X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Fapplication%2Fgsdi.java;h=a77ac2ddf2b830a46af82d06f0df6434402d9f69;hb=0b49b8e750b34d28a5989facdd8a7959870de996;hp=d5c30a383fe1e2223515a722f9aa6109786131f1;hpb=670062d012a2654b8874ee1ea865f4869dc705f1;p=jalview.git diff --git a/forester/java/src/org/forester/application/gsdi.java b/forester/java/src/org/forester/application/gsdi.java index d5c30a3..a77ac2d 100644 --- a/forester/java/src/org/forester/application/gsdi.java +++ b/forester/java/src/org/forester/application/gsdi.java @@ -63,17 +63,18 @@ public final class gsdi { 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"; + final static private String TRANSFER_TAXONOMY_OPTION = "t"; final static private String HELP_OPTION_1 = "help"; final static private String HELP_OPTION_2 = "h"; final static private String SUFFIX_FOR_SPECIES_TREE_USED = "_species_tree_used.xml"; final static private String LOGFILE_SUFFIX = "_gsdi_log.txt"; final static private String REMAPPED_SUFFIX = "_gsdi_remapped.txt"; final static private String PRG_NAME = "gsdi"; - final static private String PRG_VERSION = "1.000"; - final static private String PRG_DATE = "120629"; + final static private String PRG_VERSION = "1.001"; + final static private String PRG_DATE = "130325"; final static private String PRG_DESC = "general speciation duplication inference"; final static private String E_MAIL = "phylosoft@gmail.com"; - final static private String WWW = "www.phylosoft.org/forester"; + final static private String WWW = "https://sites.google.com/site/cmzmasek/home/software/forester"; public static void main( final String args[] ) { try { @@ -108,6 +109,7 @@ public final class gsdi { allowed_options.add( gsdi.GUESS_FORMAT_OF_SPECIES_TREE ); allowed_options.add( gsdi.MOST_PARSIMONIOUS_OPTION ); allowed_options.add( gsdi.ALLOW_STRIPPING_OF_GENE_TREE_OPTION ); + allowed_options.add( TRANSFER_TAXONOMY_OPTION ); final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options ); if ( dissallowed_options.length() > 0 ) { ForesterUtil.fatalError( gsdi.PRG_NAME, "unknown option(s): " + dissallowed_options ); @@ -138,6 +140,10 @@ public final class gsdi { } allow_stripping_of_gene_tree = true; } + boolean transfer_taxonomy = false; + if ( cla.isOptionSet( TRANSFER_TAXONOMY_OPTION ) ) { + transfer_taxonomy = true; + } Phylogeny species_tree = null; Phylogeny gene_tree = null; File gene_tree_file = null; @@ -174,7 +180,7 @@ public final class gsdi { } try { final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance(); - gene_tree = factory.create( gene_tree_file, new PhyloXmlParser() )[ 0 ]; + gene_tree = factory.create( gene_tree_file, PhyloXmlParser.createPhyloXmlParserXsdValidating() )[ 0 ]; } catch ( final IOException e ) { fatalError( "error", @@ -234,16 +240,17 @@ public final class gsdi { + ( ForesterUtil.isEmpty( species_tree.getName() ) ? "" : gene_tree.getName() ) ); System.out.println( "Species tree name : " + ( ForesterUtil.isEmpty( species_tree.getName() ) ? "" : gene_tree.getName() ) ); + System.out.println( "Transfer taxonomy : " + transfer_taxonomy ); GSDII gsdii = null; final long start_time = new Date().getTime(); try { if ( base_algorithm == ALGORITHM.GSDI ) { - System.out.println( "Algorithm : GSDI" ); - log_writer.println( "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( "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 ); @@ -255,10 +262,11 @@ public final class gsdi { species_tree, most_parsimonous_duplication_model, allow_stripping_of_gene_tree, - true ); + true, + transfer_taxonomy ); } else if ( base_algorithm == ALGORITHM.GSDIR ) { - gsdii = new GSDIR( gene_tree, species_tree, allow_stripping_of_gene_tree, true ); + gsdii = new GSDIR( gene_tree, species_tree, allow_stripping_of_gene_tree, true, transfer_taxonomy ); } } catch ( final SDIException e ) { @@ -275,9 +283,9 @@ public final class gsdi { fatalError( "unexpected error", e.toString(), log_writer ); } System.out.println( "Running time (excluding I/O) : " + ( new Date().getTime() - start_time ) - + "ms" ); + + "ms" ); log_writer.println( "Running time (excluding I/O) : " + ( new Date().getTime() - start_time ) - + "ms" ); + + "ms" ); System.out.println( "Mapping based on : " + gsdii.getTaxCompBase() ); log_writer.println( "Mapping based on : " + gsdii.getTaxCompBase() ); try { @@ -296,14 +304,14 @@ public final class gsdi { System.out.println( "Wrote resulting gene tree to : " + out_file.getCanonicalPath() ); log_writer.println( "Wrote resulting gene tree to : " + out_file.getCanonicalPath() ); final File species_tree_used_file = new File( ForesterUtil.removeSuffix( out_file.toString() ) - + SUFFIX_FOR_SPECIES_TREE_USED ); + + 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() ); + + "]: " + 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() ); @@ -372,19 +380,21 @@ public final class gsdi { private static void print_help() { System.out.println( "Usage: " + gsdi.PRG_NAME - + " [-options] " ); + + " [-options] " ); System.out.println(); System.out.println( "Options:" ); System.out.println( " -" + gsdi.ALLOW_STRIPPING_OF_GENE_TREE_OPTION - + ": to allow stripping of gene tree nodes without a matching species" ); + + ": to allow stripping of gene tree nodes without a matching species" ); System.out.println( " -" + gsdi.MOST_PARSIMONIOUS_OPTION - + ": use most parimonious duplication model for GSDI: " ); + + ": use most parimonious duplication model for GSDI: " ); System.out.println( " assign nodes as speciations which would otherwise be assiged" ); 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)" ); + + ": to allow species tree in other formats than phyloXML (i.e. Newick, NHX, Nexus)" ); System.out.println( " -" + gsdi.GSDIR_OPTION - + ": to use GSDIR algorithm instead of GSDI algorithm (re-rooting)" ); + + ": to use GSDIR algorithm instead of GSDI algorithm (re-rooting)" ); + System.out.println( " -" + TRANSFER_TAXONOMY_OPTION + + ": to transfer taxonomic data from species tree to gene tree\n" ); System.out.println(); System.out.println( "Gene tree:" ); System.out.println( " in phyloXM format, with taxonomy and sequence data in appropriate fields" ); @@ -393,7 +403,7 @@ public final class gsdi { System.out.println( " in phyloXML format (unless option -" + gsdi.GUESS_FORMAT_OF_SPECIES_TREE + " is used)" ); System.out.println(); System.out.println( "Example: gsdi -" + ALLOW_STRIPPING_OF_GENE_TREE_OPTION - + " gene_tree.xml tree_of_life.xml out.xml" ); + + " gene_tree.xml tree_of_life.xml out.xml" ); System.out.println(); }