package org.forester.phylogeny;
import java.awt.Color;
+import java.io.File;
+import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.HashSet;
import java.util.SortedMap;
import java.util.TreeMap;
+import org.forester.io.parsers.PhylogenyParser;
+import org.forester.io.parsers.phyloxml.PhyloXmlUtil;
+import org.forester.io.parsers.util.PhylogenyParserException;
import org.forester.phylogeny.data.BranchColor;
import org.forester.phylogeny.data.BranchWidth;
import org.forester.phylogeny.data.Confidence;
import org.forester.phylogeny.data.DomainArchitecture;
+import org.forester.phylogeny.data.Identifier;
+import org.forester.phylogeny.data.PhylogenyDataUtil;
+import org.forester.phylogeny.data.Sequence;
import org.forester.phylogeny.data.Taxonomy;
+import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
+import org.forester.phylogeny.factories.PhylogenyFactory;
import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
+import org.forester.util.BasicDescriptiveStatistics;
+import org.forester.util.DescriptiveStatistics;
import org.forester.util.FailedConditionCheckException;
import org.forester.util.ForesterUtil;
return !obtainLCA( node1, node2 ).isDuplication();
}
+ 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;
+ }
+
+ 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( "" );
+ }
+ }
+ }
+ }
+ }
+
+ 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( "" );
+ }
+ }
+ }
+ }
+
+ final static public void transferNodeNameToField( final Phylogeny phy,
+ final PhylogenyMethods.PhylogenyNodeField field ) {
+ final PhylogenyNodeIterator it = phy.iteratorPostorder();
+ while ( it.hasNext() ) {
+ final PhylogenyNode n = it.next();
+ final String name = n.getName().trim();
+ if ( !ForesterUtil.isEmpty( name ) ) {
+ switch ( field ) {
+ case TAXONOMY_CODE:
+ //temp hack
+ // if ( name.length() > 5 ) {
+ // n.setName( "" );
+ // if ( !n.getNodeData().isHasTaxonomy() ) {
+ // n.getNodeData().setTaxonomy( new Taxonomy() );
+ // }
+ // n.getNodeData().getTaxonomy().setScientificName( name );
+ // break;
+ // }
+ //
+ 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;
+ }
+ }
+ }
+ }
+ }
+
static double addPhylogenyDistances( final double a, final double b ) {
if ( ( a >= 0.0 ) && ( b >= 0.0 ) ) {
return a + b;
else if ( b >= 0.0 ) {
return b;
}
- return PhylogenyNode.DISTANCE_DEFAULT;
+ return PhylogenyDataUtil.BRANCH_LENGTH_DEFAULT;
}
// Helper for getUltraParalogousNodes( PhylogenyNode ).
return max;
}
- public static int calculateMaximumNumberOfDescendantsPerNode( final Phylogeny phy ) {
- int max = 0;
+ public static DescriptiveStatistics calculatNumberOfDescendantsPerNodeStatistics( final Phylogeny phy ) {
+ final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
- final PhylogenyNode node = iter.next();
- if ( node.getNumberOfDescendants() > max ) {
- max = node.getNumberOfDescendants();
+ final PhylogenyNode n = iter.next();
+ if ( !n.isExternal() ) {
+ stats.addValue( n.getNumberOfDescendants() );
}
}
- return max;
+ return stats;
+ }
+
+ public static DescriptiveStatistics calculatConfidenceStatistics( final Phylogeny phy ) {
+ final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
+ for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
+ final PhylogenyNode n = iter.next();
+ if ( !n.isExternal() ) {
+ if ( n.getBranchData().isHasConfidences() ) {
+ stats.addValue( n.getBranchData().getConfidence( 0 ).getValue() );
+ }
+ }
+ }
+ return stats;
}
/**
}
}
}
- else if ( node.getNodeData().isHasSequence()
+ if ( !match && node.getNodeData().isHasSequence()
&& match( node.getNodeData().getSequence().getName(), query, case_sensitive, partial ) ) {
match = true;
}
- else if ( node.getNodeData().isHasSequence()
+ if ( !match && node.getNodeData().isHasSequence()
&& match( node.getNodeData().getSequence().getSymbol(), query, case_sensitive, partial ) ) {
match = true;
}
- else if ( node.getNodeData().isHasSequence()
+ if ( !match
+ && node.getNodeData().isHasSequence()
&& ( node.getNodeData().getSequence().getAccession() != null )
&& match( node.getNodeData().getSequence().getAccession().getValue(),
query,
partial ) ) {
match = true;
}
- else if ( node.getNodeData().isHasSequence()
+ if ( !match && node.getNodeData().isHasSequence()
&& ( node.getNodeData().getSequence().getDomainArchitecture() != null ) ) {
final DomainArchitecture da = node.getNodeData().getSequence().getDomainArchitecture();
I: for( int i = 0; i < da.getNumberOfDomains(); ++i ) {
}
}
}
+ if ( !match && ( node.getNodeData().getBinaryCharacters() != null ) ) {
+ Iterator<String> it = node.getNodeData().getBinaryCharacters().getPresentCharacters().iterator();
+ I: while ( it.hasNext() ) {
+ if ( match( it.next(), query, case_sensitive, partial ) ) {
+ match = true;
+ break I;
+ }
+ }
+ it = node.getNodeData().getBinaryCharacters().getGainedCharacters().iterator();
+ I: while ( it.hasNext() ) {
+ if ( match( it.next(), query, case_sensitive, partial ) ) {
+ match = true;
+ break I;
+ }
+ }
+ }
if ( match ) {
nodes.add( node );
}
}
}
}
- else if ( node.getNodeData().isHasSequence()
+ if ( !match && node.getNodeData().isHasSequence()
&& match( node.getNodeData().getSequence().getName(), query, case_sensitive, partial ) ) {
match = true;
}
- else if ( node.getNodeData().isHasSequence()
+ if ( !match && node.getNodeData().isHasSequence()
&& match( node.getNodeData().getSequence().getSymbol(), query, case_sensitive, partial ) ) {
match = true;
}
- else if ( node.getNodeData().isHasSequence()
+ if ( !match
+ && node.getNodeData().isHasSequence()
&& ( node.getNodeData().getSequence().getAccession() != null )
&& match( node.getNodeData().getSequence().getAccession().getValue(),
query,
partial ) ) {
match = true;
}
- else if ( node.getNodeData().isHasSequence()
+ if ( !match && node.getNodeData().isHasSequence()
&& ( node.getNodeData().getSequence().getDomainArchitecture() != null ) ) {
final DomainArchitecture da = node.getNodeData().getSequence().getDomainArchitecture();
I: for( int i = 0; i < da.getNumberOfDomains(); ++i ) {
}
}
}
+ if ( !match && ( node.getNodeData().getBinaryCharacters() != null ) ) {
+ Iterator<String> it = node.getNodeData().getBinaryCharacters().getPresentCharacters().iterator();
+ I: while ( it.hasNext() ) {
+ if ( match( it.next(), query, case_sensitive, partial ) ) {
+ match = true;
+ break I;
+ }
+ }
+ it = node.getNodeData().getBinaryCharacters().getGainedCharacters().iterator();
+ I: while ( it.hasNext() ) {
+ if ( match( it.next(), query, case_sensitive, partial ) ) {
+ match = true;
+ break I;
+ }
+ }
+ // final String[] bcp_ary = node.getNodeData().getBinaryCharacters()
+ // .getPresentCharactersAsStringArray();
+ // I: for( final String bc : bcp_ary ) {
+ // if ( match( bc, query, case_sensitive, partial ) ) {
+ // match = true;
+ // break I;
+ // }
+ // }
+ // final String[] bcg_ary = node.getNodeData().getBinaryCharacters()
+ // .getGainedCharactersAsStringArray();
+ // I: for( final String bc : bcg_ary ) {
+ // if ( match( bc, query, case_sensitive, partial ) ) {
+ // match = true;
+ // break I;
+ // }
+ // }
+ }
if ( !match ) {
all_matched = false;
break;
}
return nodes_to_delete.size();
}
+
+ public static enum PhylogenyNodeField {
+ CLADE_NAME,
+ TAXONOMY_CODE,
+ TAXONOMY_SCIENTIFIC_NAME,
+ TAXONOMY_COMMON_NAME,
+ SEQUENCE_SYMBOL,
+ SEQUENCE_NAME,
+ TAXONOMY_ID_UNIPROT_1,
+ TAXONOMY_ID_UNIPROT_2;
+ }
+
+ public static enum TAXONOMY_EXTRACTION {
+ NO, YES, PFAM_STYLE_ONLY;
+ }
}