package org.forester.surfacing;
+import java.awt.Color;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileWriter;
import org.forester.protein.Domain;
import org.forester.protein.Protein;
import org.forester.species.Species;
+import org.forester.surfacing.DomainSimilarity.PRINT_OPTION;
import org.forester.surfacing.DomainSimilarityCalculator.Detailedness;
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.CommandLineArguments;
import org.forester.util.DescriptiveStatistics;
import org.forester.util.ForesterUtil;
+import org.forester.util.TaxonomyColors;
public final class SurfacingUtil {
- final static class DomainComparator implements Comparator<Domain> {
-
- final private boolean _ascending;
-
- public DomainComparator( final boolean ascending ) {
- _ascending = ascending;
- }
+ public final static Pattern PATTERN_SP_STYLE_TAXONOMY = Pattern.compile( "^[A-Z0-9]{3,5}$" );
+ private final static Map<String, String> _TAXCODE_HEXCOLORSTRING_MAP = new HashMap<String, String>();
+ private final static Map<String, String> _TAXCODE_TAXGROUP_MAP = new HashMap<String, String>();
+ private static final Comparator<Domain> ASCENDING_CONFIDENCE_VALUE_ORDER = new Comparator<Domain>() {
@Override
- public final int compare( final Domain d0, final Domain d1 ) {
- if ( d0.getFrom() < d1.getFrom() ) {
- return _ascending ? -1 : 1;
+ public int compare( final Domain d1,
+ final Domain d2 ) {
+ if ( d1.getPerDomainEvalue() < d2
+ .getPerDomainEvalue() ) {
+ return -1;
}
- else if ( d0.getFrom() > d1.getFrom() ) {
- return _ascending ? 1 : -1;
+ else if ( d1.getPerDomainEvalue() > d2
+ .getPerDomainEvalue() ) {
+ return 1;
+ }
+ else {
+ return d1.compareTo( d2 );
}
- return 0;
}
+ };
+ private final static NumberFormat FORMATTER_3 = new DecimalFormat( "0.000" );
+
+ private SurfacingUtil() {
+ // Hidden constructor.
}
- private final static NumberFormat FORMATTER_3 = new DecimalFormat( "0.000" );
- private static final Comparator<Domain> ASCENDING_CONFIDENCE_VALUE_ORDER = new Comparator<Domain>() {
-
- @Override
- public int compare( final Domain d1,
- final Domain d2 ) {
- if ( d1.getPerSequenceEvalue() < d2
- .getPerSequenceEvalue() ) {
- return -1;
- }
- else if ( d1
- .getPerSequenceEvalue() > d2
- .getPerSequenceEvalue() ) {
- return 1;
- }
- else {
- return d1.compareTo( d2 );
- }
- }
- };
- public final static Pattern PATTERN_SP_STYLE_TAXONOMY = Pattern.compile( "^[A-Z0-9]{3,5}$" );
public static void addAllBinaryDomainCombinationToSet( final GenomeWideCombinableDomains genome,
final SortedSet<BinaryDomainCombination> binary_domain_combinations ) {
}
}
- public static void addHtmlHead( final Writer w, final String title ) throws IOException {
- w.write( SurfacingConstants.NL );
- w.write( "<head>" );
- w.write( "<title>" );
- w.write( title );
- w.write( "</title>" );
- w.write( SurfacingConstants.NL );
- w.write( "<style>" );
- w.write( SurfacingConstants.NL );
- w.write( "a:visited { color : #6633FF; text-decoration : none; }" );
- w.write( SurfacingConstants.NL );
- w.write( "a:link { color : #6633FF; text-decoration : none; }" );
- w.write( SurfacingConstants.NL );
- w.write( "a:active { color : #99FF00; text-decoration : none; }" );
- w.write( SurfacingConstants.NL );
- w.write( "a:hover { color : #FFFFFF; background-color : #99FF00; text-decoration : none; }" );
- w.write( SurfacingConstants.NL );
- //
- w.write( "a.pl:visited { color : #505050; text-decoration : none; font-size: 7pt;}" );
- w.write( SurfacingConstants.NL );
- w.write( "a.pl:link { color : #505050; text-decoration : none; font-size: 7pt;}" );
- w.write( SurfacingConstants.NL );
- w.write( "a.pl:active { color : #505050; text-decoration : none; font-size: 7pt;}" );
- w.write( SurfacingConstants.NL );
- w.write( "a.pl:hover { color : #FFFFFF; background-color : #99FF00; text-decoration : none; font-size: 7pt;}" );
- w.write( SurfacingConstants.NL );
- //
- w.write( "a.ps:visited { color : #707070; text-decoration : none; font-size: 7pt;}" );
- w.write( SurfacingConstants.NL );
- w.write( "a.ps:link { color : #707070; text-decoration : none; font-size: 7pt;}" );
- w.write( SurfacingConstants.NL );
- w.write( "a.ps:active { color : #707070; text-decoration : none; font-size: 7pt;}" );
- w.write( SurfacingConstants.NL );
- w.write( "a.ps:hover { color : #FFFFFF; background-color : #99FF00; text-decoration : none; font-size: 7pt;}" );
- w.write( SurfacingConstants.NL );
- //
- w.write( "td { text-align: left; vertical-align: top; font-family: Verdana, Arial, Helvetica; font-size: 8pt}" );
- w.write( SurfacingConstants.NL );
- w.write( "h1 { color : #0000FF; font-family: Verdana, Arial, Helvetica; font-size: 18pt; font-weight: bold }" );
- w.write( SurfacingConstants.NL );
- w.write( "h2 { color : #0000FF; font-family: Verdana, Arial, Helvetica; font-size: 16pt; font-weight: bold }" );
- w.write( SurfacingConstants.NL );
- w.write( "</style>" );
- w.write( SurfacingConstants.NL );
- w.write( "</head>" );
- w.write( SurfacingConstants.NL );
- }
-
- private final static void addToCountMap( final Map<String, Integer> map, final String s ) {
- if ( map.containsKey( s ) ) {
- map.put( s, map.get( s ) + 1 );
- }
- else {
- map.put( s, 1 );
- }
- }
-
public static DescriptiveStatistics calculateDescriptiveStatisticsForMeanValues( final Set<DomainSimilarity> similarities ) {
final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
for( final DomainSimilarity similarity : similarities ) {
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<String, DescriptiveStatistics> protein_length_stats_by_dc,
- final Map<String, DescriptiveStatistics> domain_number_stats_by_dc,
- final Map<String, DescriptiveStatistics> domain_length_stats_by_domain ) {
- try {
- //
- // if ( protein_length_stats_by_dc != null ) {
- // for( final Entry<?, DescriptiveStatistics> 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<?, DescriptiveStatistics> 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<String, Integer> dc_gain_counts = new TreeMap<String, Integer>();
- for( final PhylogenyNodeIterator it = local_phylogeny_l.iteratorPostorder(); it.hasNext(); ) {
- final PhylogenyNode n = it.next();
- final Set<String> 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<Integer, Integer> histogram = new TreeMap<Integer, Integer>();
- final SortedMap<Integer, StringBuilder> domain_lists = new TreeMap<Integer, StringBuilder>();
- final SortedMap<Integer, DescriptiveStatistics> dc_reapp_counts_to_protein_length_stats = new TreeMap<Integer, DescriptiveStatistics>();
- final SortedMap<Integer, DescriptiveStatistics> dc_reapp_counts_to_domain_number_stats = new TreeMap<Integer, DescriptiveStatistics>();
- final SortedMap<Integer, DescriptiveStatistics> dc_reapp_counts_to_domain_lengths_stats = new TreeMap<Integer, DescriptiveStatistics>();
- final SortedMap<Integer, PriorityQueue<String>> domain_lists_go = new TreeMap<Integer, PriorityQueue<String>>();
- final SortedMap<Integer, SortedSet<String>> domain_lists_go_unique = new TreeMap<Integer, SortedSet<String>>();
- final Set<String> dcs = dc_gain_counts.keySet();
- final SortedSet<String> more_than_once = new TreeSet<String>();
- 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<String> q = new PriorityQueue<String>();
- q.addAll( splitDomainCombination( dc ) );
- domain_lists_go.put( count, q );
- final SortedSet<String> set = new TreeSet<String>();
- 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() );
+ 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 DomainSimilarity.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;
}
- 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() );
+ 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 );
}
- 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 );
- }
+ }
+ }
+ }
+
+ public static void collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile( final CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
+ final BinaryDomainCombination.DomainCombinationType dc_type,
+ final List<BinaryDomainCombination> all_binary_domains_combination_gained,
+ final boolean get_gains ) {
+ final SortedSet<String> sorted_ids = new TreeSet<String>();
+ 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
+ .obtainInstance( matrix.getCharacter( c ) ) );
}
- 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 );
- }
+ else if ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED ) {
+ all_binary_domains_combination_gained.add( DirectedBinaryDomainCombination
+ .obtainInstance( matrix.getCharacter( c ) ) );
}
- 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 {
+ all_binary_domains_combination_gained.add( BasicBinaryDomainCombination.obtainInstance( matrix
+ .getCharacter( c ) ) );
}
}
- 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<Integer> 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<String, Integer> lca_rank_counts = new TreeMap<String, Integer>();
- final SortedMap<String, Integer> lca_ancestor_species_counts = new TreeMap<String, Integer>();
- for( final String dc : more_than_once ) {
- final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
- 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<Integer, DescriptiveStatistics> 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<Integer, DescriptiveStatistics> 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<Integer, DescriptiveStatistics> 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 + "]" );
}
- 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 Map<String, List<GoId>> createDomainIdToGoIdMap( final List<PfamToGoMapping> pfam_to_go_mappings ) {
+ final Map<String, List<GoId>> domain_id_to_go_ids_map = new HashMap<String, List<GoId>>( 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<GoId>() );
+ }
+ 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 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 Map<String, Set<String>> createDomainIdToSecondaryFeaturesMap( final File secondary_features_map_file )
+ throws IOException {
+ final BasicTable<String> primary_table = BasicTableParser.parse( secondary_features_map_file, '\t' );
+ final Map<String, Set<String>> map = new TreeMap<String, Set<String>>();
+ 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<String>() );
}
+ map.get( domain_id ).add( primary_table.getValue( 1, r ) );
}
+ return map;
}
- private static SortedSet<String> collectAllDomainsChangedOnSubtree( final PhylogenyNode subtree_root,
- final boolean get_gains ) {
- final SortedSet<String> domains = new TreeSet<String>();
- 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 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 void collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile( final CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
- final BinaryDomainCombination.DomainCombinationType dc_type,
- final List<BinaryDomainCombination> all_binary_domains_combination_gained,
- final boolean get_gains ) {
- final SortedSet<String> sorted_ids = new TreeSet<String>();
- 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<String, List<GoId>> createDomainIdToGoIdMap( final List<PfamToGoMapping> pfam_to_go_mappings ) {
- final Map<String, List<GoId>> domain_id_to_go_ids_map = new HashMap<String, List<GoId>>( 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<GoId>() );
- }
- 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<String, Set<String>> createDomainIdToSecondaryFeaturesMap( final File secondary_features_map_file )
- throws IOException {
- final BasicTable<String> primary_table = BasicTableParser.parse( secondary_features_map_file, '\t' );
- final Map<String, Set<String>> map = new TreeMap<String, Set<String>>();
- 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<String>() );
- }
- 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 );
+ public static StringBuilder createParametersAsString( final boolean ignore_dufs,
+ final double ie_value_max,
+ final double fs_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( "iE-value: " + ie_value_max );
+ parameters_sb.append( ", FS E-value: " + fs_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" );
return parameters_sb;
}
- private static SortedSet<BinaryDomainCombination> createSetOfAllBinaryDomainCombinationsPerGenome( final GenomeWideCombinableDomains gwcd ) {
- final SortedMap<String, CombinableDomains> cds = gwcd.getAllCombinableDomainsIds();
- final SortedSet<BinaryDomainCombination> binary_combinations = new TreeSet<BinaryDomainCombination>();
- for( final String domain_id : cds.keySet() ) {
- final CombinableDomains cd = cds.get( domain_id );
- binary_combinations.addAll( cd.toBinaryDomainCombinations() );
- }
- return binary_combinations;
- }
-
public static void createSplitWriters( final File out_dir,
final String my_outfile,
final Map<Character, Writer> split_writers ) throws IOException {
split_writers.put( 'a', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_A.html" ) ) );
+ + "_domains_A.html" ) ) );
split_writers.put( 'b', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_B.html" ) ) );
+ + "_domains_B.html" ) ) );
split_writers.put( 'c', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_C.html" ) ) );
+ + "_domains_C.html" ) ) );
split_writers.put( 'd', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_D.html" ) ) );
+ + "_domains_D.html" ) ) );
split_writers.put( 'e', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_E.html" ) ) );
+ + "_domains_E.html" ) ) );
split_writers.put( 'f', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_F.html" ) ) );
+ + "_domains_F.html" ) ) );
split_writers.put( 'g', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_G.html" ) ) );
+ + "_domains_G.html" ) ) );
split_writers.put( 'h', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_H.html" ) ) );
+ + "_domains_H.html" ) ) );
split_writers.put( 'i', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_I.html" ) ) );
+ + "_domains_I.html" ) ) );
split_writers.put( 'j', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_J.html" ) ) );
+ + "_domains_J.html" ) ) );
split_writers.put( 'k', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_K.html" ) ) );
+ + "_domains_K.html" ) ) );
split_writers.put( 'l', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_L.html" ) ) );
+ + "_domains_L.html" ) ) );
split_writers.put( 'm', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_M.html" ) ) );
+ + "_domains_M.html" ) ) );
split_writers.put( 'n', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_N.html" ) ) );
+ + "_domains_N.html" ) ) );
split_writers.put( 'o', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_O.html" ) ) );
+ + "_domains_O.html" ) ) );
split_writers.put( 'p', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_P.html" ) ) );
+ + "_domains_P.html" ) ) );
split_writers.put( 'q', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_Q.html" ) ) );
+ + "_domains_Q.html" ) ) );
split_writers.put( 'r', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_R.html" ) ) );
+ + "_domains_R.html" ) ) );
split_writers.put( 's', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_S.html" ) ) );
+ + "_domains_S.html" ) ) );
split_writers.put( 't', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_T.html" ) ) );
+ + "_domains_T.html" ) ) );
split_writers.put( 'u', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_U.html" ) ) );
+ + "_domains_U.html" ) ) );
split_writers.put( 'v', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_V.html" ) ) );
+ + "_domains_V.html" ) ) );
split_writers.put( 'w', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_W.html" ) ) );
+ + "_domains_W.html" ) ) );
split_writers.put( 'x', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_X.html" ) ) );
+ + "_domains_X.html" ) ) );
split_writers.put( 'y', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_Y.html" ) ) );
+ + "_domains_Y.html" ) ) );
split_writers.put( 'z', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_Z.html" ) ) );
+ + "_domains_Z.html" ) ) );
split_writers.put( '0', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
- + "_domains_0.html" ) ) );
+ + "_domains_0.html" ) ) );
}
public static Map<String, Integer> createTaxCodeToIdMap( final Phylogeny phy ) {
public static void decoratePrintableDomainSimilarities( final SortedSet<DomainSimilarity> 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;
+ if ( domain_similarity instanceof DomainSimilarity ) {
+ final DomainSimilarity printable_domain_similarity = domain_similarity;
printable_domain_similarity.setDetailedness( detailedness );
}
}
/**
* Warning: This side-effects 'all_bin_domain_combinations_encountered'!
- *
- *
+ *
+ *
* @param output_file
* @param all_bin_domain_combinations_changed
* @param sum_of_all_domains_encountered
* @param all_bin_domain_combinations_encountered
* @param is_gains_analysis
- * @param protein_length_stats_by_dc
+ * @param protein_length_stats_by_dc
* @throws IOException
*/
public static void executeFitchGainsAnalysis( final File output_file,
}
if ( is_gains_analysis ) {
out.write( "Sum of all distinct domain combinations appearing once : " + one
- + ForesterUtil.LINE_SEPARATOR );
+ + ForesterUtil.LINE_SEPARATOR );
out.write( "Sum of all distinct domain combinations appearing more than once : " + above_one
- + ForesterUtil.LINE_SEPARATOR );
+ + 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: "
}
else {
out.write( "Sum of all distinct domain combinations never lost : " + never_lost
- + ForesterUtil.LINE_SEPARATOR );
+ + ForesterUtil.LINE_SEPARATOR );
out.write( "Sum of all distinct domain combinations lost once : " + one
- + ForesterUtil.LINE_SEPARATOR );
+ + ForesterUtil.LINE_SEPARATOR );
out.write( "Sum of all distinct domain combinations lost more than once : " + above_one
- + ForesterUtil.LINE_SEPARATOR );
+ + 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 );
+ + 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_lost_fitch
+ * @param use_last_in_fitch_parsimony
+ * @param perform_dc_fich
+ * @param consider_directedness_and_adjacency_for_bin_combinations
* @param all_binary_domains_combination_gained if null ignored, otherwise this is to list all binary domain combinations
* which were gained under unweighted (Fitch) parsimony.
*/
final Map<String, DescriptiveStatistics> domain_length_stats_by_domain,
final Map<String, Integer> tax_code_to_id_map,
final boolean write_to_nexus,
- final boolean use_last_in_fitch_parsimony ) {
+ final boolean use_last_in_fitch_parsimony,
+ final boolean perform_dc_fich ) {
final String sep = ForesterUtil.LINE_SEPARATOR + "###################" + ForesterUtil.LINE_SEPARATOR;
final String date_time = ForesterUtil.getCurrentDateTime();
final SortedSet<String> all_pfams_encountered = new TreeSet<String>();
domain_parsimony.executeDolloParsimonyOnDomainPresence();
}
SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossMatrix(), outfile_name
- + surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS, Format.FORESTER );
+ + surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS, Format.FORESTER );
SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossCountsMatrix(), outfile_name
- + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS, Format.FORESTER );
+ + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS, Format.FORESTER );
SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
CharacterStateMatrix.GainLossStates.GAIN,
outfile_name + surfacing.PARSIMONY_OUTPUT_DOLLO_GAINS_D,
ForesterUtil.LINE_SEPARATOR,
null );
SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(), null, outfile_name
- + surfacing.PARSIMONY_OUTPUT_DOLLO_PRESENT_D, sep, ForesterUtil.LINE_SEPARATOR, null );
+ + surfacing.PARSIMONY_OUTPUT_DOLLO_PRESENT_D, sep, ForesterUtil.LINE_SEPARATOR, null );
//HTML:
writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
go_id_to_term_map,
"dollo_on_domains_" + outfile_name,
parameters_str );
SurfacingUtil.writePhylogenyToFile( local_phylogeny_l, outfile_name
- + surfacing.DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO );
+ + surfacing.DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO );
try {
writeAllDomainsChangedOnAllSubtrees( local_phylogeny_l, true, outfile_name, "_dollo_all_gains_d" );
writeAllDomainsChangedOnAllSubtrees( local_phylogeny_l, false, outfile_name, "_dollo_all_losses_d" );
e.printStackTrace();
ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
}
- if ( domain_parsimony.calculateNumberOfBinaryDomainCombination() > 0 ) {
+ if ( perform_dc_fich && ( domain_parsimony.calculateNumberOfBinaryDomainCombination() > 0 ) ) {
// FITCH DOMAIN COMBINATIONS
// -------------------------
local_phylogeny_l = phylogeny.copy();
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 );
+ + surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS, Format.FORESTER );
SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossCountsMatrix(), outfile_name
- + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS, Format.FORESTER );
+ + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS, Format.FORESTER );
SurfacingUtil
- .writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
- CharacterStateMatrix.GainLossStates.GAIN,
- outfile_name + surfacing.PARSIMONY_OUTPUT_FITCH_GAINS_BC,
- sep,
- ForesterUtil.LINE_SEPARATOR,
- null );
+ .writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
+ CharacterStateMatrix.GainLossStates.GAIN,
+ outfile_name + surfacing.PARSIMONY_OUTPUT_FITCH_GAINS_BC,
+ sep,
+ ForesterUtil.LINE_SEPARATOR,
+ null );
SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
CharacterStateMatrix.GainLossStates.LOSS,
outfile_name
- + surfacing.PARSIMONY_OUTPUT_FITCH_LOSSES_BC,
+ + surfacing.PARSIMONY_OUTPUT_FITCH_LOSSES_BC,
sep,
ForesterUtil.LINE_SEPARATOR,
null );
SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(), null, outfile_name
- + surfacing.PARSIMONY_OUTPUT_FITCH_PRESENT_BC, sep, ForesterUtil.LINE_SEPARATOR, null );
+ + surfacing.PARSIMONY_OUTPUT_FITCH_PRESENT_BC, sep, ForesterUtil.LINE_SEPARATOR, null );
if ( all_binary_domains_combination_gained_fitch != null ) {
collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
dc_type,
}
if ( output_binary_domain_combinations_for_graphs ) {
SurfacingUtil
- .writeBinaryStatesMatrixAsListToFileForBinaryCombinationsForGraphAnalysis( domain_parsimony
- .getGainLossMatrix(),
- null,
- outfile_name
- + surfacing.PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS,
- sep,
- ForesterUtil.LINE_SEPARATOR,
- BinaryDomainCombination.OutputFormat.DOT );
+ .writeBinaryStatesMatrixAsListToFileForBinaryCombinationsForGraphAnalysis( domain_parsimony
+ .getGainLossMatrix(),
+ null,
+ outfile_name
+ + surfacing.PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS,
+ sep,
+ ForesterUtil.LINE_SEPARATOR,
+ BinaryDomainCombination.OutputFormat.DOT );
}
// HTML:
writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
date_time,
"Fitch parsimony on binary domain combination presence/absence randomization: "
+ randomization,
- "fitch_on_binary_domain_combinations_" + outfile_name,
- parameters_str );
+ "fitch_on_binary_domain_combinations_" + outfile_name,
+ parameters_str );
SurfacingUtil.writePhylogenyToFile( local_phylogeny_l, outfile_name
- + surfacing.BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH );
+ + surfacing.BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH );
calculateIndependentDomainCombinationGains( local_phylogeny_l,
outfile_name
- + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX,
+ + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX,
outfile_name
- + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX,
+ + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX,
outfile_name
- + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX,
+ + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX,
outfile_name
- + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_UNIQUE_SUFFIX,
+ + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_UNIQUE_SUFFIX,
outfile_name + "_indep_dc_gains_fitch_lca_ranks.txt",
outfile_name + "_indep_dc_gains_fitch_lca_taxonomies.txt",
outfile_name + "_indep_dc_gains_fitch_protein_statistics.txt",
Phylogeny local_phylogeny_copy = phylogeny.copy();
secondary_features_parsimony.executeDolloParsimonyOnSecondaryFeatures( mapping_results_map );
SurfacingUtil.writeMatrixToFile( secondary_features_parsimony.getGainLossMatrix(), outfile_name
- + surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES, Format.FORESTER );
+ + surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES, Format.FORESTER );
SurfacingUtil.writeMatrixToFile( secondary_features_parsimony.getGainLossCountsMatrix(), outfile_name
- + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES, Format.FORESTER );
+ + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES, Format.FORESTER );
SurfacingUtil
- .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(),
- CharacterStateMatrix.GainLossStates.GAIN,
- outfile_name
- + surfacing.PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES,
- sep,
- ForesterUtil.LINE_SEPARATOR,
- null );
+ .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(),
+ CharacterStateMatrix.GainLossStates.GAIN,
+ outfile_name
+ + surfacing.PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES,
+ sep,
+ ForesterUtil.LINE_SEPARATOR,
+ null );
SurfacingUtil
- .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(),
- CharacterStateMatrix.GainLossStates.LOSS,
- outfile_name
- + surfacing.PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES,
- sep,
- ForesterUtil.LINE_SEPARATOR,
- null );
+ .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(),
+ CharacterStateMatrix.GainLossStates.LOSS,
+ outfile_name
+ + surfacing.PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES,
+ sep,
+ ForesterUtil.LINE_SEPARATOR,
+ null );
SurfacingUtil
- .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(),
- null,
- outfile_name
- + surfacing.PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES,
- sep,
- ForesterUtil.LINE_SEPARATOR,
- null );
+ .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(),
+ null,
+ outfile_name
+ + surfacing.PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES,
+ sep,
+ ForesterUtil.LINE_SEPARATOR,
+ null );
preparePhylogeny( local_phylogeny_copy,
secondary_features_parsimony,
date_time,
"dollo_on_secondary_features_" + outfile_name,
parameters_str );
SurfacingUtil.writePhylogenyToFile( local_phylogeny_copy, outfile_name
- + surfacing.SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO );
+ + surfacing.SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO );
// FITCH DOMAIN COMBINATIONS
// -------------------------
local_phylogeny_copy = phylogeny.copy();
final String randomization = "no";
secondary_features_parsimony
- .executeFitchParsimonyOnBinaryDomainCombintionOnSecondaryFeatures( use_last_in_fitch_parsimony );
+ .executeFitchParsimonyOnBinaryDomainCombintionOnSecondaryFeatures( use_last_in_fitch_parsimony );
preparePhylogeny( local_phylogeny_copy,
secondary_features_parsimony,
date_time,
"Fitch parsimony on secondary binary domain combination presence/absence randomization: "
+ randomization,
- "fitch_on_binary_domain_combinations_" + outfile_name,
- parameters_str );
+ "fitch_on_binary_domain_combinations_" + outfile_name,
+ parameters_str );
SurfacingUtil.writePhylogenyToFile( local_phylogeny_copy, outfile_name
- + surfacing.BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH_MAPPED );
+ + surfacing.BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH_MAPPED );
calculateIndependentDomainCombinationGains( local_phylogeny_copy, outfile_name
- + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_MAPPED_OUTPUT_SUFFIX, outfile_name
- + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_MAPPED_OUTPUT_SUFFIX, outfile_name
- + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_SUFFIX, outfile_name
- + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_UNIQUE_SUFFIX, outfile_name
- + "_MAPPED_indep_dc_gains_fitch_lca_ranks.txt", outfile_name
- + "_MAPPED_indep_dc_gains_fitch_lca_taxonomies.txt", null, null, null, null );
+ + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_MAPPED_OUTPUT_SUFFIX, outfile_name
+ + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_MAPPED_OUTPUT_SUFFIX, outfile_name
+ + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_SUFFIX, outfile_name
+ + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_UNIQUE_SUFFIX, outfile_name
+ + "_MAPPED_indep_dc_gains_fitch_lca_ranks.txt", outfile_name
+ + "_MAPPED_indep_dc_gains_fitch_lca_taxonomies.txt", null, null, null, null );
}
public static void executePlusMinusAnalysis( final File output_file,
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 );
+ + 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();
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 \""
final PhylogenyNode n = it.next();
if ( ForesterUtil.isEmpty( n.getName() )
&& ( !n.getNodeData().isHasTaxonomy() || ForesterUtil.isEmpty( n.getNodeData().getTaxonomy()
- .getScientificName() ) )
- && ( !n.getNodeData().isHasTaxonomy() || ForesterUtil.isEmpty( n.getNodeData().getTaxonomy()
- .getCommonName() ) ) ) {
+ .getScientificName() ) )
+ && ( !n.getNodeData().isHasTaxonomy() || ForesterUtil.isEmpty( n.getNodeData().getTaxonomy()
+ .getCommonName() ) ) ) {
if ( n.getParent() != null ) {
names.append( " " );
names.append( n.getParent().getName() );
.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" );
+ + "] 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" );
+ + "] 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 );
+ + "]: " + error );
}
if ( ( intree == null ) || intree.isEmpty() ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" );
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 + "]" );
+ + "] 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 );
preparePhylogenyForParsimonyAnalyses( intree, input_file_properties );
if ( !intree.isCompletelyBinary() ) {
ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "input tree [" + intree_file
- + "] is not completely binary" );
+ + "] is not completely binary" );
}
intrees[ i++ ] = intree;
}
.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" );
+ + "] 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" );
+ + "] contains more than one phylogeny in phyloXML format" );
}
intree = phys[ 0 ];
}
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<PhylogenyNode> 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();
+ // }
+ final String group = obtainTaxonomyGroup( tax_code, phy );
+ final Color c = ForesterUtil.obtainColorDependingOnTaxonomyGroup( group );
+ if ( c == null ) {
+ throw new IllegalArgumentException( "no color found for taxonomy group \"" + group
+ + "\" for 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 String obtainTaxonomyGroup( final String tax_code, final Phylogeny species_tree )
+ throws IllegalArgumentException {
+ if ( !_TAXCODE_TAXGROUP_MAP.containsKey( tax_code ) ) {
+ if ( ( species_tree != null ) && !species_tree.isEmpty() ) {
+ final List<PhylogenyNode> nodes = species_tree.getNodesViaTaxonomyCode( tax_code );
+ 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 );
+ String group = null;
+ while ( n != null ) {
+ if ( n.getNodeData().isHasTaxonomy()
+ && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
+ group = ForesterUtil.obtainNormalizedTaxonomyGroup( n.getNodeData().getTaxonomy()
+ .getScientificName() );
+ }
+ if ( ForesterUtil.isEmpty( group ) && !ForesterUtil.isEmpty( n.getName() ) ) {
+ group = ForesterUtil.obtainNormalizedTaxonomyGroup( n.getName() );
+ }
+ if ( !ForesterUtil.isEmpty( group ) ) {
+ break;
+ }
+ n = n.getParent();
+ }
+ if ( ForesterUtil.isEmpty( group ) ) {
+ throw new IllegalArgumentException( "no group found for taxonomy code \"" + tax_code + "\"" );
+ }
+ _TAXCODE_TAXGROUP_MAP.put( tax_code, group );
+ }
+ else {
+ throw new IllegalArgumentException( "unable to obtain group for code " + tax_code
+ + " (tree is null or empty and code is not in map)" );
+ }
+ }
+ return _TAXCODE_TAXGROUP_MAP.get( tax_code );
+ }
+
public static void performDomainArchitectureAnalysis( final SortedMap<String, Set<String>> domain_architecutures,
final SortedMap<String, Integer> domain_architecuture_counts,
final int min_count,
}
else {
ForesterUtil
- .fatalError( surfacing.PRG_NAME,
- "node with no name, scientific name, common name, or taxonomy code present" );
+ .fatalError( surfacing.PRG_NAME,
+ "node with no name, scientific name, common name, or taxonomy code present" );
}
}
}
log( "Percentage of multidomain proteins: : " + percentage + "%", log_writer );
}
- private static void printSomeStats( final DescriptiveStatistics stats, final AsciiHistogram histo, final Writer w )
- throws IOException {
- w.write( "<hr>" );
- w.write( "<br>" );
- w.write( SurfacingConstants.NL );
- w.write( "<tt><pre>" );
- w.write( SurfacingConstants.NL );
- if ( histo != null ) {
- w.write( histo.toStringBuffer( 20, '|', 40, 5 ).toString() );
- w.write( SurfacingConstants.NL );
- }
- w.write( "</pre></tt>" );
- w.write( SurfacingConstants.NL );
- w.write( "<table>" );
- w.write( SurfacingConstants.NL );
- w.write( "<tr><td>N: </td><td>" + stats.getN() + "</td></tr>" );
- w.write( SurfacingConstants.NL );
- w.write( "<tr><td>Min: </td><td>" + stats.getMin() + "</td></tr>" );
- w.write( SurfacingConstants.NL );
- w.write( "<tr><td>Max: </td><td>" + stats.getMax() + "</td></tr>" );
- w.write( SurfacingConstants.NL );
- w.write( "<tr><td>Mean: </td><td>" + stats.arithmeticMean() + "</td></tr>" );
- w.write( SurfacingConstants.NL );
- if ( stats.getN() > 1 ) {
- w.write( "<tr><td>SD: </td><td>" + stats.sampleStandardDeviation() + "</td></tr>" );
- }
- else {
- w.write( "<tr><td>SD: </td><td>n/a</td></tr>" );
- }
- w.write( SurfacingConstants.NL );
- w.write( "</table>" );
- w.write( SurfacingConstants.NL );
- w.write( "<br>" );
- w.write( SurfacingConstants.NL );
- }
-
public static void processFilter( final File filter_file, final SortedSet<String> filter ) {
SortedSet<String> filter_str = null;
try {
}
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), '$D=<integer>' minimal Difference (default is 1), '$F=<double>' factor (default is 1.0), double), or '#' (ignore) suffix, encountered: \""
- + species + "\"" );
+ .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), '$D=<integer>' minimal Difference (default is 1), '$F=<double>' factor (default is 1.0), double), or '#' (ignore) suffix, encountered: \""
+ + species + "\"" );
}
numbers.add( new Integer( min_diff + "" ) );
numbers.add( new Double( factor + "" ) );
/*
* species | protein id | n-terminal domain | c-terminal domain | n-terminal domain per domain E-value | c-terminal domain per domain E-value
- *
- *
+ *
+ *
*/
static public StringBuffer proteinToDomainCombinations( final Protein protein,
final String protein_id,
return domains;
}
- private static List<String> 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<String> l = new ArrayList<String>( 2 );
- l.add( s[ 0 ] );
- l.add( s[ 1 ] );
- return l;
- }
-
public static int storeDomainArchitectures( final String genome,
final SortedMap<String, Set<String>> domain_architecutures,
final List<Protein> protein_list,
final SortedSet<String> domains = collectAllDomainsChangedOnSubtree( node, get_gains );
if ( domains.size() > 0 ) {
final Writer writer = ForesterUtil.createBufferedWriter( base_dir + ForesterUtil.FILE_SEPARATOR
- + node.getName() + suffix_for_filename );
+ + node.getName() + suffix_for_filename );
for( final String domain : domains ) {
writer.write( domain );
writer.write( ForesterUtil.LINE_SEPARATOR );
}
}
- private static void writeAllEncounteredPfamsToFile( final Map<String, List<GoId>> domain_id_to_go_ids_map,
- final Map<GoId, GoTerm> go_id_to_term_map,
- final String outfile_name,
- final SortedSet<String> 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<BinaryDomainCombination> 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 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<GoId> 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 );
- }
- }
- 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 ][ 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<BinaryDomainCombination> 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 );
+ 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 + "\"" );
+ if ( input_file_properties[ i ].length == 3 ) {
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote binary domain combination for \""
+ + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ", "
+ + input_file_properties[ i ][ 2 ] + ") to: \"" + dc_outfile_dot + "\"" );
+ }
+ else {
+ ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote binary domain combination for \""
+ + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ") to: \""
+ + dc_outfile_dot + "\"" );
+ }
}
public static void writeBinaryStatesMatrixAsListToFile( final CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
.getState( id, c ) == CharacterStateMatrix.GainLossStates.UNCHANGED_PRESENT ) ) ) ) {
BinaryDomainCombination bdc = null;
try {
- bdc = BasicBinaryDomainCombination.createInstance( matrix.getCharacter( c ) );
+ bdc = BasicBinaryDomainCombination.obtainInstance( matrix.getCharacter( c ) );
}
catch ( final Exception e ) {
ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
int per_node_counter = 0;
out.write( "<html>" );
out.write( SurfacingConstants.NL );
- addHtmlHead( out, title_for_html );
+ writeHtmlHead( out, title_for_html );
out.write( SurfacingConstants.NL );
out.write( "<body>" );
out.write( SurfacingConstants.NL );
per_node_counter = 0;
if ( matrix.getNumberOfCharacters() > 0 ) {
per_node_go_mapped_domain_gain_loss_outfile = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
- + ForesterUtil.FILE_SEPARATOR + id + suffix_for_per_node_events_file );
+ + ForesterUtil.FILE_SEPARATOR + id + suffix_for_per_node_events_file );
SurfacingUtil.checkForOutputFileWriteability( per_node_go_mapped_domain_gain_loss_outfile );
per_node_go_mapped_domain_gain_loss_outfile_writer = ForesterUtil
.createBufferedWriter( per_node_go_mapped_domain_gain_loss_outfile );
out.write( SurfacingConstants.NL );
out.write( "<hr>" );
out.write( SurfacingConstants.NL );
- } // for( final String id : sorted_ids ) {
+ } // for( final String id : sorted_ids ) {
out.write( "</body>" );
out.write( SurfacingConstants.NL );
out.write( "</html>" );
}
else {
per_genome_domain_promiscuity_statistics_writer.write( FORMATTER_3.format( stats
- .sampleStandardDeviation() ) + "\t" );
+ .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( 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 + "\"" );
+ 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<Character, Writer> split_writers,
+ final SortedSet<DomainSimilarity> similarities,
+ final boolean treat_as_binary,
+ final List<Species> species_order,
+ final DomainSimilarity.PRINT_OPTION print_option,
+ final DomainSimilarity.DomainSimilarityScoring scoring,
+ final boolean verbose,
+ final Map<String, Integer> tax_code_to_id_map,
+ final Phylogeny phy,
+ final Set<String> pos_filter_doms ) throws IOException {
+ if ( ( single_writer != null ) && ( ( split_writers == null ) || split_writers.isEmpty() ) ) {
+ split_writers = new HashMap<Character, Writer>();
+ 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( "<html>" );
+ 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( "<body>" );
+ w.write( SurfacingConstants.NL );
+ w.write( html_desc.toString() );
+ w.write( SurfacingConstants.NL );
+ w.write( "<hr>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<br>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<table>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<tr><td><b>Domains:</b></td></tr>" );
+ w.write( SurfacingConstants.NL );
+ }
+ break;
+ }
+ //
+ for( final DomainSimilarity similarity : similarities ) {
+ if ( ( species_order != null ) && !species_order.isEmpty() ) {
+ ( similarity ).setSpeciesOrder( species_order );
+ }
+ if ( single_writer != null ) {
+ if ( !ForesterUtil.isEmpty( pos_filter_doms ) && pos_filter_doms.contains( similarity.getDomainId() ) ) {
+ single_writer.write( "<tr><td><b><a href=\"#" + similarity.getDomainId()
+ + "\"><span style=\"color:#00ff00\">" + similarity.getDomainId()
+ + "</span></a></b></td></tr>" );
+ }
+ else {
+ single_writer.write( "<tr><td><b><a href=\"#" + similarity.getDomainId() + "\">"
+ + similarity.getDomainId() + "</a></b></td></tr>" );
+ }
+ 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' );
+ }
+ if ( !ForesterUtil.isEmpty( pos_filter_doms ) && pos_filter_doms.contains( similarity.getDomainId() ) ) {
+ local_writer.write( "<tr><td><b><a href=\"#" + similarity.getDomainId()
+ + "\"><span style=\"color:#00ff00\">" + similarity.getDomainId()
+ + "</span></a></b></td></tr>" );
+ }
+ else {
+ local_writer.write( "<tr><td><b><a href=\"#" + similarity.getDomainId() + "\">"
+ + similarity.getDomainId() + "</a></b></td></tr>" );
+ }
+ local_writer.write( SurfacingConstants.NL );
+ }
+ }
+ for( final Writer w : split_writers.values() ) {
+ w.write( "</table>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<hr>" );
+ w.write( SurfacingConstants.NL );
+ //
+ w.write( "<table>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<tr><td><b>" );
+ w.write( "Species group colors:" );
+ w.write( "</b></td></tr>" );
+ 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( "Dikarya (Ascomycota & Basidiomycota, so-called \"higher fungi\")",
+ TaxonomyColors.DIKARYA_COLOR,
+ w );
+ writeColorLabels( "other Fungi", TaxonomyColors.OTHER_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( "</table>" );
+ w.write( SurfacingConstants.NL );
+ //
+ w.write( "<hr>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<table>" );
+ w.write( SurfacingConstants.NL );
+ }
+ //
+ for( final DomainSimilarity similarity : similarities ) {
+ if ( ( species_order != null ) && !species_order.isEmpty() ) {
+ ( 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( "</table>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "</font>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "</body>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "</html>" );
+ 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( "<head>" );
+ w.write( "<title>" );
+ w.write( title );
+ w.write( "</title>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<style>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a:visited { color : #000066; text-decoration : none; }" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a:link { color : #000066; text-decoration : none; }" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a:active { color : ##000066; text-decoration : none; }" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a:hover { color : #FFFFFF; background-color : #000000; text-decoration : none; }" );
+ w.write( SurfacingConstants.NL );
+ //
+ w.write( "a.pl:visited { color : #505050; text-decoration : none; font-size: 7px;}" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a.pl:link { color : #505050; text-decoration : none; font-size: 7px;}" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a.pl:active { color : #505050; text-decoration : none; font-size: 7px;}" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a.pl:hover { color : #FFFFFF; background-color : #000000; text-decoration : none; font-size: 7px;}" );
+ w.write( SurfacingConstants.NL );
+ //
+ w.write( "a.ps:visited { color : #707070; text-decoration : none; font-size: 7px;}" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a.ps:link { color : #707070; text-decoration : none; font-size: 7px;}" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a.ps:active { color : #707070; text-decoration : none; font-size: 7px;}" );
+ w.write( SurfacingConstants.NL );
+ w.write( "a.ps:hover { color : #FFFFFF; background-color : #000000; text-decoration : none; font-size: 7px;}" );
+ w.write( SurfacingConstants.NL );
+ //
+ w.write( "td { text-align: left; vertical-align: top; font-family: Verdana, Arial, Helvetica; font-size: 8pt}" );
+ w.write( SurfacingConstants.NL );
+ w.write( "h1 { color : #0000FF; font-family: Verdana, Arial, Helvetica; font-size: 18pt; font-weight: bold }" );
+ w.write( SurfacingConstants.NL );
+ w.write( "h2 { color : #0000FF; font-family: Verdana, Arial, Helvetica; font-size: 16pt; font-weight: bold }" );
+ w.write( SurfacingConstants.NL );
+ w.write( "</style>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "</head>" );
+ 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<DistanceMatrix> 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<String> filter,
+ final List<GenomeWideCombinableDomains> 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<Species, List<Protein>> protein_lists_per_species,
+ final List<GenomeWideCombinableDomains> gwcd_list,
+ final double domain_e_cutoff,
+ final Set<String> pos_filter_doms ) {
+ final SortedSet<String> all_domains = new TreeSet<String>();
+ for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
+ all_domains.addAll( gwcd.getAllDomainIds() );
+ }
+ for( final String domain : all_domains ) {
+ if ( !ForesterUtil.isEmpty( pos_filter_doms ) && !pos_filter_doms.contains( domain ) ) {
+ continue;
+ }
+ final File out = new File( output_dir + ForesterUtil.FILE_SEPARATOR + domain + surfacing.SEQ_EXTRACT_SUFFIX );
+ checkForOutputFileWriteability( out );
+ try {
+ final Writer proteins_file_writer = new BufferedWriter( new FileWriter( out ) );
+ 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<String, Integer> 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( "<a href=\"" + SurfacingConstants.UNIPROT_TAXONOMY_ID_LINK
+ + tax_code_to_id_map.get( species ) + "\" target=\"taxonomy_window\">uniprot</a>" );
+ }
+ else {
+ writer.write( "<a href=\"" + SurfacingConstants.EOL_LINK + species
+ + "\" target=\"taxonomy_window\">eol</a>" );
+ writer.write( "|" );
+ writer.write( "<a href=\"" + SurfacingConstants.GOOGLE_SCHOLAR_SEARCH + species
+ + "\" target=\"taxonomy_window\">scholar</a>" );
+ writer.write( "|" );
+ writer.write( "<a href=\"" + SurfacingConstants.GOOGLE_WEB_SEARCH_LINK + species
+ + "\" target=\"taxonomy_window\">google</a>" );
+ }
+ writer.write( "]" );
+ }
+ }
+
+ private final static void addToCountMap( final Map<String, Integer> 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<String, DescriptiveStatistics> protein_length_stats_by_dc,
+ final Map<String, DescriptiveStatistics> domain_number_stats_by_dc,
+ final Map<String, DescriptiveStatistics> domain_length_stats_by_domain ) {
+ try {
+ //
+ // if ( protein_length_stats_by_dc != null ) {
+ // for( final Entry<?, DescriptiveStatistics> 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<?, DescriptiveStatistics> 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<String, Integer> dc_gain_counts = new TreeMap<String, Integer>();
+ for( final PhylogenyNodeIterator it = local_phylogeny_l.iteratorPostorder(); it.hasNext(); ) {
+ final PhylogenyNode n = it.next();
+ final Set<String> 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<Integer, Integer> histogram = new TreeMap<Integer, Integer>();
+ final SortedMap<Integer, StringBuilder> domain_lists = new TreeMap<Integer, StringBuilder>();
+ final SortedMap<Integer, DescriptiveStatistics> dc_reapp_counts_to_protein_length_stats = new TreeMap<Integer, DescriptiveStatistics>();
+ final SortedMap<Integer, DescriptiveStatistics> dc_reapp_counts_to_domain_number_stats = new TreeMap<Integer, DescriptiveStatistics>();
+ final SortedMap<Integer, DescriptiveStatistics> dc_reapp_counts_to_domain_lengths_stats = new TreeMap<Integer, DescriptiveStatistics>();
+ final SortedMap<Integer, PriorityQueue<String>> domain_lists_go = new TreeMap<Integer, PriorityQueue<String>>();
+ final SortedMap<Integer, SortedSet<String>> domain_lists_go_unique = new TreeMap<Integer, SortedSet<String>>();
+ final Set<String> dcs = dc_gain_counts.keySet();
+ final SortedSet<String> more_than_once = new TreeSet<String>();
+ 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<String> q = new PriorityQueue<String>();
+ q.addAll( splitDomainCombination( dc ) );
+ domain_lists_go.put( count, q );
+ final SortedSet<String> set = new TreeSet<String>();
+ 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<Integer> 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<String, Integer> lca_rank_counts = new TreeMap<String, Integer>();
+ final SortedMap<String, Integer> lca_ancestor_species_counts = new TreeMap<String, Integer>();
+ for( final String dc : more_than_once ) {
+ final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
+ 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<Integer, DescriptiveStatistics> 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<Integer, DescriptiveStatistics> 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<Integer, DescriptiveStatistics> 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<String> collectAllDomainsChangedOnSubtree( final PhylogenyNode subtree_root,
+ final boolean get_gains ) {
+ final SortedSet<String> domains = new TreeSet<String>();
+ 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<BinaryDomainCombination> createSetOfAllBinaryDomainCombinationsPerGenome( final GenomeWideCombinableDomains gwcd ) {
+ final SortedMap<String, CombinableDomains> cds = gwcd.getAllCombinableDomainsIds();
+ final SortedSet<BinaryDomainCombination> binary_combinations = new TreeSet<BinaryDomainCombination>();
+ 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( "<hr>" );
+ w.write( "<br>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<tt><pre>" );
+ w.write( SurfacingConstants.NL );
+ if ( histo != null ) {
+ w.write( histo.toStringBuffer( 20, '|', 40, 5 ).toString() );
+ w.write( SurfacingConstants.NL );
+ }
+ w.write( "</pre></tt>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<table>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<tr><td>N: </td><td>" + stats.getN() + "</td></tr>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<tr><td>Min: </td><td>" + stats.getMin() + "</td></tr>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<tr><td>Max: </td><td>" + stats.getMax() + "</td></tr>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<tr><td>Mean: </td><td>" + stats.arithmeticMean() + "</td></tr>" );
+ w.write( SurfacingConstants.NL );
+ if ( stats.getN() > 1 ) {
+ w.write( "<tr><td>SD: </td><td>" + stats.sampleStandardDeviation() + "</td></tr>" );
+ }
+ else {
+ w.write( "<tr><td>SD: </td><td>n/a</td></tr>" );
+ }
+ w.write( SurfacingConstants.NL );
+ w.write( "</table>" );
+ w.write( SurfacingConstants.NL );
+ w.write( "<br>" );
+ w.write( SurfacingConstants.NL );
+ }
+
+ private static List<String> 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<String> l = new ArrayList<String>( 2 );
+ l.add( s[ 0 ] );
+ l.add( s[ 1 ] );
+ return l;
+ }
+
+ private static void writeAllEncounteredPfamsToFile( final Map<String, List<GoId>> domain_id_to_go_ids_map,
+ final Map<GoId, GoTerm> go_id_to_term_map,
+ final String outfile_name,
+ final SortedSet<String> 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<GoId> 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 );
+ }
+ }
+ 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 );
}
}
+ private final static void writeColorLabels( final String l, final Color c, final Writer w ) throws IOException {
+ w.write( "<tr><td><b><span style=\"color:" );
+ w.write( String.format( "#%02x%02x%02x", c.getRed(), c.getGreen(), c.getBlue() ) );
+ w.write( "\">" );
+ w.write( l );
+ w.write( "</span></b></td></tr>" );
+ w.write( SurfacingConstants.NL );
+ }
+
private static void writeDomainData( final Map<String, List<GoId>> domain_id_to_go_ids_map,
final Map<GoId, GoTerm> go_id_to_term_map,
final GoNameSpace go_namespace_limit,
if ( ForesterUtil.isEmpty( domain_1 ) ) {
domain_count = 1;
}
- // The following has a difficult to understand logic.
+ // The following has a difficult to understand logic.
for( int d = 0; d < domain_count; ++d ) {
List<GoId> go_ids = null;
boolean go_annotation_present = false;
final String go_id_str = go_id.getId();
out.write( "<td>" );
out.write( "<a href=\"" + SurfacingConstants.AMIGO_LINK + go_id_str
- + "\" target=\"amigo_window\">" + go_id_str + "</a>" );
+ + "\" target=\"amigo_window\">" + go_id_str + "</a>" );
out.write( "</td><td>" );
out.write( go_term.getName() );
if ( domain_count == 2 ) {
out.write( SurfacingConstants.NL );
}
}
- } // for( int d = 0; d < domain_count; ++d )
+ } // for( int d = 0; d < domain_count; ++d )
if ( !any_go_annotation_present ) {
out.write( "<tr>" );
writeDomainIdsToHtml( out, domain_0, domain_1, prefix_for_html, domain_id_to_secondary_features_maps );
final String domain_1,
final String prefix_for_detailed_html,
final Map<String, Set<String>>[] domain_id_to_secondary_features_maps )
- throws IOException {
+ throws IOException {
out.write( "<td>" );
if ( !ForesterUtil.isEmpty( prefix_for_detailed_html ) ) {
out.write( prefix_for_detailed_html );
out.write( "</td>" );
}
- public static void writeDomainSimilaritiesToFile( final StringBuilder html_desc,
- final StringBuilder html_title,
- final Writer simple_tab_writer,
- final Writer single_writer,
- Map<Character, Writer> split_writers,
- final SortedSet<DomainSimilarity> similarities,
- final boolean treat_as_binary,
- final List<Species> species_order,
- final PrintableDomainSimilarity.PRINT_OPTION print_option,
- final DomainSimilarity.DomainSimilarityScoring scoring,
- final boolean verbose,
- final Map<String, Integer> tax_code_to_id_map,
- Phylogeny phy ) throws IOException {
- if ( ( single_writer != null ) && ( ( split_writers == null ) || split_writers.isEmpty() ) ) {
- split_writers = new HashMap<Character, Writer>();
- 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( "<html>" );
- w.write( SurfacingConstants.NL );
- if ( key != '_' ) {
- addHtmlHead( w, "DC analysis (" + html_title + ") " + key.toString().toUpperCase() );
- }
- else {
- addHtmlHead( w, "DC analysis (" + html_title + ")" );
- }
- w.write( SurfacingConstants.NL );
- w.write( "<body>" );
- w.write( SurfacingConstants.NL );
- w.write( html_desc.toString() );
- w.write( SurfacingConstants.NL );
- w.write( "<hr>" );
- w.write( SurfacingConstants.NL );
- w.write( "<br>" );
- w.write( SurfacingConstants.NL );
- w.write( "<table>" );
- w.write( SurfacingConstants.NL );
- w.write( "<tr><td><b>Domains:</b></td></tr>" );
- 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( "<tr><td><b><a href=\"#" + similarity.getDomainId() + "\">"
- + similarity.getDomainId() + "</a></b></td></tr>" );
- 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( "<tr><td><b><a href=\"#" + similarity.getDomainId() + "\">"
- + similarity.getDomainId() + "</a></b></td></tr>" );
- local_writer.write( SurfacingConstants.NL );
- }
- }
- for( final Writer w : split_writers.values() ) {
- w.write( "</table>" );
- w.write( SurfacingConstants.NL );
- w.write( "<hr>" );
- w.write( SurfacingConstants.NL );
- w.write( "<table>" );
- 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( "</table>" );
- w.write( SurfacingConstants.NL );
- w.write( "</font>" );
- w.write( SurfacingConstants.NL );
- w.write( "</body>" );
- w.write( SurfacingConstants.NL );
- w.write( "</html>" );
- w.write( SurfacingConstants.NL );
- }
- break;
- }
- for( final Writer w : split_writers.values() ) {
- w.close();
- }
- }
-
private static void writeDomainsToIndividualFilePerTreeNode( final Writer individual_files_writer,
final String domain_0,
final String domain_1 ) throws IOException {
}
}
- 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<DistanceMatrix> 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<String> pfams ) {
try {
final Writer writer = new BufferedWriter( new FileWriter( new File( outfile_name ) ) );
}
writer.close();
ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote " + pfams.size() + " pfams to [" + outfile_name
- + "]" );
+ + "]" );
}
catch ( final IOException e ) {
ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "Failure to write: " + e );
}
}
- 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<String> filter,
- final List<GenomeWideCombinableDomains> 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<Species, List<Protein>> protein_lists_per_species,
- final List<GenomeWideCombinableDomains> gwcd_list,
- final double domain_e_cutoff ) {
- final SortedSet<String> all_domains = new TreeSet<String>();
- 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<String, Integer> 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( "<a href=\"" + SurfacingConstants.UNIPROT_TAXONOMY_ID_LINK
- + tax_code_to_id_map.get( species ) + "\" target=\"taxonomy_window\">uniprot</a>" );
- }
- else {
- writer.write( "<a href=\"" + SurfacingConstants.EOL_LINK + species
- + "\" target=\"taxonomy_window\">eol</a>" );
- writer.write( "|" );
- writer.write( "<a href=\"" + SurfacingConstants.GOOGLE_SCHOLAR_SEARCH + species
- + "\" target=\"taxonomy_window\">scholar</a>" );
- writer.write( "|" );
- writer.write( "<a href=\"" + SurfacingConstants.GOOGLE_WEB_SEARCH_LINK + species
- + "\" target=\"taxonomy_window\">google</a>" );
- }
- writer.write( "]" );
- }
- }
-
private static void writeToNexus( final String outfile_name,
final CharacterStateMatrix<BinaryStates> matrix,
final Phylogeny phylogeny ) {
if ( !( matrix instanceof BasicCharacterStateMatrix ) ) {
throw new IllegalArgumentException( "can only write matrices of type [" + BasicCharacterStateMatrix.class
- + "] to nexus" );
+ + "] to nexus" );
}
final BasicCharacterStateMatrix<BinaryStates> my_matrix = ( org.forester.evoinference.matrix.character.BasicCharacterStateMatrix<BinaryStates> ) matrix;
final List<Phylogeny> phylogenies = new ArrayList<Phylogeny>( 1 );
phylogeny );
}
- private SurfacingUtil() {
- // Hidden constructor.
+ final static class DomainComparator implements Comparator<Domain> {
+
+ final private boolean _ascending;
+
+ public DomainComparator( final boolean ascending ) {
+ _ascending = ascending;
+ }
+
+ @Override
+ public final int compare( final Domain d0, final Domain d1 ) {
+ if ( d0.getFrom() < d1.getFrom() ) {
+ return _ascending ? -1 : 1;
+ }
+ else if ( d0.getFrom() > d1.getFrom() ) {
+ return _ascending ? 1 : -1;
+ }
+ return 0;
+ }
}
}