X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Fapplication%2Fsurfacing.java;h=141db17d78e239612bc29e8e7e63a93e5f5a4fcb;hb=7a194f3da2c3a659ecc67bff021d9f64c845e923;hp=394c4f662fb1a4c5fcaf0546939a573bc36631ae;hpb=bfef347dd10a29b0e95d4a7ca87e997e443f45c4;p=jalview.git diff --git a/forester/java/src/org/forester/application/surfacing.java b/forester/java/src/org/forester/application/surfacing.java index 394c4f6..141db17 100644 --- a/forester/java/src/org/forester/application/surfacing.java +++ b/forester/java/src/org/forester/application/surfacing.java @@ -215,8 +215,8 @@ public class surfacing { final static private String INPUT_GENOMES_FILE_OPTION = "genomes"; final static private String INPUT_SPECIES_TREE_OPTION = "species_tree"; final static private String SEQ_EXTRACT_OPTION = "prot_extract"; - final static private String PRG_VERSION = "2.403"; - final static private String PRG_DATE = "131127"; + final static private String PRG_VERSION = "2.404"; + final static private String PRG_DATE = "140709"; final static private String E_MAIL = "czmasek@burnham.org"; final static private String WWW = "https://sites.google.com/site/cmzmasek/home/software/forester/surfacing"; final static private boolean IGNORE_DUFS_DEFAULT = true; @@ -379,9 +379,9 @@ public class surfacing { if ( cla.isOptionSet( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS ) ) { output_binary_domain_combinationsfor_graph_analysis = true; } - final boolean output_binary_domain_combinationsfor_counts = false; + boolean output_binary_domain_combinationsfor_counts = false; if ( cla.isOptionSet( DOMAIN_COMBINITONS_COUNTS_OUTPUT_OPTION ) ) { - output_binary_domain_combinationsfor_graph_analysis = true; + output_binary_domain_combinationsfor_counts = true; } if ( cla.isOptionSet( surfacing.MAX_FS_E_VALUE_OPTION ) ) { try { @@ -806,62 +806,56 @@ public class surfacing { } SurfacingUtil.checkForOutputFileWriteability( dcc_outfile ); } - File pfam_to_go_file = null; - Map> domain_id_to_go_ids_map = null; - int domain_id_to_go_ids_count = 0; + File pfam_to_go_file = new File( "pfam2go.txt" ); if ( cla.isOptionSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) { if ( !cla.isOptionValueSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) { ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for Pfam to GO mapping file: -" + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=" ); } pfam_to_go_file = new File( cla.getOptionValue( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ); - final String error = ForesterUtil.isReadableFile( pfam_to_go_file ); - if ( !ForesterUtil.isEmpty( error ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read Pfam to GO mapping file: " + error ); - } - try { - final PfamToGoParser parser = new PfamToGoParser( pfam_to_go_file ); - final List pfam_to_go_mappings = parser.parse(); - domain_id_to_go_ids_map = SurfacingUtil.createDomainIdToGoIdMap( pfam_to_go_mappings ); - if ( parser.getMappingCount() < domain_id_to_go_ids_map.size() ) { - ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, - "parser.getMappingCount() < domain_id_to_go_ids_map.size()" ); - } - domain_id_to_go_ids_count = parser.getMappingCount(); - } - catch ( final IOException e ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from Pfam to GO mapping file: " + e ); + } + final String error1 = ForesterUtil.isReadableFile( pfam_to_go_file ); + if ( !ForesterUtil.isEmpty( error1 ) ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read Pfam to GO mapping file: " + error1 ); + } + Map> domain_id_to_go_ids_map = null; + int domain_id_to_go_ids_count = 0; + try { + final PfamToGoParser parser = new PfamToGoParser( pfam_to_go_file ); + final List pfam_to_go_mappings = parser.parse(); + domain_id_to_go_ids_map = SurfacingUtil.createDomainIdToGoIdMap( pfam_to_go_mappings ); + if ( parser.getMappingCount() < domain_id_to_go_ids_map.size() ) { + ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, + "parser.getMappingCount() < domain_id_to_go_ids_map.size()" ); } + domain_id_to_go_ids_count = parser.getMappingCount(); } - File go_obo_file = null; - List go_terms = null; + catch ( final IOException e ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from Pfam to GO mapping file: " + e ); + } + File go_obo_file = new File( "go.obo" ); if ( cla.isOptionSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) { if ( !cla.isOptionValueSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) { ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO OBO file: -" + surfacing.GO_OBO_FILE_USE_OPTION + "=" ); } - if ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO OBO file (-" - + surfacing.GO_OBO_FILE_USE_OPTION + "=) without Pfam to GO mapping file (" - + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=)" ); - } go_obo_file = new File( cla.getOptionValue( surfacing.GO_OBO_FILE_USE_OPTION ) ); - final String error = ForesterUtil.isReadableFile( go_obo_file ); - if ( !ForesterUtil.isEmpty( error ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read GO OBO file: " + error ); - } - try { - final OBOparser parser = new OBOparser( go_obo_file, OBOparser.ReturnType.BASIC_GO_TERM ); - go_terms = parser.parse(); - if ( parser.getGoTermCount() != go_terms.size() ) { - ForesterUtil - .unexpectedFatalError( surfacing.PRG_NAME, "parser.getGoTermCount() != go_terms.size()" ); - } - } - catch ( final IOException e ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from GO OBO file: " + e ); + } + final String error2 = ForesterUtil.isReadableFile( go_obo_file ); + if ( !ForesterUtil.isEmpty( error2 ) ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read GO OBO file: " + error2 ); + } + List go_terms = null; + try { + final OBOparser parser = new OBOparser( go_obo_file, OBOparser.ReturnType.BASIC_GO_TERM ); + go_terms = parser.parse(); + if ( parser.getGoTermCount() != go_terms.size() ) { + ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "parser.getGoTermCount() != go_terms.size()" ); } } + catch ( final IOException e ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from GO OBO file: " + e ); + } Map go_id_to_term_map = null; if ( ( ( domain_id_to_go_ids_map != null ) && ( domain_id_to_go_ids_map.size() > 0 ) ) && ( ( go_terms != null ) && ( go_terms.size() > 0 ) ) ) { @@ -1817,7 +1811,8 @@ public class surfacing { final DomainSimilarityCalculator calc = new BasicDomainSimilarityCalculator( domain_similarity_sort_field, sort_by_species_count_first, number_of_genomes == 2, - CALC_SIMILARITY_SCORES ); + CALC_SIMILARITY_SCORES, + true ); switch ( scoring ) { case COMBINATIONS: pw_calc = new CombinationsBasedPairwiseDomainSimilarityCalculator(); @@ -2061,7 +2056,8 @@ public class surfacing { SurfacingUtil.writeProteinListsForAllSpecies( out_dir, protein_lists_per_species, gwcd_list, - output_list_of_all_proteins_per_domain_e_value_max ); + output_list_of_all_proteins_per_domain_e_value_max, + positive_filter_file != null ? filter : null ); } gwcd_list = null; if ( all_bin_domain_combinations_gained_fitch != null ) { @@ -2194,16 +2190,12 @@ public class surfacing { System.out.println( DA_ANALYSIS_OPTION + ": to perform DA analysis" ); System.out.println( PERFORM_DOMAIN_LENGTH_ANALYSIS_OPTION + ": to perform domain length analysis" ); System.out.println(); - System.out.println( "Example 1: java -Xms128m -Xmx512m -cp path/to/forester.jar" - + " org.forester.application.surfacing p2g=pfam2go_2012_02_07.txt -dufs -cos=Pfam_260_NC1" - + " -no_eo -mo=0 -genomes=eukaryotes.txt -out_dir=out -o=o " - + " -species_tree=tol.xml -obo=gene_ontology_2012_02_07.obo -pos_filter=f.txt -all_prot" ); System.out.println(); - System.out.println( "Example 2: java -Xms128m -Xmx512m -cp path/to/forester.jar" - + " org.forester.application.surfacing -detail=punctilious -o=TEST.html -pwc=TEST" - + " -cos=Pfam_ls_22_TC2 -p2g=pfam2go -obo=gene_ontology_edit.obo " - + "-dc_sort=dom -ignore_with_self -no_singles -ie=0.001 -mo=1 -no_eo -genomes=eukaryotes.txt " - + "-ds_output=detailed_html -scoring=domains -sort=alpha " ); + System.out + .println( "Example 1: surfacing -p2g=pfam2go.txt -obo=go.obo -species_tree=tol_156.xml -no_eo -ie=0.01 -dufs -genomes=genomes_all.txt -pos_filter=tf_1.txt -out_dir=_tf1 -o=tf1" ); + System.out.println(); + System.out + .println( "Example 2: surfacing -p2g=pfam2go.txt -obo=go.obo -species_tree=tol_156.xml -last -ignore_viral_ids -no_eo -ie=0.1 -dufs -genomes=genomes_all.txt -pos_filter=tf_1.txt -all_prot -all_prot_e=0.1 -out_dir=_tf1_e01_ape01 -o=tf1_e01_ape01" ); System.out.println(); } }