X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Fapplication%2Frio.java;h=7610fc5ed46b35e4994c304d373937b797288ab0;hb=5309073b8da93adc2ece844bb84ff2735805b38c;hp=18fa912639be2dc3c927295092ac3d7ff06ef07c;hpb=1542f37267c30e690b840d4552234f1f70598a46;p=jalview.git diff --git a/forester/java/src/org/forester/application/rio.java b/forester/java/src/org/forester/application/rio.java index 18fa912..7610fc5 100644 --- a/forester/java/src/org/forester/application/rio.java +++ b/forester/java/src/org/forester/application/rio.java @@ -29,23 +29,26 @@ package org.forester.application; import java.io.File; import java.io.FileWriter; +import java.io.IOException; import java.io.PrintWriter; import java.util.ArrayList; import java.util.List; +import org.forester.datastructures.IntMatrix; import org.forester.io.parsers.phyloxml.PhyloXmlParser; 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.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 1"; - final static private String PRG_DATE = "2010.01.15"; + final static private String PRG_DATE = "2012.11.27"; 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"; @@ -74,14 +77,12 @@ public class rio { } if ( cla.isOptionSet( HELP_OPTION_1 ) || cla.isOptionSet( HELP_OPTION_2 ) || ( args.length == 0 ) ) { printHelp(); - System.exit( 0 ); } - if ( ( args.length < 3 ) || ( args.length > 10 ) ) { + if ( ( args.length < 2 ) || ( args.length > 10 ) ) { System.out.println(); System.out.println( "[" + PRG_NAME + "] incorrect number of arguments" ); System.out.println(); printHelp(); - System.exit( -1 ); } final List allowed_options = new ArrayList(); allowed_options.add( QUERY_OPTION ); @@ -94,38 +95,44 @@ public class rio { if ( dissallowed_options.length() > 0 ) { ForesterUtil.fatalError( PRG_NAME, "unknown option(s): " + dissallowed_options ); } - final File multiple_trees_file = cla.getFile( 0 ); + final File gene_trees_file = cla.getFile( 0 ); final File species_tree_file = cla.getFile( 1 ); - final File outfile = cla.getFile( 2 ); - ForesterUtil.fatalErrorIfFileNotReadable( PRG_NAME, multiple_trees_file ); + File outfile = null; + if ( cla.getNumberOfNames() > 2 ) { + outfile = cla.getFile( 2 ); + } + ForesterUtil.fatalErrorIfFileNotReadable( PRG_NAME, gene_trees_file ); ForesterUtil.fatalErrorIfFileNotReadable( PRG_NAME, species_tree_file ); if ( outfile.exists() ) { ForesterUtil.fatalError( PRG_NAME, "[" + outfile + "] already exists" ); } - String seq_name = null; + String query = null; if ( cla.isOptionSet( QUERY_OPTION ) ) { - seq_name = cla.getOptionValue( QUERY_OPTION ); + query = cla.getOptionValue( QUERY_OPTION ); } 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, "[" + outfile + "] already exists" ); + ForesterUtil.fatalError( PRG_NAME, "[" + table_outfile + "] already exists" ); } } boolean output_ultraparalogs = false; if ( cla.isOptionSet( OUTPUT_ULTRA_P_OPTION ) ) { output_ultraparalogs = true; } - double t_orthologs = 0.0; - double threshold_ultra_paralogs = 0.0; + double cutoff_for_orthologs = 50; + double cutoff_for_ultra_paralogs = 50; int sort = 2; try { if ( cla.isOptionSet( CUTOFF_ORTHO_OPTION ) ) { - t_orthologs = cla.getOptionValueAsDouble( CUTOFF_ORTHO_OPTION ); + cutoff_for_orthologs = cla.getOptionValueAsDouble( CUTOFF_ORTHO_OPTION ); } if ( cla.isOptionSet( CUTOFF_ULTRA_P_OPTION ) ) { - threshold_ultra_paralogs = cla.getOptionValueAsDouble( CUTOFF_ULTRA_P_OPTION ); + cutoff_for_ultra_paralogs = cla.getOptionValueAsDouble( CUTOFF_ULTRA_P_OPTION ); + if ( !output_ultraparalogs ) { + printHelp(); + } } if ( cla.isOptionSet( SORT_OPTION ) ) { sort = cla.getOptionValueAsInt( SORT_OPTION ); @@ -134,24 +141,31 @@ public class rio { catch ( final Exception e ) { ForesterUtil.fatalError( PRG_NAME, "error in command line: " + e.getLocalizedMessage() ); } - if ( sort < 0 ) { - sort = 0; + if ( ( cutoff_for_orthologs < 0 ) || ( cutoff_for_ultra_paralogs < 0 ) || ( sort < 0 ) || ( sort > 2 ) ) { + printHelp(); + } + if ( ( ( query == null ) && ( outfile != null ) ) || ( ( query != null ) && ( outfile == null ) ) ) { + printHelp(); } - else if ( sort > 2 ) { - sort = 2; + if ( output_ultraparalogs && ( outfile == null ) ) { + printHelp(); } long time = 0; - System.out.println( "\n" ); - System.out.println( "Gene trees: " + multiple_trees_file ); - System.out.println( "Species tree: " + species_tree_file ); - System.out.println( "Query: " + seq_name ); - System.out.println( "Outfile: " + outfile ); - System.out.println( "Outfile: " + table_outfile ); - System.out.println( "Sort: " + sort ); - System.out.println( "Threshold orthologs: " + t_orthologs ); - if ( output_ultraparalogs ) { - System.out.println( "Threshold ultra paralogs: " + threshold_ultra_paralogs ); + 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 ); + } + } + if ( table_outfile != null ) { + System.out.println( "Table output : " + table_outfile ); } + System.out.println(); time = System.currentTimeMillis(); Phylogeny species_tree = null; try { @@ -163,68 +177,110 @@ public class rio { System.exit( -1 ); } if ( !species_tree.isRooted() ) { - ForesterUtil.printErrorMessage( PRG_NAME, "Species tree is not rooted" ); + ForesterUtil.printErrorMessage( PRG_NAME, "species tree is not rooted" ); System.exit( -1 ); } if ( !species_tree.isCompletelyBinary() ) { - ForesterUtil.printErrorMessage( PRG_NAME, "Species tree is not completely binary" ); + ForesterUtil.printErrorMessage( PRG_NAME, "species tree is not completely binary" ); System.exit( -1 ); } - final RIO rio_instance = new RIO(); - final StringBuffer output = new StringBuffer(); - PrintWriter out = null; try { - rio_instance.inferOrthologs( multiple_trees_file, species_tree.copy(), seq_name ); - output.append( rio_instance.inferredOrthologsToString( seq_name, sort, t_orthologs ) ); - if ( output_ultraparalogs ) { - output.append( "\n\nUltra paralogs:\n" ); - output.append( rio_instance.inferredUltraParalogsToString( seq_name, threshold_ultra_paralogs ) ); + RIO rio; + if ( ForesterUtil.isEmpty( query ) ) { + rio = new RIO( gene_trees_file, species_tree ); + } + 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 ) ); + } + 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(); + } + if ( table_outfile != null ) { + tableOutput( table_outfile, rio ); } - output.append( "\n\nSort priority: " + RIO.getOrder( sort ) ); - output.append( "\nExt nodes : " + rio_instance.getExtNodesOfAnalyzedGeneTrees() ); - output.append( "\nSamples : " + rio_instance.getNumberOfSamples() + "\n" ); - out = new PrintWriter( new FileWriter( outfile ), true ); } catch ( final Exception e ) { ForesterUtil.printErrorMessage( PRG_NAME, e.getLocalizedMessage() ); e.printStackTrace(); System.exit( -1 ); } - out.println( output ); - out.close(); - ForesterUtil.programMessage( PRG_NAME, "wrote results to \"" + outfile + "\"" ); + if ( outfile != null ) { + ForesterUtil.programMessage( PRG_NAME, "wrote results to \"" + outfile + "\"" ); + } time = System.currentTimeMillis() - time; ForesterUtil.programMessage( PRG_NAME, "time: " + time + "ms" ); - ForesterUtil.programMessage( PRG_NAME, "OK." ); + ForesterUtil.programMessage( PRG_NAME, "OK" ); System.exit( 0 ); } + private static void tableOutput( final File table_outfile, final RIO rio ) throws IOException { + final IntMatrix m = RIO.calculateOrthologTable( rio.getAnalyzedGeneTrees() ); + writeTable( table_outfile, rio, m ); + } + + private static void writeTable( final File table_outfile, final RIO rio, final IntMatrix m ) throws IOException { + final EasyWriter w = ForesterUtil.createEasyWriter( table_outfile ); + final java.text.DecimalFormat df = new java.text.DecimalFormat( "0.###" ); + df.setDecimalSeparatorAlwaysShown( false ); + w.print( "\t" ); + for( int i = 0; i < m.size(); ++i ) { + w.print( "\t" ); + w.print( m.getLabel( i ) ); + } + w.println(); + for( int x = 0; x < m.size(); ++x ) { + w.print( m.getLabel( x ) ); + w.print( "\t" ); + 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" ); + } + w.print( "-" ); + } + else { + w.print( df.format( ( ( double ) m.get( x, y ) ) / rio.getNumberOfSamples() ) ); + } + } + w.println(); + } + w.close(); + ForesterUtil.programMessage( PRG_NAME, "wrote table to \"" + table_outfile + "\"" ); + } + private final static void printHelp() { - System.out.println( "Usage:" ); + System.out.println( "usage:" ); System.out.println(); System.out.println( PRG_NAME + " [options] [outfile]" ); System.out.println(); - System.out.println( "options:" ); + System.out.println( " options:" ); + System.out.println(); + System.out.println( " -" + CUTOFF_ORTHO_OPTION + " : cutoff for ortholog output (default: 50)" ); + System.out.println( " -" + TABLE_OUTPUT_OPTION + " : file-name for output table" ); + System.out.println( " -" + QUERY_OPTION + " : name for query (sequence/node)" ); + System.out.println( " -" + SORT_OPTION + " : sort (default: 2)" ); + 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( " -" + STRICT_OPTION - // + " : strict [default: non-strict]: all nodes between 'target' and 'evaluators' must match" ); - // System.out.println( " -" + NORMALIZE_OPTION - // + "=: normalize to this value (e.g. 100 for most bootstrap analyses) [default: no normalization]" ); - // System.out.println( " -" + FIRST_OPTION + "=: first evaluator topology to use (0-based) [default: 0]" ); - // System.out.println( " -" + LAST_OPTION - // + "=: last evaluator topology to use (0-based) [default: use all until final topology]" ); - // System.out.println(); - // System.out.println( "M= (String) Multiple gene tree file (mandatory)" ); - // System.out.println( "N= (String) Query sequence name (mandatory)" ); - // System.out.println( "S= (String) Species tree file (mandatory)" ); - // System.out.println( "O= (String) Output file name -- overwritten without warning! (mandatory)" ); - // System.out.println( "P= (int) Sort priority" ); - // System.out.println( "L= (double) Threshold orthologs for output" ); - // System.out.println( " Sort priority (\"P=\"):" ); + System.out.println( " sort:" ); System.out.println( RIO.getOrderHelp().toString() ); System.out.println(); System.out - .println( " Example: \"rio -q=D_NEMVE -s=1 -t=out -u Bcl-2_e1_20_mafft_05_40_fme.mlt species.xml out\"" ); + .println( " example: \"rio gene_trees.nh species.xml outfile -q=D_HUMAN -t=outtable -u -cu=60 -co=60\"" ); System.out.println(); + System.exit( -1 ); } }