3 // FORESTER -- software libraries and applications
4 // for evolutionary biology research and applications.
6 // Copyright (C) 2008-2009 Christian M. Zmasek
7 // Copyright (C) 2008-2009 Burnham Institute for Medical Research
10 // This library is free software; you can redistribute it and/or
11 // modify it under the terms of the GNU Lesser General Public
12 // License as published by the Free Software Foundation; either
13 // version 2.1 of the License, or (at your option) any later version.
15 // This library is distributed in the hope that it will be useful,
16 // but WITHOUT ANY WARRANTY; without even the implied warranty of
17 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
18 // Lesser General Public License for more details.
20 // You should have received a copy of the GNU Lesser General Public
21 // License along with this library; if not, write to the Free Software
22 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
24 // Contact: phylosoft @ gmail . com
25 // WWW: https://sites.google.com/site/cmzmasek/home/software/forester
27 package org.forester.surfacing;
29 import java.io.BufferedWriter;
31 import java.io.FileWriter;
32 import java.io.IOException;
33 import java.io.Writer;
34 import java.text.DecimalFormat;
35 import java.text.NumberFormat;
36 import java.util.ArrayList;
37 import java.util.Arrays;
38 import java.util.Collections;
39 import java.util.Comparator;
40 import java.util.HashMap;
41 import java.util.HashSet;
42 import java.util.Iterator;
43 import java.util.List;
45 import java.util.Map.Entry;
46 import java.util.PriorityQueue;
48 import java.util.SortedMap;
49 import java.util.SortedSet;
50 import java.util.TreeMap;
51 import java.util.TreeSet;
52 import java.util.regex.Matcher;
53 import java.util.regex.Pattern;
55 import org.forester.application.surfacing;
56 import org.forester.evoinference.distance.NeighborJoining;
57 import org.forester.evoinference.matrix.character.BasicCharacterStateMatrix;
58 import org.forester.evoinference.matrix.character.CharacterStateMatrix;
59 import org.forester.evoinference.matrix.character.CharacterStateMatrix.BinaryStates;
60 import org.forester.evoinference.matrix.character.CharacterStateMatrix.Format;
61 import org.forester.evoinference.matrix.character.CharacterStateMatrix.GainLossStates;
62 import org.forester.evoinference.matrix.distance.BasicSymmetricalDistanceMatrix;
63 import org.forester.evoinference.matrix.distance.DistanceMatrix;
64 import org.forester.go.GoId;
65 import org.forester.go.GoNameSpace;
66 import org.forester.go.GoTerm;
67 import org.forester.go.PfamToGoMapping;
68 import org.forester.io.parsers.nexus.NexusConstants;
69 import org.forester.io.writers.PhylogenyWriter;
70 import org.forester.phylogeny.Phylogeny;
71 import org.forester.phylogeny.PhylogenyMethods;
72 import org.forester.phylogeny.PhylogenyNode;
73 import org.forester.phylogeny.PhylogenyNode.NH_CONVERSION_SUPPORT_VALUE_STYLE;
74 import org.forester.phylogeny.data.BinaryCharacters;
75 import org.forester.phylogeny.data.Confidence;
76 import org.forester.phylogeny.data.Taxonomy;
77 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
78 import org.forester.protein.BasicDomain;
79 import org.forester.protein.BasicProtein;
80 import org.forester.protein.BinaryDomainCombination;
81 import org.forester.protein.Domain;
82 import org.forester.protein.Protein;
83 import org.forester.species.Species;
84 import org.forester.surfacing.DomainSimilarityCalculator.Detailedness;
85 import org.forester.surfacing.DomainSimilarityCalculator.GoAnnotationOutput;
86 import org.forester.surfacing.GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder;
87 import org.forester.util.AsciiHistogram;
88 import org.forester.util.BasicDescriptiveStatistics;
89 import org.forester.util.BasicTable;
90 import org.forester.util.BasicTableParser;
91 import org.forester.util.DescriptiveStatistics;
92 import org.forester.util.ForesterUtil;
94 public final class SurfacingUtil {
96 private final static NumberFormat FORMATTER_3 = new DecimalFormat( "0.000" );
97 private static final Comparator<Domain> ASCENDING_CONFIDENCE_VALUE_ORDER = new Comparator<Domain>() {
100 public int compare( final Domain d1,
102 if ( d1.getPerSequenceEvalue() < d2
103 .getPerSequenceEvalue() ) {
107 .getPerSequenceEvalue() > d2
108 .getPerSequenceEvalue() ) {
112 return d1.compareTo( d2 );
116 public final static Pattern PATTERN_SP_STYLE_TAXONOMY = Pattern.compile( "^[A-Z0-9]{3,5}$" );
118 private SurfacingUtil() {
119 // Hidden constructor.
122 public static void addAllBinaryDomainCombinationToSet( final GenomeWideCombinableDomains genome,
123 final SortedSet<BinaryDomainCombination> binary_domain_combinations ) {
124 final SortedMap<String, CombinableDomains> all_cd = genome.getAllCombinableDomainsIds();
125 for( final String domain_id : all_cd.keySet() ) {
126 binary_domain_combinations.addAll( all_cd.get( domain_id ).toBinaryDomainCombinations() );
130 public static void addAllDomainIdsToSet( final GenomeWideCombinableDomains genome,
131 final SortedSet<String> domain_ids ) {
132 final SortedSet<String> domains = genome.getAllDomainIds();
133 for( final String domain : domains ) {
134 domain_ids.add( domain );
138 public static void addHtmlHead( final Writer w, final String title ) throws IOException {
139 w.write( SurfacingConstants.NL );
141 w.write( "<title>" );
143 w.write( "</title>" );
144 w.write( SurfacingConstants.NL );
145 w.write( "<style>" );
146 w.write( SurfacingConstants.NL );
147 w.write( "a:visited { color : #6633FF; text-decoration : none; }" );
148 w.write( SurfacingConstants.NL );
149 w.write( "a:link { color : #6633FF; text-decoration : none; }" );
150 w.write( SurfacingConstants.NL );
151 w.write( "a:active { color : #99FF00; text-decoration : none; }" );
152 w.write( SurfacingConstants.NL );
153 w.write( "a:hover { color : #FFFFFF; background-color : #99FF00; text-decoration : none; }" );
154 w.write( SurfacingConstants.NL );
155 w.write( "td { text-align: left; vertical-align: top; font-family: Verdana, Arial, Helvetica; font-size: 8pt}" );
156 w.write( SurfacingConstants.NL );
157 w.write( "h1 { color : #0000FF; font-family: Verdana, Arial, Helvetica; font-size: 18pt; font-weight: bold }" );
158 w.write( SurfacingConstants.NL );
159 w.write( "h2 { color : #0000FF; font-family: Verdana, Arial, Helvetica; font-size: 16pt; font-weight: bold }" );
160 w.write( SurfacingConstants.NL );
161 w.write( "</style>" );
162 w.write( SurfacingConstants.NL );
163 w.write( "</head>" );
164 w.write( SurfacingConstants.NL );
167 public static DescriptiveStatistics calculateDescriptiveStatisticsForMeanValues( final Set<DomainSimilarity> similarities ) {
168 final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
169 for( final DomainSimilarity similarity : similarities ) {
170 stats.addValue( similarity.getMeanSimilarityScore() );
175 public static int calculateOverlap( final Domain domain, final List<Boolean> covered_positions ) {
176 int overlap_count = 0;
177 for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) {
178 if ( ( i < covered_positions.size() ) && ( covered_positions.get( i ) == true ) ) {
182 return overlap_count;
185 public static void checkForOutputFileWriteability( final File outfile ) {
186 final String error = ForesterUtil.isWritableFile( outfile );
187 if ( !ForesterUtil.isEmpty( error ) ) {
188 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
192 public static void collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile( final CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
193 final BinaryDomainCombination.DomainCombinationType dc_type,
194 final List<BinaryDomainCombination> all_binary_domains_combination_gained,
195 final boolean get_gains ) {
196 final SortedSet<String> sorted_ids = new TreeSet<String>();
197 for( int i = 0; i < matrix.getNumberOfIdentifiers(); ++i ) {
198 sorted_ids.add( matrix.getIdentifier( i ) );
200 for( final String id : sorted_ids ) {
201 for( int c = 0; c < matrix.getNumberOfCharacters(); ++c ) {
202 if ( ( get_gains && ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.GAIN ) )
203 || ( !get_gains && ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.LOSS ) ) ) {
204 if ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) {
205 all_binary_domains_combination_gained.add( AdjactantDirectedBinaryDomainCombination
206 .createInstance( matrix.getCharacter( c ) ) );
208 else if ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED ) {
209 all_binary_domains_combination_gained.add( DirectedBinaryDomainCombination
210 .createInstance( matrix.getCharacter( c ) ) );
213 all_binary_domains_combination_gained.add( BasicBinaryDomainCombination.createInstance( matrix
214 .getCharacter( c ) ) );
221 public static Map<String, List<GoId>> createDomainIdToGoIdMap( final List<PfamToGoMapping> pfam_to_go_mappings ) {
222 final Map<String, List<GoId>> domain_id_to_go_ids_map = new HashMap<String, List<GoId>>( pfam_to_go_mappings.size() );
223 for( final PfamToGoMapping pfam_to_go : pfam_to_go_mappings ) {
224 if ( !domain_id_to_go_ids_map.containsKey( pfam_to_go.getKey() ) ) {
225 domain_id_to_go_ids_map.put( pfam_to_go.getKey(), new ArrayList<GoId>() );
227 domain_id_to_go_ids_map.get( pfam_to_go.getKey() ).add( pfam_to_go.getValue() );
229 return domain_id_to_go_ids_map;
232 public static Map<String, Set<String>> createDomainIdToSecondaryFeaturesMap( final File secondary_features_map_file )
234 final BasicTable<String> primary_table = BasicTableParser.parse( secondary_features_map_file, '\t' );
235 final Map<String, Set<String>> map = new TreeMap<String, Set<String>>();
236 for( int r = 0; r < primary_table.getNumberOfRows(); ++r ) {
237 final String domain_id = primary_table.getValue( 0, r );
238 if ( !map.containsKey( domain_id ) ) {
239 map.put( domain_id, new HashSet<String>() );
241 map.get( domain_id ).add( primary_table.getValue( 1, r ) );
246 public static Phylogeny createNjTreeBasedOnMatrixToFile( final File nj_tree_outfile, final DistanceMatrix distance ) {
247 checkForOutputFileWriteability( nj_tree_outfile );
248 final NeighborJoining nj = NeighborJoining.createInstance();
249 final Phylogeny phylogeny = nj.execute( ( BasicSymmetricalDistanceMatrix ) distance );
250 phylogeny.setName( nj_tree_outfile.getName() );
251 writePhylogenyToFile( phylogeny, nj_tree_outfile.toString() );
255 public static Map<String, Integer> createTaxCodeToIdMap( final Phylogeny phy ) {
256 final Map<String, Integer> m = new HashMap<String, Integer>();
257 for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) {
258 final PhylogenyNode n = iter.next();
259 if ( n.getNodeData().isHasTaxonomy() ) {
260 final Taxonomy t = n.getNodeData().getTaxonomy();
261 final String c = t.getTaxonomyCode();
262 if ( !ForesterUtil.isEmpty( c ) ) {
263 if ( n.getNodeData().getTaxonomy() == null ) {
264 ForesterUtil.fatalError( surfacing.PRG_NAME, "no taxonomy id for node " + n );
266 final String id = n.getNodeData().getTaxonomy().getIdentifier().getValue();
267 if ( ForesterUtil.isEmpty( id ) ) {
268 ForesterUtil.fatalError( surfacing.PRG_NAME, "no taxonomy id for node " + n );
270 if ( m.containsKey( c ) ) {
271 ForesterUtil.fatalError( surfacing.PRG_NAME, "taxonomy code " + c + " is not unique" );
273 final int iid = Integer.valueOf( id );
274 if ( m.containsValue( iid ) ) {
275 ForesterUtil.fatalError( surfacing.PRG_NAME, "taxonomy id " + iid + " is not unique" );
281 ForesterUtil.fatalError( surfacing.PRG_NAME, "no taxonomy for node " + n );
287 public static void decoratePrintableDomainSimilarities( final SortedSet<DomainSimilarity> domain_similarities,
288 final Detailedness detailedness,
289 final GoAnnotationOutput go_annotation_output,
290 final Map<GoId, GoTerm> go_id_to_term_map,
291 final GoNameSpace go_namespace_limit ) {
292 if ( ( go_namespace_limit != null ) && ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) ) {
293 throw new IllegalArgumentException( "attempt to use a GO namespace limit without a GO id to term map" );
295 for( final DomainSimilarity domain_similarity : domain_similarities ) {
296 if ( domain_similarity instanceof PrintableDomainSimilarity ) {
297 final PrintableDomainSimilarity printable_domain_similarity = ( PrintableDomainSimilarity ) domain_similarity;
298 printable_domain_similarity.setDetailedness( detailedness );
299 printable_domain_similarity.setGoAnnotationOutput( go_annotation_output );
300 printable_domain_similarity.setGoIdToTermMap( go_id_to_term_map );
301 printable_domain_similarity.setGoNamespaceLimit( go_namespace_limit );
306 public static void doit( final List<Protein> proteins,
307 final List<String> query_domain_ids_nc_order,
309 final String separator,
310 final String limit_to_species,
311 final Map<String, List<Integer>> average_protein_lengths_by_dc ) throws IOException {
312 for( final Protein protein : proteins ) {
313 if ( ForesterUtil.isEmpty( limit_to_species )
314 || protein.getSpecies().getSpeciesId().equalsIgnoreCase( limit_to_species ) ) {
315 if ( protein.contains( query_domain_ids_nc_order, true ) ) {
316 out.write( protein.getSpecies().getSpeciesId() );
317 out.write( separator );
318 out.write( protein.getProteinId().getId() );
319 out.write( separator );
321 final Set<String> visited_domain_ids = new HashSet<String>();
322 boolean first = true;
323 for( final Domain domain : protein.getProteinDomains() ) {
324 if ( !visited_domain_ids.contains( domain.getDomainId() ) ) {
325 visited_domain_ids.add( domain.getDomainId() );
332 out.write( domain.getDomainId() );
334 out.write( "" + domain.getTotalCount() );
339 out.write( separator );
340 if ( !( ForesterUtil.isEmpty( protein.getDescription() ) || protein.getDescription()
341 .equals( SurfacingConstants.NONE ) ) ) {
342 out.write( protein.getDescription() );
344 out.write( separator );
345 if ( !( ForesterUtil.isEmpty( protein.getAccession() ) || protein.getAccession()
346 .equals( SurfacingConstants.NONE ) ) ) {
347 out.write( protein.getAccession() );
349 out.write( SurfacingConstants.NL );
356 public static void domainsPerProteinsStatistics( final String genome,
357 final List<Protein> protein_list,
358 final DescriptiveStatistics all_genomes_domains_per_potein_stats,
359 final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo,
360 final SortedSet<String> domains_which_are_always_single,
361 final SortedSet<String> domains_which_are_sometimes_single_sometimes_not,
362 final SortedSet<String> domains_which_never_single,
363 final Writer writer ) {
364 final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
365 for( final Protein protein : protein_list ) {
366 final int domains = protein.getNumberOfProteinDomains();
367 //System.out.println( domains );
368 stats.addValue( domains );
369 all_genomes_domains_per_potein_stats.addValue( domains );
370 if ( !all_genomes_domains_per_potein_histo.containsKey( domains ) ) {
371 all_genomes_domains_per_potein_histo.put( domains, 1 );
374 all_genomes_domains_per_potein_histo.put( domains,
375 1 + all_genomes_domains_per_potein_histo.get( domains ) );
377 if ( domains == 1 ) {
378 final String domain = protein.getProteinDomain( 0 ).getDomainId();
379 if ( !domains_which_are_sometimes_single_sometimes_not.contains( domain ) ) {
380 if ( domains_which_never_single.contains( domain ) ) {
381 domains_which_never_single.remove( domain );
382 domains_which_are_sometimes_single_sometimes_not.add( domain );
385 domains_which_are_always_single.add( domain );
389 else if ( domains > 1 ) {
390 for( final Domain d : protein.getProteinDomains() ) {
391 final String domain = d.getDomainId();
392 // System.out.println( domain );
393 if ( !domains_which_are_sometimes_single_sometimes_not.contains( domain ) ) {
394 if ( domains_which_are_always_single.contains( domain ) ) {
395 domains_which_are_always_single.remove( domain );
396 domains_which_are_sometimes_single_sometimes_not.add( domain );
399 domains_which_never_single.add( domain );
406 writer.write( genome );
407 writer.write( "\t" );
408 if ( stats.getN() >= 1 ) {
409 writer.write( stats.arithmeticMean() + "" );
410 writer.write( "\t" );
411 if ( stats.getN() >= 2 ) {
412 writer.write( stats.sampleStandardDeviation() + "" );
417 writer.write( "\t" );
418 writer.write( stats.median() + "" );
419 writer.write( "\t" );
420 writer.write( stats.getN() + "" );
421 writer.write( "\t" );
422 writer.write( stats.getMin() + "" );
423 writer.write( "\t" );
424 writer.write( stats.getMax() + "" );
427 writer.write( "\t" );
428 writer.write( "\t" );
429 writer.write( "\t" );
431 writer.write( "\t" );
432 writer.write( "\t" );
434 writer.write( "\n" );
436 catch ( final IOException e ) {
441 public static void executeDomainLengthAnalysis( final String[][] input_file_properties,
442 final int number_of_genomes,
443 final DomainLengthsTable domain_lengths_table,
444 final File outfile ) throws IOException {
445 final DecimalFormat df = new DecimalFormat( "#.00" );
446 checkForOutputFileWriteability( outfile );
447 final BufferedWriter out = new BufferedWriter( new FileWriter( outfile ) );
448 out.write( "MEAN BASED STATISTICS PER SPECIES" );
449 out.write( ForesterUtil.LINE_SEPARATOR );
450 out.write( domain_lengths_table.createMeanBasedStatisticsPerSpeciesTable().toString() );
451 out.write( ForesterUtil.LINE_SEPARATOR );
452 out.write( ForesterUtil.LINE_SEPARATOR );
453 final List<DomainLengths> domain_lengths_list = domain_lengths_table.getDomainLengthsList();
454 out.write( "OUTLIER SPECIES PER DOMAIN (Z>=1.5)" );
455 out.write( ForesterUtil.LINE_SEPARATOR );
456 for( final DomainLengths domain_lengths : domain_lengths_list ) {
457 final List<Species> species_list = domain_lengths.getMeanBasedOutlierSpecies( 1.5 );
458 if ( species_list.size() > 0 ) {
459 out.write( domain_lengths.getDomainId() + "\t" );
460 for( final Species species : species_list ) {
461 out.write( species + "\t" );
463 out.write( ForesterUtil.LINE_SEPARATOR );
464 // DescriptiveStatistics stats_for_domain = domain_lengths
465 // .calculateMeanBasedStatistics();
466 //AsciiHistogram histo = new AsciiHistogram( stats_for_domain );
467 //System.out.println( histo.toStringBuffer( 40, '=', 60, 4 ).toString() );
470 out.write( ForesterUtil.LINE_SEPARATOR );
471 out.write( ForesterUtil.LINE_SEPARATOR );
472 out.write( "OUTLIER SPECIES (Z 1.0)" );
473 out.write( ForesterUtil.LINE_SEPARATOR );
474 final DescriptiveStatistics stats_for_all_species = domain_lengths_table
475 .calculateMeanBasedStatisticsForAllSpecies();
476 out.write( stats_for_all_species.asSummary() );
477 out.write( ForesterUtil.LINE_SEPARATOR );
478 final AsciiHistogram histo = new AsciiHistogram( stats_for_all_species );
479 out.write( histo.toStringBuffer( 40, '=', 60, 4 ).toString() );
480 out.write( ForesterUtil.LINE_SEPARATOR );
481 final double population_sd = stats_for_all_species.sampleStandardDeviation();
482 final double population_mean = stats_for_all_species.arithmeticMean();
483 for( final Species species : domain_lengths_table.getSpecies() ) {
484 final double x = domain_lengths_table.calculateMeanBasedStatisticsForSpecies( species ).arithmeticMean();
485 final double z = ( x - population_mean ) / population_sd;
486 out.write( species + "\t" + z );
487 out.write( ForesterUtil.LINE_SEPARATOR );
489 out.write( ForesterUtil.LINE_SEPARATOR );
490 for( final Species species : domain_lengths_table.getSpecies() ) {
491 final DescriptiveStatistics stats_for_species = domain_lengths_table
492 .calculateMeanBasedStatisticsForSpecies( species );
493 final double x = stats_for_species.arithmeticMean();
494 final double z = ( x - population_mean ) / population_sd;
495 if ( ( z <= -1.0 ) || ( z >= 1.0 ) ) {
496 out.write( species + "\t" + df.format( z ) + "\t" + stats_for_species.asSummary() );
497 out.write( ForesterUtil.LINE_SEPARATOR );
501 // final List<HistogramData> histogram_datas = new ArrayList<HistogramData>();
502 // for( int i = 0; i < number_of_genomes; ++i ) {
503 // final Species species = new BasicSpecies( input_file_properties[ i ][ 0 ] );
505 // .add( new HistogramData( species.toString(), domain_lengths_table
506 // .calculateMeanBasedStatisticsForSpecies( species )
507 // .getDataAsDoubleArray(), 5, 600, null, 60 ) );
509 // final HistogramsFrame hf = new HistogramsFrame( histogram_datas );
510 // hf.setVisible( true );
516 * @param all_binary_domains_combination_lost_fitch
517 * @param use_last_in_fitch_parsimony
518 * @param consider_directedness_and_adjacency_for_bin_combinations
519 * @param all_binary_domains_combination_gained if null ignored, otherwise this is to list all binary domain combinations
520 * which were gained under unweighted (Fitch) parsimony.
522 public static void executeParsimonyAnalysis( final long random_number_seed_for_fitch_parsimony,
523 final boolean radomize_fitch_parsimony,
524 final String outfile_name,
525 final DomainParsimonyCalculator domain_parsimony,
526 final Phylogeny phylogeny,
527 final Map<String, List<GoId>> domain_id_to_go_ids_map,
528 final Map<GoId, GoTerm> go_id_to_term_map,
529 final GoNameSpace go_namespace_limit,
530 final String parameters_str,
531 final Map<String, Set<String>>[] domain_id_to_secondary_features_maps,
532 final SortedSet<String> positive_filter,
533 final boolean output_binary_domain_combinations_for_graphs,
534 final List<BinaryDomainCombination> all_binary_domains_combination_gained_fitch,
535 final List<BinaryDomainCombination> all_binary_domains_combination_lost_fitch,
536 final BinaryDomainCombination.DomainCombinationType dc_type,
537 final Map<String, DescriptiveStatistics> protein_length_stats_by_dc,
538 final Map<String, DescriptiveStatistics> domain_number_stats_by_dc,
539 final Map<String, DescriptiveStatistics> domain_length_stats_by_domain,
540 final Map<String, Integer> tax_code_to_id_map,
541 final boolean write_to_nexus,
542 final boolean use_last_in_fitch_parsimony ) {
543 final String sep = ForesterUtil.LINE_SEPARATOR + "###################" + ForesterUtil.LINE_SEPARATOR;
544 final String date_time = ForesterUtil.getCurrentDateTime();
545 final SortedSet<String> all_pfams_encountered = new TreeSet<String>();
546 final SortedSet<String> all_pfams_gained_as_domains = new TreeSet<String>();
547 final SortedSet<String> all_pfams_lost_as_domains = new TreeSet<String>();
548 final SortedSet<String> all_pfams_gained_as_dom_combinations = new TreeSet<String>();
549 final SortedSet<String> all_pfams_lost_as_dom_combinations = new TreeSet<String>();
550 if ( write_to_nexus ) {
551 writeToNexus( outfile_name, domain_parsimony, phylogeny );
555 Phylogeny local_phylogeny_l = phylogeny.copy();
556 if ( ( positive_filter != null ) && ( positive_filter.size() > 0 ) ) {
557 domain_parsimony.executeDolloParsimonyOnDomainPresence( positive_filter );
560 domain_parsimony.executeDolloParsimonyOnDomainPresence();
562 SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossMatrix(), outfile_name
563 + surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS, Format.FORESTER );
564 SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossCountsMatrix(), outfile_name
565 + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS, Format.FORESTER );
566 SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
567 CharacterStateMatrix.GainLossStates.GAIN,
568 outfile_name + surfacing.PARSIMONY_OUTPUT_DOLLO_GAINS_D,
570 ForesterUtil.LINE_SEPARATOR,
572 SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
573 CharacterStateMatrix.GainLossStates.LOSS,
574 outfile_name + surfacing.PARSIMONY_OUTPUT_DOLLO_LOSSES_D,
576 ForesterUtil.LINE_SEPARATOR,
578 SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(), null, outfile_name
579 + surfacing.PARSIMONY_OUTPUT_DOLLO_PRESENT_D, sep, ForesterUtil.LINE_SEPARATOR, null );
581 writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
585 domain_parsimony.getGainLossMatrix(),
586 CharacterStateMatrix.GainLossStates.GAIN,
587 outfile_name + surfacing.PARSIMONY_OUTPUT_DOLLO_GAINS_HTML_D,
589 ForesterUtil.LINE_SEPARATOR,
590 "Dollo Parsimony | Gains | Domains",
592 domain_id_to_secondary_features_maps,
593 all_pfams_encountered,
594 all_pfams_gained_as_domains,
596 tax_code_to_id_map );
597 writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
601 domain_parsimony.getGainLossMatrix(),
602 CharacterStateMatrix.GainLossStates.LOSS,
603 outfile_name + surfacing.PARSIMONY_OUTPUT_DOLLO_LOSSES_HTML_D,
605 ForesterUtil.LINE_SEPARATOR,
606 "Dollo Parsimony | Losses | Domains",
608 domain_id_to_secondary_features_maps,
609 all_pfams_encountered,
610 all_pfams_lost_as_domains,
612 tax_code_to_id_map );
613 // writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
614 // go_id_to_term_map,
615 // go_namespace_limit,
617 // domain_parsimony.getGainLossMatrix(),
619 // outfile_name + surfacing.PARSIMONY_OUTPUT_DOLLO_PRESENT_HTML_D,
621 // ForesterUtil.LINE_SEPARATOR,
622 // "Dollo Parsimony | Present | Domains",
624 // domain_id_to_secondary_features_maps,
625 // all_pfams_encountered,
627 // "_dollo_present_d",
628 // tax_code_to_id_map );
629 preparePhylogeny( local_phylogeny_l,
632 "Dollo parsimony on domain presence/absence",
633 "dollo_on_domains_" + outfile_name,
635 SurfacingUtil.writePhylogenyToFile( local_phylogeny_l, outfile_name
636 + surfacing.DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO );
638 writeAllDomainsChangedOnAllSubtrees( local_phylogeny_l, true, outfile_name, "_dollo_all_gains_d" );
639 writeAllDomainsChangedOnAllSubtrees( local_phylogeny_l, false, outfile_name, "_dollo_all_losses_d" );
641 catch ( final IOException e ) {
643 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
645 if ( domain_parsimony.calculateNumberOfBinaryDomainCombination() > 0 ) {
646 // FITCH DOMAIN COMBINATIONS
647 // -------------------------
648 local_phylogeny_l = phylogeny.copy();
649 String randomization = "no";
650 if ( radomize_fitch_parsimony ) {
651 domain_parsimony.executeFitchParsimonyOnBinaryDomainCombintion( random_number_seed_for_fitch_parsimony );
652 randomization = "yes, seed = " + random_number_seed_for_fitch_parsimony;
655 domain_parsimony.executeFitchParsimonyOnBinaryDomainCombintion( use_last_in_fitch_parsimony );
657 SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossMatrix(), outfile_name
658 + surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS, Format.FORESTER );
659 SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossCountsMatrix(), outfile_name
660 + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS, Format.FORESTER );
662 .writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
663 CharacterStateMatrix.GainLossStates.GAIN,
664 outfile_name + surfacing.PARSIMONY_OUTPUT_FITCH_GAINS_BC,
666 ForesterUtil.LINE_SEPARATOR,
668 SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
669 CharacterStateMatrix.GainLossStates.LOSS,
671 + surfacing.PARSIMONY_OUTPUT_FITCH_LOSSES_BC,
673 ForesterUtil.LINE_SEPARATOR,
675 SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(), null, outfile_name
676 + surfacing.PARSIMONY_OUTPUT_FITCH_PRESENT_BC, sep, ForesterUtil.LINE_SEPARATOR, null );
677 if ( all_binary_domains_combination_gained_fitch != null ) {
678 collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
680 all_binary_domains_combination_gained_fitch,
683 if ( all_binary_domains_combination_lost_fitch != null ) {
684 collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
686 all_binary_domains_combination_lost_fitch,
689 if ( output_binary_domain_combinations_for_graphs ) {
691 .writeBinaryStatesMatrixAsListToFileForBinaryCombinationsForGraphAnalysis( domain_parsimony
692 .getGainLossMatrix(),
695 + surfacing.PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS,
697 ForesterUtil.LINE_SEPARATOR,
698 BinaryDomainCombination.OutputFormat.DOT );
701 writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
705 domain_parsimony.getGainLossMatrix(),
706 CharacterStateMatrix.GainLossStates.GAIN,
707 outfile_name + surfacing.PARSIMONY_OUTPUT_FITCH_GAINS_HTML_BC,
709 ForesterUtil.LINE_SEPARATOR,
710 "Fitch Parsimony | Gains | Domain Combinations",
713 all_pfams_encountered,
714 all_pfams_gained_as_dom_combinations,
716 tax_code_to_id_map );
717 writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
721 domain_parsimony.getGainLossMatrix(),
722 CharacterStateMatrix.GainLossStates.LOSS,
723 outfile_name + surfacing.PARSIMONY_OUTPUT_FITCH_LOSSES_HTML_BC,
725 ForesterUtil.LINE_SEPARATOR,
726 "Fitch Parsimony | Losses | Domain Combinations",
729 all_pfams_encountered,
730 all_pfams_lost_as_dom_combinations,
732 tax_code_to_id_map );
733 // writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
734 // go_id_to_term_map,
735 // go_namespace_limit,
737 // domain_parsimony.getGainLossMatrix(),
739 // outfile_name + surfacing.PARSIMONY_OUTPUT_FITCH_PRESENT_HTML_BC,
741 // ForesterUtil.LINE_SEPARATOR,
742 // "Fitch Parsimony | Present | Domain Combinations",
745 // all_pfams_encountered,
747 // "_fitch_present_dc",
748 // tax_code_to_id_map );
749 writeAllEncounteredPfamsToFile( domain_id_to_go_ids_map,
752 all_pfams_encountered );
753 writePfamsToFile( outfile_name + surfacing.ALL_PFAMS_GAINED_AS_DOMAINS_SUFFIX, all_pfams_gained_as_domains );
754 writePfamsToFile( outfile_name + surfacing.ALL_PFAMS_LOST_AS_DOMAINS_SUFFIX, all_pfams_lost_as_domains );
755 writePfamsToFile( outfile_name + surfacing.ALL_PFAMS_GAINED_AS_DC_SUFFIX,
756 all_pfams_gained_as_dom_combinations );
757 writePfamsToFile( outfile_name + surfacing.ALL_PFAMS_LOST_AS_DC_SUFFIX, all_pfams_lost_as_dom_combinations );
758 preparePhylogeny( local_phylogeny_l,
761 "Fitch parsimony on binary domain combination presence/absence randomization: "
763 "fitch_on_binary_domain_combinations_" + outfile_name,
765 SurfacingUtil.writePhylogenyToFile( local_phylogeny_l, outfile_name
766 + surfacing.BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH );
767 calculateIndependentDomainCombinationGains( local_phylogeny_l,
769 + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX,
771 + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX,
773 + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX,
775 + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_UNIQUE_SUFFIX,
776 outfile_name + "_indep_dc_gains_fitch_lca_ranks.txt",
777 outfile_name + "_indep_dc_gains_fitch_lca_taxonomies.txt",
778 outfile_name + "_indep_dc_gains_fitch_protein_statistics.txt",
779 protein_length_stats_by_dc,
780 domain_number_stats_by_dc,
781 domain_length_stats_by_domain );
785 public static void executeParsimonyAnalysisForSecondaryFeatures( final String outfile_name,
786 final DomainParsimonyCalculator secondary_features_parsimony,
787 final Phylogeny phylogeny,
788 final String parameters_str,
789 final Map<Species, MappingResults> mapping_results_map,
790 final boolean use_last_in_fitch_parsimony ) {
791 final String sep = ForesterUtil.LINE_SEPARATOR + "###################" + ForesterUtil.LINE_SEPARATOR;
792 final String date_time = ForesterUtil.getCurrentDateTime();
793 System.out.println();
794 writeToNexus( outfile_name + surfacing.NEXUS_SECONDARY_FEATURES,
795 secondary_features_parsimony.createMatrixOfSecondaryFeaturePresenceOrAbsence( null ),
797 Phylogeny local_phylogeny_copy = phylogeny.copy();
798 secondary_features_parsimony.executeDolloParsimonyOnSecondaryFeatures( mapping_results_map );
799 SurfacingUtil.writeMatrixToFile( secondary_features_parsimony.getGainLossMatrix(), outfile_name
800 + surfacing.PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES, Format.FORESTER );
801 SurfacingUtil.writeMatrixToFile( secondary_features_parsimony.getGainLossCountsMatrix(), outfile_name
802 + surfacing.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES, Format.FORESTER );
804 .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(),
805 CharacterStateMatrix.GainLossStates.GAIN,
807 + surfacing.PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES,
809 ForesterUtil.LINE_SEPARATOR,
812 .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(),
813 CharacterStateMatrix.GainLossStates.LOSS,
815 + surfacing.PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES,
817 ForesterUtil.LINE_SEPARATOR,
820 .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(),
823 + surfacing.PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES,
825 ForesterUtil.LINE_SEPARATOR,
827 preparePhylogeny( local_phylogeny_copy,
828 secondary_features_parsimony,
830 "Dollo parsimony on secondary feature presence/absence",
831 "dollo_on_secondary_features_" + outfile_name,
833 SurfacingUtil.writePhylogenyToFile( local_phylogeny_copy, outfile_name
834 + surfacing.SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO );
835 // FITCH DOMAIN COMBINATIONS
836 // -------------------------
837 local_phylogeny_copy = phylogeny.copy();
838 final String randomization = "no";
839 secondary_features_parsimony
840 .executeFitchParsimonyOnBinaryDomainCombintionOnSecondaryFeatures( use_last_in_fitch_parsimony );
841 preparePhylogeny( local_phylogeny_copy,
842 secondary_features_parsimony,
844 "Fitch parsimony on secondary binary domain combination presence/absence randomization: "
846 "fitch_on_binary_domain_combinations_" + outfile_name,
848 SurfacingUtil.writePhylogenyToFile( local_phylogeny_copy, outfile_name
849 + surfacing.BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH_MAPPED );
850 calculateIndependentDomainCombinationGains( local_phylogeny_copy, outfile_name
851 + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_MAPPED_OUTPUT_SUFFIX, outfile_name
852 + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_MAPPED_OUTPUT_SUFFIX, outfile_name
853 + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_SUFFIX, outfile_name
854 + surfacing.INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_UNIQUE_SUFFIX, outfile_name
855 + "_MAPPED_indep_dc_gains_fitch_lca_ranks.txt", outfile_name
856 + "_MAPPED_indep_dc_gains_fitch_lca_taxonomies.txt", null, null, null, null );
859 public static void extractProteinNames( final List<Protein> proteins,
860 final List<String> query_domain_ids_nc_order,
862 final String separator,
863 final String limit_to_species ) throws IOException {
864 for( final Protein protein : proteins ) {
865 if ( ForesterUtil.isEmpty( limit_to_species )
866 || protein.getSpecies().getSpeciesId().equalsIgnoreCase( limit_to_species ) ) {
867 if ( protein.contains( query_domain_ids_nc_order, true ) ) {
868 out.write( protein.getSpecies().getSpeciesId() );
869 out.write( separator );
870 out.write( protein.getProteinId().getId() );
871 out.write( separator );
873 final Set<String> visited_domain_ids = new HashSet<String>();
874 boolean first = true;
875 for( final Domain domain : protein.getProteinDomains() ) {
876 if ( !visited_domain_ids.contains( domain.getDomainId() ) ) {
877 visited_domain_ids.add( domain.getDomainId() );
884 out.write( domain.getDomainId() );
886 out.write( "" + domain.getTotalCount() );
891 out.write( separator );
892 if ( !( ForesterUtil.isEmpty( protein.getDescription() ) || protein.getDescription()
893 .equals( SurfacingConstants.NONE ) ) ) {
894 out.write( protein.getDescription() );
896 out.write( separator );
897 if ( !( ForesterUtil.isEmpty( protein.getAccession() ) || protein.getAccession()
898 .equals( SurfacingConstants.NONE ) ) ) {
899 out.write( protein.getAccession() );
901 out.write( SurfacingConstants.NL );
908 public static void extractProteinNames( final SortedMap<Species, List<Protein>> protein_lists_per_species,
909 final String domain_id,
911 final String separator,
912 final String limit_to_species,
913 final double domain_e_cutoff ) throws IOException {
914 System.out.println( "Per domain E-value: " + domain_e_cutoff );
915 for( final Species species : protein_lists_per_species.keySet() ) {
916 System.out.println( species + ":" );
917 for( final Protein protein : protein_lists_per_species.get( species ) ) {
918 if ( ForesterUtil.isEmpty( limit_to_species )
919 || protein.getSpecies().getSpeciesId().equalsIgnoreCase( limit_to_species ) ) {
920 final List<Domain> domains = protein.getProteinDomains( domain_id );
921 if ( domains.size() > 0 ) {
922 out.write( protein.getSpecies().getSpeciesId() );
923 out.write( separator );
924 out.write( protein.getProteinId().getId() );
925 out.write( separator );
926 out.write( domain_id.toString() );
927 out.write( separator );
929 for( final Domain domain : domains ) {
930 if ( ( domain_e_cutoff < 0 ) || ( domain.getPerDomainEvalue() <= domain_e_cutoff ) ) {
932 out.write( domain.getFrom() + "-" + domain.getTo() );
933 if ( prev_to >= 0 ) {
934 final int l = domain.getFrom() - prev_to;
935 System.out.println( l );
937 prev_to = domain.getTo();
941 out.write( separator );
942 final List<Domain> domain_list = new ArrayList<Domain>();
943 for( final Domain domain : protein.getProteinDomains() ) {
944 if ( ( domain_e_cutoff < 0 ) || ( domain.getPerDomainEvalue() <= domain_e_cutoff ) ) {
945 domain_list.add( domain );
948 final Domain domain_ary[] = new Domain[ domain_list.size() ];
949 for( int i = 0; i < domain_list.size(); ++i ) {
950 domain_ary[ i ] = domain_list.get( i );
952 Arrays.sort( domain_ary, new DomainComparator( true ) );
954 boolean first = true;
955 for( final Domain domain : domain_ary ) {
962 out.write( domain.getDomainId().toString() );
963 out.write( ":" + domain.getFrom() + "-" + domain.getTo() );
964 out.write( ":" + domain.getPerDomainEvalue() );
967 if ( !( ForesterUtil.isEmpty( protein.getDescription() ) || protein.getDescription()
968 .equals( SurfacingConstants.NONE ) ) ) {
969 out.write( protein.getDescription() );
971 out.write( separator );
972 if ( !( ForesterUtil.isEmpty( protein.getAccession() ) || protein.getAccession()
973 .equals( SurfacingConstants.NONE ) ) ) {
974 out.write( protein.getAccession() );
976 out.write( SurfacingConstants.NL );
984 public static SortedSet<String> getAllDomainIds( final List<GenomeWideCombinableDomains> gwcd_list ) {
985 final SortedSet<String> all_domains_ids = new TreeSet<String>();
986 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
987 final Set<String> all_domains = gwcd.getAllDomainIds();
988 // for( final Domain domain : all_domains ) {
989 all_domains_ids.addAll( all_domains );
992 return all_domains_ids;
995 public static SortedMap<String, Integer> getDomainCounts( final List<Protein> protein_domain_collections ) {
996 final SortedMap<String, Integer> map = new TreeMap<String, Integer>();
997 for( final Protein protein_domain_collection : protein_domain_collections ) {
998 for( final Object name : protein_domain_collection.getProteinDomains() ) {
999 final BasicDomain protein_domain = ( BasicDomain ) name;
1000 final String id = protein_domain.getDomainId();
1001 if ( map.containsKey( id ) ) {
1002 map.put( id, map.get( id ) + 1 );
1012 public static int getNumberOfNodesLackingName( final Phylogeny p, final StringBuilder names ) {
1013 final PhylogenyNodeIterator it = p.iteratorPostorder();
1015 while ( it.hasNext() ) {
1016 final PhylogenyNode n = it.next();
1017 if ( ForesterUtil.isEmpty( n.getName() )
1018 && ( !n.getNodeData().isHasTaxonomy() || ForesterUtil.isEmpty( n.getNodeData().getTaxonomy()
1019 .getScientificName() ) )
1020 && ( !n.getNodeData().isHasTaxonomy() || ForesterUtil.isEmpty( n.getNodeData().getTaxonomy()
1021 .getCommonName() ) ) ) {
1022 if ( n.getParent() != null ) {
1023 names.append( " " );
1024 names.append( n.getParent().getName() );
1026 final List l = n.getAllExternalDescendants();
1027 for( final Object object : l ) {
1028 System.out.println( l.toString() );
1037 * Returns true is Domain domain falls in an uninterrupted stretch of
1038 * covered positions.
1041 * @param covered_positions
1044 public static boolean isEngulfed( final Domain domain, final List<Boolean> covered_positions ) {
1045 for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) {
1046 if ( ( i >= covered_positions.size() ) || ( covered_positions.get( i ) != true ) ) {
1053 public static void performDomainArchitectureAnalysis( final SortedMap<String, Set<String>> domain_architecutures,
1054 final SortedMap<String, Integer> domain_architecuture_counts,
1055 final int min_count,
1056 final File da_counts_outfile,
1057 final File unique_da_outfile ) {
1058 checkForOutputFileWriteability( da_counts_outfile );
1059 checkForOutputFileWriteability( unique_da_outfile );
1061 final BufferedWriter da_counts_out = new BufferedWriter( new FileWriter( da_counts_outfile ) );
1062 final BufferedWriter unique_da_out = new BufferedWriter( new FileWriter( unique_da_outfile ) );
1063 final Iterator<Entry<String, Integer>> it = domain_architecuture_counts.entrySet().iterator();
1064 while ( it.hasNext() ) {
1065 final Map.Entry<String, Integer> e = it.next();
1066 final String da = e.getKey();
1067 final int count = e.getValue();
1068 if ( count >= min_count ) {
1069 da_counts_out.write( da );
1070 da_counts_out.write( "\t" );
1071 da_counts_out.write( String.valueOf( count ) );
1072 da_counts_out.write( ForesterUtil.LINE_SEPARATOR );
1075 final Iterator<Entry<String, Set<String>>> it2 = domain_architecutures.entrySet().iterator();
1076 while ( it2.hasNext() ) {
1077 final Map.Entry<String, Set<String>> e2 = it2.next();
1078 final String genome = e2.getKey();
1079 final Set<String> das = e2.getValue();
1080 if ( das.contains( da ) ) {
1081 unique_da_out.write( genome );
1082 unique_da_out.write( "\t" );
1083 unique_da_out.write( da );
1084 unique_da_out.write( ForesterUtil.LINE_SEPARATOR );
1089 unique_da_out.close();
1090 da_counts_out.close();
1092 catch ( final IOException e ) {
1093 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1095 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote distance matrices to \"" + da_counts_outfile + "\"" );
1096 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote distance matrices to \"" + unique_da_outfile + "\"" );
1100 public static void preparePhylogeny( final Phylogeny p,
1101 final DomainParsimonyCalculator domain_parsimony,
1102 final String date_time,
1103 final String method,
1105 final String parameters_str ) {
1106 domain_parsimony.decoratePhylogenyWithDomains( p );
1107 final StringBuilder desc = new StringBuilder();
1108 desc.append( "[Method: " + method + "] [Date: " + date_time + "] " );
1109 desc.append( "[Cost: " + domain_parsimony.getCost() + "] " );
1110 desc.append( "[Gains: " + domain_parsimony.getTotalGains() + "] " );
1111 desc.append( "[Losses: " + domain_parsimony.getTotalLosses() + "] " );
1112 desc.append( "[Unchanged: " + domain_parsimony.getTotalUnchanged() + "] " );
1113 desc.append( "[Parameters: " + parameters_str + "]" );
1115 p.setDescription( desc.toString() );
1116 p.setConfidence( new Confidence( domain_parsimony.getCost(), "parsimony" ) );
1117 p.setRerootable( false );
1118 p.setRooted( true );
1122 * species | protein id | n-terminal domain | c-terminal domain | n-terminal domain per domain E-value | c-terminal domain per domain E-value
1126 static public StringBuffer proteinToDomainCombinations( final Protein protein,
1127 final String protein_id,
1128 final String separator ) {
1129 final StringBuffer sb = new StringBuffer();
1130 if ( protein.getSpecies() == null ) {
1131 throw new IllegalArgumentException( "species must not be null" );
1133 if ( ForesterUtil.isEmpty( protein.getSpecies().getSpeciesId() ) ) {
1134 throw new IllegalArgumentException( "species id must not be empty" );
1136 final List<Domain> domains = protein.getProteinDomains();
1137 if ( domains.size() > 1 ) {
1138 final Map<String, Integer> counts = new HashMap<String, Integer>();
1139 for( final Domain domain : domains ) {
1140 final String id = domain.getDomainId();
1141 if ( counts.containsKey( id ) ) {
1142 counts.put( id, counts.get( id ) + 1 );
1145 counts.put( id, 1 );
1148 final Set<String> dcs = new HashSet<String>();
1149 for( int i = 1; i < domains.size(); ++i ) {
1150 for( int j = 0; j < i; ++j ) {
1151 Domain domain_n = domains.get( i );
1152 Domain domain_c = domains.get( j );
1153 if ( domain_n.getFrom() > domain_c.getFrom() ) {
1154 domain_n = domains.get( j );
1155 domain_c = domains.get( i );
1157 final String dc = domain_n.getDomainId() + domain_c.getDomainId();
1158 if ( !dcs.contains( dc ) ) {
1160 sb.append( protein.getSpecies() );
1161 sb.append( separator );
1162 sb.append( protein_id );
1163 sb.append( separator );
1164 sb.append( domain_n.getDomainId() );
1165 sb.append( separator );
1166 sb.append( domain_c.getDomainId() );
1167 sb.append( separator );
1168 sb.append( domain_n.getPerDomainEvalue() );
1169 sb.append( separator );
1170 sb.append( domain_c.getPerDomainEvalue() );
1171 sb.append( separator );
1172 sb.append( counts.get( domain_n.getDomainId() ) );
1173 sb.append( separator );
1174 sb.append( counts.get( domain_c.getDomainId() ) );
1175 sb.append( ForesterUtil.LINE_SEPARATOR );
1180 else if ( domains.size() == 1 ) {
1181 sb.append( protein.getSpecies() );
1182 sb.append( separator );
1183 sb.append( protein_id );
1184 sb.append( separator );
1185 sb.append( domains.get( 0 ).getDomainId() );
1186 sb.append( separator );
1187 sb.append( separator );
1188 sb.append( domains.get( 0 ).getPerDomainEvalue() );
1189 sb.append( separator );
1190 sb.append( separator );
1192 sb.append( separator );
1193 sb.append( ForesterUtil.LINE_SEPARATOR );
1196 sb.append( protein.getSpecies() );
1197 sb.append( separator );
1198 sb.append( protein_id );
1199 sb.append( separator );
1200 sb.append( separator );
1201 sb.append( separator );
1202 sb.append( separator );
1203 sb.append( separator );
1204 sb.append( separator );
1205 sb.append( ForesterUtil.LINE_SEPARATOR );
1212 * Example regarding engulfment: ------------0.1 ----------0.2 --0.3 =>
1213 * domain with 0.3 is ignored
1215 * -----------0.1 ----------0.2 --0.3 => domain with 0.3 is ignored
1218 * ------------0.1 ----------0.3 --0.2 => domains with 0.3 and 0.2 are _not_
1221 * @param max_allowed_overlap
1222 * maximal allowed overlap (inclusive) to be still considered not
1223 * overlapping (zero or negative value to allow any overlap)
1224 * @param remove_engulfed_domains
1225 * to remove domains which are completely engulfed by coverage of
1226 * domains with better support
1230 public static Protein removeOverlappingDomains( final int max_allowed_overlap,
1231 final boolean remove_engulfed_domains,
1232 final Protein protein ) {
1233 final Protein pruned_protein = new BasicProtein( protein.getProteinId().getId(), protein.getSpecies()
1234 .getSpeciesId(), protein.getLength() );
1235 final List<Domain> sorted = SurfacingUtil.sortDomainsWithAscendingConfidenceValues( protein );
1236 final List<Boolean> covered_positions = new ArrayList<Boolean>();
1237 for( final Domain domain : sorted ) {
1238 if ( ( ( max_allowed_overlap < 0 ) || ( SurfacingUtil.calculateOverlap( domain, covered_positions ) <= max_allowed_overlap ) )
1239 && ( !remove_engulfed_domains || !isEngulfed( domain, covered_positions ) ) ) {
1240 final int covered_positions_size = covered_positions.size();
1241 for( int i = covered_positions_size; i < domain.getFrom(); ++i ) {
1242 covered_positions.add( false );
1244 final int new_covered_positions_size = covered_positions.size();
1245 for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) {
1246 if ( i < new_covered_positions_size ) {
1247 covered_positions.set( i, true );
1250 covered_positions.add( true );
1253 pruned_protein.addProteinDomain( domain );
1256 return pruned_protein;
1259 public static List<Domain> sortDomainsWithAscendingConfidenceValues( final Protein protein ) {
1260 final List<Domain> domains = new ArrayList<Domain>();
1261 for( final Domain d : protein.getProteinDomains() ) {
1264 Collections.sort( domains, SurfacingUtil.ASCENDING_CONFIDENCE_VALUE_ORDER );
1268 public static int storeDomainArchitectures( final String genome,
1269 final SortedMap<String, Set<String>> domain_architecutures,
1270 final List<Protein> protein_list,
1271 final Map<String, Integer> distinct_domain_architecuture_counts ) {
1272 final Set<String> da = new HashSet<String>();
1273 domain_architecutures.put( genome, da );
1274 for( final Protein protein : protein_list ) {
1275 final String da_str = ( ( BasicProtein ) protein ).toDomainArchitectureString( "~", 3, "=" );
1276 if ( !da.contains( da_str ) ) {
1277 if ( !distinct_domain_architecuture_counts.containsKey( da_str ) ) {
1278 distinct_domain_architecuture_counts.put( da_str, 1 );
1281 distinct_domain_architecuture_counts.put( da_str,
1282 distinct_domain_architecuture_counts.get( da_str ) + 1 );
1290 public static void writeAllDomainsChangedOnAllSubtrees( final Phylogeny p,
1291 final boolean get_gains,
1292 final String outdir,
1293 final String suffix_for_filename ) throws IOException {
1294 CharacterStateMatrix.GainLossStates state = CharacterStateMatrix.GainLossStates.GAIN;
1296 state = CharacterStateMatrix.GainLossStates.LOSS;
1298 final File base_dir = createBaseDirForPerNodeDomainFiles( surfacing.BASE_DIRECTORY_PER_SUBTREE_DOMAIN_GAIN_LOSS_FILES,
1302 for( final PhylogenyNodeIterator it = p.iteratorPostorder(); it.hasNext(); ) {
1303 final PhylogenyNode node = it.next();
1304 if ( !node.isExternal() ) {
1305 final SortedSet<String> domains = collectAllDomainsChangedOnSubtree( node, get_gains );
1306 if ( domains.size() > 0 ) {
1307 final Writer writer = ForesterUtil.createBufferedWriter( base_dir + ForesterUtil.FILE_SEPARATOR
1308 + node.getName() + suffix_for_filename );
1309 for( final String domain : domains ) {
1310 writer.write( domain );
1311 writer.write( ForesterUtil.LINE_SEPARATOR );
1319 public static void writeBinaryDomainCombinationsFileForGraphAnalysis( final String[][] input_file_properties,
1320 final File output_dir,
1321 final GenomeWideCombinableDomains gwcd,
1323 final GenomeWideCombinableDomainsSortOrder dc_sort_order ) {
1324 File dc_outfile_dot = new File( input_file_properties[ i ][ 1 ]
1325 + surfacing.DOMAIN_COMBINITONS_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS );
1326 if ( output_dir != null ) {
1327 dc_outfile_dot = new File( output_dir + ForesterUtil.FILE_SEPARATOR + dc_outfile_dot );
1329 checkForOutputFileWriteability( dc_outfile_dot );
1330 final SortedSet<BinaryDomainCombination> binary_combinations = createSetOfAllBinaryDomainCombinationsPerGenome( gwcd );
1332 final BufferedWriter out_dot = new BufferedWriter( new FileWriter( dc_outfile_dot ) );
1333 for( final BinaryDomainCombination bdc : binary_combinations ) {
1334 out_dot.write( bdc.toGraphDescribingLanguage( BinaryDomainCombination.OutputFormat.DOT, null, null )
1336 out_dot.write( SurfacingConstants.NL );
1340 catch ( final IOException e ) {
1341 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1343 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote binary domain combination for \""
1344 + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ", "
1345 + input_file_properties[ i ][ 2 ] + ") to: \"" + dc_outfile_dot + "\"" );
1348 public static void writeBinaryStatesMatrixAsListToFile( final CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
1349 final CharacterStateMatrix.GainLossStates state,
1350 final String filename,
1351 final String indentifier_characters_separator,
1352 final String character_separator,
1353 final Map<String, String> descriptions ) {
1354 final File outfile = new File( filename );
1355 checkForOutputFileWriteability( outfile );
1356 final SortedSet<String> sorted_ids = new TreeSet<String>();
1357 for( int i = 0; i < matrix.getNumberOfIdentifiers(); ++i ) {
1358 sorted_ids.add( matrix.getIdentifier( i ) );
1361 final BufferedWriter out = new BufferedWriter( new FileWriter( outfile ) );
1362 for( final String id : sorted_ids ) {
1363 out.write( indentifier_characters_separator );
1364 out.write( "#" + id );
1365 out.write( indentifier_characters_separator );
1366 for( int c = 0; c < matrix.getNumberOfCharacters(); ++c ) {
1368 // using null to indicate either UNCHANGED_PRESENT or GAIN.
1369 if ( ( matrix.getState( id, c ) == state )
1370 || ( ( state == null ) && ( ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.GAIN ) || ( matrix
1371 .getState( id, c ) == CharacterStateMatrix.GainLossStates.UNCHANGED_PRESENT ) ) ) ) {
1372 out.write( matrix.getCharacter( c ) );
1373 if ( ( descriptions != null ) && !descriptions.isEmpty()
1374 && descriptions.containsKey( matrix.getCharacter( c ) ) ) {
1376 out.write( descriptions.get( matrix.getCharacter( c ) ) );
1378 out.write( character_separator );
1385 catch ( final IOException e ) {
1386 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1388 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote characters list: \"" + filename + "\"" );
1391 public static void writeBinaryStatesMatrixAsListToFileForBinaryCombinationsForGraphAnalysis( final CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
1392 final CharacterStateMatrix.GainLossStates state,
1393 final String filename,
1394 final String indentifier_characters_separator,
1395 final String character_separator,
1396 final BinaryDomainCombination.OutputFormat bc_output_format ) {
1397 final File outfile = new File( filename );
1398 checkForOutputFileWriteability( outfile );
1399 final SortedSet<String> sorted_ids = new TreeSet<String>();
1400 for( int i = 0; i < matrix.getNumberOfIdentifiers(); ++i ) {
1401 sorted_ids.add( matrix.getIdentifier( i ) );
1404 final BufferedWriter out = new BufferedWriter( new FileWriter( outfile ) );
1405 for( final String id : sorted_ids ) {
1406 out.write( indentifier_characters_separator );
1407 out.write( "#" + id );
1408 out.write( indentifier_characters_separator );
1409 for( int c = 0; c < matrix.getNumberOfCharacters(); ++c ) {
1411 // using null to indicate either UNCHANGED_PRESENT or GAIN.
1412 if ( ( matrix.getState( id, c ) == state )
1413 || ( ( state == null ) && ( ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.GAIN ) || ( matrix
1414 .getState( id, c ) == CharacterStateMatrix.GainLossStates.UNCHANGED_PRESENT ) ) ) ) {
1415 BinaryDomainCombination bdc = null;
1417 bdc = BasicBinaryDomainCombination.createInstance( matrix.getCharacter( c ) );
1419 catch ( final Exception e ) {
1420 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
1422 out.write( bdc.toGraphDescribingLanguage( bc_output_format, null, null ).toString() );
1423 out.write( character_separator );
1430 catch ( final IOException e ) {
1431 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1433 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote characters list: \"" + filename + "\"" );
1436 public static void writeBinaryStatesMatrixToList( final Map<String, List<GoId>> domain_id_to_go_ids_map,
1437 final Map<GoId, GoTerm> go_id_to_term_map,
1438 final GoNameSpace go_namespace_limit,
1439 final boolean domain_combinations,
1440 final CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
1441 final CharacterStateMatrix.GainLossStates state,
1442 final String filename,
1443 final String indentifier_characters_separator,
1444 final String character_separator,
1445 final String title_for_html,
1446 final String prefix_for_html,
1447 final Map<String, Set<String>>[] domain_id_to_secondary_features_maps,
1448 final SortedSet<String> all_pfams_encountered,
1449 final SortedSet<String> pfams_gained_or_lost,
1450 final String suffix_for_per_node_events_file,
1451 final Map<String, Integer> tax_code_to_id_map ) {
1452 if ( ( go_namespace_limit != null ) && ( ( go_id_to_term_map == null ) || ( go_id_to_term_map.size() < 1 ) ) ) {
1453 throw new IllegalArgumentException( "attempt to use GO namespace limit without a GO-id to term map" );
1455 else if ( ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) ) {
1456 throw new IllegalArgumentException( "attempt to output detailed HTML without a Pfam to GO map" );
1458 else if ( ( ( go_id_to_term_map == null ) || ( go_id_to_term_map.size() < 1 ) ) ) {
1459 throw new IllegalArgumentException( "attempt to output detailed HTML without a GO-id to term map" );
1461 final File outfile = new File( filename );
1462 checkForOutputFileWriteability( outfile );
1463 final SortedSet<String> sorted_ids = new TreeSet<String>();
1464 for( int i = 0; i < matrix.getNumberOfIdentifiers(); ++i ) {
1465 sorted_ids.add( matrix.getIdentifier( i ) );
1468 final Writer out = new BufferedWriter( new FileWriter( outfile ) );
1469 final File per_node_go_mapped_domain_gain_loss_files_base_dir = createBaseDirForPerNodeDomainFiles( surfacing.BASE_DIRECTORY_PER_NODE_DOMAIN_GAIN_LOSS_FILES,
1470 domain_combinations,
1473 Writer per_node_go_mapped_domain_gain_loss_outfile_writer = null;
1474 File per_node_go_mapped_domain_gain_loss_outfile = null;
1475 int per_node_counter = 0;
1476 out.write( "<html>" );
1477 out.write( SurfacingConstants.NL );
1478 addHtmlHead( out, title_for_html );
1479 out.write( SurfacingConstants.NL );
1480 out.write( "<body>" );
1481 out.write( SurfacingConstants.NL );
1482 out.write( "<h1>" );
1483 out.write( SurfacingConstants.NL );
1484 out.write( title_for_html );
1485 out.write( SurfacingConstants.NL );
1486 out.write( "</h1>" );
1487 out.write( SurfacingConstants.NL );
1488 out.write( "<table>" );
1489 out.write( SurfacingConstants.NL );
1490 for( final String id : sorted_ids ) {
1491 final Matcher matcher = PATTERN_SP_STYLE_TAXONOMY.matcher( id );
1492 if ( matcher.matches() ) {
1495 out.write( "<tr>" );
1496 out.write( "<td>" );
1497 out.write( "<a href=\"#" + id + "\">" + id + "</a>" );
1498 out.write( "</td>" );
1499 out.write( "</tr>" );
1500 out.write( SurfacingConstants.NL );
1502 out.write( "</table>" );
1503 out.write( SurfacingConstants.NL );
1504 for( final String id : sorted_ids ) {
1505 final Matcher matcher = PATTERN_SP_STYLE_TAXONOMY.matcher( id );
1506 if ( matcher.matches() ) {
1509 out.write( SurfacingConstants.NL );
1510 out.write( "<h2>" );
1511 out.write( "<a name=\"" + id + "\">" + id + "</a>" );
1512 writeTaxonomyLinks( out, id, tax_code_to_id_map );
1513 out.write( "</h2>" );
1514 out.write( SurfacingConstants.NL );
1515 out.write( "<table>" );
1516 out.write( SurfacingConstants.NL );
1517 out.write( "<tr>" );
1518 out.write( "<td><b>" );
1519 out.write( "Pfam domain(s)" );
1520 out.write( "</b></td><td><b>" );
1521 out.write( "GO term acc" );
1522 out.write( "</b></td><td><b>" );
1523 out.write( "GO term" );
1524 out.write( "</b></td><td><b>" );
1525 out.write( "GO namespace" );
1526 out.write( "</b></td>" );
1527 out.write( "</tr>" );
1528 out.write( SurfacingConstants.NL );
1529 out.write( "</tr>" );
1530 out.write( SurfacingConstants.NL );
1531 per_node_counter = 0;
1532 if ( matrix.getNumberOfCharacters() > 0 ) {
1533 per_node_go_mapped_domain_gain_loss_outfile = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
1534 + ForesterUtil.FILE_SEPARATOR + id + suffix_for_per_node_events_file );
1535 SurfacingUtil.checkForOutputFileWriteability( per_node_go_mapped_domain_gain_loss_outfile );
1536 per_node_go_mapped_domain_gain_loss_outfile_writer = ForesterUtil
1537 .createBufferedWriter( per_node_go_mapped_domain_gain_loss_outfile );
1540 per_node_go_mapped_domain_gain_loss_outfile = null;
1541 per_node_go_mapped_domain_gain_loss_outfile_writer = null;
1543 for( int c = 0; c < matrix.getNumberOfCharacters(); ++c ) {
1545 // using null to indicate either UNCHANGED_PRESENT or GAIN.
1546 if ( ( matrix.getState( id, c ) == state )
1547 || ( ( state == null ) && ( ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.UNCHANGED_PRESENT ) || ( matrix
1548 .getState( id, c ) == CharacterStateMatrix.GainLossStates.GAIN ) ) ) ) {
1549 final String character = matrix.getCharacter( c );
1550 String domain_0 = "";
1551 String domain_1 = "";
1552 if ( character.indexOf( BinaryDomainCombination.SEPARATOR ) > 0 ) {
1553 final String[] s = character.split( BinaryDomainCombination.SEPARATOR );
1554 if ( s.length != 2 ) {
1555 throw new AssertionError( "this should not have happened: unexpected format for domain combination: ["
1556 + character + "]" );
1562 domain_0 = character;
1564 writeDomainData( domain_id_to_go_ids_map,
1571 character_separator,
1572 domain_id_to_secondary_features_maps,
1574 all_pfams_encountered.add( domain_0 );
1575 if ( pfams_gained_or_lost != null ) {
1576 pfams_gained_or_lost.add( domain_0 );
1578 if ( !ForesterUtil.isEmpty( domain_1 ) ) {
1579 all_pfams_encountered.add( domain_1 );
1580 if ( pfams_gained_or_lost != null ) {
1581 pfams_gained_or_lost.add( domain_1 );
1584 if ( per_node_go_mapped_domain_gain_loss_outfile_writer != null ) {
1585 writeDomainsToIndividualFilePerTreeNode( per_node_go_mapped_domain_gain_loss_outfile_writer,
1592 if ( per_node_go_mapped_domain_gain_loss_outfile_writer != null ) {
1593 per_node_go_mapped_domain_gain_loss_outfile_writer.close();
1594 if ( per_node_counter < 1 ) {
1595 per_node_go_mapped_domain_gain_loss_outfile.delete();
1597 per_node_counter = 0;
1599 out.write( "</table>" );
1600 out.write( SurfacingConstants.NL );
1601 out.write( "<hr>" );
1602 out.write( SurfacingConstants.NL );
1603 } // for( final String id : sorted_ids ) {
1604 out.write( "</body>" );
1605 out.write( SurfacingConstants.NL );
1606 out.write( "</html>" );
1607 out.write( SurfacingConstants.NL );
1611 catch ( final IOException e ) {
1612 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1614 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote characters detailed HTML list: \"" + filename + "\"" );
1617 public static void writeDomainCombinationsCountsFile( final String[][] input_file_properties,
1618 final File output_dir,
1619 final Writer per_genome_domain_promiscuity_statistics_writer,
1620 final GenomeWideCombinableDomains gwcd,
1622 final GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order ) {
1623 File dc_outfile = new File( input_file_properties[ i ][ 1 ]
1624 + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
1625 if ( output_dir != null ) {
1626 dc_outfile = new File( output_dir + ForesterUtil.FILE_SEPARATOR + dc_outfile );
1628 checkForOutputFileWriteability( dc_outfile );
1630 final BufferedWriter out = new BufferedWriter( new FileWriter( dc_outfile ) );
1631 out.write( gwcd.toStringBuilder( dc_sort_order ).toString() );
1634 catch ( final IOException e ) {
1635 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1637 final DescriptiveStatistics stats = gwcd.getPerGenomeDomainPromiscuityStatistics();
1639 per_genome_domain_promiscuity_statistics_writer.write( input_file_properties[ i ][ 1 ] + "\t" );
1640 per_genome_domain_promiscuity_statistics_writer.write( FORMATTER_3.format( stats.arithmeticMean() ) + "\t" );
1641 if ( stats.getN() < 2 ) {
1642 per_genome_domain_promiscuity_statistics_writer.write( "n/a" + "\t" );
1645 per_genome_domain_promiscuity_statistics_writer.write( FORMATTER_3.format( stats
1646 .sampleStandardDeviation() ) + "\t" );
1648 per_genome_domain_promiscuity_statistics_writer.write( FORMATTER_3.format( stats.median() ) + "\t" );
1649 per_genome_domain_promiscuity_statistics_writer.write( ( int ) stats.getMin() + "\t" );
1650 per_genome_domain_promiscuity_statistics_writer.write( ( int ) stats.getMax() + "\t" );
1651 per_genome_domain_promiscuity_statistics_writer.write( stats.getN() + "\t" );
1652 final SortedSet<String> mpds = gwcd.getMostPromiscuosDomain();
1653 for( final String mpd : mpds ) {
1654 per_genome_domain_promiscuity_statistics_writer.write( mpd + " " );
1656 per_genome_domain_promiscuity_statistics_writer.write( ForesterUtil.LINE_SEPARATOR );
1658 catch ( final IOException e ) {
1659 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1661 if ( input_file_properties[ i ].length == 3 ) {
1662 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote domain combination counts for \""
1663 + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ", "
1664 + input_file_properties[ i ][ 2 ] + ") to: \"" + dc_outfile + "\"" );
1667 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote domain combination counts for \""
1668 + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ") to: \""
1669 + dc_outfile + "\"" );
1673 public static DescriptiveStatistics writeDomainSimilaritiesToFile( final StringBuilder html_desc,
1674 final StringBuilder html_title,
1675 final Writer single_writer,
1676 Map<Character, Writer> split_writers,
1677 final SortedSet<DomainSimilarity> similarities,
1678 final boolean treat_as_binary,
1679 final List<Species> species_order,
1680 final PrintableDomainSimilarity.PRINT_OPTION print_option,
1681 final DomainSimilarity.DomainSimilaritySortField sort_field,
1682 final DomainSimilarity.DomainSimilarityScoring scoring,
1683 final boolean verbose,
1684 final Map<String, Integer> tax_code_to_id_map )
1685 throws IOException {
1686 final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
1687 String histogram_title = null;
1688 switch ( sort_field ) {
1689 case ABS_MAX_COUNTS_DIFFERENCE:
1690 if ( treat_as_binary ) {
1691 histogram_title = "absolute counts difference:";
1694 histogram_title = "absolute (maximal) counts difference:";
1697 case MAX_COUNTS_DIFFERENCE:
1698 if ( treat_as_binary ) {
1699 histogram_title = "counts difference:";
1702 histogram_title = "(maximal) counts difference:";
1706 histogram_title = "score mean:";
1709 histogram_title = "score minimum:";
1712 histogram_title = "score maximum:";
1714 case MAX_DIFFERENCE:
1715 if ( treat_as_binary ) {
1716 histogram_title = "difference:";
1719 histogram_title = "(maximal) difference:";
1723 histogram_title = "score mean:";
1726 histogram_title = "score standard deviation:";
1729 histogram_title = "species number:";
1732 throw new AssertionError( "Unknown sort field: " + sort_field );
1734 for( final DomainSimilarity similarity : similarities ) {
1735 switch ( sort_field ) {
1736 case ABS_MAX_COUNTS_DIFFERENCE:
1737 stats.addValue( Math.abs( similarity.getMaximalDifferenceInCounts() ) );
1739 case MAX_COUNTS_DIFFERENCE:
1740 stats.addValue( similarity.getMaximalDifferenceInCounts() );
1743 stats.addValue( similarity.getMeanSimilarityScore() );
1746 stats.addValue( similarity.getMinimalSimilarityScore() );
1749 stats.addValue( similarity.getMaximalSimilarityScore() );
1751 case MAX_DIFFERENCE:
1752 stats.addValue( similarity.getMaximalDifference() );
1755 stats.addValue( similarity.getMeanSimilarityScore() );
1758 stats.addValue( similarity.getStandardDeviationOfSimilarityScore() );
1761 stats.addValue( similarity.getSpecies().size() );
1764 throw new AssertionError( "Unknown sort field: " + sort_field );
1767 AsciiHistogram histo = null;
1768 if ( stats.getMin() < stats.getMin() ) {
1769 histo = new AsciiHistogram( stats, histogram_title );
1772 if ( histo != null ) {
1773 System.out.println( histo.toStringBuffer( 20, '|', 40, 5 ) );
1775 System.out.println();
1776 System.out.println( "N : " + stats.getN() );
1777 System.out.println( "Min : " + stats.getMin() );
1778 System.out.println( "Max : " + stats.getMax() );
1779 System.out.println( "Mean : " + stats.arithmeticMean() );
1780 if ( stats.getN() > 1 ) {
1781 System.out.println( "SD : " + stats.sampleStandardDeviation() );
1784 System.out.println( "SD : n/a" );
1786 System.out.println( "Median : " + stats.median() );
1787 if ( stats.getN() > 1 ) {
1788 System.out.println( "Pearsonian skewness : " + stats.pearsonianSkewness() );
1791 System.out.println( "Pearsonian skewness : n/a" );
1794 if ( ( single_writer != null ) && ( ( split_writers == null ) || split_writers.isEmpty() ) ) {
1795 split_writers = new HashMap<Character, Writer>();
1796 split_writers.put( '_', single_writer );
1798 switch ( print_option ) {
1799 case SIMPLE_TAB_DELIMITED:
1802 for( final Character key : split_writers.keySet() ) {
1803 final Writer w = split_writers.get( key );
1804 w.write( "<html>" );
1805 w.write( SurfacingConstants.NL );
1807 addHtmlHead( w, "DCs (" + html_title + ") " + key.toString().toUpperCase() );
1810 addHtmlHead( w, "DCs (" + html_title + ")" );
1812 w.write( SurfacingConstants.NL );
1813 w.write( "<body>" );
1814 w.write( SurfacingConstants.NL );
1815 w.write( html_desc.toString() );
1816 w.write( SurfacingConstants.NL );
1819 w.write( SurfacingConstants.NL );
1820 w.write( "<tt><pre>" );
1821 w.write( SurfacingConstants.NL );
1822 if ( histo != null ) {
1823 w.write( histo.toStringBuffer( 20, '|', 40, 5 ).toString() );
1824 w.write( SurfacingConstants.NL );
1826 w.write( "</pre></tt>" );
1827 w.write( SurfacingConstants.NL );
1828 w.write( "<table>" );
1829 w.write( SurfacingConstants.NL );
1830 w.write( "<tr><td>N: </td><td>" + stats.getN() + "</td></tr>" );
1831 w.write( SurfacingConstants.NL );
1832 w.write( "<tr><td>Min: </td><td>" + stats.getMin() + "</td></tr>" );
1833 w.write( SurfacingConstants.NL );
1834 w.write( "<tr><td>Max: </td><td>" + stats.getMax() + "</td></tr>" );
1835 w.write( SurfacingConstants.NL );
1836 w.write( "<tr><td>Mean: </td><td>" + stats.arithmeticMean() + "</td></tr>" );
1837 w.write( SurfacingConstants.NL );
1838 if ( stats.getN() > 1 ) {
1839 w.write( "<tr><td>SD: </td><td>" + stats.sampleStandardDeviation() + "</td></tr>" );
1842 w.write( "<tr><td>SD: </td><td>n/a</td></tr>" );
1844 w.write( SurfacingConstants.NL );
1845 w.write( "<tr><td>Median: </td><td>" + stats.median() + "</td></tr>" );
1846 w.write( SurfacingConstants.NL );
1847 if ( stats.getN() > 1 ) {
1848 w.write( "<tr><td>Pearsonian skewness: </td><td>" + stats.pearsonianSkewness() + "</td></tr>" );
1851 w.write( "<tr><td>Pearsonian skewness: </td><td>n/a</td></tr>" );
1853 w.write( SurfacingConstants.NL );
1854 w.write( "</table>" );
1855 w.write( SurfacingConstants.NL );
1857 w.write( SurfacingConstants.NL );
1859 w.write( SurfacingConstants.NL );
1861 w.write( SurfacingConstants.NL );
1862 w.write( "<table>" );
1863 w.write( SurfacingConstants.NL );
1867 for( final Writer w : split_writers.values() ) {
1868 w.write( SurfacingConstants.NL );
1870 for( final DomainSimilarity similarity : similarities ) {
1871 if ( ( species_order != null ) && !species_order.isEmpty() ) {
1872 ( ( PrintableDomainSimilarity ) similarity ).setSpeciesOrder( species_order );
1874 if ( single_writer != null ) {
1875 single_writer.write( similarity.toStringBuffer( print_option, tax_code_to_id_map ).toString() );
1876 single_writer.write( SurfacingConstants.NL );
1879 Writer local_writer = split_writers.get( ( similarity.getDomainId().charAt( 0 ) + "" ).toLowerCase()
1881 if ( local_writer == null ) {
1882 local_writer = split_writers.get( '0' );
1884 local_writer.write( similarity.toStringBuffer( print_option, tax_code_to_id_map ).toString() );
1885 local_writer.write( SurfacingConstants.NL );
1887 // for( final Writer w : split_writers.values() ) {
1888 //w.write( SurfacingConstants.NL );
1891 switch ( print_option ) {
1893 for( final Writer w : split_writers.values() ) {
1894 w.write( SurfacingConstants.NL );
1895 w.write( "</table>" );
1896 w.write( SurfacingConstants.NL );
1897 w.write( "</font>" );
1898 w.write( SurfacingConstants.NL );
1899 w.write( "</body>" );
1900 w.write( SurfacingConstants.NL );
1901 w.write( "</html>" );
1902 w.write( SurfacingConstants.NL );
1906 for( final Writer w : split_writers.values() ) {
1912 public static void writeMatrixToFile( final CharacterStateMatrix<?> matrix,
1913 final String filename,
1914 final Format format ) {
1915 final File outfile = new File( filename );
1916 checkForOutputFileWriteability( outfile );
1918 final BufferedWriter out = new BufferedWriter( new FileWriter( outfile ) );
1919 matrix.toWriter( out, format );
1923 catch ( final IOException e ) {
1924 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1926 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote matrix: \"" + filename + "\"" );
1929 public static void writeMatrixToFile( final File matrix_outfile, final List<DistanceMatrix> matrices ) {
1930 checkForOutputFileWriteability( matrix_outfile );
1932 final BufferedWriter out = new BufferedWriter( new FileWriter( matrix_outfile ) );
1933 for( final DistanceMatrix distance_matrix : matrices ) {
1934 out.write( distance_matrix.toStringBuffer( DistanceMatrix.Format.PHYLIP ).toString() );
1935 out.write( ForesterUtil.LINE_SEPARATOR );
1940 catch ( final IOException e ) {
1941 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1943 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote distance matrices to \"" + matrix_outfile + "\"" );
1946 public static void writePhylogenyToFile( final Phylogeny phylogeny, final String filename ) {
1947 final PhylogenyWriter writer = new PhylogenyWriter();
1949 writer.toPhyloXML( new File( filename ), phylogeny, 1 );
1951 catch ( final IOException e ) {
1952 ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "failed to write phylogeny to \"" + filename + "\": "
1955 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote phylogeny to \"" + filename + "\"" );
1958 public static void writeTaxonomyLinks( final Writer writer,
1959 final String species,
1960 final Map<String, Integer> tax_code_to_id_map ) throws IOException {
1961 if ( ( species.length() > 1 ) && ( species.indexOf( '_' ) < 1 ) ) {
1962 writer.write( " [" );
1963 if ( ( tax_code_to_id_map != null ) && tax_code_to_id_map.containsKey( species ) ) {
1964 writer.write( "<a href=\"" + SurfacingConstants.UNIPROT_TAXONOMY_ID_LINK
1965 + tax_code_to_id_map.get( species ) + "\" target=\"taxonomy_window\">uniprot</a>" );
1968 writer.write( "<a href=\"" + SurfacingConstants.EOL_LINK + species
1969 + "\" target=\"taxonomy_window\">eol</a>" );
1970 writer.write( "|" );
1971 writer.write( "<a href=\"" + SurfacingConstants.GOOGLE_SCHOLAR_SEARCH + species
1972 + "\" target=\"taxonomy_window\">scholar</a>" );
1973 writer.write( "|" );
1974 writer.write( "<a href=\"" + SurfacingConstants.GOOGLE_WEB_SEARCH_LINK + species
1975 + "\" target=\"taxonomy_window\">google</a>" );
1977 writer.write( "]" );
1981 private final static void addToCountMap( final Map<String, Integer> map, final String s ) {
1982 if ( map.containsKey( s ) ) {
1983 map.put( s, map.get( s ) + 1 );
1990 private static void calculateIndependentDomainCombinationGains( final Phylogeny local_phylogeny_l,
1991 final String outfilename_for_counts,
1992 final String outfilename_for_dc,
1993 final String outfilename_for_dc_for_go_mapping,
1994 final String outfilename_for_dc_for_go_mapping_unique,
1995 final String outfilename_for_rank_counts,
1996 final String outfilename_for_ancestor_species_counts,
1997 final String outfilename_for_protein_stats,
1998 final Map<String, DescriptiveStatistics> protein_length_stats_by_dc,
1999 final Map<String, DescriptiveStatistics> domain_number_stats_by_dc,
2000 final Map<String, DescriptiveStatistics> domain_length_stats_by_domain ) {
2003 // if ( protein_length_stats_by_dc != null ) {
2004 // for( final Entry<?, DescriptiveStatistics> entry : protein_length_stats_by_dc.entrySet() ) {
2005 // System.out.print( entry.getKey().toString() );
2006 // System.out.print( ": " );
2007 // double[] a = entry.getValue().getDataAsDoubleArray();
2008 // for( int i = 0; i < a.length; i++ ) {
2009 // System.out.print( a[ i ] + " " );
2011 // System.out.println();
2014 // if ( domain_number_stats_by_dc != null ) {
2015 // for( final Entry<?, DescriptiveStatistics> entry : domain_number_stats_by_dc.entrySet() ) {
2016 // System.out.print( entry.getKey().toString() );
2017 // System.out.print( ": " );
2018 // double[] a = entry.getValue().getDataAsDoubleArray();
2019 // for( int i = 0; i < a.length; i++ ) {
2020 // System.out.print( a[ i ] + " " );
2022 // System.out.println();
2026 final BufferedWriter out_counts = new BufferedWriter( new FileWriter( outfilename_for_counts ) );
2027 final BufferedWriter out_dc = new BufferedWriter( new FileWriter( outfilename_for_dc ) );
2028 final BufferedWriter out_dc_for_go_mapping = new BufferedWriter( new FileWriter( outfilename_for_dc_for_go_mapping ) );
2029 final BufferedWriter out_dc_for_go_mapping_unique = new BufferedWriter( new FileWriter( outfilename_for_dc_for_go_mapping_unique ) );
2030 final SortedMap<String, Integer> dc_gain_counts = new TreeMap<String, Integer>();
2031 for( final PhylogenyNodeIterator it = local_phylogeny_l.iteratorPostorder(); it.hasNext(); ) {
2032 final PhylogenyNode n = it.next();
2033 final Set<String> gained_dc = n.getNodeData().getBinaryCharacters().getGainedCharacters();
2034 for( final String dc : gained_dc ) {
2035 if ( dc_gain_counts.containsKey( dc ) ) {
2036 dc_gain_counts.put( dc, dc_gain_counts.get( dc ) + 1 );
2039 dc_gain_counts.put( dc, 1 );
2043 final SortedMap<Integer, Integer> histogram = new TreeMap<Integer, Integer>();
2044 final SortedMap<Integer, StringBuilder> domain_lists = new TreeMap<Integer, StringBuilder>();
2045 final SortedMap<Integer, DescriptiveStatistics> dc_reapp_counts_to_protein_length_stats = new TreeMap<Integer, DescriptiveStatistics>();
2046 final SortedMap<Integer, DescriptiveStatistics> dc_reapp_counts_to_domain_number_stats = new TreeMap<Integer, DescriptiveStatistics>();
2047 final SortedMap<Integer, DescriptiveStatistics> dc_reapp_counts_to_domain_lengths_stats = new TreeMap<Integer, DescriptiveStatistics>();
2048 final SortedMap<Integer, PriorityQueue<String>> domain_lists_go = new TreeMap<Integer, PriorityQueue<String>>();
2049 final SortedMap<Integer, SortedSet<String>> domain_lists_go_unique = new TreeMap<Integer, SortedSet<String>>();
2050 final Set<String> dcs = dc_gain_counts.keySet();
2051 final SortedSet<String> more_than_once = new TreeSet<String>();
2052 DescriptiveStatistics gained_once_lengths_stats = new BasicDescriptiveStatistics();
2053 DescriptiveStatistics gained_once_domain_count_stats = new BasicDescriptiveStatistics();
2054 DescriptiveStatistics gained_multiple_times_lengths_stats = new BasicDescriptiveStatistics();
2055 final DescriptiveStatistics gained_multiple_times_domain_count_stats = new BasicDescriptiveStatistics();
2056 long gained_multiple_times_domain_length_sum = 0;
2057 long gained_once_domain_length_sum = 0;
2058 long gained_multiple_times_domain_length_count = 0;
2059 long gained_once_domain_length_count = 0;
2060 for( final String dc : dcs ) {
2061 final int count = dc_gain_counts.get( dc );
2062 if ( histogram.containsKey( count ) ) {
2063 histogram.put( count, histogram.get( count ) + 1 );
2064 domain_lists.get( count ).append( ", " + dc );
2065 domain_lists_go.get( count ).addAll( splitDomainCombination( dc ) );
2066 domain_lists_go_unique.get( count ).addAll( splitDomainCombination( dc ) );
2069 histogram.put( count, 1 );
2070 domain_lists.put( count, new StringBuilder( dc ) );
2071 final PriorityQueue<String> q = new PriorityQueue<String>();
2072 q.addAll( splitDomainCombination( dc ) );
2073 domain_lists_go.put( count, q );
2074 final SortedSet<String> set = new TreeSet<String>();
2075 set.addAll( splitDomainCombination( dc ) );
2076 domain_lists_go_unique.put( count, set );
2078 if ( protein_length_stats_by_dc != null ) {
2079 if ( !dc_reapp_counts_to_protein_length_stats.containsKey( count ) ) {
2080 dc_reapp_counts_to_protein_length_stats.put( count, new BasicDescriptiveStatistics() );
2082 dc_reapp_counts_to_protein_length_stats.get( count ).addValue( protein_length_stats_by_dc.get( dc )
2083 .arithmeticMean() );
2085 if ( domain_number_stats_by_dc != null ) {
2086 if ( !dc_reapp_counts_to_domain_number_stats.containsKey( count ) ) {
2087 dc_reapp_counts_to_domain_number_stats.put( count, new BasicDescriptiveStatistics() );
2089 dc_reapp_counts_to_domain_number_stats.get( count ).addValue( domain_number_stats_by_dc.get( dc )
2090 .arithmeticMean() );
2092 if ( domain_length_stats_by_domain != null ) {
2093 if ( !dc_reapp_counts_to_domain_lengths_stats.containsKey( count ) ) {
2094 dc_reapp_counts_to_domain_lengths_stats.put( count, new BasicDescriptiveStatistics() );
2096 final String[] ds = dc.split( "=" );
2097 dc_reapp_counts_to_domain_lengths_stats.get( count ).addValue( domain_length_stats_by_domain
2098 .get( ds[ 0 ] ).arithmeticMean() );
2099 dc_reapp_counts_to_domain_lengths_stats.get( count ).addValue( domain_length_stats_by_domain
2100 .get( ds[ 1 ] ).arithmeticMean() );
2103 more_than_once.add( dc );
2104 if ( protein_length_stats_by_dc != null ) {
2105 final DescriptiveStatistics s = protein_length_stats_by_dc.get( dc );
2106 for( final double element : s.getData() ) {
2107 gained_multiple_times_lengths_stats.addValue( element );
2110 if ( domain_number_stats_by_dc != null ) {
2111 final DescriptiveStatistics s = domain_number_stats_by_dc.get( dc );
2112 for( final double element : s.getData() ) {
2113 gained_multiple_times_domain_count_stats.addValue( element );
2116 if ( domain_length_stats_by_domain != null ) {
2117 final String[] ds = dc.split( "=" );
2118 final DescriptiveStatistics s0 = domain_length_stats_by_domain.get( ds[ 0 ] );
2119 final DescriptiveStatistics s1 = domain_length_stats_by_domain.get( ds[ 1 ] );
2120 for( final double element : s0.getData() ) {
2121 gained_multiple_times_domain_length_sum += element;
2122 ++gained_multiple_times_domain_length_count;
2124 for( final double element : s1.getData() ) {
2125 gained_multiple_times_domain_length_sum += element;
2126 ++gained_multiple_times_domain_length_count;
2131 if ( protein_length_stats_by_dc != null ) {
2132 final DescriptiveStatistics s = protein_length_stats_by_dc.get( dc );
2133 for( final double element : s.getData() ) {
2134 gained_once_lengths_stats.addValue( element );
2137 if ( domain_number_stats_by_dc != null ) {
2138 final DescriptiveStatistics s = domain_number_stats_by_dc.get( dc );
2139 for( final double element : s.getData() ) {
2140 gained_once_domain_count_stats.addValue( element );
2143 if ( domain_length_stats_by_domain != null ) {
2144 final String[] ds = dc.split( "=" );
2145 final DescriptiveStatistics s0 = domain_length_stats_by_domain.get( ds[ 0 ] );
2146 final DescriptiveStatistics s1 = domain_length_stats_by_domain.get( ds[ 1 ] );
2147 for( final double element : s0.getData() ) {
2148 gained_once_domain_length_sum += element;
2149 ++gained_once_domain_length_count;
2151 for( final double element : s1.getData() ) {
2152 gained_once_domain_length_sum += element;
2153 ++gained_once_domain_length_count;
2158 final Set<Integer> histogram_keys = histogram.keySet();
2159 for( final Integer histogram_key : histogram_keys ) {
2160 final int count = histogram.get( histogram_key );
2161 final StringBuilder dc = domain_lists.get( histogram_key );
2162 out_counts.write( histogram_key + "\t" + count + ForesterUtil.LINE_SEPARATOR );
2163 out_dc.write( histogram_key + "\t" + dc + ForesterUtil.LINE_SEPARATOR );
2164 out_dc_for_go_mapping.write( "#" + histogram_key + ForesterUtil.LINE_SEPARATOR );
2165 final Object[] sorted = domain_lists_go.get( histogram_key ).toArray();
2166 Arrays.sort( sorted );
2167 for( final Object domain : sorted ) {
2168 out_dc_for_go_mapping.write( domain + ForesterUtil.LINE_SEPARATOR );
2170 out_dc_for_go_mapping_unique.write( "#" + histogram_key + ForesterUtil.LINE_SEPARATOR );
2171 for( final String domain : domain_lists_go_unique.get( histogram_key ) ) {
2172 out_dc_for_go_mapping_unique.write( domain + ForesterUtil.LINE_SEPARATOR );
2177 out_dc_for_go_mapping.close();
2178 out_dc_for_go_mapping_unique.close();
2179 final SortedMap<String, Integer> lca_rank_counts = new TreeMap<String, Integer>();
2180 final SortedMap<String, Integer> lca_ancestor_species_counts = new TreeMap<String, Integer>();
2181 for( final String dc : more_than_once ) {
2182 final List<PhylogenyNode> nodes = new ArrayList<PhylogenyNode>();
2183 for( final PhylogenyNodeIterator it = local_phylogeny_l.iteratorExternalForward(); it.hasNext(); ) {
2184 final PhylogenyNode n = it.next();
2185 if ( n.getNodeData().getBinaryCharacters().getGainedCharacters().contains( dc ) ) {
2189 for( int i = 0; i < ( nodes.size() - 1 ); ++i ) {
2190 for( int j = i + 1; j < nodes.size(); ++j ) {
2191 final PhylogenyNode lca = PhylogenyMethods.calculateLCA( nodes.get( i ), nodes.get( j ) );
2192 String rank = "unknown";
2193 if ( lca.getNodeData().isHasTaxonomy()
2194 && !ForesterUtil.isEmpty( lca.getNodeData().getTaxonomy().getRank() ) ) {
2195 rank = lca.getNodeData().getTaxonomy().getRank();
2197 addToCountMap( lca_rank_counts, rank );
2199 if ( lca.getNodeData().isHasTaxonomy()
2200 && !ForesterUtil.isEmpty( lca.getNodeData().getTaxonomy().getScientificName() ) ) {
2201 lca_species = lca.getNodeData().getTaxonomy().getScientificName();
2203 else if ( lca.getNodeData().isHasTaxonomy()
2204 && !ForesterUtil.isEmpty( lca.getNodeData().getTaxonomy().getCommonName() ) ) {
2205 lca_species = lca.getNodeData().getTaxonomy().getCommonName();
2208 lca_species = lca.getName();
2210 addToCountMap( lca_ancestor_species_counts, lca_species );
2214 final BufferedWriter out_for_rank_counts = new BufferedWriter( new FileWriter( outfilename_for_rank_counts ) );
2215 final BufferedWriter out_for_ancestor_species_counts = new BufferedWriter( new FileWriter( outfilename_for_ancestor_species_counts ) );
2216 ForesterUtil.map2writer( out_for_rank_counts, lca_rank_counts, "\t", ForesterUtil.LINE_SEPARATOR );
2217 ForesterUtil.map2writer( out_for_ancestor_species_counts,
2218 lca_ancestor_species_counts,
2220 ForesterUtil.LINE_SEPARATOR );
2221 out_for_rank_counts.close();
2222 out_for_ancestor_species_counts.close();
2223 if ( !ForesterUtil.isEmpty( outfilename_for_protein_stats )
2224 && ( ( domain_length_stats_by_domain != null ) || ( protein_length_stats_by_dc != null ) || ( domain_number_stats_by_dc != null ) ) ) {
2225 final BufferedWriter w = new BufferedWriter( new FileWriter( outfilename_for_protein_stats ) );
2226 w.write( "Domain Lengths: " );
2228 if ( domain_length_stats_by_domain != null ) {
2229 for( final Entry<Integer, DescriptiveStatistics> entry : dc_reapp_counts_to_domain_lengths_stats
2231 w.write( entry.getKey().toString() );
2232 w.write( "\t" + entry.getValue().arithmeticMean() );
2233 w.write( "\t" + entry.getValue().median() );
2240 w.write( "Protein Lengths: " );
2242 if ( protein_length_stats_by_dc != null ) {
2243 for( final Entry<Integer, DescriptiveStatistics> entry : dc_reapp_counts_to_protein_length_stats
2245 w.write( entry.getKey().toString() );
2246 w.write( "\t" + entry.getValue().arithmeticMean() );
2247 w.write( "\t" + entry.getValue().median() );
2254 w.write( "Number of domains: " );
2256 if ( domain_number_stats_by_dc != null ) {
2257 for( final Entry<Integer, DescriptiveStatistics> entry : dc_reapp_counts_to_domain_number_stats
2259 w.write( entry.getKey().toString() );
2260 w.write( "\t" + entry.getValue().arithmeticMean() );
2261 w.write( "\t" + entry.getValue().median() );
2268 w.write( "Gained once, domain lengths:" );
2270 w.write( "N: " + gained_once_domain_length_count );
2272 w.write( "Avg: " + ( ( double ) gained_once_domain_length_sum / gained_once_domain_length_count ) );
2275 w.write( "Gained multiple times, domain lengths:" );
2277 w.write( "N: " + gained_multiple_times_domain_length_count );
2280 + ( ( double ) gained_multiple_times_domain_length_sum / gained_multiple_times_domain_length_count ) );
2285 w.write( "Gained once, protein lengths:" );
2287 w.write( gained_once_lengths_stats.toString() );
2288 gained_once_lengths_stats = null;
2291 w.write( "Gained once, domain counts:" );
2293 w.write( gained_once_domain_count_stats.toString() );
2294 gained_once_domain_count_stats = null;
2297 w.write( "Gained multiple times, protein lengths:" );
2299 w.write( gained_multiple_times_lengths_stats.toString() );
2300 gained_multiple_times_lengths_stats = null;
2303 w.write( "Gained multiple times, domain counts:" );
2305 w.write( gained_multiple_times_domain_count_stats.toString() );
2310 catch ( final IOException e ) {
2311 ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "Failure to write: " + e );
2313 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote independent domain combination gains fitch counts to ["
2314 + outfilename_for_counts + "]" );
2315 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote independent domain combination gains fitch lists to ["
2316 + outfilename_for_dc + "]" );
2317 ForesterUtil.programMessage( surfacing.PRG_NAME,
2318 "Wrote independent domain combination gains fitch lists to (for GO mapping) ["
2319 + outfilename_for_dc_for_go_mapping + "]" );
2320 ForesterUtil.programMessage( surfacing.PRG_NAME,
2321 "Wrote independent domain combination gains fitch lists to (for GO mapping, unique) ["
2322 + outfilename_for_dc_for_go_mapping_unique + "]" );
2325 private static SortedSet<String> collectAllDomainsChangedOnSubtree( final PhylogenyNode subtree_root,
2326 final boolean get_gains ) {
2327 final SortedSet<String> domains = new TreeSet<String>();
2328 for( final PhylogenyNode descendant : PhylogenyMethods.getAllDescendants( subtree_root ) ) {
2329 final BinaryCharacters chars = descendant.getNodeData().getBinaryCharacters();
2331 domains.addAll( chars.getGainedCharacters() );
2334 domains.addAll( chars.getLostCharacters() );
2340 private static File createBaseDirForPerNodeDomainFiles( final String base_dir,
2341 final boolean domain_combinations,
2342 final CharacterStateMatrix.GainLossStates state,
2343 final String outfile ) {
2344 File per_node_go_mapped_domain_gain_loss_files_base_dir = new File( new File( outfile ).getParent()
2345 + ForesterUtil.FILE_SEPARATOR + base_dir );
2346 if ( !per_node_go_mapped_domain_gain_loss_files_base_dir.exists() ) {
2347 per_node_go_mapped_domain_gain_loss_files_base_dir.mkdir();
2349 if ( domain_combinations ) {
2350 per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
2351 + ForesterUtil.FILE_SEPARATOR + "DC" );
2354 per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
2355 + ForesterUtil.FILE_SEPARATOR + "DOMAINS" );
2357 if ( !per_node_go_mapped_domain_gain_loss_files_base_dir.exists() ) {
2358 per_node_go_mapped_domain_gain_loss_files_base_dir.mkdir();
2360 if ( state == GainLossStates.GAIN ) {
2361 per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
2362 + ForesterUtil.FILE_SEPARATOR + "GAINS" );
2364 else if ( state == GainLossStates.LOSS ) {
2365 per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
2366 + ForesterUtil.FILE_SEPARATOR + "LOSSES" );
2369 per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
2370 + ForesterUtil.FILE_SEPARATOR + "PRESENT" );
2372 if ( !per_node_go_mapped_domain_gain_loss_files_base_dir.exists() ) {
2373 per_node_go_mapped_domain_gain_loss_files_base_dir.mkdir();
2375 return per_node_go_mapped_domain_gain_loss_files_base_dir;
2378 private static SortedSet<BinaryDomainCombination> createSetOfAllBinaryDomainCombinationsPerGenome( final GenomeWideCombinableDomains gwcd ) {
2379 final SortedMap<String, CombinableDomains> cds = gwcd.getAllCombinableDomainsIds();
2380 final SortedSet<BinaryDomainCombination> binary_combinations = new TreeSet<BinaryDomainCombination>();
2381 for( final String domain_id : cds.keySet() ) {
2382 final CombinableDomains cd = cds.get( domain_id );
2383 binary_combinations.addAll( cd.toBinaryDomainCombinations() );
2385 return binary_combinations;
2388 private static List<String> splitDomainCombination( final String dc ) {
2389 final String[] s = dc.split( "=" );
2390 if ( s.length != 2 ) {
2391 ForesterUtil.printErrorMessage( surfacing.PRG_NAME, "Stringyfied domain combination has illegal format: "
2395 final List<String> l = new ArrayList<String>( 2 );
2401 private static void writeAllEncounteredPfamsToFile( final Map<String, List<GoId>> domain_id_to_go_ids_map,
2402 final Map<GoId, GoTerm> go_id_to_term_map,
2403 final String outfile_name,
2404 final SortedSet<String> all_pfams_encountered ) {
2405 final File all_pfams_encountered_file = new File( outfile_name + surfacing.ALL_PFAMS_ENCOUNTERED_SUFFIX );
2406 final File all_pfams_encountered_with_go_annotation_file = new File( outfile_name
2407 + surfacing.ALL_PFAMS_ENCOUNTERED_WITH_GO_ANNOTATION_SUFFIX );
2408 final File encountered_pfams_summary_file = new File( outfile_name + surfacing.ENCOUNTERED_PFAMS_SUMMARY_SUFFIX );
2409 int biological_process_counter = 0;
2410 int cellular_component_counter = 0;
2411 int molecular_function_counter = 0;
2412 int pfams_with_mappings_counter = 0;
2413 int pfams_without_mappings_counter = 0;
2414 int pfams_without_mappings_to_bp_or_mf_counter = 0;
2415 int pfams_with_mappings_to_bp_or_mf_counter = 0;
2417 final Writer all_pfams_encountered_writer = new BufferedWriter( new FileWriter( all_pfams_encountered_file ) );
2418 final Writer all_pfams_encountered_with_go_annotation_writer = new BufferedWriter( new FileWriter( all_pfams_encountered_with_go_annotation_file ) );
2419 final Writer summary_writer = new BufferedWriter( new FileWriter( encountered_pfams_summary_file ) );
2420 summary_writer.write( "# Pfam to GO mapping summary" );
2421 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
2422 summary_writer.write( "# Actual summary is at the end of this file." );
2423 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
2424 summary_writer.write( "# Encountered Pfams without a GO mapping:" );
2425 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
2426 for( final String pfam : all_pfams_encountered ) {
2427 all_pfams_encountered_writer.write( pfam );
2428 all_pfams_encountered_writer.write( ForesterUtil.LINE_SEPARATOR );
2429 final String domain_id = new String( pfam );
2430 if ( domain_id_to_go_ids_map.containsKey( domain_id ) ) {
2431 ++pfams_with_mappings_counter;
2432 all_pfams_encountered_with_go_annotation_writer.write( pfam );
2433 all_pfams_encountered_with_go_annotation_writer.write( ForesterUtil.LINE_SEPARATOR );
2434 final List<GoId> go_ids = domain_id_to_go_ids_map.get( domain_id );
2435 boolean maps_to_bp = false;
2436 boolean maps_to_cc = false;
2437 boolean maps_to_mf = false;
2438 for( final GoId go_id : go_ids ) {
2439 final GoTerm go_term = go_id_to_term_map.get( go_id );
2440 if ( go_term.getGoNameSpace().isBiologicalProcess() ) {
2443 else if ( go_term.getGoNameSpace().isCellularComponent() ) {
2446 else if ( go_term.getGoNameSpace().isMolecularFunction() ) {
2451 ++biological_process_counter;
2454 ++cellular_component_counter;
2457 ++molecular_function_counter;
2459 if ( maps_to_bp || maps_to_mf ) {
2460 ++pfams_with_mappings_to_bp_or_mf_counter;
2463 ++pfams_without_mappings_to_bp_or_mf_counter;
2467 ++pfams_without_mappings_to_bp_or_mf_counter;
2468 ++pfams_without_mappings_counter;
2469 summary_writer.write( pfam );
2470 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
2473 all_pfams_encountered_writer.close();
2474 all_pfams_encountered_with_go_annotation_writer.close();
2475 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote all [" + all_pfams_encountered.size()
2476 + "] encountered Pfams to: \"" + all_pfams_encountered_file + "\"" );
2477 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote all [" + pfams_with_mappings_counter
2478 + "] encountered Pfams with GO mappings to: \"" + all_pfams_encountered_with_go_annotation_file
2480 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote summary (including all ["
2481 + pfams_without_mappings_counter + "] encountered Pfams without GO mappings) to: \""
2482 + encountered_pfams_summary_file + "\"" );
2483 ForesterUtil.programMessage( surfacing.PRG_NAME, "Sum of Pfams encountered : "
2484 + all_pfams_encountered.size() );
2485 ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams without a mapping : "
2486 + pfams_without_mappings_counter + " ["
2487 + ( ( 100 * pfams_without_mappings_counter ) / all_pfams_encountered.size() ) + "%]" );
2488 ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams without mapping to proc. or func. : "
2489 + pfams_without_mappings_to_bp_or_mf_counter + " ["
2490 + ( ( 100 * pfams_without_mappings_to_bp_or_mf_counter ) / all_pfams_encountered.size() ) + "%]" );
2491 ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams with a mapping : "
2492 + pfams_with_mappings_counter + " ["
2493 + ( ( 100 * pfams_with_mappings_counter ) / all_pfams_encountered.size() ) + "%]" );
2494 ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams with a mapping to proc. or func. : "
2495 + pfams_with_mappings_to_bp_or_mf_counter + " ["
2496 + ( ( 100 * pfams_with_mappings_to_bp_or_mf_counter ) / all_pfams_encountered.size() ) + "%]" );
2497 ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams with mapping to biological process: "
2498 + biological_process_counter + " ["
2499 + ( ( 100 * biological_process_counter ) / all_pfams_encountered.size() ) + "%]" );
2500 ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams with mapping to molecular function: "
2501 + molecular_function_counter + " ["
2502 + ( ( 100 * molecular_function_counter ) / all_pfams_encountered.size() ) + "%]" );
2503 ForesterUtil.programMessage( surfacing.PRG_NAME, "Pfams with mapping to cellular component: "
2504 + cellular_component_counter + " ["
2505 + ( ( 100 * cellular_component_counter ) / all_pfams_encountered.size() ) + "%]" );
2506 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
2507 summary_writer.write( "# Sum of Pfams encountered : " + all_pfams_encountered.size() );
2508 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
2509 summary_writer.write( "# Pfams without a mapping : " + pfams_without_mappings_counter
2510 + " [" + ( ( 100 * pfams_without_mappings_counter ) / all_pfams_encountered.size() ) + "%]" );
2511 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
2512 summary_writer.write( "# Pfams without mapping to proc. or func. : "
2513 + pfams_without_mappings_to_bp_or_mf_counter + " ["
2514 + ( ( 100 * pfams_without_mappings_to_bp_or_mf_counter ) / all_pfams_encountered.size() ) + "%]" );
2515 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
2516 summary_writer.write( "# Pfams with a mapping : " + pfams_with_mappings_counter + " ["
2517 + ( ( 100 * pfams_with_mappings_counter ) / all_pfams_encountered.size() ) + "%]" );
2518 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
2519 summary_writer.write( "# Pfams with a mapping to proc. or func. : "
2520 + pfams_with_mappings_to_bp_or_mf_counter + " ["
2521 + ( ( 100 * pfams_with_mappings_to_bp_or_mf_counter ) / all_pfams_encountered.size() ) + "%]" );
2522 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
2523 summary_writer.write( "# Pfams with mapping to biological process: " + biological_process_counter + " ["
2524 + ( ( 100 * biological_process_counter ) / all_pfams_encountered.size() ) + "%]" );
2525 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
2526 summary_writer.write( "# Pfams with mapping to molecular function: " + molecular_function_counter + " ["
2527 + ( ( 100 * molecular_function_counter ) / all_pfams_encountered.size() ) + "%]" );
2528 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
2529 summary_writer.write( "# Pfams with mapping to cellular component: " + cellular_component_counter + " ["
2530 + ( ( 100 * cellular_component_counter ) / all_pfams_encountered.size() ) + "%]" );
2531 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
2532 summary_writer.close();
2534 catch ( final IOException e ) {
2535 ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "Failure to write: " + e );
2539 private static void writeDomainData( final Map<String, List<GoId>> domain_id_to_go_ids_map,
2540 final Map<GoId, GoTerm> go_id_to_term_map,
2541 final GoNameSpace go_namespace_limit,
2543 final String domain_0,
2544 final String domain_1,
2545 final String prefix_for_html,
2546 final String character_separator_for_non_html_output,
2547 final Map<String, Set<String>>[] domain_id_to_secondary_features_maps,
2548 final Set<GoId> all_go_ids ) throws IOException {
2549 boolean any_go_annotation_present = false;
2550 boolean first_has_no_go = false;
2551 int domain_count = 2; // To distinguish between domains and binary domain combinations.
2552 if ( ForesterUtil.isEmpty( domain_1 ) ) {
2555 // The following has a difficult to understand logic.
2556 for( int d = 0; d < domain_count; ++d ) {
2557 List<GoId> go_ids = null;
2558 boolean go_annotation_present = false;
2560 if ( domain_id_to_go_ids_map.containsKey( domain_0 ) ) {
2561 go_annotation_present = true;
2562 any_go_annotation_present = true;
2563 go_ids = domain_id_to_go_ids_map.get( domain_0 );
2566 first_has_no_go = true;
2570 if ( domain_id_to_go_ids_map.containsKey( domain_1 ) ) {
2571 go_annotation_present = true;
2572 any_go_annotation_present = true;
2573 go_ids = domain_id_to_go_ids_map.get( domain_1 );
2576 if ( go_annotation_present ) {
2577 boolean first = ( ( d == 0 ) || ( ( d == 1 ) && first_has_no_go ) );
2578 for( final GoId go_id : go_ids ) {
2579 out.write( "<tr>" );
2582 writeDomainIdsToHtml( out,
2586 domain_id_to_secondary_features_maps );
2589 out.write( "<td></td>" );
2591 if ( !go_id_to_term_map.containsKey( go_id ) ) {
2592 throw new IllegalArgumentException( "GO-id [" + go_id + "] not found in GO-id to GO-term map" );
2594 final GoTerm go_term = go_id_to_term_map.get( go_id );
2595 if ( ( go_namespace_limit == null ) || go_namespace_limit.equals( go_term.getGoNameSpace() ) ) {
2596 // final String top = GoUtils.getPenultimateGoTerm( go_term, go_id_to_term_map ).getName();
2597 final String go_id_str = go_id.getId();
2598 out.write( "<td>" );
2599 out.write( "<a href=\"" + SurfacingConstants.AMIGO_LINK + go_id_str
2600 + "\" target=\"amigo_window\">" + go_id_str + "</a>" );
2601 out.write( "</td><td>" );
2602 out.write( go_term.getName() );
2603 if ( domain_count == 2 ) {
2604 out.write( " (" + d + ")" );
2606 out.write( "</td><td>" );
2607 // out.write( top );
2608 // out.write( "</td><td>" );
2610 out.write( go_term.getGoNameSpace().toShortString() );
2612 out.write( "</td>" );
2613 if ( all_go_ids != null ) {
2614 all_go_ids.add( go_id );
2618 out.write( "<td>" );
2619 out.write( "</td><td>" );
2620 out.write( "</td><td>" );
2621 out.write( "</td><td>" );
2622 out.write( "</td>" );
2624 out.write( "</tr>" );
2625 out.write( SurfacingConstants.NL );
2628 } // for( int d = 0; d < domain_count; ++d )
2629 if ( !any_go_annotation_present ) {
2630 out.write( "<tr>" );
2631 writeDomainIdsToHtml( out, domain_0, domain_1, prefix_for_html, domain_id_to_secondary_features_maps );
2632 out.write( "<td>" );
2633 out.write( "</td><td>" );
2634 out.write( "</td><td>" );
2635 out.write( "</td><td>" );
2636 out.write( "</td>" );
2637 out.write( "</tr>" );
2638 out.write( SurfacingConstants.NL );
2642 private static void writeDomainIdsToHtml( final Writer out,
2643 final String domain_0,
2644 final String domain_1,
2645 final String prefix_for_detailed_html,
2646 final Map<String, Set<String>>[] domain_id_to_secondary_features_maps )
2647 throws IOException {
2648 out.write( "<td>" );
2649 if ( !ForesterUtil.isEmpty( prefix_for_detailed_html ) ) {
2650 out.write( prefix_for_detailed_html );
2653 out.write( "<a href=\"" + SurfacingConstants.PFAM_FAMILY_ID_LINK + domain_0 + "\">" + domain_0 + "</a>" );
2654 out.write( "</td>" );
2657 private static void writeDomainsToIndividualFilePerTreeNode( final Writer individual_files_writer,
2658 final String domain_0,
2659 final String domain_1 ) throws IOException {
2660 individual_files_writer.write( domain_0 );
2661 individual_files_writer.write( ForesterUtil.LINE_SEPARATOR );
2662 if ( !ForesterUtil.isEmpty( domain_1 ) ) {
2663 individual_files_writer.write( domain_1 );
2664 individual_files_writer.write( ForesterUtil.LINE_SEPARATOR );
2668 private static void writePfamsToFile( final String outfile_name, final SortedSet<String> pfams ) {
2670 final Writer writer = new BufferedWriter( new FileWriter( new File( outfile_name ) ) );
2671 for( final String pfam : pfams ) {
2672 writer.write( pfam );
2673 writer.write( ForesterUtil.LINE_SEPARATOR );
2676 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote " + pfams.size() + " pfams to [" + outfile_name
2679 catch ( final IOException e ) {
2680 ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "Failure to write: " + e );
2684 private static void writeToNexus( final String outfile_name,
2685 final CharacterStateMatrix<BinaryStates> matrix,
2686 final Phylogeny phylogeny ) {
2687 if ( !( matrix instanceof BasicCharacterStateMatrix ) ) {
2688 throw new IllegalArgumentException( "can only write matrices of type [" + BasicCharacterStateMatrix.class
2691 final BasicCharacterStateMatrix<BinaryStates> my_matrix = ( org.forester.evoinference.matrix.character.BasicCharacterStateMatrix<BinaryStates> ) matrix;
2692 final List<Phylogeny> phylogenies = new ArrayList<Phylogeny>( 1 );
2693 phylogenies.add( phylogeny );
2695 final BufferedWriter w = new BufferedWriter( new FileWriter( outfile_name ) );
2696 w.write( NexusConstants.NEXUS );
2697 w.write( ForesterUtil.LINE_SEPARATOR );
2698 my_matrix.writeNexusTaxaBlock( w );
2699 my_matrix.writeNexusBinaryChractersBlock( w );
2700 PhylogenyWriter.writeNexusTreesBlock( w, phylogenies, NH_CONVERSION_SUPPORT_VALUE_STYLE.NONE );
2703 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote Nexus file: \"" + outfile_name + "\"" );
2705 catch ( final IOException e ) {
2706 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2710 private static void writeToNexus( final String outfile_name,
2711 final DomainParsimonyCalculator domain_parsimony,
2712 final Phylogeny phylogeny ) {
2713 writeToNexus( outfile_name + surfacing.NEXUS_EXTERNAL_DOMAINS,
2714 domain_parsimony.createMatrixOfDomainPresenceOrAbsence(),
2716 writeToNexus( outfile_name + surfacing.NEXUS_EXTERNAL_DOMAIN_COMBINATIONS,
2717 domain_parsimony.createMatrixOfBinaryDomainCombinationPresenceOrAbsence(),
2721 final static class DomainComparator implements Comparator<Domain> {
2723 final private boolean _ascending;
2725 public DomainComparator( final boolean ascending ) {
2726 _ascending = ascending;
2730 public final int compare( final Domain d0, final Domain d1 ) {
2731 if ( d0.getFrom() < d1.getFrom() ) {
2732 return _ascending ? -1 : 1;
2734 else if ( d0.getFrom() > d1.getFrom() ) {
2735 return _ascending ? 1 : -1;