import java.io.File;
import java.io.FileWriter;
+import java.io.IOException;
import java.io.PrintWriter;
import java.util.ArrayList;
-import java.util.Vector;
+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.PhylogenyMethods;
-import org.forester.phylogeny.PhylogenyNode;
import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
import org.forester.phylogeny.factories.PhylogenyFactory;
-import org.forester.phylogeny.iterators.PreorderTreeIterator;
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 = "2.03 ALPHA";
- final static private String PRG_DATE = "2010.01.15";
- final static private String E_MAIL = "czmasek@burnham.org";
- final static private String WWW = "www.phylosoft.org/forester/";
- final static private boolean TIME = true;
- final static private boolean VERBOSE = true;
- // For method getDistances -- calculation of distances.
- final static private boolean MINIMIZE_COST = false;
- // For method getDistances -- calculation of distances.
- final static private boolean MINIMIZE_DUPS = true;
- // For method getDistances -- calculation of distances.
- final static private boolean MINIMIZE_HEIGHT = true;
- final static private int WARN_NO_ORTHOS_DEFAULT = 2;
- final static private int
- // How many sd away from mean to root.
- WARN_MORE_THAN_ONE_ORTHO_DEFAULT = 2;
- // How many sd away from mean to LCA of orthos.
- final static private double THRESHOLD_ULTRA_PARALOGS_DEFAULT = 50;
- // How many sd away from mean to LCA of orthos.
- final static private double WARN_ONE_ORTHO_DEFAULT = 2;
+ final static private String PRG_NAME = "rio";
+ final static private String PRG_VERSION = "3.00 beta 1";
+ 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";
+ 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";
- // Factor between the two distances to their LCA
- // (larger/smaller).
- // Factor between the two distances to their LCA
- // (larger/smaller).
- /**
- * Calculates the mean and standard deviation of all nodes of Phylogeny t
- * which have a bootstrap values zero or more. Returns null in case of
- * failure (e.g t has no bootstrap values, or just one).
- * <p>
- *
- * @param t
- * reference to a tree with bootstrap values
- * @return Array of doubles, [0] is the mean, [1] the standard deviation
- */
- private static double[] calculateMeanBoostrapValue( final Phylogeny t ) {
- double b = 0;
- int n = 0;
- long sum = 0;
- double x = 0.0, mean = 0.0;
- final double[] da = new double[ 2 ];
- final Vector<Double> bv = new Vector<Double>();
- PhylogenyNode node = null;
- PreorderTreeIterator i = null;
- i = new PreorderTreeIterator( t );
- // Calculates the mean.
- while ( i.hasNext() ) {
- node = i.next();
- if ( !( ( node.getParent() != null ) && node.getParent().isRoot()
- && ( PhylogenyMethods.getConfidenceValue( node.getParent().getChildNode1() ) > 0 )
- && ( PhylogenyMethods.getConfidenceValue( node.getParent().getChildNode2() ) > 0 ) && ( node
- .getParent().getChildNode2() == node ) ) ) {
- b = PhylogenyMethods.getConfidenceValue( node );
- if ( b > 0 ) {
- sum += b;
- bv.addElement( new Double( b ) );
- n++;
- }
- }
- // i.next();
+ public static void main( final String[] args ) {
+ ForesterUtil.printProgramInformation( PRG_NAME,
+ "resampled inference of orthologs",
+ PRG_VERSION,
+ PRG_DATE,
+ E_MAIL,
+ WWW,
+ ForesterUtil.getForesterLibraryInformation() );
+ CommandLineArguments cla = null;
+ try {
+ cla = new CommandLineArguments( args );
}
- if ( n < 2 ) {
- return null;
+ catch ( final Exception e ) {
+ ForesterUtil.fatalError( PRG_NAME, e.getMessage() );
}
- mean = ( double ) sum / n;
- // Calculates the standard deviation.
- sum = 0;
- for( int j = 0; j < n; ++j ) {
- b = ( bv.elementAt( j ) ).intValue();
- x = b - mean;
- sum += ( x * x );
+ if ( cla.isOptionSet( HELP_OPTION_1 ) || cla.isOptionSet( HELP_OPTION_2 ) || ( args.length == 0 ) ) {
+ printHelp();
}
- da[ 0 ] = mean;
- da[ 1 ] = java.lang.Math.sqrt( sum / ( n - 1.0 ) );
- return da;
- }
-
- private final static void errorInCommandLine() {
- System.out.println( "\nrio: Error in command line.\n" );
- printHelp();
- System.exit( -1 );
- }
-
- public static void main( final String[] args ) {
- ForesterUtil.printProgramInformation( PRG_NAME, PRG_VERSION, PRG_DATE, E_MAIL, WWW );
- File species_tree_file = null;
- File multiple_trees_file = null;
- File outfile = null;
- String seq_name = "";
- String arg = "";
- boolean output_ultraparalogs = false;
- ArrayList<String> orthologs_al_for_dc = null;
- double t_orthologs = 0.0;
- double t_orthologs_dc = 0.0;
- double threshold_ultra_paralogs = 0.0;
- double[] bs_mean_sd = null;
- int sort = 13;
- Phylogeny species_tree = null;
- RIO rio_instance = null;
- PrintWriter out = null;
- long time = 0;
- if ( args.length < 2 ) {
+ 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( 0 );
}
- else if ( ( args.length < 3 ) || ( args.length > 18 ) ) {
- errorInCommandLine();
+ 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 );
+ final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
+ if ( dissallowed_options.length() > 0 ) {
+ ForesterUtil.fatalError( PRG_NAME, "unknown option(s): " + dissallowed_options );
}
- for( final String arg2 : args ) {
- if ( arg2.trim().charAt( 0 ) != 'p' ) {
- if ( arg2.trim().length() < 3 ) {
- errorInCommandLine();
- }
- else {
- arg = arg2.trim().substring( 2 );
- }
+ 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 );
+ }
+ 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 query = null;
+ if ( cla.isOptionSet( 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, "[" + table_outfile + "] already exists" );
}
- try {
- switch ( arg2.trim().charAt( 0 ) ) {
- case 'M':
- multiple_trees_file = new File( arg );
- break;
- case 'N':
- seq_name = arg;
- break;
- case 'S':
- species_tree_file = new File( arg );
- break;
- case 'O':
- outfile = new File( arg );
- break;
- case 'p':
- output_ultraparalogs = true;
- break;
- case 'P':
- sort = Integer.parseInt( arg );
- if ( ( sort < 0 ) || ( sort > 17 ) ) {
- errorInCommandLine();
- }
- break;
- case 'L':
- t_orthologs = Double.parseDouble( arg );
- break;
- case 'v':
- threshold_ultra_paralogs = Double.parseDouble( arg );
- break;
- default:
- errorInCommandLine();
+ }
+ boolean output_ultraparalogs = false;
+ if ( cla.isOptionSet( OUTPUT_ULTRA_P_OPTION ) ) {
+ output_ultraparalogs = true;
+ }
+ double cutoff_for_orthologs = 50;
+ double cutoff_for_ultra_paralogs = 50;
+ int sort = 2;
+ try {
+ if ( cla.isOptionSet( CUTOFF_ORTHO_OPTION ) ) {
+ cutoff_for_orthologs = cla.getOptionValueAsDouble( CUTOFF_ORTHO_OPTION );
+ }
+ if ( cla.isOptionSet( CUTOFF_ULTRA_P_OPTION ) ) {
+ cutoff_for_ultra_paralogs = cla.getOptionValueAsDouble( CUTOFF_ULTRA_P_OPTION );
+ if ( !output_ultraparalogs ) {
+ printHelp();
}
}
- catch ( final Exception e ) {
- errorInCommandLine();
+ if ( cla.isOptionSet( SORT_OPTION ) ) {
+ sort = cla.getOptionValueAsInt( SORT_OPTION );
}
}
- if ( ( seq_name == "" ) || ( species_tree_file == null ) || ( multiple_trees_file == null )
- || ( outfile == null ) ) {
- errorInCommandLine();
+ catch ( final Exception e ) {
+ ForesterUtil.fatalError( PRG_NAME, "error in command line: " + e.getLocalizedMessage() );
+ }
+ 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();
}
- if ( ( sort < 0 ) || ( sort > 2 ) ) {
- errorInCommandLine();
+ if ( output_ultraparalogs && ( outfile == null ) ) {
+ printHelp();
}
- if ( VERBOSE ) {
- System.out.println( "\nMultiple trees file: " + multiple_trees_file );
- System.out.println( "Seq name: " + seq_name );
- System.out.println( "Species tree file: " + species_tree_file );
- System.out.println( "Outfile: " + outfile );
- System.out.println( "Sort: " + sort );
- System.out.println( "Threshold orthologs: " + t_orthologs );
- System.out.println( "Threshold orthologs for distance calc.: " + t_orthologs_dc );
+ 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( "Threshold ultra paralogs: " + threshold_ultra_paralogs );
+ System.out.println( "Cutoff for ultra paralogs : " + cutoff_for_ultra_paralogs );
}
}
- if ( TIME && VERBOSE ) {
- time = System.currentTimeMillis();
+ if ( table_outfile != null ) {
+ System.out.println( "Table output : " + table_outfile );
}
+ 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 ];
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 );
}
- rio_instance = new RIO();
- final StringBuffer output = new StringBuffer();
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 ( TIME && VERBOSE ) {
- time = System.currentTimeMillis() - time;
- ForesterUtil.programMessage( PRG_NAME, "time: " + time + "ms" );
+ if ( outfile != null ) {
+ ForesterUtil.programMessage( PRG_NAME, "wrote results to \"" + outfile + "\"" );
}
- ForesterUtil.programMessage( PRG_NAME, "OK." );
+ time = System.currentTimeMillis() - time;
+ ForesterUtil.programMessage( PRG_NAME, "time: " + time + "ms" );
+ 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( "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( RIO.getOrderHelp().toString() );
+ 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" );
+ 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( " 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( " Example: \"rio M=gene_trees.xml N=bcl2_NEMVE S=species_tree.xml D=distances P=13 p O=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.exit( -1 );
}
}
git://source.jalview.org / jalview.git / blobdiff