import java.util.TreeMap;
import java.util.TreeSet;
-import org.forester.io.parsers.PhylogenyParser;
-import org.forester.io.parsers.nhx.NHXParser;
+import org.forester.io.parsers.nhx.NHXParser.TAXONOMY_EXTRACTION;
import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException;
import org.forester.io.parsers.phyloxml.PhyloXmlParser;
-import org.forester.io.parsers.util.ParserUtils;
import org.forester.io.writers.PhylogenyWriter;
import org.forester.phylogeny.Phylogeny;
import org.forester.phylogeny.PhylogenyMethods;
import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
import org.forester.phylogeny.factories.PhylogenyFactory;
import org.forester.sdi.GSDI;
+import org.forester.sdi.GSDII;
import org.forester.sdi.GSDIR;
-import org.forester.sdi.SDI;
-import org.forester.sdi.SDI.ALGORITHM;
-import org.forester.sdi.SDI.TaxonomyComparisonBase;
import org.forester.sdi.SDIException;
-import org.forester.sdi.SDIse;
+import org.forester.sdi.SDIutil;
+import org.forester.sdi.SDIutil.ALGORITHM;
import org.forester.util.CommandLineArguments;
import org.forester.util.EasyWriter;
import org.forester.util.ForesterConstants;
final static public boolean REPLACE_UNDERSCORES_IN_NH_SPECIES_TREE = true;
final static private String ALLOW_STRIPPING_OF_GENE_TREE_OPTION = "g";
- final static private String SDISE_OPTION = "b";
final static private String GSDIR_OPTION = "r";
final static private String MOST_PARSIMONIOUS_OPTION = "m";
final static private String GUESS_FORMAT_OF_SPECIES_TREE = "q";
System.exit( -1 );
}
final List<String> allowed_options = new ArrayList<String>();
- allowed_options.add( gsdi.SDISE_OPTION );
allowed_options.add( gsdi.GSDIR_OPTION );
allowed_options.add( gsdi.GUESS_FORMAT_OF_SPECIES_TREE );
allowed_options.add( gsdi.MOST_PARSIMONIOUS_OPTION );
if ( cla.isOptionSet( gsdi.GSDIR_OPTION ) ) {
base_algorithm = ALGORITHM.GSDIR;
}
- else if ( cla.isOptionSet( gsdi.SDISE_OPTION ) ) {
- base_algorithm = ALGORITHM.SDI;
- }
if ( cla.isOptionSet( gsdi.MOST_PARSIMONIOUS_OPTION ) ) {
if ( base_algorithm == ALGORITHM.SDI ) {
ForesterUtil.fatalError( gsdi.PRG_NAME, "Cannot use most parsimonious duplication mode with SDI" );
gene_tree = factory.create( gene_tree_file, new PhyloXmlParser() )[ 0 ];
}
catch ( final IOException e ) {
- fatalError( "ERROR",
- "Failed to read gene tree from [" + gene_tree_file + "]: " + e.getMessage(),
+ fatalError( "error",
+ "failed to read gene tree from [" + gene_tree_file + "]: " + e.getMessage(),
log_writer );
}
try {
- final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
- final PhylogenyParser p = ParserUtils.createParserDependingOnFileType( species_tree_file, true );
- if ( p instanceof PhyloXmlParser ) {
- species_tree = factory.create( species_tree_file, p )[ 0 ];
- }
- else {
- if ( REPLACE_UNDERSCORES_IN_NH_SPECIES_TREE && ( p instanceof NHXParser ) ) {
- ( ( NHXParser ) p ).setReplaceUnderscores( true );
- }
- species_tree = factory.create( species_tree_file, p )[ 0 ];
- final TaxonomyComparisonBase comp_base = GSDI.determineTaxonomyComparisonBase( gene_tree );
- switch ( comp_base ) {
- case SCIENTIFIC_NAME:
- try {
- PhylogenyMethods
- .transferNodeNameToField( species_tree,
- PhylogenyMethods.PhylogenyNodeField.TAXONOMY_SCIENTIFIC_NAME,
- true );
- }
- catch ( final PhyloXmlDataFormatException e ) {
- fatalError( "USER ERROR", "Failed to transfer general node name to scientific name, in ["
- + species_tree_file + "]: " + e.getMessage(), log_writer );
- }
- break;
- case CODE:
- try {
- PhylogenyMethods
- .transferNodeNameToField( species_tree,
- PhylogenyMethods.PhylogenyNodeField.TAXONOMY_CODE,
- true );
- }
- catch ( final PhyloXmlDataFormatException e ) {
- fatalError( "USER ERROR", "Failed to transfer general node name to taxonomy code, in ["
- + species_tree_file + "]: " + e.getMessage(), log_writer );
- }
- break;
- case ID:
- try {
- PhylogenyMethods.transferNodeNameToField( species_tree,
- PhylogenyMethods.PhylogenyNodeField.TAXONOMY_ID,
- true );
- }
- catch ( final PhyloXmlDataFormatException e ) {
- fatalError( "USER ERROR", "Failed to transfer general node name to taxonomy id, in ["
- + species_tree_file + "]: " + e.getMessage(), log_writer );
- }
- break;
- default:
- fatalError( "UNEXPECTED ERROR", "unable to determine comparison base", log_writer );
- }
- }
+ species_tree = SDIutil.parseSpeciesTree( gene_tree,
+ species_tree_file,
+ REPLACE_UNDERSCORES_IN_NH_SPECIES_TREE,
+ true,
+ TAXONOMY_EXTRACTION.NO );
+ }
+ catch ( final PhyloXmlDataFormatException e ) {
+ fatalError( "user error",
+ "failed to transfer general node name, in [" + species_tree_file + "]: " + e.getMessage(),
+ log_writer );
+ }
+ catch ( final SDIException e ) {
+ fatalError( "user error", e.getMessage(), log_writer );
}
catch ( final IOException e ) {
- fatalError( "ERROR",
+ fatalError( "error",
"Failed to read species tree from [" + species_tree_file + "]: " + e.getMessage(),
log_writer );
}
+ ( ForesterUtil.isEmpty( species_tree.getName() ) ? "" : gene_tree.getName() ) );
System.out.println( "Species tree name : "
+ ( ForesterUtil.isEmpty( species_tree.getName() ) ? "" : gene_tree.getName() ) );
- SDI sdi = null;
+ GSDII gsdii = null;
final long start_time = new Date().getTime();
try {
- if ( ( base_algorithm == ALGORITHM.GSDI ) || ( base_algorithm == ALGORITHM.GSDIR ) ) {
- if ( base_algorithm == ALGORITHM.GSDI ) {
- System.out.println( "Algorithm : GSDI" );
- log_writer.println( "Algorithm : GSDI" );
- }
- else if ( base_algorithm == ALGORITHM.GSDIR ) {
- System.out.println( "Algorithm : GSDIR" );
- log_writer.println( "Algorithm : GSDIR" );
- }
- System.out.println( "Use most parsimonous duplication model : " + most_parsimonous_duplication_model );
- System.out.println( "Allow stripping of gene tree nodes : " + allow_stripping_of_gene_tree );
- log_writer.println( "Use most parsimonous duplication model : " + most_parsimonous_duplication_model );
- log_writer.println( "Allow stripping of gene tree nodes : " + allow_stripping_of_gene_tree );
- log_writer.flush();
- if ( base_algorithm == ALGORITHM.GSDI ) {
- sdi = new GSDI( gene_tree,
- species_tree,
- most_parsimonous_duplication_model,
- allow_stripping_of_gene_tree,
- true );
- }
- else if ( base_algorithm == ALGORITHM.GSDIR ) {
- sdi = new GSDIR( gene_tree, species_tree, allow_stripping_of_gene_tree, true );
- }
+ if ( base_algorithm == ALGORITHM.GSDI ) {
+ System.out.println( "Algorithm : GSDI" );
+ log_writer.println( "Algorithm : GSDI" );
}
- else {
- System.out.println();
- System.out.println( "Algorithm : SDI" );
- log_writer.println( "Algorithm : SDI" );
- log_writer.flush();
- sdi = new SDIse( gene_tree, species_tree );
+ else if ( base_algorithm == ALGORITHM.GSDIR ) {
+ System.out.println( "Algorithm : GSDIR" );
+ log_writer.println( "Algorithm : GSDIR" );
+ }
+ System.out.println( "Use most parsimonous duplication model : " + most_parsimonous_duplication_model );
+ System.out.println( "Allow stripping of gene tree nodes : " + allow_stripping_of_gene_tree );
+ log_writer.println( "Use most parsimonous duplication model : " + most_parsimonous_duplication_model );
+ log_writer.println( "Allow stripping of gene tree nodes : " + allow_stripping_of_gene_tree );
+ log_writer.flush();
+ if ( base_algorithm == ALGORITHM.GSDI ) {
+ gsdii = new GSDI( gene_tree,
+ species_tree,
+ most_parsimonous_duplication_model,
+ allow_stripping_of_gene_tree,
+ true );
+ }
+ else if ( base_algorithm == ALGORITHM.GSDIR ) {
+ gsdii = new GSDIR( gene_tree, species_tree, allow_stripping_of_gene_tree, true );
}
}
catch ( final SDIException e ) {
catch ( final IOException e ) {
fatalError( "error", e.toString(), log_writer );
}
+ catch ( final OutOfMemoryError e ) {
+ ForesterUtil.outOfMemoryError( e );
+ }
catch ( final Exception e ) {
e.printStackTrace();
fatalError( "unexpected error", e.toString(), log_writer );
+ "ms" );
log_writer.println( "Running time (excluding I/O) : " + ( new Date().getTime() - start_time )
+ "ms" );
- if ( ( base_algorithm == ALGORITHM.GSDI ) ) {
- final GSDI gsdi = ( GSDI ) sdi;
- System.out.println( "Mapping based on : " + gsdi.getTaxCompBase() );
- log_writer.println( "Mapping based on : " + gsdi.getTaxCompBase() );
- }
+ System.out.println( "Mapping based on : " + gsdii.getTaxCompBase() );
+ log_writer.println( "Mapping based on : " + gsdii.getTaxCompBase() );
if ( ( base_algorithm == ALGORITHM.GSDIR ) ) {
- final GSDIR gsdir = ( GSDIR ) sdi;
- System.out.println( "Mapping based on : " + gsdir.getTaxCompBase() );
- log_writer.println( "Mapping based on : " + gsdir.getTaxCompBase() );
- System.out.println( "Minimal duplications sum : " + gsdir.getMinDuplicationsSum() );
- log_writer.println( "Minimal duplications sum : " + gsdir.getMinDuplicationsSum() );
+ final GSDIR gsdir = ( GSDIR ) gsdii;
System.out.println( "Duplications sum statistics : " + gsdir.getMinDuplicationsSum() );
log_writer.println( "Duplications sum statistics : " + gsdir.getMinDuplicationsSum() );
}
final PhylogenyWriter writer = new PhylogenyWriter();
if ( base_algorithm == ALGORITHM.GSDIR ) {
writer.toPhyloXML( out_file,
- ( ( GSDIR ) sdi ).getMinDuplicationsSumGeneTrees(),
+ ( ( GSDIR ) gsdii ).getMinDuplicationsSumGeneTrees(),
0,
ForesterUtil.LINE_SEPARATOR );
}
}
System.out.println( "Wrote resulting gene tree to : " + out_file.getCanonicalPath() );
log_writer.println( "Wrote resulting gene tree to : " + out_file.getCanonicalPath() );
- if ( base_algorithm == ALGORITHM.SDI ) {
- sdi.computeMappingCostL();
- System.out.println( "Mapping cost : " + sdi.computeMappingCostL() );
- log_writer.println( "Mapping cost : " + sdi.computeMappingCostL() );
- }
- else if ( ( base_algorithm == ALGORITHM.GSDI ) || ( base_algorithm == ALGORITHM.GSDIR ) ) {
- final GSDI gsdi = ( GSDI ) sdi;
- final File species_tree_used_file = new File( ForesterUtil.removeSuffix( out_file.toString() )
- + SUFFIX_FOR_SPECIES_TREE_USED );
- try {
- final PhylogenyWriter writer = new PhylogenyWriter();
- writer.toPhyloXML( species_tree_used_file, gsdi.getSpeciesTree(), 0 );
- }
- catch ( final IOException e ) {
- ForesterUtil.fatalError( PRG_NAME, "Failed to write to [" + species_tree_used_file.getCanonicalPath()
- + "]: " + e.getMessage() );
- }
- System.out.println( "Wrote (stripped) species tree to : "
- + species_tree_used_file.getCanonicalPath() );
- log_writer.println( "Wrote (stripped) species tree to : "
- + species_tree_used_file.getCanonicalPath() );
- if ( ( gsdi.getReMappedScientificNamesFromGeneTree() != null )
- && !gsdi.getReMappedScientificNamesFromGeneTree().isEmpty() ) {
- System.out.println( "Number of gene tree species remapped : "
- + gsdi.getReMappedScientificNamesFromGeneTree().size() );
- log_writer.println( "Number of gene tree species remapped : "
- + gsdi.getReMappedScientificNamesFromGeneTree().size() );
- writeToRemappedFile( out_file, gsdi.getReMappedScientificNamesFromGeneTree(), log_writer );
- }
+ final File species_tree_used_file = new File( ForesterUtil.removeSuffix( out_file.toString() )
+ + SUFFIX_FOR_SPECIES_TREE_USED );
+ try {
+ final PhylogenyWriter writer = new PhylogenyWriter();
+ writer.toPhyloXML( species_tree_used_file, species_tree, 0 );
+ }
+ catch ( final IOException e ) {
+ ForesterUtil.fatalError( PRG_NAME, "Failed to write to [" + species_tree_used_file.getCanonicalPath()
+ + "]: " + e.getMessage() );
+ }
+ System.out.println( "Wrote (stripped) species tree to : " + species_tree_used_file.getCanonicalPath() );
+ log_writer.println( "Wrote (stripped) species tree to : " + species_tree_used_file.getCanonicalPath() );
+ if ( ( gsdii.getReMappedScientificNamesFromGeneTree() != null )
+ && !gsdii.getReMappedScientificNamesFromGeneTree().isEmpty() ) {
+ System.out.println( "Number of gene tree species remapped : "
+ + gsdii.getReMappedScientificNamesFromGeneTree().size() );
+ log_writer.println( "Number of gene tree species remapped : "
+ + gsdii.getReMappedScientificNamesFromGeneTree().size() );
+ writeToRemappedFile( out_file, gsdii.getReMappedScientificNamesFromGeneTree(), log_writer );
}
System.out.println( "Number of external nodes in gene tree : " + gene_tree.getNumberOfExternalNodes() );
log_writer.println( "Number of external nodes in gene tree : " + gene_tree.getNumberOfExternalNodes() );
- System.out.println( "Number of external nodes in species tree : "
- + sdi.getSpeciesTree().getNumberOfExternalNodes() );
- log_writer.println( "Number of external nodes in species tree : "
- + sdi.getSpeciesTree().getNumberOfExternalNodes() );
- if ( ( base_algorithm == ALGORITHM.GSDI ) ) {
- final GSDI gsdi = ( GSDI ) sdi;
- final int poly = PhylogenyMethods.countNumberOfPolytomies( gsdi.getSpeciesTree() );
- System.out.println( "Number of polytomies in species tree : " + poly );
- log_writer.println( "Number of polytomies in species tree : " + poly );
- System.out.println( "External nodes stripped from gene tree : "
- + gsdi.getStrippedExternalGeneTreeNodes().size() );
- log_writer.println( "External nodes stripped from gene tree : "
- + gsdi.getStrippedExternalGeneTreeNodes().size() );
- System.out.println( "External nodes stripped from species tree: "
- + gsdi.getStrippedSpeciesTreeNodes().size() );
- log_writer.println( "External nodes stripped from species tree: "
- + gsdi.getStrippedSpeciesTreeNodes().size() );
- }
+ System.out.println( "Number of external nodes in species tree : " + species_tree.getNumberOfExternalNodes() );
+ log_writer.println( "Number of external nodes in species tree : " + species_tree.getNumberOfExternalNodes() );
+ final int poly = PhylogenyMethods.countNumberOfPolytomies( species_tree );
+ System.out.println( "Number of polytomies in species tree : " + poly );
+ log_writer.println( "Number of polytomies in species tree : " + poly );
+ System.out.println( "External nodes stripped from gene tree : "
+ + gsdii.getStrippedExternalGeneTreeNodes().size() );
+ log_writer.println( "External nodes stripped from gene tree : "
+ + gsdii.getStrippedExternalGeneTreeNodes().size() );
+ System.out.println( "External nodes stripped from species tree: " + gsdii.getStrippedSpeciesTreeNodes().size() );
+ log_writer.println( "External nodes stripped from species tree: " + gsdii.getStrippedSpeciesTreeNodes().size() );
System.out.println();
- System.out.println( "Number of duplications : " + sdi.getDuplicationsSum() );
- log_writer.println( "Number of duplications : " + sdi.getDuplicationsSum() );
- if ( ( base_algorithm == ALGORITHM.GSDI ) ) {
- final GSDI gsdi = ( GSDI ) sdi;
+ System.out.println( "Number of speciations : " + gsdii.getSpeciationsSum() );
+ log_writer.println( "Number of speciations : " + gsdii.getSpeciationsSum() );
+ if ( ( base_algorithm == ALGORITHM.GSDIR ) ) {
+ final GSDIR gsdir = ( GSDIR ) gsdii;
+ System.out.println( "Minimal number of duplications : " + gsdir.getMinDuplicationsSum() );
+ log_writer.println( "Minimal number of duplications : " + gsdir.getMinDuplicationsSum() );
+ }
+ else if ( ( base_algorithm == ALGORITHM.GSDI ) ) {
+ final GSDI gsdi = ( GSDI ) gsdii;
+ System.out.println( "Number of duplications : " + gsdi.getDuplicationsSum() );
+ log_writer.println( "Number of duplications : " + gsdi.getDuplicationsSum() );
if ( !most_parsimonous_duplication_model ) {
final int u = gsdi.getSpeciationOrDuplicationEventsSum();
System.out.println( "Number of potential duplications : " + u );
log_writer.println( "Number of potential duplications : " + u );
}
- System.out.println( "Number of speciations : " + gsdi.getSpeciationsSum() );
- log_writer.println( "Number of speciations : " + gsdi.getSpeciationsSum() );
- log_writer.println();
- printMappedNodesToLog( log_writer, gsdi );
- log_writer.println();
- printStrippedGeneTreeNodesToLog( log_writer, gsdi );
}
+ log_writer.println();
+ printMappedNodesToLog( log_writer, gsdii );
+ log_writer.println();
+ printStrippedGeneTreeNodesToLog( log_writer, gsdii );
System.out.println();
System.out.println( "Wrote log to : " + log_file.getCanonicalPath() );
System.out.println();
log_writer.close();
}
- private static void writeToRemappedFile( final File out_file,
- final SortedSet<String> remapped,
- final EasyWriter log_writer ) throws IOException {
- final File file = new File( ForesterUtil.removeSuffix( out_file.toString() ) + REMAPPED_SUFFIX );
- final EasyWriter remapped_writer = ForesterUtil.createEasyWriter( file );
- for( final String s : remapped ) {
- remapped_writer.println( s );
- }
- remapped_writer.close();
- System.out.println( "Wrote remapped gene tree species to : " + file.getCanonicalPath() );
- log_writer.println( "Wrote remapped gene tree species to : " + file.getCanonicalPath() );
- }
-
- private static void printMappedNodesToLog( final EasyWriter log_writer, final GSDI gsdi ) throws IOException {
- final SortedSet<String> ss = new TreeSet<String>();
- for( final PhylogenyNode n : gsdi.getMappedExternalSpeciesTreeNodes() ) {
- ss.add( n.toString() );
- }
- log_writer.println( "The following " + ss.size() + " species were used: " );
- for( final String s : ss ) {
- log_writer.println( " " + s );
- }
- }
-
private static void fatalError( final String type, final String msg, final EasyWriter log_writer ) {
try {
log_writer.flush();
ForesterUtil.fatalError( gsdi.PRG_NAME, msg );
}
- private static void printStrippedGeneTreeNodesToLog( final EasyWriter log_writer, final GSDI gsdi )
- throws IOException {
- final SortedMap<String, Integer> sm = new TreeMap<String, Integer>();
- for( final PhylogenyNode n : gsdi.getStrippedExternalGeneTreeNodes() ) {
- final String s = n.toString();
- if ( sm.containsKey( s ) ) {
- sm.put( s, sm.get( s ) + 1 );
- }
- else {
- sm.put( s, 1 );
- }
- }
- log_writer.println( "The following " + sm.size() + " nodes were stripped from the gene tree: " );
- for( final String s : sm.keySet() ) {
- final int count = sm.get( s );
- if ( count == 1 ) {
- log_writer.println( " " + s );
- }
- else {
- log_writer.println( " " + s + " [" + count + "]" );
- }
- }
- }
-
private static void print_help() {
System.out.println( "Usage: " + gsdi.PRG_NAME
+ " [-options] <gene tree in phyloXML format> <species tree> <outfile>" );
System.out.println( " as potential duplications due to polytomies in the species tree" );
System.out.println( " -" + gsdi.GUESS_FORMAT_OF_SPECIES_TREE
+ ": to allow species tree in other formats than phyloXML (i.e. Newick, NHX, Nexus)" );
- System.out.println( " -" + gsdi.SDISE_OPTION
- + ": to use SDIse algorithm instead of GSDI algorithm (for binary species trees)" );
System.out.println( " -" + gsdi.GSDIR_OPTION
+ ": to use GSDIR algorithm instead of GSDI algorithm (re-rooting)" );
System.out.println();
+ " gene_tree.xml tree_of_life.xml out.xml" );
System.out.println();
}
+
+ private static void printMappedNodesToLog( final EasyWriter log_writer, final GSDII gsdi ) throws IOException {
+ final SortedSet<String> ss = new TreeSet<String>();
+ for( final PhylogenyNode n : gsdi.getMappedExternalSpeciesTreeNodes() ) {
+ ss.add( n.toString() );
+ }
+ log_writer.println( "The following " + ss.size() + " species were used: " );
+ for( final String s : ss ) {
+ log_writer.println( " " + s );
+ }
+ }
+
+ private static void printStrippedGeneTreeNodesToLog( final EasyWriter log_writer, final GSDII gsdi )
+ throws IOException {
+ final SortedMap<String, Integer> sm = new TreeMap<String, Integer>();
+ for( final PhylogenyNode n : gsdi.getStrippedExternalGeneTreeNodes() ) {
+ final String s = n.toString();
+ if ( sm.containsKey( s ) ) {
+ sm.put( s, sm.get( s ) + 1 );
+ }
+ else {
+ sm.put( s, 1 );
+ }
+ }
+ log_writer.println( "The following " + sm.size() + " nodes were stripped from the gene tree: " );
+ for( final String s : sm.keySet() ) {
+ final int count = sm.get( s );
+ if ( count == 1 ) {
+ log_writer.println( " " + s );
+ }
+ else {
+ log_writer.println( " " + s + " [" + count + "]" );
+ }
+ }
+ }
+
+ private static void writeToRemappedFile( final File out_file,
+ final SortedSet<String> remapped,
+ final EasyWriter log_writer ) throws IOException {
+ final File file = new File( ForesterUtil.removeSuffix( out_file.toString() ) + REMAPPED_SUFFIX );
+ final EasyWriter remapped_writer = ForesterUtil.createEasyWriter( file );
+ for( final String s : remapped ) {
+ remapped_writer.println( s );
+ }
+ remapped_writer.close();
+ System.out.println( "Wrote remapped gene tree species to : " + file.getCanonicalPath() );
+ log_writer.println( "Wrote remapped gene tree species to : " + file.getCanonicalPath() );
+ }
}
git://source.jalview.org / jalview.git / blobdiff