// 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.FileWriter;
import java.io.IOException;
-import java.io.PrintWriter;
+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.phylogeny.factories.ParserBasedPhylogenyFactory;
-import org.forester.phylogeny.factories.PhylogenyFactory;
-import org.forester.sdi.RIO;
-import org.forester.sdi.RioException;
+import org.forester.rio.RIO;
+import org.forester.rio.RIO.REROOTING;
+import org.forester.rio.RIOException;
import org.forester.sdi.SDIException;
+import org.forester.sdi.SDIutil.ALGORITHM;
+import org.forester.util.BasicDescriptiveStatistics;
import org.forester.util.CommandLineArguments;
import org.forester.util.EasyWriter;
import org.forester.util.ForesterUtil;
public class rio {
- final static private String PRG_NAME = "rio";
- final static private String PRG_VERSION = "3.00 beta 3";
- final static private String PRG_DATE = "2012.12.05";
- 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 QUERY_OPTION = "q";
- final static private String SORT_OPTION = "s";
- final static private String OUTPUT_ULTRA_P_OPTION = "u";
- final static private String CUTOFF_ULTRA_P_OPTION = "cu";
- final static private String CUTOFF_ORTHO_OPTION = "co";
- final static private String TABLE_OUTPUT_OPTION = "t";
+ 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,
cla = new CommandLineArguments( args );
}
catch ( final Exception e ) {
- ForesterUtil.fatalError( PRG_NAME, e.getMessage() );
+ ForesterUtil.fatalError( e.getMessage() );
}
if ( cla.isOptionSet( HELP_OPTION_1 ) || cla.isOptionSet( HELP_OPTION_2 ) || ( args.length == 0 ) ) {
printHelp();
}
- if ( ( args.length < 2 ) || ( args.length > 10 ) ) {
+ if ( ( args.length < 3 ) || ( args.length > 11 ) || ( cla.getNumberOfNames() < 3 ) ) {
System.out.println();
- System.out.println( "[" + PRG_NAME + "] incorrect number of arguments" );
+ System.out.println( "error: incorrect number of arguments" );
System.out.println();
printHelp();
}
final List<String> allowed_options = new ArrayList<String>();
- allowed_options.add( QUERY_OPTION );
- allowed_options.add( SORT_OPTION );
- allowed_options.add( CUTOFF_ULTRA_P_OPTION );
- allowed_options.add( CUTOFF_ORTHO_OPTION );
- allowed_options.add( TABLE_OUTPUT_OPTION );
- allowed_options.add( OUTPUT_ULTRA_P_OPTION );
+ allowed_options.add( GT_FIRST );
+ allowed_options.add( GT_LAST );
+ 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( PRG_NAME, "unknown option(s): " + dissallowed_options );
+ ForesterUtil.fatalError( "unknown option(s): " + dissallowed_options );
}
final File gene_trees_file = cla.getFile( 0 );
final File species_tree_file = cla.getFile( 1 );
- File outfile = null;
- if ( cla.getNumberOfNames() > 2 ) {
- outfile = cla.getFile( 2 );
+ final File orthology_outtable = cla.getFile( 2 );
+ final File logfile;
+ if ( cla.getNumberOfNames() > 3 ) {
+ logfile = cla.getFile( 3 );
+ if ( logfile.exists() ) {
+ ForesterUtil.fatalError( "\"" + logfile + "\" already exists" );
+ }
}
- ForesterUtil.fatalErrorIfFileNotReadable( PRG_NAME, gene_trees_file );
- ForesterUtil.fatalErrorIfFileNotReadable( PRG_NAME, species_tree_file );
- if ( ( outfile != null ) && outfile.exists() ) {
- ForesterUtil.fatalError( PRG_NAME, "[" + outfile + "] already exists" );
+ else {
+ logfile = null;
}
- String query = null;
- if ( cla.isOptionSet( QUERY_OPTION ) ) {
- query = cla.getOptionValue( QUERY_OPTION );
+ boolean sdir = false;
+ if ( cla.isOptionSet( USE_SDIR ) ) {
+ if ( cla.isOptionHasAValue( USE_SDIR ) ) {
+ ForesterUtil.fatalError( "no value allowed for -" + USE_SDIR );
+ }
+ sdir = true;
+ if ( logfile != null ) {
+ ForesterUtil.fatalError( "no logfile output for SDIR algorithm" );
+ }
}
- File table_outfile = null;
- if ( cla.isOptionSet( TABLE_OUTPUT_OPTION ) ) {
- table_outfile = new File( cla.getOptionValue( TABLE_OUTPUT_OPTION ) );
- if ( table_outfile.exists() ) {
- ForesterUtil.fatalError( PRG_NAME, "[" + table_outfile + "] already exists" );
+ String outgroup = null;
+ if ( cla.isOptionSet( OUTGROUP ) ) {
+ if ( !cla.isOptionHasAValue( OUTGROUP ) ) {
+ ForesterUtil.fatalError( "no value for -" + OUTGROUP );
}
+ if ( sdir ) {
+ ForesterUtil.fatalError( "no outgroup option for SDIR algorithm" );
+ }
+ outgroup = cla.getOptionValueAsCleanString( OUTGROUP );
}
- boolean output_ultraparalogs = false;
- if ( cla.isOptionSet( OUTPUT_ULTRA_P_OPTION ) ) {
- output_ultraparalogs = true;
+ REROOTING rerooting = REROOTING.BY_ALGORITHM;
+ if ( cla.isOptionSet( REROOTING_OPT ) ) {
+ if ( !cla.isOptionHasAValue( REROOTING_OPT ) ) {
+ ForesterUtil.fatalError( "no value for -" + REROOTING_OPT );
+ }
+ if ( sdir ) {
+ ForesterUtil.fatalError( "no re-rooting option for SDIR algorithm" );
+ }
+ final String rerooting_str = cla.getOptionValueAsCleanString( REROOTING_OPT ).toLowerCase();
+ if ( rerooting_str.equals( "none" ) ) {
+ rerooting = REROOTING.NONE;
+ }
+ else if ( rerooting_str.equals( "midpoint" ) ) {
+ rerooting = REROOTING.MIDPOINT;
+ }
+ else if ( rerooting_str.equals( "outgroup" ) ) {
+ rerooting = REROOTING.OUTGROUP;
+ }
+ else {
+ ForesterUtil
+ .fatalError( "values for re-rooting are: 'none', 'midpoint', or 'outgroup' (minizming duplications is default)" );
+ }
}
- double cutoff_for_orthologs = 50;
- double cutoff_for_ultra_paralogs = 50;
- int sort = 1;
- try {
- if ( cla.isOptionSet( CUTOFF_ORTHO_OPTION ) ) {
- cutoff_for_orthologs = cla.getOptionValueAsDouble( CUTOFF_ORTHO_OPTION );
- if ( query == null ) {
- ForesterUtil.fatalError( PRG_NAME, "missing query name, type \"rio -h\" for help" );
- }
- if ( outfile == null ) {
- ForesterUtil.fatalError( PRG_NAME, "missing outfile, type \"rio -h\" for help" );
- }
+ if ( ForesterUtil.isEmpty( outgroup ) && ( rerooting == REROOTING.OUTGROUP ) ) {
+ ForesterUtil.fatalError( "selected re-rooting by outgroup, but outgroup not set" );
+ }
+ if ( !ForesterUtil.isEmpty( outgroup ) && ( rerooting != REROOTING.OUTGROUP ) ) {
+ ForesterUtil.fatalError( "outgroup set, but selected re-rooting by other approach" );
+ }
+ int gt_first = RIO.DEFAULT_RANGE;
+ int gt_last = RIO.DEFAULT_RANGE;
+ if ( cla.isOptionSet( GT_FIRST ) ) {
+ if ( !cla.isOptionHasAValue( GT_FIRST ) ) {
+ ForesterUtil.fatalError( "no value for -" + GT_FIRST );
+ }
+ if ( sdir ) {
+ ForesterUtil.fatalError( "no gene tree range option for SDIR algorithm" );
+ }
+ try {
+ gt_first = cla.getOptionValueAsInt( GT_FIRST );
}
- if ( cla.isOptionSet( CUTOFF_ULTRA_P_OPTION ) ) {
- cutoff_for_ultra_paralogs = cla.getOptionValueAsDouble( CUTOFF_ULTRA_P_OPTION );
- output_ultraparalogs = true;
+ catch ( final IOException e ) {
+ ForesterUtil.fatalError( "could not parse integer for -" + GT_FIRST + " option" );
}
- if ( cla.isOptionSet( SORT_OPTION ) ) {
- sort = cla.getOptionValueAsInt( SORT_OPTION );
+ if ( gt_first < 0 ) {
+ ForesterUtil.fatalError( "attempt to set index of first tree to analyze to: " + gt_first );
}
}
- catch ( final Exception e ) {
- ForesterUtil.fatalError( PRG_NAME, "error in command line: " + e.getLocalizedMessage() );
+ if ( cla.isOptionSet( GT_LAST ) ) {
+ if ( !cla.isOptionHasAValue( GT_LAST ) ) {
+ ForesterUtil.fatalError( "no value for -" + GT_LAST );
+ }
+ if ( sdir ) {
+ ForesterUtil.fatalError( "no gene tree range option for SDIR algorithm" );
+ }
+ try {
+ gt_last = cla.getOptionValueAsInt( GT_LAST );
+ }
+ catch ( final IOException e ) {
+ ForesterUtil.fatalError( "could not parse integer for -" + GT_LAST + " option" );
+ }
+ if ( gt_last < 0 ) {
+ ForesterUtil.fatalError( "attempt to set index of last tree to analyze to: " + gt_last );
+ }
+ }
+ if ( ( ( gt_last != RIO.DEFAULT_RANGE ) && ( gt_first != RIO.DEFAULT_RANGE ) ) && ( ( gt_last < gt_first ) ) ) {
+ 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" );
+ }
}
- if ( ( cutoff_for_orthologs < 0 ) || ( cutoff_for_ultra_paralogs < 0 ) || ( sort < 0 ) || ( sort > 2 ) ) {
- ForesterUtil.fatalError( PRG_NAME, "numberical option out of range, type \"rio -h\" for help" );
+ 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" );
+ }
}
- if ( ( ( query == null ) && ( ( outfile != null ) || output_ultraparalogs ) ) ) {
- ForesterUtil.fatalError( PRG_NAME, "missing query name, type \"rio -h\" for help" );
+ 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;
}
- if ( ( output_ultraparalogs && ( outfile == null ) ) || ( ( query != null ) && ( outfile == null ) ) ) {
- ForesterUtil.fatalError( PRG_NAME, "missing outfile, type \"rio -h\" for help" );
+ ForesterUtil.fatalErrorIfFileNotReadable( gene_trees_file );
+ ForesterUtil.fatalErrorIfFileNotReadable( species_tree_file );
+ if ( orthology_outtable.exists() ) {
+ ForesterUtil.fatalError( "\"" + orthology_outtable + "\" already exists" );
}
long time = 0;
System.out.println( "Gene trees : " + gene_trees_file );
System.out.println( "Species tree : " + species_tree_file );
- if ( query != null ) {
- System.out.println( "Query : " + query );
- System.out.println( "Outfile : " + outfile );
- System.out.println( "Sort : " + sort );
- System.out.println( "Cutoff for orthologs : " + cutoff_for_orthologs );
- if ( output_ultraparalogs ) {
- System.out.println( "Cutoff for ultra paralogs : " + cutoff_for_ultra_paralogs );
+ System.out.println( "All vs all orthology table: " + orthology_outtable );
+ if ( logfile != null ) {
+ System.out.println( "Logfile : " + logfile );
+ }
+ if ( gt_first != RIO.DEFAULT_RANGE ) {
+ System.out.println( "First gene tree to analyze: " + gt_first );
+ }
+ if ( gt_last != RIO.DEFAULT_RANGE ) {
+ System.out.println( "Last gene tree to analyze : " + gt_last );
+ }
+ String rerooting_str = "";
+ switch ( rerooting ) {
+ case BY_ALGORITHM: {
+ rerooting_str = "by minimizing duplications";
+ break;
+ }
+ case MIDPOINT: {
+ rerooting_str = "by midpoint method";
+ break;
+ }
+ case OUTGROUP: {
+ rerooting_str = "by outgroup: " + outgroup;
+ break;
+ }
+ case NONE: {
+ rerooting_str = "none";
+ break;
}
}
- if ( table_outfile != null ) {
- System.out.println( "Table output : " + table_outfile );
+ System.out.println( "Re-rooting : " + rerooting_str );
+ if ( !sdir ) {
+ System.out.println( "Non binary species tree : allowed" );
}
- System.out.println();
- time = System.currentTimeMillis();
- Phylogeny species_tree = null;
- try {
- final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
- species_tree = factory.create( species_tree_file, new PhyloXmlParser() )[ 0 ];
+ else {
+ System.out.println( "Non binary species tree : disallowed" );
}
- catch ( final Exception e ) {
- e.printStackTrace();
- System.exit( -1 );
+ if ( return_species_tree != null ) {
+ System.out.println( "Write used species tree to: " + return_species_tree );
}
- if ( !species_tree.isRooted() ) {
- ForesterUtil.fatalError( PRG_NAME, "species tree is not rooted" );
+ if ( return_gene_tree != null ) {
+ System.out.println( "Write best gene tree to : " + return_gene_tree );
+ System.out.println( "Transfer taxonomic data : " + transfer_taxonomy );
}
- if ( !species_tree.isCompletelyBinary() ) {
- ForesterUtil.fatalError( PRG_NAME, "species tree is not completely binary" );
+ time = System.currentTimeMillis();
+ final ALGORITHM algorithm;
+ if ( sdir ) {
+ algorithm = ALGORITHM.SDIR;
+ }
+ else {
+ algorithm = ALGORITHM.GSDIR;
}
try {
final RIO rio;
- if ( ForesterUtil.isEmpty( query ) ) {
- rio = new RIO( gene_trees_file, species_tree );
+ 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 {
- rio = new RIO( gene_trees_file, species_tree, query );
- }
- if ( outfile != null ) {
- final StringBuilder output = new StringBuilder();
- output.append( rio.inferredOrthologsToString( query, sort, cutoff_for_orthologs ) );
- if ( output_ultraparalogs ) {
- output.append( "\n\nUltra paralogs:\n" );
- output.append( rio.inferredUltraParalogsToString( query, cutoff_for_ultra_paralogs ) );
+ 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 );
}
- output.append( "\n\nSort priority: " + RIO.getOrder( sort ) );
- output.append( "\nExt nodes : " + rio.getExtNodesOfAnalyzedGeneTrees() );
- output.append( "\nSamples : " + rio.getNumberOfSamples() + "\n" );
- final PrintWriter out = new PrintWriter( new FileWriter( outfile ), true );
- out.println( output );
- out.close();
+ 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 ( table_outfile != null ) {
- tableOutput( table_outfile, rio );
+ if ( algorithm == ALGORITHM.GSDIR ) {
+ System.out.println( "Taxonomy linking based on : " + rio.getGSDIRtaxCompBase() );
}
+ 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,
+ species_tree_file,
+ gene_trees_file,
+ orthology_outtable,
+ PRG_NAME,
+ PRG_VERSION,
+ PRG_DATE,
+ ForesterUtil.getForesterLibraryInformation() );
+ }
+ 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() ) + "%)" );
+ if ( stats.getN() > 3 ) {
+ System.out.println( "Median number of duplications: " + df.format( stats.median() ) + " ("
+ + df.format( ( 100.0 * stats.median() ) / rio.getIntNodesOfAnalyzedGeneTrees() ) + "%)" );
+ }
+ System.out.println( "Minimum duplications : " + ( int ) stats.getMin() + " ("
+ + df.format( ( 100.0 * stats.getMin() ) / rio.getIntNodesOfAnalyzedGeneTrees() ) + "%)" );
+ System.out.println( "Maximum duplications : " + ( int ) stats.getMax() + " ("
+ + 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() );
}
- catch ( final RioException e ) {
- ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
+ catch ( final RIOException e ) {
+ ForesterUtil.fatalError( e.getLocalizedMessage() );
}
catch ( final SDIException e ) {
- ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
+ ForesterUtil.fatalError( e.getLocalizedMessage() );
}
catch ( final IOException e ) {
- ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
+ ForesterUtil.fatalError( e.getLocalizedMessage() );
+ }
+ catch ( final OutOfMemoryError e ) {
+ ForesterUtil.outOfMemoryError( e );
}
catch ( final Exception e ) {
- ForesterUtil.unexpectedFatalError( PRG_NAME, e );
+ ForesterUtil.unexpectedFatalError( e );
}
- if ( outfile != null ) {
- ForesterUtil.programMessage( PRG_NAME, "wrote results to \"" + outfile + "\"" );
+ catch ( final Error e ) {
+ ForesterUtil.unexpectedFatalError( e );
}
time = System.currentTimeMillis() - time;
- ForesterUtil.programMessage( PRG_NAME, "time: " + time + "ms" );
- ForesterUtil.programMessage( PRG_NAME, "OK" );
+ System.out.println( "Time: " + time + "ms" );
+ System.out.println( "OK" );
System.exit( 0 );
}
- private static void tableOutput( final File table_outfile, final RIO rio ) throws IOException, RioException {
- final IntMatrix m = RIO.calculateOrthologTable( rio.getAnalyzedGeneTrees() );
- writeTable( table_outfile, rio, m );
+ private final static void printHelp() {
+ System.out.println( "Usage" );
+ System.out.println();
+ System.out
+ .println( PRG_NAME
+ + " [options] <gene trees infile> <species tree infile> <all vs all orthology table outfile> [logfile]" );
+ System.out.println();
+ System.out.println( " Options" );
+ System.out.println( " -" + GT_FIRST + "=<first> : first gene tree to analyze (0-based index)" );
+ System.out.println( " -" + GT_LAST + "=<last> : last gene tree to analyze (0-based index)" );
+ System.out.println( " -" + REROOTING_OPT
+ + "=<re-rooting>: re-rooting method for gene trees, possible values or 'none', 'midpoint'," );
+ 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.out.println();
+ System.out.println( " Formats" );
+ System.out
+ .println( " The gene trees, as well as the species tree, ideally are in phyloXML (www.phyloxml.org) format," );
+ System.out
+ .println( " but can also be in New Hamphshire (Newick) or Nexus format as long as species information can be" );
+ System.out
+ .println( " extracted from the gene names (e.g. \"HUMAN\" from \"BCL2_HUMAN\") and matched to a single species" );
+ System.out.println( " in the species tree." );
+ System.out.println();
+ System.out.println( " Examples" );
+ System.out.println( " \"rio gene_trees.nh species.xml outtable.tsv log.txt\"" );
+ System.out.println();
+ System.out.println( " More information: http://code.google.com/p/forester/wiki/RIO" );
+ System.out.println();
+ System.exit( -1 );
}
- private static void writeTable( final File table_outfile, final RIO rio, final IntMatrix m ) throws IOException {
+ private static void writeLogFile( final File logfile,
+ final RIO rio,
+ final File species_tree_file,
+ final File gene_trees_file,
+ final File outtable,
+ final String prg_name,
+ final String prg_v,
+ final String prg_date,
+ final String f ) throws IOException {
+ final EasyWriter out = ForesterUtil.createEasyWriter( logfile );
+ out.println( prg_name );
+ out.println( "version : " + prg_v );
+ out.println( "date : " + prg_date );
+ out.println( "based on: " + f );
+ out.println( "----------------------------------" );
+ out.println( "Gene trees : " + gene_trees_file );
+ out.println( "Species tree : " + species_tree_file );
+ out.println( "All vs all orthology table : " + outtable );
+ out.flush();
+ out.println( rio.getLog().toString() );
+ out.close();
+ System.out.println( "Wrote log to \"" + logfile + "\"" );
+ }
+
+ 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.getNumberOfSamples() ) {
- ForesterUtil.unexpectedFatalError( PRG_NAME, "diagonal value is off" );
+ 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.getNumberOfSamples() ) );
+ w.print( df.format( ( ( double ) m.get( x, y ) ) / gene_trees_analyzed ) );
}
}
w.println();
}
w.close();
- ForesterUtil.programMessage( PRG_NAME, "wrote table to \"" + table_outfile + "\"" );
+ System.out.println( "Wrote table to \"" + table_outfile + "\"" );
}
- private final static void printHelp() {
- System.out.println( "Usage" );
- System.out.println();
- System.out.println( PRG_NAME + " [options] <gene trees file> <species tree file> [outfile]" );
- System.out.println();
- System.out.println( " Options" );
- System.out.println( " -" + CUTOFF_ORTHO_OPTION + " : cutoff for ortholog output (default: 50)" );
- System.out.println( " -" + TABLE_OUTPUT_OPTION
- + " : file-name for output table of all vs. all ortholgy support" );
- System.out.println( " -" + QUERY_OPTION
- + " : name for query (sequence/node), if this is used, [outfile] is required as well" );
- System.out.println( " -" + SORT_OPTION + " : sort (default: 1)" );
- System.out.println( " -" + OUTPUT_ULTRA_P_OPTION
- + " : to output ultra-paralogs (species specific expansions/paralogs)" );
- System.out.println( " -" + CUTOFF_ULTRA_P_OPTION + " : cutoff for ultra-paralog output (default: 50)" );
- System.out.println();
- System.out.println( " Note" );
- System.out.println( " Either output of all vs. all ortholgy support with -t=<output table> and/or output for" );
- System.out.println( " one query sequence with -q=<query name> and a [outfile] are required." );
- System.out.println();
- System.out.println( " Sort" );
- System.out.println( RIO.getOrderHelp().toString() );
- System.out.println( " Formats" );
- System.out.println( " The species tree is expected to be in phyloXML format." );
- System.out
- .println( " The gene trees ideally are in phyloXML as well, but can also be in New Hamphshire (Newick)" );
- System.out.println( " or Nexus format as long as species information can be extracted from the gene names" );
- System.out.println( " (e.g. \"HUMAN\" from \"BCL2_HUMAN\")." );
- System.out.println();
- System.out.println( " Examples" );
- System.out.println( " \"rio gene_trees.nh species.xml outfile -q=BCL2_HUMAN -t=outtable -u -cu=60 -co=60\"" );
- System.out.println( " \"rio gene_trees.nh species.xml -t=outtable\"" );
- System.out.println();
- System.out.println( " More information: http://code.google.com/p/forester/wiki/RIO" );
- System.out.println();
- System.exit( -1 );
+ 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 + "\"" );
}
}
git://source.jalview.org / jalview.git / blobdiff