X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Fsurfacing%2FSurfacingUtil.java;h=3b52234c5eb90259dfac140570e1d1b45822e288;hb=cb49ee5684c6907b3161db82ff9aea72961b8548;hp=1433d700a5e97e493221e12d71b1390a63ca17a2;hpb=ed149d1b26c50c0673b5491fc639cdcb6afdde2f;p=jalview.git diff --git a/forester/java/src/org/forester/surfacing/SurfacingUtil.java b/forester/java/src/org/forester/surfacing/SurfacingUtil.java index 1433d70..3b52234 100644 --- a/forester/java/src/org/forester/surfacing/SurfacingUtil.java +++ b/forester/java/src/org/forester/surfacing/SurfacingUtil.java @@ -96,6 +96,7 @@ import org.forester.util.CommandLineArguments; import org.forester.util.DescriptiveStatistics; import org.forester.util.ForesterUtil; import org.forester.util.TaxonomyColors; +import org.forester.util.TaxonomyGroups; public final class SurfacingUtil { @@ -111,8 +112,9 @@ public final class SurfacingUtil { .getPerDomainEvalue() ) { return -1; } - else if ( d1.getPerDomainEvalue() > d2 - .getPerDomainEvalue() ) { + else if ( d1 + .getPerDomainEvalue() > d2 + .getPerDomainEvalue() ) { return 1; } else { @@ -175,8 +177,8 @@ public final class SurfacingUtil { break; } final String error = ForesterUtil - .isWritableFile( new File( outdir == null ? pairwise_similarities_output_file_str : outdir - + ForesterUtil.FILE_SEPARATOR + pairwise_similarities_output_file_str ) ); + .isWritableFile( new File( outdir == null ? pairwise_similarities_output_file_str + : outdir + ForesterUtil.FILE_SEPARATOR + pairwise_similarities_output_file_str ) ); if ( !ForesterUtil.isEmpty( error ) ) { ForesterUtil.fatalError( surfacing.PRG_NAME, error ); } @@ -195,18 +197,19 @@ public final class SurfacingUtil { for( final String id : sorted_ids ) { for( int c = 0; c < matrix.getNumberOfCharacters(); ++c ) { if ( ( get_gains && ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.GAIN ) ) - || ( !get_gains && ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.LOSS ) ) ) { + || ( !get_gains + && ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.LOSS ) ) ) { if ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) { all_binary_domains_combination_gained.add( AdjactantDirectedBinaryDomainCombination .obtainInstance( matrix.getCharacter( c ) ) ); } else if ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED ) { - all_binary_domains_combination_gained.add( DirectedBinaryDomainCombination - .obtainInstance( matrix.getCharacter( c ) ) ); + all_binary_domains_combination_gained + .add( DirectedBinaryDomainCombination.obtainInstance( matrix.getCharacter( c ) ) ); } else { - all_binary_domains_combination_gained.add( BasicBinaryDomainCombination.obtainInstance( matrix - .getCharacter( c ) ) ); + all_binary_domains_combination_gained + .add( BasicBinaryDomainCombination.obtainInstance( matrix.getCharacter( c ) ) ); } } } @@ -214,7 +217,8 @@ public final class SurfacingUtil { } public static Map> createDomainIdToGoIdMap( final List pfam_to_go_mappings ) { - final Map> domain_id_to_go_ids_map = new HashMap>( pfam_to_go_mappings.size() ); + final Map> domain_id_to_go_ids_map = new HashMap>( pfam_to_go_mappings + .size() ); for( final PfamToGoMapping pfam_to_go : pfam_to_go_mappings ) { if ( !domain_id_to_go_ids_map.containsKey( pfam_to_go.getKey() ) ) { domain_id_to_go_ids_map.put( pfam_to_go.getKey(), new ArrayList() ); @@ -238,7 +242,8 @@ public final class SurfacingUtil { return map; } - public static Phylogeny createNjTreeBasedOnMatrixToFile( final File nj_tree_outfile, final DistanceMatrix distance ) { + public static Phylogeny createNjTreeBasedOnMatrixToFile( final File nj_tree_outfile, + final DistanceMatrix distance ) { checkForOutputFileWriteability( nj_tree_outfile ); final NeighborJoining nj = NeighborJoining.createInstance(); final Phylogeny phylogeny = nj.execute( ( BasicSymmetricalDistanceMatrix ) distance ); @@ -287,61 +292,89 @@ public final class SurfacingUtil { public static void createSplitWriters( final File out_dir, final String my_outfile, - final Map split_writers ) throws IOException { - split_writers.put( 'a', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_A.html" ) ) ); - split_writers.put( 'b', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_B.html" ) ) ); - split_writers.put( 'c', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_C.html" ) ) ); - split_writers.put( 'd', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_D.html" ) ) ); - split_writers.put( 'e', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_E.html" ) ) ); - split_writers.put( 'f', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_F.html" ) ) ); - split_writers.put( 'g', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_G.html" ) ) ); - split_writers.put( 'h', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_H.html" ) ) ); - split_writers.put( 'i', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_I.html" ) ) ); - split_writers.put( 'j', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_J.html" ) ) ); - split_writers.put( 'k', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_K.html" ) ) ); - split_writers.put( 'l', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_L.html" ) ) ); - split_writers.put( 'm', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_M.html" ) ) ); - split_writers.put( 'n', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_N.html" ) ) ); - split_writers.put( 'o', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_O.html" ) ) ); - split_writers.put( 'p', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_P.html" ) ) ); - split_writers.put( 'q', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_Q.html" ) ) ); - split_writers.put( 'r', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_R.html" ) ) ); - split_writers.put( 's', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_S.html" ) ) ); - split_writers.put( 't', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_T.html" ) ) ); - split_writers.put( 'u', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_U.html" ) ) ); - split_writers.put( 'v', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_V.html" ) ) ); - split_writers.put( 'w', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_W.html" ) ) ); - split_writers.put( 'x', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_X.html" ) ) ); - split_writers.put( 'y', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_Y.html" ) ) ); - split_writers.put( 'z', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_Z.html" ) ) ); - split_writers.put( '0', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile - + "_domains_0.html" ) ) ); + final Map split_writers ) + throws IOException { + split_writers.put( 'a', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_A.html" ) ) ); + split_writers.put( 'b', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_B.html" ) ) ); + split_writers.put( 'c', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_C.html" ) ) ); + split_writers.put( 'd', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_D.html" ) ) ); + split_writers.put( 'e', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_E.html" ) ) ); + split_writers.put( 'f', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_F.html" ) ) ); + split_writers.put( 'g', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_G.html" ) ) ); + split_writers.put( 'h', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_H.html" ) ) ); + split_writers.put( 'i', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_I.html" ) ) ); + split_writers.put( 'j', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_J.html" ) ) ); + split_writers.put( 'k', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_K.html" ) ) ); + split_writers.put( 'l', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_L.html" ) ) ); + split_writers.put( 'm', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_M.html" ) ) ); + split_writers.put( 'n', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_N.html" ) ) ); + split_writers.put( 'o', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_O.html" ) ) ); + split_writers.put( 'p', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_P.html" ) ) ); + split_writers.put( 'q', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_Q.html" ) ) ); + split_writers.put( 'r', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_R.html" ) ) ); + split_writers.put( 's', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_S.html" ) ) ); + split_writers.put( 't', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_T.html" ) ) ); + split_writers.put( 'u', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_U.html" ) ) ); + split_writers.put( 'v', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_V.html" ) ) ); + split_writers.put( 'w', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_W.html" ) ) ); + split_writers.put( 'x', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_X.html" ) ) ); + split_writers.put( 'y', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_Y.html" ) ) ); + split_writers.put( 'z', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_Z.html" ) ) ); + split_writers.put( '0', + new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile + + "_domains_0.html" ) ) ); } public static Map createTaxCodeToIdMap( final Phylogeny phy ) { @@ -391,7 +424,8 @@ public final class SurfacingUtil { final Writer out, final String separator, final String limit_to_species, - final Map> average_protein_lengths_by_dc ) throws IOException { + final Map> average_protein_lengths_by_dc ) + throws IOException { for( final Protein protein : proteins ) { if ( ForesterUtil.isEmpty( limit_to_species ) || protein.getSpecies().getSpeciesId().equalsIgnoreCase( limit_to_species ) ) { @@ -420,13 +454,13 @@ public final class SurfacingUtil { } out.write( "]" ); out.write( separator ); - if ( !( ForesterUtil.isEmpty( protein.getDescription() ) || protein.getDescription() - .equals( SurfacingConstants.NONE ) ) ) { + if ( !( ForesterUtil.isEmpty( protein.getDescription() ) + || protein.getDescription().equals( SurfacingConstants.NONE ) ) ) { out.write( protein.getDescription() ); } out.write( separator ); - if ( !( ForesterUtil.isEmpty( protein.getAccession() ) || protein.getAccession() - .equals( SurfacingConstants.NONE ) ) ) { + if ( !( ForesterUtil.isEmpty( protein.getAccession() ) + || protein.getAccession().equals( SurfacingConstants.NONE ) ) ) { out.write( protein.getAccession() ); } out.write( SurfacingConstants.NL ); @@ -524,7 +558,8 @@ public final class SurfacingUtil { public static void executeDomainLengthAnalysis( final String[][] input_file_properties, final int number_of_genomes, final DomainLengthsTable domain_lengths_table, - final File outfile ) throws IOException { + final File outfile ) + throws IOException { final DecimalFormat df = new DecimalFormat( "#.00" ); checkForOutputFileWriteability( outfile ); final BufferedWriter out = new BufferedWriter( new FileWriter( outfile ) ); @@ -582,21 +617,22 @@ public final class SurfacingUtil { /** * Warning: This side-effects 'all_bin_domain_combinations_encountered'! - * - * + * + * * @param output_file * @param all_bin_domain_combinations_changed * @param sum_of_all_domains_encountered * @param all_bin_domain_combinations_encountered * @param is_gains_analysis - * @param protein_length_stats_by_dc + * @param protein_length_stats_by_dc * @throws IOException */ public static void executeFitchGainsAnalysis( final File output_file, final List all_bin_domain_combinations_changed, final int sum_of_all_domains_encountered, final SortedSet all_bin_domain_combinations_encountered, - final boolean is_gains_analysis ) throws IOException { + final boolean is_gains_analysis ) + throws IOException { checkForOutputFileWriteability( output_file ); final Writer out = ForesterUtil.createBufferedWriter( output_file ); final SortedMap bdc_to_counts = ForesterUtil @@ -659,17 +695,17 @@ public final class SurfacingUtil { out.write( "All domains : " + sum_of_all_domains_encountered ); out.close(); - ForesterUtil.programMessage( surfacing.PRG_NAME, - "Wrote fitch domain combination dynamics counts analysis to \"" + output_file - + "\"" ); + ForesterUtil + .programMessage( surfacing.PRG_NAME, + "Wrote fitch domain combination dynamics counts analysis to \"" + output_file + "\"" ); } /** - * - * @param all_binary_domains_combination_lost_fitch - * @param use_last_in_fitch_parsimony - * @param perform_dc_fich - * @param consider_directedness_and_adjacency_for_bin_combinations + * + * @param all_binary_domains_combination_lost_fitch + * @param use_last_in_fitch_parsimony + * @param perform_dc_fich + * @param consider_directedness_and_adjacency_for_bin_combinations * @param all_binary_domains_combination_gained if null ignored, otherwise this is to list all binary domain combinations * which were gained under unweighted (Fitch) parsimony. */ @@ -714,10 +750,12 @@ public final class SurfacingUtil { else { domain_parsimony.executeDolloParsimonyOnDomainPresence(); } - SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossMatrix(), outfile_name - + surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS, Format.FORESTER ); - SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossCountsMatrix(), outfile_name - + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS, Format.FORESTER ); + SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossMatrix(), + outfile_name + surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS, + Format.FORESTER ); + SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossCountsMatrix(), + outfile_name + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS, + Format.FORESTER ); SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(), CharacterStateMatrix.GainLossStates.GAIN, outfile_name + surfacing.PARSIMONY_OUTPUT_DOLLO_GAINS_D, @@ -730,8 +768,12 @@ public final class SurfacingUtil { sep, ForesterUtil.LINE_SEPARATOR, null ); - SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(), null, outfile_name - + surfacing.PARSIMONY_OUTPUT_DOLLO_PRESENT_D, sep, ForesterUtil.LINE_SEPARATOR, null ); + SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(), + null, + outfile_name + surfacing.PARSIMONY_OUTPUT_DOLLO_PRESENT_D, + sep, + ForesterUtil.LINE_SEPARATOR, + null ); //HTML: writeBinaryStatesMatrixToList( domain_id_to_go_ids_map, go_id_to_term_map, @@ -765,30 +807,30 @@ public final class SurfacingUtil { all_pfams_lost_as_domains, "_dollo_losses_d", tax_code_to_id_map ); - // writeBinaryStatesMatrixToList( domain_id_to_go_ids_map, - // go_id_to_term_map, - // go_namespace_limit, - // false, - // domain_parsimony.getGainLossMatrix(), - // null, - // outfile_name + surfacing.PARSIMONY_OUTPUT_DOLLO_PRESENT_HTML_D, - // sep, - // ForesterUtil.LINE_SEPARATOR, - // "Dollo Parsimony | Present | Domains", - // "", - // domain_id_to_secondary_features_maps, - // all_pfams_encountered, - // null, - // "_dollo_present_d", - // tax_code_to_id_map ); + writeBinaryStatesMatrixToList( domain_id_to_go_ids_map, + go_id_to_term_map, + go_namespace_limit, + false, + domain_parsimony.getGainLossMatrix(), + null, + outfile_name + surfacing.PARSIMONY_OUTPUT_DOLLO_PRESENT_HTML_D, + sep, + ForesterUtil.LINE_SEPARATOR, + "Dollo Parsimony | Present | Domains", + "", + domain_id_to_secondary_features_maps, + all_pfams_encountered, + null, + "_dollo_present_d", + tax_code_to_id_map ); preparePhylogeny( local_phylogeny_l, domain_parsimony, date_time, "Dollo parsimony on domain presence/absence", "dollo_on_domains_" + outfile_name, parameters_str ); - SurfacingUtil.writePhylogenyToFile( local_phylogeny_l, outfile_name - + surfacing.DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO ); + SurfacingUtil.writePhylogenyToFile( local_phylogeny_l, + outfile_name + surfacing.DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO ); try { writeAllDomainsChangedOnAllSubtrees( local_phylogeny_l, true, outfile_name, "_dollo_all_gains_d" ); writeAllDomainsChangedOnAllSubtrees( local_phylogeny_l, false, outfile_name, "_dollo_all_losses_d" ); @@ -803,23 +845,27 @@ public final class SurfacingUtil { local_phylogeny_l = phylogeny.copy(); String randomization = "no"; if ( radomize_fitch_parsimony ) { - domain_parsimony.executeFitchParsimonyOnBinaryDomainCombintion( random_number_seed_for_fitch_parsimony ); + domain_parsimony + .executeFitchParsimonyOnBinaryDomainCombintion( random_number_seed_for_fitch_parsimony ); randomization = "yes, seed = " + random_number_seed_for_fitch_parsimony; } else { domain_parsimony.executeFitchParsimonyOnBinaryDomainCombintion( use_last_in_fitch_parsimony ); } - SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossMatrix(), outfile_name - + surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS, Format.FORESTER ); - SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossCountsMatrix(), outfile_name - + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS, Format.FORESTER ); - SurfacingUtil - .writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(), - CharacterStateMatrix.GainLossStates.GAIN, - outfile_name + surfacing.PARSIMONY_OUTPUT_FITCH_GAINS_BC, - sep, - ForesterUtil.LINE_SEPARATOR, - null ); + SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossMatrix(), + outfile_name + + surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS, + Format.FORESTER ); + SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossCountsMatrix(), + outfile_name + + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS, + Format.FORESTER ); + SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(), + CharacterStateMatrix.GainLossStates.GAIN, + outfile_name + surfacing.PARSIMONY_OUTPUT_FITCH_GAINS_BC, + sep, + ForesterUtil.LINE_SEPARATOR, + null ); SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(), CharacterStateMatrix.GainLossStates.LOSS, outfile_name @@ -827,30 +873,30 @@ public final class SurfacingUtil { sep, ForesterUtil.LINE_SEPARATOR, null ); - SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(), null, outfile_name - + surfacing.PARSIMONY_OUTPUT_FITCH_PRESENT_BC, sep, ForesterUtil.LINE_SEPARATOR, null ); + SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(), + null, + outfile_name + + surfacing.PARSIMONY_OUTPUT_FITCH_PRESENT_BC, + sep, + ForesterUtil.LINE_SEPARATOR, + null ); if ( all_binary_domains_combination_gained_fitch != null ) { - collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(), - dc_type, - all_binary_domains_combination_gained_fitch, - true ); + collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile( domain_parsimony + .getGainLossMatrix(), dc_type, all_binary_domains_combination_gained_fitch, true ); } if ( all_binary_domains_combination_lost_fitch != null ) { - collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(), - dc_type, - all_binary_domains_combination_lost_fitch, - false ); + collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile( domain_parsimony + .getGainLossMatrix(), dc_type, all_binary_domains_combination_lost_fitch, false ); } if ( output_binary_domain_combinations_for_graphs ) { - SurfacingUtil - .writeBinaryStatesMatrixAsListToFileForBinaryCombinationsForGraphAnalysis( domain_parsimony - .getGainLossMatrix(), - null, - outfile_name - + surfacing.PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS, - sep, - ForesterUtil.LINE_SEPARATOR, - BinaryDomainCombination.OutputFormat.DOT ); + SurfacingUtil.writeBinaryStatesMatrixAsListToFileForBinaryCombinationsForGraphAnalysis( domain_parsimony + .getGainLossMatrix(), + null, + outfile_name + + surfacing.PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS, + sep, + ForesterUtil.LINE_SEPARATOR, + BinaryDomainCombination.OutputFormat.DOT ); } // HTML: writeBinaryStatesMatrixToList( domain_id_to_go_ids_map, @@ -905,11 +951,13 @@ public final class SurfacingUtil { go_id_to_term_map, outfile_name, all_pfams_encountered ); - writePfamsToFile( outfile_name + surfacing.ALL_PFAMS_GAINED_AS_DOMAINS_SUFFIX, all_pfams_gained_as_domains ); + writePfamsToFile( outfile_name + surfacing.ALL_PFAMS_GAINED_AS_DOMAINS_SUFFIX, + all_pfams_gained_as_domains ); writePfamsToFile( outfile_name + surfacing.ALL_PFAMS_LOST_AS_DOMAINS_SUFFIX, all_pfams_lost_as_domains ); writePfamsToFile( outfile_name + surfacing.ALL_PFAMS_GAINED_AS_DC_SUFFIX, all_pfams_gained_as_dom_combinations ); - writePfamsToFile( outfile_name + surfacing.ALL_PFAMS_LOST_AS_DC_SUFFIX, all_pfams_lost_as_dom_combinations ); + writePfamsToFile( outfile_name + surfacing.ALL_PFAMS_LOST_AS_DC_SUFFIX, + all_pfams_lost_as_dom_combinations ); preparePhylogeny( local_phylogeny_l, domain_parsimony, date_time, @@ -917,8 +965,10 @@ public final class SurfacingUtil { + randomization, "fitch_on_binary_domain_combinations_" + outfile_name, parameters_str ); - SurfacingUtil.writePhylogenyToFile( local_phylogeny_l, outfile_name - + surfacing.BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH ); + SurfacingUtil + .writePhylogenyToFile( local_phylogeny_l, + outfile_name + + surfacing.BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH ); calculateIndependentDomainCombinationGains( local_phylogeny_l, outfile_name + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX, @@ -951,42 +1001,43 @@ public final class SurfacingUtil { phylogeny ); Phylogeny local_phylogeny_copy = phylogeny.copy(); secondary_features_parsimony.executeDolloParsimonyOnSecondaryFeatures( mapping_results_map ); - SurfacingUtil.writeMatrixToFile( secondary_features_parsimony.getGainLossMatrix(), outfile_name - + surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES, Format.FORESTER ); - SurfacingUtil.writeMatrixToFile( secondary_features_parsimony.getGainLossCountsMatrix(), outfile_name - + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES, Format.FORESTER ); - SurfacingUtil - .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(), - CharacterStateMatrix.GainLossStates.GAIN, - outfile_name - + surfacing.PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES, - sep, - ForesterUtil.LINE_SEPARATOR, - null ); - SurfacingUtil - .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(), - CharacterStateMatrix.GainLossStates.LOSS, - outfile_name - + surfacing.PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES, - sep, - ForesterUtil.LINE_SEPARATOR, - null ); - SurfacingUtil - .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(), - null, - outfile_name - + surfacing.PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES, - sep, - ForesterUtil.LINE_SEPARATOR, - null ); + SurfacingUtil.writeMatrixToFile( secondary_features_parsimony.getGainLossMatrix(), + outfile_name + surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES, + Format.FORESTER ); + SurfacingUtil.writeMatrixToFile( secondary_features_parsimony.getGainLossCountsMatrix(), + outfile_name + + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES, + Format.FORESTER ); + SurfacingUtil.writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(), + CharacterStateMatrix.GainLossStates.GAIN, + outfile_name + + surfacing.PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES, + sep, + ForesterUtil.LINE_SEPARATOR, + null ); + SurfacingUtil.writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(), + CharacterStateMatrix.GainLossStates.LOSS, + outfile_name + + surfacing.PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES, + sep, + ForesterUtil.LINE_SEPARATOR, + null ); + SurfacingUtil.writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(), + null, + outfile_name + + surfacing.PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES, + sep, + ForesterUtil.LINE_SEPARATOR, + null ); preparePhylogeny( local_phylogeny_copy, secondary_features_parsimony, date_time, "Dollo parsimony on secondary feature presence/absence", "dollo_on_secondary_features_" + outfile_name, parameters_str ); - SurfacingUtil.writePhylogenyToFile( local_phylogeny_copy, outfile_name - + surfacing.SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO ); + SurfacingUtil + .writePhylogenyToFile( local_phylogeny_copy, + outfile_name + surfacing.SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO ); // FITCH DOMAIN COMBINATIONS // ------------------------- local_phylogeny_copy = phylogeny.copy(); @@ -1000,15 +1051,25 @@ public final class SurfacingUtil { + randomization, "fitch_on_binary_domain_combinations_" + outfile_name, parameters_str ); - SurfacingUtil.writePhylogenyToFile( local_phylogeny_copy, outfile_name - + surfacing.BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH_MAPPED ); - calculateIndependentDomainCombinationGains( local_phylogeny_copy, outfile_name - + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_MAPPED_OUTPUT_SUFFIX, outfile_name - + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_MAPPED_OUTPUT_SUFFIX, outfile_name - + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_SUFFIX, outfile_name - + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_UNIQUE_SUFFIX, outfile_name - + "_MAPPED_indep_dc_gains_fitch_lca_ranks.txt", outfile_name - + "_MAPPED_indep_dc_gains_fitch_lca_taxonomies.txt", null, null, null, null ); + SurfacingUtil + .writePhylogenyToFile( local_phylogeny_copy, + outfile_name + + surfacing.BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH_MAPPED ); + calculateIndependentDomainCombinationGains( local_phylogeny_copy, + outfile_name + + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_MAPPED_OUTPUT_SUFFIX, + outfile_name + + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_MAPPED_OUTPUT_SUFFIX, + outfile_name + + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_SUFFIX, + outfile_name + + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_UNIQUE_SUFFIX, + outfile_name + "_MAPPED_indep_dc_gains_fitch_lca_ranks.txt", + outfile_name + "_MAPPED_indep_dc_gains_fitch_lca_taxonomies.txt", + null, + null, + null, + null ); } public static void executePlusMinusAnalysis( final File output_file, @@ -1053,23 +1114,26 @@ public final class SurfacingUtil { catch ( final IOException e ) { ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() ); } - ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \"" - + html_out_dom + "\"" ); - ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \"" - + plain_out_dom + "\"" ); - ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \"" + html_out_dc - + "\"" ); - ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based passing GO ids to \"" - + passing_domains_go_ids_out_dom + "\"" ); - ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based all GO ids to \"" - + all_domains_go_ids_out_dom + "\"" ); + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Wrote plus minus domain analysis results to \"" + html_out_dom + "\"" ); + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Wrote plus minus domain analysis results to \"" + plain_out_dom + "\"" ); + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Wrote plus minus domain analysis results to \"" + html_out_dc + "\"" ); + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Wrote plus minus domain analysis based passing GO ids to \"" + + passing_domains_go_ids_out_dom + "\"" ); + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Wrote plus minus domain analysis based all GO ids to \"" + + all_domains_go_ids_out_dom + "\"" ); } public static void extractProteinNames( final List proteins, final List query_domain_ids_nc_order, final Writer out, final String separator, - final String limit_to_species ) throws IOException { + final String limit_to_species ) + throws IOException { for( final Protein protein : proteins ) { if ( ForesterUtil.isEmpty( limit_to_species ) || protein.getSpecies().getSpeciesId().equalsIgnoreCase( limit_to_species ) ) { @@ -1098,13 +1162,13 @@ public final class SurfacingUtil { } out.write( "]" ); out.write( separator ); - if ( !( ForesterUtil.isEmpty( protein.getDescription() ) || protein.getDescription() - .equals( SurfacingConstants.NONE ) ) ) { + if ( !( ForesterUtil.isEmpty( protein.getDescription() ) + || protein.getDescription().equals( SurfacingConstants.NONE ) ) ) { out.write( protein.getDescription() ); } out.write( separator ); - if ( !( ForesterUtil.isEmpty( protein.getAccession() ) || protein.getAccession() - .equals( SurfacingConstants.NONE ) ) ) { + if ( !( ForesterUtil.isEmpty( protein.getAccession() ) + || protein.getAccession().equals( SurfacingConstants.NONE ) ) ) { out.write( protein.getAccession() ); } out.write( SurfacingConstants.NL ); @@ -1119,7 +1183,8 @@ public final class SurfacingUtil { final Writer out, final String separator, final String limit_to_species, - final double domain_e_cutoff ) throws IOException { + final double domain_e_cutoff ) + throws IOException { //System.out.println( "Per domain E-value: " + domain_e_cutoff ); for( final Species species : protein_lists_per_species.keySet() ) { //System.out.println( species + ":" ); @@ -1173,13 +1238,13 @@ public final class SurfacingUtil { out.write( ":" + domain.getPerDomainEvalue() ); } out.write( "}" ); - if ( !( ForesterUtil.isEmpty( protein.getDescription() ) || protein.getDescription() - .equals( SurfacingConstants.NONE ) ) ) { + if ( !( ForesterUtil.isEmpty( protein.getDescription() ) + || protein.getDescription().equals( SurfacingConstants.NONE ) ) ) { out.write( protein.getDescription() ); } out.write( separator ); - if ( !( ForesterUtil.isEmpty( protein.getAccession() ) || protein.getAccession() - .equals( SurfacingConstants.NONE ) ) ) { + if ( !( ForesterUtil.isEmpty( protein.getAccession() ) + || protein.getAccession().equals( SurfacingConstants.NONE ) ) ) { out.write( protein.getAccession() ); } out.write( SurfacingConstants.NL ); @@ -1224,10 +1289,10 @@ public final class SurfacingUtil { while ( it.hasNext() ) { final PhylogenyNode n = it.next(); if ( ForesterUtil.isEmpty( n.getName() ) - && ( !n.getNodeData().isHasTaxonomy() || ForesterUtil.isEmpty( n.getNodeData().getTaxonomy() - .getScientificName() ) ) - && ( !n.getNodeData().isHasTaxonomy() || ForesterUtil.isEmpty( n.getNodeData().getTaxonomy() - .getCommonName() ) ) ) { + && ( !n.getNodeData().isHasTaxonomy() + || ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) + && ( !n.getNodeData().isHasTaxonomy() + || ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getCommonName() ) ) ) { if ( n.getParent() != null ) { names.append( " " ); names.append( n.getParent().getName() ); @@ -1261,25 +1326,27 @@ public final class SurfacingUtil { Phylogeny intree = null; final String error = ForesterUtil.isReadableFile( intree_file ); if ( !ForesterUtil.isEmpty( error ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read input tree file [" + intree_file + "]: " - + error ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "cannot read input tree file [" + intree_file + "]: " + error ); } try { final Phylogeny[] p_array = ParserBasedPhylogenyFactory.getInstance() .create( intree_file, ParserUtils.createParserDependingOnFileType( intree_file, true ) ); if ( p_array.length < 1 ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file - + "] does not contain any phylogeny in phyloXML format" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "file [" + intree_file + + "] does not contain any phylogeny in phyloXML format" ); } else if ( p_array.length > 1 ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file - + "] contains more than one phylogeny in phyloXML format" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "file [" + intree_file + + "] contains more than one phylogeny in phyloXML format" ); } intree = p_array[ 0 ]; } catch ( final Exception e ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read input tree from file [" + intree_file - + "]: " + error ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "failed to read input tree from file [" + intree_file + "]: " + error ); } if ( ( intree == null ) || intree.isEmpty() ) { ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" ); @@ -1287,23 +1354,17 @@ public final class SurfacingUtil { if ( !intree.isRooted() ) { ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is not rooted" ); } - if ( intree.getNumberOfExternalNodes() < number_of_genomes ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, - "number of external nodes [" + intree.getNumberOfExternalNodes() - + "] of input tree [" + intree_file - + "] is smaller than the number of genomes the be analyzed [" - + number_of_genomes + "]" ); - } final StringBuilder parent_names = new StringBuilder(); final int nodes_lacking_name = getNumberOfNodesLackingName( intree, parent_names ); if ( nodes_lacking_name > 0 ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] has " - + nodes_lacking_name + " node(s) lacking a name [parent names:" + parent_names + "]" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "input tree [" + intree_file + "] has " + nodes_lacking_name + + " node(s) lacking a name [parent names:" + parent_names + "]" ); } preparePhylogenyForParsimonyAnalyses( intree, input_file_properties ); if ( !intree.isCompletelyBinary() ) { - ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "input tree [" + intree_file - + "] is not completely binary" ); + ForesterUtil.printWarningMessage( surfacing.PRG_NAME, + "input tree [" + intree_file + "] is not completely binary" ); } intrees[ i++ ] = intree; } @@ -1314,24 +1375,27 @@ public final class SurfacingUtil { Phylogeny intree = null; final String error = ForesterUtil.isReadableFile( intree_file ); if ( !ForesterUtil.isEmpty( error ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read input tree file [" + intree_file + "]: " + error ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "cannot read input tree file [" + intree_file + "]: " + error ); } try { final Phylogeny[] phys = ParserBasedPhylogenyFactory.getInstance() .create( intree_file, ParserUtils.createParserDependingOnFileType( intree_file, true ) ); if ( phys.length < 1 ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file - + "] does not contain any phylogeny in phyloXML format" ); + ForesterUtil + .fatalError( surfacing.PRG_NAME, + "file [" + intree_file + "] does not contain any phylogeny in phyloXML format" ); } else if ( phys.length > 1 ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file - + "] contains more than one phylogeny in phyloXML format" ); + ForesterUtil + .fatalError( surfacing.PRG_NAME, + "file [" + intree_file + "] contains more than one phylogeny in phyloXML format" ); } intree = phys[ 0 ]; } catch ( final Exception e ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read input tree from file [" + intree_file + "]: " - + error ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "failed to read input tree from file [" + intree_file + "]: " + error ); } if ( ( intree == null ) || intree.isEmpty() ) { ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" ); @@ -1402,8 +1466,8 @@ public final class SurfacingUtil { while ( n != null ) { if ( n.getNodeData().isHasTaxonomy() && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) { - group = ForesterUtil.obtainNormalizedTaxonomyGroup( n.getNodeData().getTaxonomy() - .getScientificName() ); + group = ForesterUtil + .obtainNormalizedTaxonomyGroup( n.getNodeData().getTaxonomy().getScientificName() ); } if ( ForesterUtil.isEmpty( group ) && !ForesterUtil.isEmpty( n.getName() ) ) { group = ForesterUtil.obtainNormalizedTaxonomyGroup( n.getName() ); @@ -1414,7 +1478,7 @@ public final class SurfacingUtil { n = n.getParent(); } if ( ForesterUtil.isEmpty( group ) ) { - throw new IllegalArgumentException( "no group found for taxonomy code \"" + tax_code + "\"" ); + group = TaxonomyGroups.OTHER; } _TAXCODE_TAXGROUP_MAP.put( tax_code, group ); } @@ -1499,8 +1563,9 @@ public final class SurfacingUtil { final String[] genomes = new String[ input_file_properties.length ]; for( int i = 0; i < input_file_properties.length; ++i ) { if ( intree.getNodes( input_file_properties[ i ][ 1 ] ).size() > 1 ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ] - + "] is not unique in input tree " + intree.getName() ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "node named [" + input_file_properties[ i ][ 1 ] + + "] is not unique in input tree " + intree.getName() ); } genomes[ i ] = input_file_properties[ i ][ 1 ]; } @@ -1528,7 +1593,6 @@ public final class SurfacingUtil { } } } - // final List igns = PhylogenyMethods.deleteExternalNodesPositiveSelection( genomes, intree ); if ( igns.size() > 0 ) { System.out.println( "Not using the following " + igns.size() + " nodes:" ); @@ -1537,15 +1601,29 @@ public final class SurfacingUtil { } System.out.println( "--" ); } + //Test for node names: + final SortedSet not_found = new TreeSet(); + final SortedSet not_unique = new TreeSet(); for( final String[] input_file_propertie : input_file_properties ) { - try { - intree.getNode( input_file_propertie[ 1 ] ); + final String name = input_file_propertie[ 1 ]; + final List nodes = intree.getNodes( name ); + if ( ( nodes == null ) || ( nodes.size() < 1 ) ) { + not_found.add( name ); } - catch ( final IllegalArgumentException e ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_propertie[ 1 ] - + "] not present/not unique in input tree" ); + if ( nodes.size() > 1 ) { + not_unique.add( name ); } } + if ( not_found.size() > 0 ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, + "the following " + not_found.size() + + " node(s) are not present in the input tree: " + not_found ); + } + if ( not_unique.size() > 0 ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, + "the following " + not_unique.size() + + " node(s) are not unique in the input tree: " + not_unique ); + } } public static void printOutPercentageOfMultidomainProteins( final SortedMap all_genomes_domains_per_potein_histo, @@ -1594,17 +1672,17 @@ public final class SurfacingUtil { final Set paths = new HashSet(); for( int i = 0; i < input_file_properties.length; ++i ) { if ( !PhyloXmlUtil.TAXOMONY_CODE_PATTERN.matcher( input_file_properties[ i ][ 1 ] ).matches() ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for species code: " - + input_file_properties[ i ][ 1 ] ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "illegal format for species code: " + input_file_properties[ i ][ 1 ] ); } if ( specs.contains( input_file_properties[ i ][ 1 ] ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "species code " + input_file_properties[ i ][ 1 ] - + " is not unique" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "species code " + input_file_properties[ i ][ 1 ] + " is not unique" ); } specs.add( input_file_properties[ i ][ 1 ] ); if ( paths.contains( input_file_properties[ i ][ 0 ] ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "path " + input_file_properties[ i ][ 0 ] - + " is not unique" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "path " + input_file_properties[ i ][ 0 ] + " is not unique" ); } paths.add( input_file_properties[ i ][ 0 ] ); final String error = ForesterUtil.isReadableFile( new File( input_file_properties[ i ][ 0 ] ) ); @@ -1622,8 +1700,9 @@ public final class SurfacingUtil { final List numbers ) { if ( cla.isOptionSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) { if ( !cla.isOptionValueSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for 'plus-minus' file: -" - + surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "no value for 'plus-minus' file: -" + surfacing.PLUS_MINUS_ANALYSIS_OPTION + + "=" ); } final File plus_minus_file = new File( cla.getOptionValue( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ); final String msg = ForesterUtil.isReadableFile( plus_minus_file ); @@ -1691,18 +1770,18 @@ public final class SurfacingUtil { factor = Double.parseDouble( species.substring( 3 ) ); } catch ( final NumberFormatException e ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, "could not parse double value for factor from: \"" - + species.substring( 3 ) + "\"" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "could not parse double value for factor from: \"" + + species.substring( 3 ) + "\"" ); } } else if ( species.startsWith( "#" ) ) { // Comment, ignore. } else { - ForesterUtil - .fatalError( surfacing.PRG_NAME, - "species/genome names in 'plus minus' file must begin with '*' (high copy target genome), '+' (high copy base genomes), '-' (low copy genomes), '$D=' minimal Difference (default is 1), '$F=' factor (default is 1.0), double), or '#' (ignore) suffix, encountered: \"" - + species + "\"" ); + ForesterUtil.fatalError( surfacing.PRG_NAME, + "species/genome names in 'plus minus' file must begin with '*' (high copy target genome), '+' (high copy base genomes), '-' (low copy genomes), '$D=' minimal Difference (default is 1), '$F=' factor (default is 1.0), double), or '#' (ignore) suffix, encountered: \"" + + species + "\"" ); } numbers.add( new Integer( min_diff + "" ) ); numbers.add( new Double( factor + "" ) ); @@ -1715,8 +1794,8 @@ public final class SurfacingUtil { /* * species | protein id | n-terminal domain | c-terminal domain | n-terminal domain per domain E-value | c-terminal domain per domain E-value - * - * + * + * */ static public StringBuffer proteinToDomainCombinations( final Protein protein, final String protein_id, @@ -1836,7 +1915,8 @@ public final class SurfacingUtil { public static void writeAllDomainsChangedOnAllSubtrees( final Phylogeny p, final boolean get_gains, final String outdir, - final String suffix_for_filename ) throws IOException { + final String suffix_for_filename ) + throws IOException { CharacterStateMatrix.GainLossStates state = CharacterStateMatrix.GainLossStates.GAIN; if ( !get_gains ) { state = CharacterStateMatrix.GainLossStates.LOSS; @@ -1886,9 +1966,19 @@ public final class SurfacingUtil { catch ( final IOException e ) { ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() ); } - ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote binary domain combination for \"" - + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ", " - + input_file_properties[ i ][ 2 ] + ") to: \"" + dc_outfile_dot + "\"" ); + if ( input_file_properties[ i ].length == 3 ) { + ForesterUtil + .programMessage( surfacing.PRG_NAME, + "Wrote binary domain combination for \"" + input_file_properties[ i ][ 0 ] + "\" (" + + input_file_properties[ i ][ 1 ] + ", " + input_file_properties[ i ][ 2 ] + + ") to: \"" + dc_outfile_dot + "\"" ); + } + else { + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Wrote binary domain combination for \"" + input_file_properties[ i ][ 0 ] + + "\" (" + input_file_properties[ i ][ 1 ] + ") to: \"" + + dc_outfile_dot + "\"" ); + } } public static void writeBinaryStatesMatrixAsListToFile( final CharacterStateMatrix matrix, @@ -1912,9 +2002,10 @@ public final class SurfacingUtil { for( int c = 0; c < matrix.getNumberOfCharacters(); ++c ) { // Not nice: // using null to indicate either UNCHANGED_PRESENT or GAIN. - if ( ( matrix.getState( id, c ) == state ) - || ( ( state == null ) && ( ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.GAIN ) || ( matrix - .getState( id, c ) == CharacterStateMatrix.GainLossStates.UNCHANGED_PRESENT ) ) ) ) { + if ( ( matrix.getState( id, c ) == state ) || ( ( state == null ) + && ( ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.GAIN ) || ( matrix + .getState( id, + c ) == CharacterStateMatrix.GainLossStates.UNCHANGED_PRESENT ) ) ) ) { out.write( matrix.getCharacter( c ) ); if ( ( descriptions != null ) && !descriptions.isEmpty() && descriptions.containsKey( matrix.getCharacter( c ) ) ) { @@ -1955,9 +2046,10 @@ public final class SurfacingUtil { for( int c = 0; c < matrix.getNumberOfCharacters(); ++c ) { // Not nice: // using null to indicate either UNCHANGED_PRESENT or GAIN. - if ( ( matrix.getState( id, c ) == state ) - || ( ( state == null ) && ( ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.GAIN ) || ( matrix - .getState( id, c ) == CharacterStateMatrix.GainLossStates.UNCHANGED_PRESENT ) ) ) ) { + if ( ( matrix.getState( id, c ) == state ) || ( ( state == null ) + && ( ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.GAIN ) || ( matrix + .getState( id, + c ) == CharacterStateMatrix.GainLossStates.UNCHANGED_PRESENT ) ) ) ) { BinaryDomainCombination bdc = null; try { bdc = BasicBinaryDomainCombination.obtainInstance( matrix.getCharacter( c ) ); @@ -2089,9 +2181,9 @@ public final class SurfacingUtil { for( int c = 0; c < matrix.getNumberOfCharacters(); ++c ) { // Not nice: // using null to indicate either UNCHANGED_PRESENT or GAIN. - if ( ( matrix.getState( id, c ) == state ) - || ( ( state == null ) && ( ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.UNCHANGED_PRESENT ) || ( matrix - .getState( id, c ) == CharacterStateMatrix.GainLossStates.GAIN ) ) ) ) { + if ( ( matrix.getState( id, c ) == state ) || ( ( state == null ) + && ( ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.UNCHANGED_PRESENT ) + || ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.GAIN ) ) ) ) { final String character = matrix.getCharacter( c ); String domain_0 = ""; String domain_1 = ""; @@ -2146,7 +2238,7 @@ public final class SurfacingUtil { out.write( SurfacingConstants.NL ); out.write( "
" ); out.write( SurfacingConstants.NL ); - } // for( final String id : sorted_ids ) { + } // for( final String id : sorted_ids ) { out.write( "" ); out.write( SurfacingConstants.NL ); out.write( "" ); @@ -2183,13 +2275,14 @@ public final class SurfacingUtil { final DescriptiveStatistics stats = gwcd.getPerGenomeDomainPromiscuityStatistics(); try { per_genome_domain_promiscuity_statistics_writer.write( input_file_properties[ i ][ 1 ] + "\t" ); - per_genome_domain_promiscuity_statistics_writer.write( FORMATTER_3.format( stats.arithmeticMean() ) + "\t" ); + per_genome_domain_promiscuity_statistics_writer + .write( FORMATTER_3.format( stats.arithmeticMean() ) + "\t" ); if ( stats.getN() < 2 ) { per_genome_domain_promiscuity_statistics_writer.write( "n/a" + "\t" ); } else { - per_genome_domain_promiscuity_statistics_writer.write( FORMATTER_3.format( stats - .sampleStandardDeviation() ) + "\t" ); + per_genome_domain_promiscuity_statistics_writer + .write( FORMATTER_3.format( stats.sampleStandardDeviation() ) + "\t" ); } per_genome_domain_promiscuity_statistics_writer.write( FORMATTER_3.format( stats.median() ) + "\t" ); per_genome_domain_promiscuity_statistics_writer.write( ( int ) stats.getMin() + "\t" ); @@ -2205,14 +2298,16 @@ public final class SurfacingUtil { ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() ); } if ( input_file_properties[ i ].length == 3 ) { - ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote domain combination counts for \"" - + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ", " - + input_file_properties[ i ][ 2 ] + ") to: \"" + dc_outfile + "\"" ); + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Wrote domain combination counts for \"" + input_file_properties[ i ][ 0 ] + + "\" (" + input_file_properties[ i ][ 1 ] + ", " + + input_file_properties[ i ][ 2 ] + ") to: \"" + dc_outfile + "\"" ); } else { - ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote domain combination counts for \"" - + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ") to: \"" - + dc_outfile + "\"" ); + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Wrote domain combination counts for \"" + input_file_properties[ i ][ 0 ] + + "\" (" + input_file_properties[ i ][ 1 ] + ") to: \"" + dc_outfile + + "\"" ); } } @@ -2229,7 +2324,8 @@ public final class SurfacingUtil { final boolean verbose, final Map tax_code_to_id_map, final Phylogeny phy, - final Set pos_filter_doms ) throws IOException { + final Set pos_filter_doms ) + throws IOException { if ( ( single_writer != null ) && ( ( split_writers == null ) || split_writers.isEmpty() ) ) { split_writers = new HashMap(); split_writers.put( '_', single_writer ); @@ -2270,7 +2366,8 @@ public final class SurfacingUtil { ( similarity ).setSpeciesOrder( species_order ); } if ( single_writer != null ) { - if ( !ForesterUtil.isEmpty( pos_filter_doms ) && pos_filter_doms.contains( similarity.getDomainId() ) ) { + if ( !ForesterUtil.isEmpty( pos_filter_doms ) + && pos_filter_doms.contains( similarity.getDomainId() ) ) { single_writer.write( "" + similarity.getDomainId() + "" ); @@ -2282,12 +2379,13 @@ public final class SurfacingUtil { single_writer.write( SurfacingConstants.NL ); } else { - Writer local_writer = split_writers.get( ( similarity.getDomainId().charAt( 0 ) + "" ).toLowerCase() - .charAt( 0 ) ); + Writer local_writer = split_writers + .get( ( similarity.getDomainId().charAt( 0 ) + "" ).toLowerCase().charAt( 0 ) ); if ( local_writer == null ) { local_writer = split_writers.get( '0' ); } - if ( !ForesterUtil.isEmpty( pos_filter_doms ) && pos_filter_doms.contains( similarity.getDomainId() ) ) { + if ( !ForesterUtil.isEmpty( pos_filter_doms ) + && pos_filter_doms.contains( similarity.getDomainId() ) ) { local_writer.write( "" + similarity.getDomainId() + "" ); @@ -2355,17 +2453,16 @@ public final class SurfacingUtil { ( similarity ).setSpeciesOrder( species_order ); } if ( simple_tab_writer != null ) { - simple_tab_writer.write( similarity.toStringBuffer( PRINT_OPTION.SIMPLE_TAB_DELIMITED, - tax_code_to_id_map, - null ).toString() ); + simple_tab_writer.write( similarity + .toStringBuffer( PRINT_OPTION.SIMPLE_TAB_DELIMITED, tax_code_to_id_map, null ).toString() ); } if ( single_writer != null ) { single_writer.write( similarity.toStringBuffer( print_option, tax_code_to_id_map, phy ).toString() ); single_writer.write( SurfacingConstants.NL ); } else { - Writer local_writer = split_writers.get( ( similarity.getDomainId().charAt( 0 ) + "" ).toLowerCase() - .charAt( 0 ) ); + Writer local_writer = split_writers + .get( ( similarity.getDomainId().charAt( 0 ) + "" ).toLowerCase().charAt( 0 ) ); if ( local_writer == null ) { local_writer = split_writers.get( '0' ); } @@ -2483,8 +2580,8 @@ public final class SurfacingUtil { writer.toPhyloXML( new File( filename ), phylogeny, 1 ); } catch ( final IOException e ) { - ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "failed to write phylogeny to \"" + filename + "\": " - + e ); + ForesterUtil.printWarningMessage( surfacing.PRG_NAME, + "failed to write phylogeny to \"" + filename + "\": " + e ); } ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote phylogeny to \"" + filename + "\"" ); } @@ -2494,12 +2591,12 @@ public final class SurfacingUtil { final SortedSet filter, final List gwcd_list ) { try { - writeMatrixToFile( DomainParsimonyCalculator.createMatrixOfDomainPresenceOrAbsence( gwcd_list, - positive_filter_file == null ? null - : filter ), + writeMatrixToFile( DomainParsimonyCalculator + .createMatrixOfDomainPresenceOrAbsence( gwcd_list, positive_filter_file == null ? null : filter ), output_file + surfacing.DOMAINS_PRESENT_NEXUS, Format.NEXUS_BINARY ); - writeMatrixToFile( DomainParsimonyCalculator.createMatrixOfBinaryDomainCombinationPresenceOrAbsence( gwcd_list ), + writeMatrixToFile( DomainParsimonyCalculator + .createMatrixOfBinaryDomainCombinationPresenceOrAbsence( gwcd_list ), output_file + surfacing.BDC_PRESENT_NEXUS, Format.NEXUS_BINARY ); } @@ -2511,13 +2608,18 @@ public final class SurfacingUtil { public static void writeProteinListsForAllSpecies( final File output_dir, final SortedMap> protein_lists_per_species, final List gwcd_list, - final double domain_e_cutoff ) { + final double domain_e_cutoff, + final Set pos_filter_doms ) { final SortedSet all_domains = new TreeSet(); for( final GenomeWideCombinableDomains gwcd : gwcd_list ) { all_domains.addAll( gwcd.getAllDomainIds() ); } for( final String domain : all_domains ) { - final File out = new File( output_dir + ForesterUtil.FILE_SEPARATOR + domain + surfacing.SEQ_EXTRACT_SUFFIX ); + if ( !ForesterUtil.isEmpty( pos_filter_doms ) && !pos_filter_doms.contains( domain ) ) { + continue; + } + final File out = new File( output_dir + ForesterUtil.FILE_SEPARATOR + domain + + surfacing.SEQ_EXTRACT_SUFFIX ); checkForOutputFileWriteability( out ); try { final Writer proteins_file_writer = new BufferedWriter( new FileWriter( out ) ); @@ -2538,7 +2640,8 @@ public final class SurfacingUtil { public static void writeTaxonomyLinks( final Writer writer, final String species, - final Map tax_code_to_id_map ) throws IOException { + final Map tax_code_to_id_map ) + throws IOException { if ( ( species.length() > 1 ) && ( species.indexOf( '_' ) < 1 ) ) { writer.write( " [" ); if ( ( tax_code_to_id_map != null ) && tax_code_to_id_map.containsKey( species ) ) { @@ -2660,25 +2763,25 @@ public final class SurfacingUtil { if ( !dc_reapp_counts_to_protein_length_stats.containsKey( count ) ) { dc_reapp_counts_to_protein_length_stats.put( count, new BasicDescriptiveStatistics() ); } - dc_reapp_counts_to_protein_length_stats.get( count ).addValue( protein_length_stats_by_dc.get( dc ) - .arithmeticMean() ); + dc_reapp_counts_to_protein_length_stats.get( count ) + .addValue( protein_length_stats_by_dc.get( dc ).arithmeticMean() ); } if ( domain_number_stats_by_dc != null ) { if ( !dc_reapp_counts_to_domain_number_stats.containsKey( count ) ) { dc_reapp_counts_to_domain_number_stats.put( count, new BasicDescriptiveStatistics() ); } - dc_reapp_counts_to_domain_number_stats.get( count ).addValue( domain_number_stats_by_dc.get( dc ) - .arithmeticMean() ); + dc_reapp_counts_to_domain_number_stats.get( count ) + .addValue( domain_number_stats_by_dc.get( dc ).arithmeticMean() ); } if ( domain_length_stats_by_domain != null ) { if ( !dc_reapp_counts_to_domain_lengths_stats.containsKey( count ) ) { dc_reapp_counts_to_domain_lengths_stats.put( count, new BasicDescriptiveStatistics() ); } final String[] ds = dc.split( "=" ); - dc_reapp_counts_to_domain_lengths_stats.get( count ).addValue( domain_length_stats_by_domain - .get( ds[ 0 ] ).arithmeticMean() ); - dc_reapp_counts_to_domain_lengths_stats.get( count ).addValue( domain_length_stats_by_domain - .get( ds[ 1 ] ).arithmeticMean() ); + dc_reapp_counts_to_domain_lengths_stats.get( count ) + .addValue( domain_length_stats_by_domain.get( ds[ 0 ] ).arithmeticMean() ); + dc_reapp_counts_to_domain_lengths_stats.get( count ) + .addValue( domain_length_stats_by_domain.get( ds[ 1 ] ).arithmeticMean() ); } if ( count > 1 ) { more_than_once.add( dc ); @@ -2801,8 +2904,8 @@ public final class SurfacingUtil { ForesterUtil.LINE_SEPARATOR ); out_for_rank_counts.close(); out_for_ancestor_species_counts.close(); - if ( !ForesterUtil.isEmpty( outfilename_for_protein_stats ) - && ( ( domain_length_stats_by_domain != null ) || ( protein_length_stats_by_dc != null ) || ( domain_number_stats_by_dc != null ) ) ) { + if ( !ForesterUtil.isEmpty( outfilename_for_protein_stats ) && ( ( domain_length_stats_by_domain != null ) + || ( protein_length_stats_by_dc != null ) || ( domain_number_stats_by_dc != null ) ) ) { final BufferedWriter w = new BufferedWriter( new FileWriter( outfilename_for_protein_stats ) ); w.write( "Domain Lengths: " ); w.write( "\n" ); @@ -2857,8 +2960,8 @@ public final class SurfacingUtil { w.write( "\n" ); w.write( "N: " + gained_multiple_times_domain_length_count ); w.write( "\n" ); - w.write( "Avg: " - + ( ( double ) gained_multiple_times_domain_length_sum / gained_multiple_times_domain_length_count ) ); + w.write( "Avg: " + ( ( double ) gained_multiple_times_domain_length_sum + / gained_multiple_times_domain_length_count ) ); w.write( "\n" ); w.write( "\n" ); w.write( "\n" ); @@ -2891,10 +2994,12 @@ public final class SurfacingUtil { catch ( final IOException e ) { ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "Failure to write: " + e ); } - ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote independent domain combination gains fitch counts to [" - + outfilename_for_counts + "]" ); - ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote independent domain combination gains fitch lists to [" - + outfilename_for_dc + "]" ); + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Wrote independent domain combination gains fitch counts to [" + + outfilename_for_counts + "]" ); + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Wrote independent domain combination gains fitch lists to [" + outfilename_for_dc + + "]" ); ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote independent domain combination gains fitch lists to (for GO mapping) [" + outfilename_for_dc_for_go_mapping + "]" ); @@ -3005,8 +3110,8 @@ public final class SurfacingUtil { private static List splitDomainCombination( final String dc ) { final String[] s = dc.split( "=" ); if ( s.length != 2 ) { - ForesterUtil.printErrorMessage( surfacing.PRG_NAME, "Stringyfied domain combination has illegal format: " - + dc ); + ForesterUtil.printErrorMessage( surfacing.PRG_NAME, + "Stringyfied domain combination has illegal format: " + dc ); System.exit( -1 ); } final List l = new ArrayList( 2 ); @@ -3022,7 +3127,8 @@ public final class SurfacingUtil { final File all_pfams_encountered_file = new File( outfile_name + surfacing.ALL_PFAMS_ENCOUNTERED_SUFFIX ); final File all_pfams_encountered_with_go_annotation_file = new File( outfile_name + surfacing.ALL_PFAMS_ENCOUNTERED_WITH_GO_ANNOTATION_SUFFIX ); - final File encountered_pfams_summary_file = new File( outfile_name + surfacing.ENCOUNTERED_PFAMS_SUMMARY_SUFFIX ); + final File encountered_pfams_summary_file = new File( outfile_name + + surfacing.ENCOUNTERED_PFAMS_SUMMARY_SUFFIX ); int biological_process_counter = 0; int cellular_component_counter = 0; int molecular_function_counter = 0; @@ -3089,42 +3195,61 @@ public final class SurfacingUtil { } all_pfams_encountered_writer.close(); all_pfams_encountered_with_go_annotation_writer.close(); - ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote all [" + all_pfams_encountered.size() - + "] encountered Pfams to: \"" + all_pfams_encountered_file + "\"" ); - ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote all [" + pfams_with_mappings_counter - + "] encountered Pfams with GO mappings to: \"" + all_pfams_encountered_with_go_annotation_file - + "\"" ); - ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote summary (including all [" - + pfams_without_mappings_counter + "] encountered Pfams without GO mappings) to: \"" - + encountered_pfams_summary_file + "\"" ); - ForesterUtil.programMessage( surfacing.PRG_NAME, "Sum of Pfams encountered : " - + all_pfams_encountered.size() ); - ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams without a mapping : " - + pfams_without_mappings_counter + " [" - + ( ( 100 * pfams_without_mappings_counter ) / all_pfams_encountered.size() ) + "%]" ); - ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams without mapping to proc. or func. : " - + pfams_without_mappings_to_bp_or_mf_counter + " [" - + ( ( 100 * pfams_without_mappings_to_bp_or_mf_counter ) / all_pfams_encountered.size() ) + "%]" ); - ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams with a mapping : " - + pfams_with_mappings_counter + " [" - + ( ( 100 * pfams_with_mappings_counter ) / all_pfams_encountered.size() ) + "%]" ); - ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams with a mapping to proc. or func. : " - + pfams_with_mappings_to_bp_or_mf_counter + " [" - + ( ( 100 * pfams_with_mappings_to_bp_or_mf_counter ) / all_pfams_encountered.size() ) + "%]" ); - ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams with mapping to biological process: " - + biological_process_counter + " [" - + ( ( 100 * biological_process_counter ) / all_pfams_encountered.size() ) + "%]" ); - ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams with mapping to molecular function: " - + molecular_function_counter + " [" - + ( ( 100 * molecular_function_counter ) / all_pfams_encountered.size() ) + "%]" ); - ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams with mapping to cellular component: " - + cellular_component_counter + " [" - + ( ( 100 * cellular_component_counter ) / all_pfams_encountered.size() ) + "%]" ); + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Wrote all [" + all_pfams_encountered.size() + "] encountered Pfams to: \"" + + all_pfams_encountered_file + "\"" ); + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Wrote all [" + pfams_with_mappings_counter + + "] encountered Pfams with GO mappings to: \"" + + all_pfams_encountered_with_go_annotation_file + "\"" ); + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Wrote summary (including all [" + pfams_without_mappings_counter + + "] encountered Pfams without GO mappings) to: \"" + + encountered_pfams_summary_file + "\"" ); + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Sum of Pfams encountered : " + all_pfams_encountered.size() ); + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Pfams without a mapping : " + pfams_without_mappings_counter + + " [" + ( ( 100 * pfams_without_mappings_counter ) + / all_pfams_encountered.size() ) + + "%]" ); + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Pfams without mapping to proc. or func. : " + + pfams_without_mappings_to_bp_or_mf_counter + " [" + + ( ( 100 * pfams_without_mappings_to_bp_or_mf_counter ) + / all_pfams_encountered.size() ) + + "%]" ); + ForesterUtil + .programMessage( surfacing.PRG_NAME, + "Pfams with a mapping : " + pfams_with_mappings_counter + " [" + + ( ( 100 * pfams_with_mappings_counter ) / all_pfams_encountered.size() ) + + "%]" ); + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Pfams with a mapping to proc. or func. : " + + pfams_with_mappings_to_bp_or_mf_counter + " [" + + ( ( 100 * pfams_with_mappings_to_bp_or_mf_counter ) + / all_pfams_encountered.size() ) + + "%]" ); + ForesterUtil + .programMessage( surfacing.PRG_NAME, + "Pfams with mapping to biological process: " + biological_process_counter + " [" + + ( ( 100 * biological_process_counter ) / all_pfams_encountered.size() ) + + "%]" ); + ForesterUtil + .programMessage( surfacing.PRG_NAME, + "Pfams with mapping to molecular function: " + molecular_function_counter + " [" + + ( ( 100 * molecular_function_counter ) / all_pfams_encountered.size() ) + + "%]" ); + ForesterUtil + .programMessage( surfacing.PRG_NAME, + "Pfams with mapping to cellular component: " + cellular_component_counter + " [" + + ( ( 100 * cellular_component_counter ) / all_pfams_encountered.size() ) + + "%]" ); summary_writer.write( ForesterUtil.LINE_SEPARATOR ); summary_writer.write( "# Sum of Pfams encountered : " + all_pfams_encountered.size() ); summary_writer.write( ForesterUtil.LINE_SEPARATOR ); - summary_writer.write( "# Pfams without a mapping : " + pfams_without_mappings_counter - + " [" + ( ( 100 * pfams_without_mappings_counter ) / all_pfams_encountered.size() ) + "%]" ); + summary_writer.write( "# Pfams without a mapping : " + pfams_without_mappings_counter + " [" + + ( ( 100 * pfams_without_mappings_counter ) / all_pfams_encountered.size() ) + "%]" ); summary_writer.write( ForesterUtil.LINE_SEPARATOR ); summary_writer.write( "# Pfams without mapping to proc. or func. : " + pfams_without_mappings_to_bp_or_mf_counter + " [" @@ -3171,14 +3296,15 @@ public final class SurfacingUtil { final String prefix_for_html, final String character_separator_for_non_html_output, final Map>[] domain_id_to_secondary_features_maps, - final Set all_go_ids ) throws IOException { + final Set all_go_ids ) + throws IOException { boolean any_go_annotation_present = false; boolean first_has_no_go = false; int domain_count = 2; // To distinguish between domains and binary domain combinations. if ( ForesterUtil.isEmpty( domain_1 ) ) { domain_count = 1; } - // The following has a difficult to understand logic. + // The following has a difficult to understand logic. for( int d = 0; d < domain_count; ++d ) { List go_ids = null; boolean go_annotation_present = false; @@ -3251,7 +3377,7 @@ public final class SurfacingUtil { out.write( SurfacingConstants.NL ); } } - } // for( int d = 0; d < domain_count; ++d ) + } // for( int d = 0; d < domain_count; ++d ) if ( !any_go_annotation_present ) { out.write( "" ); writeDomainIdsToHtml( out, domain_0, domain_1, prefix_for_html, domain_id_to_secondary_features_maps ); @@ -3282,7 +3408,8 @@ public final class SurfacingUtil { private static void writeDomainsToIndividualFilePerTreeNode( final Writer individual_files_writer, final String domain_0, - final String domain_1 ) throws IOException { + final String domain_1 ) + throws IOException { individual_files_writer.write( domain_0 ); individual_files_writer.write( ForesterUtil.LINE_SEPARATOR ); if ( !ForesterUtil.isEmpty( domain_1 ) ) { @@ -3299,8 +3426,8 @@ public final class SurfacingUtil { writer.write( ForesterUtil.LINE_SEPARATOR ); } writer.close(); - ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote " + pfams.size() + " pfams to [" + outfile_name - + "]" ); + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Wrote " + pfams.size() + " pfams to [" + outfile_name + "]" ); } catch ( final IOException e ) { ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "Failure to write: " + e );