// Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
//
// Contact: phylosoft @ gmail . com
-// WWW: www.phylosoft.org/forester
+// WWW: https://sites.google.com/site/cmzmasek/home/software/forester
package org.forester.application;
import java.io.File;
import java.io.IOException;
+import java.math.RoundingMode;
import java.util.ArrayList;
import java.util.List;
import org.forester.datastructures.IntMatrix;
+import org.forester.io.parsers.IteratingPhylogenyParser;
+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.phyloxml.PhyloXmlParser;
+import org.forester.io.parsers.util.ParserUtils;
+import org.forester.io.writers.PhylogenyWriter;
+import org.forester.phylogeny.Phylogeny;
import org.forester.rio.RIO;
import org.forester.rio.RIO.REROOTING;
import org.forester.rio.RIOException;
public class rio {
- final static private String PRG_NAME = "rio";
- final static private String PRG_VERSION = "4.000 beta 3";
- final static private String PRG_DATE = "2012.12.19";
- final static private String E_MAIL = "czmasek@burnham.org";
- final static private String WWW = "www.phylosoft.org/forester/";
- final static private String HELP_OPTION_1 = "help";
- final static private String HELP_OPTION_2 = "h";
- final static private String GT_FIRST = "f";
- final static private String GT_LAST = "l";
- final static private String REROOTING_OPT = "r";
- final static private String OUTGROUP = "o";
- final static private String USE_SDIR = "b";
+ final static private String PRG_NAME = "rio";
+ final static private String PRG_VERSION = "4.000 beta 10";
+ final static private String PRG_DATE = "140211";
+ final static private String E_MAIL = "phyloxml@gmail.com";
+ final static private String WWW = "https://sites.google.com/site/cmzmasek/home/software/forester";
+ final static private String HELP_OPTION_1 = "help";
+ final static private String HELP_OPTION_2 = "h";
+ final static private String GT_FIRST = "f";
+ final static private String GT_LAST = "l";
+ final static private String REROOTING_OPT = "r";
+ final static private String OUTGROUP = "o";
+ final static private String RETURN_SPECIES_TREE = "s";
+ final static private String RETURN_BEST_GENE_TREE = "g";
+ final static private String USE_SDIR = "b";
+ final static private String TRANSFER_TAXONOMY_OPTION = "t";
public static void main( final String[] args ) {
ForesterUtil.printProgramInformation( PRG_NAME,
if ( cla.isOptionSet( HELP_OPTION_1 ) || cla.isOptionSet( HELP_OPTION_2 ) || ( args.length == 0 ) ) {
printHelp();
}
- if ( ( args.length < 3 ) || ( args.length > 9 ) ) {
+ if ( ( args.length < 3 ) || ( args.length > 11 ) || ( cla.getNumberOfNames() < 3 ) ) {
System.out.println();
System.out.println( "error: incorrect number of arguments" );
System.out.println();
allowed_options.add( REROOTING_OPT );
allowed_options.add( OUTGROUP );
allowed_options.add( USE_SDIR );
+ allowed_options.add( RETURN_SPECIES_TREE );
+ allowed_options.add( RETURN_BEST_GENE_TREE );
+ allowed_options.add( TRANSFER_TAXONOMY_OPTION );
final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
if ( dissallowed_options.length() > 0 ) {
ForesterUtil.fatalError( "unknown option(s): " + dissallowed_options );
ForesterUtil.fatalError( "attempt to set range (0-based) of gene to analyze to: from " + gt_first + " to "
+ gt_last );
}
+ File return_species_tree = null;
+ if ( !sdir && cla.isOptionSet( RETURN_SPECIES_TREE ) ) {
+ if ( !cla.isOptionHasAValue( RETURN_SPECIES_TREE ) ) {
+ ForesterUtil.fatalError( "no value for -" + RETURN_SPECIES_TREE );
+ }
+ final String s = cla.getOptionValueAsCleanString( RETURN_SPECIES_TREE );
+ return_species_tree = new File( s );
+ if ( return_species_tree.exists() ) {
+ ForesterUtil.fatalError( "\"" + return_species_tree + "\" already exists" );
+ }
+ }
+ File return_gene_tree = null;
+ if ( !sdir && cla.isOptionSet( RETURN_BEST_GENE_TREE ) ) {
+ if ( !cla.isOptionHasAValue( RETURN_BEST_GENE_TREE ) ) {
+ ForesterUtil.fatalError( "no value for -" + RETURN_BEST_GENE_TREE );
+ }
+ final String s = cla.getOptionValueAsCleanString( RETURN_BEST_GENE_TREE );
+ return_gene_tree = new File( s );
+ if ( return_gene_tree.exists() ) {
+ ForesterUtil.fatalError( "\"" + return_gene_tree + "\" already exists" );
+ }
+ }
+ boolean transfer_taxonomy = false;
+ if ( !sdir && cla.isOptionSet( TRANSFER_TAXONOMY_OPTION ) ) {
+ if ( return_gene_tree == null ) {
+ ForesterUtil.fatalError( "no point in transferring taxonomy data without returning best gene tree" );
+ }
+ transfer_taxonomy = true;
+ }
ForesterUtil.fatalErrorIfFileNotReadable( gene_trees_file );
ForesterUtil.fatalErrorIfFileNotReadable( species_tree_file );
if ( orthology_outtable.exists() ) {
else {
System.out.println( "Non binary species tree : disallowed" );
}
+ if ( return_species_tree != null ) {
+ System.out.println( "Write used species tree to: " + return_species_tree );
+ }
+ if ( return_gene_tree != null ) {
+ System.out.println( "Write best gene tree to : " + return_gene_tree );
+ System.out.println( "Transfer taxonomic data : " + transfer_taxonomy );
+ }
time = System.currentTimeMillis();
- // Phylogeny species_tree = null;
- // try {
- // final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
- // species_tree = factory.create( species_tree_file, new PhyloXmlParser() )[ 0 ];
- // }
- // catch ( final Exception e ) {
- // e.printStackTrace();
- // System.exit( -1 );
- // }
final ALGORITHM algorithm;
if ( sdir ) {
algorithm = ALGORITHM.SDIR;
algorithm = ALGORITHM.GSDIR;
}
try {
- final RIO rio = RIO.executeAnalysis( gene_trees_file,
- species_tree_file,
- algorithm,
- rerooting,
- outgroup,
- gt_first,
- gt_last,
- logfile != null,
- true );
+ final RIO rio;
+ boolean iterating = false;
+ final PhylogenyParser p = ParserUtils.createParserDependingOnFileType( gene_trees_file, true );
+ if ( p instanceof PhyloXmlParser ) {
+ rio = RIO.executeAnalysis( gene_trees_file,
+ species_tree_file,
+ algorithm,
+ rerooting,
+ outgroup,
+ gt_first,
+ gt_last,
+ logfile != null,
+ true,
+ transfer_taxonomy );
+ }
+ else {
+ iterating = true;
+ if ( p instanceof NHXParser ) {
+ final NHXParser nhx = ( NHXParser ) p;
+ nhx.setReplaceUnderscores( false );
+ nhx.setIgnoreQuotes( true );
+ 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.AGGRESSIVE );
+ }
+ else {
+ throw new RuntimeException( "unknown parser type: " + p );
+ }
+ final IteratingPhylogenyParser ip = ( IteratingPhylogenyParser ) p;
+ ip.setSource( gene_trees_file );
+ rio = RIO.executeAnalysis( ip,
+ species_tree_file,
+ algorithm,
+ rerooting,
+ outgroup,
+ gt_first,
+ gt_last,
+ logfile != null,
+ true,
+ transfer_taxonomy );
+ }
if ( algorithm == ALGORITHM.GSDIR ) {
System.out.println( "Taxonomy linking based on : " + rio.getGSDIRtaxCompBase() );
}
- tableOutput( orthology_outtable, rio );
+ final IntMatrix m;
+ if ( iterating ) {
+ m = rio.getOrthologTable();
+ }
+ else {
+ m = RIO.calculateOrthologTable( rio.getAnalyzedGeneTrees(), true );
+ }
+ final BasicDescriptiveStatistics stats = rio.getDuplicationsStatistics();
+ writeTable( orthology_outtable, stats.getN(), m );
if ( ( algorithm != ALGORITHM.SDIR ) && ( logfile != null ) ) {
writeLogFile( logfile,
rio,
PRG_DATE,
ForesterUtil.getForesterLibraryInformation() );
}
- final BasicDescriptiveStatistics stats = rio.getDuplicationsStatistics();
+ if ( return_species_tree != null ) {
+ writeTree( rio.getSpeciesTree(), return_species_tree, "Wrote (stripped) species tree to" );
+ }
+ if ( return_gene_tree != null ) {
+ String tt = "";
+ if ( transfer_taxonomy ) {
+ tt = "(with transferred taxonomic data) ";
+ }
+ writeTree( rio.getMinDuplicationsGeneTree(),
+ return_gene_tree,
+ "Wrote (one) minimal duplication gene tree " + tt + "to" );
+ }
final java.text.DecimalFormat df = new java.text.DecimalFormat( "0.#" );
System.out.println( "Mean number of duplications : " + df.format( stats.arithmeticMean() ) + " (sd: "
+ df.format( stats.sampleStandardDeviation() ) + ") ("
- + df.format( 100.0 * stats.arithmeticMean() / rio.getIntNodesOfAnalyzedGeneTrees() ) + "%)" );
+ + df.format( ( 100.0 * stats.arithmeticMean() ) / rio.getIntNodesOfAnalyzedGeneTrees() ) + "%)" );
if ( stats.getN() > 3 ) {
System.out.println( "Median number of duplications: " + df.format( stats.median() ) + " ("
- + df.format( 100.0 * stats.median() / rio.getIntNodesOfAnalyzedGeneTrees() ) + "%)" );
+ + df.format( ( 100.0 * stats.median() ) / rio.getIntNodesOfAnalyzedGeneTrees() ) + "%)" );
}
System.out.println( "Minimum duplications : " + ( int ) stats.getMin() + " ("
- + df.format( 100.0 * stats.getMin() / rio.getIntNodesOfAnalyzedGeneTrees() ) + "%)" );
+ + df.format( ( 100.0 * stats.getMin() ) / rio.getIntNodesOfAnalyzedGeneTrees() ) + "%)" );
System.out.println( "Maximum duplications : " + ( int ) stats.getMax() + " ("
- + df.format( 100.0 * stats.getMax() / rio.getIntNodesOfAnalyzedGeneTrees() ) + "%)" );
+ + df.format( ( 100.0 * stats.getMax() ) / rio.getIntNodesOfAnalyzedGeneTrees() ) + "%)" );
System.out.println( "Gene tree internal nodes : " + rio.getIntNodesOfAnalyzedGeneTrees() );
System.out.println( "Gene tree external nodes : " + rio.getExtNodesOfAnalyzedGeneTrees() );
}
System.out.println( " or 'outgroup' (default: by minizming duplications)" );
System.out.println( " -" + OUTGROUP
+ "=<outgroup> : for rooting by outgroup, name of outgroup (external gene tree node)" );
+ System.out
+ .println( " -" + RETURN_SPECIES_TREE + "=<outfile> : to write the (stripped) species tree to file" );
+ System.out.println( " -" + RETURN_BEST_GENE_TREE
+ + "=<outfile> : to write (one) minimal duplication gene tree to file" );
+ System.out
+ .println( " -"
+ + TRANSFER_TAXONOMY_OPTION
+ + " : to transfer taxonomic data from species tree to returned minimal duplication gene tree\n"
+ + " (if -" + RETURN_BEST_GENE_TREE + " option is used)" );
System.out.println( " -" + USE_SDIR
+ " : to use SDIR instead of GSDIR (faster, but non-binary species trees are" );
System.out.println( " disallowed, as are most options)" );
System.exit( -1 );
}
- private static void tableOutput( final File table_outfile, final RIO rio ) throws IOException, RIOException {
- final IntMatrix m = RIO.calculateOrthologTable( rio.getAnalyzedGeneTrees(), true );
- writeTable( table_outfile, rio, m );
- }
-
private static void writeLogFile( final File logfile,
final RIO rio,
final File species_tree_file,
System.out.println( "Wrote log to \"" + logfile + "\"" );
}
- private static void writeTable( final File table_outfile, final RIO rio, final IntMatrix m ) throws IOException {
+ private static void writeTable( final File table_outfile, final int gene_trees_analyzed, final IntMatrix m )
+ throws IOException {
final EasyWriter w = ForesterUtil.createEasyWriter( table_outfile );
- final java.text.DecimalFormat df = new java.text.DecimalFormat( "0.###" );
+ final java.text.DecimalFormat df = new java.text.DecimalFormat( "0.####" );
df.setDecimalSeparatorAlwaysShown( false );
+ df.setRoundingMode( RoundingMode.HALF_UP );
for( int i = 0; i < m.size(); ++i ) {
w.print( "\t" );
w.print( m.getLabel( i ) );
for( int y = 0; y < m.size(); ++y ) {
w.print( "\t" );
if ( x == y ) {
- if ( m.get( x, y ) != rio.getAnalyzedGeneTrees().length ) {
+ if ( m.get( x, y ) != gene_trees_analyzed ) {
ForesterUtil.unexpectedFatalError( "diagonal value is off" );
}
w.print( "-" );
}
else {
- w.print( df.format( ( ( double ) m.get( x, y ) ) / rio.getAnalyzedGeneTrees().length ) );
+ w.print( df.format( ( ( double ) m.get( x, y ) ) / gene_trees_analyzed ) );
}
}
w.println();
w.close();
System.out.println( "Wrote table to \"" + table_outfile + "\"" );
}
+
+ private static void writeTree( final Phylogeny p, final File f, final String comment ) throws IOException {
+ final PhylogenyWriter writer = new PhylogenyWriter();
+ writer.toPhyloXML( f, p, 0 );
+ System.out.println( comment + " \"" + f + "\"" );
+ }
}