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: www.phylosoft.org/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.Collections;
38 import java.util.Comparator;
39 import java.util.HashMap;
40 import java.util.HashSet;
41 import java.util.List;
44 import java.util.SortedMap;
45 import java.util.SortedSet;
46 import java.util.TreeMap;
47 import java.util.TreeSet;
48 import java.util.regex.Matcher;
49 import java.util.regex.Pattern;
51 import org.forester.application.surfacing_old;
52 import org.forester.evoinference.distance.NeighborJoining;
53 import org.forester.evoinference.matrix.character.BasicCharacterStateMatrix;
54 import org.forester.evoinference.matrix.character.CharacterStateMatrix;
55 import org.forester.evoinference.matrix.character.CharacterStateMatrix.BinaryStates;
56 import org.forester.evoinference.matrix.character.CharacterStateMatrix.Format;
57 import org.forester.evoinference.matrix.character.CharacterStateMatrix.GainLossStates;
58 import org.forester.evoinference.matrix.distance.DistanceMatrix;
59 import org.forester.go.GoId;
60 import org.forester.go.GoNameSpace;
61 import org.forester.go.GoTerm;
62 import org.forester.go.GoUtils;
63 import org.forester.go.PfamToGoMapping;
64 import org.forester.io.parsers.nexus.NexusConstants;
65 import org.forester.io.writers.PhylogenyWriter;
66 import org.forester.phylogeny.Phylogeny;
67 import org.forester.phylogeny.PhylogenyMethods;
68 import org.forester.phylogeny.PhylogenyNode;
69 import org.forester.phylogeny.data.BinaryCharacters;
70 import org.forester.phylogeny.data.Confidence;
71 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
72 import org.forester.surfacing.DomainSimilarityCalculator.Detailedness;
73 import org.forester.surfacing.DomainSimilarityCalculator.GoAnnotationOutput;
74 import org.forester.surfacing.GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder;
75 import org.forester.util.AsciiHistogram;
76 import org.forester.util.BasicDescriptiveStatistics;
77 import org.forester.util.BasicTable;
78 import org.forester.util.BasicTableParser;
79 import org.forester.util.DescriptiveStatistics;
80 import org.forester.util.ForesterUtil;
82 public final class SurfacingUtil {
84 private final static NumberFormat FORMATTER = new DecimalFormat( "0.0E0" );
85 private final static NumberFormat FORMATTER_3 = new DecimalFormat( "0.000" );
86 private static final Comparator<Domain> ASCENDING_CONFIDENCE_VALUE_ORDER = new Comparator<Domain>() {
88 public int compare( final Domain d1,
90 if ( d1.getPerSequenceEvalue() < d2
91 .getPerSequenceEvalue() ) {
95 .getPerSequenceEvalue() > d2
96 .getPerSequenceEvalue() ) {
100 return d1.compareTo( d2 );
104 public final static Pattern PATTERN_SP_STYLE_TAXONOMY = Pattern.compile( "^[A-Z0-9]{3,5}$" );
106 private SurfacingUtil() {
107 // Hidden constructor.
110 public static void addAllBinaryDomainCombinationToSet( final GenomeWideCombinableDomains genome,
111 final SortedSet<BinaryDomainCombination> binary_domain_combinations ) {
112 final SortedMap<DomainId, CombinableDomains> all_cd = genome.getAllCombinableDomainsIds();
113 for( final DomainId domain_id : all_cd.keySet() ) {
114 binary_domain_combinations.addAll( all_cd.get( domain_id ).toBinaryDomainCombinations() );
118 public static void addAllDomainIdsToSet( final GenomeWideCombinableDomains genome,
119 final SortedSet<DomainId> domain_ids ) {
120 final SortedSet<DomainId> domains = genome.getAllDomainIds();
121 for( final DomainId domain : domains ) {
122 domain_ids.add( domain );
126 public static void addHtmlHead( final Writer w, final String title ) throws IOException {
127 w.write( SurfacingConstants.NL );
129 w.write( "<title>" );
131 w.write( "</title>" );
132 w.write( SurfacingConstants.NL );
133 w.write( "<style>" );
134 w.write( SurfacingConstants.NL );
135 w.write( "a:visited { color : #6633FF; text-decoration : none; }" );
136 w.write( SurfacingConstants.NL );
137 w.write( "a:link { color : #6633FF; text-decoration : none; }" );
138 w.write( SurfacingConstants.NL );
139 w.write( "a:active { color : #99FF00; text-decoration : none; }" );
140 w.write( SurfacingConstants.NL );
141 w.write( "a:hover { color : #FFFFFF; background-color : #99FF00; text-decoration : none; }" );
142 w.write( SurfacingConstants.NL );
143 w.write( "td { text-align: left; vertical-align: top; font-family: Verdana, Arial, Helvetica; font-size: 8pt}" );
144 w.write( SurfacingConstants.NL );
145 w.write( "h1 { color : #0000FF; font-family: Verdana, Arial, Helvetica; font-size: 18pt; font-weight: bold }" );
146 w.write( SurfacingConstants.NL );
147 w.write( "h2 { color : #0000FF; font-family: Verdana, Arial, Helvetica; font-size: 16pt; font-weight: bold }" );
148 w.write( SurfacingConstants.NL );
149 w.write( "</style>" );
150 w.write( SurfacingConstants.NL );
151 w.write( "</head>" );
152 w.write( SurfacingConstants.NL );
155 public static DescriptiveStatistics calculateDescriptiveStatisticsForMeanValues( final Set<DomainSimilarity> similarities ) {
156 final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
157 for( final DomainSimilarity similarity : similarities ) {
158 stats.addValue( similarity.getMeanSimilarityScore() );
163 public static int calculateOverlap( final Domain domain, final List<Boolean> covered_positions ) {
164 int overlap_count = 0;
165 for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) {
166 if ( ( i < covered_positions.size() ) && ( covered_positions.get( i ) == true ) ) {
170 return overlap_count;
173 public static void checkForOutputFileWriteability( final File outfile ) {
174 final String error = ForesterUtil.isWritableFile( outfile );
175 if ( !ForesterUtil.isEmpty( error ) ) {
176 ForesterUtil.fatalError( surfacing_old.PRG_NAME, error );
180 private static SortedSet<String> collectAllDomainsChangedOnSubtree( final PhylogenyNode subtree_root,
181 final boolean get_gains ) {
182 final SortedSet<String> domains = new TreeSet<String>();
183 for( final PhylogenyNode descendant : PhylogenyMethods.getAllDescendants( subtree_root ) ) {
184 final BinaryCharacters chars = descendant.getNodeData().getBinaryCharacters();
186 domains.addAll( chars.getGainedCharacters() );
189 domains.addAll( chars.getLostCharacters() );
195 public static void collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile( final CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
196 final BinaryDomainCombination.DomainCombinationType dc_type,
197 final List<BinaryDomainCombination> all_binary_domains_combination_gained,
198 final boolean get_gains ) {
199 final SortedSet<String> sorted_ids = new TreeSet<String>();
200 for( int i = 0; i < matrix.getNumberOfIdentifiers(); ++i ) {
201 sorted_ids.add( matrix.getIdentifier( i ) );
203 for( final String id : sorted_ids ) {
204 for( int c = 0; c < matrix.getNumberOfCharacters(); ++c ) {
205 if ( ( get_gains && ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.GAIN ) )
206 || ( !get_gains && ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.LOSS ) ) ) {
207 if ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) {
208 all_binary_domains_combination_gained.add( AdjactantDirectedBinaryDomainCombination
209 .createInstance( matrix.getCharacter( c ) ) );
211 else if ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED ) {
212 all_binary_domains_combination_gained.add( DirectedBinaryDomainCombination
213 .createInstance( matrix.getCharacter( c ) ) );
216 all_binary_domains_combination_gained.add( BasicBinaryDomainCombination.createInstance( matrix
217 .getCharacter( c ) ) );
224 private static File createBaseDirForPerNodeDomainFiles( final String base_dir,
225 final boolean domain_combinations,
226 final CharacterStateMatrix.GainLossStates state,
227 final String outfile ) {
228 File per_node_go_mapped_domain_gain_loss_files_base_dir = new File( new File( outfile ).getParent()
229 + ForesterUtil.FILE_SEPARATOR + base_dir );
230 if ( !per_node_go_mapped_domain_gain_loss_files_base_dir.exists() ) {
231 per_node_go_mapped_domain_gain_loss_files_base_dir.mkdir();
233 if ( domain_combinations ) {
234 per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
235 + ForesterUtil.FILE_SEPARATOR + "DC" );
238 per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
239 + ForesterUtil.FILE_SEPARATOR + "DOMAINS" );
241 if ( !per_node_go_mapped_domain_gain_loss_files_base_dir.exists() ) {
242 per_node_go_mapped_domain_gain_loss_files_base_dir.mkdir();
244 if ( state == GainLossStates.GAIN ) {
245 per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
246 + ForesterUtil.FILE_SEPARATOR + "GAINS" );
248 else if ( state == GainLossStates.LOSS ) {
249 per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
250 + ForesterUtil.FILE_SEPARATOR + "LOSSES" );
253 per_node_go_mapped_domain_gain_loss_files_base_dir = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
254 + ForesterUtil.FILE_SEPARATOR + "PRESENT" );
256 if ( !per_node_go_mapped_domain_gain_loss_files_base_dir.exists() ) {
257 per_node_go_mapped_domain_gain_loss_files_base_dir.mkdir();
259 return per_node_go_mapped_domain_gain_loss_files_base_dir;
262 public static Map<DomainId, List<GoId>> createDomainIdToGoIdMap( final List<PfamToGoMapping> pfam_to_go_mappings ) {
263 final Map<DomainId, List<GoId>> domain_id_to_go_ids_map = new HashMap<DomainId, List<GoId>>( pfam_to_go_mappings
265 for( final PfamToGoMapping pfam_to_go : pfam_to_go_mappings ) {
266 if ( !domain_id_to_go_ids_map.containsKey( pfam_to_go.getKey() ) ) {
267 domain_id_to_go_ids_map.put( pfam_to_go.getKey(), new ArrayList<GoId>() );
269 domain_id_to_go_ids_map.get( pfam_to_go.getKey() ).add( pfam_to_go.getValue() );
271 return domain_id_to_go_ids_map;
274 public static Map<DomainId, Set<String>> createDomainIdToSecondaryFeaturesMap( final File secondary_features_map_file )
276 final BasicTable<String> primary_table = BasicTableParser.parse( secondary_features_map_file, "\t" );
277 final Map<DomainId, Set<String>> map = new TreeMap<DomainId, Set<String>>();
278 for( int r = 0; r < primary_table.getNumberOfRows(); ++r ) {
279 final DomainId domain_id = new DomainId( primary_table.getValue( 0, r ) );
280 if ( !map.containsKey( domain_id ) ) {
281 map.put( domain_id, new HashSet<String>() );
283 map.get( domain_id ).add( primary_table.getValue( 1, r ) );
288 public static Phylogeny createNjTreeBasedOnMatrixToFile( final File nj_tree_outfile, final DistanceMatrix distance ) {
289 checkForOutputFileWriteability( nj_tree_outfile );
290 final NeighborJoining nj = NeighborJoining.createInstance();
291 final Phylogeny phylogeny = nj.execute( distance );
292 phylogeny.setName( nj_tree_outfile.getName() );
293 writePhylogenyToFile( phylogeny, nj_tree_outfile.toString() );
297 private static SortedSet<BinaryDomainCombination> createSetOfAllBinaryDomainCombinationsPerGenome( final GenomeWideCombinableDomains gwcd ) {
298 final SortedMap<DomainId, CombinableDomains> cds = gwcd.getAllCombinableDomainsIds();
299 final SortedSet<BinaryDomainCombination> binary_combinations = new TreeSet<BinaryDomainCombination>();
300 for( final DomainId domain_id : cds.keySet() ) {
301 final CombinableDomains cd = cds.get( domain_id );
302 binary_combinations.addAll( cd.toBinaryDomainCombinations() );
304 return binary_combinations;
307 public static void decoratePrintableDomainSimilarities( final SortedSet<DomainSimilarity> domain_similarities,
308 final Detailedness detailedness,
309 final GoAnnotationOutput go_annotation_output,
310 final Map<GoId, GoTerm> go_id_to_term_map,
311 final GoNameSpace go_namespace_limit ) {
312 if ( ( go_namespace_limit != null ) && ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) ) {
313 throw new IllegalArgumentException( "attempt to use a GO namespace limit without a GO id to term map" );
315 for( final DomainSimilarity domain_similarity : domain_similarities ) {
316 if ( domain_similarity instanceof PrintableDomainSimilarity ) {
317 final PrintableDomainSimilarity printable_domain_similarity = ( PrintableDomainSimilarity ) domain_similarity;
318 printable_domain_similarity.setDetailedness( detailedness );
319 printable_domain_similarity.setGoAnnotationOutput( go_annotation_output );
320 printable_domain_similarity.setGoIdToTermMap( go_id_to_term_map );
321 printable_domain_similarity.setGoNamespaceLimit( go_namespace_limit );
326 public static void executeDomainLengthAnalysis( final String[][] input_file_properties,
327 final int number_of_genomes,
328 final DomainLengthsTable domain_lengths_table,
329 final File outfile ) throws IOException {
330 final DecimalFormat df = new DecimalFormat( "#.00" );
331 checkForOutputFileWriteability( outfile );
332 final BufferedWriter out = new BufferedWriter( new FileWriter( outfile ) );
333 out.write( "MEAN BASED STATISTICS PER SPECIES" );
334 out.write( ForesterUtil.LINE_SEPARATOR );
335 out.write( domain_lengths_table.createMeanBasedStatisticsPerSpeciesTable().toString() );
336 out.write( ForesterUtil.LINE_SEPARATOR );
337 out.write( ForesterUtil.LINE_SEPARATOR );
338 final List<DomainLengths> domain_lengths_list = domain_lengths_table.getDomainLengthsList();
339 out.write( "OUTLIER SPECIES PER DOMAIN (Z>=1.5)" );
340 out.write( ForesterUtil.LINE_SEPARATOR );
341 for( final DomainLengths domain_lengths : domain_lengths_list ) {
342 final List<Species> species_list = domain_lengths.getMeanBasedOutlierSpecies( 1.5 );
343 if ( species_list.size() > 0 ) {
344 out.write( domain_lengths.getDomainId() + "\t" );
345 for( final Species species : species_list ) {
346 out.write( species + "\t" );
348 out.write( ForesterUtil.LINE_SEPARATOR );
349 // DescriptiveStatistics stats_for_domain = domain_lengths
350 // .calculateMeanBasedStatistics();
351 //AsciiHistogram histo = new AsciiHistogram( stats_for_domain );
352 //System.out.println( histo.toStringBuffer( 40, '=', 60, 4 ).toString() );
355 out.write( ForesterUtil.LINE_SEPARATOR );
356 out.write( ForesterUtil.LINE_SEPARATOR );
357 out.write( "OUTLIER SPECIES (Z 1.0)" );
358 out.write( ForesterUtil.LINE_SEPARATOR );
359 final DescriptiveStatistics stats_for_all_species = domain_lengths_table
360 .calculateMeanBasedStatisticsForAllSpecies();
361 out.write( stats_for_all_species.asSummary() );
362 out.write( ForesterUtil.LINE_SEPARATOR );
363 final AsciiHistogram histo = new AsciiHistogram( stats_for_all_species );
364 out.write( histo.toStringBuffer( 40, '=', 60, 4 ).toString() );
365 out.write( ForesterUtil.LINE_SEPARATOR );
366 final double population_sd = stats_for_all_species.sampleStandardDeviation();
367 final double population_mean = stats_for_all_species.arithmeticMean();
368 for( final Species species : domain_lengths_table.getSpecies() ) {
369 final double x = domain_lengths_table.calculateMeanBasedStatisticsForSpecies( species ).arithmeticMean();
370 final double z = ( x - population_mean ) / population_sd;
371 out.write( species + "\t" + z );
372 out.write( ForesterUtil.LINE_SEPARATOR );
374 out.write( ForesterUtil.LINE_SEPARATOR );
375 for( final Species species : domain_lengths_table.getSpecies() ) {
376 final DescriptiveStatistics stats_for_species = domain_lengths_table
377 .calculateMeanBasedStatisticsForSpecies( species );
378 final double x = stats_for_species.arithmeticMean();
379 final double z = ( x - population_mean ) / population_sd;
380 if ( ( z <= -1.0 ) || ( z >= 1.0 ) ) {
381 out.write( species + "\t" + df.format( z ) + "\t" + stats_for_species.asSummary() );
382 out.write( ForesterUtil.LINE_SEPARATOR );
386 // final List<HistogramData> histogram_datas = new ArrayList<HistogramData>();
387 // for( int i = 0; i < number_of_genomes; ++i ) {
388 // final Species species = new BasicSpecies( input_file_properties[ i ][ 0 ] );
390 // .add( new HistogramData( species.toString(), domain_lengths_table
391 // .calculateMeanBasedStatisticsForSpecies( species )
392 // .getDataAsDoubleArray(), 5, 600, null, 60 ) );
394 // final HistogramsFrame hf = new HistogramsFrame( histogram_datas );
395 // hf.setVisible( true );
401 * @param all_binary_domains_combination_lost_fitch
402 * @param consider_directedness_and_adjacency_for_bin_combinations
403 * @param all_binary_domains_combination_gained if null ignored, otherwise this is to list all binary domain combinations
404 * which were gained under unweighted (Fitch) parsimony.
406 public static void executeParsimonyAnalysis( final long random_number_seed_for_fitch_parsimony,
407 final boolean radomize_fitch_parsimony,
408 final String outfile_name,
409 final DomainParsimonyCalculator domain_parsimony,
410 final Phylogeny phylogeny,
411 final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
412 final Map<GoId, GoTerm> go_id_to_term_map,
413 final GoNameSpace go_namespace_limit,
414 final String parameters_str,
415 final Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps,
416 final SortedSet<DomainId> positive_filter,
417 final boolean output_binary_domain_combinations_for_graphs,
418 final List<BinaryDomainCombination> all_binary_domains_combination_gained_fitch,
419 final List<BinaryDomainCombination> all_binary_domains_combination_lost_fitch,
420 final BinaryDomainCombination.DomainCombinationType dc_type ) {
421 final String sep = ForesterUtil.LINE_SEPARATOR + "###################" + ForesterUtil.LINE_SEPARATOR;
422 final String date_time = ForesterUtil.getCurrentDateTime();
423 final SortedSet<String> all_pfams_encountered = new TreeSet<String>();
424 final SortedSet<String> all_pfams_gained_as_domains = new TreeSet<String>();
425 final SortedSet<String> all_pfams_lost_as_domains = new TreeSet<String>();
426 final SortedSet<String> all_pfams_gained_as_dom_combinations = new TreeSet<String>();
427 final SortedSet<String> all_pfams_lost_as_dom_combinations = new TreeSet<String>();
428 writeToNexus( outfile_name, domain_parsimony, phylogeny );
431 Phylogeny local_phylogeny_l = phylogeny.copy();
432 if ( ( positive_filter != null ) && ( positive_filter.size() > 0 ) ) {
433 domain_parsimony.executeDolloParsimonyOnDomainPresence( positive_filter );
436 domain_parsimony.executeDolloParsimonyOnDomainPresence();
438 SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossMatrix(), outfile_name
439 + surfacing_old.PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS, Format.FORESTER );
440 SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossCountsMatrix(), outfile_name
441 + surfacing_old.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS, Format.FORESTER );
442 SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
443 CharacterStateMatrix.GainLossStates.GAIN,
444 outfile_name + surfacing_old.PARSIMONY_OUTPUT_DOLLO_GAINS_D,
446 ForesterUtil.LINE_SEPARATOR,
449 .writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
450 CharacterStateMatrix.GainLossStates.LOSS,
451 outfile_name + surfacing_old.PARSIMONY_OUTPUT_DOLLO_LOSSES_D,
453 ForesterUtil.LINE_SEPARATOR,
455 SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(), null, outfile_name
456 + surfacing_old.PARSIMONY_OUTPUT_DOLLO_PRESENT_D, sep, ForesterUtil.LINE_SEPARATOR, null );
458 writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
462 domain_parsimony.getGainLossMatrix(),
463 CharacterStateMatrix.GainLossStates.GAIN,
464 outfile_name + surfacing_old.PARSIMONY_OUTPUT_DOLLO_GAINS_HTML_D,
466 ForesterUtil.LINE_SEPARATOR,
467 "Dollo Parsimony | Gains | Domains",
469 domain_id_to_secondary_features_maps,
470 all_pfams_encountered,
471 all_pfams_gained_as_domains,
473 writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
477 domain_parsimony.getGainLossMatrix(),
478 CharacterStateMatrix.GainLossStates.LOSS,
479 outfile_name + surfacing_old.PARSIMONY_OUTPUT_DOLLO_LOSSES_HTML_D,
481 ForesterUtil.LINE_SEPARATOR,
482 "Dollo Parsimony | Losses | Domains",
484 domain_id_to_secondary_features_maps,
485 all_pfams_encountered,
486 all_pfams_lost_as_domains,
488 writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
492 domain_parsimony.getGainLossMatrix(),
494 outfile_name + surfacing_old.PARSIMONY_OUTPUT_DOLLO_PRESENT_HTML_D,
496 ForesterUtil.LINE_SEPARATOR,
497 "Dollo Parsimony | Present | Domains",
499 domain_id_to_secondary_features_maps,
500 all_pfams_encountered,
502 "_dollo_present_d" );
503 preparePhylogeny( local_phylogeny_l,
506 "Dollo parsimony on domain presence/absence",
507 "dollo_on_domains_" + outfile_name,
509 SurfacingUtil.writePhylogenyToFile( local_phylogeny_l, outfile_name
510 + surfacing_old.DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO );
512 writeAllDomainsChangedOnAllSubtrees( local_phylogeny_l, true, outfile_name, "_dollo_all_gains_d" );
513 writeAllDomainsChangedOnAllSubtrees( local_phylogeny_l, false, outfile_name, "_dollo_all_losses_d" );
515 catch ( final IOException e ) {
517 ForesterUtil.fatalError( surfacing_old.PRG_NAME, e.getLocalizedMessage() );
519 if ( domain_parsimony.calculateNumberOfBinaryDomainCombination() > 0 ) {
520 // FITCH DOMAIN COMBINATIONS
521 // -------------------------
522 local_phylogeny_l = phylogeny.copy();
523 String randomization = "no";
524 if ( radomize_fitch_parsimony ) {
525 domain_parsimony.executeFitchParsimonyOnBinaryDomainCombintion( random_number_seed_for_fitch_parsimony );
526 randomization = "yes, seed = " + random_number_seed_for_fitch_parsimony;
529 domain_parsimony.executeFitchParsimonyOnBinaryDomainCombintion( false );
531 SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossMatrix(), outfile_name
532 + surfacing_old.PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS, Format.FORESTER );
533 SurfacingUtil.writeMatrixToFile( domain_parsimony.getGainLossCountsMatrix(), outfile_name
534 + surfacing_old.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS, Format.FORESTER );
535 SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
536 CharacterStateMatrix.GainLossStates.GAIN,
538 + surfacing_old.PARSIMONY_OUTPUT_FITCH_GAINS_BC,
540 ForesterUtil.LINE_SEPARATOR,
543 .writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(),
544 CharacterStateMatrix.GainLossStates.LOSS,
545 outfile_name + surfacing_old.PARSIMONY_OUTPUT_FITCH_LOSSES_BC,
547 ForesterUtil.LINE_SEPARATOR,
549 SurfacingUtil.writeBinaryStatesMatrixAsListToFile( domain_parsimony.getGainLossMatrix(), null, outfile_name
550 + surfacing_old.PARSIMONY_OUTPUT_FITCH_PRESENT_BC, sep, ForesterUtil.LINE_SEPARATOR, null );
551 if ( all_binary_domains_combination_gained_fitch != null ) {
552 collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile( domain_parsimony
553 .getGainLossMatrix(), dc_type, all_binary_domains_combination_gained_fitch, true );
555 if ( all_binary_domains_combination_lost_fitch != null ) {
556 collectChangedDomainCombinationsFromBinaryStatesMatrixAsListToFile( domain_parsimony
557 .getGainLossMatrix(), dc_type, all_binary_domains_combination_lost_fitch, false );
559 if ( output_binary_domain_combinations_for_graphs ) {
561 .writeBinaryStatesMatrixAsListToFileForBinaryCombinationsForGraphAnalysis( domain_parsimony
562 .getGainLossMatrix(),
565 + surfacing_old.PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS,
567 ForesterUtil.LINE_SEPARATOR,
568 BinaryDomainCombination.OutputFormat.DOT );
571 writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
575 domain_parsimony.getGainLossMatrix(),
576 CharacterStateMatrix.GainLossStates.GAIN,
577 outfile_name + surfacing_old.PARSIMONY_OUTPUT_FITCH_GAINS_HTML_BC,
579 ForesterUtil.LINE_SEPARATOR,
580 "Fitch Parsimony | Gains | Domain Combinations",
583 all_pfams_encountered,
584 all_pfams_gained_as_dom_combinations,
586 writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
590 domain_parsimony.getGainLossMatrix(),
591 CharacterStateMatrix.GainLossStates.LOSS,
592 outfile_name + surfacing_old.PARSIMONY_OUTPUT_FITCH_LOSSES_HTML_BC,
594 ForesterUtil.LINE_SEPARATOR,
595 "Fitch Parsimony | Losses | Domain Combinations",
598 all_pfams_encountered,
599 all_pfams_lost_as_dom_combinations,
600 "_fitch_losses_dc" );
601 writeBinaryStatesMatrixToList( domain_id_to_go_ids_map,
605 domain_parsimony.getGainLossMatrix(),
607 outfile_name + surfacing_old.PARSIMONY_OUTPUT_FITCH_PRESENT_HTML_BC,
609 ForesterUtil.LINE_SEPARATOR,
610 "Fitch Parsimony | Present | Domain Combinations",
613 all_pfams_encountered,
615 "_fitch_present_dc" );
616 writeAllEncounteredPfamsToFile( domain_id_to_go_ids_map,
619 all_pfams_encountered );
620 writePfamsToFile( outfile_name + surfacing_old.ALL_PFAMS_GAINED_AS_DOMAINS_SUFFIX,
621 all_pfams_gained_as_domains );
622 writePfamsToFile( outfile_name + surfacing_old.ALL_PFAMS_LOST_AS_DOMAINS_SUFFIX, all_pfams_lost_as_domains );
623 writePfamsToFile( outfile_name + surfacing_old.ALL_PFAMS_GAINED_AS_DC_SUFFIX,
624 all_pfams_gained_as_dom_combinations );
625 writePfamsToFile( outfile_name + surfacing_old.ALL_PFAMS_LOST_AS_DC_SUFFIX,
626 all_pfams_lost_as_dom_combinations );
627 preparePhylogeny( local_phylogeny_l,
630 "Fitch parsimony on binary domain combination presence/absence randomization: "
632 "fitch_on_binary_domain_combinations_" + outfile_name,
634 SurfacingUtil.writePhylogenyToFile( local_phylogeny_l, outfile_name
635 + surfacing_old.BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH );
639 public static void executeParsimonyAnalysisForSecondaryFeatures( final String outfile_name,
640 final DomainParsimonyCalculator secondary_features_parsimony,
641 final Phylogeny phylogeny,
642 final String parameters_str,
643 final Map<Species, MappingResults> mapping_results_map ) {
644 final String sep = ForesterUtil.LINE_SEPARATOR + "###################" + ForesterUtil.LINE_SEPARATOR;
645 final String date_time = ForesterUtil.getCurrentDateTime();
646 System.out.println();
647 writeToNexus( outfile_name + surfacing_old.NEXUS_SECONDARY_FEATURES, secondary_features_parsimony
648 .createMatrixOfSecondaryFeaturePresenceOrAbsence( null ), phylogeny );
649 final Phylogeny local_phylogeny_copy = phylogeny.copy();
650 secondary_features_parsimony.executeDolloParsimonyOnSecondaryFeatures( mapping_results_map );
651 SurfacingUtil.writeMatrixToFile( secondary_features_parsimony.getGainLossMatrix(), outfile_name
652 + surfacing_old.PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES, Format.FORESTER );
653 SurfacingUtil.writeMatrixToFile( secondary_features_parsimony.getGainLossCountsMatrix(), outfile_name
654 + surfacing_old.PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES, Format.FORESTER );
656 .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(),
657 CharacterStateMatrix.GainLossStates.GAIN,
659 + surfacing_old.PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES,
661 ForesterUtil.LINE_SEPARATOR,
664 .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(),
665 CharacterStateMatrix.GainLossStates.LOSS,
667 + surfacing_old.PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES,
669 ForesterUtil.LINE_SEPARATOR,
672 .writeBinaryStatesMatrixAsListToFile( secondary_features_parsimony.getGainLossMatrix(),
675 + surfacing_old.PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES,
677 ForesterUtil.LINE_SEPARATOR,
679 preparePhylogeny( local_phylogeny_copy,
680 secondary_features_parsimony,
682 "Dollo parsimony on secondary feature presence/absence",
683 "dollo_on_secondary_features_" + outfile_name,
685 SurfacingUtil.writePhylogenyToFile( local_phylogeny_copy, outfile_name
686 + surfacing_old.SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO );
689 public static void extractProteinNames( final List<Protein> proteins,
690 final List<DomainId> query_domain_ids_nc_order,
692 final String separator ) throws IOException {
693 for( final Protein protein : proteins ) {
694 if ( protein.contains( query_domain_ids_nc_order, true ) ) {
695 out.write( protein.getSpecies().getSpeciesId() );
696 out.write( separator );
697 out.write( protein.getProteinId().getId() );
698 out.write( separator );
700 final Set<DomainId> visited_domain_ids = new HashSet<DomainId>();
701 boolean first = true;
702 for( final Domain domain : protein.getProteinDomains() ) {
703 if ( !visited_domain_ids.contains( domain.getDomainId() ) ) {
704 visited_domain_ids.add( domain.getDomainId() );
711 out.write( domain.getDomainId().getId() );
713 out.write( "" + domain.getTotalCount() );
718 out.write( separator );
719 if ( !( ForesterUtil.isEmpty( protein.getDescription() ) || protein.getDescription()
720 .equals( SurfacingConstants.NONE ) ) ) {
721 out.write( protein.getDescription() );
723 out.write( separator );
724 if ( !( ForesterUtil.isEmpty( protein.getAccession() ) || protein.getAccession()
725 .equals( SurfacingConstants.NONE ) ) ) {
726 out.write( protein.getAccession() );
728 out.write( SurfacingConstants.NL );
734 public static void extractProteinNames( final SortedMap<Species, List<Protein>> protein_lists_per_species,
735 final DomainId domain_id,
737 final String separator ) throws IOException {
738 for( final Species species : protein_lists_per_species.keySet() ) {
739 for( final Protein protein : protein_lists_per_species.get( species ) ) {
740 final List<Domain> domains = protein.getProteinDomains( domain_id );
741 if ( domains.size() > 0 ) {
742 final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
743 for( final Domain domain : domains ) {
744 stats.addValue( domain.getPerSequenceEvalue() );
746 out.write( protein.getSpecies().getSpeciesId() );
747 out.write( separator );
748 out.write( protein.getProteinId().getId() );
749 out.write( separator );
750 out.write( "[" + FORMATTER.format( stats.median() ) + "]" );
751 out.write( separator );
752 if ( !( ForesterUtil.isEmpty( protein.getDescription() ) || protein.getDescription()
753 .equals( SurfacingConstants.NONE ) ) ) {
754 out.write( protein.getDescription() );
756 out.write( separator );
757 if ( !( ForesterUtil.isEmpty( protein.getAccession() ) || protein.getAccession()
758 .equals( SurfacingConstants.NONE ) ) ) {
759 out.write( protein.getAccession() );
761 out.write( SurfacingConstants.NL );
768 public static SortedSet<DomainId> getAllDomainIds( final List<GenomeWideCombinableDomains> gwcd_list ) {
769 final SortedSet<DomainId> all_domains_ids = new TreeSet<DomainId>();
770 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
771 final Set<DomainId> all_domains = gwcd.getAllDomainIds();
772 // for( final Domain domain : all_domains ) {
773 all_domains_ids.addAll( all_domains );
776 return all_domains_ids;
779 public static SortedMap<String, Integer> getDomainCounts( final List<Protein> protein_domain_collections ) {
780 final SortedMap<String, Integer> map = new TreeMap<String, Integer>();
781 for( final Protein protein_domain_collection : protein_domain_collections ) {
782 for( final Object name : protein_domain_collection.getProteinDomains() ) {
783 final BasicDomain protein_domain = ( BasicDomain ) name;
784 final String id = protein_domain.getDomainId().getId();
785 if ( map.containsKey( id ) ) {
786 map.put( id, map.get( id ) + 1 );
796 public static int getNumberOfNodesLackingName( final Phylogeny p, final StringBuilder names ) {
797 final PhylogenyNodeIterator it = p.iteratorPostorder();
799 while ( it.hasNext() ) {
800 final PhylogenyNode n = it.next();
801 if ( ForesterUtil.isEmpty( n.getName() )
802 && ( !n.getNodeData().isHasTaxonomy() || ForesterUtil.isEmpty( n.getNodeData().getTaxonomy()
803 .getScientificName() ) ) ) {
804 if ( n.getParent() != null ) {
806 names.append( n.getParent().getName() );
815 * Returns true is Domain domain falls in an uninterrupted stretch of
819 * @param covered_positions
822 public static boolean isEngulfed( final Domain domain, final List<Boolean> covered_positions ) {
823 for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) {
824 if ( ( i >= covered_positions.size() ) || ( covered_positions.get( i ) != true ) ) {
831 public static void preparePhylogeny( final Phylogeny p,
832 final DomainParsimonyCalculator domain_parsimony,
833 final String date_time,
836 final String parameters_str ) {
837 domain_parsimony.decoratePhylogenyWithDomains( p );
838 final StringBuilder desc = new StringBuilder();
839 desc.append( "[Method: " + method + "] [Date: " + date_time + "] " );
840 desc.append( "[Cost: " + domain_parsimony.getCost() + "] " );
841 desc.append( "[Gains: " + domain_parsimony.getTotalGains() + "] " );
842 desc.append( "[Losses: " + domain_parsimony.getTotalLosses() + "] " );
843 desc.append( "[Unchanged: " + domain_parsimony.getTotalUnchanged() + "] " );
844 desc.append( "[Parameters: " + parameters_str + "]" );
846 p.setDescription( desc.toString() );
847 p.setConfidence( new Confidence( domain_parsimony.getCost(), "parsimony" ) );
848 p.setRerootable( false );
854 * Example regarding engulfment: ------------0.1 ----------0.2 --0.3 =>
855 * domain with 0.3 is ignored
857 * -----------0.1 ----------0.2 --0.3 => domain with 0.3 is ignored
860 * ------------0.1 ----------0.3 --0.2 => domains with 0.3 and 0.2 are _not_
863 * @param max_allowed_overlap
864 * maximal allowed overlap (inclusive) to be still considered not
865 * overlapping (zero or negative value to allow any overlap)
866 * @param remove_engulfed_domains
867 * to remove domains which are completely engulfed by coverage of
868 * domains with better support
872 public static Protein removeOverlappingDomains( final int max_allowed_overlap,
873 final boolean remove_engulfed_domains,
874 final Protein protein ) {
875 final Protein pruned_protein = new BasicProtein( protein.getProteinId().getId(), protein.getSpecies()
877 final List<Domain> sorted = SurfacingUtil.sortDomainsWithAscendingConfidenceValues( protein );
878 final List<Boolean> covered_positions = new ArrayList<Boolean>();
879 for( final Domain domain : sorted ) {
880 if ( ( ( max_allowed_overlap < 0 ) || ( SurfacingUtil.calculateOverlap( domain, covered_positions ) <= max_allowed_overlap ) )
881 && ( !remove_engulfed_domains || !isEngulfed( domain, covered_positions ) ) ) {
882 final int covered_positions_size = covered_positions.size();
883 for( int i = covered_positions_size; i < domain.getFrom(); ++i ) {
884 covered_positions.add( false );
886 final int new_covered_positions_size = covered_positions.size();
887 for( int i = domain.getFrom(); i <= domain.getTo(); ++i ) {
888 if ( i < new_covered_positions_size ) {
889 covered_positions.set( i, true );
892 covered_positions.add( true );
895 pruned_protein.addProteinDomain( domain );
898 return pruned_protein;
901 static List<Domain> sortDomainsWithAscendingConfidenceValues( final Protein protein ) {
902 final List<Domain> domains = new ArrayList<Domain>();
903 for( final Domain d : protein.getProteinDomains() ) {
906 Collections.sort( domains, SurfacingUtil.ASCENDING_CONFIDENCE_VALUE_ORDER );
910 public static void writeAllDomainsChangedOnAllSubtrees( final Phylogeny p,
911 final boolean get_gains,
913 final String suffix_for_filename ) throws IOException {
914 CharacterStateMatrix.GainLossStates state = CharacterStateMatrix.GainLossStates.GAIN;
916 state = CharacterStateMatrix.GainLossStates.LOSS;
918 final File base_dir = createBaseDirForPerNodeDomainFiles( surfacing_old.BASE_DIRECTORY_PER_SUBTREE_DOMAIN_GAIN_LOSS_FILES,
922 for( final PhylogenyNodeIterator it = p.iteratorPostorder(); it.hasNext(); ) {
923 final PhylogenyNode node = it.next();
924 if ( !node.isExternal() ) {
925 final SortedSet<String> domains = collectAllDomainsChangedOnSubtree( node, get_gains );
926 if ( domains.size() > 0 ) {
927 final Writer writer = ForesterUtil.createBufferedWriter( base_dir + ForesterUtil.FILE_SEPARATOR
928 + node.getName() + suffix_for_filename );
929 for( final String domain : domains ) {
930 writer.write( domain );
931 writer.write( ForesterUtil.LINE_SEPARATOR );
939 private static void writeAllEncounteredPfamsToFile( final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
940 final Map<GoId, GoTerm> go_id_to_term_map,
941 final String outfile_name,
942 final SortedSet<String> all_pfams_encountered ) {
943 final File all_pfams_encountered_file = new File( outfile_name + surfacing_old.ALL_PFAMS_ENCOUNTERED_SUFFIX );
944 final File all_pfams_encountered_with_go_annotation_file = new File( outfile_name
945 + surfacing_old.ALL_PFAMS_ENCOUNTERED_WITH_GO_ANNOTATION_SUFFIX );
946 final File encountered_pfams_summary_file = new File( outfile_name
947 + surfacing_old.ENCOUNTERED_PFAMS_SUMMARY_SUFFIX );
948 int biological_process_counter = 0;
949 int cellular_component_counter = 0;
950 int molecular_function_counter = 0;
951 int pfams_with_mappings_counter = 0;
952 int pfams_without_mappings_counter = 0;
953 int pfams_without_mappings_to_bp_or_mf_counter = 0;
954 int pfams_with_mappings_to_bp_or_mf_counter = 0;
956 final Writer all_pfams_encountered_writer = new BufferedWriter( new FileWriter( all_pfams_encountered_file ) );
957 final Writer all_pfams_encountered_with_go_annotation_writer = new BufferedWriter( new FileWriter( all_pfams_encountered_with_go_annotation_file ) );
958 final Writer summary_writer = new BufferedWriter( new FileWriter( encountered_pfams_summary_file ) );
959 summary_writer.write( "# Pfam to GO mapping summary" );
960 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
961 summary_writer.write( "# Actual summary is at the end of this file." );
962 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
963 summary_writer.write( "# Encountered Pfams without a GO mapping:" );
964 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
965 for( final String pfam : all_pfams_encountered ) {
966 all_pfams_encountered_writer.write( pfam );
967 all_pfams_encountered_writer.write( ForesterUtil.LINE_SEPARATOR );
968 final DomainId domain_id = new DomainId( pfam );
969 if ( domain_id_to_go_ids_map.containsKey( domain_id ) ) {
970 ++pfams_with_mappings_counter;
971 all_pfams_encountered_with_go_annotation_writer.write( pfam );
972 all_pfams_encountered_with_go_annotation_writer.write( ForesterUtil.LINE_SEPARATOR );
973 final List<GoId> go_ids = domain_id_to_go_ids_map.get( domain_id );
974 boolean maps_to_bp = false;
975 boolean maps_to_cc = false;
976 boolean maps_to_mf = false;
977 for( final GoId go_id : go_ids ) {
978 final GoTerm go_term = go_id_to_term_map.get( go_id );
979 if ( go_term.getGoNameSpace().isBiologicalProcess() ) {
982 else if ( go_term.getGoNameSpace().isCellularComponent() ) {
985 else if ( go_term.getGoNameSpace().isMolecularFunction() ) {
990 ++biological_process_counter;
993 ++cellular_component_counter;
996 ++molecular_function_counter;
998 if ( maps_to_bp || maps_to_mf ) {
999 ++pfams_with_mappings_to_bp_or_mf_counter;
1002 ++pfams_without_mappings_to_bp_or_mf_counter;
1006 ++pfams_without_mappings_to_bp_or_mf_counter;
1007 ++pfams_without_mappings_counter;
1008 summary_writer.write( pfam );
1009 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
1012 all_pfams_encountered_writer.close();
1013 all_pfams_encountered_with_go_annotation_writer.close();
1014 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Wrote all [" + all_pfams_encountered.size()
1015 + "] encountered Pfams to: \"" + all_pfams_encountered_file + "\"" );
1016 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Wrote all [" + pfams_with_mappings_counter
1017 + "] encountered Pfams with GO mappings to: \"" + all_pfams_encountered_with_go_annotation_file
1019 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Wrote summary (including all ["
1020 + pfams_without_mappings_counter + "] encountered Pfams without GO mappings) to: \""
1021 + encountered_pfams_summary_file + "\"" );
1022 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Sum of Pfams encountered : "
1023 + all_pfams_encountered.size() );
1024 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Pfams without a mapping : "
1025 + pfams_without_mappings_counter + " ["
1026 + ( 100 * pfams_without_mappings_counter / all_pfams_encountered.size() ) + "%]" );
1027 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Pfams without mapping to proc. or func. : "
1028 + pfams_without_mappings_to_bp_or_mf_counter + " ["
1029 + ( 100 * pfams_without_mappings_to_bp_or_mf_counter / all_pfams_encountered.size() ) + "%]" );
1030 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Pfams with a mapping : "
1031 + pfams_with_mappings_counter + " ["
1032 + ( 100 * pfams_with_mappings_counter / all_pfams_encountered.size() ) + "%]" );
1033 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Pfams with a mapping to proc. or func. : "
1034 + pfams_with_mappings_to_bp_or_mf_counter + " ["
1035 + ( 100 * pfams_with_mappings_to_bp_or_mf_counter / all_pfams_encountered.size() ) + "%]" );
1036 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Pfams with mapping to biological process: "
1037 + biological_process_counter + " ["
1038 + ( 100 * biological_process_counter / all_pfams_encountered.size() ) + "%]" );
1039 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Pfams with mapping to molecular function: "
1040 + molecular_function_counter + " ["
1041 + ( 100 * molecular_function_counter / all_pfams_encountered.size() ) + "%]" );
1042 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Pfams with mapping to cellular component: "
1043 + cellular_component_counter + " ["
1044 + ( 100 * cellular_component_counter / all_pfams_encountered.size() ) + "%]" );
1045 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
1046 summary_writer.write( "# Sum of Pfams encountered : " + all_pfams_encountered.size() );
1047 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
1048 summary_writer.write( "# Pfams without a mapping : " + pfams_without_mappings_counter
1049 + " [" + ( 100 * pfams_without_mappings_counter / all_pfams_encountered.size() ) + "%]" );
1050 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
1051 summary_writer.write( "# Pfams without mapping to proc. or func. : "
1052 + pfams_without_mappings_to_bp_or_mf_counter + " ["
1053 + ( 100 * pfams_without_mappings_to_bp_or_mf_counter / all_pfams_encountered.size() ) + "%]" );
1054 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
1055 summary_writer.write( "# Pfams with a mapping : " + pfams_with_mappings_counter + " ["
1056 + ( 100 * pfams_with_mappings_counter / all_pfams_encountered.size() ) + "%]" );
1057 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
1058 summary_writer.write( "# Pfams with a mapping to proc. or func. : "
1059 + pfams_with_mappings_to_bp_or_mf_counter + " ["
1060 + ( 100 * pfams_with_mappings_to_bp_or_mf_counter / all_pfams_encountered.size() ) + "%]" );
1061 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
1062 summary_writer.write( "# Pfams with mapping to biological process: " + biological_process_counter + " ["
1063 + ( 100 * biological_process_counter / all_pfams_encountered.size() ) + "%]" );
1064 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
1065 summary_writer.write( "# Pfams with mapping to molecular function: " + molecular_function_counter + " ["
1066 + ( 100 * molecular_function_counter / all_pfams_encountered.size() ) + "%]" );
1067 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
1068 summary_writer.write( "# Pfams with mapping to cellular component: " + cellular_component_counter + " ["
1069 + ( 100 * cellular_component_counter / all_pfams_encountered.size() ) + "%]" );
1070 summary_writer.write( ForesterUtil.LINE_SEPARATOR );
1071 summary_writer.close();
1073 catch ( final IOException e ) {
1074 ForesterUtil.printWarningMessage( surfacing_old.PRG_NAME, "Failure to write: " + e );
1078 public static void writeBinaryDomainCombinationsFileForGraphAnalysis( final String[][] input_file_properties,
1079 final File output_dir,
1080 final GenomeWideCombinableDomains gwcd,
1082 final GenomeWideCombinableDomainsSortOrder dc_sort_order ) {
1083 File dc_outfile_dot = new File( input_file_properties[ i ][ 0 ]
1084 + surfacing_old.DOMAIN_COMBINITONS_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS );
1085 if ( output_dir != null ) {
1086 dc_outfile_dot = new File( output_dir + ForesterUtil.FILE_SEPARATOR + dc_outfile_dot );
1088 checkForOutputFileWriteability( dc_outfile_dot );
1089 final SortedSet<BinaryDomainCombination> binary_combinations = createSetOfAllBinaryDomainCombinationsPerGenome( gwcd );
1091 final BufferedWriter out_dot = new BufferedWriter( new FileWriter( dc_outfile_dot ) );
1092 for( final BinaryDomainCombination bdc : binary_combinations ) {
1093 out_dot.write( bdc.toGraphDescribingLanguage( BinaryDomainCombination.OutputFormat.DOT, null, null )
1095 out_dot.write( SurfacingConstants.NL );
1099 catch ( final IOException e ) {
1100 ForesterUtil.fatalError( surfacing_old.PRG_NAME, e.getMessage() );
1102 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Wrote binary domain combination for \""
1103 + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ", "
1104 + input_file_properties[ i ][ 2 ] + ") to: \"" + dc_outfile_dot + "\"" );
1108 * species | protein id | n-terminal domain | c-terminal domain | n-terminal domain per domain E-value | c-terminal domain per domain E-value
1112 static public StringBuffer proteinToDomainCombinations( final Protein protein,
1113 final String protein_id,
1114 final String separator ) {
1115 final StringBuffer sb = new StringBuffer();
1116 if ( protein.getSpecies() == null ) {
1117 throw new IllegalArgumentException( "species must not be null" );
1119 if ( ForesterUtil.isEmpty( protein.getSpecies().getSpeciesId() ) ) {
1120 throw new IllegalArgumentException( "species id must not be empty" );
1122 final List<Domain> domains = protein.getProteinDomains();
1123 if ( domains.size() > 1 ) {
1124 final Map<String, Integer> counts = new HashMap<String, Integer>();
1125 for( final Domain domain : domains ) {
1126 final String id = domain.getDomainId().getId();
1127 if ( counts.containsKey( id ) ) {
1128 counts.put( id, counts.get( id ) + 1 );
1131 counts.put( id, 1 );
1134 for( int i = 1; i < domains.size(); ++i ) {
1135 for( int j = 0; j < i; ++j ) {
1136 Domain domain_n = domains.get( i );
1137 Domain domain_c = domains.get( j );
1138 if ( domain_n.getFrom() > domain_c.getFrom() ) {
1139 domain_n = domains.get( j );
1140 domain_c = domains.get( i );
1142 sb.append( protein.getSpecies() );
1143 sb.append( separator );
1144 sb.append( protein_id );
1145 sb.append( separator );
1146 sb.append( domain_n.getDomainId().getId() );
1147 sb.append( separator );
1148 sb.append( domain_c.getDomainId().getId() );
1149 sb.append( separator );
1150 sb.append( domain_n.getPerDomainEvalue() );
1151 sb.append( separator );
1152 sb.append( domain_c.getPerDomainEvalue() );
1153 sb.append( separator );
1154 sb.append( counts.get( domain_n.getDomainId().getId() ) );
1155 sb.append( separator );
1156 sb.append( counts.get( domain_c.getDomainId().getId() ) );
1157 sb.append( ForesterUtil.LINE_SEPARATOR );
1161 else if ( domains.size() == 1 ) {
1162 sb.append( protein.getSpecies() );
1163 sb.append( separator );
1164 sb.append( protein_id );
1165 sb.append( separator );
1166 sb.append( domains.get( 0 ).getDomainId().getId() );
1167 sb.append( separator );
1168 sb.append( separator );
1169 sb.append( domains.get( 0 ).getPerDomainEvalue() );
1170 sb.append( separator );
1171 sb.append( separator );
1173 sb.append( separator );
1174 sb.append( ForesterUtil.LINE_SEPARATOR );
1177 sb.append( protein.getSpecies() );
1178 sb.append( separator );
1179 sb.append( protein_id );
1180 sb.append( separator );
1181 sb.append( separator );
1182 sb.append( separator );
1183 sb.append( separator );
1184 sb.append( separator );
1185 sb.append( separator );
1186 sb.append( ForesterUtil.LINE_SEPARATOR );
1191 public static void writeBinaryStatesMatrixAsListToFile( final CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
1192 final CharacterStateMatrix.GainLossStates state,
1193 final String filename,
1194 final String indentifier_characters_separator,
1195 final String character_separator,
1196 final Map<String, String> descriptions ) {
1197 final File outfile = new File( filename );
1198 checkForOutputFileWriteability( outfile );
1199 final SortedSet<String> sorted_ids = new TreeSet<String>();
1200 for( int i = 0; i < matrix.getNumberOfIdentifiers(); ++i ) {
1201 sorted_ids.add( matrix.getIdentifier( i ) );
1204 final BufferedWriter out = new BufferedWriter( new FileWriter( outfile ) );
1205 for( final String id : sorted_ids ) {
1206 out.write( indentifier_characters_separator );
1207 out.write( "#" + id );
1208 out.write( indentifier_characters_separator );
1209 for( int c = 0; c < matrix.getNumberOfCharacters(); ++c ) {
1211 // using null to indicate either UNCHANGED_PRESENT or GAIN.
1212 if ( ( matrix.getState( id, c ) == state )
1213 || ( ( state == null ) && ( ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.GAIN ) || ( matrix
1214 .getState( id, c ) == CharacterStateMatrix.GainLossStates.UNCHANGED_PRESENT ) ) ) ) {
1215 out.write( matrix.getCharacter( c ) );
1216 if ( ( descriptions != null ) && !descriptions.isEmpty()
1217 && descriptions.containsKey( matrix.getCharacter( c ) ) ) {
1219 out.write( descriptions.get( matrix.getCharacter( c ) ) );
1221 out.write( character_separator );
1228 catch ( final IOException e ) {
1229 ForesterUtil.fatalError( surfacing_old.PRG_NAME, e.getMessage() );
1231 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Wrote characters list: \"" + filename + "\"" );
1234 public static void writeBinaryStatesMatrixAsListToFileForBinaryCombinationsForGraphAnalysis( final CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
1235 final CharacterStateMatrix.GainLossStates state,
1236 final String filename,
1237 final String indentifier_characters_separator,
1238 final String character_separator,
1239 final BinaryDomainCombination.OutputFormat bc_output_format ) {
1240 final File outfile = new File( filename );
1241 checkForOutputFileWriteability( outfile );
1242 final SortedSet<String> sorted_ids = new TreeSet<String>();
1243 for( int i = 0; i < matrix.getNumberOfIdentifiers(); ++i ) {
1244 sorted_ids.add( matrix.getIdentifier( i ) );
1247 final BufferedWriter out = new BufferedWriter( new FileWriter( outfile ) );
1248 for( final String id : sorted_ids ) {
1249 out.write( indentifier_characters_separator );
1250 out.write( "#" + id );
1251 out.write( indentifier_characters_separator );
1252 for( int c = 0; c < matrix.getNumberOfCharacters(); ++c ) {
1254 // using null to indicate either UNCHANGED_PRESENT or GAIN.
1255 if ( ( matrix.getState( id, c ) == state )
1256 || ( ( state == null ) && ( ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.GAIN ) || ( matrix
1257 .getState( id, c ) == CharacterStateMatrix.GainLossStates.UNCHANGED_PRESENT ) ) ) ) {
1258 BinaryDomainCombination bdc = null;
1260 bdc = BasicBinaryDomainCombination.createInstance( matrix.getCharacter( c ) );
1262 catch ( final Exception e ) {
1263 ForesterUtil.fatalError( surfacing_old.PRG_NAME, e.getLocalizedMessage() );
1265 out.write( bdc.toGraphDescribingLanguage( bc_output_format, null, null ).toString() );
1266 out.write( character_separator );
1273 catch ( final IOException e ) {
1274 ForesterUtil.fatalError( surfacing_old.PRG_NAME, e.getMessage() );
1276 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Wrote characters list: \"" + filename + "\"" );
1279 public static void writeBinaryStatesMatrixToList( final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
1280 final Map<GoId, GoTerm> go_id_to_term_map,
1281 final GoNameSpace go_namespace_limit,
1282 final boolean domain_combinations,
1283 final CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
1284 final CharacterStateMatrix.GainLossStates state,
1285 final String filename,
1286 final String indentifier_characters_separator,
1287 final String character_separator,
1288 final String title_for_html,
1289 final String prefix_for_html,
1290 final Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps,
1291 final SortedSet<String> all_pfams_encountered,
1292 final SortedSet<String> pfams_gained_or_lost,
1293 final String suffix_for_per_node_events_file ) {
1294 if ( ( go_namespace_limit != null ) && ( ( go_id_to_term_map == null ) || ( go_id_to_term_map.size() < 1 ) ) ) {
1295 throw new IllegalArgumentException( "attempt to use GO namespace limit without a GO-id to term map" );
1297 else if ( ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) ) {
1298 throw new IllegalArgumentException( "attempt to output detailed HTML without a Pfam to GO map" );
1300 else if ( ( ( go_id_to_term_map == null ) || ( go_id_to_term_map.size() < 1 ) ) ) {
1301 throw new IllegalArgumentException( "attempt to output detailed HTML without a GO-id to term map" );
1303 final File outfile = new File( filename );
1304 checkForOutputFileWriteability( outfile );
1305 final SortedSet<String> sorted_ids = new TreeSet<String>();
1306 for( int i = 0; i < matrix.getNumberOfIdentifiers(); ++i ) {
1307 sorted_ids.add( matrix.getIdentifier( i ) );
1310 final Writer out = new BufferedWriter( new FileWriter( outfile ) );
1311 final File per_node_go_mapped_domain_gain_loss_files_base_dir = createBaseDirForPerNodeDomainFiles( surfacing_old.BASE_DIRECTORY_PER_NODE_DOMAIN_GAIN_LOSS_FILES,
1312 domain_combinations,
1315 Writer per_node_go_mapped_domain_gain_loss_outfile_writer = null;
1316 File per_node_go_mapped_domain_gain_loss_outfile = null;
1317 int per_node_counter = 0;
1318 out.write( "<html>" );
1319 out.write( SurfacingConstants.NL );
1320 addHtmlHead( out, title_for_html );
1321 out.write( SurfacingConstants.NL );
1322 out.write( "<body>" );
1323 out.write( SurfacingConstants.NL );
1324 out.write( "<h1>" );
1325 out.write( SurfacingConstants.NL );
1326 out.write( title_for_html );
1327 out.write( SurfacingConstants.NL );
1328 out.write( "</h1>" );
1329 out.write( SurfacingConstants.NL );
1330 out.write( "<table>" );
1331 out.write( SurfacingConstants.NL );
1332 for( final String id : sorted_ids ) {
1333 final Matcher matcher = PATTERN_SP_STYLE_TAXONOMY.matcher( id );
1334 if ( matcher.matches() ) {
1337 out.write( "<tr>" );
1338 out.write( "<td>" );
1339 out.write( "<a href=\"#" + id + "\">" + id + "</a>" );
1340 out.write( "</td>" );
1341 out.write( "</tr>" );
1342 out.write( SurfacingConstants.NL );
1344 out.write( "</table>" );
1345 out.write( SurfacingConstants.NL );
1346 for( final String id : sorted_ids ) {
1347 final Matcher matcher = PATTERN_SP_STYLE_TAXONOMY.matcher( id );
1348 if ( matcher.matches() ) {
1351 out.write( SurfacingConstants.NL );
1352 out.write( "<h2>" );
1353 out.write( "<a name=\"" + id + "\">" + id + "</a>" );
1354 writeTaxonomyLinks( out, id );
1355 out.write( "</h2>" );
1356 out.write( SurfacingConstants.NL );
1357 out.write( "<table>" );
1358 out.write( SurfacingConstants.NL );
1359 out.write( "<tr>" );
1360 out.write( "<td><b>" );
1361 out.write( "Pfam domain(s)" );
1362 out.write( "</b></td><td><b>" );
1363 out.write( "GO term acc" );
1364 out.write( "</b></td><td><b>" );
1365 out.write( "GO term" );
1366 out.write( "</b></td><td><b>" );
1367 out.write( "GO namespace" );
1368 out.write( "</b></td>" );
1369 out.write( "</tr>" );
1370 out.write( SurfacingConstants.NL );
1371 out.write( "</tr>" );
1372 out.write( SurfacingConstants.NL );
1373 per_node_counter = 0;
1374 if ( matrix.getNumberOfCharacters() > 0 ) {
1375 per_node_go_mapped_domain_gain_loss_outfile = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
1376 + ForesterUtil.FILE_SEPARATOR + id + suffix_for_per_node_events_file );
1377 SurfacingUtil.checkForOutputFileWriteability( per_node_go_mapped_domain_gain_loss_outfile );
1378 per_node_go_mapped_domain_gain_loss_outfile_writer = ForesterUtil
1379 .createBufferedWriter( per_node_go_mapped_domain_gain_loss_outfile );
1382 per_node_go_mapped_domain_gain_loss_outfile = null;
1383 per_node_go_mapped_domain_gain_loss_outfile_writer = null;
1385 for( int c = 0; c < matrix.getNumberOfCharacters(); ++c ) {
1387 // using null to indicate either UNCHANGED_PRESENT or GAIN.
1388 if ( ( matrix.getState( id, c ) == state )
1389 || ( ( state == null ) && ( ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.UNCHANGED_PRESENT ) || ( matrix
1390 .getState( id, c ) == CharacterStateMatrix.GainLossStates.GAIN ) ) ) ) {
1391 final String character = matrix.getCharacter( c );
1392 String domain_0 = "";
1393 String domain_1 = "";
1394 if ( character.indexOf( BinaryDomainCombination.SEPARATOR ) > 0 ) {
1395 final String[] s = character.split( BinaryDomainCombination.SEPARATOR );
1396 if ( s.length != 2 ) {
1397 throw new AssertionError( "this should not have happened: unexpected format for domain combination: ["
1398 + character + "]" );
1404 domain_0 = character;
1406 writeDomainData( domain_id_to_go_ids_map,
1413 character_separator,
1414 domain_id_to_secondary_features_maps,
1416 all_pfams_encountered.add( domain_0 );
1417 if ( pfams_gained_or_lost != null ) {
1418 pfams_gained_or_lost.add( domain_0 );
1420 if ( !ForesterUtil.isEmpty( domain_1 ) ) {
1421 all_pfams_encountered.add( domain_1 );
1422 if ( pfams_gained_or_lost != null ) {
1423 pfams_gained_or_lost.add( domain_1 );
1426 if ( per_node_go_mapped_domain_gain_loss_outfile_writer != null ) {
1427 writeDomainsToIndividualFilePerTreeNode( per_node_go_mapped_domain_gain_loss_outfile_writer,
1434 if ( per_node_go_mapped_domain_gain_loss_outfile_writer != null ) {
1435 per_node_go_mapped_domain_gain_loss_outfile_writer.close();
1436 if ( per_node_counter < 1 ) {
1437 per_node_go_mapped_domain_gain_loss_outfile.delete();
1439 per_node_counter = 0;
1441 out.write( "</table>" );
1442 out.write( SurfacingConstants.NL );
1443 out.write( "<hr>" );
1444 out.write( SurfacingConstants.NL );
1445 } // for( final String id : sorted_ids ) {
1446 out.write( "</body>" );
1447 out.write( SurfacingConstants.NL );
1448 out.write( "</html>" );
1449 out.write( SurfacingConstants.NL );
1453 catch ( final IOException e ) {
1454 ForesterUtil.fatalError( surfacing_old.PRG_NAME, e.getMessage() );
1456 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Wrote characters detailed HTML list: \"" + filename
1460 public static void writeBinaryStatesMatrixToListORIGIG( final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
1461 final Map<GoId, GoTerm> go_id_to_term_map,
1462 final GoNameSpace go_namespace_limit,
1463 final boolean domain_combinations,
1464 final CharacterStateMatrix<CharacterStateMatrix.GainLossStates> matrix,
1465 final CharacterStateMatrix.GainLossStates state,
1466 final String filename,
1467 final String indentifier_characters_separator,
1468 final String character_separator,
1469 final String title_for_html,
1470 final String prefix_for_html,
1471 final Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps,
1472 final SortedSet<String> all_pfams_encountered,
1473 final SortedSet<String> pfams_gained_or_lost,
1474 final String suffix_for_per_node_events_file ) {
1475 if ( ( go_namespace_limit != null ) && ( ( go_id_to_term_map == null ) || ( go_id_to_term_map.size() < 1 ) ) ) {
1476 throw new IllegalArgumentException( "attempt to use GO namespace limit without a GO-id to term map" );
1478 else if ( ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) ) {
1479 throw new IllegalArgumentException( "attempt to output detailed HTML without a Pfam to GO map" );
1481 else if ( ( ( go_id_to_term_map == null ) || ( go_id_to_term_map.size() < 1 ) ) ) {
1482 throw new IllegalArgumentException( "attempt to output detailed HTML without a GO-id to term map" );
1484 final File outfile = new File( filename );
1485 checkForOutputFileWriteability( outfile );
1486 final SortedSet<String> sorted_ids = new TreeSet<String>();
1487 for( int i = 0; i < matrix.getNumberOfIdentifiers(); ++i ) {
1488 sorted_ids.add( matrix.getIdentifier( i ) );
1491 final Writer out = new BufferedWriter( new FileWriter( outfile ) );
1492 final File per_node_go_mapped_domain_gain_loss_files_base_dir = createBaseDirForPerNodeDomainFiles( surfacing_old.BASE_DIRECTORY_PER_NODE_DOMAIN_GAIN_LOSS_FILES,
1493 domain_combinations,
1496 Writer per_node_go_mapped_domain_gain_loss_outfile_writer = null;
1497 File per_node_go_mapped_domain_gain_loss_outfile = null;
1498 int per_node_counter = 0;
1499 out.write( "<html>" );
1500 out.write( SurfacingConstants.NL );
1501 addHtmlHead( out, title_for_html );
1502 out.write( SurfacingConstants.NL );
1503 out.write( "<body>" );
1504 out.write( SurfacingConstants.NL );
1505 out.write( "<h1>" );
1506 out.write( SurfacingConstants.NL );
1507 out.write( title_for_html );
1508 out.write( SurfacingConstants.NL );
1509 out.write( "</h1>" );
1510 out.write( SurfacingConstants.NL );
1511 out.write( "<table>" );
1512 out.write( SurfacingConstants.NL );
1513 for( final String id : sorted_ids ) {
1514 out.write( "<tr>" );
1515 out.write( "<td>" );
1516 out.write( "<a href=\"#" + id + "\">" + id + "</a>" );
1517 writeTaxonomyLinks( out, id );
1518 out.write( "</td>" );
1519 out.write( "</tr>" );
1520 out.write( SurfacingConstants.NL );
1522 out.write( "</table>" );
1523 out.write( SurfacingConstants.NL );
1524 for( final String id : sorted_ids ) {
1525 out.write( SurfacingConstants.NL );
1526 out.write( "<h2>" );
1527 out.write( "<a name=\"" + id + "\">" + id + "</a>" );
1528 writeTaxonomyLinks( out, id );
1529 out.write( "</h2>" );
1530 out.write( SurfacingConstants.NL );
1531 out.write( "<table>" );
1532 out.write( SurfacingConstants.NL );
1533 out.write( "<tr>" );
1534 out.write( "<td><b>" );
1535 out.write( "Pfam domain(s)" );
1536 out.write( "</b></td><td><b>" );
1537 out.write( "GO term acc" );
1538 out.write( "</b></td><td><b>" );
1539 out.write( "GO term" );
1540 out.write( "</b></td><td><b>" );
1541 out.write( "Penultimate GO term" );
1542 out.write( "</b></td><td><b>" );
1543 out.write( "GO namespace" );
1544 out.write( "</b></td>" );
1545 out.write( "</tr>" );
1546 out.write( SurfacingConstants.NL );
1547 out.write( "</tr>" );
1548 out.write( SurfacingConstants.NL );
1549 per_node_counter = 0;
1550 if ( matrix.getNumberOfCharacters() > 0 ) {
1551 per_node_go_mapped_domain_gain_loss_outfile = new File( per_node_go_mapped_domain_gain_loss_files_base_dir
1552 + ForesterUtil.FILE_SEPARATOR + id + suffix_for_per_node_events_file );
1553 SurfacingUtil.checkForOutputFileWriteability( per_node_go_mapped_domain_gain_loss_outfile );
1554 per_node_go_mapped_domain_gain_loss_outfile_writer = ForesterUtil
1555 .createBufferedWriter( per_node_go_mapped_domain_gain_loss_outfile );
1558 per_node_go_mapped_domain_gain_loss_outfile = null;
1559 per_node_go_mapped_domain_gain_loss_outfile_writer = null;
1561 for( int c = 0; c < matrix.getNumberOfCharacters(); ++c ) {
1563 // using null to indicate either UNCHANGED_PRESENT or GAIN.
1564 if ( ( matrix.getState( id, c ) == state )
1565 || ( ( state == null ) && ( ( matrix.getState( id, c ) == CharacterStateMatrix.GainLossStates.UNCHANGED_PRESENT ) || ( matrix
1566 .getState( id, c ) == CharacterStateMatrix.GainLossStates.GAIN ) ) ) ) {
1567 final String character = matrix.getCharacter( c );
1568 String domain_0 = "";
1569 String domain_1 = "";
1570 if ( character.indexOf( BinaryDomainCombination.SEPARATOR ) > 0 ) {
1571 final String[] s = character.split( BinaryDomainCombination.SEPARATOR );
1572 if ( s.length != 2 ) {
1573 throw new AssertionError( "this should not have happened: unexpected format for domain combination: ["
1574 + character + "]" );
1580 domain_0 = character;
1582 writeDomainData( domain_id_to_go_ids_map,
1589 character_separator,
1590 domain_id_to_secondary_features_maps,
1592 all_pfams_encountered.add( domain_0 );
1593 if ( pfams_gained_or_lost != null ) {
1594 pfams_gained_or_lost.add( domain_0 );
1596 if ( !ForesterUtil.isEmpty( domain_1 ) ) {
1597 all_pfams_encountered.add( domain_1 );
1598 if ( pfams_gained_or_lost != null ) {
1599 pfams_gained_or_lost.add( domain_1 );
1602 if ( per_node_go_mapped_domain_gain_loss_outfile_writer != null ) {
1603 writeDomainsToIndividualFilePerTreeNode( per_node_go_mapped_domain_gain_loss_outfile_writer,
1610 if ( per_node_go_mapped_domain_gain_loss_outfile_writer != null ) {
1611 per_node_go_mapped_domain_gain_loss_outfile_writer.close();
1612 if ( per_node_counter < 1 ) {
1613 per_node_go_mapped_domain_gain_loss_outfile.delete();
1615 per_node_counter = 0;
1617 out.write( "</table>" );
1618 out.write( SurfacingConstants.NL );
1619 out.write( "<hr>" );
1620 out.write( SurfacingConstants.NL );
1621 } // for( final String id : sorted_ids ) {
1622 out.write( "</body>" );
1623 out.write( SurfacingConstants.NL );
1624 out.write( "</html>" );
1625 out.write( SurfacingConstants.NL );
1629 catch ( final IOException e ) {
1630 ForesterUtil.fatalError( surfacing_old.PRG_NAME, e.getMessage() );
1632 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Wrote characters detailed HTML list: \"" + filename
1636 public static void writeDomainCombinationsCountsFile( final String[][] input_file_properties,
1637 final File output_dir,
1638 final Writer per_genome_domain_promiscuity_statistics_writer,
1639 final GenomeWideCombinableDomains gwcd,
1641 final GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order ) {
1642 File dc_outfile = new File( input_file_properties[ i ][ 0 ]
1643 + surfacing_old.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
1644 if ( output_dir != null ) {
1645 dc_outfile = new File( output_dir + ForesterUtil.FILE_SEPARATOR + dc_outfile );
1647 checkForOutputFileWriteability( dc_outfile );
1649 final BufferedWriter out = new BufferedWriter( new FileWriter( dc_outfile ) );
1650 out.write( gwcd.toStringBuilder( dc_sort_order ).toString() );
1653 catch ( final IOException e ) {
1654 ForesterUtil.fatalError( surfacing_old.PRG_NAME, e.getMessage() );
1656 final DescriptiveStatistics stats = gwcd.getPerGenomeDomainPromiscuityStatistics();
1658 per_genome_domain_promiscuity_statistics_writer.write( input_file_properties[ i ][ 0 ] + "\t" );
1659 per_genome_domain_promiscuity_statistics_writer.write( FORMATTER_3.format( stats.arithmeticMean() ) + "\t" );
1660 if ( stats.getN() < 2 ) {
1661 per_genome_domain_promiscuity_statistics_writer.write( "n/a" + "\t" );
1664 per_genome_domain_promiscuity_statistics_writer.write( FORMATTER_3.format( stats
1665 .sampleStandardDeviation() )
1668 per_genome_domain_promiscuity_statistics_writer.write( FORMATTER_3.format( stats.median() ) + "\t" );
1669 per_genome_domain_promiscuity_statistics_writer.write( ( int ) stats.getMin() + "\t" );
1670 per_genome_domain_promiscuity_statistics_writer.write( ( int ) stats.getMax() + "\t" );
1671 per_genome_domain_promiscuity_statistics_writer.write( stats.getN() + "\t" );
1672 final SortedSet<DomainId> mpds = gwcd.getMostPromiscuosDomain();
1673 for( final DomainId mpd : mpds ) {
1674 per_genome_domain_promiscuity_statistics_writer.write( mpd.getId() + " " );
1676 per_genome_domain_promiscuity_statistics_writer.write( ForesterUtil.LINE_SEPARATOR );
1678 catch ( final IOException e ) {
1679 ForesterUtil.fatalError( surfacing_old.PRG_NAME, e.getMessage() );
1681 if ( input_file_properties[ i ].length == 3 ) {
1682 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Wrote domain combination counts for \""
1683 + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ", "
1684 + input_file_properties[ i ][ 2 ] + ") to: \"" + dc_outfile + "\"" );
1687 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Wrote domain combination counts for \""
1688 + input_file_properties[ i ][ 0 ] + "\" (" + input_file_properties[ i ][ 1 ] + ") to: \""
1689 + dc_outfile + "\"" );
1693 private static void writeDomainData( final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
1694 final Map<GoId, GoTerm> go_id_to_term_map,
1695 final GoNameSpace go_namespace_limit,
1697 final String domain_0,
1698 final String domain_1,
1699 final String prefix_for_html,
1700 final String character_separator_for_non_html_output,
1701 final Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps,
1702 final Set<GoId> all_go_ids ) throws IOException {
1703 boolean any_go_annotation_present = false;
1704 boolean first_has_no_go = false;
1705 int domain_count = 2; // To distinguish between domains and binary domain combinations.
1706 if ( ForesterUtil.isEmpty( domain_1 ) ) {
1709 // The following has a difficult to understand logic.
1710 for( int d = 0; d < domain_count; ++d ) {
1711 List<GoId> go_ids = null;
1712 boolean go_annotation_present = false;
1714 final DomainId domain_id = new DomainId( domain_0 );
1715 if ( domain_id_to_go_ids_map.containsKey( domain_id ) ) {
1716 go_annotation_present = true;
1717 any_go_annotation_present = true;
1718 go_ids = domain_id_to_go_ids_map.get( domain_id );
1721 first_has_no_go = true;
1725 final DomainId domain_id = new DomainId( domain_1 );
1726 if ( domain_id_to_go_ids_map.containsKey( domain_id ) ) {
1727 go_annotation_present = true;
1728 any_go_annotation_present = true;
1729 go_ids = domain_id_to_go_ids_map.get( domain_id );
1732 if ( go_annotation_present ) {
1733 boolean first = ( ( d == 0 ) || ( ( d == 1 ) && first_has_no_go ) );
1734 for( final GoId go_id : go_ids ) {
1735 out.write( "<tr>" );
1738 writeDomainIdsToHtml( out,
1742 domain_id_to_secondary_features_maps );
1745 out.write( "<td></td>" );
1747 if ( !go_id_to_term_map.containsKey( go_id ) ) {
1748 throw new IllegalArgumentException( "GO-id [" + go_id + "] not found in GO-id to GO-term map" );
1750 final GoTerm go_term = go_id_to_term_map.get( go_id );
1751 if ( ( go_namespace_limit == null ) || go_namespace_limit.equals( go_term.getGoNameSpace() ) ) {
1752 // final String top = GoUtils.getPenultimateGoTerm( go_term, go_id_to_term_map ).getName();
1753 final String go_id_str = go_id.getId();
1754 out.write( "<td>" );
1755 out.write( "<a href=\"" + SurfacingConstants.AMIGO_LINK + go_id_str
1756 + "\" target=\"amigo_window\">" + go_id_str + "</a>" );
1757 out.write( "</td><td>" );
1758 out.write( go_term.getName() );
1759 if ( domain_count == 2 ) {
1760 out.write( " (" + d + ")" );
1762 out.write( "</td><td>" );
1763 // out.write( top );
1764 // out.write( "</td><td>" );
1766 out.write( go_term.getGoNameSpace().toShortString() );
1768 out.write( "</td>" );
1769 if ( all_go_ids != null ) {
1770 all_go_ids.add( go_id );
1774 out.write( "<td>" );
1775 out.write( "</td><td>" );
1776 out.write( "</td><td>" );
1777 out.write( "</td><td>" );
1778 out.write( "</td>" );
1780 out.write( "</tr>" );
1781 out.write( SurfacingConstants.NL );
1784 } // for( int d = 0; d < domain_count; ++d )
1785 if ( !any_go_annotation_present ) {
1786 out.write( "<tr>" );
1787 writeDomainIdsToHtml( out, domain_0, domain_1, prefix_for_html, domain_id_to_secondary_features_maps );
1788 out.write( "<td>" );
1789 out.write( "</td><td>" );
1790 out.write( "</td><td>" );
1791 out.write( "</td><td>" );
1792 out.write( "</td>" );
1793 out.write( "</tr>" );
1794 out.write( SurfacingConstants.NL );
1798 private static void writeDomainDataORIG( final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
1799 final Map<GoId, GoTerm> go_id_to_term_map,
1800 final GoNameSpace go_namespace_limit,
1802 final String domain_0,
1803 final String domain_1,
1804 final String prefix_for_html,
1805 final String character_separator_for_non_html_output,
1806 final Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps,
1807 final Set<GoId> all_go_ids ) throws IOException {
1808 boolean any_go_annotation_present = false;
1809 boolean first_has_no_go = false;
1810 int domain_count = 2; // To distinguish between domains and binary domain combinations.
1811 if ( ForesterUtil.isEmpty( domain_1 ) ) {
1814 // The following has a difficult to understand logic.
1815 for( int d = 0; d < domain_count; ++d ) {
1816 List<GoId> go_ids = null;
1817 boolean go_annotation_present = false;
1819 final DomainId domain_id = new DomainId( domain_0 );
1820 if ( domain_id_to_go_ids_map.containsKey( domain_id ) ) {
1821 go_annotation_present = true;
1822 any_go_annotation_present = true;
1823 go_ids = domain_id_to_go_ids_map.get( domain_id );
1826 first_has_no_go = true;
1830 final DomainId domain_id = new DomainId( domain_1 );
1831 if ( domain_id_to_go_ids_map.containsKey( domain_id ) ) {
1832 go_annotation_present = true;
1833 any_go_annotation_present = true;
1834 go_ids = domain_id_to_go_ids_map.get( domain_id );
1837 if ( go_annotation_present ) {
1838 boolean first = ( ( d == 0 ) || ( ( d == 1 ) && first_has_no_go ) );
1839 for( final GoId go_id : go_ids ) {
1840 out.write( "<tr>" );
1843 writeDomainIdsToHtml( out,
1847 domain_id_to_secondary_features_maps );
1850 out.write( "<td></td>" );
1852 if ( !go_id_to_term_map.containsKey( go_id ) ) {
1853 throw new IllegalArgumentException( "GO-id [" + go_id + "] not found in GO-id to GO-term map" );
1855 final GoTerm go_term = go_id_to_term_map.get( go_id );
1856 if ( ( go_namespace_limit == null ) || go_namespace_limit.equals( go_term.getGoNameSpace() ) ) {
1857 final String top = GoUtils.getPenultimateGoTerm( go_term, go_id_to_term_map ).getName();
1858 final String go_id_str = go_id.getId();
1859 out.write( "<td>" );
1860 out.write( "<a href=\"" + SurfacingConstants.AMIGO_LINK + go_id_str
1861 + "\" target=\"amigo_window\">" + go_id_str + "</a>" );
1862 out.write( "</td><td>" );
1863 out.write( go_term.getName() );
1864 if ( domain_count == 2 ) {
1865 out.write( " (" + d + ")" );
1867 out.write( "</td><td>" );
1869 out.write( "</td><td>" );
1871 out.write( go_term.getGoNameSpace().toShortString() );
1873 out.write( "</td>" );
1874 if ( all_go_ids != null ) {
1875 all_go_ids.add( go_id );
1879 out.write( "<td>" );
1880 out.write( "</td><td>" );
1881 out.write( "</td><td>" );
1882 out.write( "</td><td>" );
1883 out.write( "</td>" );
1885 out.write( "</tr>" );
1886 out.write( SurfacingConstants.NL );
1889 } // for( int d = 0; d < domain_count; ++d )
1890 if ( !any_go_annotation_present ) {
1891 out.write( "<tr>" );
1892 writeDomainIdsToHtml( out, domain_0, domain_1, prefix_for_html, domain_id_to_secondary_features_maps );
1893 out.write( "<td>" );
1894 out.write( "</td><td>" );
1895 out.write( "</td><td>" );
1896 out.write( "</td><td>" );
1897 out.write( "</td>" );
1898 out.write( "</tr>" );
1899 out.write( SurfacingConstants.NL );
1903 private static void writeDomainIdsToHtml( final Writer out,
1904 final String domain_0,
1905 final String domain_1,
1906 final String prefix_for_detailed_html,
1907 final Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps )
1908 throws IOException {
1909 out.write( "<td>" );
1910 if ( !ForesterUtil.isEmpty( prefix_for_detailed_html ) ) {
1911 out.write( prefix_for_detailed_html );
1914 out.write( "<a href=\"" + SurfacingConstants.PFAM_FAMILY_ID_LINK + domain_0 + "\">" + domain_0 + "</a>" );
1915 //if ( ForesterUtil.isEmpty( domain_1 ) ) {
1916 // out.write( " <a href=\"" + SurfacingConstants.GOOGLE_SCHOLAR_LINK + domain_0
1917 // + SurfacingConstants.GOOGLE_SCHOLAR_LIMITS + "\">[gs]</a>" );
1919 // if ( !ForesterUtil.isEmpty( domain_1 ) ) {
1920 // out.write( "=" );
1921 // out.write( "<a href=\"" + SurfacingConstants.PFAM_FAMILY_ID_LINK + domain_1 + "\">" + domain_1 + "</a>" );
1923 // else if ( ( domain_id_to_secondary_features_maps != null )
1924 // && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
1925 // out.write( " [" );
1926 // boolean first = true;
1927 // for( final Map<DomainId, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
1928 // final Set<String> sec_features = domain_id_to_secondary_features_map.get( new DomainId( domain_0 ) );
1929 // if ( ( sec_features != null ) && ( sec_features.size() > 0 ) ) {
1930 // for( final String sec_feature : sec_features ) {
1935 // out.write( ", " );
1937 // if ( SurfacingConstants.SECONDARY_FEATURES_ARE_SCOP
1938 // && ( SurfacingConstants.SECONDARY_FEATURES_SCOP_LINK != null ) ) {
1939 // out.write( "<a href=\"" + SurfacingConstants.SECONDARY_FEATURES_SCOP_LINK + sec_feature
1940 // + "\" target=\"scop_window\">" + sec_feature + "</a>" );
1943 // out.write( sec_feature );
1948 // out.write( "]" );
1950 out.write( "</td>" );
1953 private static void writeDomainIdsToHtmlORIG( final Writer out,
1954 final String domain_0,
1955 final String domain_1,
1956 final String prefix_for_detailed_html,
1957 final Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps )
1958 throws IOException {
1959 out.write( "<td>" );
1960 if ( !ForesterUtil.isEmpty( prefix_for_detailed_html ) ) {
1961 out.write( prefix_for_detailed_html );
1964 out.write( "<a href=\"" + SurfacingConstants.PFAM_FAMILY_ID_LINK + domain_0 + "\">" + domain_0 + "</a>" );
1965 if ( ForesterUtil.isEmpty( domain_1 ) ) {
1966 out.write( " <a href=\"" + SurfacingConstants.GOOGLE_SCHOLAR_LINK + domain_0
1967 + SurfacingConstants.GOOGLE_SCHOLAR_LIMITS + "\">[gs]</a>" );
1969 if ( !ForesterUtil.isEmpty( domain_1 ) ) {
1971 out.write( "<a href=\"" + SurfacingConstants.PFAM_FAMILY_ID_LINK + domain_1 + "\">" + domain_1 + "</a>" );
1973 else if ( ( domain_id_to_secondary_features_maps != null )
1974 && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
1976 boolean first = true;
1977 for( final Map<DomainId, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
1978 final Set<String> sec_features = domain_id_to_secondary_features_map.get( new DomainId( domain_0 ) );
1979 if ( ( sec_features != null ) && ( sec_features.size() > 0 ) ) {
1980 for( final String sec_feature : sec_features ) {
1987 if ( SurfacingConstants.SECONDARY_FEATURES_ARE_SCOP
1988 && ( SurfacingConstants.SECONDARY_FEATURES_SCOP_LINK != null ) ) {
1989 out.write( "<a href=\"" + SurfacingConstants.SECONDARY_FEATURES_SCOP_LINK + sec_feature
1990 + "\" target=\"scop_window\">" + sec_feature + "</a>" );
1993 out.write( sec_feature );
2000 out.write( "</td>" );
2003 public static DescriptiveStatistics writeDomainSimilaritiesToFile( final StringBuilder html_desc,
2004 final StringBuilder html_title,
2006 final SortedSet<DomainSimilarity> similarities,
2007 final boolean treat_as_binary,
2008 final List<Species> species_order,
2009 final PrintableDomainSimilarity.PRINT_OPTION print_option,
2010 final DomainSimilarity.DomainSimilaritySortField sort_field,
2011 final DomainSimilarity.DomainSimilarityScoring scoring,
2012 final boolean verbose ) throws IOException {
2013 final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
2014 String histogram_title = null;
2015 switch ( sort_field ) {
2016 case ABS_MAX_COUNTS_DIFFERENCE:
2017 if ( treat_as_binary ) {
2018 histogram_title = "absolute counts difference:";
2021 histogram_title = "absolute (maximal) counts difference:";
2024 case MAX_COUNTS_DIFFERENCE:
2025 if ( treat_as_binary ) {
2026 histogram_title = "counts difference:";
2029 histogram_title = "(maximal) counts difference:";
2033 histogram_title = "score mean:";
2036 histogram_title = "score minimum:";
2039 histogram_title = "score maximum:";
2041 case MAX_DIFFERENCE:
2042 if ( treat_as_binary ) {
2043 histogram_title = "difference:";
2046 histogram_title = "(maximal) difference:";
2050 histogram_title = "score mean:";
2053 histogram_title = "score standard deviation:";
2056 histogram_title = "species number:";
2059 throw new AssertionError( "Unknown sort field: " + sort_field );
2061 for( final DomainSimilarity similarity : similarities ) {
2062 switch ( sort_field ) {
2063 case ABS_MAX_COUNTS_DIFFERENCE:
2064 stats.addValue( Math.abs( similarity.getMaximalDifferenceInCounts() ) );
2066 case MAX_COUNTS_DIFFERENCE:
2067 stats.addValue( similarity.getMaximalDifferenceInCounts() );
2070 stats.addValue( similarity.getMeanSimilarityScore() );
2073 stats.addValue( similarity.getMinimalSimilarityScore() );
2076 stats.addValue( similarity.getMaximalSimilarityScore() );
2078 case MAX_DIFFERENCE:
2079 stats.addValue( similarity.getMaximalDifference() );
2082 stats.addValue( similarity.getMeanSimilarityScore() );
2085 stats.addValue( similarity.getStandardDeviationOfSimilarityScore() );
2088 stats.addValue( similarity.getSpecies().size() );
2091 throw new AssertionError( "Unknown sort field: " + sort_field );
2095 // final HistogramData[] hists = new HistogramData[ 1 ];
2098 // List<HistogramDataItem> data_items = new
2099 // ArrayList<HistogramDataItem>();
2100 // double[] values = stats.getDataAsDoubleArray();
2101 // for( int i = 0; i < values.length; i++ ) {
2102 // HistogramDataItem data_item = new BasicHistogramDataItem( "", values[
2104 // data_items.add( data_item );
2108 // HistogramData hd0 = new HistogramData( "name",
2116 // hists[ 0 ] = hd0;
2118 // final HistogramsFrame hf = new HistogramsFrame( hists );
2119 // hf.setVisible( true );
2121 AsciiHistogram histo = null;
2122 if ( stats.getMin() < stats.getMin() ) {
2123 histo = new AsciiHistogram( stats, histogram_title );
2126 if ( histo != null ) {
2127 System.out.println( histo.toStringBuffer( 20, '|', 40, 5 ) );
2129 System.out.println();
2130 System.out.println( "N : " + stats.getN() );
2131 System.out.println( "Min : " + stats.getMin() );
2132 System.out.println( "Max : " + stats.getMax() );
2133 System.out.println( "Mean : " + stats.arithmeticMean() );
2134 if ( stats.getN() > 1 ) {
2135 System.out.println( "SD : " + stats.sampleStandardDeviation() );
2138 System.out.println( "SD : n/a" );
2140 System.out.println( "Median : " + stats.median() );
2141 if ( stats.getN() > 1 ) {
2142 System.out.println( "Pearsonian skewness : " + stats.pearsonianSkewness() );
2145 System.out.println( "Pearsonian skewness : n/a" );
2148 switch ( print_option ) {
2149 case SIMPLE_TAB_DELIMITED:
2152 w.write( "<html>" );
2153 w.write( SurfacingConstants.NL );
2154 addHtmlHead( w, "SURFACING :: " + html_title );
2155 w.write( SurfacingConstants.NL );
2156 w.write( "<body>" );
2157 w.write( SurfacingConstants.NL );
2158 w.write( html_desc.toString() );
2159 w.write( SurfacingConstants.NL );
2162 w.write( SurfacingConstants.NL );
2163 w.write( "<tt><pre>" );
2164 w.write( SurfacingConstants.NL );
2165 if ( histo != null ) {
2166 w.write( histo.toStringBuffer( 20, '|', 40, 5 ).toString() );
2167 w.write( SurfacingConstants.NL );
2169 w.write( "</pre></tt>" );
2170 w.write( SurfacingConstants.NL );
2171 w.write( "<table>" );
2172 w.write( SurfacingConstants.NL );
2173 w.write( "<tr><td>N: </td><td>" + stats.getN() + "</td></tr>" );
2174 w.write( SurfacingConstants.NL );
2175 w.write( "<tr><td>Min: </td><td>" + stats.getMin() + "</td></tr>" );
2176 w.write( SurfacingConstants.NL );
2177 w.write( "<tr><td>Max: </td><td>" + stats.getMax() + "</td></tr>" );
2178 w.write( SurfacingConstants.NL );
2179 w.write( "<tr><td>Mean: </td><td>" + stats.arithmeticMean() + "</td></tr>" );
2180 w.write( SurfacingConstants.NL );
2181 if ( stats.getN() > 1 ) {
2182 w.write( "<tr><td>SD: </td><td>" + stats.sampleStandardDeviation() + "</td></tr>" );
2185 w.write( "<tr><td>SD: </td><td>n/a</td></tr>" );
2187 w.write( SurfacingConstants.NL );
2188 w.write( "<tr><td>Median: </td><td>" + stats.median() + "</td></tr>" );
2189 w.write( SurfacingConstants.NL );
2190 if ( stats.getN() > 1 ) {
2191 w.write( "<tr><td>Pearsonian skewness: </td><td>" + stats.pearsonianSkewness() + "</td></tr>" );
2194 w.write( "<tr><td>Pearsonian skewness: </td><td>n/a</td></tr>" );
2196 w.write( SurfacingConstants.NL );
2197 w.write( "</table>" );
2198 w.write( SurfacingConstants.NL );
2200 w.write( SurfacingConstants.NL );
2202 w.write( SurfacingConstants.NL );
2204 w.write( SurfacingConstants.NL );
2205 w.write( "<table>" );
2206 w.write( SurfacingConstants.NL );
2209 w.write( SurfacingConstants.NL );
2210 for( final DomainSimilarity similarity : similarities ) {
2211 if ( ( species_order != null ) && !species_order.isEmpty() ) {
2212 ( ( PrintableDomainSimilarity ) similarity ).setSpeciesOrder( species_order );
2214 w.write( similarity.toStringBuffer( print_option ).toString() );
2215 w.write( SurfacingConstants.NL );
2217 switch ( print_option ) {
2219 w.write( SurfacingConstants.NL );
2220 w.write( "</table>" );
2221 w.write( SurfacingConstants.NL );
2222 w.write( "</font>" );
2223 w.write( SurfacingConstants.NL );
2224 w.write( "</body>" );
2225 w.write( SurfacingConstants.NL );
2226 w.write( "</html>" );
2227 w.write( SurfacingConstants.NL );
2235 private static void writeDomainsToIndividualFilePerTreeNode( final Writer individual_files_writer,
2236 final String domain_0,
2237 final String domain_1 ) throws IOException {
2238 individual_files_writer.write( domain_0 );
2239 individual_files_writer.write( ForesterUtil.LINE_SEPARATOR );
2240 if ( !ForesterUtil.isEmpty( domain_1 ) ) {
2241 individual_files_writer.write( domain_1 );
2242 individual_files_writer.write( ForesterUtil.LINE_SEPARATOR );
2246 public static void writeMatrixToFile( final CharacterStateMatrix<?> matrix,
2247 final String filename,
2248 final Format format ) {
2249 final File outfile = new File( filename );
2250 checkForOutputFileWriteability( outfile );
2252 final BufferedWriter out = new BufferedWriter( new FileWriter( outfile ) );
2253 matrix.toWriter( out, format );
2257 catch ( final IOException e ) {
2258 ForesterUtil.fatalError( surfacing_old.PRG_NAME, e.getMessage() );
2260 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Wrote matrix: \"" + filename + "\"" );
2263 public static void writeMatrixToFile( final File matrix_outfile, final List<DistanceMatrix> matrices ) {
2264 checkForOutputFileWriteability( matrix_outfile );
2266 final BufferedWriter out = new BufferedWriter( new FileWriter( matrix_outfile ) );
2267 for( final DistanceMatrix distance_matrix : matrices ) {
2268 out.write( distance_matrix.toStringBuffer( DistanceMatrix.Format.PHYLIP ).toString() );
2269 out.write( ForesterUtil.LINE_SEPARATOR );
2274 catch ( final IOException e ) {
2275 ForesterUtil.fatalError( surfacing_old.PRG_NAME, e.getMessage() );
2277 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Wrote distance matrices to \"" + matrix_outfile + "\"" );
2280 private static void writePfamsToFile( final String outfile_name, final SortedSet<String> pfams ) {
2282 final Writer writer = new BufferedWriter( new FileWriter( new File( outfile_name ) ) );
2283 for( final String pfam : pfams ) {
2284 writer.write( pfam );
2285 writer.write( ForesterUtil.LINE_SEPARATOR );
2288 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Wrote " + pfams.size() + " pfams to [" + outfile_name
2291 catch ( final IOException e ) {
2292 ForesterUtil.printWarningMessage( surfacing_old.PRG_NAME, "Failure to write: " + e );
2296 public static void writePhylogenyToFile( final Phylogeny phylogeny, final String filename ) {
2297 final PhylogenyWriter writer = new PhylogenyWriter();
2299 writer.toPhyloXML( new File( filename ), phylogeny, 1 );
2301 catch ( final IOException e ) {
2302 ForesterUtil.printWarningMessage( surfacing_old.PRG_NAME, "failed to write phylogeny to \"" + filename
2305 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Wrote phylogeny to \"" + filename + "\"" );
2308 public static void writeTaxonomyLinks( final Writer writer, final String species ) throws IOException {
2309 if ( ( species.length() > 1 ) && ( species.indexOf( '_' ) < 1 ) ) {
2310 final Matcher matcher = PATTERN_SP_STYLE_TAXONOMY.matcher( species );
2311 writer.write( " [" );
2312 if ( matcher.matches() ) {
2313 writer.write( "<a href=\"" + SurfacingConstants.UNIPROT_LINK + species
2314 + "\" target=\"taxonomy_window\">uniprot</a>" );
2317 writer.write( "<a href=\"" + SurfacingConstants.EOL_LINK + species
2318 + "\" target=\"taxonomy_window\">eol</a>" );
2319 writer.write( "|" );
2320 writer.write( "<a href=\"" + SurfacingConstants.TOL_LINK + species
2321 + "\" target=\"taxonomy_window\">tol</a>" );
2323 writer.write( "]" );
2327 public static void writeTaxonomyLinksORIG( final Writer writer, final String species ) throws IOException {
2328 if ( ( species.length() > 1 ) && ( species.indexOf( '_' ) < 1 ) ) {
2329 final Matcher matcher = PATTERN_SP_STYLE_TAXONOMY.matcher( species );
2330 writer.write( " [" );
2331 if ( matcher.matches() ) {
2332 writer.write( "<a href=\"" + SurfacingConstants.UNIPROT_LINK + species
2333 + "\" target=\"taxonomy_window\">uniprot</a>" );
2336 writer.write( "<a href=\"" + SurfacingConstants.EOL_LINK + species
2337 + "\" target=\"taxonomy_window\">eol</a>" );
2338 writer.write( "|" );
2339 writer.write( "<a href=\"" + SurfacingConstants.TOL_LINK + species
2340 + "\" target=\"taxonomy_window\">tol</a>" );
2341 writer.write( "|" );
2342 writer.write( "<a href=\"" + SurfacingConstants.WIKIPEDIA_LINK + species
2343 + "\" target=\"taxonomy_window\">wikipedia</a>" );
2344 writer.write( "|" );
2345 writer.write( "<a href=\"" + SurfacingConstants.GOOGLE_SCHOLAR_LINK + species
2346 + "\" target=\"taxonomy_window\">gs</a>" );
2348 writer.write( "]" );
2352 private static void writeToNexus( final String outfile_name, final CharacterStateMatrix<BinaryStates> matrix ) {
2353 if ( !( matrix instanceof BasicCharacterStateMatrix ) ) {
2354 throw new IllegalArgumentException( "can only write matrices of type [" + BasicCharacterStateMatrix.class
2357 final BasicCharacterStateMatrix<BinaryStates> my_matrix = ( org.forester.evoinference.matrix.character.BasicCharacterStateMatrix<BinaryStates> ) matrix;
2359 final BufferedWriter w = new BufferedWriter( new FileWriter( outfile_name ) );
2360 w.write( NexusConstants.NEXUS );
2361 w.write( ForesterUtil.LINE_SEPARATOR );
2362 my_matrix.writeNexusTaxaBlock( w );
2363 my_matrix.writeNexusBinaryChractersBlock( w );
2366 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Wrote Nexus file: \"" + outfile_name + "\"" );
2368 catch ( final IOException e ) {
2369 ForesterUtil.fatalError( surfacing_old.PRG_NAME, e.getMessage() );
2373 private static void writeToNexus( final String outfile_name,
2374 final CharacterStateMatrix<BinaryStates> matrix,
2375 final Phylogeny phylogeny ) {
2376 if ( !( matrix instanceof BasicCharacterStateMatrix ) ) {
2377 throw new IllegalArgumentException( "can only write matrices of type [" + BasicCharacterStateMatrix.class
2380 final BasicCharacterStateMatrix<BinaryStates> my_matrix = ( org.forester.evoinference.matrix.character.BasicCharacterStateMatrix<BinaryStates> ) matrix;
2381 final List<Phylogeny> phylogenies = new ArrayList<Phylogeny>( 1 );
2382 phylogenies.add( phylogeny );
2384 final BufferedWriter w = new BufferedWriter( new FileWriter( outfile_name ) );
2385 w.write( NexusConstants.NEXUS );
2386 w.write( ForesterUtil.LINE_SEPARATOR );
2387 my_matrix.writeNexusTaxaBlock( w );
2388 my_matrix.writeNexusBinaryChractersBlock( w );
2389 PhylogenyWriter.writeNexusTreesBlock( w, phylogenies );
2392 ForesterUtil.programMessage( surfacing_old.PRG_NAME, "Wrote Nexus file: \"" + outfile_name + "\"" );
2394 catch ( final IOException e ) {
2395 ForesterUtil.fatalError( surfacing_old.PRG_NAME, e.getMessage() );
2399 private static void writeToNexus( final String outfile_name, final DomainParsimonyCalculator domain_parsimony ) {
2400 writeToNexus( outfile_name + surfacing_old.NEXUS_EXTERNAL_DOMAINS, domain_parsimony
2401 .createMatrixOfDomainPresenceOrAbsence() );
2402 writeToNexus( outfile_name + surfacing_old.NEXUS_EXTERNAL_DOMAIN_COMBINATIONS, domain_parsimony
2403 .createMatrixOfBinaryDomainCombinationPresenceOrAbsence() );
2406 private static void writeToNexus( final String outfile_name,
2407 final DomainParsimonyCalculator domain_parsimony,
2408 final Phylogeny phylogeny ) {
2409 writeToNexus( outfile_name + surfacing_old.NEXUS_EXTERNAL_DOMAINS, domain_parsimony
2410 .createMatrixOfDomainPresenceOrAbsence(), phylogeny );
2411 writeToNexus( outfile_name + surfacing_old.NEXUS_EXTERNAL_DOMAIN_COMBINATIONS, domain_parsimony
2412 .createMatrixOfBinaryDomainCombinationPresenceOrAbsence(), phylogeny );