import java.util.HashSet;
import java.util.List;
import java.util.Set;
+import java.util.SortedSet;
+import java.util.TreeSet;
import org.forester.datastructures.IntMatrix;
import org.forester.io.parsers.PhylogenyParser;
+import org.forester.io.parsers.nexus.NexusPhylogeniesParser;
import org.forester.io.parsers.nhx.NHXParser;
+import org.forester.io.parsers.nhx.NHXParser.TAXONOMY_EXTRACTION;
import org.forester.io.parsers.util.ParserUtils;
import org.forester.phylogeny.Phylogeny;
import org.forester.phylogeny.PhylogenyMethods;
import org.forester.phylogeny.PhylogenyNode;
+import org.forester.phylogeny.data.Taxonomy;
import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
import org.forester.phylogeny.factories.PhylogenyFactory;
+import org.forester.sdi.GSDI;
import org.forester.sdi.GSDIR;
import org.forester.sdi.SDIException;
import org.forester.sdi.SDIR;
+import org.forester.sdi.SDIutil;
import org.forester.sdi.SDIutil.ALGORITHM;
import org.forester.sdi.SDIutil.TaxonomyComparisonBase;
import org.forester.util.BasicDescriptiveStatistics;
public final class RIO {
- private final static boolean ROOT_BY_MINIMIZING_SUM_OF_DUPS = true;
- private final static boolean ROOT_BY_MINIMIZING_TREE_HEIGHT = true;
- private Phylogeny[] _analyzed_gene_trees;
- private List<PhylogenyNode> _removed_gene_tree_nodes;
- private int _ext_nodes;
- private TaxonomyComparisonBase _gsdir_tax_comp_base;
- private StringBuilder _log;
- private boolean _produce_log;
- private boolean _verbose;
-
- public RIO( final File gene_trees_file,
- final Phylogeny species_tree,
- final ALGORITHM algorithm,
- final boolean produce_log,
- final boolean verbose ) throws IOException, SDIException, RIOException {
- init( produce_log, verbose );
- inferOrthologs( gene_trees_file, species_tree, algorithm );
- }
+ public static final int DEFAULT_RANGE = -1;
+ private Phylogeny[] _analyzed_gene_trees;
+ private List<PhylogenyNode> _removed_gene_tree_nodes;
+ private int _ext_nodes;
+ private int _int_nodes;
+ private TaxonomyComparisonBase _gsdir_tax_comp_base;
+ private final StringBuilder _log;
+ private final BasicDescriptiveStatistics _duplications_stats;
+ private final boolean _produce_log;
+ private final boolean _verbose;
+ private final REROOTING _rerooting;
- public RIO( final Phylogeny[] gene_trees,
- final Phylogeny species_tree,
- final ALGORITHM algorithm,
- final boolean produce_log,
- final boolean verbose ) throws IOException, SDIException, RIOException {
- init( produce_log, verbose );
- inferOrthologs( gene_trees, species_tree, algorithm );
+ private RIO( final Phylogeny[] gene_trees,
+ final Phylogeny species_tree,
+ final ALGORITHM algorithm,
+ final REROOTING rerooting,
+ final String outgroup,
+ int first,
+ int last,
+ final boolean produce_log,
+ final boolean verbose ) throws IOException, SDIException, RIOException {
+ if ( ( last == DEFAULT_RANGE ) && ( first >= 0 ) ) {
+ last = gene_trees.length - 1;
+ }
+ else if ( ( first == DEFAULT_RANGE ) && ( last >= 0 ) ) {
+ first = 0;
+ }
+ removeSingleDescendentsNodes( species_tree, verbose );
+ checkPreconditions( gene_trees, species_tree, rerooting, outgroup, first, last );
+ _produce_log = produce_log;
+ _verbose = verbose;
+ _rerooting = rerooting;
+ _ext_nodes = -1;
+ _int_nodes = -1;
+ _log = new StringBuilder();
+ _gsdir_tax_comp_base = null;
+ _analyzed_gene_trees = null;
+ _removed_gene_tree_nodes = null;
+ _duplications_stats = new BasicDescriptiveStatistics();
+ inferOrthologs( gene_trees, species_tree, algorithm, outgroup, first, last );
}
public final Phylogeny[] getAnalyzedGeneTrees() {
return _analyzed_gene_trees;
}
+ public final BasicDescriptiveStatistics getDuplicationsStatistics() {
+ return _duplications_stats;
+ }
+
/**
* Returns the numbers of number of ext nodes in gene trees analyzed (after
* stripping).
return _ext_nodes;
}
+ /**
+ * Returns the numbers of number of int nodes in gene trees analyzed (after
+ * stripping).
+ *
+ * @return number of int nodes in gene trees analyzed (after stripping)
+ */
+ public final int getIntNodesOfAnalyzedGeneTrees() {
+ return _int_nodes;
+ }
+
public final TaxonomyComparisonBase getGSDIRtaxCompBase() {
return _gsdir_tax_comp_base;
}
return _removed_gene_tree_nodes;
}
- private final void inferOrthologs( final File gene_trees_file,
- final Phylogeny species_tree,
- final ALGORITHM algorithm ) throws SDIException, RIOException,
- FileNotFoundException, IOException {
- final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
- final PhylogenyParser p = ParserUtils.createParserDependingOnFileType( gene_trees_file, true );
- if ( p instanceof NHXParser ) {
- final NHXParser nhx = ( NHXParser ) p;
- nhx.setReplaceUnderscores( false );
- nhx.setIgnoreQuotes( true );
- nhx.setTaxonomyExtraction( NHXParser.TAXONOMY_EXTRACTION.YES );
- }
- final Phylogeny[] gene_trees = factory.create( gene_trees_file, p );
- inferOrthologs( gene_trees, species_tree, algorithm );
- }
-
private final void inferOrthologs( final Phylogeny[] gene_trees,
final Phylogeny species_tree,
- final ALGORITHM algorithm ) throws SDIException, RIOException,
- FileNotFoundException, IOException {
+ final ALGORITHM algorithm,
+ final String outgroup,
+ final int first,
+ final int last ) throws SDIException, RIOException, FileNotFoundException,
+ IOException {
if ( algorithm == ALGORITHM.SDIR ) {
// Removes from species_tree all species not found in gene_tree.
PhylogenyMethods.taxonomyBasedDeletionOfExternalNodes( gene_trees[ 0 ], species_tree );
throw new RIOException( "failed to establish species based mapping between gene and species trees" );
}
}
- if ( _produce_log ) {
- _log = new StringBuilder();
- writeLogSubHeader();
+ final Phylogeny[] my_gene_trees;
+ if ( ( first >= 0 ) && ( last >= first ) && ( last < gene_trees.length ) ) {
+ my_gene_trees = new Phylogeny[ 1 + last - first ];
+ int c = 0;
+ for( int i = first; i <= last; ++i ) {
+ my_gene_trees[ c++ ] = gene_trees[ i ];
+ }
}
- _analyzed_gene_trees = new Phylogeny[ gene_trees.length ];
- int gene_tree_ext_nodes = 0;
- if ( _verbose ) {
+ else {
+ my_gene_trees = gene_trees;
+ }
+ if ( log() ) {
+ preLog( gene_trees, species_tree, algorithm, outgroup, first, last );
+ }
+ if ( _verbose && ( my_gene_trees.length >= 4 ) ) {
System.out.println();
}
- for( int i = 0; i < gene_trees.length; ++i ) {
- final Phylogeny gt = gene_trees[ i ];
- if ( _verbose ) {
- ForesterUtil.updateProgress( ( double ) i / gene_trees.length );
+ _analyzed_gene_trees = new Phylogeny[ my_gene_trees.length ];
+ int gene_tree_ext_nodes = 0;
+ for( int i = 0; i < my_gene_trees.length; ++i ) {
+ final Phylogeny gt = my_gene_trees[ i ];
+ if ( _verbose && ( my_gene_trees.length > 4 ) ) {
+ ForesterUtil.updateProgress( ( ( double ) i ) / my_gene_trees.length );
}
if ( i == 0 ) {
gene_tree_ext_nodes = gt.getNumberOfExternalNodes();
throw new RIOException( "failed to establish species based mapping between gene and species trees" );
}
}
- _analyzed_gene_trees[ i ] = performOrthologInference( gt, species_tree, algorithm, i );
+ _analyzed_gene_trees[ i ] = performOrthologInference( gt, species_tree, algorithm, outgroup, i );
}
- if ( _verbose ) {
+ if ( log() ) {
+ postLog( species_tree );
+ }
+ if ( _verbose && ( my_gene_trees.length > 4 ) ) {
System.out.println();
System.out.println();
}
}
- private final void init( final boolean produce_log, final boolean verbose ) {
- _produce_log = produce_log;
- _verbose = verbose;
- _ext_nodes = -1;
- _log = null;
- _gsdir_tax_comp_base = null;
- _analyzed_gene_trees = null;
- _removed_gene_tree_nodes = null;
+ private final boolean log() {
+ return _produce_log;
+ }
+
+ private final void log( final String s ) {
+ _log.append( s );
+ _log.append( ForesterUtil.LINE_SEPARATOR );
+ }
+
+ private final void logRemovedGeneTreeNodes() {
+ log( "Species stripped from gene trees:" );
+ final SortedSet<String> rn = new TreeSet<String>();
+ for( final PhylogenyNode n : getRemovedGeneTreeNodes() ) {
+ final Taxonomy t = n.getNodeData().getTaxonomy();
+ switch ( getGSDIRtaxCompBase() ) {
+ case CODE: {
+ rn.add( t.getTaxonomyCode() );
+ break;
+ }
+ case ID: {
+ rn.add( t.getIdentifier().toString() );
+ break;
+ }
+ case SCIENTIFIC_NAME: {
+ rn.add( t.getScientificName() );
+ break;
+ }
+ }
+ }
+ for( final String s : rn ) {
+ log( s );
+ }
+ log( "" );
}
private final Phylogeny performOrthologInference( final Phylogeny gene_tree,
final Phylogeny species_tree,
final ALGORITHM algorithm,
+ final String outgroup,
final int i ) throws SDIException, RIOException {
final Phylogeny assigned_tree;
switch ( algorithm ) {
case SDIR: {
- final SDIR sdir = new SDIR();
- assigned_tree = sdir.infer( gene_tree,
- species_tree,
- false,
- RIO.ROOT_BY_MINIMIZING_SUM_OF_DUPS,
- RIO.ROOT_BY_MINIMIZING_TREE_HEIGHT,
- true,
- 1 )[ 0 ];
+ assigned_tree = performOrthologInferenceBySDI( gene_tree, species_tree );
break;
}
case GSDIR: {
- // System.out.println( "gene/species tree size before: " + gene_tree.getNumberOfExternalNodes() + "/"
- // + species_tree.getNumberOfExternalNodes() );
- final GSDIR gsdir = new GSDIR( gene_tree, species_tree, true, i == 0 );
- // System.out.println( "gene/species tree size before: " + gene_tree.getNumberOfExternalNodes() + "/"
- // + species_tree.getNumberOfExternalNodes() );
- assigned_tree = gsdir.getMinDuplicationsSumGeneTrees().get( 0 );
- if ( i == 0 ) {
- _removed_gene_tree_nodes = gsdir.getStrippedExternalGeneTreeNodes();
- for( final PhylogenyNode r : _removed_gene_tree_nodes ) {
- if ( !r.getNodeData().isHasTaxonomy() ) {
- throw new RIOException( "node with no (appropriate) taxonomic information found in gene tree #1: "
- + r.toString() );
- }
- }
- }
- if ( _produce_log ) {
- writeStatsToLog( i, gsdir );
- }
- _gsdir_tax_comp_base = gsdir.getTaxCompBase();
+ assigned_tree = performOrthologInferenceByGSDI( gene_tree, species_tree, outgroup, i );
break;
}
default: {
}
if ( i == 0 ) {
_ext_nodes = assigned_tree.getNumberOfExternalNodes();
+ _int_nodes = assigned_tree.getNumberOfInternalNodes();
}
else if ( _ext_nodes != assigned_tree.getNumberOfExternalNodes() ) {
throw new RIOException( "after stripping gene tree #" + ( i + 1 )
return assigned_tree;
}
- private void writeLogSubHeader() {
+ private final Phylogeny performOrthologInferenceByGSDI( final Phylogeny gene_tree,
+ final Phylogeny species_tree,
+ final String outgroup,
+ final int i ) throws SDIException, RIOException {
+ final Phylogeny assigned_tree;
+ if ( _rerooting == REROOTING.BY_ALGORITHM ) {
+ final GSDIR gsdir = new GSDIR( gene_tree, species_tree, true, i == 0 );
+ final List<Phylogeny> assigned_trees = gsdir.getMinDuplicationsSumGeneTrees();
+ if ( i == 0 ) {
+ _removed_gene_tree_nodes = gsdir.getStrippedExternalGeneTreeNodes();
+ for( final PhylogenyNode r : _removed_gene_tree_nodes ) {
+ if ( !r.getNodeData().isHasTaxonomy() ) {
+ throw new RIOException( "node with no (appropriate) taxonomic information found in gene tree #1: "
+ + r.toString() );
+ }
+ }
+ }
+ final List<Integer> shortests = GSDIR.getIndexesOfShortestTree( assigned_trees );
+ assigned_tree = assigned_trees.get( shortests.get( 0 ) );
+ if ( log() ) {
+ writeStatsToLog( i, gsdir, shortests );
+ }
+ if ( i == 0 ) {
+ _gsdir_tax_comp_base = gsdir.getTaxCompBase();
+ }
+ _duplications_stats.addValue( gsdir.getMinDuplicationsSum() );
+ }
+ else {
+ if ( _rerooting == REROOTING.MIDPOINT ) {
+ PhylogenyMethods.midpointRoot( gene_tree );
+ }
+ else if ( _rerooting == REROOTING.OUTGROUP ) {
+ final PhylogenyNode n = gene_tree.getNode( outgroup );
+ gene_tree.reRoot( n );
+ }
+ final GSDI gsdi = new GSDI( gene_tree, species_tree, true, true, true );
+ _removed_gene_tree_nodes = gsdi.getStrippedExternalGeneTreeNodes();
+ for( final PhylogenyNode r : _removed_gene_tree_nodes ) {
+ if ( !r.getNodeData().isHasTaxonomy() ) {
+ throw new RIOException( "node with no (appropriate) taxonomic information found in gene tree #1: "
+ + r.toString() );
+ }
+ }
+ assigned_tree = gene_tree;
+ if ( i == 0 ) {
+ _gsdir_tax_comp_base = gsdi.getTaxCompBase();
+ }
+ _duplications_stats.addValue( gsdi.getDuplicationsSum() );
+ }
+ return assigned_tree;
+ }
+
+ private final Phylogeny performOrthologInferenceBySDI( final Phylogeny gene_tree, final Phylogeny species_tree )
+ throws SDIException {
+ final SDIR sdir = new SDIR();
+ return sdir.infer( gene_tree, species_tree, false, true, true, true, 1 )[ 0 ];
+ }
+
+ private final void postLog( final Phylogeny species_tree ) {
+ log( "" );
+ if ( getRemovedGeneTreeNodes().size() > 0 ) {
+ logRemovedGeneTreeNodes();
+ }
+ log( "Species tree external nodes (after stripping) : " + species_tree.getNumberOfExternalNodes() );
+ log( "Species tree polytomies (after stripping) : "
+ + PhylogenyMethods.countNumberOfPolytomies( species_tree ) );
+ log( "Taxonomy linking based on : " + getGSDIRtaxCompBase() );
+ final java.text.DecimalFormat df = new java.text.DecimalFormat( "0.#" );
+ log( "Gene trees analyzed : " + _duplications_stats.getN() );
+ log( "Mean number of duplications : " + df.format( _duplications_stats.arithmeticMean() )
+ + " (sd: " + df.format( _duplications_stats.sampleStandardDeviation() ) + ")" + " ("
+ + df.format( 100.0 * _duplications_stats.arithmeticMean() / getIntNodesOfAnalyzedGeneTrees() ) + "%)" );
+ if ( _duplications_stats.getN() > 3 ) {
+ log( "Median number of duplications : " + df.format( _duplications_stats.median() )
+ + " (" + df.format( 100.0 * _duplications_stats.median() / getIntNodesOfAnalyzedGeneTrees() )
+ + "%)" );
+ }
+ log( "Minimum duplications : " + ( int ) _duplications_stats.getMin() + " ("
+ + df.format( 100.0 * _duplications_stats.getMin() / getIntNodesOfAnalyzedGeneTrees() ) + "%)" );
+ log( "Maximum duplications : " + ( int ) _duplications_stats.getMax() + " ("
+ + df.format( 100.0 * _duplications_stats.getMax() / getIntNodesOfAnalyzedGeneTrees() ) + "%)" );
+ log( "Gene tree internal nodes : " + getIntNodesOfAnalyzedGeneTrees() );
+ log( "Gene tree external nodes : " + getExtNodesOfAnalyzedGeneTrees() );
+ }
+
+ private final void preLog( final Phylogeny[] gene_trees,
+ final Phylogeny species_tree,
+ final ALGORITHM algorithm,
+ final String outgroup,
+ final int first,
+ final int last ) {
+ log( "Number of gene trees (total) : " + gene_trees.length );
+ log( "Algorithm : " + algorithm );
+ log( "Species tree external nodes (prior to stripping): " + species_tree.getNumberOfExternalNodes() );
+ log( "Species tree polytomies (prior to stripping) : "
+ + PhylogenyMethods.countNumberOfPolytomies( species_tree ) );
+ String rs = "";
+ switch ( _rerooting ) {
+ case BY_ALGORITHM: {
+ rs = "minimizing duplications";
+ break;
+ }
+ case MIDPOINT: {
+ rs = "midpoint";
+ break;
+ }
+ case OUTGROUP: {
+ rs = "outgroup: " + outgroup;
+ break;
+ }
+ case NONE: {
+ rs = "none";
+ break;
+ }
+ }
+ log( "Re-rooting : " + rs );
+ if ( ( first >= 0 ) || ( last >= 0 ) ) {
+ log( "Gene trees analyzed range : " + first + "-" + last );
+ }
+ if ( _rerooting == REROOTING.BY_ALGORITHM ) {
+ writeLogSubHeader();
+ }
+ }
+
+ private final void writeLogSubHeader() {
+ _log.append( ForesterUtil.LINE_SEPARATOR );
+ _log.append( "Some information about duplication numbers in gene trees:" );
+ _log.append( ForesterUtil.LINE_SEPARATOR );
_log.append( "#" );
_log.append( "\t" );
- _log.append( "with minimal number of duplications" );
+ _log.append( "re-rootings with minimal number of duplications" );
_log.append( "/" );
- _log.append( "root placements" );
- _log.append( "\t[" );
- _log.append( "min" );
- _log.append( "-" );
- _log.append( "max" );
- _log.append( "]" );
+ _log.append( "total root placements" );
+ _log.append( "\t" );
+ _log.append( "duplications range" );
+ _log.append( "\t" );
+ _log.append( "mininal duplication re-rootings with shortest tree heigth" );
_log.append( ForesterUtil.LINE_SEPARATOR );
}
- private final void writeStatsToLog( final int i, final GSDIR gsdir ) {
+ private final void writeStatsToLog( final int i, final GSDIR gsdir, final List<Integer> shortests ) {
final BasicDescriptiveStatistics stats = gsdir.getDuplicationsSumStats();
_log.append( i );
_log.append( "\t" );
_log.append( gsdir.getMinDuplicationsSumGeneTrees().size() );
_log.append( "/" );
_log.append( stats.getN() );
- _log.append( "\t[" );
+ _log.append( "\t" );
_log.append( ( int ) stats.getMin() );
_log.append( "-" );
_log.append( ( int ) stats.getMax() );
- _log.append( "]" );
+ _log.append( "\t" );
+ _log.append( shortests.size() );
_log.append( ForesterUtil.LINE_SEPARATOR );
}
}
return m;
}
+
+ public final static RIO executeAnalysis( final File gene_trees_file,
+ final File species_tree_file,
+ final ALGORITHM algorithm,
+ final REROOTING rerooting,
+ final String outgroup,
+ final int first,
+ final int last,
+ final boolean produce_log,
+ final boolean verbose ) throws IOException, SDIException, RIOException {
+ final Phylogeny[] gene_trees = parseGeneTrees( gene_trees_file );
+ if ( gene_trees.length < 1 ) {
+ throw new RIOException( "\"" + gene_trees_file + "\" is devoid of appropriate gene trees" );
+ }
+ final Phylogeny species_tree = SDIutil.parseSpeciesTree( gene_trees[ 0 ],
+ species_tree_file,
+ false,
+ true,
+ TAXONOMY_EXTRACTION.NO );
+ return new RIO( gene_trees, species_tree, algorithm, rerooting, outgroup, first, last, produce_log, verbose );
+ }
+
+ public final static RIO executeAnalysis( final File gene_trees_file,
+ final Phylogeny species_tree,
+ final ALGORITHM algorithm,
+ final REROOTING rerooting,
+ final String outgroup,
+ final boolean produce_log,
+ final boolean verbose ) throws IOException, SDIException, RIOException {
+ return new RIO( parseGeneTrees( gene_trees_file ),
+ species_tree,
+ algorithm,
+ rerooting,
+ outgroup,
+ DEFAULT_RANGE,
+ DEFAULT_RANGE,
+ produce_log,
+ verbose );
+ }
+
+ public final static RIO executeAnalysis( final File gene_trees_file,
+ final Phylogeny species_tree,
+ final ALGORITHM algorithm,
+ final REROOTING rerooting,
+ final String outgroup,
+ final int first,
+ final int last,
+ final boolean produce_log,
+ final boolean verbose ) throws IOException, SDIException, RIOException {
+ return new RIO( parseGeneTrees( gene_trees_file ),
+ species_tree,
+ algorithm,
+ rerooting,
+ outgroup,
+ first,
+ last,
+ produce_log,
+ verbose );
+ }
+
+ public final static RIO executeAnalysis( final Phylogeny[] gene_trees, final Phylogeny species_tree )
+ throws IOException, SDIException, RIOException {
+ return new RIO( gene_trees,
+ species_tree,
+ ALGORITHM.GSDIR,
+ REROOTING.BY_ALGORITHM,
+ null,
+ DEFAULT_RANGE,
+ DEFAULT_RANGE,
+ false,
+ false );
+ }
+
+ public final static RIO executeAnalysis( final Phylogeny[] gene_trees,
+ final Phylogeny species_tree,
+ final ALGORITHM algorithm,
+ final REROOTING rerooting,
+ final String outgroup,
+ final boolean produce_log,
+ final boolean verbose ) throws IOException, SDIException, RIOException {
+ return new RIO( gene_trees,
+ species_tree,
+ algorithm,
+ rerooting,
+ outgroup,
+ DEFAULT_RANGE,
+ DEFAULT_RANGE,
+ produce_log,
+ verbose );
+ }
+
+ public final static RIO executeAnalysis( final Phylogeny[] gene_trees,
+ final Phylogeny species_tree,
+ final ALGORITHM algorithm,
+ final REROOTING rerooting,
+ final String outgroup,
+ final int first,
+ final int last,
+ final boolean produce_log,
+ final boolean verbose ) throws IOException, SDIException, RIOException {
+ return new RIO( gene_trees, species_tree, algorithm, rerooting, outgroup, first, last, produce_log, verbose );
+ }
+
+ private final static void checkPreconditions( final Phylogeny[] gene_trees,
+ final Phylogeny species_tree,
+ final REROOTING rerooting,
+ final String outgroup,
+ final int first,
+ final int last ) throws RIOException {
+ if ( !species_tree.isRooted() ) {
+ throw new RIOException( "species tree is not rooted" );
+ }
+ if ( !( ( last == DEFAULT_RANGE ) && ( first == DEFAULT_RANGE ) )
+ && ( ( last < first ) || ( last >= gene_trees.length ) || ( last < 0 ) || ( first < 0 ) ) ) {
+ throw new RIOException( "attempt to set range (0-based) of gene to analyze to: from " + first + " to "
+ + last + " (out of " + gene_trees.length + ")" );
+ }
+ if ( ( rerooting == REROOTING.OUTGROUP ) && ForesterUtil.isEmpty( outgroup ) ) {
+ throw new RIOException( "outgroup not set for midpoint rooting" );
+ }
+ if ( ( rerooting != REROOTING.OUTGROUP ) && !ForesterUtil.isEmpty( outgroup ) ) {
+ throw new RIOException( "outgroup only used for midpoint rooting" );
+ }
+ if ( ( rerooting == REROOTING.MIDPOINT )
+ && ( PhylogenyMethods.calculateMaxDistanceToRoot( gene_trees[ 0 ] ) <= 0 ) ) {
+ throw new RIOException( "attempt to use midpoint rooting on gene trees which seem to have no (positive) branch lengths (cladograms)" );
+ }
+ if ( rerooting == REROOTING.OUTGROUP ) {
+ try {
+ gene_trees[ 0 ].getNode( outgroup );
+ }
+ catch ( final IllegalArgumentException e ) {
+ throw new RIOException( "cannot perform re-rooting by outgroup: " + e.getLocalizedMessage() );
+ }
+ }
+ }
+
+ private final static Phylogeny[] parseGeneTrees( final File gene_trees_file ) throws FileNotFoundException,
+ IOException {
+ final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
+ final PhylogenyParser p = ParserUtils.createParserDependingOnFileType( gene_trees_file, true );
+ if ( p instanceof NHXParser ) {
+ final NHXParser nhx = ( NHXParser ) p;
+ nhx.setReplaceUnderscores( false );
+ nhx.setIgnoreQuotes( true );
+ nhx.setTaxonomyExtraction( NHXParser.TAXONOMY_EXTRACTION.YES );
+ }
+ else if ( p instanceof NexusPhylogeniesParser ) {
+ final NexusPhylogeniesParser nex = ( NexusPhylogeniesParser ) p;
+ nex.setReplaceUnderscores( false );
+ nex.setIgnoreQuotes( true );
+ nex.setTaxonomyExtraction( TAXONOMY_EXTRACTION.YES );
+ }
+ return factory.create( gene_trees_file, p );
+ }
+
+ private final static void removeSingleDescendentsNodes( final Phylogeny species_tree, final boolean verbose ) {
+ final int o = PhylogenyMethods.countNumberOfOneDescendantNodes( species_tree );
+ if ( o > 0 ) {
+ if ( verbose ) {
+ System.out.println( "warning: species tree has " + o
+ + " internal nodes with only one descendent which are therefore going to be removed" );
+ }
+ PhylogenyMethods.deleteInternalNodesWithOnlyOneDescendent( species_tree );
+ }
+ }
+
+ public enum REROOTING {
+ NONE, BY_ALGORITHM, MIDPOINT, OUTGROUP;
+ }
}