private final boolean _produce_log;
private final boolean _verbose;
private final REROOTING _rerooting;
+ private final Phylogeny _species_tree;
+ private Phylogeny _min_dub_gene_tree;
- private RIO( final Phylogeny[] gene_trees,
+ private RIO( final IteratingPhylogenyParser p,
final Phylogeny species_tree,
final ALGORITHM algorithm,
final REROOTING rerooting,
int first,
int last,
final boolean produce_log,
- final boolean verbose ) throws IOException, SDIException, RIOException {
+ final boolean verbose,
+ final boolean transfer_taxonomy ) throws IOException, SDIException, RIOException {
if ( ( last == DEFAULT_RANGE ) && ( first >= 0 ) ) {
- last = gene_trees.length - 1;
+ last = END_OF_GT;
}
else if ( ( first == DEFAULT_RANGE ) && ( last >= 0 ) ) {
first = 0;
}
removeSingleDescendentsNodes( species_tree, verbose );
- checkPreconditions( gene_trees, species_tree, rerooting, outgroup, first, last );
+ p.reset();
+ checkPreconditions( p, species_tree, rerooting, outgroup, first, last );
_produce_log = produce_log;
_verbose = verbose;
_rerooting = rerooting;
_analyzed_gene_trees = null;
_removed_gene_tree_nodes = null;
_duplications_stats = new BasicDescriptiveStatistics();
- inferOrthologs( gene_trees, species_tree, algorithm, outgroup, first, last );
+ p.reset();
+ inferOrthologs( p, species_tree, algorithm, outgroup, first, last, transfer_taxonomy );
+ _species_tree = species_tree;
}
- private RIO( final IteratingPhylogenyParser p,
+ private RIO( final Phylogeny[] gene_trees,
final Phylogeny species_tree,
final ALGORITHM algorithm,
final REROOTING rerooting,
int first,
int last,
final boolean produce_log,
- final boolean verbose ) throws IOException, SDIException, RIOException {
+ final boolean verbose,
+ final boolean transfer_taxonomy ) throws IOException, SDIException, RIOException {
if ( ( last == DEFAULT_RANGE ) && ( first >= 0 ) ) {
- last = END_OF_GT;
+ last = gene_trees.length - 1;
}
else if ( ( first == DEFAULT_RANGE ) && ( last >= 0 ) ) {
first = 0;
}
removeSingleDescendentsNodes( species_tree, verbose );
- p.reset();
- checkPreconditions( p, species_tree, rerooting, outgroup, first, last );
+ checkPreconditions( gene_trees, species_tree, rerooting, outgroup, first, last );
_produce_log = produce_log;
_verbose = verbose;
_rerooting = rerooting;
_analyzed_gene_trees = null;
_removed_gene_tree_nodes = null;
_duplications_stats = new BasicDescriptiveStatistics();
- p.reset();
- inferOrthologs( p, species_tree, algorithm, outgroup, first, last );
+ inferOrthologs( gene_trees, species_tree, algorithm, outgroup, first, last, transfer_taxonomy );
+ _species_tree = species_tree;
}
public final Phylogeny[] getAnalyzedGeneTrees() {
return _ext_nodes;
}
+ public final TaxonomyComparisonBase getGSDIRtaxCompBase() {
+ return _gsdir_tax_comp_base;
+ }
+
/**
* Returns the numbers of number of int nodes in gene trees analyzed (after
* stripping).
return _int_nodes;
}
- public final TaxonomyComparisonBase getGSDIRtaxCompBase() {
- return _gsdir_tax_comp_base;
- }
-
public final StringBuilder getLog() {
return _log;
}
+ final public Phylogeny getMinDuplicationsGeneTree() {
+ return _min_dub_gene_tree;
+ }
+
+ public final IntMatrix getOrthologTable() {
+ return _m;
+ }
+
public final List<PhylogenyNode> getRemovedGeneTreeNodes() {
return _removed_gene_tree_nodes;
}
- private final void inferOrthologs( final Phylogeny[] gene_trees,
- final Phylogeny species_tree,
- 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 );
- if ( species_tree.isEmpty() ) {
- throw new RIOException( "failed to establish species based mapping between gene and species trees" );
- }
- }
- 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 ];
- }
- }
- else {
- my_gene_trees = gene_trees;
- }
- if ( log() ) {
- preLog( gene_trees.length, species_tree, algorithm, outgroup );
- }
- if ( _verbose && ( my_gene_trees.length >= 4 ) ) {
- System.out.println();
- }
- _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();
- }
- else if ( gene_tree_ext_nodes != gt.getNumberOfExternalNodes() ) {
- throw new RIOException( "gene tree #" + i + " has a different number of external nodes ("
- + gt.getNumberOfExternalNodes() + ") than the preceding gene tree(s) (" + gene_tree_ext_nodes
- + ")" );
- }
- if ( algorithm == ALGORITHM.SDIR ) {
- // Removes from gene_tree all species not found in species_tree.
- PhylogenyMethods.taxonomyBasedDeletionOfExternalNodes( species_tree, gt );
- if ( gt.isEmpty() ) {
- throw new RIOException( "failed to establish species based mapping between gene and species trees" );
- }
- }
- _analyzed_gene_trees[ i ] = performOrthologInference( gt, species_tree, algorithm, outgroup, i );
- }
- if ( log() ) {
- postLog( species_tree, first, last );
- }
- if ( _verbose && ( my_gene_trees.length > 4 ) ) {
- System.out.println();
- System.out.println();
- }
+ public final Phylogeny getSpeciesTree() {
+ return _species_tree;
}
private final void inferOrthologs( final IteratingPhylogenyParser parser,
final ALGORITHM algorithm,
final String outgroup,
int first,
- final int last ) throws SDIException, RIOException, FileNotFoundException,
- IOException {
+ final int last,
+ final boolean transfer_taxonomy ) throws SDIException, RIOException,
+ FileNotFoundException, IOException {
if ( !parser.hasNext() ) {
throw new RIOException( "no gene trees to analyze" );
}
while ( parser.hasNext() ) {
final Phylogeny gt = parser.next();
if ( no_range || ( ( i >= first ) && ( i <= last ) ) ) {
+ if ( gt.isEmpty() ) {
+ throw new RIOException( "gene tree #" + i + " is empty" );
+ }
+ if ( gt.getNumberOfExternalNodes() == 1 ) {
+ throw new RIOException( "gene tree #" + i + " has only one external node" );
+ }
if ( _verbose ) {
ForesterUtil.updateProgress( i, pf );
}
throw new RIOException( "failed to establish species based mapping between gene and species trees" );
}
}
- final Phylogeny analyzed_gt = performOrthologInference( gt, species_tree, algorithm, outgroup, counter );
+ final Phylogeny analyzed_gt = performOrthologInference( gt,
+ species_tree,
+ algorithm,
+ outgroup,
+ counter,
+ transfer_taxonomy );
RIO.calculateOrthologTable( analyzed_gt, true, counter );
++counter;
}
first = 0;
}
if ( log() ) {
- postLog( species_tree, first, first + counter - 1 );
+ postLog( species_tree, first, ( first + counter ) - 1 );
}
if ( _verbose ) {
System.out.println();
}
}
+ private final void inferOrthologs( final Phylogeny[] gene_trees,
+ final Phylogeny species_tree,
+ final ALGORITHM algorithm,
+ final String outgroup,
+ final int first,
+ final int last,
+ final boolean transfer_taxonomy ) 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 );
+ if ( species_tree.isEmpty() ) {
+ throw new RIOException( "failed to establish species based mapping between gene and species trees" );
+ }
+ }
+ 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 ];
+ }
+ }
+ else {
+ my_gene_trees = gene_trees;
+ }
+ if ( log() ) {
+ preLog( gene_trees.length, species_tree, algorithm, outgroup );
+ }
+ if ( _verbose && ( my_gene_trees.length >= 4 ) ) {
+ System.out.println();
+ }
+ _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 ( gt.isEmpty() ) {
+ throw new RIOException( "gene tree #" + i + " is empty" );
+ }
+ if ( gt.getNumberOfExternalNodes() == 1 ) {
+ throw new RIOException( "gene tree #" + i + " has only one external node" );
+ }
+ if ( _verbose && ( my_gene_trees.length > 4 ) ) {
+ ForesterUtil.updateProgress( ( ( double ) i ) / my_gene_trees.length );
+ }
+ if ( i == 0 ) {
+ gene_tree_ext_nodes = gt.getNumberOfExternalNodes();
+ }
+ else if ( gene_tree_ext_nodes != gt.getNumberOfExternalNodes() ) {
+ throw new RIOException( "gene tree #" + i + " has a different number of external nodes ("
+ + gt.getNumberOfExternalNodes() + ") than the preceding gene tree(s) (" + gene_tree_ext_nodes
+ + ")" );
+ }
+ if ( algorithm == ALGORITHM.SDIR ) {
+ // Removes from gene_tree all species not found in species_tree.
+ PhylogenyMethods.taxonomyBasedDeletionOfExternalNodes( species_tree, gt );
+ if ( gt.isEmpty() ) {
+ throw new RIOException( "failed to establish species based mapping between gene and species trees" );
+ }
+ }
+ _analyzed_gene_trees[ i ] = performOrthologInference( gt,
+ species_tree,
+ algorithm,
+ outgroup,
+ i,
+ transfer_taxonomy );
+ }
+ if ( log() ) {
+ postLog( species_tree, first, last );
+ }
+ if ( _verbose && ( my_gene_trees.length > 4 ) ) {
+ System.out.println();
+ System.out.println();
+ }
+ }
+
private final boolean log() {
return _produce_log;
}
final Phylogeny species_tree,
final ALGORITHM algorithm,
final String outgroup,
- final int i ) throws SDIException, RIOException {
+ final int i,
+ final boolean transfer_taxonomy ) throws SDIException,
+ RIOException {
final Phylogeny assigned_tree;
switch ( algorithm ) {
case SDIR: {
break;
}
case GSDIR: {
- assigned_tree = performOrthologInferenceByGSDI( gene_tree, species_tree, outgroup, i );
+ assigned_tree = performOrthologInferenceByGSDI( gene_tree, species_tree, outgroup, i, transfer_taxonomy );
break;
}
default: {
private final Phylogeny performOrthologInferenceByGSDI( final Phylogeny gene_tree,
final Phylogeny species_tree,
final String outgroup,
- final int i ) throws SDIException, RIOException {
+ final int i,
+ final boolean transfer_taxonomy ) throws SDIException,
+ RIOException {
final Phylogeny assigned_tree;
+ final int dups;
if ( _rerooting == REROOTING.BY_ALGORITHM ) {
- final GSDIR gsdir = new GSDIR( gene_tree, species_tree, true, i == 0 );
+ final GSDIR gsdir = new GSDIR( gene_tree, species_tree, true, i == 0, transfer_taxonomy );
assigned_tree = gsdir.getMinDuplicationsSumGeneTree();
if ( i == 0 ) {
_removed_gene_tree_nodes = gsdir.getStrippedExternalGeneTreeNodes();
if ( i == 0 ) {
_gsdir_tax_comp_base = gsdir.getTaxCompBase();
}
- _duplications_stats.addValue( gsdir.getMinDuplicationsSum() );
+ dups = gsdir.getMinDuplicationsSum();
}
else {
if ( _rerooting == REROOTING.MIDPOINT ) {
final PhylogenyNode n = gene_tree.getNode( outgroup );
gene_tree.reRoot( n );
}
- final GSDI gsdi = new GSDI( gene_tree, species_tree, true, true, true );
+ final GSDI gsdi = new GSDI( gene_tree, species_tree, true, true, true, transfer_taxonomy );
_removed_gene_tree_nodes = gsdi.getStrippedExternalGeneTreeNodes();
for( final PhylogenyNode r : _removed_gene_tree_nodes ) {
if ( !r.getNodeData().isHasTaxonomy() ) {
if ( i == 0 ) {
_gsdir_tax_comp_base = gsdi.getTaxCompBase();
}
- _duplications_stats.addValue( gsdi.getDuplicationsSum() );
+ dups = gsdi.getDuplicationsSum();
+ }
+ if ( ( i == 0 ) || ( dups < _duplications_stats.getMin() ) ) {
+ _min_dub_gene_tree = assigned_tree;
}
+ _duplications_stats.addValue( dups );
return assigned_tree;
}
log( "Re-rooting : " + rs );
}
- public final IntMatrix getOrthologTable() {
- return _m;
- }
-
- private final static void calculateOrthologTable( final Phylogeny g, final boolean sort, final int counter )
- throws RIOException {
- final List<String> labels = new ArrayList<String>();
- final Set<String> labels_set = new HashSet<String>();
- if ( counter == 0 ) {
- for( final PhylogenyNode n : g.getExternalNodes() ) {
- final String label = obtainLabel( labels_set, n );
- labels_set.add( label );
- labels.add( label );
- }
- if ( sort ) {
- Collections.sort( labels );
- }
- _m = new IntMatrix( labels );
- }
- updateCounts( _m, counter, g );
- }
-
- private final static String obtainLabel( final Set<String> labels_set, final PhylogenyNode n ) throws RIOException {
- String label;
- if ( n.getNodeData().isHasSequence() && !ForesterUtil.isEmpty( n.getNodeData().getSequence().getName() ) ) {
- label = n.getNodeData().getSequence().getName();
- }
- else if ( n.getNodeData().isHasSequence() && !ForesterUtil.isEmpty( n.getNodeData().getSequence().getSymbol() ) ) {
- label = n.getNodeData().getSequence().getSymbol();
- }
- else if ( !ForesterUtil.isEmpty( n.getName() ) ) {
- label = n.getName();
- }
- else {
- throw new RIOException( "node " + n + " has no appropriate label" );
- }
- if ( labels_set.contains( label ) ) {
- throw new RIOException( "label " + label + " is not unique" );
- }
- return label;
- }
-
- private final static void updateCounts( final IntMatrix m, final int counter, final Phylogeny g )
- throws RIOException {
- PhylogenyMethods.preOrderReId( g );
- final HashMap<String, PhylogenyNode> map = PhylogenyMethods.createNameToExtNodeMap( g );
- for( int x = 0; x < m.size(); ++x ) {
- final String mx = m.getLabel( x );
- final PhylogenyNode nx = map.get( mx );
- if ( nx == null ) {
- throw new RIOException( "node \"" + mx + "\" not present in gene tree #" + counter );
- }
- String my;
- PhylogenyNode ny;
- for( int y = 0; y < m.size(); ++y ) {
- my = m.getLabel( y );
- ny = map.get( my );
- if ( ny == null ) {
- throw new RIOException( "node \"" + my + "\" not present in gene tree #" + counter );
- }
- if ( !PhylogenyMethods.calculateLCAonTreeWithIdsInPreOrder( nx, ny ).isDuplication() ) {
- m.inreaseByOne( x, y );
- }
- }
- }
- }
-
public final static IntMatrix calculateOrthologTable( final Phylogeny[] analyzed_gene_trees, final boolean sort )
throws RIOException {
final List<String> labels = new ArrayList<String>();
final int first,
final int last,
final boolean produce_log,
- final boolean verbose ) throws IOException, SDIException, RIOException {
+ final boolean verbose,
+ final boolean transfer_taxonomy ) 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" );
false,
true,
TAXONOMY_EXTRACTION.NO );
- return new RIO( gene_trees, species_tree, algorithm, rerooting, outgroup, first, last, produce_log, verbose );
+ return new RIO( gene_trees,
+ species_tree,
+ algorithm,
+ rerooting,
+ outgroup,
+ first,
+ last,
+ produce_log,
+ verbose,
+ transfer_taxonomy );
+ }
+
+ 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,
+ final boolean transfer_taxonomy ) throws IOException, SDIException,
+ RIOException {
+ return new RIO( parseGeneTrees( gene_trees_file ),
+ species_tree,
+ algorithm,
+ rerooting,
+ outgroup,
+ DEFAULT_RANGE,
+ DEFAULT_RANGE,
+ produce_log,
+ verbose,
+ transfer_taxonomy );
+ }
+
+ 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,
+ final boolean transfer_taxonomy ) throws IOException, SDIException,
+ RIOException {
+ return new RIO( parseGeneTrees( gene_trees_file ),
+ species_tree,
+ algorithm,
+ rerooting,
+ outgroup,
+ first,
+ last,
+ produce_log,
+ verbose,
+ transfer_taxonomy );
}
public final static RIO executeAnalysis( final IteratingPhylogenyParser p,
final int first,
final int last,
final boolean produce_log,
- final boolean verbose ) throws IOException, SDIException, RIOException {
+ final boolean verbose,
+ final boolean transfer_taxonomy ) throws IOException, SDIException,
+ RIOException {
final Phylogeny g0 = p.next();
if ( ( g0 == null ) || g0.isEmpty() || ( g0.getNumberOfExternalNodes() < 2 ) ) {
throw new RIOException( "input file does not seem to contain any gene trees" );
true,
TAXONOMY_EXTRACTION.NO );
p.reset();
- return new RIO( p, 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 ),
+ return new RIO( p,
species_tree,
algorithm,
rerooting,
outgroup,
- DEFAULT_RANGE,
- DEFAULT_RANGE,
+ first,
+ last,
produce_log,
- verbose );
+ verbose,
+ transfer_taxonomy );
}
public final static RIO executeAnalysis( final IteratingPhylogenyParser p,
final REROOTING rerooting,
final String outgroup,
final boolean produce_log,
- final boolean verbose ) throws IOException, SDIException, RIOException {
+ final boolean verbose,
+ final boolean transfer_taxonomy ) throws IOException, SDIException,
+ RIOException {
return new RIO( p,
species_tree,
algorithm,
DEFAULT_RANGE,
DEFAULT_RANGE,
produce_log,
- verbose );
+ verbose,
+ transfer_taxonomy );
}
- public final static RIO executeAnalysis( final File gene_trees_file,
+ public final static RIO executeAnalysis( final IteratingPhylogenyParser p,
final Phylogeny species_tree,
final ALGORITHM algorithm,
final REROOTING rerooting,
final int first,
final int last,
final boolean produce_log,
- final boolean verbose ) throws IOException, SDIException, RIOException {
- return new RIO( parseGeneTrees( gene_trees_file ),
+ final boolean verbose,
+ final boolean transfer_taxonomy ) throws IOException, SDIException,
+ RIOException {
+ return new RIO( p,
species_tree,
algorithm,
rerooting,
first,
last,
produce_log,
- verbose );
+ verbose,
+ transfer_taxonomy );
}
public final static RIO executeAnalysis( final Phylogeny[] gene_trees, final Phylogeny species_tree )
DEFAULT_RANGE,
DEFAULT_RANGE,
false,
+ false,
false );
}
final REROOTING rerooting,
final String outgroup,
final boolean produce_log,
- final boolean verbose ) throws IOException, SDIException, RIOException {
+ final boolean verbose,
+ final boolean transfer_taxonomy ) throws IOException, SDIException,
+ RIOException {
return new RIO( gene_trees,
species_tree,
algorithm,
DEFAULT_RANGE,
DEFAULT_RANGE,
produce_log,
- verbose );
+ verbose,
+ transfer_taxonomy );
}
public final static RIO executeAnalysis( final Phylogeny[] gene_trees,
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 );
+ final boolean verbose,
+ final boolean transfer_taxonomy ) throws IOException, SDIException,
+ RIOException {
+ return new RIO( gene_trees,
+ species_tree,
+ algorithm,
+ rerooting,
+ outgroup,
+ first,
+ last,
+ produce_log,
+ verbose,
+ transfer_taxonomy );
}
- public final static RIO executeAnalysis( final IteratingPhylogenyParser p,
- 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( p, species_tree, algorithm, rerooting, outgroup, first, last, produce_log, verbose );
+ private final static void calculateOrthologTable( final Phylogeny g, final boolean sort, final int counter )
+ throws RIOException {
+ if ( counter == 0 ) {
+ final List<String> labels = new ArrayList<String>();
+ final Set<String> labels_set = new HashSet<String>();
+ for( final PhylogenyNode n : g.getExternalNodes() ) {
+ final String label = obtainLabel( labels_set, n );
+ labels_set.add( label );
+ labels.add( label );
+ }
+ if ( sort ) {
+ Collections.sort( labels );
+ }
+ _m = new IntMatrix( labels );
+ }
+ updateCounts( _m, counter, g );
}
- private final static void checkPreconditions( final Phylogeny[] gene_trees,
+ private final static void checkPreconditions( final IteratingPhylogenyParser p,
final Phylogeny species_tree,
final REROOTING rerooting,
final String outgroup,
final int first,
- final int last ) throws RIOException {
+ final int last ) throws RIOException, IOException {
+ final Phylogeny g0 = p.next();
+ if ( ( g0 == null ) || g0.isEmpty() ) {
+ throw new RIOException( "input file does not seem to contain any gene trees" );
+ }
+ if ( g0.getNumberOfExternalNodes() < 2 ) {
+ throw new RIOException( "input file does not seem to contain any useable gene trees" );
+ }
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 ) ) ) {
+ && ( ( last < first ) || ( 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 + ")" );
+ + last );
}
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 ) ) {
+ if ( ( rerooting == REROOTING.MIDPOINT ) && ( PhylogenyMethods.calculateMaxDistanceToRoot( g0 ) <= 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 );
+ g0.getNode( outgroup );
}
catch ( final IllegalArgumentException e ) {
throw new RIOException( "cannot perform re-rooting by outgroup: " + e.getLocalizedMessage() );
}
}
- private final static void checkPreconditions( final IteratingPhylogenyParser p,
+ 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, IOException {
- final Phylogeny g0 = p.next();
- if ( ( g0 == null ) || g0.isEmpty() ) {
- throw new RIOException( "input file does not seem to contain any gene trees" );
- }
- if ( g0.getNumberOfExternalNodes() < 2 ) {
- throw new RIOException( "input file does not seem to contain any useable gene trees" );
- }
+ 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 < 0 ) || ( first < 0 ) ) ) {
+ && ( ( 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 );
+ + 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( g0 ) <= 0 ) ) {
+ 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 {
- g0.getNode( outgroup );
+ gene_trees[ 0 ].getNode( outgroup );
}
catch ( final IllegalArgumentException e ) {
throw new RIOException( "cannot perform re-rooting by outgroup: " + e.getLocalizedMessage() );
}
}
+ private final static String obtainLabel( final Set<String> labels_set, final PhylogenyNode n ) throws RIOException {
+ String label;
+ if ( n.getNodeData().isHasSequence() && !ForesterUtil.isEmpty( n.getNodeData().getSequence().getName() ) ) {
+ label = n.getNodeData().getSequence().getName();
+ }
+ else if ( n.getNodeData().isHasSequence() && !ForesterUtil.isEmpty( n.getNodeData().getSequence().getSymbol() ) ) {
+ label = n.getNodeData().getSequence().getSymbol();
+ }
+ else if ( n.getNodeData().isHasSequence()
+ && !ForesterUtil.isEmpty( n.getNodeData().getSequence().getGeneName() ) ) {
+ label = n.getNodeData().getSequence().getGeneName();
+ }
+ else if ( !ForesterUtil.isEmpty( n.getName() ) ) {
+ label = n.getName();
+ }
+ else {
+ throw new RIOException( "node " + n + " has no appropriate label" );
+ }
+ if ( labels_set.contains( label ) ) {
+ throw new RIOException( "label " + label + " is not unique" );
+ }
+ return label;
+ }
+
private final static Phylogeny[] parseGeneTrees( final File gene_trees_file ) throws FileNotFoundException,
IOException {
final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
final NHXParser nhx = ( NHXParser ) p;
nhx.setReplaceUnderscores( false );
nhx.setIgnoreQuotes( true );
- nhx.setTaxonomyExtraction( NHXParser.TAXONOMY_EXTRACTION.YES );
+ nhx.setTaxonomyExtraction( TAXONOMY_EXTRACTION.AGGRESSIVE );
}
else if ( p instanceof NexusPhylogeniesParser ) {
final NexusPhylogeniesParser nex = ( NexusPhylogeniesParser ) p;
nex.setReplaceUnderscores( false );
nex.setIgnoreQuotes( true );
- nex.setTaxonomyExtraction( TAXONOMY_EXTRACTION.YES );
+ nex.setTaxonomyExtraction( TAXONOMY_EXTRACTION.AGGRESSIVE );
}
return factory.create( gene_trees_file, p );
}
}
}
+ private final static void updateCounts( final IntMatrix m, final int counter, final Phylogeny g )
+ throws RIOException {
+ PhylogenyMethods.preOrderReId( g );
+ final HashMap<String, PhylogenyNode> map = PhylogenyMethods.createNameToExtNodeMap( g );
+ for( int x = 0; x < m.size(); ++x ) {
+ final String mx = m.getLabel( x );
+ final PhylogenyNode nx = map.get( mx );
+ if ( nx == null ) {
+ throw new RIOException( "node \"" + mx + "\" not present in gene tree #" + counter );
+ }
+ String my;
+ PhylogenyNode ny;
+ for( int y = 0; y < m.size(); ++y ) {
+ my = m.getLabel( y );
+ ny = map.get( my );
+ if ( ny == null ) {
+ throw new RIOException( "node \"" + my + "\" not present in gene tree #" + counter );
+ }
+ if ( !PhylogenyMethods.calculateLCAonTreeWithIdsInPreOrder( nx, ny ).isDuplication() ) {
+ m.inreaseByOne( x, y );
+ }
+ }
+ }
+ }
+
public enum REROOTING {
NONE, BY_ALGORITHM, MIDPOINT, OUTGROUP;
}
git://source.jalview.org / jalview.git / blobdiff