogenyNodeIterator it = phy.iteratorPostorder();
+ public static List<String> deleteExternalNodesPositiveSelection( final String[] node_names_to_keep,
+ final Phylogeny p ) {
+ final PhylogenyNodeIterator it = p.iteratorExternalForward();
+ final String[] to_delete = new String[ p.getNumberOfExternalNodes() ];
+ int i = 0;
+ Arrays.sort( node_names_to_keep );
while ( it.hasNext() ) {
- final PhylogenyNode n = it.next();
- if ( !n.isExternal() && !ForesterUtil.isEmpty( n.getName() ) ) {
- double value = -1;
- try {
- value = Double.parseDouble( n.getName() );
- }
- catch ( final NumberFormatException e ) {
- throw new IllegalArgumentException( "failed to parse number from [" + n.getName() + "]: "
- + e.getLocalizedMessage() );
- }
- if ( value >= 0.0 ) {
- n.getBranchData().addConfidence( new Confidence( value, "bootstrap" ) );
- n.setName( "" );
- }
+ final String curent_name = it.next().getName();
+ if ( Arrays.binarySearch( node_names_to_keep, curent_name ) < 0 ) {
+ to_delete[ i++ ] = curent_name;
+ }
+ }
+ PhylogenyMethods.deleteExternalNodesNegativeSelection( to_delete, p );
+ final List<String> deleted = new ArrayList<String>();
+ for( final String n : to_delete ) {
+ if ( !ForesterUtil.isEmpty( n ) ) {
+ deleted.add( n );
}
}
+ return deleted;
}
- final static public void sortNodeDescendents( final PhylogenyNode node, final DESCENDANT_SORT_PRIORITY pri ) {
- class PhylogenyNodeSortTaxonomyPriority implements Comparator<PhylogenyNode> {
-
- @Override
- public int compare( final PhylogenyNode n1, final PhylogenyNode n2 ) {
- if ( n1.getNodeData().isHasTaxonomy() && n2.getNodeData().isHasTaxonomy() ) {
- if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getScientificName() ) )
- && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getScientificName() ) ) ) {
- return n1.getNodeData().getTaxonomy().getScientificName().toLowerCase()
- .compareTo( n2.getNodeData().getTaxonomy().getScientificName().toLowerCase() );
- }
- if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getTaxonomyCode() ) )
- && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getTaxonomyCode() ) ) ) {
- return n1.getNodeData().getTaxonomy().getTaxonomyCode()
- .compareTo( n2.getNodeData().getTaxonomy().getTaxonomyCode() );
- }
- if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getCommonName() ) )
- && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getCommonName() ) ) ) {
- return n1.getNodeData().getTaxonomy().getCommonName().toLowerCase()
- .compareTo( n2.getNodeData().getTaxonomy().getCommonName().toLowerCase() );
- }
- }
- if ( n1.getNodeData().isHasSequence() && n2.getNodeData().isHasSequence() ) {
- if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getName() ) )
- && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getName() ) ) ) {
- return n1.getNodeData().getSequence().getName().toLowerCase()
- .compareTo( n2.getNodeData().getSequence().getName().toLowerCase() );
- }
- if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getSymbol() ) )
- && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getSymbol() ) ) ) {
- return n1.getNodeData().getSequence().getSymbol()
- .compareTo( n2.getNodeData().getSequence().getSymbol() );
- }
- if ( ( n1.getNodeData().getSequence().getAccession() != null )
- && ( n2.getNodeData().getSequence().getAccession() != null )
- && !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getAccession().getValue() )
- && !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getAccession().getValue() ) ) {
- return n1.getNodeData().getSequence().getAccession().getValue()
- .compareTo( n2.getNodeData().getSequence().getAccession().getValue() );
- }
- }
- if ( ( !ForesterUtil.isEmpty( n1.getName() ) ) && ( !ForesterUtil.isEmpty( n2.getName() ) ) ) {
- return n1.getName().toLowerCase().compareTo( n2.getName().toLowerCase() );
- }
- return 0;
- }
- }
- class PhylogenyNodeSortSequencePriority implements Comparator<PhylogenyNode> {
-
- @Override
- public int compare( final PhylogenyNode n1, final PhylogenyNode n2 ) {
- if ( n1.getNodeData().isHasSequence() && n2.getNodeData().isHasSequence() ) {
- if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getName() ) )
- && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getName() ) ) ) {
- return n1.getNodeData().getSequence().getName().toLowerCase()
- .compareTo( n2.getNodeData().getSequence().getName().toLowerCase() );
- }
- if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getSymbol() ) )
- && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getSymbol() ) ) ) {
- return n1.getNodeData().getSequence().getSymbol()
- .compareTo( n2.getNodeData().getSequence().getSymbol() );
- }
- if ( ( n1.getNodeData().getSequence().getAccession() != null )
- && ( n2.getNodeData().getSequence().getAccession() != null )
- && !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getAccession().getValue() )
- && !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getAccession().getValue() ) ) {
- return n1.getNodeData().getSequence().getAccession().getValue()
- .compareTo( n2.getNodeData().getSequence().getAccession().getValue() );
- }
- }
- if ( n1.getNodeData().isHasTaxonomy() && n2.getNodeData().isHasTaxonomy() ) {
- if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getScientificName() ) )
- && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getScientificName() ) ) ) {
- return n1.getNodeData().getTaxonomy().getScientificName().toLowerCase()
- .compareTo( n2.getNodeData().getTaxonomy().getScientificName().toLowerCase() );
- }
- if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getTaxonomyCode() ) )
- && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getTaxonomyCode() ) ) ) {
- return n1.getNodeData().getTaxonomy().getTaxonomyCode()
- .compareTo( n2.getNodeData().getTaxonomy().getTaxonomyCode() );
- }
- if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getCommonName() ) )
- && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getCommonName() ) ) ) {
- return n1.getNodeData().getTaxonomy().getCommonName().toLowerCase()
- .compareTo( n2.getNodeData().getTaxonomy().getCommonName().toLowerCase() );
- }
- }
- if ( ( !ForesterUtil.isEmpty( n1.getName() ) ) && ( !ForesterUtil.isEmpty( n2.getName() ) ) ) {
- return n1.getName().toLowerCase().compareTo( n2.getName().toLowerCase() );
- }
- return 0;
- }
- }
- class PhylogenyNodeSortNodeNamePriority implements Comparator<PhylogenyNode> {
-
- @Override
- public int compare( final PhylogenyNode n1, final PhylogenyNode n2 ) {
- if ( ( !ForesterUtil.isEmpty( n1.getName() ) ) && ( !ForesterUtil.isEmpty( n2.getName() ) ) ) {
- return n1.getName().toLowerCase().compareTo( n2.getName().toLowerCase() );
- }
- if ( n1.getNodeData().isHasTaxonomy() && n2.getNodeData().isHasTaxonomy() ) {
- if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getScientificName() ) )
- && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getScientificName() ) ) ) {
- return n1.getNodeData().getTaxonomy().getScientificName().toLowerCase()
- .compareTo( n2.getNodeData().getTaxonomy().getScientificName().toLowerCase() );
- }
- if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getTaxonomyCode() ) )
- && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getTaxonomyCode() ) ) ) {
- return n1.getNodeData().getTaxonomy().getTaxonomyCode()
- .compareTo( n2.getNodeData().getTaxonomy().getTaxonomyCode() );
- }
- if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getCommonName() ) )
- && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getCommonName() ) ) ) {
- return n1.getNodeData().getTaxonomy().getCommonName().toLowerCase()
- .compareTo( n2.getNodeData().getTaxonomy().getCommonName().toLowerCase() );
- }
- }
- if ( n1.getNodeData().isHasSequence() && n2.getNodeData().isHasSequence() ) {
- if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getName() ) )
- && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getName() ) ) ) {
- return n1.getNodeData().getSequence().getName().toLowerCase()
- .compareTo( n2.getNodeData().getSequence().getName().toLowerCase() );
- }
- if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getSymbol() ) )
- && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getSymbol() ) ) ) {
- return n1.getNodeData().getSequence().getSymbol()
- .compareTo( n2.getNodeData().getSequence().getSymbol() );
- }
- if ( ( n1.getNodeData().getSequence().getAccession() != null )
- && ( n2.getNodeData().getSequence().getAccession() != null )
- && !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getAccession().getValue() )
- && !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getAccession().getValue() ) ) {
- return n1.getNodeData().getSequence().getAccession().getValue()
- .compareTo( n2.getNodeData().getSequence().getAccession().getValue() );
- }
- }
- return 0;
- }
- }
- Comparator<PhylogenyNode> c;
- switch ( pri ) {
- case SEQUENCE:
- c = new PhylogenyNodeSortSequencePriority();
- break;
- case NODE_NAME:
- c = new PhylogenyNodeSortNodeNamePriority();
- break;
- default:
- c = new PhylogenyNodeSortTaxonomyPriority();
- }
- final List<PhylogenyNode> descs = node.getDescendants();
- Collections.sort( descs, c );
- int i = 0;
- for( final PhylogenyNode desc : descs ) {
- node.setChildNode( i++, desc );
- }
- }
-
- final static public void transferNodeNameToField( final Phylogeny phy,
- final PhylogenyMethods.PhylogenyNodeField field,
- final boolean external_only ) throws PhyloXmlDataFormatException {
- final PhylogenyNodeIterator it = phy.iteratorPostorder();
- while ( it.hasNext() ) {
- final PhylogenyNode n = it.next();
- if ( external_only && n.isInternal() ) {
- continue;
- }
- final String name = n.getName().trim();
- if ( !ForesterUtil.isEmpty( name ) ) {
- switch ( field ) {
- case TAXONOMY_CODE:
- n.setName( "" );
- setTaxonomyCode( n, name );
- break;
- case TAXONOMY_SCIENTIFIC_NAME:
- n.setName( "" );
- if ( !n.getNodeData().isHasTaxonomy() ) {
- n.getNodeData().setTaxonomy( new Taxonomy() );
- }
- n.getNodeData().getTaxonomy().setScientificName( name );
- break;
- case TAXONOMY_COMMON_NAME:
- n.setName( "" );
- if ( !n.getNodeData().isHasTaxonomy() ) {
- n.getNodeData().setTaxonomy( new Taxonomy() );
- }
- n.getNodeData().getTaxonomy().setCommonName( name );
- break;
- case SEQUENCE_SYMBOL:
- n.setName( "" );
- if ( !n.getNodeData().isHasSequence() ) {
- n.getNodeData().setSequence( new Sequence() );
- }
- n.getNodeData().getSequence().setSymbol( name );
- break;
- case SEQUENCE_NAME:
- n.setName( "" );
- if ( !n.getNodeData().isHasSequence() ) {
- n.getNodeData().setSequence( new Sequence() );
- }
- n.getNodeData().getSequence().setName( name );
- break;
- case TAXONOMY_ID_UNIPROT_1: {
- if ( !n.getNodeData().isHasTaxonomy() ) {
- n.getNodeData().setTaxonomy( new Taxonomy() );
- }
- String id = name;
- final int i = name.indexOf( '_' );
- if ( i > 0 ) {
- id = name.substring( 0, i );
- }
- else {
- n.setName( "" );
- }
- n.getNodeData().getTaxonomy()
- .setIdentifier( new Identifier( id, PhyloXmlUtil.UNIPROT_TAX_PROVIDER ) );
- break;
- }
- case TAXONOMY_ID_UNIPROT_2: {
- if ( !n.getNodeData().isHasTaxonomy() ) {
- n.getNodeData().setTaxonomy( new Taxonomy() );
- }
- String id = name;
- final int i = name.indexOf( '_' );
- if ( i > 0 ) {
- id = name.substring( i + 1, name.length() );
- }
- else {
- n.setName( "" );
- }
- n.getNodeData().getTaxonomy()
- .setIdentifier( new Identifier( id, PhyloXmlUtil.UNIPROT_TAX_PROVIDER ) );
- break;
- }
- case TAXONOMY_ID: {
- if ( !n.getNodeData().isHasTaxonomy() ) {
- n.getNodeData().setTaxonomy( new Taxonomy() );
- }
- n.getNodeData().getTaxonomy().setIdentifier( new Identifier( name ) );
- break;
- }
- }
- }
- }
- }
-
- static double addPhylogenyDistances( final double a, final double b ) {
- if ( ( a >= 0.0 ) && ( b >= 0.0 ) ) {
- return a + b;
- }
- else if ( a >= 0.0 ) {
- return a;
- }
- else if ( b >= 0.0 ) {
- return b;
- }
- return PhylogenyDataUtil.BRANCH_LENGTH_DEFAULT;
- }
-
- public final static boolean isAllDecendentsAreDuplications( final PhylogenyNode n ) {
- if ( n.isExternal() ) {
- return true;
- }
- else {
- if ( n.isDuplication() ) {
- for( final PhylogenyNode desc : n.getDescendants() ) {
- if ( !isAllDecendentsAreDuplications( desc ) ) {
- return false;
- }
- }
- return true;
- }
- else {
- return false;
- }
- }
- }
-
- public static short calculateMaxBranchesToLeaf( final PhylogenyNode node ) {
- if ( node.isExternal() ) {
- return 0;
- }
- short max = 0;
- for( PhylogenyNode d : node.getAllExternalDescendants() ) {
- short steps = 0;
- while ( d != node ) {
- if ( d.isCollapse() ) {
- steps = 0;
- }
- else {
- steps++;
- }
- d = d.getParent();
- }
- if ( max < steps ) {
- max = steps;
- }
- }
- return max;
- }
-
- public static int calculateMaxDepth( final Phylogeny phy ) {
- int max = 0;
- for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) {
- final PhylogenyNode node = iter.next();
- final int steps = node.calculateDepth();
- if ( steps > max ) {
- max = steps;
- }
- }
- return max;
- }
-
- public static double calculateMaxDistanceToRoot( final Phylogeny phy ) {
- double max = 0.0;
- for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) {
- final PhylogenyNode node = iter.next();
- final double d = node.calculateDistanceToRoot();
- if ( d > max ) {
- max = d;
- }
- }
- return max;
- }
-
- public static int countNumberOfPolytomies( final Phylogeny phy ) {
- int count = 0;
- for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
- final PhylogenyNode n = iter.next();
- if ( !n.isExternal() && ( n.getNumberOfDescendants() > 2 ) ) {
- count++;
- }
- }
- return count;
- }
-
- public static DescriptiveStatistics calculatNumberOfDescendantsPerNodeStatistics( final Phylogeny phy ) {
- final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
- for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
- final PhylogenyNode n = iter.next();
- if ( !n.isExternal() ) {
- stats.addValue( n.getNumberOfDescendants() );
- }
- }
- return stats;
- }
-
- public static DescriptiveStatistics calculatBranchLengthStatistics( final Phylogeny phy ) {
- final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
- for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
- final PhylogenyNode n = iter.next();
- if ( !n.isRoot() && ( n.getDistanceToParent() >= 0.0 ) ) {
- stats.addValue( n.getDistanceToParent() );
- }
- }
- return stats;
- }
-
- public static List<DescriptiveStatistics> calculatConfidenceStatistics( final Phylogeny phy ) {
- final List<DescriptiveStatistics> stats = new ArrayList<DescriptiveStatistics>();
- for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
- final PhylogenyNode n = iter.next();
- if ( !n.isExternal() && !n.isRoot() ) {
- if ( n.getBranchData().isHasConfidences() ) {
- for( int i = 0; i < n.getBranchData().getConfidences().size(); ++i ) {
- final Confidence c = n.getBranchData().getConfidences().get( i );
- if ( ( i > ( stats.size() - 1 ) ) || ( stats.get( i ) == null ) ) {
- stats.add( i, new BasicDescriptiveStatistics() );
- }
- if ( !ForesterUtil.isEmpty( c.getType() ) ) {
- if ( !ForesterUtil.isEmpty( stats.get( i ).getDescription() ) ) {
- if ( !stats.get( i ).getDescription().equalsIgnoreCase( c.getType() ) ) {
- throw new IllegalArgumentException( "support values in node [" + n.toString()
- + "] appear inconsistently ordered" );
- }
- }
- stats.get( i ).setDescription( c.getType() );
- }
- stats.get( i ).addValue( ( ( c != null ) && ( c.getValue() >= 0 ) ) ? c.getValue() : 0 );
- }
- }
- }
- }
- return stats;
- }
-
- /**
- * Returns the set of distinct taxonomies of
- * all external nodes of node.
- * If at least one the external nodes has no taxonomy,
- * null is returned.
- *
- */
- public static Set<Taxonomy> obtainDistinctTaxonomies( final PhylogenyNode node ) {
- final List<PhylogenyNode> descs = node.getAllExternalDescendants();
- final Set<Taxonomy> tax_set = new HashSet<Taxonomy>();
- for( final PhylogenyNode n : descs ) {
- if ( !n.getNodeData().isHasTaxonomy() || n.getNodeData().getTaxonomy().isEmpty() ) {
- return null;
- }
- tax_set.add( n.getNodeData().getTaxonomy() );
- }
- return tax_set;
- }
-
- /**
- * Returns a map of distinct taxonomies of
- * all external nodes of node.
- * If at least one of the external nodes has no taxonomy,
- * null is returned.
- *
- */
- public static SortedMap<Taxonomy, Integer> obtainDistinctTaxonomyCounts( final PhylogenyNode node ) {
- final List<PhylogenyNode> descs = node.getAllExternalDescendants();
- final SortedMap<Taxonomy, Integer> tax_map = new TreeMap<Taxonomy, Integer>();
- for( final PhylogenyNode n : descs ) {
- if ( !n.getNodeData().isHasTaxonomy() || n.getNodeData().getTaxonomy().isEmpty() ) {
- return null;
- }
- final Taxonomy t = n.getNodeData().getTaxonomy();
- if ( tax_map.containsKey( t ) ) {
- tax_map.put( t, tax_map.get( t ) + 1 );
- }
- else {
- tax_map.put( t, 1 );
- }
- }
- return tax_map;
- }
-
- public static int calculateNumberOfExternalNodesWithoutTaxonomy( final PhylogenyNode node ) {
- final List<PhylogenyNode> descs = node.getAllExternalDescendants();
- int x = 0;
- for( final PhylogenyNode n : descs ) {
- if ( !n.getNodeData().isHasTaxonomy() || n.getNodeData().getTaxonomy().isEmpty() ) {
- x++;
- }
- }
- return x;
- }
-
- /**
- * Deep copies the phylogeny originating from this node.
- */
- static PhylogenyNode copySubTree( final PhylogenyNode source ) {
- if ( source == null ) {
- return null;
- }
- else {
- final PhylogenyNode newnode = source.copyNodeData();
- if ( !source.isExternal() ) {
- for( int i = 0; i < source.getNumberOfDescendants(); ++i ) {
- newnode.setChildNode( i, PhylogenyMethods.copySubTree( source.getChildNode( i ) ) );
- }
- }
- return newnode;
- }
- }
-
- /**
- * Shallow copies the phylogeny originating from this node.
- */
- static PhylogenyNode copySubTreeShallow( final PhylogenyNode source ) {
- if ( source == null ) {
- return null;
- }
- else {
- final PhylogenyNode newnode = source.copyNodeDataShallow();
- if ( !source.isExternal() ) {
- for( int i = 0; i < source.getNumberOfDescendants(); ++i ) {
- newnode.setChildNode( i, PhylogenyMethods.copySubTreeShallow( source.getChildNode( i ) ) );
- }
- }
- return newnode;
- }
- }
-
- public static void deleteExternalNodesNegativeSelection( final Set<Integer> to_delete, final Phylogeny phy ) {
- phy.clearHashIdToNodeMap();
- for( final Integer id : to_delete ) {
- phy.deleteSubtree( phy.getNode( id ), true );
- }
- phy.clearHashIdToNodeMap();
- phy.externalNodesHaveChanged();
- }
-
- public static void deleteExternalNodesNegativeSelection( final String[] node_names_to_delete, final Phylogeny p )
- throws IllegalArgumentException {
- for( final String element : node_names_to_delete ) {
- if ( ForesterUtil.isEmpty( element ) ) {
- continue;
- }
- List<PhylogenyNode> nodes = null;
- nodes = p.getNodes( element );
- final Iterator<PhylogenyNode> it = nodes.iterator();
- while ( it.hasNext() ) {
- final PhylogenyNode n = it.next();
- if ( !n.isExternal() ) {
- throw new IllegalArgumentException( "attempt to delete non-external node \"" + element + "\"" );
- }
- p.deleteSubtree( n, true );
- }
+ final public static void deleteNonOrthologousExternalNodes( final Phylogeny phy, final PhylogenyNode n ) {
+ if ( n.isInternal() ) {
+ throw new IllegalArgumentException( "node is not external" );
}
- p.clearHashIdToNodeMap();
- p.externalNodesHaveChanged();
- }
-
- public static void deleteExternalNodesPositiveSelection( final Set<Taxonomy> species_to_keep, final Phylogeny phy ) {
- // final Set<Integer> to_delete = new HashSet<Integer>();
+ final ArrayList<PhylogenyNode> to_delete = new ArrayList<PhylogenyNode>();
for( final PhylogenyNodeIterator it = phy.iteratorExternalForward(); it.hasNext(); ) {
- final PhylogenyNode n = it.next();
- if ( n.getNodeData().isHasTaxonomy() ) {
- if ( !species_to_keep.contains( n.getNodeData().getTaxonomy() ) ) {
- //to_delete.add( n.getNodeId() );
- phy.deleteSubtree( n, true );
- }
- }
- else {
- throw new IllegalArgumentException( "node " + n.getId() + " has no taxonomic data" );
+ final PhylogenyNode i = it.next();
+ if ( !PhylogenyMethods.getEventAtLCA( n, i ).isSpeciation() ) {
+ to_delete.add( i );
}
}
+ for( final PhylogenyNode d : to_delete ) {
+ phy.deleteSubtree( d, true );
+ }
phy.clearHashIdToNodeMap();
phy.externalNodesHaveChanged();
}
- public static List<String> deleteExternalNodesPositiveSelection( final String[] node_names_to_keep,
- final Phylogeny p ) {
- final PhylogenyNodeIterator it = p.iteratorExternalForward();
- final String[] to_delete = new String[ p.getNumberOfExternalNodes() ];
- int i = 0;
- Arrays.sort( node_names_to_keep );
- while ( it.hasNext() ) {
- final String curent_name = it.next().getName();
- if ( Arrays.binarySearch( node_names_to_keep, curent_name ) < 0 ) {
- to_delete[ i++ ] = curent_name;
- }
- }
- PhylogenyMethods.deleteExternalNodesNegativeSelection( to_delete, p );
- final List<String> deleted = new ArrayList<String>();
- for( final String n : to_delete ) {
- if ( !ForesterUtil.isEmpty( n ) ) {
- deleted.add( n );
- }
- }
- return deleted;
- }
-
public static List<PhylogenyNode> getAllDescendants( final PhylogenyNode node ) {
final List<PhylogenyNode> descs = new ArrayList<PhylogenyNode>();
final Set<Integer> encountered = new HashSet<Integer>();
return values;
}
- /**
- * Calculates the distance between PhylogenyNodes n1 and n2.
- * PRECONDITION: n1 is a descendant of n2.
- *
- * @param n1
- * a descendant of n2
- * @param n2
- * @return distance between n1 and n2
- */
- private static double getDistance( PhylogenyNode n1, final PhylogenyNode n2 ) {
- double d = 0.0;
- while ( n1 != n2 ) {
- if ( n1.getDistanceToParent() > 0.0 ) {
- d += n1.getDistanceToParent();
- }
- n1 = n1.getParent();
- }
- return d;
+ final public static Event getEventAtLCA( final PhylogenyNode n1, final PhylogenyNode n2 ) {
+ return calculateLCA( n1, n2 ).getNodeData().getEvent();
}
/**
}
/**
- * Returns all Nodes which are connected to external PhylogenyNode n of this
- * Phylogeny by a path containing only speciation events. We call these
- * "super orthologs". Nodes are returned as Vector of references to Nodes.
- * <p>
- * PRECONDITION: This tree must be binary and rooted, and speciation -
- * duplication need to be assigned for each of its internal Nodes.
- * <p>
- * Returns null if this Phylogeny is empty or if n is internal.
- * @param n
- * external PhylogenyNode whose strictly speciation related Nodes
- * are to be returned
- * @return References to all strictly speciation related Nodes of
- * PhylogenyNode n of this Phylogeny, null if this Phylogeny is
- * empty or if n is internal
- */
- public static List<PhylogenyNode> getSuperOrthologousNodes( final PhylogenyNode n ) {
- // FIXME
- PhylogenyNode node = n;
- PhylogenyNode deepest = null;
- final List<PhylogenyNode> v = new ArrayList<PhylogenyNode>();
- if ( !node.isExternal() ) {
- return null;
- }
- while ( !node.isRoot() && !node.getParent().isDuplication() ) {
- node = node.getParent();
- }
- deepest = node;
- deepest.setIndicatorsToZero();
- do {
- if ( !node.isExternal() ) {
- if ( node.getIndicator() == 0 ) {
- node.setIndicator( ( byte ) 1 );
- if ( !node.isDuplication() ) {
- node = node.getChildNode1();
- }
- }
- if ( node.getIndicator() == 1 ) {
- node.setIndicator( ( byte ) 2 );
- if ( !node.isDuplication() ) {
- node = node.getChildNode2();
- }
- }
- if ( ( node != deepest ) && ( node.getIndicator() == 2 ) ) {
- node = node.getParent();
- }
- }
- else {
- if ( node != n ) {
- v.add( node );
- }
- if ( node != deepest ) {
- node = node.getParent();
- }
- else {
- node.setIndicator( ( byte ) 2 );
- }
- }
- } while ( ( node != deepest ) || ( deepest.getIndicator() != 2 ) );
- return v;
- }
-
- /**
* Convenience method for display purposes.
* Not intended for algorithms.
*/
return node.getNodeData().getTaxonomy().getIdentifier().getValue();
}
- /**
- * Returns all Nodes which are connected to external PhylogenyNode n of this
- * Phylogeny by a path containing, and leading to, only duplication events.
- * We call these "ultra paralogs". Nodes are returned as Vector of
- * references to Nodes.
- * <p>
- * PRECONDITION: This tree must be binary and rooted, and speciation -
- * duplication need to be assigned for each of its internal Nodes.
- * <p>
- * Returns null if this Phylogeny is empty or if n is internal.
- * <p>
- * (Last modified: 10/06/01)
- *
- * @param n
- * external PhylogenyNode whose ultra paralogs are to be returned
- * @return Vector of references to all ultra paralogs of PhylogenyNode n of
- * this Phylogeny, null if this Phylogeny is empty or if n is
- * internal
- */
- public static List<PhylogenyNode> getUltraParalogousNodes( final PhylogenyNode n ) {
- // FIXME test me
- PhylogenyNode node = n;
- if ( !node.isExternal() ) {
- throw new IllegalArgumentException( "attempt to get ultra-paralogous nodes of internal node" );
+ public final static boolean isAllDecendentsAreDuplications( final PhylogenyNode n ) {
+ if ( n.isExternal() ) {
+ return true;
}
- while ( !node.isRoot() && node.getParent().isDuplication() && isAllDecendentsAreDuplications( node.getParent() ) ) {
- node = node.getParent();
+ else {
+ if ( n.isDuplication() ) {
+ for( final PhylogenyNode desc : n.getDescendants() ) {
+ if ( !isAllDecendentsAreDuplications( desc ) ) {
+ return false;
+ }
+ }
+ return true;
+ }
+ else {
+ return false;
+ }
}
- final List<PhylogenyNode> nodes = node.getAllExternalDescendants();
- nodes.remove( n );
- return nodes;
}
public static boolean isHasExternalDescendant( final PhylogenyNode node ) {
}
}
- private static boolean match( final String s,
- final String query,
- final boolean case_sensitive,
- final boolean partial ) {
- if ( ForesterUtil.isEmpty( s ) || ForesterUtil.isEmpty( query ) ) {
- return false;
- }
- String my_s = s.trim();
- String my_query = query.trim();
- if ( !case_sensitive ) {
- my_s = my_s.toLowerCase();
- my_query = my_query.toLowerCase();
- }
- if ( partial ) {
- return my_s.indexOf( my_query ) >= 0;
- }
- else {
- return my_s.equals( my_query );
- }
- }
-
public static void midpointRoot( final Phylogeny phylogeny ) {
if ( phylogeny.getNumberOfExternalNodes() < 2 ) {
return;
}
}
- public static void normalizeBootstrapValues( final Phylogeny phylogeny,
- final double max_bootstrap_value,
- final double max_normalized_value ) {
- for( final PhylogenyNodeIterator iter = phylogeny.iteratorPreorder(); iter.hasNext(); ) {
- final PhylogenyNode node = iter.next();
- if ( node.isInternal() ) {
- final double confidence = getConfidenceValue( node );
- if ( confidence != Confidence.CONFIDENCE_DEFAULT_VALUE ) {
- if ( confidence >= max_bootstrap_value ) {
- setBootstrapConfidence( node, max_normalized_value );
- }
- else {
- setBootstrapConfidence( node, ( confidence * max_normalized_value ) / max_bootstrap_value );
+ public static void normalizeBootstrapValues( final Phylogeny phylogeny,
+ final double max_bootstrap_value,
+ final double max_normalized_value ) {
+ for( final PhylogenyNodeIterator iter = phylogeny.iteratorPreorder(); iter.hasNext(); ) {
+ final PhylogenyNode node = iter.next();
+ if ( node.isInternal() ) {
+ final double confidence = getConfidenceValue( node );
+ if ( confidence != Confidence.CONFIDENCE_DEFAULT_VALUE ) {
+ if ( confidence >= max_bootstrap_value ) {
+ setBootstrapConfidence( node, max_normalized_value );
+ }
+ else {
+ setBootstrapConfidence( node, ( confidence * max_normalized_value ) / max_bootstrap_value );
+ }
+ }
+ }
+ }
+ }
+
+ public static List<PhylogenyNode> obtainAllNodesAsList( final Phylogeny phy ) {
+ final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
+ if ( phy.isEmpty() ) {
+ return nodes;
+ }
+ for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
+ nodes.add( iter.next() );
+ }
+ return nodes;
+ }
+
+ /**
+ * Returns the set of distinct taxonomies of
+ * all external nodes of node.
+ * If at least one the external nodes has no taxonomy,
+ * null is returned.
+ *
+ */
+ public static Set<Taxonomy> obtainDistinctTaxonomies( final PhylogenyNode node ) {
+ final List<PhylogenyNode> descs = node.getAllExternalDescendants();
+ final Set<Taxonomy> tax_set = new HashSet<Taxonomy>();
+ for( final PhylogenyNode n : descs ) {
+ if ( !n.getNodeData().isHasTaxonomy() || n.getNodeData().getTaxonomy().isEmpty() ) {
+ return null;
+ }
+ tax_set.add( n.getNodeData().getTaxonomy() );
+ }
+ return tax_set;
+ }
+
+ /**
+ * Returns a map of distinct taxonomies of
+ * all external nodes of node.
+ * If at least one of the external nodes has no taxonomy,
+ * null is returned.
+ *
+ */
+ public static SortedMap<Taxonomy, Integer> obtainDistinctTaxonomyCounts( final PhylogenyNode node ) {
+ final List<PhylogenyNode> descs = node.getAllExternalDescendants();
+ final SortedMap<Taxonomy, Integer> tax_map = new TreeMap<Taxonomy, Integer>();
+ for( final PhylogenyNode n : descs ) {
+ if ( !n.getNodeData().isHasTaxonomy() || n.getNodeData().getTaxonomy().isEmpty() ) {
+ return null;
+ }
+ final Taxonomy t = n.getNodeData().getTaxonomy();
+ if ( tax_map.containsKey( t ) ) {
+ tax_map.put( t, tax_map.get( t ) + 1 );
+ }
+ else {
+ tax_map.put( t, 1 );
+ }
+ }
+ return tax_map;
+ }
+
+ /**
+ * Arranges the order of childern for each node of this Phylogeny in such a
+ * way that either the branch with more children is on top (right) or on
+ * bottom (left), dependent on the value of boolean order.
+ *
+ * @param order
+ * decides in which direction to order
+ * @param pri
+ */
+ public static void orderAppearance( final PhylogenyNode n,
+ final boolean order,
+ final boolean order_ext_alphabetically,
+ final DESCENDANT_SORT_PRIORITY pri ) {
+ if ( n.isExternal() ) {
+ return;
+ }
+ else {
+ PhylogenyNode temp = null;
+ if ( ( n.getNumberOfDescendants() == 2 )
+ && ( n.getChildNode1().getNumberOfExternalNodes() != n.getChildNode2().getNumberOfExternalNodes() )
+ && ( ( n.getChildNode1().getNumberOfExternalNodes() < n.getChildNode2().getNumberOfExternalNodes() ) == order ) ) {
+ temp = n.getChildNode1();
+ n.setChild1( n.getChildNode2() );
+ n.setChild2( temp );
+ }
+ else if ( order_ext_alphabetically ) {
+ boolean all_ext = true;
+ for( final PhylogenyNode i : n.getDescendants() ) {
+ if ( !i.isExternal() ) {
+ all_ext = false;
+ break;
}
}
+ if ( all_ext ) {
+ PhylogenyMethods.sortNodeDescendents( n, pri );
+ }
+ }
+ for( int i = 0; i < n.getNumberOfDescendants(); ++i ) {
+ orderAppearance( n.getChildNode( i ), order, order_ext_alphabetically, pri );
}
}
}
- public static List<PhylogenyNode> obtainAllNodesAsList( final Phylogeny phy ) {
- final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
- if ( phy.isEmpty() ) {
- return nodes;
- }
- for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
- nodes.add( iter.next() );
- }
- return nodes;
- }
-
public static void postorderBranchColorAveragingExternalNodeBased( final Phylogeny p ) {
for( final PhylogenyNodeIterator iter = p.iteratorPostorder(); iter.hasNext(); ) {
final PhylogenyNode node = iter.next();
}
}
+ public static final void preOrderReId( final Phylogeny phy ) {
+ if ( phy.isEmpty() ) {
+ return;
+ }
+ phy.setIdToNodeMap( null );
+ int i = PhylogenyNode.getNodeCount();
+ for( final PhylogenyNodeIterator it = phy.iteratorPreorder(); it.hasNext(); ) {
+ it.next().setId( i++ );
+ }
+ PhylogenyNode.setNodeCount( i );
+ }
+
+ public final static Phylogeny[] readPhylogenies( final PhylogenyParser parser, final File file ) throws IOException {
+ final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
+ final Phylogeny[] trees = factory.create( file, parser );
+ if ( ( trees == null ) || ( trees.length == 0 ) ) {
+ throw new PhylogenyParserException( "Unable to parse phylogeny from file: " + file );
+ }
+ return trees;
+ }
+
+ public final static Phylogeny[] readPhylogenies( final PhylogenyParser parser, final List<File> files )
+ throws IOException {
+ final List<Phylogeny> tree_list = new ArrayList<Phylogeny>();
+ for( final File file : files ) {
+ final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
+ final Phylogeny[] trees = factory.create( file, parser );
+ if ( ( trees == null ) || ( trees.length == 0 ) ) {
+ throw new PhylogenyParserException( "Unable to parse phylogeny from file: " + file );
+ }
+ tree_list.addAll( Arrays.asList( trees ) );
+ }
+ return tree_list.toArray( new Phylogeny[ tree_list.size() ] );
+ }
+
public static void removeNode( final PhylogenyNode remove_me, final Phylogeny phylogeny ) {
if ( remove_me.isRoot() ) {
throw new IllegalArgumentException( "ill advised attempt to remove root node" );
if ( !node.getNodeData().isHasTaxonomy() ) {
node.getNodeData().setTaxonomy( new Taxonomy() );
}
- node.getNodeData().getTaxonomy().setTaxonomyCode( taxonomy_code );
+ node.getNodeData().getTaxonomy().setTaxonomyCode( taxonomy_code );
+ }
+
+ final static public void sortNodeDescendents( final PhylogenyNode node, final DESCENDANT_SORT_PRIORITY pri ) {
+ class PhylogenyNodeSortTaxonomyPriority implements Comparator<PhylogenyNode> {
+
+ @Override
+ public int compare( final PhylogenyNode n1, final PhylogenyNode n2 ) {
+ if ( n1.getNodeData().isHasTaxonomy() && n2.getNodeData().isHasTaxonomy() ) {
+ if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getScientificName() ) )
+ && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getScientificName() ) ) ) {
+ return n1.getNodeData().getTaxonomy().getScientificName().toLowerCase()
+ .compareTo( n2.getNodeData().getTaxonomy().getScientificName().toLowerCase() );
+ }
+ if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getTaxonomyCode() ) )
+ && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getTaxonomyCode() ) ) ) {
+ return n1.getNodeData().getTaxonomy().getTaxonomyCode()
+ .compareTo( n2.getNodeData().getTaxonomy().getTaxonomyCode() );
+ }
+ if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getCommonName() ) )
+ && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getCommonName() ) ) ) {
+ return n1.getNodeData().getTaxonomy().getCommonName().toLowerCase()
+ .compareTo( n2.getNodeData().getTaxonomy().getCommonName().toLowerCase() );
+ }
+ }
+ if ( n1.getNodeData().isHasSequence() && n2.getNodeData().isHasSequence() ) {
+ if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getName() ) )
+ && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getName() ) ) ) {
+ return n1.getNodeData().getSequence().getName().toLowerCase()
+ .compareTo( n2.getNodeData().getSequence().getName().toLowerCase() );
+ }
+ if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getSymbol() ) )
+ && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getSymbol() ) ) ) {
+ return n1.getNodeData().getSequence().getSymbol()
+ .compareTo( n2.getNodeData().getSequence().getSymbol() );
+ }
+ if ( ( n1.getNodeData().getSequence().getAccession() != null )
+ && ( n2.getNodeData().getSequence().getAccession() != null )
+ && !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getAccession().getValue() )
+ && !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getAccession().getValue() ) ) {
+ return n1.getNodeData().getSequence().getAccession().getValue()
+ .compareTo( n2.getNodeData().getSequence().getAccession().getValue() );
+ }
+ }
+ if ( ( !ForesterUtil.isEmpty( n1.getName() ) ) && ( !ForesterUtil.isEmpty( n2.getName() ) ) ) {
+ return n1.getName().toLowerCase().compareTo( n2.getName().toLowerCase() );
+ }
+ return 0;
+ }
+ }
+ class PhylogenyNodeSortSequencePriority implements Comparator<PhylogenyNode> {
+
+ @Override
+ public int compare( final PhylogenyNode n1, final PhylogenyNode n2 ) {
+ if ( n1.getNodeData().isHasSequence() && n2.getNodeData().isHasSequence() ) {
+ if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getName() ) )
+ && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getName() ) ) ) {
+ return n1.getNodeData().getSequence().getName().toLowerCase()
+ .compareTo( n2.getNodeData().getSequence().getName().toLowerCase() );
+ }
+ if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getSymbol() ) )
+ && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getSymbol() ) ) ) {
+ return n1.getNodeData().getSequence().getSymbol()
+ .compareTo( n2.getNodeData().getSequence().getSymbol() );
+ }
+ if ( ( n1.getNodeData().getSequence().getAccession() != null )
+ && ( n2.getNodeData().getSequence().getAccession() != null )
+ && !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getAccession().getValue() )
+ && !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getAccession().getValue() ) ) {
+ return n1.getNodeData().getSequence().getAccession().getValue()
+ .compareTo( n2.getNodeData().getSequence().getAccession().getValue() );
+ }
+ }
+ if ( n1.getNodeData().isHasTaxonomy() && n2.getNodeData().isHasTaxonomy() ) {
+ if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getScientificName() ) )
+ && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getScientificName() ) ) ) {
+ return n1.getNodeData().getTaxonomy().getScientificName().toLowerCase()
+ .compareTo( n2.getNodeData().getTaxonomy().getScientificName().toLowerCase() );
+ }
+ if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getTaxonomyCode() ) )
+ && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getTaxonomyCode() ) ) ) {
+ return n1.getNodeData().getTaxonomy().getTaxonomyCode()
+ .compareTo( n2.getNodeData().getTaxonomy().getTaxonomyCode() );
+ }
+ if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getCommonName() ) )
+ && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getCommonName() ) ) ) {
+ return n1.getNodeData().getTaxonomy().getCommonName().toLowerCase()
+ .compareTo( n2.getNodeData().getTaxonomy().getCommonName().toLowerCase() );
+ }
+ }
+ if ( ( !ForesterUtil.isEmpty( n1.getName() ) ) && ( !ForesterUtil.isEmpty( n2.getName() ) ) ) {
+ return n1.getName().toLowerCase().compareTo( n2.getName().toLowerCase() );
+ }
+ return 0;
+ }
+ }
+ class PhylogenyNodeSortNodeNamePriority implements Comparator<PhylogenyNode> {
+
+ @Override
+ public int compare( final PhylogenyNode n1, final PhylogenyNode n2 ) {
+ if ( ( !ForesterUtil.isEmpty( n1.getName() ) ) && ( !ForesterUtil.isEmpty( n2.getName() ) ) ) {
+ return n1.getName().toLowerCase().compareTo( n2.getName().toLowerCase() );
+ }
+ if ( n1.getNodeData().isHasTaxonomy() && n2.getNodeData().isHasTaxonomy() ) {
+ if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getScientificName() ) )
+ && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getScientificName() ) ) ) {
+ return n1.getNodeData().getTaxonomy().getScientificName().toLowerCase()
+ .compareTo( n2.getNodeData().getTaxonomy().getScientificName().toLowerCase() );
+ }
+ if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getTaxonomyCode() ) )
+ && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getTaxonomyCode() ) ) ) {
+ return n1.getNodeData().getTaxonomy().getTaxonomyCode()
+ .compareTo( n2.getNodeData().getTaxonomy().getTaxonomyCode() );
+ }
+ if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getCommonName() ) )
+ && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getCommonName() ) ) ) {
+ return n1.getNodeData().getTaxonomy().getCommonName().toLowerCase()
+ .compareTo( n2.getNodeData().getTaxonomy().getCommonName().toLowerCase() );
+ }
+ }
+ if ( n1.getNodeData().isHasSequence() && n2.getNodeData().isHasSequence() ) {
+ if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getName() ) )
+ && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getName() ) ) ) {
+ return n1.getNodeData().getSequence().getName().toLowerCase()
+ .compareTo( n2.getNodeData().getSequence().getName().toLowerCase() );
+ }
+ if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getSymbol() ) )
+ && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getSymbol() ) ) ) {
+ return n1.getNodeData().getSequence().getSymbol()
+ .compareTo( n2.getNodeData().getSequence().getSymbol() );
+ }
+ if ( ( n1.getNodeData().getSequence().getAccession() != null )
+ && ( n2.getNodeData().getSequence().getAccession() != null )
+ && !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getAccession().getValue() )
+ && !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getAccession().getValue() ) ) {
+ return n1.getNodeData().getSequence().getAccession().getValue()
+ .compareTo( n2.getNodeData().getSequence().getAccession().getValue() );
+ }
+ }
+ return 0;
+ }
+ }
+ Comparator<PhylogenyNode> c;
+ switch ( pri ) {
+ case SEQUENCE:
+ c = new PhylogenyNodeSortSequencePriority();
+ break;
+ case NODE_NAME:
+ c = new PhylogenyNodeSortNodeNamePriority();
+ break;
+ default:
+ c = new PhylogenyNodeSortTaxonomyPriority();
+ }
+ final List<PhylogenyNode> descs = node.getDescendants();
+ Collections.sort( descs, c );
+ int i = 0;
+ for( final PhylogenyNode desc : descs ) {
+ node.setChildNode( i++, desc );
+ }
}
/**
return nodes_to_delete;
}
- /**
- * Arranges the order of childern for each node of this Phylogeny in such a
- * way that either the branch with more children is on top (right) or on
- * bottom (left), dependent on the value of boolean order.
- *
- * @param order
- * decides in which direction to order
- * @param pri
- */
- public static void orderAppearance( final PhylogenyNode n,
- final boolean order,
- final boolean order_ext_alphabetically,
- final DESCENDANT_SORT_PRIORITY pri ) {
- if ( n.isExternal() ) {
- return;
+ final static public void transferInternalNamesToBootstrapSupport( final Phylogeny phy ) {
+ final PhylogenyNodeIterator it = phy.iteratorPostorder();
+ while ( it.hasNext() ) {
+ final PhylogenyNode n = it.next();
+ if ( !n.isExternal() && !ForesterUtil.isEmpty( n.getName() ) ) {
+ double value = -1;
+ try {
+ value = Double.parseDouble( n.getName() );
+ }
+ catch ( final NumberFormatException e ) {
+ throw new IllegalArgumentException( "failed to parse number from [" + n.getName() + "]: "
+ + e.getLocalizedMessage() );
+ }
+ if ( value >= 0.0 ) {
+ n.getBranchData().addConfidence( new Confidence( value, "bootstrap" ) );
+ n.setName( "" );
+ }
+ }
}
- else {
- PhylogenyNode temp = null;
- if ( ( n.getNumberOfDescendants() == 2 )
- && ( n.getChildNode1().getNumberOfExternalNodes() != n.getChildNode2().getNumberOfExternalNodes() )
- && ( ( n.getChildNode1().getNumberOfExternalNodes() < n.getChildNode2().getNumberOfExternalNodes() ) == order ) ) {
- temp = n.getChildNode1();
- n.setChild1( n.getChildNode2() );
- n.setChild2( temp );
+ }
+
+ final static public void transferInternalNodeNamesToConfidence( final Phylogeny phy ) {
+ final PhylogenyNodeIterator it = phy.iteratorPostorder();
+ while ( it.hasNext() ) {
+ final PhylogenyNode n = it.next();
+ if ( !n.isExternal() && !n.getBranchData().isHasConfidences() ) {
+ if ( !ForesterUtil.isEmpty( n.getName() ) ) {
+ double d = -1.0;
+ try {
+ d = Double.parseDouble( n.getName() );
+ }
+ catch ( final Exception e ) {
+ d = -1.0;
+ }
+ if ( d >= 0.0 ) {
+ n.getBranchData().addConfidence( new Confidence( d, "" ) );
+ n.setName( "" );
+ }
+ }
}
- else if ( order_ext_alphabetically ) {
- boolean all_ext = true;
- for( final PhylogenyNode i : n.getDescendants() ) {
- if ( !i.isExternal() ) {
- all_ext = false;
+ }
+ }
+
+ final static public void transferNodeNameToField( final Phylogeny phy,
+ final PhylogenyNodeField field,
+ final boolean external_only ) throws PhyloXmlDataFormatException {
+ final PhylogenyNodeIterator it = phy.iteratorPostorder();
+ while ( it.hasNext() ) {
+ final PhylogenyNode n = it.next();
+ if ( external_only && n.isInternal() ) {
+ continue;
+ }
+ final String name = n.getName().trim();
+ if ( !ForesterUtil.isEmpty( name ) ) {
+ switch ( field ) {
+ case TAXONOMY_CODE:
+ n.setName( "" );
+ setTaxonomyCode( n, name );
+ break;
+ case TAXONOMY_SCIENTIFIC_NAME:
+ n.setName( "" );
+ if ( !n.getNodeData().isHasTaxonomy() ) {
+ n.getNodeData().setTaxonomy( new Taxonomy() );
+ }
+ n.getNodeData().getTaxonomy().setScientificName( name );
+ break;
+ case TAXONOMY_COMMON_NAME:
+ n.setName( "" );
+ if ( !n.getNodeData().isHasTaxonomy() ) {
+ n.getNodeData().setTaxonomy( new Taxonomy() );
+ }
+ n.getNodeData().getTaxonomy().setCommonName( name );
+ break;
+ case SEQUENCE_SYMBOL:
+ n.setName( "" );
+ if ( !n.getNodeData().isHasSequence() ) {
+ n.getNodeData().setSequence( new Sequence() );
+ }
+ n.getNodeData().getSequence().setSymbol( name );
+ break;
+ case SEQUENCE_NAME:
+ n.setName( "" );
+ if ( !n.getNodeData().isHasSequence() ) {
+ n.getNodeData().setSequence( new Sequence() );
+ }
+ n.getNodeData().getSequence().setName( name );
+ break;
+ case TAXONOMY_ID_UNIPROT_1: {
+ if ( !n.getNodeData().isHasTaxonomy() ) {
+ n.getNodeData().setTaxonomy( new Taxonomy() );
+ }
+ String id = name;
+ final int i = name.indexOf( '_' );
+ if ( i > 0 ) {
+ id = name.substring( 0, i );
+ }
+ else {
+ n.setName( "" );
+ }
+ n.getNodeData().getTaxonomy()
+ .setIdentifier( new Identifier( id, PhyloXmlUtil.UNIPROT_TAX_PROVIDER ) );
+ break;
+ }
+ case TAXONOMY_ID_UNIPROT_2: {
+ if ( !n.getNodeData().isHasTaxonomy() ) {
+ n.getNodeData().setTaxonomy( new Taxonomy() );
+ }
+ String id = name;
+ final int i = name.indexOf( '_' );
+ if ( i > 0 ) {
+ id = name.substring( i + 1, name.length() );
+ }
+ else {
+ n.setName( "" );
+ }
+ n.getNodeData().getTaxonomy()
+ .setIdentifier( new Identifier( id, PhyloXmlUtil.UNIPROT_TAX_PROVIDER ) );
+ break;
+ }
+ case TAXONOMY_ID: {
+ if ( !n.getNodeData().isHasTaxonomy() ) {
+ n.getNodeData().setTaxonomy( new Taxonomy() );
+ }
+ n.getNodeData().getTaxonomy().setIdentifier( new Identifier( name ) );
break;
}
}
- if ( all_ext ) {
- PhylogenyMethods.sortNodeDescendents( n, pri );
+ }
+ }
+ }
+
+ static double addPhylogenyDistances( final double a, final double b ) {
+ if ( ( a >= 0.0 ) && ( b >= 0.0 ) ) {
+ return a + b;
+ }
+ else if ( a >= 0.0 ) {
+ return a;
+ }
+ else if ( b >= 0.0 ) {
+ return b;
+ }
+ return PhylogenyDataUtil.BRANCH_LENGTH_DEFAULT;
+ }
+
+ /**
+ * Deep copies the phylogeny originating from this node.
+ */
+ static PhylogenyNode copySubTree( final PhylogenyNode source ) {
+ if ( source == null ) {
+ return null;
+ }
+ else {
+ final PhylogenyNode newnode = source.copyNodeData();
+ if ( !source.isExternal() ) {
+ for( int i = 0; i < source.getNumberOfDescendants(); ++i ) {
+ newnode.setChildNode( i, PhylogenyMethods.copySubTree( source.getChildNode( i ) ) );
}
}
- for( int i = 0; i < n.getNumberOfDescendants(); ++i ) {
- orderAppearance( n.getChildNode( i ), order, order_ext_alphabetically, pri );
+ return newnode;
+ }
+ }
+
+ /**
+ * Shallow copies the phylogeny originating from this node.
+ */
+ static PhylogenyNode copySubTreeShallow( final PhylogenyNode source ) {
+ if ( source == null ) {
+ return null;
+ }
+ else {
+ final PhylogenyNode newnode = source.copyNodeDataShallow();
+ if ( !source.isExternal() ) {
+ for( int i = 0; i < source.getNumberOfDescendants(); ++i ) {
+ newnode.setChildNode( i, PhylogenyMethods.copySubTreeShallow( source.getChildNode( i ) ) );
+ }
+ }
+ return newnode;
+ }
+ }
+
+ /**
+ * Calculates the distance between PhylogenyNodes n1 and n2.
+ * PRECONDITION: n1 is a descendant of n2.
+ *
+ * @param n1
+ * a descendant of n2
+ * @param n2
+ * @return distance between n1 and n2
+ */
+ private static double getDistance( PhylogenyNode n1, final PhylogenyNode n2 ) {
+ double d = 0.0;
+ while ( n1 != n2 ) {
+ if ( n1.getDistanceToParent() > 0.0 ) {
+ d += n1.getDistanceToParent();
}
+ n1 = n1.getParent();
+ }
+ return d;
+ }
+
+ private static boolean match( final String s,
+ final String query,
+ final boolean case_sensitive,
+ final boolean partial ) {
+ if ( ForesterUtil.isEmpty( s ) || ForesterUtil.isEmpty( query ) ) {
+ return false;
+ }
+ String my_s = s.trim();
+ String my_query = query.trim();
+ if ( !case_sensitive ) {
+ my_s = my_s.toLowerCase();
+ my_query = my_query.toLowerCase();
+ }
+ if ( partial ) {
+ return my_s.indexOf( my_query ) >= 0;
+ }
+ else {
+ return my_s.equals( my_query );
}
}
+ public static enum DESCENDANT_SORT_PRIORITY {
+ TAXONOMY, SEQUENCE, NODE_NAME;
+ }
+
public static enum PhylogenyNodeField {
CLADE_NAME,
TAXONOMY_CODE,
TAXONOMY_ID_UNIPROT_2,
TAXONOMY_ID;
}
-
- public static enum DESCENDANT_SORT_PRIORITY {
- TAXONOMY, SEQUENCE, NODE_NAME;
- }
}
git://source.jalview.org / jalview.git / commitdiff