X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Fsurfacing%2FSurfacingUtil.java;h=73544b7f96b42024ad4ae955e70d9b5b1d1496c1;hb=c914fef4ec7f50e4cf01375a30207992c84659a3;hp=1cc2c7a0c4da0718edc106d48c4219ba93dbb410;hpb=cec76926e7d634373e238e61b805c723ef4c0ca7;p=jalview.git diff --git a/forester/java/src/org/forester/surfacing/SurfacingUtil.java b/forester/java/src/org/forester/surfacing/SurfacingUtil.java index 1cc2c7a..73544b7 100644 --- a/forester/java/src/org/forester/surfacing/SurfacingUtil.java +++ b/forester/java/src/org/forester/surfacing/SurfacingUtil.java @@ -22,10 +22,11 @@ // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA // // Contact: phylosoft @ gmail . com -// WWW: www.phylosoft.org/forester +// WWW: https://sites.google.com/site/cmzmasek/home/software/forester package org.forester.surfacing; +import java.awt.Color; import java.io.BufferedWriter; import java.io.File; import java.io.FileWriter; @@ -39,6 +40,7 @@ import java.util.Collections; import java.util.Comparator; import java.util.HashMap; import java.util.HashSet; +import java.util.Iterator; import java.util.List; import java.util.Map; import java.util.Map.Entry; @@ -65,57 +67,60 @@ import org.forester.go.GoNameSpace; import org.forester.go.GoTerm; import org.forester.go.PfamToGoMapping; import org.forester.io.parsers.nexus.NexusConstants; +import org.forester.io.parsers.phyloxml.PhyloXmlUtil; +import org.forester.io.parsers.util.ParserUtils; import org.forester.io.writers.PhylogenyWriter; -import org.forester.msa.MsaCompactor.SORT_BY; import org.forester.phylogeny.Phylogeny; import org.forester.phylogeny.PhylogenyMethods; import org.forester.phylogeny.PhylogenyNode; -import org.forester.phylogeny.PhylogenyNodeI.NH_CONVERSION_SUPPORT_VALUE_STYLE; +import org.forester.phylogeny.PhylogenyNode.NH_CONVERSION_SUPPORT_VALUE_STYLE; import org.forester.phylogeny.data.BinaryCharacters; import org.forester.phylogeny.data.Confidence; +import org.forester.phylogeny.data.Taxonomy; +import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory; import org.forester.phylogeny.iterators.PhylogenyNodeIterator; import org.forester.protein.BasicDomain; import org.forester.protein.BasicProtein; import org.forester.protein.BinaryDomainCombination; import org.forester.protein.Domain; -import org.forester.protein.DomainId; import org.forester.protein.Protein; import org.forester.species.Species; import org.forester.surfacing.DomainSimilarityCalculator.Detailedness; -import org.forester.surfacing.DomainSimilarityCalculator.GoAnnotationOutput; import org.forester.surfacing.GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder; +import org.forester.surfacing.PrintableDomainSimilarity.PRINT_OPTION; import org.forester.util.AsciiHistogram; import org.forester.util.BasicDescriptiveStatistics; import org.forester.util.BasicTable; import org.forester.util.BasicTableParser; +import org.forester.util.CommandLineArguments; import org.forester.util.DescriptiveStatistics; import org.forester.util.ForesterUtil; +import org.forester.util.TaxonomyColors; public final class SurfacingUtil { - private final static NumberFormat FORMATTER = new DecimalFormat( "0.0E0" ); - private final static NumberFormat FORMATTER_3 = new DecimalFormat( "0.000" ); - private static final Comparator ASCENDING_CONFIDENCE_VALUE_ORDER = new Comparator() { - - @Override - public int compare( final Domain d1, - final Domain d2 ) { - if ( d1.getPerSequenceEvalue() < d2 - .getPerSequenceEvalue() ) { - return -1; - } - else if ( d1 - .getPerSequenceEvalue() > d2 - .getPerSequenceEvalue() ) { - return 1; - } - else { - return d1.compareTo( d2 ); - } - } - }; - public final static Pattern PATTERN_SP_STYLE_TAXONOMY = Pattern.compile( "^[A-Z0-9]{3,5}$" ); - private static final boolean USE_LAST = true; + public final static Pattern PATTERN_SP_STYLE_TAXONOMY = Pattern.compile( "^[A-Z0-9]{3,5}$" ); + private final static Map _TAXCODE_HEXCOLORSTRING_MAP = new HashMap(); + private static final Comparator ASCENDING_CONFIDENCE_VALUE_ORDER = new Comparator() { + + @Override + public int compare( final Domain d1, + final Domain d2 ) { + if ( d1.getPerSequenceEvalue() < d2 + .getPerSequenceEvalue() ) { + return -1; + } + else if ( d1 + .getPerSequenceEvalue() > d2 + .getPerSequenceEvalue() ) { + return 1; + } + else { + return d1.compareTo( d2 ); + } + } + }; + private final static NumberFormat FORMATTER_3 = new DecimalFormat( "0.000" ); private SurfacingUtil() { // Hidden constructor. @@ -123,49 +128,20 @@ public final class SurfacingUtil { public static void addAllBinaryDomainCombinationToSet( final GenomeWideCombinableDomains genome, final SortedSet binary_domain_combinations ) { - final SortedMap all_cd = genome.getAllCombinableDomainsIds(); - for( final DomainId domain_id : all_cd.keySet() ) { + final SortedMap all_cd = genome.getAllCombinableDomainsIds(); + for( final String domain_id : all_cd.keySet() ) { binary_domain_combinations.addAll( all_cd.get( domain_id ).toBinaryDomainCombinations() ); } } public static void addAllDomainIdsToSet( final GenomeWideCombinableDomains genome, - final SortedSet domain_ids ) { - final SortedSet domains = genome.getAllDomainIds(); - for( final DomainId domain : domains ) { + final SortedSet domain_ids ) { + final SortedSet domains = genome.getAllDomainIds(); + for( final String domain : domains ) { domain_ids.add( domain ); } } - public static void addHtmlHead( final Writer w, final String title ) throws IOException { - w.write( SurfacingConstants.NL ); - w.write( "" ); - w.write( "" ); - w.write( title ); - w.write( "" ); - w.write( SurfacingConstants.NL ); - w.write( "" ); - w.write( SurfacingConstants.NL ); - w.write( "" ); - w.write( SurfacingConstants.NL ); - } - public static DescriptiveStatistics calculateDescriptiveStatisticsForMeanValues( final Set similarities ) { final DescriptiveStatistics stats = new BasicDescriptiveStatistics(); for( final DomainSimilarity similarity : similarities ) { @@ -174,508 +150,372 @@ public final class SurfacingUtil { return stats; } - private static void calculateIndependentDomainCombinationGains( final Phylogeny local_phylogeny_l, - final String outfilename_for_counts, - final String outfilename_for_dc, - final String outfilename_for_dc_for_go_mapping, - final String outfilename_for_dc_for_go_mapping_unique, - final String outfilename_for_rank_counts, - final String outfilename_for_ancestor_species_counts, - final String outfilename_for_protein_stats, - final Map protein_length_stats_by_dc, - final Map domain_number_stats_by_dc, - final Map domain_length_stats_by_domain ) { - try { - // - // if ( protein_length_stats_by_dc != null ) { - // for( final Entry entry : protein_length_stats_by_dc.entrySet() ) { - // System.out.print( entry.getKey().toString() ); - // System.out.print( ": " ); - // double[] a = entry.getValue().getDataAsDoubleArray(); - // for( int i = 0; i < a.length; i++ ) { - // System.out.print( a[ i ] + " " ); - // } - // System.out.println(); - // } - // } - // if ( domain_number_stats_by_dc != null ) { - // for( final Entry entry : domain_number_stats_by_dc.entrySet() ) { - // System.out.print( entry.getKey().toString() ); - // System.out.print( ": " ); - // double[] a = entry.getValue().getDataAsDoubleArray(); - // for( int i = 0; i < a.length; i++ ) { - // System.out.print( a[ i ] + " " ); - // } - // System.out.println(); - // } - // } - // - final BufferedWriter out_counts = new BufferedWriter( new FileWriter( outfilename_for_counts ) ); - final BufferedWriter out_dc = new BufferedWriter( new FileWriter( outfilename_for_dc ) ); - final BufferedWriter out_dc_for_go_mapping = new BufferedWriter( new FileWriter( outfilename_for_dc_for_go_mapping ) ); - final BufferedWriter out_dc_for_go_mapping_unique = new BufferedWriter( new FileWriter( outfilename_for_dc_for_go_mapping_unique ) ); - final SortedMap dc_gain_counts = new TreeMap(); - for( final PhylogenyNodeIterator it = local_phylogeny_l.iteratorPostorder(); it.hasNext(); ) { - final PhylogenyNode n = it.next(); - final Set gained_dc = n.getNodeData().getBinaryCharacters().getGainedCharacters(); - for( final String dc : gained_dc ) { - if ( dc_gain_counts.containsKey( dc ) ) { - dc_gain_counts.put( dc, dc_gain_counts.get( dc ) + 1 ); + public static void checkForOutputFileWriteability( final File outfile ) { + final String error = ForesterUtil.isWritableFile( outfile ); + if ( !ForesterUtil.isEmpty( error ) ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, error ); + } + } + + public static void checkWriteabilityForPairwiseComparisons( final PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option, + final String[][] input_file_properties, + final String automated_pairwise_comparison_suffix, + final File outdir ) { + for( int i = 0; i < input_file_properties.length; ++i ) { + for( int j = 0; j < i; ++j ) { + final String species_i = input_file_properties[ i ][ 1 ]; + final String species_j = input_file_properties[ j ][ 1 ]; + String pairwise_similarities_output_file_str = surfacing.PAIRWISE_DOMAIN_COMPARISONS_PREFIX + species_i + + "_" + species_j + automated_pairwise_comparison_suffix; + switch ( domain_similarity_print_option ) { + case HTML: + if ( !pairwise_similarities_output_file_str.endsWith( ".html" ) ) { + pairwise_similarities_output_file_str += ".html"; + } + break; + } + final String error = ForesterUtil + .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 ); + } + } + } + } + + public static void collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile( final CharacterStateMatrix matrix, + final BinaryDomainCombination.DomainCombinationType dc_type, + final List all_binary_domains_combination_gained, + final boolean get_gains ) { + final SortedSet sorted_ids = new TreeSet(); + for( int i = 0; i < matrix.getNumberOfIdentifiers(); ++i ) { + sorted_ids.add( matrix.getIdentifier( i ) ); + } + 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 ) ) ) { + if ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) { + all_binary_domains_combination_gained.add( AdjactantDirectedBinaryDomainCombination + .createInstance( matrix.getCharacter( c ) ) ); + } + else if ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED ) { + all_binary_domains_combination_gained.add( DirectedBinaryDomainCombination + .createInstance( matrix.getCharacter( c ) ) ); } else { - dc_gain_counts.put( dc, 1 ); + all_binary_domains_combination_gained.add( BasicBinaryDomainCombination.createInstance( matrix + .getCharacter( c ) ) ); } } } - final SortedMap histogram = new TreeMap(); - final SortedMap domain_lists = new TreeMap(); - final SortedMap dc_reapp_counts_to_protein_length_stats = new TreeMap(); - final SortedMap dc_reapp_counts_to_domain_number_stats = new TreeMap(); - final SortedMap dc_reapp_counts_to_domain_lengths_stats = new TreeMap(); - final SortedMap> domain_lists_go = new TreeMap>(); - final SortedMap> domain_lists_go_unique = new TreeMap>(); - final Set dcs = dc_gain_counts.keySet(); - final SortedSet more_than_once = new TreeSet(); - final DescriptiveStatistics gained_once_lengths_stats = new BasicDescriptiveStatistics(); - final DescriptiveStatistics gained_once_domain_count_stats = new BasicDescriptiveStatistics(); - final DescriptiveStatistics gained_multiple_times_lengths_stats = new BasicDescriptiveStatistics(); - final DescriptiveStatistics gained_multiple_times_domain_count_stats = new BasicDescriptiveStatistics(); - long gained_multiple_times_domain_length_sum = 0; - long gained_once_domain_length_sum = 0; - long gained_multiple_times_domain_length_count = 0; - long gained_once_domain_length_count = 0; - for( final String dc : dcs ) { - final int count = dc_gain_counts.get( dc ); - if ( histogram.containsKey( count ) ) { - histogram.put( count, histogram.get( count ) + 1 ); - domain_lists.get( count ).append( ", " + dc ); - domain_lists_go.get( count ).addAll( splitDomainCombination( dc ) ); - domain_lists_go_unique.get( count ).addAll( splitDomainCombination( dc ) ); - } - else { - histogram.put( count, 1 ); - domain_lists.put( count, new StringBuilder( dc ) ); - final PriorityQueue q = new PriorityQueue(); - q.addAll( splitDomainCombination( dc ) ); - domain_lists_go.put( count, q ); - final SortedSet set = new TreeSet(); - set.addAll( splitDomainCombination( dc ) ); - domain_lists_go_unique.put( count, set ); - } - if ( protein_length_stats_by_dc != null ) { - if ( !dc_reapp_counts_to_protein_length_stats.containsKey( count ) ) { - dc_reapp_counts_to_protein_length_stats.put( count, new BasicDescriptiveStatistics() ); + } + } + + 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() ); + 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() ); + } + domain_id_to_go_ids_map.get( pfam_to_go.getKey() ).add( pfam_to_go.getValue() ); + } + return domain_id_to_go_ids_map; + } + + public static Map> createDomainIdToSecondaryFeaturesMap( final File secondary_features_map_file ) + throws IOException { + final BasicTable primary_table = BasicTableParser.parse( secondary_features_map_file, '\t' ); + final Map> map = new TreeMap>(); + for( int r = 0; r < primary_table.getNumberOfRows(); ++r ) { + final String domain_id = primary_table.getValue( 0, r ); + if ( !map.containsKey( domain_id ) ) { + map.put( domain_id, new HashSet() ); + } + map.get( domain_id ).add( primary_table.getValue( 1, r ) ); + } + return map; + } + + 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 ); + phylogeny.setName( nj_tree_outfile.getName() ); + writePhylogenyToFile( phylogeny, nj_tree_outfile.toString() ); + return phylogeny; + } + + public static StringBuilder createParametersAsString( final boolean ignore_dufs, + final double e_value_max, + final int max_allowed_overlap, + final boolean no_engulfing_overlaps, + final File cutoff_scores_file, + final BinaryDomainCombination.DomainCombinationType dc_type ) { + final StringBuilder parameters_sb = new StringBuilder(); + parameters_sb.append( "E-value: " + e_value_max ); + if ( cutoff_scores_file != null ) { + parameters_sb.append( ", Cutoff-scores-file: " + cutoff_scores_file ); + } + else { + parameters_sb.append( ", Cutoff-scores-file: not-set" ); + } + if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) { + parameters_sb.append( ", Max-overlap: " + max_allowed_overlap ); + } + else { + parameters_sb.append( ", Max-overlap: not-set" ); + } + if ( no_engulfing_overlaps ) { + parameters_sb.append( ", Engulfing-overlaps: not-allowed" ); + } + else { + parameters_sb.append( ", Engulfing-overlaps: allowed" ); + } + if ( ignore_dufs ) { + parameters_sb.append( ", Ignore-dufs: true" ); + } + else { + parameters_sb.append( ", Ignore-dufs: false" ); + } + parameters_sb.append( ", DC type (if applicable): " + dc_type ); + return parameters_sb; + } + + 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" ) ) ); + } + + public static Map createTaxCodeToIdMap( final Phylogeny phy ) { + final Map m = new HashMap(); + for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) { + final PhylogenyNode n = iter.next(); + if ( n.getNodeData().isHasTaxonomy() ) { + final Taxonomy t = n.getNodeData().getTaxonomy(); + final String c = t.getTaxonomyCode(); + if ( !ForesterUtil.isEmpty( c ) ) { + if ( n.getNodeData().getTaxonomy() == null ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, "no taxonomy id for node " + n ); } - 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() ); + final String id = n.getNodeData().getTaxonomy().getIdentifier().getValue(); + if ( ForesterUtil.isEmpty( id ) ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, "no taxonomy id for node " + n ); } - 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() ); + if ( m.containsKey( c ) ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, "taxonomy code " + c + " is not unique" ); } - 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() ); + final int iid = Integer.valueOf( id ); + if ( m.containsValue( iid ) ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, "taxonomy id " + iid + " is not unique" ); + } + m.put( c, iid ); } - if ( count > 1 ) { - more_than_once.add( dc ); - if ( protein_length_stats_by_dc != null ) { - final DescriptiveStatistics s = protein_length_stats_by_dc.get( dc ); - for( final double element : s.getData() ) { - gained_multiple_times_lengths_stats.addValue( element ); + } + else { + ForesterUtil.fatalError( surfacing.PRG_NAME, "no taxonomy for node " + n ); + } + } + return m; + } + + public static void decoratePrintableDomainSimilarities( final SortedSet domain_similarities, + final Detailedness detailedness ) { + for( final DomainSimilarity domain_similarity : domain_similarities ) { + if ( domain_similarity instanceof PrintableDomainSimilarity ) { + final PrintableDomainSimilarity printable_domain_similarity = ( PrintableDomainSimilarity ) domain_similarity; + printable_domain_similarity.setDetailedness( detailedness ); + } + } + } + + public static void doit( final List proteins, + final List query_domain_ids_nc_order, + final Writer out, + final String separator, + final String limit_to_species, + 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 ) ) { + if ( protein.contains( query_domain_ids_nc_order, true ) ) { + out.write( protein.getSpecies().getSpeciesId() ); + out.write( separator ); + out.write( protein.getProteinId().getId() ); + out.write( separator ); + out.write( "[" ); + final Set visited_domain_ids = new HashSet(); + boolean first = true; + for( final Domain domain : protein.getProteinDomains() ) { + if ( !visited_domain_ids.contains( domain.getDomainId() ) ) { + visited_domain_ids.add( domain.getDomainId() ); + if ( first ) { + first = false; + } + else { + out.write( " " ); + } + out.write( domain.getDomainId() ); + out.write( " {" ); + out.write( "" + domain.getTotalCount() ); + out.write( "}" ); } } - if ( domain_number_stats_by_dc != null ) { - final DescriptiveStatistics s = domain_number_stats_by_dc.get( dc ); - for( final double element : s.getData() ) { - gained_multiple_times_domain_count_stats.addValue( element ); - } - } - if ( domain_length_stats_by_domain != null ) { - final String[] ds = dc.split( "=" ); - final DescriptiveStatistics s0 = domain_length_stats_by_domain.get( ds[ 0 ] ); - final DescriptiveStatistics s1 = domain_length_stats_by_domain.get( ds[ 1 ] ); - for( final double element : s0.getData() ) { - gained_multiple_times_domain_length_sum += element; - ++gained_multiple_times_domain_length_count; - } - for( final double element : s1.getData() ) { - gained_multiple_times_domain_length_sum += element; - ++gained_multiple_times_domain_length_count; - } - } - } - else { - if ( protein_length_stats_by_dc != null ) { - final DescriptiveStatistics s = protein_length_stats_by_dc.get( dc ); - for( final double element : s.getData() ) { - gained_once_lengths_stats.addValue( element ); - } - } - if ( domain_number_stats_by_dc != null ) { - final DescriptiveStatistics s = domain_number_stats_by_dc.get( dc ); - for( final double element : s.getData() ) { - gained_once_domain_count_stats.addValue( element ); - } + out.write( "]" ); + out.write( separator ); + if ( !( ForesterUtil.isEmpty( protein.getDescription() ) || protein.getDescription() + .equals( SurfacingConstants.NONE ) ) ) { + out.write( protein.getDescription() ); } - if ( domain_length_stats_by_domain != null ) { - final String[] ds = dc.split( "=" ); - final DescriptiveStatistics s0 = domain_length_stats_by_domain.get( ds[ 0 ] ); - final DescriptiveStatistics s1 = domain_length_stats_by_domain.get( ds[ 1 ] ); - for( final double element : s0.getData() ) { - gained_once_domain_length_sum += element; - ++gained_once_domain_length_count; - } - for( final double element : s1.getData() ) { - gained_once_domain_length_sum += element; - ++gained_once_domain_length_count; - } + out.write( separator ); + if ( !( ForesterUtil.isEmpty( protein.getAccession() ) || protein.getAccession() + .equals( SurfacingConstants.NONE ) ) ) { + out.write( protein.getAccession() ); } + out.write( SurfacingConstants.NL ); } } - final Set histogram_keys = histogram.keySet(); - for( final Integer histogram_key : histogram_keys ) { - final int count = histogram.get( histogram_key ); - final StringBuilder dc = domain_lists.get( histogram_key ); - out_counts.write( histogram_key + "\t" + count + ForesterUtil.LINE_SEPARATOR ); - out_dc.write( histogram_key + "\t" + dc + ForesterUtil.LINE_SEPARATOR ); - out_dc_for_go_mapping.write( "#" + histogram_key + ForesterUtil.LINE_SEPARATOR ); - final Object[] sorted = domain_lists_go.get( histogram_key ).toArray(); - Arrays.sort( sorted ); - for( final Object domain : sorted ) { - out_dc_for_go_mapping.write( domain + ForesterUtil.LINE_SEPARATOR ); - } - out_dc_for_go_mapping_unique.write( "#" + histogram_key + ForesterUtil.LINE_SEPARATOR ); - for( final String domain : domain_lists_go_unique.get( histogram_key ) ) { - out_dc_for_go_mapping_unique.write( domain + ForesterUtil.LINE_SEPARATOR ); - } + } + out.flush(); + } + + public static void domainsPerProteinsStatistics( final String genome, + final List protein_list, + final DescriptiveStatistics all_genomes_domains_per_potein_stats, + final SortedMap all_genomes_domains_per_potein_histo, + final SortedSet domains_which_are_always_single, + final SortedSet domains_which_are_sometimes_single_sometimes_not, + final SortedSet domains_which_never_single, + final Writer writer ) { + final DescriptiveStatistics stats = new BasicDescriptiveStatistics(); + for( final Protein protein : protein_list ) { + final int domains = protein.getNumberOfProteinDomains(); + //System.out.println( domains ); + stats.addValue( domains ); + all_genomes_domains_per_potein_stats.addValue( domains ); + if ( !all_genomes_domains_per_potein_histo.containsKey( domains ) ) { + all_genomes_domains_per_potein_histo.put( domains, 1 ); } - out_counts.close(); - out_dc.close(); - out_dc_for_go_mapping.close(); - out_dc_for_go_mapping_unique.close(); - final SortedMap lca_rank_counts = new TreeMap(); - final SortedMap lca_ancestor_species_counts = new TreeMap(); - for( final String dc : more_than_once ) { - final List nodes = new ArrayList(); - for( final PhylogenyNodeIterator it = local_phylogeny_l.iteratorExternalForward(); it.hasNext(); ) { - final PhylogenyNode n = it.next(); - if ( n.getNodeData().getBinaryCharacters().getGainedCharacters().contains( dc ) ) { - nodes.add( n ); + else { + all_genomes_domains_per_potein_histo.put( domains, + 1 + all_genomes_domains_per_potein_histo.get( domains ) ); + } + if ( domains == 1 ) { + final String domain = protein.getProteinDomain( 0 ).getDomainId(); + if ( !domains_which_are_sometimes_single_sometimes_not.contains( domain ) ) { + if ( domains_which_never_single.contains( domain ) ) { + domains_which_never_single.remove( domain ); + domains_which_are_sometimes_single_sometimes_not.add( domain ); + } + else { + domains_which_are_always_single.add( domain ); } } - for( int i = 0; i < nodes.size() - 1; ++i ) { - for( int j = i + 1; j < nodes.size(); ++j ) { - final PhylogenyNode lca = PhylogenyMethods.obtainLCA( nodes.get( i ), - nodes.get( j ) ); - String rank = "unknown"; - if ( lca.getNodeData().isHasTaxonomy() - && !ForesterUtil.isEmpty( lca.getNodeData().getTaxonomy().getRank() ) ) { - rank = lca.getNodeData().getTaxonomy().getRank(); - } - addToCountMap( lca_rank_counts, rank ); - String lca_species; - if ( lca.getNodeData().isHasTaxonomy() - && !ForesterUtil.isEmpty( lca.getNodeData().getTaxonomy().getScientificName() ) ) { - lca_species = lca.getNodeData().getTaxonomy().getScientificName(); - } - else if ( lca.getNodeData().isHasTaxonomy() - && !ForesterUtil.isEmpty( lca.getNodeData().getTaxonomy().getCommonName() ) ) { - lca_species = lca.getNodeData().getTaxonomy().getCommonName(); + } + else if ( domains > 1 ) { + for( final Domain d : protein.getProteinDomains() ) { + final String domain = d.getDomainId(); + // System.out.println( domain ); + if ( !domains_which_are_sometimes_single_sometimes_not.contains( domain ) ) { + if ( domains_which_are_always_single.contains( domain ) ) { + domains_which_are_always_single.remove( domain ); + domains_which_are_sometimes_single_sometimes_not.add( domain ); } else { - lca_species = lca.getName(); + domains_which_never_single.add( domain ); } - addToCountMap( lca_ancestor_species_counts, lca_species ); } } } - final BufferedWriter out_for_rank_counts = new BufferedWriter( new FileWriter( outfilename_for_rank_counts ) ); - final BufferedWriter out_for_ancestor_species_counts = new BufferedWriter( new FileWriter( outfilename_for_ancestor_species_counts ) ); - ForesterUtil.map2writer( out_for_rank_counts, lca_rank_counts, "\t", ForesterUtil.LINE_SEPARATOR ); - ForesterUtil.map2writer( out_for_ancestor_species_counts, - lca_ancestor_species_counts, - "\t", - 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 ) ) ) { - final BufferedWriter w = new BufferedWriter( new FileWriter( outfilename_for_protein_stats ) ); - w.write( "Domain Lengths: " ); - w.write( "\n" ); - if ( domain_length_stats_by_domain != null ) { - for( final Entry entry : dc_reapp_counts_to_domain_lengths_stats - .entrySet() ) { - w.write( entry.getKey().toString() ); - w.write( "\t" + entry.getValue().arithmeticMean() ); - w.write( "\t" + entry.getValue().median() ); - w.write( "\n" ); - } - } - w.flush(); - w.write( "\n" ); - w.write( "\n" ); - w.write( "Protein Lengths: " ); - w.write( "\n" ); - if ( protein_length_stats_by_dc != null ) { - for( final Entry entry : dc_reapp_counts_to_protein_length_stats - .entrySet() ) { - w.write( entry.getKey().toString() ); - w.write( "\t" + entry.getValue().arithmeticMean() ); - w.write( "\t" + entry.getValue().median() ); - w.write( "\n" ); - } + } + try { + writer.write( genome ); + writer.write( "\t" ); + if ( stats.getN() >= 1 ) { + writer.write( stats.arithmeticMean() + "" ); + writer.write( "\t" ); + if ( stats.getN() >= 2 ) { + writer.write( stats.sampleStandardDeviation() + "" ); } - w.flush(); - w.write( "\n" ); - w.write( "\n" ); - w.write( "Number of domains: " ); - w.write( "\n" ); - if ( domain_number_stats_by_dc != null ) { - for( final Entry entry : dc_reapp_counts_to_domain_number_stats - .entrySet() ) { - w.write( entry.getKey().toString() ); - w.write( "\t" + entry.getValue().arithmeticMean() ); - w.write( "\t" + entry.getValue().median() ); - w.write( "\n" ); - } + else { + writer.write( "" ); } - w.flush(); - w.write( "\n" ); - w.write( "\n" ); - w.write( "Gained once, domain lengths:" ); - w.write( "\n" ); - w.write( "N: " + gained_once_domain_length_count ); - w.write( "\n" ); - w.write( "Avg: " + ( ( double ) gained_once_domain_length_sum / gained_once_domain_length_count ) ); - w.write( "\n" ); - w.write( "\n" ); - w.write( "Gained multiple times, domain lengths:" ); - 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( "\n" ); - w.write( "\n" ); - w.write( "\n" ); - w.write( "\n" ); - w.write( "Gained once, protein lengths:" ); - w.write( "\n" ); - w.write( gained_once_lengths_stats.toString() ); - w.write( "\n" ); - w.write( "\n" ); - w.write( "Gained once, domain counts:" ); - w.write( "\n" ); - w.write( gained_once_domain_count_stats.toString() ); - w.write( "\n" ); - w.write( "\n" ); - w.write( "Gained multiple times, protein lengths:" ); - w.write( "\n" ); - w.write( gained_multiple_times_lengths_stats.toString() ); - w.write( "\n" ); - w.write( "\n" ); - w.write( "Gained multiple times, domain counts:" ); - w.write( "\n" ); - w.write( gained_multiple_times_domain_count_stats.toString() ); - w.flush(); - w.close(); + writer.write( "\t" ); + writer.write( stats.median() + "" ); + writer.write( "\t" ); + writer.write( stats.getN() + "" ); + writer.write( "\t" ); + writer.write( stats.getMin() + "" ); + writer.write( "\t" ); + writer.write( stats.getMax() + "" ); + } + else { + writer.write( "\t" ); + writer.write( "\t" ); + writer.write( "\t" ); + writer.write( "0" ); + writer.write( "\t" ); + writer.write( "\t" ); } + writer.write( "\n" ); } 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 lists to (for GO mapping) [" - + outfilename_for_dc_for_go_mapping + "]" ); - ForesterUtil.programMessage( surfacing.PRG_NAME, - "Wrote independent domain combination gains fitch lists to (for GO mapping, unique) [" - + outfilename_for_dc_for_go_mapping_unique + "]" ); - } - - private final static void addToCountMap( final Map map, final String s ) { - if ( map.containsKey( s ) ) { - map.put( s, map.get( s ) + 1 ); - } - else { - map.put( s, 1 ); - } - } - - public static int calculateOverlap( final Domain domain, final List covered_positions ) { - int overlap_count = 0; - for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) { - if ( ( i < covered_positions.size() ) && ( covered_positions.get( i ) == true ) ) { - ++overlap_count; - } - } - return overlap_count; - } - - public static void checkForOutputFileWriteability( final File outfile ) { - final String error = ForesterUtil.isWritableFile( outfile ); - if ( !ForesterUtil.isEmpty( error ) ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, error ); - } - } - - private static SortedSet collectAllDomainsChangedOnSubtree( final PhylogenyNode subtree_root, - final boolean get_gains ) { - final SortedSet domains = new TreeSet(); - for( final PhylogenyNode descendant : PhylogenyMethods.getAllDescendants( subtree_root ) ) { - final BinaryCharacters chars = descendant.getNodeData().getBinaryCharacters(); - if ( get_gains ) { - domains.addAll( chars.getGainedCharacters() ); - } - else { - domains.addAll( chars.getLostCharacters() ); - } - } - return domains; - } - - public static void collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile( final CharacterStateMatrix matrix, - final BinaryDomainCombination.DomainCombinationType dc_type, - final List all_binary_domains_combination_gained, - final boolean get_gains ) { - final SortedSet sorted_ids = new TreeSet(); - for( int i = 0; i < matrix.getNumberOfIdentifiers(); ++i ) { - sorted_ids.add( matrix.getIdentifier( i ) ); - } - 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 ) ) ) { - if ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) { - all_binary_domains_combination_gained.add( AdjactantDirectedBinaryDomainCombination - .createInstance( matrix.getCharacter( c ) ) ); - } - else if ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED ) { - all_binary_domains_combination_gained.add( DirectedBinaryDomainCombination - .createInstance( matrix.getCharacter( c ) ) ); - } - else { - all_binary_domains_combination_gained.add( BasicBinaryDomainCombination.createInstance( matrix - .getCharacter( c ) ) ); - } - } - } - } - } - - private static File createBaseDirForPerNodeDomainFiles( final String base_dir, - final boolean domain_combinations, - final CharacterStateMatrix.GainLossStates state, - final String outfile ) { - File per_node_go_mapped_domain_gain_loss_files_base_dir = new File( new File( outfile ).getParent() - + ForesterUtil.FILE_SEPARATOR + base_dir ); - if ( !per_node_go_mapped_domain_gain_loss_files_base_dir.exists() ) { - per_node_go_mapped_domain_gain_loss_files_base_dir.mkdir(); - } - if ( domain_combinations ) { - per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir - + ForesterUtil.FILE_SEPARATOR + "DC" ); - } - else { - per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir - + ForesterUtil.FILE_SEPARATOR + "DOMAINS" ); - } - if ( !per_node_go_mapped_domain_gain_loss_files_base_dir.exists() ) { - per_node_go_mapped_domain_gain_loss_files_base_dir.mkdir(); - } - if ( state == GainLossStates.GAIN ) { - per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir - + ForesterUtil.FILE_SEPARATOR + "GAINS" ); - } - else if ( state == GainLossStates.LOSS ) { - per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir - + ForesterUtil.FILE_SEPARATOR + "LOSSES" ); - } - else { - per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir - + ForesterUtil.FILE_SEPARATOR + "PRESENT" ); - } - if ( !per_node_go_mapped_domain_gain_loss_files_base_dir.exists() ) { - per_node_go_mapped_domain_gain_loss_files_base_dir.mkdir(); - } - return per_node_go_mapped_domain_gain_loss_files_base_dir; - } - - 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() ); - 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() ); - } - domain_id_to_go_ids_map.get( pfam_to_go.getKey() ).add( pfam_to_go.getValue() ); - } - return domain_id_to_go_ids_map; - } - - public static Map> createDomainIdToSecondaryFeaturesMap( final File secondary_features_map_file ) - throws IOException { - final BasicTable primary_table = BasicTableParser.parse( secondary_features_map_file, "\t" ); - final Map> map = new TreeMap>(); - for( int r = 0; r < primary_table.getNumberOfRows(); ++r ) { - final DomainId domain_id = new DomainId( primary_table.getValue( 0, r ) ); - if ( !map.containsKey( domain_id ) ) { - map.put( domain_id, new HashSet() ); - } - map.get( domain_id ).add( primary_table.getValue( 1, r ) ); - } - return map; - } - - 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 ); - phylogeny.setName( nj_tree_outfile.getName() ); - writePhylogenyToFile( phylogeny, nj_tree_outfile.toString() ); - return phylogeny; - } - - private static SortedSet createSetOfAllBinaryDomainCombinationsPerGenome( final GenomeWideCombinableDomains gwcd ) { - final SortedMap cds = gwcd.getAllCombinableDomainsIds(); - final SortedSet binary_combinations = new TreeSet(); - for( final DomainId domain_id : cds.keySet() ) { - final CombinableDomains cd = cds.get( domain_id ); - binary_combinations.addAll( cd.toBinaryDomainCombinations() ); - } - return binary_combinations; - } - - public static void decoratePrintableDomainSimilarities( final SortedSet domain_similarities, - final Detailedness detailedness, - final GoAnnotationOutput go_annotation_output, - final Map go_id_to_term_map, - final GoNameSpace go_namespace_limit ) { - if ( ( go_namespace_limit != null ) && ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) ) { - throw new IllegalArgumentException( "attempt to use a GO namespace limit without a GO id to term map" ); - } - for( final DomainSimilarity domain_similarity : domain_similarities ) { - if ( domain_similarity instanceof PrintableDomainSimilarity ) { - final PrintableDomainSimilarity printable_domain_similarity = ( PrintableDomainSimilarity ) domain_similarity; - printable_domain_similarity.setDetailedness( detailedness ); - printable_domain_similarity.setGoAnnotationOutput( go_annotation_output ); - printable_domain_similarity.setGoIdToTermMap( go_id_to_term_map ); - printable_domain_similarity.setGoNamespaceLimit( go_namespace_limit ); - } + e.printStackTrace(); } } @@ -702,10 +542,6 @@ public final class SurfacingUtil { out.write( species + "\t" ); } out.write( ForesterUtil.LINE_SEPARATOR ); - // DescriptiveStatistics stats_for_domain = domain_lengths - // .calculateMeanBasedStatistics(); - //AsciiHistogram histo = new AsciiHistogram( stats_for_domain ); - //System.out.println( histo.toStringBuffer( 40, '=', 60, 4 ).toString() ); } } out.write( ForesterUtil.LINE_SEPARATOR ); @@ -739,22 +575,97 @@ public final class SurfacingUtil { } } out.close(); - // final List histogram_datas = new ArrayList(); - // for( int i = 0; i < number_of_genomes; ++i ) { - // final Species species = new BasicSpecies( input_file_properties[ i ][ 0 ] ); - // histogram_datas - // .add( new HistogramData( species.toString(), domain_lengths_table - // .calculateMeanBasedStatisticsForSpecies( species ) - // .getDataAsDoubleArray(), 5, 600, null, 60 ) ); - // } - // final HistogramsFrame hf = new HistogramsFrame( histogram_datas ); - // hf.setVisible( true ); System.gc(); } /** + * 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 + * @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 { + checkForOutputFileWriteability( output_file ); + final Writer out = ForesterUtil.createBufferedWriter( output_file ); + final SortedMap bdc_to_counts = ForesterUtil + .listToSortedCountsMap( all_bin_domain_combinations_changed ); + final SortedSet all_domains_in_combination_changed_more_than_once = new TreeSet(); + final SortedSet all_domains_in_combination_changed_only_once = new TreeSet(); + int above_one = 0; + int one = 0; + for( final Object bdc_object : bdc_to_counts.keySet() ) { + final BinaryDomainCombination bdc = ( BinaryDomainCombination ) bdc_object; + final int count = bdc_to_counts.get( bdc_object ); + if ( count < 1 ) { + ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "count < 1 " ); + } + out.write( bdc + "\t" + count + ForesterUtil.LINE_SEPARATOR ); + if ( count > 1 ) { + all_domains_in_combination_changed_more_than_once.add( bdc.getId0() ); + all_domains_in_combination_changed_more_than_once.add( bdc.getId1() ); + above_one++; + } + else if ( count == 1 ) { + all_domains_in_combination_changed_only_once.add( bdc.getId0() ); + all_domains_in_combination_changed_only_once.add( bdc.getId1() ); + one++; + } + } + final int all = all_bin_domain_combinations_encountered.size(); + int never_lost = -1; + if ( !is_gains_analysis ) { + all_bin_domain_combinations_encountered.removeAll( all_bin_domain_combinations_changed ); + never_lost = all_bin_domain_combinations_encountered.size(); + for( final BinaryDomainCombination bdc : all_bin_domain_combinations_encountered ) { + out.write( bdc + "\t" + "0" + ForesterUtil.LINE_SEPARATOR ); + } + } + if ( is_gains_analysis ) { + out.write( "Sum of all distinct domain combinations appearing once : " + one + + ForesterUtil.LINE_SEPARATOR ); + out.write( "Sum of all distinct domain combinations appearing more than once : " + above_one + + ForesterUtil.LINE_SEPARATOR ); + out.write( "Sum of all distinct domains in combinations apppearing only once : " + + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR ); + out.write( "Sum of all distinct domains in combinations apppearing more than once: " + + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR ); + } + else { + out.write( "Sum of all distinct domain combinations never lost : " + never_lost + + ForesterUtil.LINE_SEPARATOR ); + out.write( "Sum of all distinct domain combinations lost once : " + one + + ForesterUtil.LINE_SEPARATOR ); + out.write( "Sum of all distinct domain combinations lost more than once : " + above_one + + ForesterUtil.LINE_SEPARATOR ); + out.write( "Sum of all distinct domains in combinations lost only once : " + + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR ); + out.write( "Sum of all distinct domains in combinations lost more than once: " + + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR ); + } + out.write( "All binary combinations : " + all + + ForesterUtil.LINE_SEPARATOR ); + 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 + + "\"" ); + } + + /** * * @param all_binary_domains_combination_lost_fitch + * @param use_last_in_fitch_parsimony * @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. @@ -764,19 +675,22 @@ public final class SurfacingUtil { final String outfile_name, final DomainParsimonyCalculator domain_parsimony, final Phylogeny phylogeny, - final Map> domain_id_to_go_ids_map, + final Map> domain_id_to_go_ids_map, final Map go_id_to_term_map, final GoNameSpace go_namespace_limit, final String parameters_str, - final Map>[] domain_id_to_secondary_features_maps, - final SortedSet positive_filter, + final Map>[] domain_id_to_secondary_features_maps, + final SortedSet positive_filter, final boolean output_binary_domain_combinations_for_graphs, final List all_binary_domains_combination_gained_fitch, final List all_binary_domains_combination_lost_fitch, final BinaryDomainCombination.DomainCombinationType dc_type, final Map protein_length_stats_by_dc, final Map domain_number_stats_by_dc, - final Map domain_length_stats_by_domain ) { + final Map domain_length_stats_by_domain, + final Map tax_code_to_id_map, + final boolean write_to_nexus, + final boolean use_last_in_fitch_parsimony ) { final String sep = ForesterUtil.LINE_SEPARATOR + "###################" + ForesterUtil.LINE_SEPARATOR; final String date_time = ForesterUtil.getCurrentDateTime(); final SortedSet all_pfams_encountered = new TreeSet(); @@ -784,7 +698,9 @@ public final class SurfacingUtil { final SortedSet all_pfams_lost_as_domains = new TreeSet(); final SortedSet all_pfams_gained_as_dom_combinations = new TreeSet(); final SortedSet all_pfams_lost_as_dom_combinations = new TreeSet(); - writeToNexus( outfile_name, domain_parsimony, phylogeny ); + if ( write_to_nexus ) { + writeToNexus( outfile_name, domain_parsimony, phylogeny ); + } // DOLLO DOMAINS // ------------- Phylogeny local_phylogeny_l = phylogeny.copy(); @@ -827,7 +743,8 @@ public final class SurfacingUtil { domain_id_to_secondary_features_maps, all_pfams_encountered, all_pfams_gained_as_domains, - "_dollo_gains_d" ); + "_dollo_gains_d", + tax_code_to_id_map ); writeBinaryStatesMatrixToList( domain_id_to_go_ids_map, go_id_to_term_map, go_namespace_limit, @@ -842,22 +759,24 @@ public final class SurfacingUtil { domain_id_to_secondary_features_maps, all_pfams_encountered, all_pfams_lost_as_domains, - "_dollo_losses_d" ); - 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" ); + "_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 ); preparePhylogeny( local_phylogeny_l, domain_parsimony, date_time, @@ -884,7 +803,7 @@ public final class SurfacingUtil { randomization = "yes, seed = " + random_number_seed_for_fitch_parsimony; } else { - domain_parsimony.executeFitchParsimonyOnBinaryDomainCombintion( USE_LAST ); + 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 ); @@ -944,7 +863,8 @@ public final class SurfacingUtil { null, all_pfams_encountered, all_pfams_gained_as_dom_combinations, - "_fitch_gains_dc" ); + "_fitch_gains_dc", + tax_code_to_id_map ); writeBinaryStatesMatrixToList( domain_id_to_go_ids_map, go_id_to_term_map, go_namespace_limit, @@ -959,22 +879,24 @@ public final class SurfacingUtil { null, all_pfams_encountered, all_pfams_lost_as_dom_combinations, - "_fitch_losses_dc" ); - writeBinaryStatesMatrixToList( domain_id_to_go_ids_map, - go_id_to_term_map, - go_namespace_limit, - true, - domain_parsimony.getGainLossMatrix(), - null, - outfile_name + surfacing.PARSIMONY_OUTPUT_FITCH_PRESENT_HTML_BC, - sep, - ForesterUtil.LINE_SEPARATOR, - "Fitch Parsimony | Present | Domain Combinations", - "", - null, - all_pfams_encountered, - null, - "_fitch_present_dc" ); + "_fitch_losses_dc", + tax_code_to_id_map ); + // writeBinaryStatesMatrixToList( domain_id_to_go_ids_map, + // go_id_to_term_map, + // go_namespace_limit, + // true, + // domain_parsimony.getGainLossMatrix(), + // null, + // outfile_name + surfacing.PARSIMONY_OUTPUT_FITCH_PRESENT_HTML_BC, + // sep, + // ForesterUtil.LINE_SEPARATOR, + // "Fitch Parsimony | Present | Domain Combinations", + // "", + // null, + // all_pfams_encountered, + // null, + // "_fitch_present_dc", + // tax_code_to_id_map ); writeAllEncounteredPfamsToFile( domain_id_to_go_ids_map, go_id_to_term_map, outfile_name, @@ -1015,7 +937,8 @@ public final class SurfacingUtil { final DomainParsimonyCalculator secondary_features_parsimony, final Phylogeny phylogeny, final String parameters_str, - final Map mapping_results_map ) { + final Map mapping_results_map, + final boolean use_last_in_fitch_parsimony ) { final String sep = ForesterUtil.LINE_SEPARATOR + "###################" + ForesterUtil.LINE_SEPARATOR; final String date_time = ForesterUtil.getCurrentDateTime(); System.out.println(); @@ -1064,7 +987,8 @@ public final class SurfacingUtil { // ------------------------- local_phylogeny_copy = phylogeny.copy(); final String randomization = "no"; - secondary_features_parsimony.executeFitchParsimonyOnBinaryDomainCombintionOnSecondaryFeatures( USE_LAST ); + secondary_features_parsimony + .executeFitchParsimonyOnBinaryDomainCombintionOnSecondaryFeatures( use_last_in_fitch_parsimony ); preparePhylogeny( local_phylogeny_copy, secondary_features_parsimony, date_time, @@ -1083,58 +1007,62 @@ public final class SurfacingUtil { + "_MAPPED_indep_dc_gains_fitch_lca_taxonomies.txt", null, null, null, null ); } - public static void doit( final List proteins, - final List query_domain_ids_nc_order, - final Writer out, - final String separator, - final String limit_to_species, - 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 ) ) { - if ( protein.contains( query_domain_ids_nc_order, true ) ) { - out.write( protein.getSpecies().getSpeciesId() ); - out.write( separator ); - out.write( protein.getProteinId().getId() ); - out.write( separator ); - out.write( "[" ); - final Set visited_domain_ids = new HashSet(); - boolean first = true; - for( final Domain domain : protein.getProteinDomains() ) { - if ( !visited_domain_ids.contains( domain.getDomainId() ) ) { - visited_domain_ids.add( domain.getDomainId() ); - if ( first ) { - first = false; - } - else { - out.write( " " ); - } - out.write( domain.getDomainId().getId() ); - out.write( " {" ); - out.write( "" + domain.getTotalCount() ); - out.write( "}" ); - } - } - out.write( "]" ); - out.write( separator ); - 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 ) ) ) { - out.write( protein.getAccession() ); - } - out.write( SurfacingConstants.NL ); - } - } + public static void executePlusMinusAnalysis( final File output_file, + final List plus_minus_analysis_high_copy_base, + final List plus_minus_analysis_high_copy_target, + final List plus_minus_analysis_low_copy, + final List gwcd_list, + final SortedMap> protein_lists_per_species, + final Map> domain_id_to_go_ids_map, + final Map go_id_to_term_map, + final List plus_minus_analysis_numbers ) { + final Set all_spec = new HashSet(); + for( final GenomeWideCombinableDomains gwcd : gwcd_list ) { + all_spec.add( gwcd.getSpecies().getSpeciesId() ); + } + final File html_out_dom = new File( output_file + surfacing.PLUS_MINUS_DOM_SUFFIX_HTML ); + final File plain_out_dom = new File( output_file + surfacing.PLUS_MINUS_DOM_SUFFIX ); + final File html_out_dc = new File( output_file + surfacing.PLUS_MINUS_DC_SUFFIX_HTML ); + final File all_domains_go_ids_out_dom = new File( output_file + surfacing.PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX ); + final File passing_domains_go_ids_out_dom = new File( output_file + + surfacing.PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX ); + final File proteins_file_base = new File( output_file + "" ); + final int min_diff = ( ( Integer ) plus_minus_analysis_numbers.get( 0 ) ).intValue(); + final double factor = ( ( Double ) plus_minus_analysis_numbers.get( 1 ) ).doubleValue(); + try { + DomainCountsDifferenceUtil.calculateCopyNumberDifferences( gwcd_list, + protein_lists_per_species, + plus_minus_analysis_high_copy_base, + plus_minus_analysis_high_copy_target, + plus_minus_analysis_low_copy, + min_diff, + factor, + plain_out_dom, + html_out_dom, + html_out_dc, + domain_id_to_go_ids_map, + go_id_to_term_map, + all_domains_go_ids_out_dom, + passing_domains_go_ids_out_dom, + proteins_file_base ); } - out.flush(); + 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 + "\"" ); } public static void extractProteinNames( final List proteins, - final List query_domain_ids_nc_order, + final List query_domain_ids_nc_order, final Writer out, final String separator, final String limit_to_species ) throws IOException { @@ -1147,7 +1075,7 @@ public final class SurfacingUtil { out.write( protein.getProteinId().getId() ); out.write( separator ); out.write( "[" ); - final Set visited_domain_ids = new HashSet(); + final Set visited_domain_ids = new HashSet(); boolean first = true; for( final Domain domain : protein.getProteinDomains() ) { if ( !visited_domain_ids.contains( domain.getDomainId() ) ) { @@ -1158,7 +1086,7 @@ public final class SurfacingUtil { else { out.write( " " ); } - out.write( domain.getDomainId().getId() ); + out.write( domain.getDomainId() ); out.write( " {" ); out.write( "" + domain.getTotalCount() ); out.write( "}" ); @@ -1183,13 +1111,14 @@ public final class SurfacingUtil { } public static void extractProteinNames( final SortedMap> protein_lists_per_species, - final DomainId domain_id, + final String domain_id, final Writer out, final String separator, final String limit_to_species, final double domain_e_cutoff ) throws IOException { - System.out.println( "Per domain E-value: " + domain_e_cutoff ); + //System.out.println( "Per domain E-value: " + domain_e_cutoff ); for( final Species species : protein_lists_per_species.keySet() ) { + //System.out.println( species + ":" ); for( final Protein protein : protein_lists_per_species.get( species ) ) { if ( ForesterUtil.isEmpty( limit_to_species ) || protein.getSpecies().getSpeciesId().equalsIgnoreCase( limit_to_species ) ) { @@ -1201,34 +1130,33 @@ public final class SurfacingUtil { out.write( separator ); out.write( domain_id.toString() ); out.write( separator ); + int prev_to = -1; for( final Domain domain : domains ) { - if ( domain_e_cutoff < 0 || domain.getPerDomainEvalue() <= domain_e_cutoff ) { - out.write( "/" ); - out.write( domain.getFrom() + "-" + domain.getTo() ); + if ( ( domain_e_cutoff < 0 ) || ( domain.getPerDomainEvalue() <= domain_e_cutoff ) ) { + out.write( "/" ); + out.write( domain.getFrom() + "-" + domain.getTo() ); + if ( prev_to >= 0 ) { + final int l = domain.getFrom() - prev_to; + // System.out.println( l ); + } + prev_to = domain.getTo(); } } out.write( "/" ); out.write( separator ); - final List domain_list = new ArrayList(); - for( final Domain domain : protein.getProteinDomains() ) { - if ( domain_e_cutoff < 0 || domain.getPerDomainEvalue() <= domain_e_cutoff ) { + if ( ( domain_e_cutoff < 0 ) || ( domain.getPerDomainEvalue() <= domain_e_cutoff ) ) { domain_list.add( domain ); } } - - Domain domain_ary[] = new Domain[ domain_list.size() ]; - + final Domain domain_ary[] = new Domain[ domain_list.size() ]; for( int i = 0; i < domain_list.size(); ++i ) { domain_ary[ i ] = domain_list.get( i ); } - Arrays.sort( domain_ary, new DomainComparator( true ) ); - out.write( "{" ); boolean first = true; - for( final Domain domain : domain_ary ) { if ( first ) { first = false; @@ -1237,7 +1165,7 @@ public final class SurfacingUtil { out.write( "," ); } out.write( domain.getDomainId().toString() ); - out.write( ":" + domain.getFrom() + "-" + domain.getTo() ); + out.write( ":" + domain.getFrom() + "-" + domain.getTo() ); out.write( ":" + domain.getPerDomainEvalue() ); } out.write( "}" ); @@ -1258,10 +1186,10 @@ public final class SurfacingUtil { out.flush(); } - public static SortedSet getAllDomainIds( final List gwcd_list ) { - final SortedSet all_domains_ids = new TreeSet(); + public static SortedSet getAllDomainIds( final List gwcd_list ) { + final SortedSet all_domains_ids = new TreeSet(); for( final GenomeWideCombinableDomains gwcd : gwcd_list ) { - final Set all_domains = gwcd.getAllDomainIds(); + final Set all_domains = gwcd.getAllDomainIds(); // for( final Domain domain : all_domains ) { all_domains_ids.addAll( all_domains ); // } @@ -1274,7 +1202,7 @@ public final class SurfacingUtil { for( final Protein protein_domain_collection : protein_domain_collections ) { for( final Object name : protein_domain_collection.getProteinDomains() ) { final BasicDomain protein_domain = ( BasicDomain ) name; - final String id = protein_domain.getDomainId().getId(); + final String id = protein_domain.getDomainId(); if ( map.containsKey( id ) ) { map.put( id, map.get( id ) + 1 ); } @@ -1310,21 +1238,192 @@ public final class SurfacingUtil { return c; } - /** - * Returns true is Domain domain falls in an uninterrupted stretch of - * covered positions. - * - * @param domain - * @param covered_positions - * @return - */ - public static boolean isEngulfed( final Domain domain, final List covered_positions ) { - for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) { - if ( ( i >= covered_positions.size() ) || ( covered_positions.get( i ) != true ) ) { - return false; - } + public static void log( final String msg, final Writer w ) { + try { + w.write( msg ); + w.write( ForesterUtil.LINE_SEPARATOR ); + } + catch ( final IOException e ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() ); } - return true; + } + + public static Phylogeny[] obtainAndPreProcessIntrees( final File[] intree_files, + final int number_of_genomes, + final String[][] input_file_properties ) { + final Phylogeny[] intrees = new Phylogeny[ intree_files.length ]; + int i = 0; + for( final File intree_file : intree_files ) { + 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 ); + } + 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" ); + } + else if ( p_array.length > 1 ) { + 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 ); + } + if ( ( intree == null ) || intree.isEmpty() ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" ); + } + 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 + "]" ); + } + preparePhylogenyForParsimonyAnalyses( intree, input_file_properties ); + if ( !intree.isCompletelyBinary() ) { + ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "input tree [" + intree_file + + "] is not completely binary" ); + } + intrees[ i++ ] = intree; + } + return intrees; + } + + public static Phylogeny obtainFirstIntree( final File intree_file ) { + 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 ); + } + 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" ); + } + else if ( phys.length > 1 ) { + 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 ); + } + if ( ( intree == null ) || intree.isEmpty() ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" ); + } + if ( !intree.isRooted() ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is not rooted" ); + } + return intree; + } + + public static String obtainHexColorStringDependingOnTaxonomyGroup( final String tax_code, final Phylogeny phy ) + throws IllegalArgumentException { + if ( !_TAXCODE_HEXCOLORSTRING_MAP.containsKey( tax_code ) ) { + if ( ( phy != null ) && !phy.isEmpty() ) { + final List nodes = phy.getNodesViaTaxonomyCode( tax_code ); + Color c = null; + if ( ( nodes == null ) || nodes.isEmpty() ) { + throw new IllegalArgumentException( "code " + tax_code + " is not found" ); + } + if ( nodes.size() != 1 ) { + throw new IllegalArgumentException( "code " + tax_code + " is not unique" ); + } + PhylogenyNode n = nodes.get( 0 ); + while ( n != null ) { + if ( n.getNodeData().isHasTaxonomy() + && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) { + c = ForesterUtil.obtainColorDependingOnTaxonomyGroup( n.getNodeData().getTaxonomy() + .getScientificName(), tax_code ); + } + if ( ( c == null ) && !ForesterUtil.isEmpty( n.getName() ) ) { + c = ForesterUtil.obtainColorDependingOnTaxonomyGroup( n.getName(), tax_code ); + } + if ( c != null ) { + break; + } + n = n.getParent(); + } + if ( c == null ) { + throw new IllegalArgumentException( "no color found for taxonomy code \"" + tax_code + "\"" ); + } + final String hex = String.format( "#%02x%02x%02x", c.getRed(), c.getGreen(), c.getBlue() ); + _TAXCODE_HEXCOLORSTRING_MAP.put( tax_code, hex ); + } + else { + throw new IllegalArgumentException( "unable to obtain color for code " + tax_code + + " (tree is null or empty and code is not in map)" ); + } + } + return _TAXCODE_HEXCOLORSTRING_MAP.get( tax_code ); + } + + public static void performDomainArchitectureAnalysis( final SortedMap> domain_architecutures, + final SortedMap domain_architecuture_counts, + final int min_count, + final File da_counts_outfile, + final File unique_da_outfile ) { + checkForOutputFileWriteability( da_counts_outfile ); + checkForOutputFileWriteability( unique_da_outfile ); + try { + final BufferedWriter da_counts_out = new BufferedWriter( new FileWriter( da_counts_outfile ) ); + final BufferedWriter unique_da_out = new BufferedWriter( new FileWriter( unique_da_outfile ) ); + final Iterator> it = domain_architecuture_counts.entrySet().iterator(); + while ( it.hasNext() ) { + final Map.Entry e = it.next(); + final String da = e.getKey(); + final int count = e.getValue(); + if ( count >= min_count ) { + da_counts_out.write( da ); + da_counts_out.write( "\t" ); + da_counts_out.write( String.valueOf( count ) ); + da_counts_out.write( ForesterUtil.LINE_SEPARATOR ); + } + if ( count == 1 ) { + final Iterator>> it2 = domain_architecutures.entrySet().iterator(); + while ( it2.hasNext() ) { + final Map.Entry> e2 = it2.next(); + final String genome = e2.getKey(); + final Set das = e2.getValue(); + if ( das.contains( da ) ) { + unique_da_out.write( genome ); + unique_da_out.write( "\t" ); + unique_da_out.write( da ); + unique_da_out.write( ForesterUtil.LINE_SEPARATOR ); + } + } + } + } + unique_da_out.close(); + da_counts_out.close(); + } + catch ( final IOException e ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() ); + } + ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote distance matrices to \"" + da_counts_outfile + "\"" ); + ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote distance matrices to \"" + unique_da_outfile + "\"" ); + // } public static void preparePhylogeny( final Phylogeny p, @@ -1348,6 +1447,225 @@ public final class SurfacingUtil { p.setRooted( true ); } + public static void preparePhylogenyForParsimonyAnalyses( final Phylogeny intree, + final String[][] input_file_properties ) { + 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() ); + } + genomes[ i ] = input_file_properties[ i ][ 1 ]; + } + // + final PhylogenyNodeIterator it = intree.iteratorPostorder(); + while ( it.hasNext() ) { + final PhylogenyNode n = it.next(); + if ( ForesterUtil.isEmpty( n.getName() ) ) { + if ( n.getNodeData().isHasTaxonomy() + && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getTaxonomyCode() ) ) { + n.setName( n.getNodeData().getTaxonomy().getTaxonomyCode() ); + } + else if ( n.getNodeData().isHasTaxonomy() + && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) { + n.setName( n.getNodeData().getTaxonomy().getScientificName() ); + } + else if ( n.getNodeData().isHasTaxonomy() + && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getCommonName() ) ) { + n.setName( n.getNodeData().getTaxonomy().getCommonName() ); + } + else { + ForesterUtil + .fatalError( surfacing.PRG_NAME, + "node with no name, scientific name, common name, or taxonomy code present" ); + } + } + } + // + final List igns = PhylogenyMethods.deleteExternalNodesPositiveSelection( genomes, intree ); + if ( igns.size() > 0 ) { + System.out.println( "Not using the following " + igns.size() + " nodes:" ); + for( int i = 0; i < igns.size(); ++i ) { + System.out.println( " " + i + ": " + igns.get( i ) ); + } + System.out.println( "--" ); + } + for( final String[] input_file_propertie : input_file_properties ) { + try { + intree.getNode( input_file_propertie[ 1 ] ); + } + catch ( final IllegalArgumentException e ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_propertie[ 1 ] + + "] not present/not unique in input tree" ); + } + } + } + + public static void printOutPercentageOfMultidomainProteins( final SortedMap all_genomes_domains_per_potein_histo, + final Writer log_writer ) { + int sum = 0; + for( final Entry entry : all_genomes_domains_per_potein_histo.entrySet() ) { + sum += entry.getValue(); + } + final double percentage = ( 100.0 * ( sum - all_genomes_domains_per_potein_histo.get( 1 ) ) ) / sum; + ForesterUtil.programMessage( surfacing.PRG_NAME, "Percentage of multidomain proteins: " + percentage + "%" ); + log( "Percentage of multidomain proteins: : " + percentage + "%", log_writer ); + } + + public static void processFilter( final File filter_file, final SortedSet filter ) { + SortedSet filter_str = null; + try { + filter_str = ForesterUtil.file2set( filter_file ); + } + catch ( final IOException e ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() ); + } + if ( filter_str != null ) { + for( final String string : filter_str ) { + filter.add( string ); + } + } + if ( surfacing.VERBOSE ) { + System.out.println( "Filter:" ); + for( final String domainId : filter ) { + System.out.println( domainId ); + } + } + } + + public static String[][] processInputGenomesFile( final File input_genomes ) { + String[][] input_file_properties = null; + try { + input_file_properties = ForesterUtil.file22dArray( input_genomes ); + } + catch ( final IOException e ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, + "genomes files is to be in the following format \" \": " + + e.getLocalizedMessage() ); + } + final Set specs = new HashSet(); + 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 ] ); + } + if ( specs.contains( input_file_properties[ i ][ 1 ] ) ) { + 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" ); + } + paths.add( input_file_properties[ i ][ 0 ] ); + final String error = ForesterUtil.isReadableFile( new File( input_file_properties[ i ][ 0 ] ) ); + if ( !ForesterUtil.isEmpty( error ) ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, error ); + } + } + return input_file_properties; + } + + public static void processPlusMinusAnalysisOption( final CommandLineArguments cla, + final List high_copy_base, + final List high_copy_target, + final List low_copy, + 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 + "=" ); + } + final File plus_minus_file = new File( cla.getOptionValue( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ); + final String msg = ForesterUtil.isReadableFile( plus_minus_file ); + if ( !ForesterUtil.isEmpty( msg ) ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + plus_minus_file + "\": " + msg ); + } + processPlusMinusFile( plus_minus_file, high_copy_base, high_copy_target, low_copy, numbers ); + } + } + + // First numbers is minimal difference, second is factor. + public static void processPlusMinusFile( final File plus_minus_file, + final List high_copy_base, + final List high_copy_target, + final List low_copy, + final List numbers ) { + Set species_set = null; + int min_diff = surfacing.PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT; + double factor = surfacing.PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT; + try { + species_set = ForesterUtil.file2set( plus_minus_file ); + } + catch ( final IOException e ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() ); + } + if ( species_set != null ) { + for( final String species : species_set ) { + final String species_trimmed = species.substring( 1 ); + if ( species.startsWith( "+" ) ) { + if ( low_copy.contains( species_trimmed ) ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, + "species/genome names can not appear with both '+' and '-' suffix, as appears the case for: \"" + + species_trimmed + "\"" ); + } + high_copy_base.add( species_trimmed ); + } + else if ( species.startsWith( "*" ) ) { + if ( low_copy.contains( species_trimmed ) ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, + "species/genome names can not appear with both '*' and '-' suffix, as appears the case for: \"" + + species_trimmed + "\"" ); + } + high_copy_target.add( species_trimmed ); + } + else if ( species.startsWith( "-" ) ) { + if ( high_copy_base.contains( species_trimmed ) || high_copy_target.contains( species_trimmed ) ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, + "species/genome names can not appear with both '+' or '*' and '-' suffix, as appears the case for: \"" + + species_trimmed + "\"" ); + } + low_copy.add( species_trimmed ); + } + else if ( species.startsWith( "$D" ) ) { + try { + min_diff = Integer.parseInt( species.substring( 3 ) ); + } + catch ( final NumberFormatException e ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, + "could not parse integer value for minimal difference from: \"" + + species.substring( 3 ) + "\"" ); + } + } + else if ( species.startsWith( "$F" ) ) { + try { + 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 ) + "\"" ); + } + } + 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 + "\"" ); + } + numbers.add( new Integer( min_diff + "" ) ); + numbers.add( new Double( factor + "" ) ); + } + } + else { + ForesterUtil.fatalError( surfacing.PRG_NAME, "'plus minus' file [" + plus_minus_file + "] appears empty" ); + } + } + /* * species | protein id | n-terminal domain | c-terminal domain | n-terminal domain per domain E-value | c-terminal domain per domain E-value * @@ -1367,7 +1685,7 @@ public final class SurfacingUtil { if ( domains.size() > 1 ) { final Map counts = new HashMap(); for( final Domain domain : domains ) { - final String id = domain.getDomainId().getId(); + final String id = domain.getDomainId(); if ( counts.containsKey( id ) ) { counts.put( id, counts.get( id ) + 1 ); } @@ -1384,24 +1702,24 @@ public final class SurfacingUtil { domain_n = domains.get( j ); domain_c = domains.get( i ); } - final String dc = domain_n.getDomainId().getId() + domain_c.getDomainId().getId(); + final String dc = domain_n.getDomainId() + domain_c.getDomainId(); if ( !dcs.contains( dc ) ) { dcs.add( dc ); sb.append( protein.getSpecies() ); sb.append( separator ); sb.append( protein_id ); sb.append( separator ); - sb.append( domain_n.getDomainId().getId() ); + sb.append( domain_n.getDomainId() ); sb.append( separator ); - sb.append( domain_c.getDomainId().getId() ); + sb.append( domain_c.getDomainId() ); sb.append( separator ); sb.append( domain_n.getPerDomainEvalue() ); sb.append( separator ); sb.append( domain_c.getPerDomainEvalue() ); sb.append( separator ); - sb.append( counts.get( domain_n.getDomainId().getId() ) ); + sb.append( counts.get( domain_n.getDomainId() ) ); sb.append( separator ); - sb.append( counts.get( domain_c.getDomainId().getId() ) ); + sb.append( counts.get( domain_c.getDomainId() ) ); sb.append( ForesterUtil.LINE_SEPARATOR ); } } @@ -1412,7 +1730,7 @@ public final class SurfacingUtil { sb.append( separator ); sb.append( protein_id ); sb.append( separator ); - sb.append( domains.get( 0 ).getDomainId().getId() ); + sb.append( domains.get( 0 ).getDomainId() ); sb.append( separator ); sb.append( separator ); sb.append( domains.get( 0 ).getPerDomainEvalue() ); @@ -1437,55 +1755,6 @@ public final class SurfacingUtil { return sb; } - /** - * - * Example regarding engulfment: ------------0.1 ----------0.2 --0.3 => - * domain with 0.3 is ignored - * - * -----------0.1 ----------0.2 --0.3 => domain with 0.3 is ignored - * - * - * ------------0.1 ----------0.3 --0.2 => domains with 0.3 and 0.2 are _not_ - * ignored - * - * @param max_allowed_overlap - * maximal allowed overlap (inclusive) to be still considered not - * overlapping (zero or negative value to allow any overlap) - * @param remove_engulfed_domains - * to remove domains which are completely engulfed by coverage of - * domains with better support - * @param protein - * @return - */ - public static Protein removeOverlappingDomains( final int max_allowed_overlap, - final boolean remove_engulfed_domains, - final Protein protein ) { - final Protein pruned_protein = new BasicProtein( protein.getProteinId().getId(), protein.getSpecies() - .getSpeciesId(), protein.getLength() ); - final List sorted = SurfacingUtil.sortDomainsWithAscendingConfidenceValues( protein ); - final List covered_positions = new ArrayList(); - for( final Domain domain : sorted ) { - if ( ( ( max_allowed_overlap < 0 ) || ( SurfacingUtil.calculateOverlap( domain, covered_positions ) <= max_allowed_overlap ) ) - && ( !remove_engulfed_domains || !isEngulfed( domain, covered_positions ) ) ) { - final int covered_positions_size = covered_positions.size(); - for( int i = covered_positions_size; i < domain.getFrom(); ++i ) { - covered_positions.add( false ); - } - final int new_covered_positions_size = covered_positions.size(); - for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) { - if ( i < new_covered_positions_size ) { - covered_positions.set( i, true ); - } - else { - covered_positions.add( true ); - } - } - pruned_protein.addProteinDomain( domain ); - } - } - return pruned_protein; - } - public static List sortDomainsWithAscendingConfidenceValues( final Protein protein ) { final List domains = new ArrayList(); for( final Domain d : protein.getProteinDomains() ) { @@ -1495,17 +1764,26 @@ public final class SurfacingUtil { return domains; } - 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 ); - System.exit( -1 ); + public static int storeDomainArchitectures( final String genome, + final SortedMap> domain_architecutures, + final List protein_list, + final Map distinct_domain_architecuture_counts ) { + final Set da = new HashSet(); + domain_architecutures.put( genome, da ); + for( final Protein protein : protein_list ) { + final String da_str = ( ( BasicProtein ) protein ).toDomainArchitectureString( "~", 3, "=" ); + if ( !da.contains( da_str ) ) { + if ( !distinct_domain_architecuture_counts.containsKey( da_str ) ) { + distinct_domain_architecuture_counts.put( da_str, 1 ); + } + else { + distinct_domain_architecuture_counts.put( da_str, + distinct_domain_architecuture_counts.get( da_str ) + 1 ); + } + da.add( da_str ); + } } - final List l = new ArrayList( 2 ); - l.add( s[ 0 ] ); - l.add( s[ 1 ] ); - return l; + return da.size(); } public static void writeAllDomainsChangedOnAllSubtrees( final Phylogeny p, @@ -1537,212 +1815,66 @@ public final class SurfacingUtil { } } - private static void writeAllEncounteredPfamsToFile( final Map> domain_id_to_go_ids_map, - final Map go_id_to_term_map, - final String outfile_name, - final SortedSet all_pfams_encountered ) { - 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 ); - int biological_process_counter = 0; - int cellular_component_counter = 0; - int molecular_function_counter = 0; - int pfams_with_mappings_counter = 0; - int pfams_without_mappings_counter = 0; - int pfams_without_mappings_to_bp_or_mf_counter = 0; - int pfams_with_mappings_to_bp_or_mf_counter = 0; + public static void writeBinaryDomainCombinationsFileForGraphAnalysis( final String[][] input_file_properties, + final File output_dir, + final GenomeWideCombinableDomains gwcd, + final int i, + final GenomeWideCombinableDomainsSortOrder dc_sort_order ) { + File dc_outfile_dot = new File( input_file_properties[ i ][ 1 ] + + surfacing.DOMAIN_COMBINITONS_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS ); + if ( output_dir != null ) { + dc_outfile_dot = new File( output_dir + ForesterUtil.FILE_SEPARATOR + dc_outfile_dot ); + } + checkForOutputFileWriteability( dc_outfile_dot ); + final SortedSet binary_combinations = createSetOfAllBinaryDomainCombinationsPerGenome( gwcd ); try { - final Writer all_pfams_encountered_writer = new BufferedWriter( new FileWriter( all_pfams_encountered_file ) ); - final Writer all_pfams_encountered_with_go_annotation_writer = new BufferedWriter( new FileWriter( all_pfams_encountered_with_go_annotation_file ) ); - final Writer summary_writer = new BufferedWriter( new FileWriter( encountered_pfams_summary_file ) ); - summary_writer.write( "# Pfam to GO mapping summary" ); - summary_writer.write( ForesterUtil.LINE_SEPARATOR ); - summary_writer.write( "# Actual summary is at the end of this file." ); - summary_writer.write( ForesterUtil.LINE_SEPARATOR ); - summary_writer.write( "# Encountered Pfams without a GO mapping:" ); - summary_writer.write( ForesterUtil.LINE_SEPARATOR ); - for( final String pfam : all_pfams_encountered ) { - all_pfams_encountered_writer.write( pfam ); - all_pfams_encountered_writer.write( ForesterUtil.LINE_SEPARATOR ); - final DomainId domain_id = new DomainId( pfam ); - if ( domain_id_to_go_ids_map.containsKey( domain_id ) ) { - ++pfams_with_mappings_counter; - all_pfams_encountered_with_go_annotation_writer.write( pfam ); - all_pfams_encountered_with_go_annotation_writer.write( ForesterUtil.LINE_SEPARATOR ); - final List go_ids = domain_id_to_go_ids_map.get( domain_id ); - boolean maps_to_bp = false; - boolean maps_to_cc = false; - boolean maps_to_mf = false; - for( final GoId go_id : go_ids ) { - final GoTerm go_term = go_id_to_term_map.get( go_id ); - if ( go_term.getGoNameSpace().isBiologicalProcess() ) { - maps_to_bp = true; - } - else if ( go_term.getGoNameSpace().isCellularComponent() ) { - maps_to_cc = true; - } - else if ( go_term.getGoNameSpace().isMolecularFunction() ) { - maps_to_mf = true; + final BufferedWriter out_dot = new BufferedWriter( new FileWriter( dc_outfile_dot ) ); + for( final BinaryDomainCombination bdc : binary_combinations ) { + out_dot.write( bdc.toGraphDescribingLanguage( BinaryDomainCombination.OutputFormat.DOT, null, null ) + .toString() ); + out_dot.write( SurfacingConstants.NL ); + } + out_dot.close(); + } + 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 + "\"" ); + } + + public static void writeBinaryStatesMatrixAsListToFile( final CharacterStateMatrix matrix, + final CharacterStateMatrix.GainLossStates state, + final String filename, + final String indentifier_characters_separator, + final String character_separator, + final Map descriptions ) { + final File outfile = new File( filename ); + checkForOutputFileWriteability( outfile ); + final SortedSet sorted_ids = new TreeSet(); + for( int i = 0; i < matrix.getNumberOfIdentifiers(); ++i ) { + sorted_ids.add( matrix.getIdentifier( i ) ); + } + try { + final BufferedWriter out = new BufferedWriter( new FileWriter( outfile ) ); + for( final String id : sorted_ids ) { + out.write( indentifier_characters_separator ); + out.write( "#" + id ); + out.write( indentifier_characters_separator ); + 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 ) ) ) ) { + out.write( matrix.getCharacter( c ) ); + if ( ( descriptions != null ) && !descriptions.isEmpty() + && descriptions.containsKey( matrix.getCharacter( c ) ) ) { + out.write( "\t" ); + out.write( descriptions.get( matrix.getCharacter( c ) ) ); } - } - if ( maps_to_bp ) { - ++biological_process_counter; - } - if ( maps_to_cc ) { - ++cellular_component_counter; - } - if ( maps_to_mf ) { - ++molecular_function_counter; - } - if ( maps_to_bp || maps_to_mf ) { - ++pfams_with_mappings_to_bp_or_mf_counter; - } - else { - ++pfams_without_mappings_to_bp_or_mf_counter; - } - } - else { - ++pfams_without_mappings_to_bp_or_mf_counter; - ++pfams_without_mappings_counter; - summary_writer.write( pfam ); - summary_writer.write( ForesterUtil.LINE_SEPARATOR ); - } - } - 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() ) - + "%]" ); - 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( ForesterUtil.LINE_SEPARATOR ); - summary_writer.write( "# 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() ) + "%]" ); - summary_writer.write( ForesterUtil.LINE_SEPARATOR ); - summary_writer.write( "# Pfams with a mapping : " + pfams_with_mappings_counter + " [" - + ( 100 * pfams_with_mappings_counter / all_pfams_encountered.size() ) + "%]" ); - summary_writer.write( ForesterUtil.LINE_SEPARATOR ); - summary_writer.write( "# 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() ) + "%]" ); - summary_writer.write( ForesterUtil.LINE_SEPARATOR ); - summary_writer.write( "# Pfams with mapping to biological process: " + biological_process_counter + " [" - + ( 100 * biological_process_counter / all_pfams_encountered.size() ) + "%]" ); - summary_writer.write( ForesterUtil.LINE_SEPARATOR ); - summary_writer.write( "# Pfams with mapping to molecular function: " + molecular_function_counter + " [" - + ( 100 * molecular_function_counter / all_pfams_encountered.size() ) + "%]" ); - summary_writer.write( ForesterUtil.LINE_SEPARATOR ); - summary_writer.write( "# 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.close(); - } - catch ( final IOException e ) { - ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "Failure to write: " + e ); - } - } - - public static void writeBinaryDomainCombinationsFileForGraphAnalysis( final String[][] input_file_properties, - final File output_dir, - final GenomeWideCombinableDomains gwcd, - final int i, - final GenomeWideCombinableDomainsSortOrder dc_sort_order ) { - File dc_outfile_dot = new File( input_file_properties[ i ][ 0 ] - + surfacing.DOMAIN_COMBINITONS_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS ); - if ( output_dir != null ) { - dc_outfile_dot = new File( output_dir + ForesterUtil.FILE_SEPARATOR + dc_outfile_dot ); - } - checkForOutputFileWriteability( dc_outfile_dot ); - final SortedSet binary_combinations = createSetOfAllBinaryDomainCombinationsPerGenome( gwcd ); - try { - final BufferedWriter out_dot = new BufferedWriter( new FileWriter( dc_outfile_dot ) ); - for( final BinaryDomainCombination bdc : binary_combinations ) { - out_dot.write( bdc.toGraphDescribingLanguage( BinaryDomainCombination.OutputFormat.DOT, null, null ) - .toString() ); - out_dot.write( SurfacingConstants.NL ); - } - out_dot.close(); - } - 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 + "\"" ); - } - - public static void writeBinaryStatesMatrixAsListToFile( final CharacterStateMatrix matrix, - final CharacterStateMatrix.GainLossStates state, - final String filename, - final String indentifier_characters_separator, - final String character_separator, - final Map descriptions ) { - final File outfile = new File( filename ); - checkForOutputFileWriteability( outfile ); - final SortedSet sorted_ids = new TreeSet(); - for( int i = 0; i < matrix.getNumberOfIdentifiers(); ++i ) { - sorted_ids.add( matrix.getIdentifier( i ) ); - } - try { - final BufferedWriter out = new BufferedWriter( new FileWriter( outfile ) ); - for( final String id : sorted_ids ) { - out.write( indentifier_characters_separator ); - out.write( "#" + id ); - out.write( indentifier_characters_separator ); - 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 ) ) ) ) { - out.write( matrix.getCharacter( c ) ); - if ( ( descriptions != null ) && !descriptions.isEmpty() - && descriptions.containsKey( matrix.getCharacter( c ) ) ) { - out.write( "\t" ); - out.write( descriptions.get( matrix.getCharacter( c ) ) ); - } - out.write( character_separator ); + out.write( character_separator ); } } } @@ -1800,7 +1932,7 @@ public final class SurfacingUtil { ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote characters list: \"" + filename + "\"" ); } - public static void writeBinaryStatesMatrixToList( final Map> domain_id_to_go_ids_map, + public static void writeBinaryStatesMatrixToList( final Map> domain_id_to_go_ids_map, final Map go_id_to_term_map, final GoNameSpace go_namespace_limit, final boolean domain_combinations, @@ -1811,10 +1943,11 @@ public final class SurfacingUtil { final String character_separator, final String title_for_html, final String prefix_for_html, - final Map>[] domain_id_to_secondary_features_maps, + final Map>[] domain_id_to_secondary_features_maps, final SortedSet all_pfams_encountered, final SortedSet pfams_gained_or_lost, - final String suffix_for_per_node_events_file ) { + final String suffix_for_per_node_events_file, + final Map tax_code_to_id_map ) { if ( ( go_namespace_limit != null ) && ( ( go_id_to_term_map == null ) || ( go_id_to_term_map.size() < 1 ) ) ) { throw new IllegalArgumentException( "attempt to use GO namespace limit without a GO-id to term map" ); } @@ -1841,7 +1974,7 @@ public final class SurfacingUtil { int per_node_counter = 0; out.write( "" ); out.write( SurfacingConstants.NL ); - addHtmlHead( out, title_for_html ); + writeHtmlHead( out, title_for_html ); out.write( SurfacingConstants.NL ); out.write( "" ); out.write( SurfacingConstants.NL ); @@ -1875,7 +2008,7 @@ public final class SurfacingUtil { out.write( SurfacingConstants.NL ); out.write( "

" ); out.write( "" + id + "" ); - writeTaxonomyLinks( out, id ); + writeTaxonomyLinks( out, id, tax_code_to_id_map ); out.write( "

" ); out.write( SurfacingConstants.NL ); out.write( "" ); @@ -1955,88 +2088,1016 @@ public final class SurfacingUtil { } } } - if ( per_node_go_mapped_domain_gain_loss_outfile_writer != null ) { - per_node_go_mapped_domain_gain_loss_outfile_writer.close(); - if ( per_node_counter < 1 ) { - per_node_go_mapped_domain_gain_loss_outfile.delete(); - } - per_node_counter = 0; + if ( per_node_go_mapped_domain_gain_loss_outfile_writer != null ) { + per_node_go_mapped_domain_gain_loss_outfile_writer.close(); + if ( per_node_counter < 1 ) { + per_node_go_mapped_domain_gain_loss_outfile.delete(); + } + per_node_counter = 0; + } + out.write( "
" ); + out.write( SurfacingConstants.NL ); + out.write( "
" ); + out.write( SurfacingConstants.NL ); + } // for( final String id : sorted_ids ) { + out.write( "" ); + out.write( SurfacingConstants.NL ); + out.write( "" ); + out.write( SurfacingConstants.NL ); + out.flush(); + out.close(); + } + catch ( final IOException e ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() ); + } + ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote characters detailed HTML list: \"" + filename + "\"" ); + } + + public static void writeDomainCombinationsCountsFile( final String[][] input_file_properties, + final File output_dir, + final Writer per_genome_domain_promiscuity_statistics_writer, + final GenomeWideCombinableDomains gwcd, + final int i, + final GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order ) { + File dc_outfile = new File( input_file_properties[ i ][ 1 ] + + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX ); + if ( output_dir != null ) { + dc_outfile = new File( output_dir + ForesterUtil.FILE_SEPARATOR + dc_outfile ); + } + checkForOutputFileWriteability( dc_outfile ); + try { + final BufferedWriter out = new BufferedWriter( new FileWriter( dc_outfile ) ); + out.write( gwcd.toStringBuilder( dc_sort_order ).toString() ); + out.close(); + } + catch ( final IOException e ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() ); + } + 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" ); + 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.median() ) + "\t" ); + per_genome_domain_promiscuity_statistics_writer.write( ( int ) stats.getMin() + "\t" ); + per_genome_domain_promiscuity_statistics_writer.write( ( int ) stats.getMax() + "\t" ); + per_genome_domain_promiscuity_statistics_writer.write( stats.getN() + "\t" ); + final SortedSet mpds = gwcd.getMostPromiscuosDomain(); + for( final String mpd : mpds ) { + per_genome_domain_promiscuity_statistics_writer.write( mpd + " " ); + } + per_genome_domain_promiscuity_statistics_writer.write( ForesterUtil.LINE_SEPARATOR ); + } + catch ( final IOException e ) { + 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 + "\"" ); + } + else { + ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote domain combination counts for \"" + + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ") to: \"" + + dc_outfile + "\"" ); + } + } + + public static void writeDomainSimilaritiesToFile( final StringBuilder html_desc, + final StringBuilder html_title, + final Writer simple_tab_writer, + final Writer single_writer, + Map split_writers, + final SortedSet similarities, + final boolean treat_as_binary, + final List species_order, + final PrintableDomainSimilarity.PRINT_OPTION print_option, + final DomainSimilarity.DomainSimilarityScoring scoring, + final boolean verbose, + final Map tax_code_to_id_map, + final Phylogeny phy ) throws IOException { + if ( ( single_writer != null ) && ( ( split_writers == null ) || split_writers.isEmpty() ) ) { + split_writers = new HashMap(); + split_writers.put( '_', single_writer ); + } + switch ( print_option ) { + case SIMPLE_TAB_DELIMITED: + break; + case HTML: + for( final Character key : split_writers.keySet() ) { + final Writer w = split_writers.get( key ); + w.write( "" ); + w.write( SurfacingConstants.NL ); + if ( key != '_' ) { + writeHtmlHead( w, "DC analysis (" + html_title + ") " + key.toString().toUpperCase() ); + } + else { + writeHtmlHead( w, "DC analysis (" + html_title + ")" ); + } + w.write( SurfacingConstants.NL ); + w.write( "" ); + w.write( SurfacingConstants.NL ); + w.write( html_desc.toString() ); + w.write( SurfacingConstants.NL ); + w.write( "
" ); + w.write( SurfacingConstants.NL ); + w.write( "
" ); + w.write( SurfacingConstants.NL ); + w.write( "" ); + w.write( SurfacingConstants.NL ); + w.write( "" ); + w.write( SurfacingConstants.NL ); + } + break; + } + // + for( final DomainSimilarity similarity : similarities ) { + if ( ( species_order != null ) && !species_order.isEmpty() ) { + ( ( PrintableDomainSimilarity ) similarity ).setSpeciesOrder( species_order ); + } + if ( single_writer != null ) { + single_writer.write( "" ); + single_writer.write( SurfacingConstants.NL ); + } + else { + Writer local_writer = split_writers.get( ( similarity.getDomainId().charAt( 0 ) + "" ).toLowerCase() + .charAt( 0 ) ); + if ( local_writer == null ) { + local_writer = split_writers.get( '0' ); + } + local_writer.write( "" ); + local_writer.write( SurfacingConstants.NL ); + } + } + for( final Writer w : split_writers.values() ) { + w.write( "
Domains:
" + + similarity.getDomainId() + "
" + + similarity.getDomainId() + "
" ); + w.write( SurfacingConstants.NL ); + w.write( "
" ); + w.write( SurfacingConstants.NL ); + // + w.write( "" ); + w.write( SurfacingConstants.NL ); + w.write( "" ); + w.write( SurfacingConstants.NL ); + writeColorLabels( "Deuterostomia", TaxonomyColors.DEUTEROSTOMIA_COLOR, w ); + writeColorLabels( "Protostomia", TaxonomyColors.PROTOSTOMIA_COLOR, w ); + writeColorLabels( "Cnidaria", TaxonomyColors.CNIDARIA_COLOR, w ); + writeColorLabels( "Placozoa", TaxonomyColors.PLACOZOA_COLOR, w ); + writeColorLabels( "Ctenophora (comb jellies)", TaxonomyColors.CTENOPHORA_COLOR, w ); + writeColorLabels( "Porifera (sponges)", TaxonomyColors.PORIFERA_COLOR, w ); + writeColorLabels( "Choanoflagellida", TaxonomyColors.CHOANOFLAGELLIDA, w ); + writeColorLabels( "Ichthyosporea & Filasterea", TaxonomyColors.ICHTHYOSPOREA_AND_FILASTEREA, w ); + writeColorLabels( "Fungi", TaxonomyColors.FUNGI_COLOR, w ); + writeColorLabels( "Nucleariidae and Fonticula group", + TaxonomyColors.NUCLEARIIDAE_AND_FONTICULA_GROUP_COLOR, + w ); + writeColorLabels( "Amoebozoa", TaxonomyColors.AMOEBOZOA_COLOR, w ); + writeColorLabels( "Embryophyta (plants)", TaxonomyColors.EMBRYOPHYTA_COLOR, w ); + writeColorLabels( "Chlorophyta (green algae)", TaxonomyColors.CHLOROPHYTA_COLOR, w ); + writeColorLabels( "Rhodophyta (red algae)", TaxonomyColors.RHODOPHYTA_COLOR, w ); + writeColorLabels( "Glaucocystophyce (Glaucophyta)", TaxonomyColors.GLAUCOPHYTA_COLOR, w ); + writeColorLabels( "Hacrobia (Cryptophyta & Haptophyceae & Centroheliozoa)", + TaxonomyColors.HACROBIA_COLOR, + w ); + writeColorLabels( "Stramenopiles (Chromophyta, heterokonts)", TaxonomyColors.STRAMENOPILES_COLOR, w ); + writeColorLabels( "Alveolata", TaxonomyColors.ALVEOLATA_COLOR, w ); + writeColorLabels( "Rhizaria", TaxonomyColors.RHIZARIA_COLOR, w ); + writeColorLabels( "Excavata", TaxonomyColors.EXCAVATA_COLOR, w ); + writeColorLabels( "Apusozoa", TaxonomyColors.APUSOZOA_COLOR, w ); + writeColorLabels( "Archaea", TaxonomyColors.ARCHAEA_COLOR, w ); + writeColorLabels( "Bacteria", TaxonomyColors.BACTERIA_COLOR, w ); + w.write( "
" ); + w.write( "Species group colors:" ); + w.write( "
" ); + w.write( SurfacingConstants.NL ); + // + w.write( "
" ); + w.write( SurfacingConstants.NL ); + w.write( "" ); + w.write( SurfacingConstants.NL ); + } + // + for( final DomainSimilarity similarity : similarities ) { + if ( ( species_order != null ) && !species_order.isEmpty() ) { + ( ( PrintableDomainSimilarity ) 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() ); + } + 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 ) ); + if ( local_writer == null ) { + local_writer = split_writers.get( '0' ); + } + local_writer.write( similarity.toStringBuffer( print_option, tax_code_to_id_map, phy ).toString() ); + local_writer.write( SurfacingConstants.NL ); + } + } + switch ( print_option ) { + case HTML: + for( final Writer w : split_writers.values() ) { + w.write( SurfacingConstants.NL ); + w.write( "
" ); + w.write( SurfacingConstants.NL ); + w.write( "" ); + w.write( SurfacingConstants.NL ); + w.write( "" ); + w.write( SurfacingConstants.NL ); + w.write( "" ); + w.write( SurfacingConstants.NL ); + } + break; + default: + break; + } + for( final Writer w : split_writers.values() ) { + w.close(); + } + } + + public static void writeHtmlHead( final Writer w, final String title ) throws IOException { + w.write( SurfacingConstants.NL ); + w.write( "" ); + w.write( "" ); + w.write( title ); + w.write( "" ); + w.write( SurfacingConstants.NL ); + w.write( "" ); + w.write( SurfacingConstants.NL ); + w.write( "" ); + w.write( SurfacingConstants.NL ); + } + + public static void writeMatrixToFile( final CharacterStateMatrix matrix, + final String filename, + final Format format ) { + final File outfile = new File( filename ); + checkForOutputFileWriteability( outfile ); + try { + final BufferedWriter out = new BufferedWriter( new FileWriter( outfile ) ); + matrix.toWriter( out, format ); + out.flush(); + out.close(); + } + catch ( final IOException e ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() ); + } + ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote matrix: \"" + filename + "\"" ); + } + + public static void writeMatrixToFile( final File matrix_outfile, final List matrices ) { + checkForOutputFileWriteability( matrix_outfile ); + try { + final BufferedWriter out = new BufferedWriter( new FileWriter( matrix_outfile ) ); + for( final DistanceMatrix distance_matrix : matrices ) { + out.write( distance_matrix.toStringBuffer( DistanceMatrix.Format.PHYLIP ).toString() ); + out.write( ForesterUtil.LINE_SEPARATOR ); + out.flush(); + } + out.close(); + } + catch ( final IOException e ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() ); + } + ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote distance matrices to \"" + matrix_outfile + "\"" ); + } + + public static void writePhylogenyToFile( final Phylogeny phylogeny, final String filename ) { + final PhylogenyWriter writer = new PhylogenyWriter(); + try { + writer.toPhyloXML( new File( filename ), phylogeny, 1 ); + } + catch ( final IOException e ) { + ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "failed to write phylogeny to \"" + filename + "\": " + + e ); + } + ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote phylogeny to \"" + filename + "\"" ); + } + + public static void writePresentToNexus( final File output_file, + final File positive_filter_file, + final SortedSet filter, + final List gwcd_list ) { + try { + 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 ), + output_file + surfacing.BDC_PRESENT_NEXUS, + Format.NEXUS_BINARY ); + } + catch ( final Exception e ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() ); + } + } + + public static void writeProteinListsForAllSpecies( final File output_dir, + final SortedMap> protein_lists_per_species, + final List gwcd_list, + final double domain_e_cutoff ) { + 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 ); + checkForOutputFileWriteability( out ); + try { + final Writer proteins_file_writer = new BufferedWriter( new FileWriter( out ) ); + extractProteinNames( protein_lists_per_species, + domain, + proteins_file_writer, + "\t", + surfacing.LIMIT_SPEC_FOR_PROT_EX, + domain_e_cutoff ); + proteins_file_writer.close(); + } + catch ( final IOException e ) { + ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() ); + } + ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote proteins list to \"" + out + "\"" ); + } + } + + public static void writeTaxonomyLinks( final Writer writer, + final String species, + 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 ) ) { + writer.write( "uniprot" ); + } + else { + writer.write( "eol" ); + writer.write( "|" ); + writer.write( "scholar" ); + writer.write( "|" ); + writer.write( "google" ); + } + writer.write( "]" ); + } + } + + private final static void addToCountMap( final Map map, final String s ) { + if ( map.containsKey( s ) ) { + map.put( s, map.get( s ) + 1 ); + } + else { + map.put( s, 1 ); + } + } + + private static void calculateIndependentDomainCombinationGains( final Phylogeny local_phylogeny_l, + final String outfilename_for_counts, + final String outfilename_for_dc, + final String outfilename_for_dc_for_go_mapping, + final String outfilename_for_dc_for_go_mapping_unique, + final String outfilename_for_rank_counts, + final String outfilename_for_ancestor_species_counts, + final String outfilename_for_protein_stats, + final Map protein_length_stats_by_dc, + final Map domain_number_stats_by_dc, + final Map domain_length_stats_by_domain ) { + try { + // + // if ( protein_length_stats_by_dc != null ) { + // for( final Entry entry : protein_length_stats_by_dc.entrySet() ) { + // System.out.print( entry.getKey().toString() ); + // System.out.print( ": " ); + // double[] a = entry.getValue().getDataAsDoubleArray(); + // for( int i = 0; i < a.length; i++ ) { + // System.out.print( a[ i ] + " " ); + // } + // System.out.println(); + // } + // } + // if ( domain_number_stats_by_dc != null ) { + // for( final Entry entry : domain_number_stats_by_dc.entrySet() ) { + // System.out.print( entry.getKey().toString() ); + // System.out.print( ": " ); + // double[] a = entry.getValue().getDataAsDoubleArray(); + // for( int i = 0; i < a.length; i++ ) { + // System.out.print( a[ i ] + " " ); + // } + // System.out.println(); + // } + // } + // + final BufferedWriter out_counts = new BufferedWriter( new FileWriter( outfilename_for_counts ) ); + final BufferedWriter out_dc = new BufferedWriter( new FileWriter( outfilename_for_dc ) ); + final BufferedWriter out_dc_for_go_mapping = new BufferedWriter( new FileWriter( outfilename_for_dc_for_go_mapping ) ); + final BufferedWriter out_dc_for_go_mapping_unique = new BufferedWriter( new FileWriter( outfilename_for_dc_for_go_mapping_unique ) ); + final SortedMap dc_gain_counts = new TreeMap(); + for( final PhylogenyNodeIterator it = local_phylogeny_l.iteratorPostorder(); it.hasNext(); ) { + final PhylogenyNode n = it.next(); + final Set gained_dc = n.getNodeData().getBinaryCharacters().getGainedCharacters(); + for( final String dc : gained_dc ) { + if ( dc_gain_counts.containsKey( dc ) ) { + dc_gain_counts.put( dc, dc_gain_counts.get( dc ) + 1 ); + } + else { + dc_gain_counts.put( dc, 1 ); + } + } + } + final SortedMap histogram = new TreeMap(); + final SortedMap domain_lists = new TreeMap(); + final SortedMap dc_reapp_counts_to_protein_length_stats = new TreeMap(); + final SortedMap dc_reapp_counts_to_domain_number_stats = new TreeMap(); + final SortedMap dc_reapp_counts_to_domain_lengths_stats = new TreeMap(); + final SortedMap> domain_lists_go = new TreeMap>(); + final SortedMap> domain_lists_go_unique = new TreeMap>(); + final Set dcs = dc_gain_counts.keySet(); + final SortedSet more_than_once = new TreeSet(); + DescriptiveStatistics gained_once_lengths_stats = new BasicDescriptiveStatistics(); + DescriptiveStatistics gained_once_domain_count_stats = new BasicDescriptiveStatistics(); + DescriptiveStatistics gained_multiple_times_lengths_stats = new BasicDescriptiveStatistics(); + final DescriptiveStatistics gained_multiple_times_domain_count_stats = new BasicDescriptiveStatistics(); + long gained_multiple_times_domain_length_sum = 0; + long gained_once_domain_length_sum = 0; + long gained_multiple_times_domain_length_count = 0; + long gained_once_domain_length_count = 0; + for( final String dc : dcs ) { + final int count = dc_gain_counts.get( dc ); + if ( histogram.containsKey( count ) ) { + histogram.put( count, histogram.get( count ) + 1 ); + domain_lists.get( count ).append( ", " + dc ); + domain_lists_go.get( count ).addAll( splitDomainCombination( dc ) ); + domain_lists_go_unique.get( count ).addAll( splitDomainCombination( dc ) ); + } + else { + histogram.put( count, 1 ); + domain_lists.put( count, new StringBuilder( dc ) ); + final PriorityQueue q = new PriorityQueue(); + q.addAll( splitDomainCombination( dc ) ); + domain_lists_go.put( count, q ); + final SortedSet set = new TreeSet(); + set.addAll( splitDomainCombination( dc ) ); + domain_lists_go_unique.put( count, set ); + } + if ( protein_length_stats_by_dc != null ) { + 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() ); + } + 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() ); + } + 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() ); + } + if ( count > 1 ) { + more_than_once.add( dc ); + if ( protein_length_stats_by_dc != null ) { + final DescriptiveStatistics s = protein_length_stats_by_dc.get( dc ); + for( final double element : s.getData() ) { + gained_multiple_times_lengths_stats.addValue( element ); + } + } + if ( domain_number_stats_by_dc != null ) { + final DescriptiveStatistics s = domain_number_stats_by_dc.get( dc ); + for( final double element : s.getData() ) { + gained_multiple_times_domain_count_stats.addValue( element ); + } + } + if ( domain_length_stats_by_domain != null ) { + final String[] ds = dc.split( "=" ); + final DescriptiveStatistics s0 = domain_length_stats_by_domain.get( ds[ 0 ] ); + final DescriptiveStatistics s1 = domain_length_stats_by_domain.get( ds[ 1 ] ); + for( final double element : s0.getData() ) { + gained_multiple_times_domain_length_sum += element; + ++gained_multiple_times_domain_length_count; + } + for( final double element : s1.getData() ) { + gained_multiple_times_domain_length_sum += element; + ++gained_multiple_times_domain_length_count; + } + } + } + else { + if ( protein_length_stats_by_dc != null ) { + final DescriptiveStatistics s = protein_length_stats_by_dc.get( dc ); + for( final double element : s.getData() ) { + gained_once_lengths_stats.addValue( element ); + } + } + if ( domain_number_stats_by_dc != null ) { + final DescriptiveStatistics s = domain_number_stats_by_dc.get( dc ); + for( final double element : s.getData() ) { + gained_once_domain_count_stats.addValue( element ); + } + } + if ( domain_length_stats_by_domain != null ) { + final String[] ds = dc.split( "=" ); + final DescriptiveStatistics s0 = domain_length_stats_by_domain.get( ds[ 0 ] ); + final DescriptiveStatistics s1 = domain_length_stats_by_domain.get( ds[ 1 ] ); + for( final double element : s0.getData() ) { + gained_once_domain_length_sum += element; + ++gained_once_domain_length_count; + } + for( final double element : s1.getData() ) { + gained_once_domain_length_sum += element; + ++gained_once_domain_length_count; + } + } + } + } + final Set histogram_keys = histogram.keySet(); + for( final Integer histogram_key : histogram_keys ) { + final int count = histogram.get( histogram_key ); + final StringBuilder dc = domain_lists.get( histogram_key ); + out_counts.write( histogram_key + "\t" + count + ForesterUtil.LINE_SEPARATOR ); + out_dc.write( histogram_key + "\t" + dc + ForesterUtil.LINE_SEPARATOR ); + out_dc_for_go_mapping.write( "#" + histogram_key + ForesterUtil.LINE_SEPARATOR ); + final Object[] sorted = domain_lists_go.get( histogram_key ).toArray(); + Arrays.sort( sorted ); + for( final Object domain : sorted ) { + out_dc_for_go_mapping.write( domain + ForesterUtil.LINE_SEPARATOR ); + } + out_dc_for_go_mapping_unique.write( "#" + histogram_key + ForesterUtil.LINE_SEPARATOR ); + for( final String domain : domain_lists_go_unique.get( histogram_key ) ) { + out_dc_for_go_mapping_unique.write( domain + ForesterUtil.LINE_SEPARATOR ); + } + } + out_counts.close(); + out_dc.close(); + out_dc_for_go_mapping.close(); + out_dc_for_go_mapping_unique.close(); + final SortedMap lca_rank_counts = new TreeMap(); + final SortedMap lca_ancestor_species_counts = new TreeMap(); + for( final String dc : more_than_once ) { + final List nodes = new ArrayList(); + for( final PhylogenyNodeIterator it = local_phylogeny_l.iteratorExternalForward(); it.hasNext(); ) { + final PhylogenyNode n = it.next(); + if ( n.getNodeData().getBinaryCharacters().getGainedCharacters().contains( dc ) ) { + nodes.add( n ); + } + } + for( int i = 0; i < ( nodes.size() - 1 ); ++i ) { + for( int j = i + 1; j < nodes.size(); ++j ) { + final PhylogenyNode lca = PhylogenyMethods.calculateLCA( nodes.get( i ), nodes.get( j ) ); + String rank = "unknown"; + if ( lca.getNodeData().isHasTaxonomy() + && !ForesterUtil.isEmpty( lca.getNodeData().getTaxonomy().getRank() ) ) { + rank = lca.getNodeData().getTaxonomy().getRank(); + } + addToCountMap( lca_rank_counts, rank ); + String lca_species; + if ( lca.getNodeData().isHasTaxonomy() + && !ForesterUtil.isEmpty( lca.getNodeData().getTaxonomy().getScientificName() ) ) { + lca_species = lca.getNodeData().getTaxonomy().getScientificName(); + } + else if ( lca.getNodeData().isHasTaxonomy() + && !ForesterUtil.isEmpty( lca.getNodeData().getTaxonomy().getCommonName() ) ) { + lca_species = lca.getNodeData().getTaxonomy().getCommonName(); + } + else { + lca_species = lca.getName(); + } + addToCountMap( lca_ancestor_species_counts, lca_species ); + } + } + } + final BufferedWriter out_for_rank_counts = new BufferedWriter( new FileWriter( outfilename_for_rank_counts ) ); + final BufferedWriter out_for_ancestor_species_counts = new BufferedWriter( new FileWriter( outfilename_for_ancestor_species_counts ) ); + ForesterUtil.map2writer( out_for_rank_counts, lca_rank_counts, "\t", ForesterUtil.LINE_SEPARATOR ); + ForesterUtil.map2writer( out_for_ancestor_species_counts, + lca_ancestor_species_counts, + "\t", + 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 ) ) ) { + final BufferedWriter w = new BufferedWriter( new FileWriter( outfilename_for_protein_stats ) ); + w.write( "Domain Lengths: " ); + w.write( "\n" ); + if ( domain_length_stats_by_domain != null ) { + for( final Entry entry : dc_reapp_counts_to_domain_lengths_stats + .entrySet() ) { + w.write( entry.getKey().toString() ); + w.write( "\t" + entry.getValue().arithmeticMean() ); + w.write( "\t" + entry.getValue().median() ); + w.write( "\n" ); + } + } + w.flush(); + w.write( "\n" ); + w.write( "\n" ); + w.write( "Protein Lengths: " ); + w.write( "\n" ); + if ( protein_length_stats_by_dc != null ) { + for( final Entry entry : dc_reapp_counts_to_protein_length_stats + .entrySet() ) { + w.write( entry.getKey().toString() ); + w.write( "\t" + entry.getValue().arithmeticMean() ); + w.write( "\t" + entry.getValue().median() ); + w.write( "\n" ); + } + } + w.flush(); + w.write( "\n" ); + w.write( "\n" ); + w.write( "Number of domains: " ); + w.write( "\n" ); + if ( domain_number_stats_by_dc != null ) { + for( final Entry entry : dc_reapp_counts_to_domain_number_stats + .entrySet() ) { + w.write( entry.getKey().toString() ); + w.write( "\t" + entry.getValue().arithmeticMean() ); + w.write( "\t" + entry.getValue().median() ); + w.write( "\n" ); + } + } + w.flush(); + w.write( "\n" ); + w.write( "\n" ); + w.write( "Gained once, domain lengths:" ); + w.write( "\n" ); + w.write( "N: " + gained_once_domain_length_count ); + w.write( "\n" ); + w.write( "Avg: " + ( ( double ) gained_once_domain_length_sum / gained_once_domain_length_count ) ); + w.write( "\n" ); + w.write( "\n" ); + w.write( "Gained multiple times, domain lengths:" ); + 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( "\n" ); + w.write( "\n" ); + w.write( "\n" ); + w.write( "\n" ); + w.write( "Gained once, protein lengths:" ); + w.write( "\n" ); + w.write( gained_once_lengths_stats.toString() ); + gained_once_lengths_stats = null; + w.write( "\n" ); + w.write( "\n" ); + w.write( "Gained once, domain counts:" ); + w.write( "\n" ); + w.write( gained_once_domain_count_stats.toString() ); + gained_once_domain_count_stats = null; + w.write( "\n" ); + w.write( "\n" ); + w.write( "Gained multiple times, protein lengths:" ); + w.write( "\n" ); + w.write( gained_multiple_times_lengths_stats.toString() ); + gained_multiple_times_lengths_stats = null; + w.write( "\n" ); + w.write( "\n" ); + w.write( "Gained multiple times, domain counts:" ); + w.write( "\n" ); + w.write( gained_multiple_times_domain_count_stats.toString() ); + w.flush(); + w.close(); + } + } + 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 lists to (for GO mapping) [" + + outfilename_for_dc_for_go_mapping + "]" ); + ForesterUtil.programMessage( surfacing.PRG_NAME, + "Wrote independent domain combination gains fitch lists to (for GO mapping, unique) [" + + outfilename_for_dc_for_go_mapping_unique + "]" ); + } + + private static SortedSet collectAllDomainsChangedOnSubtree( final PhylogenyNode subtree_root, + final boolean get_gains ) { + final SortedSet domains = new TreeSet(); + for( final PhylogenyNode descendant : PhylogenyMethods.getAllDescendants( subtree_root ) ) { + final BinaryCharacters chars = descendant.getNodeData().getBinaryCharacters(); + if ( get_gains ) { + domains.addAll( chars.getGainedCharacters() ); + } + else { + domains.addAll( chars.getLostCharacters() ); + } + } + return domains; + } + + private static File createBaseDirForPerNodeDomainFiles( final String base_dir, + final boolean domain_combinations, + final CharacterStateMatrix.GainLossStates state, + final String outfile ) { + File per_node_go_mapped_domain_gain_loss_files_base_dir = new File( new File( outfile ).getParent() + + ForesterUtil.FILE_SEPARATOR + base_dir ); + if ( !per_node_go_mapped_domain_gain_loss_files_base_dir.exists() ) { + per_node_go_mapped_domain_gain_loss_files_base_dir.mkdir(); + } + if ( domain_combinations ) { + per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir + + ForesterUtil.FILE_SEPARATOR + "DC" ); + } + else { + per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir + + ForesterUtil.FILE_SEPARATOR + "DOMAINS" ); + } + if ( !per_node_go_mapped_domain_gain_loss_files_base_dir.exists() ) { + per_node_go_mapped_domain_gain_loss_files_base_dir.mkdir(); + } + if ( state == GainLossStates.GAIN ) { + per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir + + ForesterUtil.FILE_SEPARATOR + "GAINS" ); + } + else if ( state == GainLossStates.LOSS ) { + per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir + + ForesterUtil.FILE_SEPARATOR + "LOSSES" ); + } + else { + per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir + + ForesterUtil.FILE_SEPARATOR + "PRESENT" ); + } + if ( !per_node_go_mapped_domain_gain_loss_files_base_dir.exists() ) { + per_node_go_mapped_domain_gain_loss_files_base_dir.mkdir(); + } + return per_node_go_mapped_domain_gain_loss_files_base_dir; + } + + private static SortedSet createSetOfAllBinaryDomainCombinationsPerGenome( final GenomeWideCombinableDomains gwcd ) { + final SortedMap cds = gwcd.getAllCombinableDomainsIds(); + final SortedSet binary_combinations = new TreeSet(); + for( final String domain_id : cds.keySet() ) { + final CombinableDomains cd = cds.get( domain_id ); + binary_combinations.addAll( cd.toBinaryDomainCombinations() ); + } + return binary_combinations; + } + + private static void printSomeStats( final DescriptiveStatistics stats, final AsciiHistogram histo, final Writer w ) + throws IOException { + w.write( "
" ); + w.write( "
" ); + w.write( SurfacingConstants.NL ); + w.write( "
" );
+        w.write( SurfacingConstants.NL );
+        if ( histo != null ) {
+            w.write( histo.toStringBuffer( 20, '|', 40, 5 ).toString() );
+            w.write( SurfacingConstants.NL );
+        }
+        w.write( "
" ); + w.write( SurfacingConstants.NL ); + w.write( "" ); + w.write( SurfacingConstants.NL ); + w.write( "" ); + w.write( SurfacingConstants.NL ); + w.write( "" ); + w.write( SurfacingConstants.NL ); + w.write( "" ); + w.write( SurfacingConstants.NL ); + w.write( "" ); + w.write( SurfacingConstants.NL ); + if ( stats.getN() > 1 ) { + w.write( "" ); + } + else { + w.write( "" ); + } + w.write( SurfacingConstants.NL ); + w.write( "
N: " + stats.getN() + "
Min: " + stats.getMin() + "
Max: " + stats.getMax() + "
Mean: " + stats.arithmeticMean() + "
SD: " + stats.sampleStandardDeviation() + "
SD: n/a
" ); + w.write( SurfacingConstants.NL ); + w.write( "
" ); + w.write( SurfacingConstants.NL ); + } + + 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 ); + System.exit( -1 ); + } + final List l = new ArrayList( 2 ); + l.add( s[ 0 ] ); + l.add( s[ 1 ] ); + return l; + } + + private static void writeAllEncounteredPfamsToFile( final Map> domain_id_to_go_ids_map, + final Map go_id_to_term_map, + final String outfile_name, + final SortedSet all_pfams_encountered ) { + 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 ); + int biological_process_counter = 0; + int cellular_component_counter = 0; + int molecular_function_counter = 0; + int pfams_with_mappings_counter = 0; + int pfams_without_mappings_counter = 0; + int pfams_without_mappings_to_bp_or_mf_counter = 0; + int pfams_with_mappings_to_bp_or_mf_counter = 0; + try { + final Writer all_pfams_encountered_writer = new BufferedWriter( new FileWriter( all_pfams_encountered_file ) ); + final Writer all_pfams_encountered_with_go_annotation_writer = new BufferedWriter( new FileWriter( all_pfams_encountered_with_go_annotation_file ) ); + final Writer summary_writer = new BufferedWriter( new FileWriter( encountered_pfams_summary_file ) ); + summary_writer.write( "# Pfam to GO mapping summary" ); + summary_writer.write( ForesterUtil.LINE_SEPARATOR ); + summary_writer.write( "# Actual summary is at the end of this file." ); + summary_writer.write( ForesterUtil.LINE_SEPARATOR ); + summary_writer.write( "# Encountered Pfams without a GO mapping:" ); + summary_writer.write( ForesterUtil.LINE_SEPARATOR ); + for( final String pfam : all_pfams_encountered ) { + all_pfams_encountered_writer.write( pfam ); + all_pfams_encountered_writer.write( ForesterUtil.LINE_SEPARATOR ); + final String domain_id = new String( pfam ); + if ( domain_id_to_go_ids_map.containsKey( domain_id ) ) { + ++pfams_with_mappings_counter; + all_pfams_encountered_with_go_annotation_writer.write( pfam ); + all_pfams_encountered_with_go_annotation_writer.write( ForesterUtil.LINE_SEPARATOR ); + final List go_ids = domain_id_to_go_ids_map.get( domain_id ); + boolean maps_to_bp = false; + boolean maps_to_cc = false; + boolean maps_to_mf = false; + for( final GoId go_id : go_ids ) { + final GoTerm go_term = go_id_to_term_map.get( go_id ); + if ( go_term.getGoNameSpace().isBiologicalProcess() ) { + maps_to_bp = true; + } + else if ( go_term.getGoNameSpace().isCellularComponent() ) { + maps_to_cc = true; + } + else if ( go_term.getGoNameSpace().isMolecularFunction() ) { + maps_to_mf = true; + } + } + if ( maps_to_bp ) { + ++biological_process_counter; + } + if ( maps_to_cc ) { + ++cellular_component_counter; + } + if ( maps_to_mf ) { + ++molecular_function_counter; + } + if ( maps_to_bp || maps_to_mf ) { + ++pfams_with_mappings_to_bp_or_mf_counter; + } + else { + ++pfams_without_mappings_to_bp_or_mf_counter; + } + } + else { + ++pfams_without_mappings_to_bp_or_mf_counter; + ++pfams_without_mappings_counter; + summary_writer.write( pfam ); + summary_writer.write( ForesterUtil.LINE_SEPARATOR ); } - out.write( "" ); - out.write( SurfacingConstants.NL ); - out.write( "
" ); - out.write( SurfacingConstants.NL ); - } // for( final String id : sorted_ids ) { - out.write( "" ); - out.write( SurfacingConstants.NL ); - out.write( "" ); - out.write( SurfacingConstants.NL ); - out.flush(); - out.close(); + } + 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() ) + "%]" ); + 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( ForesterUtil.LINE_SEPARATOR ); + summary_writer.write( "# 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() ) + "%]" ); + summary_writer.write( ForesterUtil.LINE_SEPARATOR ); + summary_writer.write( "# Pfams with a mapping : " + pfams_with_mappings_counter + " [" + + ( ( 100 * pfams_with_mappings_counter ) / all_pfams_encountered.size() ) + "%]" ); + summary_writer.write( ForesterUtil.LINE_SEPARATOR ); + summary_writer.write( "# 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() ) + "%]" ); + summary_writer.write( ForesterUtil.LINE_SEPARATOR ); + summary_writer.write( "# Pfams with mapping to biological process: " + biological_process_counter + " [" + + ( ( 100 * biological_process_counter ) / all_pfams_encountered.size() ) + "%]" ); + summary_writer.write( ForesterUtil.LINE_SEPARATOR ); + summary_writer.write( "# Pfams with mapping to molecular function: " + molecular_function_counter + " [" + + ( ( 100 * molecular_function_counter ) / all_pfams_encountered.size() ) + "%]" ); + summary_writer.write( ForesterUtil.LINE_SEPARATOR ); + summary_writer.write( "# 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.close(); } catch ( final IOException e ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() ); + ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "Failure to write: " + e ); } - ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote characters detailed HTML list: \"" + filename + "\"" ); } - public static void writeDomainCombinationsCountsFile( final String[][] input_file_properties, - final File output_dir, - final Writer per_genome_domain_promiscuity_statistics_writer, - final GenomeWideCombinableDomains gwcd, - final int i, - final GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order ) { - File dc_outfile = new File( input_file_properties[ i ][ 0 ] - + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX ); - if ( output_dir != null ) { - dc_outfile = new File( output_dir + ForesterUtil.FILE_SEPARATOR + dc_outfile ); - } - checkForOutputFileWriteability( dc_outfile ); - try { - final BufferedWriter out = new BufferedWriter( new FileWriter( dc_outfile ) ); - out.write( gwcd.toStringBuilder( dc_sort_order ).toString() ); - out.close(); - } - catch ( final IOException e ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() ); - } - final DescriptiveStatistics stats = gwcd.getPerGenomeDomainPromiscuityStatistics(); - try { - per_genome_domain_promiscuity_statistics_writer.write( input_file_properties[ i ][ 0 ] + "\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.median() ) + "\t" ); - per_genome_domain_promiscuity_statistics_writer.write( ( int ) stats.getMin() + "\t" ); - per_genome_domain_promiscuity_statistics_writer.write( ( int ) stats.getMax() + "\t" ); - per_genome_domain_promiscuity_statistics_writer.write( stats.getN() + "\t" ); - final SortedSet mpds = gwcd.getMostPromiscuosDomain(); - for( final DomainId mpd : mpds ) { - per_genome_domain_promiscuity_statistics_writer.write( mpd.getId() + " " ); - } - per_genome_domain_promiscuity_statistics_writer.write( ForesterUtil.LINE_SEPARATOR ); - } - catch ( final IOException e ) { - 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 + "\"" ); - } - else { - ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote domain combination counts for \"" - + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ") to: \"" - + dc_outfile + "\"" ); - } + private final static void writeColorLabels( final String l, final Color c, final Writer w ) throws IOException { + w.write( "" ); + w.write( l ); + w.write( "" ); + w.write( SurfacingConstants.NL ); } - private static void writeDomainData( final Map> domain_id_to_go_ids_map, + private static void writeDomainData( final Map> domain_id_to_go_ids_map, final Map go_id_to_term_map, final GoNameSpace go_namespace_limit, final Writer out, @@ -2044,7 +3105,7 @@ public final class SurfacingUtil { final String domain_1, final String prefix_for_html, final String character_separator_for_non_html_output, - final Map>[] domain_id_to_secondary_features_maps, + final Map>[] domain_id_to_secondary_features_maps, final Set all_go_ids ) throws IOException { boolean any_go_annotation_present = false; boolean first_has_no_go = false; @@ -2057,22 +3118,20 @@ public final class SurfacingUtil { List go_ids = null; boolean go_annotation_present = false; if ( d == 0 ) { - final DomainId domain_id = new DomainId( domain_0 ); - if ( domain_id_to_go_ids_map.containsKey( domain_id ) ) { + if ( domain_id_to_go_ids_map.containsKey( domain_0 ) ) { go_annotation_present = true; any_go_annotation_present = true; - go_ids = domain_id_to_go_ids_map.get( domain_id ); + go_ids = domain_id_to_go_ids_map.get( domain_0 ); } else { first_has_no_go = true; } } else { - final DomainId domain_id = new DomainId( domain_1 ); - if ( domain_id_to_go_ids_map.containsKey( domain_id ) ) { + if ( domain_id_to_go_ids_map.containsKey( domain_1 ) ) { go_annotation_present = true; any_go_annotation_present = true; - go_ids = domain_id_to_go_ids_map.get( domain_id ); + go_ids = domain_id_to_go_ids_map.get( domain_1 ); } } if ( go_annotation_present ) { @@ -2083,339 +3142,77 @@ public final class SurfacingUtil { first = false; writeDomainIdsToHtml( out, domain_0, - domain_1, - prefix_for_html, - domain_id_to_secondary_features_maps ); - } - else { - out.write( "" ); - } - if ( !go_id_to_term_map.containsKey( go_id ) ) { - throw new IllegalArgumentException( "GO-id [" + go_id + "] not found in GO-id to GO-term map" ); - } - final GoTerm go_term = go_id_to_term_map.get( go_id ); - if ( ( go_namespace_limit == null ) || go_namespace_limit.equals( go_term.getGoNameSpace() ) ) { - // final String top = GoUtils.getPenultimateGoTerm( go_term, go_id_to_term_map ).getName(); - final String go_id_str = go_id.getId(); - out.write( "" ); - out.write( "" + go_id_str + "" ); - out.write( "" ); - out.write( go_term.getName() ); - if ( domain_count == 2 ) { - out.write( " (" + d + ")" ); - } - out.write( "" ); - // out.write( top ); - // out.write( "" ); - out.write( "[" ); - out.write( go_term.getGoNameSpace().toShortString() ); - out.write( "]" ); - out.write( "" ); - if ( all_go_ids != null ) { - all_go_ids.add( go_id ); - } - } - else { - out.write( "" ); - out.write( "" ); - out.write( "" ); - out.write( "" ); - out.write( "" ); - } - out.write( "" ); - out.write( SurfacingConstants.NL ); - } - } - } // 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 ); - out.write( "" ); - out.write( "" ); - out.write( "" ); - out.write( "" ); - out.write( "" ); - out.write( "" ); - out.write( SurfacingConstants.NL ); - } - } - - private static void writeDomainIdsToHtml( final Writer out, - final String domain_0, - final String domain_1, - final String prefix_for_detailed_html, - final Map>[] domain_id_to_secondary_features_maps ) - throws IOException { - out.write( "" ); - if ( !ForesterUtil.isEmpty( prefix_for_detailed_html ) ) { - out.write( prefix_for_detailed_html ); - out.write( " " ); - } - out.write( "" + domain_0 + "" ); - out.write( "" ); - } - - public static DescriptiveStatistics writeDomainSimilaritiesToFile( final StringBuilder html_desc, - final StringBuilder html_title, - final Writer single_writer, - Map split_writers, - final SortedSet similarities, - final boolean treat_as_binary, - final List species_order, - final PrintableDomainSimilarity.PRINT_OPTION print_option, - final DomainSimilarity.DomainSimilaritySortField sort_field, - final DomainSimilarity.DomainSimilarityScoring scoring, - final boolean verbose ) throws IOException { - final DescriptiveStatistics stats = new BasicDescriptiveStatistics(); - String histogram_title = null; - switch ( sort_field ) { - case ABS_MAX_COUNTS_DIFFERENCE: - if ( treat_as_binary ) { - histogram_title = "absolute counts difference:"; - } - else { - histogram_title = "absolute (maximal) counts difference:"; - } - break; - case MAX_COUNTS_DIFFERENCE: - if ( treat_as_binary ) { - histogram_title = "counts difference:"; - } - else { - histogram_title = "(maximal) counts difference:"; - } - break; - case DOMAIN_ID: - histogram_title = "score mean:"; - break; - case MIN: - histogram_title = "score minimum:"; - break; - case MAX: - histogram_title = "score maximum:"; - break; - case MAX_DIFFERENCE: - if ( treat_as_binary ) { - histogram_title = "difference:"; - } - else { - histogram_title = "(maximal) difference:"; - } - break; - case MEAN: - histogram_title = "score mean:"; - break; - case SD: - histogram_title = "score standard deviation:"; - break; - case SPECIES_COUNT: - histogram_title = "species number:"; - break; - default: - throw new AssertionError( "Unknown sort field: " + sort_field ); - } - for( final DomainSimilarity similarity : similarities ) { - switch ( sort_field ) { - case ABS_MAX_COUNTS_DIFFERENCE: - stats.addValue( Math.abs( similarity.getMaximalDifferenceInCounts() ) ); - break; - case MAX_COUNTS_DIFFERENCE: - stats.addValue( similarity.getMaximalDifferenceInCounts() ); - break; - case DOMAIN_ID: - stats.addValue( similarity.getMeanSimilarityScore() ); - break; - case MIN: - stats.addValue( similarity.getMinimalSimilarityScore() ); - break; - case MAX: - stats.addValue( similarity.getMaximalSimilarityScore() ); - break; - case MAX_DIFFERENCE: - stats.addValue( similarity.getMaximalDifference() ); - break; - case MEAN: - stats.addValue( similarity.getMeanSimilarityScore() ); - break; - case SD: - stats.addValue( similarity.getStandardDeviationOfSimilarityScore() ); - break; - case SPECIES_COUNT: - stats.addValue( similarity.getSpecies().size() ); - break; - default: - throw new AssertionError( "Unknown sort field: " + sort_field ); - } - } - // - // final HistogramData[] hists = new HistogramData[ 1 ]; - // - // - // List data_items = new - // ArrayList(); - // double[] values = stats.getDataAsDoubleArray(); - // for( int i = 0; i < values.length; i++ ) { - // HistogramDataItem data_item = new BasicHistogramDataItem( "", values[ - // i ] ); - // data_items.add( data_item ); - // } - // - // - // HistogramData hd0 = new HistogramData( "name", - // data_items, - // null, 20, - // 40 ); - // - // - // - // - // hists[ 0 ] = hd0; - // - // final HistogramsFrame hf = new HistogramsFrame( hists ); - // hf.setVisible( true ); - // - AsciiHistogram histo = null; - if ( stats.getMin() < stats.getMin() ) { - histo = new AsciiHistogram( stats, histogram_title ); - } - if ( verbose ) { - if ( histo != null ) { - System.out.println( histo.toStringBuffer( 20, '|', 40, 5 ) ); - } - System.out.println(); - System.out.println( "N : " + stats.getN() ); - System.out.println( "Min : " + stats.getMin() ); - System.out.println( "Max : " + stats.getMax() ); - System.out.println( "Mean : " + stats.arithmeticMean() ); - if ( stats.getN() > 1 ) { - System.out.println( "SD : " + stats.sampleStandardDeviation() ); - } - else { - System.out.println( "SD : n/a" ); - } - System.out.println( "Median : " + stats.median() ); - if ( stats.getN() > 1 ) { - System.out.println( "Pearsonian skewness : " + stats.pearsonianSkewness() ); - } - else { - System.out.println( "Pearsonian skewness : n/a" ); - } - } - if ( ( single_writer != null ) && ( ( split_writers == null ) || split_writers.isEmpty() ) ) { - split_writers = new HashMap(); - split_writers.put( '_', single_writer ); - } - switch ( print_option ) { - case SIMPLE_TAB_DELIMITED: - break; - case HTML: - for( final Character key : split_writers.keySet() ) { - final Writer w = split_writers.get( key ); - w.write( "" ); - w.write( SurfacingConstants.NL ); - if ( key != '_' ) { - addHtmlHead( w, "DCs (" + html_title + ") " + key.toString().toUpperCase() ); - } - else { - addHtmlHead( w, "DCs (" + html_title + ")" ); - } - w.write( SurfacingConstants.NL ); - w.write( "" ); - w.write( SurfacingConstants.NL ); - w.write( html_desc.toString() ); - w.write( SurfacingConstants.NL ); - w.write( "
" ); - w.write( "
" ); - w.write( SurfacingConstants.NL ); - w.write( "
" );
-                    w.write( SurfacingConstants.NL );
-                    if ( histo != null ) {
-                        w.write( histo.toStringBuffer( 20, '|', 40, 5 ).toString() );
-                        w.write( SurfacingConstants.NL );
-                    }
-                    w.write( "
" ); - w.write( SurfacingConstants.NL ); - w.write( "" ); - w.write( SurfacingConstants.NL ); - w.write( "" ); - w.write( SurfacingConstants.NL ); - w.write( "" ); - w.write( SurfacingConstants.NL ); - w.write( "" ); - w.write( SurfacingConstants.NL ); - w.write( "" ); - w.write( SurfacingConstants.NL ); - if ( stats.getN() > 1 ) { - w.write( "" ); + domain_1, + prefix_for_html, + domain_id_to_secondary_features_maps ); } else { - w.write( "" ); + out.write( "" ); } - w.write( SurfacingConstants.NL ); - w.write( "" ); - w.write( SurfacingConstants.NL ); - if ( stats.getN() > 1 ) { - w.write( "" ); + if ( !go_id_to_term_map.containsKey( go_id ) ) { + throw new IllegalArgumentException( "GO-id [" + go_id + "] not found in GO-id to GO-term map" ); + } + final GoTerm go_term = go_id_to_term_map.get( go_id ); + if ( ( go_namespace_limit == null ) || go_namespace_limit.equals( go_term.getGoNameSpace() ) ) { + // final String top = GoUtils.getPenultimateGoTerm( go_term, go_id_to_term_map ).getName(); + final String go_id_str = go_id.getId(); + out.write( "" ); + if ( all_go_ids != null ) { + all_go_ids.add( go_id ); + } } else { - w.write( "" ); + out.write( "" ); } - w.write( SurfacingConstants.NL ); - w.write( "
N: " + stats.getN() + "
Min: " + stats.getMin() + "
Max: " + stats.getMax() + "
Mean: " + stats.arithmeticMean() + "
SD: " + stats.sampleStandardDeviation() + "
SD: n/a
Median: " + stats.median() + "
Pearsonian skewness: " + stats.pearsonianSkewness() + "
" ); + out.write( "" + go_id_str + "" ); + out.write( "" ); + out.write( go_term.getName() ); + if ( domain_count == 2 ) { + out.write( " (" + d + ")" ); + } + out.write( "" ); + // out.write( top ); + // out.write( "" ); + out.write( "[" ); + out.write( go_term.getGoNameSpace().toShortString() ); + out.write( "]" ); + out.write( "
Pearsonian skewness: n/a
" ); + out.write( "" ); + out.write( "" ); + out.write( "" ); + out.write( "
" ); - w.write( SurfacingConstants.NL ); - w.write( "
" ); - w.write( SurfacingConstants.NL ); - w.write( "
" ); - w.write( SurfacingConstants.NL ); - w.write( "
" ); - w.write( SurfacingConstants.NL ); - w.write( "" ); - w.write( SurfacingConstants.NL ); - } - break; - } - for( final Writer w : split_writers.values() ) { - w.write( SurfacingConstants.NL ); - } - for( final DomainSimilarity similarity : similarities ) { - if ( ( species_order != null ) && !species_order.isEmpty() ) { - ( ( PrintableDomainSimilarity ) similarity ).setSpeciesOrder( species_order ); - } - if ( single_writer != null ) { - single_writer.write( similarity.toStringBuffer( print_option ).toString() ); - } - else { - Writer local_writer = split_writers.get( ( similarity.getDomainId().getId().charAt( 0 ) + "" ) - .toLowerCase().charAt( 0 ) ); - if ( local_writer == null ) { - local_writer = split_writers.get( '0' ); + out.write( "" ); + out.write( SurfacingConstants.NL ); } - local_writer.write( similarity.toStringBuffer( print_option ).toString() ); } - for( final Writer w : split_writers.values() ) { - w.write( SurfacingConstants.NL ); - } - } - switch ( print_option ) { - case HTML: - for( final Writer w : split_writers.values() ) { - w.write( SurfacingConstants.NL ); - w.write( "
" ); - w.write( SurfacingConstants.NL ); - w.write( "" ); - w.write( SurfacingConstants.NL ); - w.write( "" ); - w.write( SurfacingConstants.NL ); - w.write( "" ); - w.write( SurfacingConstants.NL ); - } - break; + } // 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 ); + out.write( "" ); + out.write( "" ); + out.write( "" ); + out.write( "" ); + out.write( "" ); + out.write( "" ); + out.write( SurfacingConstants.NL ); } - for( final Writer w : split_writers.values() ) { - w.close(); + } + + private static void writeDomainIdsToHtml( final Writer out, + final String domain_0, + final String domain_1, + final String prefix_for_detailed_html, + final Map>[] domain_id_to_secondary_features_maps ) + throws IOException { + out.write( "" ); + if ( !ForesterUtil.isEmpty( prefix_for_detailed_html ) ) { + out.write( prefix_for_detailed_html ); + out.write( " " ); } - return stats; + out.write( "" + domain_0 + "" ); + out.write( "" ); } private static void writeDomainsToIndividualFilePerTreeNode( final Writer individual_files_writer, @@ -2429,40 +3226,6 @@ public final class SurfacingUtil { } } - public static void writeMatrixToFile( final CharacterStateMatrix matrix, - final String filename, - final Format format ) { - final File outfile = new File( filename ); - checkForOutputFileWriteability( outfile ); - try { - final BufferedWriter out = new BufferedWriter( new FileWriter( outfile ) ); - matrix.toWriter( out, format ); - out.flush(); - out.close(); - } - catch ( final IOException e ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() ); - } - ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote matrix: \"" + filename + "\"" ); - } - - public static void writeMatrixToFile( final File matrix_outfile, final List matrices ) { - checkForOutputFileWriteability( matrix_outfile ); - try { - final BufferedWriter out = new BufferedWriter( new FileWriter( matrix_outfile ) ); - for( final DistanceMatrix distance_matrix : matrices ) { - out.write( distance_matrix.toStringBuffer( DistanceMatrix.Format.PHYLIP ).toString() ); - out.write( ForesterUtil.LINE_SEPARATOR ); - out.flush(); - } - out.close(); - } - catch ( final IOException e ) { - ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() ); - } - ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote distance matrices to \"" + matrix_outfile + "\"" ); - } - private static void writePfamsToFile( final String outfile_name, final SortedSet pfams ) { try { final Writer writer = new BufferedWriter( new FileWriter( new File( outfile_name ) ) ); @@ -2479,37 +3242,6 @@ public final class SurfacingUtil { } } - public static void writePhylogenyToFile( final Phylogeny phylogeny, final String filename ) { - final PhylogenyWriter writer = new PhylogenyWriter(); - try { - writer.toPhyloXML( new File( filename ), phylogeny, 1 ); - } - catch ( final IOException e ) { - ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "failed to write phylogeny to \"" + filename + "\": " - + e ); - } - ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote phylogeny to \"" + filename + "\"" ); - } - - public static void writeTaxonomyLinks( final Writer writer, final String species ) throws IOException { - if ( ( species.length() > 1 ) && ( species.indexOf( '_' ) < 1 ) ) { - final Matcher matcher = PATTERN_SP_STYLE_TAXONOMY.matcher( species ); - writer.write( " [" ); - if ( matcher.matches() ) { - writer.write( "uniprot" ); - } - else { - writer.write( "eol" ); - writer.write( "|" ); - writer.write( "tol" ); - } - writer.write( "]" ); - } - } - private static void writeToNexus( final String outfile_name, final CharacterStateMatrix matrix, final Phylogeny phylogeny ) { @@ -2547,91 +3279,6 @@ public final class SurfacingUtil { phylogeny ); } - public static void domainsPerProteinsStatistics( final String genome, - final List protein_list, - final DescriptiveStatistics all_genomes_domains_per_potein_stats, - final SortedMap all_genomes_domains_per_potein_histo, - final SortedSet domains_which_are_always_single, - final SortedSet domains_which_are_sometimes_single_sometimes_not, - final SortedSet domains_which_never_single, - final Writer writer ) { - final DescriptiveStatistics stats = new BasicDescriptiveStatistics(); - for( final Protein protein : protein_list ) { - final int domains = protein.getNumberOfProteinDomains(); - //System.out.println( domains ); - stats.addValue( domains ); - all_genomes_domains_per_potein_stats.addValue( domains ); - if ( !all_genomes_domains_per_potein_histo.containsKey( domains ) ) { - all_genomes_domains_per_potein_histo.put( domains, 1 ); - } - else { - all_genomes_domains_per_potein_histo.put( domains, - 1 + all_genomes_domains_per_potein_histo.get( domains ) ); - } - if ( domains == 1 ) { - final String domain = protein.getProteinDomain( 0 ).getDomainId().getId(); - if ( !domains_which_are_sometimes_single_sometimes_not.contains( domain ) ) { - if ( domains_which_never_single.contains( domain ) ) { - domains_which_never_single.remove( domain ); - domains_which_are_sometimes_single_sometimes_not.add( domain ); - } - else { - domains_which_are_always_single.add( domain ); - } - } - } - else if ( domains > 1 ) { - for( final Domain d : protein.getProteinDomains() ) { - final String domain = d.getDomainId().getId(); - // System.out.println( domain ); - if ( !domains_which_are_sometimes_single_sometimes_not.contains( domain ) ) { - if ( domains_which_are_always_single.contains( domain ) ) { - domains_which_are_always_single.remove( domain ); - domains_which_are_sometimes_single_sometimes_not.add( domain ); - } - else { - domains_which_never_single.add( domain ); - } - } - } - } - } - try { - writer.write( genome ); - writer.write( "\t" ); - if ( stats.getN() >= 1 ) { - writer.write( stats.arithmeticMean() + "" ); - writer.write( "\t" ); - if ( stats.getN() >= 2 ) { - writer.write( stats.sampleStandardDeviation() + "" ); - } - else { - writer.write( "" ); - } - writer.write( "\t" ); - writer.write( stats.median() + "" ); - writer.write( "\t" ); - writer.write( stats.getN() + "" ); - writer.write( "\t" ); - writer.write( stats.getMin() + "" ); - writer.write( "\t" ); - writer.write( stats.getMax() + "" ); - } - else { - writer.write( "\t" ); - writer.write( "\t" ); - writer.write( "\t" ); - writer.write( "0" ); - writer.write( "\t" ); - writer.write( "\t" ); - } - writer.write( "\n" ); - } - catch ( final IOException e ) { - e.printStackTrace(); - } - } - final static class DomainComparator implements Comparator { final private boolean _ascending; @@ -2642,7 +3289,6 @@ public final class SurfacingUtil { @Override public final int compare( final Domain d0, final Domain d1 ) { - if ( d0.getFrom() < d1.getFrom() ) { return _ascending ? -1 : 1; } @@ -2650,13 +3296,6 @@ public final class SurfacingUtil { return _ascending ? 1 : -1; } return 0; - } - } } - - - - -