3 // FORESTER -- software libraries and applications
4 // for evolutionary biology research and applications.
6 // Copyright (C) 2008-2009 Christian M. Zmasek
7 // Copyright (C) 2008-2009 Burnham Institute for Medical Research
10 // This library is free software; you can redistribute it and/or
11 // modify it under the terms of the GNU Lesser General Public
12 // License as published by the Free Software Foundation; either
13 // version 2.1 of the License, or (at your option) any later version.
15 // This library is distributed in the hope that it will be useful,
16 // but WITHOUT ANY WARRANTY; without even the implied warranty of
17 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
18 // Lesser General Public License for more details.
20 // You should have received a copy of the GNU Lesser General Public
21 // License along with this library; if not, write to the Free Software
22 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
24 // Contact: phylosoft @ gmail . com
25 // WWW: https://sites.google.com/site/cmzmasek/home/software/forester
27 package org.forester.application;
29 import java.io.BufferedWriter;
31 import java.io.FileWriter;
32 import java.io.IOException;
33 import java.io.Writer;
34 import java.util.ArrayList;
35 import java.util.Date;
36 import java.util.HashMap;
37 import java.util.HashSet;
38 import java.util.List;
40 import java.util.Map.Entry;
42 import java.util.SortedMap;
43 import java.util.SortedSet;
44 import java.util.TreeMap;
45 import java.util.TreeSet;
47 import org.forester.evoinference.matrix.character.CharacterStateMatrix.Format;
48 import org.forester.go.GoId;
49 import org.forester.go.GoNameSpace;
50 import org.forester.go.GoTerm;
51 import org.forester.go.GoUtils;
52 import org.forester.go.OBOparser;
53 import org.forester.go.PfamToGoMapping;
54 import org.forester.go.PfamToGoParser;
55 import org.forester.io.parsers.HmmscanPerDomainTableParser;
56 import org.forester.io.parsers.HmmscanPerDomainTableParser.INDIVIDUAL_SCORE_CUTOFF;
57 import org.forester.io.parsers.phyloxml.PhyloXmlUtil;
58 import org.forester.io.parsers.util.ParserUtils;
59 import org.forester.phylogeny.Phylogeny;
60 import org.forester.phylogeny.PhylogenyMethods;
61 import org.forester.phylogeny.PhylogenyNode;
62 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
63 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
64 import org.forester.protein.BinaryDomainCombination;
65 import org.forester.protein.Domain;
66 import org.forester.protein.Protein;
67 import org.forester.species.BasicSpecies;
68 import org.forester.species.Species;
69 import org.forester.surfacing.BasicDomainSimilarityCalculator;
70 import org.forester.surfacing.BasicGenomeWideCombinableDomains;
71 import org.forester.surfacing.CombinationsBasedPairwiseDomainSimilarityCalculator;
72 import org.forester.surfacing.DomainCountsBasedPairwiseSimilarityCalculator;
73 import org.forester.surfacing.DomainCountsDifferenceUtil;
74 import org.forester.surfacing.DomainLengthsTable;
75 import org.forester.surfacing.DomainParsimonyCalculator;
76 import org.forester.surfacing.DomainSimilarity;
77 import org.forester.surfacing.DomainSimilarity.DomainSimilarityScoring;
78 import org.forester.surfacing.DomainSimilarity.DomainSimilaritySortField;
79 import org.forester.surfacing.DomainSimilarityCalculator;
80 import org.forester.surfacing.DomainSimilarityCalculator.Detailedness;
81 import org.forester.surfacing.GenomeWideCombinableDomains;
82 import org.forester.surfacing.GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder;
83 import org.forester.surfacing.MappingResults;
84 import org.forester.surfacing.PairwiseDomainSimilarityCalculator;
85 import org.forester.surfacing.PairwiseGenomeComparator;
86 import org.forester.surfacing.PrintableDomainSimilarity;
87 import org.forester.surfacing.PrintableDomainSimilarity.PRINT_OPTION;
88 import org.forester.surfacing.ProteinCountsBasedPairwiseDomainSimilarityCalculator;
89 import org.forester.surfacing.SurfacingUtil;
90 import org.forester.util.BasicDescriptiveStatistics;
91 import org.forester.util.BasicTable;
92 import org.forester.util.BasicTableParser;
93 import org.forester.util.CommandLineArguments;
94 import org.forester.util.DescriptiveStatistics;
95 import org.forester.util.ForesterConstants;
96 import org.forester.util.ForesterUtil;
98 public class surfacing {
100 private static final int MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING = 1000;
101 public final static String DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS = "graph_analysis_out";
102 public final static String DOMAIN_COMBINITONS_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_dc.dot";
103 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_fitch_present_dc.dot";
104 public final static String DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX = ".dcc";
106 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS = "_dollo_gl_d";
107 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_gl_dc";
108 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_DOMAINS = "_fitch_gl_d";
109 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_gl_dc";
111 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS = "_dollo_glc_d";
112 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_glc_dc";
113 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_DOMAINS = "_fitch_glc_d";
114 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_glc_dc";
116 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_BC = "_fitch_gains_dc";
117 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_HTML_BC = "_fitch_gains_dc.html";
118 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_BC = "_fitch_losses_dc";
119 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_HTML_BC = "_fitch_losses_dc.html";
120 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC = "_fitch_present_dc";
121 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_HTML_BC = "_fitch_present_dc.html";
122 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_D = "_dollo_gains_d";
123 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_HTML_D = "_dollo_gains_d.html";
124 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_D = "_dollo_losses_d";
125 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_HTML_D = "_dollo_losses_d.html";
126 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_D = "_dollo_present_d";
127 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_HTML_D = "_dollo_present_d.html";
128 public final static String DOMAINS_PRESENT_NEXUS = "_dom.nex";
129 public final static String BDC_PRESENT_NEXUS = "_dc.nex";
131 public final static String PRG_NAME = "surfacing";
132 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_d_dollo"
133 + ForesterConstants.PHYLO_XML_SUFFIX;
134 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_d_fitch"
135 + ForesterConstants.PHYLO_XML_SUFFIX;
136 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_dc_dollo"
137 + ForesterConstants.PHYLO_XML_SUFFIX;
138 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_dc_fitch"
139 + ForesterConstants.PHYLO_XML_SUFFIX;
140 public static final String NEXUS_EXTERNAL_DOMAINS = "_dom.nex";
141 public static final String NEXUS_EXTERNAL_DOMAIN_COMBINATIONS = "_dc.nex";
142 public static final String NEXUS_SECONDARY_FEATURES = "_secondary_features.nex";
143 public static final String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_gl_secondary_features";
144 public static final String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_glc_secondary_features";
145 public static final String PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES = "_dollo_gains_secondary_features";
146 public static final String PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES = "_dollo_losses_secondary_features";
147 public static final String PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES = "_dollo_present_secondary_features";
148 public static final String SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_secondary_features_dollo"
149 + ForesterConstants.PHYLO_XML_SUFFIX;
150 public static final String PARSIMONY_OUTPUT_DOLLO_ALL_GOID_D_ALL_NAMESPACES = "_dollo_goid_d";
151 public static final String PARSIMONY_OUTPUT_FITCH_ALL_GOID_BC_ALL_NAMESPACES = "_fitch_goid_dc";
152 final static private String HELP_OPTION_1 = "help";
153 final static private String HELP_OPTION_2 = "h";
154 final static private String OUTPUT_DIR_OPTION = "out_dir";
155 final static private String SCORING_OPTION = "scoring";
156 private static final DomainSimilarityScoring SCORING_DEFAULT = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
157 final static private String SCORING_DOMAIN_COUNT_BASED = "domains";
158 final static private String SCORING_PROTEIN_COUNT_BASED = "proteins";
159 final static private String SCORING_COMBINATION_BASED = "combinations";
160 final static private String DETAILEDNESS_OPTION = "detail";
161 private final static Detailedness DETAILEDNESS_DEFAULT = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
162 final static private String SPECIES_MATRIX_OPTION = "smatrix";
163 final static private String DETAILEDNESS_BASIC = "basic";
164 final static private String DETAILEDNESS_LIST_IDS = "list_ids";
165 final static private String DETAILEDNESS_PUNCTILIOUS = "punctilious";
166 final static private String DOMAIN_SIMILARITY_SORT_OPTION = "sort";
167 private static final DomainSimilaritySortField DOMAIN_SORT_FILD_DEFAULT = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
168 final static private String DOMAIN_SIMILARITY_SORT_MIN = "min";
169 final static private String DOMAIN_SIMILARITY_SORT_MAX = "max";
170 final static private String DOMAIN_SIMILARITY_SORT_SD = "sd";
171 final static private String DOMAIN_SIMILARITY_SORT_MEAN = "mean";
172 final static private String DOMAIN_SIMILARITY_SORT_DIFF = "diff";
173 final static private String DOMAIN_SIMILARITY_SORT_COUNTS_DIFF = "count_diff";
174 final static private String DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF = "abs_count_diff";
175 final static private String DOMAIN_SIMILARITY_SORT_SPECIES_COUNT = "species";
176 final static private String DOMAIN_SIMILARITY_SORT_ALPHA = "alpha";
177 final static private String DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION = "species_first";
178 final static private String DOMAIN_COUNT_SORT_OPTION = "dc_sort";
179 private static final GenomeWideCombinableDomainsSortOrder DOMAINS_SORT_ORDER_DEFAULT = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
180 final static private String DOMAIN_COUNT_SORT_ALPHA = "alpha";
181 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT = "dom";
182 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT = "prot";
183 final static private String DOMAIN_COUNT_SORT_COMBINATIONS_COUNT = "comb";
184 final static private String CUTOFF_SCORE_FILE_OPTION = "cos";
185 final static private String NOT_IGNORE_DUFS_OPTION = "dufs";
186 final static private String MAX_E_VALUE_OPTION = "e";
187 final static private String MAX_ALLOWED_OVERLAP_OPTION = "mo";
188 final static private String NO_ENGULFING_OVERLAP_OPTION = "no_eo";
189 final static private String IGNORE_COMBINATION_WITH_SAME_OPTION = "ignore_self_comb";
190 final static private String PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION = "dc_regain_stats";
191 final static private String DA_ANALYSIS_OPTION = "DA_analyis";
192 final static private String USE_LAST_IN_FITCH_OPTION = "last";
193 final static private String PAIRWISE_DOMAIN_COMPARISONS_PREFIX = "pwc_";
194 final static private String PAIRWISE_DOMAIN_COMPARISONS_OPTION = "pwc";
195 final static private String OUTPUT_FILE_OPTION = "o";
196 final static private String PFAM_TO_GO_FILE_USE_OPTION = "p2g";
197 final static private String GO_OBO_FILE_USE_OPTION = "obo";
198 final static private String GO_NAMESPACE_LIMIT_OPTION = "go_namespace";
199 final static private String GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION = "molecular_function";
200 final static private String GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS = "biological_process";
201 final static private String GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT = "cellular_component";
202 final static private String SECONDARY_FEATURES_PARSIMONY_MAP_FILE = "secondary";
203 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED = "simple_tab";
204 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML = "simple_html";
205 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML = "detailed_html";
206 final static private String DOMAIN_SIMILARITY_PRINT_OPTION = "ds_output";
207 private static final PRINT_OPTION DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT = PrintableDomainSimilarity.PRINT_OPTION.HTML;
208 final static private String IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION = "ignore_singlet_domains";
209 final static private String IGNORE_VIRAL_IDS = "ignore_viral_ids";
210 final static private boolean IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT = false;
211 final static private String IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION = "ignore_species_specific_domains";
212 final static private boolean IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT = false;
213 final static private String MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score.pwd";
214 final static private String MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains.pwd";
215 final static private String MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations.pwd";
216 final static private String NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score_NJ"
217 + ForesterConstants.PHYLO_XML_SUFFIX;
218 final static private String NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains_NJ"
219 + ForesterConstants.PHYLO_XML_SUFFIX;
220 final static private String NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations_NJ"
221 + ForesterConstants.PHYLO_XML_SUFFIX;
222 final static private String FILTER_POSITIVE_OPTION = "pos_filter";
223 final static private String FILTER_NEGATIVE_OPTION = "neg_filter";
224 final static private String FILTER_NEGATIVE_DOMAINS_OPTION = "neg_dom_filter";
225 final static private String INPUT_GENOMES_FILE_OPTION = "genomes";
226 final static private String INPUT_SPECIES_TREE_OPTION = "species_tree";
227 final static private String SEQ_EXTRACT_OPTION = "prot_extract";
228 final static private String PRG_VERSION = "2.290";
229 final static private String PRG_DATE = "130709";
230 final static private String E_MAIL = "czmasek@burnham.org";
231 final static private String WWW = "https://sites.google.com/site/cmzmasek/home/software/forester/surfacing";
232 final static private boolean IGNORE_DUFS_DEFAULT = true;
233 final static private boolean IGNORE_COMBINATION_WITH_SAME_DEFAULLT = false;
234 final static private double MAX_E_VALUE_DEFAULT = -1;
235 final static private int MAX_ALLOWED_OVERLAP_DEFAULT = -1;
236 private static final String RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION = "random_seed";
237 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS = "consider_bdc_direction";
238 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY = "consider_bdc_adj";
239 private static final String SEQ_EXTRACT_SUFFIX = ".prot";
240 private static final String PLUS_MINUS_ANALYSIS_OPTION = "plus_minus";
241 private static final String PLUS_MINUS_DOM_SUFFIX = "_plus_minus_dom.txt";
242 private static final String PLUS_MINUS_DOM_SUFFIX_HTML = "_plus_minus_dom.html";
243 private static final String PLUS_MINUS_DC_SUFFIX_HTML = "_plus_minus_dc.html";
244 private static final int PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT = 0;
245 private static final double PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT = 1.0;
246 private static final String PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_all.txt";
247 private static final String PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_passing.txt";
248 private static final String OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS = "all_prot";
249 final static private String OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION = "all_prot_e";
250 private static final boolean VERBOSE = false;
251 private static final String OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_gains_counts";
252 private static final String OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_losses_counts";
253 private static final String DOMAIN_LENGTHS_ANALYSIS_SUFFIX = "_domain_lengths_analysis";
254 private static final boolean PERFORM_DOMAIN_LENGTH_ANALYSIS = true;
255 public static final String ALL_PFAMS_ENCOUNTERED_SUFFIX = "_all_encountered_pfams";
256 public static final String ALL_PFAMS_ENCOUNTERED_WITH_GO_ANNOTATION_SUFFIX = "_all_encountered_pfams_with_go_annotation";
257 public static final String ENCOUNTERED_PFAMS_SUMMARY_SUFFIX = "_encountered_pfams_summary";
258 public static final String ALL_PFAMS_GAINED_AS_DOMAINS_SUFFIX = "_all_pfams_gained_as_domains";
259 public static final String ALL_PFAMS_LOST_AS_DOMAINS_SUFFIX = "_all_pfams_lost_as_domains";
260 public static final String ALL_PFAMS_GAINED_AS_DC_SUFFIX = "_all_pfams_gained_as_dc";
261 public static final String ALL_PFAMS_LOST_AS_DC_SUFFIX = "_all_pfams_lost_as_dc";
262 public static final String BASE_DIRECTORY_PER_NODE_DOMAIN_GAIN_LOSS_FILES = "PER_NODE_EVENTS";
263 public static final String BASE_DIRECTORY_PER_SUBTREE_DOMAIN_GAIN_LOSS_FILES = "PER_SUBTREE_EVENTS";
264 public static final String D_PROMISCUITY_FILE_SUFFIX = "_domain_promiscuities";
265 private static final String LOG_FILE_SUFFIX = "_log.txt";
266 private static final String DATA_FILE_SUFFIX = "_domain_combination_data.txt";
267 private static final String DATA_FILE_DESC = "#SPECIES\tPRTEIN_ID\tN_TERM_DOMAIN\tC_TERM_DOMAIN\tN_TERM_DOMAIN_PER_DOMAIN_E_VALUE\tC_TERM_DOMAIN_PER_DOMAIN_E_VALUE\tN_TERM_DOMAIN_COUNTS_PER_PROTEIN\tC_TERM_DOMAIN_COUNTS_PER_PROTEIN";
268 private static final String WRITE_TO_NEXUS_OPTION = "nexus";
269 private static final INDIVIDUAL_SCORE_CUTOFF INDIVIDUAL_SCORE_CUTOFF_DEFAULT = INDIVIDUAL_SCORE_CUTOFF.FULL_SEQUENCE; //TODO look at me! change?
270 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts.txt";
271 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists.txt";
272 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping.txt";
273 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_UNIQUE_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping_unique.txt";
274 public static final String LIMIT_SPEC_FOR_PROT_EX = null; // e.g. "HUMAN"; set to null for not using this feature (default).
275 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH_MAPPED = "_dc_MAPPED_secondary_features_fitch"
276 + ForesterConstants.PHYLO_XML_SUFFIX;
277 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts_MAPPED.txt";
278 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_MAPPED.txt";
279 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping_MAPPED.txt";
280 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_UNIQUE_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping_unique_MAPPED.txt";
282 private static void checkWriteabilityForPairwiseComparisons( final PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option,
283 final String[][] input_file_properties,
284 final String automated_pairwise_comparison_suffix,
285 final File outdir ) {
286 for( int i = 0; i < input_file_properties.length; ++i ) {
287 for( int j = 0; j < i; ++j ) {
288 final String species_i = input_file_properties[ i ][ 1 ];
289 final String species_j = input_file_properties[ j ][ 1 ];
290 String pairwise_similarities_output_file_str = PAIRWISE_DOMAIN_COMPARISONS_PREFIX + species_i + "_"
291 + species_j + automated_pairwise_comparison_suffix;
292 switch ( domain_similarity_print_option ) {
294 if ( !pairwise_similarities_output_file_str.endsWith( ".html" ) ) {
295 pairwise_similarities_output_file_str += ".html";
299 final String error = ForesterUtil
300 .isWritableFile( new File( outdir == null ? pairwise_similarities_output_file_str : outdir
301 + ForesterUtil.FILE_SEPARATOR + pairwise_similarities_output_file_str ) );
302 if ( !ForesterUtil.isEmpty( error ) ) {
303 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
309 private static StringBuilder createParametersAsString( final boolean ignore_dufs,
310 final double e_value_max,
311 final int max_allowed_overlap,
312 final boolean no_engulfing_overlaps,
313 final File cutoff_scores_file,
314 final BinaryDomainCombination.DomainCombinationType dc_type ) {
315 final StringBuilder parameters_sb = new StringBuilder();
316 parameters_sb.append( "E-value: " + e_value_max );
317 if ( cutoff_scores_file != null ) {
318 parameters_sb.append( ", Cutoff-scores-file: " + cutoff_scores_file );
321 parameters_sb.append( ", Cutoff-scores-file: not-set" );
323 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
324 parameters_sb.append( ", Max-overlap: " + max_allowed_overlap );
327 parameters_sb.append( ", Max-overlap: not-set" );
329 if ( no_engulfing_overlaps ) {
330 parameters_sb.append( ", Engulfing-overlaps: not-allowed" );
333 parameters_sb.append( ", Engulfing-overlaps: allowed" );
336 parameters_sb.append( ", Ignore-dufs: true" );
339 parameters_sb.append( ", Ignore-dufs: false" );
341 parameters_sb.append( ", DC type (if applicable): " + dc_type );
342 return parameters_sb;
346 * Warning: This side-effects 'all_bin_domain_combinations_encountered'!
350 * @param all_bin_domain_combinations_changed
351 * @param sum_of_all_domains_encountered
352 * @param all_bin_domain_combinations_encountered
353 * @param is_gains_analysis
354 * @param protein_length_stats_by_dc
355 * @throws IOException
357 private static void executeFitchGainsAnalysis( final File output_file,
358 final List<BinaryDomainCombination> all_bin_domain_combinations_changed,
359 final int sum_of_all_domains_encountered,
360 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered,
361 final boolean is_gains_analysis ) throws IOException {
362 SurfacingUtil.checkForOutputFileWriteability( output_file );
363 final Writer out = ForesterUtil.createBufferedWriter( output_file );
364 final SortedMap<Object, Integer> bdc_to_counts = ForesterUtil
365 .listToSortedCountsMap( all_bin_domain_combinations_changed );
366 final SortedSet<String> all_domains_in_combination_changed_more_than_once = new TreeSet<String>();
367 final SortedSet<String> all_domains_in_combination_changed_only_once = new TreeSet<String>();
370 for( final Object bdc_object : bdc_to_counts.keySet() ) {
371 final BinaryDomainCombination bdc = ( BinaryDomainCombination ) bdc_object;
372 final int count = bdc_to_counts.get( bdc_object );
374 ForesterUtil.unexpectedFatalError( PRG_NAME, "count < 1 " );
376 out.write( bdc + "\t" + count + ForesterUtil.LINE_SEPARATOR );
378 all_domains_in_combination_changed_more_than_once.add( bdc.getId0() );
379 all_domains_in_combination_changed_more_than_once.add( bdc.getId1() );
382 else if ( count == 1 ) {
383 all_domains_in_combination_changed_only_once.add( bdc.getId0() );
384 all_domains_in_combination_changed_only_once.add( bdc.getId1() );
388 final int all = all_bin_domain_combinations_encountered.size();
390 if ( !is_gains_analysis ) {
391 all_bin_domain_combinations_encountered.removeAll( all_bin_domain_combinations_changed );
392 never_lost = all_bin_domain_combinations_encountered.size();
393 for( final BinaryDomainCombination bdc : all_bin_domain_combinations_encountered ) {
394 out.write( bdc + "\t" + "0" + ForesterUtil.LINE_SEPARATOR );
397 if ( is_gains_analysis ) {
398 out.write( "Sum of all distinct domain combinations appearing once : " + one
399 + ForesterUtil.LINE_SEPARATOR );
400 out.write( "Sum of all distinct domain combinations appearing more than once : " + above_one
401 + ForesterUtil.LINE_SEPARATOR );
402 out.write( "Sum of all distinct domains in combinations apppearing only once : "
403 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
404 out.write( "Sum of all distinct domains in combinations apppearing more than once: "
405 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
408 out.write( "Sum of all distinct domain combinations never lost : " + never_lost
409 + ForesterUtil.LINE_SEPARATOR );
410 out.write( "Sum of all distinct domain combinations lost once : " + one
411 + ForesterUtil.LINE_SEPARATOR );
412 out.write( "Sum of all distinct domain combinations lost more than once : " + above_one
413 + ForesterUtil.LINE_SEPARATOR );
414 out.write( "Sum of all distinct domains in combinations lost only once : "
415 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
416 out.write( "Sum of all distinct domains in combinations lost more than once: "
417 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
419 out.write( "All binary combinations : " + all
420 + ForesterUtil.LINE_SEPARATOR );
421 out.write( "All domains : "
422 + sum_of_all_domains_encountered );
424 ForesterUtil.programMessage( surfacing.PRG_NAME,
425 "Wrote fitch domain combination dynamics counts analysis to \"" + output_file
429 private static void executePlusMinusAnalysis( final File output_file,
430 final List<String> plus_minus_analysis_high_copy_base,
431 final List<String> plus_minus_analysis_high_copy_target,
432 final List<String> plus_minus_analysis_low_copy,
433 final List<GenomeWideCombinableDomains> gwcd_list,
434 final SortedMap<Species, List<Protein>> protein_lists_per_species,
435 final Map<String, List<GoId>> domain_id_to_go_ids_map,
436 final Map<GoId, GoTerm> go_id_to_term_map,
437 final List<Object> plus_minus_analysis_numbers ) {
438 final Set<String> all_spec = new HashSet<String>();
439 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
440 all_spec.add( gwcd.getSpecies().getSpeciesId() );
442 final File html_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX_HTML );
443 final File plain_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX );
444 final File html_out_dc = new File( output_file + PLUS_MINUS_DC_SUFFIX_HTML );
445 final File all_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX );
446 final File passing_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX );
447 final File proteins_file_base = new File( output_file + "" );
448 final int min_diff = ( ( Integer ) plus_minus_analysis_numbers.get( 0 ) ).intValue();
449 final double factor = ( ( Double ) plus_minus_analysis_numbers.get( 1 ) ).doubleValue();
451 DomainCountsDifferenceUtil.calculateCopyNumberDifferences( gwcd_list,
452 protein_lists_per_species,
453 plus_minus_analysis_high_copy_base,
454 plus_minus_analysis_high_copy_target,
455 plus_minus_analysis_low_copy,
461 domain_id_to_go_ids_map,
463 all_domains_go_ids_out_dom,
464 passing_domains_go_ids_out_dom,
465 proteins_file_base );
467 catch ( final IOException e ) {
468 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
470 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
471 + html_out_dom + "\"" );
472 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
473 + plain_out_dom + "\"" );
474 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \"" + html_out_dc
476 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based passing GO ids to \""
477 + passing_domains_go_ids_out_dom + "\"" );
478 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based all GO ids to \""
479 + all_domains_go_ids_out_dom + "\"" );
482 private static Phylogeny[] getIntrees( final File[] intree_files,
483 final int number_of_genomes,
484 final String[][] input_file_properties ) {
485 final Phylogeny[] intrees = new Phylogeny[ intree_files.length ];
487 for( final File intree_file : intree_files ) {
488 Phylogeny intree = null;
489 final String error = ForesterUtil.isReadableFile( intree_file );
490 if ( !ForesterUtil.isEmpty( error ) ) {
491 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read input tree file [" + intree_file + "]: "
495 final Phylogeny[] p_array = ParserBasedPhylogenyFactory.getInstance()
496 .create( intree_file, ParserUtils.createParserDependingOnFileType( intree_file, true ) );
497 if ( p_array.length < 1 ) {
498 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
499 + "] does not contain any phylogeny in phyloXML format" );
501 else if ( p_array.length > 1 ) {
502 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
503 + "] contains more than one phylogeny in phyloXML format" );
505 intree = p_array[ 0 ];
507 catch ( final Exception e ) {
508 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read input tree from file [" + intree_file
511 if ( ( intree == null ) || intree.isEmpty() ) {
512 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" );
514 if ( !intree.isRooted() ) {
515 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is not rooted" );
517 if ( intree.getNumberOfExternalNodes() < number_of_genomes ) {
518 ForesterUtil.fatalError( surfacing.PRG_NAME,
519 "number of external nodes [" + intree.getNumberOfExternalNodes()
520 + "] of input tree [" + intree_file
521 + "] is smaller than the number of genomes the be analyzed ["
522 + number_of_genomes + "]" );
524 final StringBuilder parent_names = new StringBuilder();
525 final int nodes_lacking_name = SurfacingUtil.getNumberOfNodesLackingName( intree, parent_names );
526 if ( nodes_lacking_name > 0 ) {
527 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] has "
528 + nodes_lacking_name + " node(s) lacking a name [parent names:" + parent_names + "]" );
530 preparePhylogenyForParsimonyAnalyses( intree, input_file_properties );
531 if ( !intree.isCompletelyBinary() ) {
532 ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "input tree [" + intree_file
533 + "] is not completely binary" );
535 intrees[ i++ ] = intree;
540 private static void log( final String msg, final Writer w ) {
543 w.write( ForesterUtil.LINE_SEPARATOR );
545 catch ( final IOException e ) {
546 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
550 public static void main( final String args[] ) {
551 final long start_time = new Date().getTime();
552 // final StringBuffer log = new StringBuffer();
553 final StringBuilder html_desc = new StringBuilder();
554 ForesterUtil.printProgramInformation( surfacing.PRG_NAME,
555 surfacing.PRG_VERSION,
559 final String nl = ForesterUtil.LINE_SEPARATOR;
560 html_desc.append( "<table>" + nl );
561 html_desc.append( "<tr><td>Produced by:</td><td>" + surfacing.PRG_NAME + "</td></tr>" + nl );
562 html_desc.append( "<tr><td>Version:</td><td>" + surfacing.PRG_VERSION + "</td></tr>" + nl );
563 html_desc.append( "<tr><td>Release Date:</td><td>" + surfacing.PRG_DATE + "</td></tr>" + nl );
564 html_desc.append( "<tr><td>Contact:</td><td>" + surfacing.E_MAIL + "</td></tr>" + nl );
565 html_desc.append( "<tr><td>WWW:</td><td>" + surfacing.WWW + "</td></tr>" + nl );
566 CommandLineArguments cla = null;
568 cla = new CommandLineArguments( args );
570 catch ( final Exception e ) {
571 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
573 if ( cla.isOptionSet( surfacing.HELP_OPTION_1 ) || cla.isOptionSet( surfacing.HELP_OPTION_2 ) ) {
574 surfacing.printHelp();
577 if ( ( args.length < 1 ) ) {
578 surfacing.printHelp();
581 final List<String> allowed_options = new ArrayList<String>();
582 allowed_options.add( surfacing.NOT_IGNORE_DUFS_OPTION );
583 allowed_options.add( surfacing.MAX_E_VALUE_OPTION );
584 allowed_options.add( surfacing.DETAILEDNESS_OPTION );
585 allowed_options.add( surfacing.OUTPUT_FILE_OPTION );
586 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_OPTION );
587 allowed_options.add( surfacing.SPECIES_MATRIX_OPTION );
588 allowed_options.add( surfacing.SCORING_OPTION );
589 allowed_options.add( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
590 allowed_options.add( surfacing.NO_ENGULFING_OVERLAP_OPTION );
591 allowed_options.add( surfacing.DOMAIN_COUNT_SORT_OPTION );
592 allowed_options.add( surfacing.CUTOFF_SCORE_FILE_OPTION );
593 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION );
594 allowed_options.add( surfacing.OUTPUT_DIR_OPTION );
595 allowed_options.add( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION );
596 allowed_options.add( surfacing.PFAM_TO_GO_FILE_USE_OPTION );
597 allowed_options.add( surfacing.GO_OBO_FILE_USE_OPTION );
598 allowed_options.add( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION );
599 allowed_options.add( surfacing.GO_NAMESPACE_LIMIT_OPTION );
600 allowed_options.add( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
601 allowed_options.add( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION );
602 allowed_options.add( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS );
603 allowed_options.add( INPUT_SPECIES_TREE_OPTION );
604 allowed_options.add( FILTER_POSITIVE_OPTION );
605 allowed_options.add( FILTER_NEGATIVE_OPTION );
606 allowed_options.add( INPUT_GENOMES_FILE_OPTION );
607 allowed_options.add( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
608 allowed_options.add( FILTER_NEGATIVE_DOMAINS_OPTION );
609 allowed_options.add( IGNORE_VIRAL_IDS );
610 allowed_options.add( SEQ_EXTRACT_OPTION );
611 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
612 allowed_options.add( SECONDARY_FEATURES_PARSIMONY_MAP_FILE );
613 allowed_options.add( PLUS_MINUS_ANALYSIS_OPTION );
614 allowed_options.add( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS );
615 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS );
616 allowed_options.add( CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY );
617 allowed_options.add( WRITE_TO_NEXUS_OPTION );
618 allowed_options.add( PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION );
619 allowed_options.add( DA_ANALYSIS_OPTION );
620 allowed_options.add( USE_LAST_IN_FITCH_OPTION );
621 boolean ignore_dufs = surfacing.IGNORE_DUFS_DEFAULT;
622 boolean ignore_combination_with_same = surfacing.IGNORE_COMBINATION_WITH_SAME_DEFAULLT;
623 double e_value_max = surfacing.MAX_E_VALUE_DEFAULT;
624 int max_allowed_overlap = surfacing.MAX_ALLOWED_OVERLAP_DEFAULT;
625 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
626 if ( dissallowed_options.length() > 0 ) {
627 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown option(s): " + dissallowed_options );
629 boolean use_last_in_fitch_parsimony = false;
630 if ( cla.isOptionSet( USE_LAST_IN_FITCH_OPTION ) ) {
631 use_last_in_fitch_parsimony = true;
633 boolean write_to_nexus = false;
634 if ( cla.isOptionSet( WRITE_TO_NEXUS_OPTION ) ) {
635 write_to_nexus = true;
637 boolean perform_dc_regain_proteins_stats = false;
638 if ( cla.isOptionSet( PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION ) ) {
639 perform_dc_regain_proteins_stats = true;
641 boolean da_analysis = false;
642 if ( cla.isOptionSet( DA_ANALYSIS_OPTION ) ) {
645 boolean output_binary_domain_combinationsfor_graph_analysis = false;
646 if ( cla.isOptionSet( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS ) ) {
647 output_binary_domain_combinationsfor_graph_analysis = true;
649 if ( cla.isOptionSet( surfacing.MAX_E_VALUE_OPTION ) ) {
651 e_value_max = cla.getOptionValueAsDouble( surfacing.MAX_E_VALUE_OPTION );
653 catch ( final Exception e ) {
654 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for E-value maximum" );
657 if ( cla.isOptionSet( surfacing.MAX_ALLOWED_OVERLAP_OPTION ) ) {
659 max_allowed_overlap = cla.getOptionValueAsInt( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
661 catch ( final Exception e ) {
662 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for maximal allowed domain overlap" );
665 boolean no_engulfing_overlaps = false;
666 if ( cla.isOptionSet( surfacing.NO_ENGULFING_OVERLAP_OPTION ) ) {
667 no_engulfing_overlaps = true;
669 boolean ignore_virus_like_ids = false;
670 if ( cla.isOptionSet( surfacing.IGNORE_VIRAL_IDS ) ) {
671 ignore_virus_like_ids = true;
673 if ( cla.isOptionSet( surfacing.NOT_IGNORE_DUFS_OPTION ) ) {
676 if ( cla.isOptionSet( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION ) ) {
677 ignore_combination_with_same = true;
679 boolean ignore_domains_without_combs_in_all_spec = IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT;
680 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION ) ) {
681 ignore_domains_without_combs_in_all_spec = true;
683 boolean ignore_species_specific_domains = IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT;
684 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION ) ) {
685 ignore_species_specific_domains = true;
687 File output_file = null;
688 if ( cla.isOptionSet( surfacing.OUTPUT_FILE_OPTION ) ) {
689 if ( !cla.isOptionValueSet( surfacing.OUTPUT_FILE_OPTION ) ) {
690 ForesterUtil.fatalError( surfacing.PRG_NAME,
691 "no value for domain combinations similarities output file: -"
692 + surfacing.OUTPUT_FILE_OPTION + "=<file>" );
694 output_file = new File( cla.getOptionValue( surfacing.OUTPUT_FILE_OPTION ) );
695 SurfacingUtil.checkForOutputFileWriteability( output_file );
697 File cutoff_scores_file = null;
698 Map<String, Double> individual_score_cutoffs = null;
699 if ( cla.isOptionSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
700 if ( !cla.isOptionValueSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
701 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for individual domain score cutoffs file: -"
702 + surfacing.CUTOFF_SCORE_FILE_OPTION + "=<file>" );
704 cutoff_scores_file = new File( cla.getOptionValue( surfacing.CUTOFF_SCORE_FILE_OPTION ) );
705 final String error = ForesterUtil.isReadableFile( cutoff_scores_file );
706 if ( !ForesterUtil.isEmpty( error ) ) {
707 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read individual domain score cutoffs file: "
711 final BasicTable<String> scores_table = BasicTableParser.parse( cutoff_scores_file, ' ' );
712 individual_score_cutoffs = scores_table.getColumnsAsMapDouble( 0, 1 );
714 catch ( final IOException e ) {
715 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from individual score cutoffs file: " + e );
718 BinaryDomainCombination.DomainCombinationType dc_type = BinaryDomainCombination.DomainCombinationType.BASIC;
719 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS ) ) {
720 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED;
722 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY ) ) {
723 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT;
726 if ( cla.isOptionSet( surfacing.OUTPUT_DIR_OPTION ) ) {
727 if ( !cla.isOptionValueSet( surfacing.OUTPUT_DIR_OPTION ) ) {
728 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for output directory: -"
729 + surfacing.OUTPUT_DIR_OPTION + "=<dir>" );
731 out_dir = new File( cla.getOptionValue( surfacing.OUTPUT_DIR_OPTION ) );
732 if ( out_dir.exists() && ( out_dir.listFiles().length > 0 ) ) {
733 ForesterUtil.fatalError( surfacing.PRG_NAME, "\"" + out_dir + "\" aready exists and is not empty" );
735 if ( !out_dir.exists() ) {
736 final boolean success = out_dir.mkdir();
737 if ( !success || !out_dir.exists() ) {
738 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to create \"" + out_dir + "\"" );
741 if ( !out_dir.canWrite() ) {
742 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot write to \"" + out_dir + "\"" );
745 File positive_filter_file = null;
746 File negative_filter_file = null;
747 File negative_domains_filter_file = null;
748 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) && cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
749 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use both negative and positive protein filter" );
751 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION )
752 && ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) || cla
753 .isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) ) {
755 .fatalError( surfacing.PRG_NAME,
756 "attempt to use both negative or positive protein filter together wirh a negative domains filter" );
758 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
759 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
760 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative filter: -"
761 + surfacing.FILTER_NEGATIVE_OPTION + "=<file>" );
763 negative_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_OPTION ) );
764 final String msg = ForesterUtil.isReadableFile( negative_filter_file );
765 if ( !ForesterUtil.isEmpty( msg ) ) {
766 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_filter_file + "\": "
770 else if ( cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
771 if ( !cla.isOptionValueSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
772 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for positive filter: -"
773 + surfacing.FILTER_POSITIVE_OPTION + "=<file>" );
775 positive_filter_file = new File( cla.getOptionValue( surfacing.FILTER_POSITIVE_OPTION ) );
776 final String msg = ForesterUtil.isReadableFile( positive_filter_file );
777 if ( !ForesterUtil.isEmpty( msg ) ) {
778 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + positive_filter_file + "\": "
782 else if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
783 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
784 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative domains filter: -"
785 + surfacing.FILTER_NEGATIVE_DOMAINS_OPTION + "=<file>" );
787 negative_domains_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) );
788 final String msg = ForesterUtil.isReadableFile( negative_domains_filter_file );
789 if ( !ForesterUtil.isEmpty( msg ) ) {
790 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_domains_filter_file
794 final List<String> plus_minus_analysis_high_copy_base_species = new ArrayList<String>();
795 final List<String> plus_minus_analysis_high_copy_target_species = new ArrayList<String>();
796 final List<String> plus_minus_analysis_high_low_copy_species = new ArrayList<String>();
797 final List<Object> plus_minus_analysis_numbers = new ArrayList<Object>();
798 processPlusMinusAnalysisOption( cla,
799 plus_minus_analysis_high_copy_base_species,
800 plus_minus_analysis_high_copy_target_species,
801 plus_minus_analysis_high_low_copy_species,
802 plus_minus_analysis_numbers );
803 File input_genomes_file = null;
804 if ( cla.isOptionSet( surfacing.INPUT_GENOMES_FILE_OPTION ) ) {
805 if ( !cla.isOptionValueSet( surfacing.INPUT_GENOMES_FILE_OPTION ) ) {
806 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input genomes file: -"
807 + surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>" );
809 input_genomes_file = new File( cla.getOptionValue( surfacing.INPUT_GENOMES_FILE_OPTION ) );
810 final String msg = ForesterUtil.isReadableFile( input_genomes_file );
811 if ( !ForesterUtil.isEmpty( msg ) ) {
813 .fatalError( surfacing.PRG_NAME, "can not read from \"" + input_genomes_file + "\": " + msg );
817 ForesterUtil.fatalError( surfacing.PRG_NAME, "no input genomes file given: "
818 + surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>" );
820 DomainSimilarity.DomainSimilarityScoring scoring = SCORING_DEFAULT;
821 if ( cla.isOptionSet( surfacing.SCORING_OPTION ) ) {
822 if ( !cla.isOptionValueSet( surfacing.SCORING_OPTION ) ) {
823 ForesterUtil.fatalError( surfacing.PRG_NAME,
824 "no value for scoring method for domain combinations similarity calculation: -"
825 + surfacing.SCORING_OPTION + "=<"
826 + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
827 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|"
828 + surfacing.SCORING_COMBINATION_BASED + ">\"" );
830 final String scoring_str = cla.getOptionValue( surfacing.SCORING_OPTION );
831 if ( scoring_str.equals( surfacing.SCORING_DOMAIN_COUNT_BASED ) ) {
832 scoring = DomainSimilarity.DomainSimilarityScoring.DOMAINS;
834 else if ( scoring_str.equals( surfacing.SCORING_COMBINATION_BASED ) ) {
835 scoring = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
837 else if ( scoring_str.equals( surfacing.SCORING_PROTEIN_COUNT_BASED ) ) {
838 scoring = DomainSimilarity.DomainSimilarityScoring.PROTEINS;
841 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + scoring_str
842 + "\" for scoring method for domain combinations similarity calculation: \"-"
843 + surfacing.SCORING_OPTION + "=<" + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
844 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|" + surfacing.SCORING_COMBINATION_BASED + ">\"" );
847 boolean sort_by_species_count_first = false;
848 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION ) ) {
849 sort_by_species_count_first = true;
851 boolean species_matrix = false;
852 if ( cla.isOptionSet( surfacing.SPECIES_MATRIX_OPTION ) ) {
853 species_matrix = true;
855 boolean output_protein_lists_for_all_domains = false;
856 double output_list_of_all_proteins_per_domain_e_value_max = -1;
857 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS ) ) {
858 output_protein_lists_for_all_domains = true;
859 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION ) ) {
861 output_list_of_all_proteins_per_domain_e_value_max = cla
862 .getOptionValueAsDouble( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
864 catch ( final Exception e ) {
865 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for per domain E-value maximum" );
869 Detailedness detailedness = DETAILEDNESS_DEFAULT;
870 if ( cla.isOptionSet( surfacing.DETAILEDNESS_OPTION ) ) {
871 if ( !cla.isOptionValueSet( surfacing.DETAILEDNESS_OPTION ) ) {
872 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for -" + surfacing.DETAILEDNESS_OPTION + "=<"
873 + surfacing.DETAILEDNESS_BASIC + "|" + surfacing.DETAILEDNESS_LIST_IDS + "|"
874 + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
876 final String detness = cla.getOptionValue( surfacing.DETAILEDNESS_OPTION ).toLowerCase();
877 if ( detness.equals( surfacing.DETAILEDNESS_BASIC ) ) {
878 detailedness = DomainSimilarityCalculator.Detailedness.BASIC;
880 else if ( detness.equals( surfacing.DETAILEDNESS_LIST_IDS ) ) {
881 detailedness = DomainSimilarityCalculator.Detailedness.LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES;
883 else if ( detness.equals( surfacing.DETAILEDNESS_PUNCTILIOUS ) ) {
884 detailedness = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
887 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + detness + "\" for detailedness: \"-"
888 + surfacing.DETAILEDNESS_OPTION + "=<" + surfacing.DETAILEDNESS_BASIC + "|"
889 + surfacing.DETAILEDNESS_LIST_IDS + "|" + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
892 String automated_pairwise_comparison_suffix = null;
893 boolean perform_pwc = false;
894 boolean write_pwc_files = false;
895 if ( cla.isOptionSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
897 if ( !cla.isOptionValueSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
898 write_pwc_files = false;
901 write_pwc_files = true;
902 automated_pairwise_comparison_suffix = "_"
903 + cla.getOptionValue( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
906 String query_domain_ids = null;
907 if ( cla.isOptionSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
908 if ( !cla.isOptionValueSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
910 .fatalError( surfacing.PRG_NAME,
911 "no domain ids given for sequences with given domains to be extracted : -"
912 + surfacing.SEQ_EXTRACT_OPTION
913 + "=<ordered domain sequences, domain ids separated by '~', sequences separated by '#'>" );
915 query_domain_ids = cla.getOptionValue( surfacing.SEQ_EXTRACT_OPTION );
917 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field = DOMAIN_SORT_FILD_DEFAULT;
918 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field_for_automated_pwc = DOMAIN_SORT_FILD_DEFAULT;
919 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
920 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
921 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for domain combinations similarities sorting: -"
922 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
923 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
924 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
925 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
926 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|"
927 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
930 final String sort_str = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ).toLowerCase();
931 if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ALPHA ) ) {
932 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
933 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
935 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MAX ) ) {
936 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX;
937 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
939 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MIN ) ) {
940 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MIN;
941 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
943 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MEAN ) ) {
944 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MEAN;
945 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MEAN;
947 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT ) ) {
948 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SPECIES_COUNT;
949 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
951 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SD ) ) {
952 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SD;
953 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
955 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_DIFF ) ) {
956 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
957 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
959 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF ) ) {
960 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
961 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
963 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF ) ) {
964 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
965 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
968 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort_str
969 + "\" for domain combinations similarities sorting: \"-"
970 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
971 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
972 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
973 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
974 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|" + "|"
975 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
979 PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option = DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT;
980 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
981 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
982 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for print option: -"
983 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
984 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
985 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
987 final String sort = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ).toLowerCase();
988 if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML ) ) {
989 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.HTML;
991 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML ) ) {
992 ForesterUtil.fatalError( surfacing.PRG_NAME, "simple HTML output not implemented yet :(" );
994 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED ) ) {
995 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.SIMPLE_TAB_DELIMITED;
998 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort + "\" for print option: -"
999 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
1000 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
1001 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
1004 GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order = DOMAINS_SORT_ORDER_DEFAULT;
1005 if ( cla.isOptionSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
1006 if ( !cla.isOptionValueSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
1007 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for sorting of domain counts: -"
1008 + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<" + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|"
1009 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1010 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1011 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1013 final String sort = cla.getOptionValue( surfacing.DOMAIN_COUNT_SORT_OPTION ).toLowerCase();
1014 if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_ALPHA ) ) {
1015 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
1017 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT ) ) {
1018 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_COUNT;
1020 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT ) ) {
1021 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_PROTEINS_COUNT;
1023 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT ) ) {
1024 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.COMBINATIONS_COUNT;
1027 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort
1028 + "\" for sorting of domain counts: \"-" + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<"
1029 + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|" + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1030 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1031 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1034 final String[][] input_file_properties = processInputGenomesFile( input_genomes_file );
1035 final int number_of_genomes = input_file_properties.length;
1036 if ( number_of_genomes < 2 ) {
1037 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot analyze less than two files" );
1039 if ( ( number_of_genomes < 3 ) && perform_pwc ) {
1040 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use : -"
1041 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1042 + "=<suffix> to turn on pairwise analyses with less than three input files" );
1044 checkWriteabilityForPairwiseComparisons( domain_similarity_print_option,
1045 input_file_properties,
1046 automated_pairwise_comparison_suffix,
1048 for( int i = 0; i < number_of_genomes; i++ ) {
1049 File dcc_outfile = new File( input_file_properties[ i ][ 1 ]
1050 + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
1051 if ( out_dir != null ) {
1052 dcc_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + dcc_outfile );
1054 SurfacingUtil.checkForOutputFileWriteability( dcc_outfile );
1056 File pfam_to_go_file = null;
1057 Map<String, List<GoId>> domain_id_to_go_ids_map = null;
1058 int domain_id_to_go_ids_count = 0;
1059 if ( cla.isOptionSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1060 if ( !cla.isOptionValueSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1061 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for Pfam to GO mapping file: -"
1062 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>" );
1064 pfam_to_go_file = new File( cla.getOptionValue( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) );
1065 final String error = ForesterUtil.isReadableFile( pfam_to_go_file );
1066 if ( !ForesterUtil.isEmpty( error ) ) {
1067 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read Pfam to GO mapping file: " + error );
1070 final PfamToGoParser parser = new PfamToGoParser( pfam_to_go_file );
1071 final List<PfamToGoMapping> pfam_to_go_mappings = parser.parse();
1072 domain_id_to_go_ids_map = SurfacingUtil.createDomainIdToGoIdMap( pfam_to_go_mappings );
1073 if ( parser.getMappingCount() < domain_id_to_go_ids_map.size() ) {
1074 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME,
1075 "parser.getMappingCount() < domain_id_to_go_ids_map.size()" );
1077 domain_id_to_go_ids_count = parser.getMappingCount();
1079 catch ( final IOException e ) {
1080 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from Pfam to GO mapping file: " + e );
1083 File go_obo_file = null;
1084 List<GoTerm> go_terms = null;
1085 if ( cla.isOptionSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1086 if ( !cla.isOptionValueSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1087 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO OBO file: -"
1088 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>" );
1090 if ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) {
1091 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO OBO file (-"
1092 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>) without Pfam to GO mapping file ("
1093 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1095 go_obo_file = new File( cla.getOptionValue( surfacing.GO_OBO_FILE_USE_OPTION ) );
1096 final String error = ForesterUtil.isReadableFile( go_obo_file );
1097 if ( !ForesterUtil.isEmpty( error ) ) {
1098 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read GO OBO file: " + error );
1101 final OBOparser parser = new OBOparser( go_obo_file, OBOparser.ReturnType.BASIC_GO_TERM );
1102 go_terms = parser.parse();
1103 if ( parser.getGoTermCount() != go_terms.size() ) {
1105 .unexpectedFatalError( surfacing.PRG_NAME, "parser.getGoTermCount() != go_terms.size()" );
1108 catch ( final IOException e ) {
1109 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from GO OBO file: " + e );
1112 Map<GoId, GoTerm> go_id_to_term_map = null;
1113 if ( ( ( domain_id_to_go_ids_map != null ) && ( domain_id_to_go_ids_map.size() > 0 ) )
1114 && ( ( go_terms != null ) && ( go_terms.size() > 0 ) ) ) {
1115 go_id_to_term_map = GoUtils.createGoIdToGoTermMap( go_terms );
1117 GoNameSpace go_namespace_limit = null;
1118 if ( cla.isOptionSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1119 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1120 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO namespace limit (-"
1121 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<namespace>) without Pfam to GO mapping file ("
1122 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>) and GO OBO file (-"
1123 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1125 if ( !cla.isOptionValueSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1126 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO namespace limit: \"-"
1127 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1128 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1129 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1130 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1132 final String go_namespace_limit_str = cla.getOptionValue( surfacing.GO_NAMESPACE_LIMIT_OPTION )
1134 if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION ) ) {
1135 go_namespace_limit = GoNameSpace.createMolecularFunction();
1137 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS ) ) {
1138 go_namespace_limit = GoNameSpace.createBiologicalProcess();
1140 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT ) ) {
1141 go_namespace_limit = GoNameSpace.createCellularComponent();
1144 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + go_namespace_limit_str
1145 + "\" for GO namespace limit: \"-" + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1146 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1147 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1148 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1151 if ( ( domain_similarity_sort_field == DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE )
1152 && ( number_of_genomes > 2 ) ) {
1153 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
1155 File[] intree_files = null;
1156 Phylogeny[] intrees = null;
1157 if ( cla.isOptionSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1158 if ( number_of_genomes < 3 ) {
1159 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer gains and losses on input species trees (-"
1160 + surfacing.INPUT_SPECIES_TREE_OPTION + " without pairwise analyses ("
1161 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1162 + "=<suffix for pairwise comparison output files>)" );
1164 if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1165 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input tree: -"
1166 + surfacing.INPUT_SPECIES_TREE_OPTION + "=<tree file in phyloXML format>" );
1168 final String intrees_str = cla.getOptionValue( surfacing.INPUT_SPECIES_TREE_OPTION );
1169 if ( intrees_str.indexOf( "#" ) > 0 ) {
1170 final String[] intrees_strs = intrees_str.split( "#" );
1171 intree_files = new File[ intrees_strs.length ];
1173 for( final String s : intrees_strs ) {
1174 intree_files[ i++ ] = new File( s.trim() );
1178 intree_files = new File[ 1 ];
1179 intree_files[ 0 ] = new File( intrees_str );
1181 intrees = getIntrees( intree_files, number_of_genomes, input_file_properties );
1183 long random_number_seed_for_fitch_parsimony = 0l;
1184 boolean radomize_fitch_parsimony = false;
1185 if ( cla.isOptionSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1186 if ( !cla.isOptionValueSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1187 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for random number seed: -"
1188 + surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION + "=<seed>" );
1191 random_number_seed_for_fitch_parsimony = cla
1192 .getOptionValueAsLong( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
1194 catch ( final IOException e ) {
1195 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1197 radomize_fitch_parsimony = true;
1199 SortedSet<String> filter = null;
1200 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1201 || ( negative_domains_filter_file != null ) ) {
1202 filter = new TreeSet<String>();
1203 if ( positive_filter_file != null ) {
1204 processFilter( positive_filter_file, filter );
1206 else if ( negative_filter_file != null ) {
1207 processFilter( negative_filter_file, filter );
1209 else if ( negative_domains_filter_file != null ) {
1210 processFilter( negative_domains_filter_file, filter );
1213 Map<String, Set<String>>[] domain_id_to_secondary_features_maps = null;
1214 File[] secondary_features_map_files = null;
1215 final File domain_lengths_analysis_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1216 + DOMAIN_LENGTHS_ANALYSIS_SUFFIX );
1217 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
1218 SurfacingUtil.checkForOutputFileWriteability( domain_lengths_analysis_outfile );
1220 if ( cla.isOptionSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1221 if ( !cla.isOptionValueSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1222 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for secondary features map file: -"
1223 + surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE + "=<file>" );
1225 final String[] secondary_features_map_files_strs = cla
1226 .getOptionValue( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ).split( "#" );
1227 secondary_features_map_files = new File[ secondary_features_map_files_strs.length ];
1228 domain_id_to_secondary_features_maps = new Map[ secondary_features_map_files_strs.length ];
1230 for( final String secondary_features_map_files_str : secondary_features_map_files_strs ) {
1231 secondary_features_map_files[ i ] = new File( secondary_features_map_files_str );
1232 final String error = ForesterUtil.isReadableFile( secondary_features_map_files[ i ] );
1233 if ( !ForesterUtil.isEmpty( error ) ) {
1234 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read secondary features map file: " + error );
1237 domain_id_to_secondary_features_maps[ i ] = SurfacingUtil
1238 .createDomainIdToSecondaryFeaturesMap( secondary_features_map_files[ i ] );
1240 catch ( final IOException e ) {
1241 ForesterUtil.fatalError( surfacing.PRG_NAME,
1242 "cannot read secondary features map file: " + e.getMessage() );
1244 catch ( final Exception e ) {
1245 ForesterUtil.fatalError( surfacing.PRG_NAME, "problem with contents of features map file ["
1246 + secondary_features_map_files[ i ] + "]: " + e.getMessage() );
1251 if ( out_dir == null ) {
1252 ForesterUtil.fatalError( surfacing.PRG_NAME, "no output directory indicated (-"
1253 + surfacing.OUTPUT_DIR_OPTION + "=<dir>)" );
1255 if ( output_file == null ) {
1256 ForesterUtil.fatalError( surfacing.PRG_NAME, "no name for (main) output file indicated (-"
1257 + surfacing.OUTPUT_FILE_OPTION + "=<file>)" );
1259 if ( ( domain_id_to_go_ids_map == null ) || domain_id_to_go_ids_map.isEmpty() ) {
1260 ForesterUtil.fatalError( surfacing.PRG_NAME,
1261 "no (acceptable) Pfam to GO id mapping file provided ('pfam2go file') (-"
1262 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1264 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1265 ForesterUtil.fatalError( surfacing.PRG_NAME,
1266 "no (acceptable) go id to term mapping file provided ('GO OBO file') (-"
1267 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1269 System.out.println( "Output directory : " + out_dir );
1270 System.out.println( "Input genomes from : " + input_genomes_file );
1271 html_desc.append( "<tr><td>Input genomes from:</td><td>" + input_genomes_file + "</td></tr>" + nl );
1272 if ( positive_filter_file != null ) {
1273 final int filter_size = filter.size();
1274 System.out.println( "Positive protein filter : " + positive_filter_file + " [" + filter_size
1276 html_desc.append( "<tr><td>Positive protein filter:</td><td>" + positive_filter_file + " [" + filter_size
1277 + " domain ids]</td></tr>" + nl );
1279 if ( negative_filter_file != null ) {
1280 final int filter_size = filter.size();
1281 System.out.println( "Negative protein filter : " + negative_filter_file + " [" + filter_size
1283 html_desc.append( "<tr><td>Negative protein filter:</td><td>" + negative_filter_file + " [" + filter_size
1284 + " domain ids]</td></tr>" + nl );
1286 if ( negative_domains_filter_file != null ) {
1287 final int filter_size = filter.size();
1288 System.out.println( "Negative domain filter : " + negative_domains_filter_file + " [" + filter_size
1290 html_desc.append( "<tr><td>Negative domain filter:</td><td>" + negative_domains_filter_file + " ["
1291 + filter_size + " domain ids]</td></tr>" + nl );
1293 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
1295 for( final String s : plus_minus_analysis_high_copy_base_species ) {
1296 plus0 += "+" + s + " ";
1299 for( final String s : plus_minus_analysis_high_copy_target_species ) {
1300 plus1 += "*" + s + " ";
1303 for( final String s : plus_minus_analysis_high_low_copy_species ) {
1304 minus += "-" + s + " ";
1306 System.out.println( "Plus-minus analysis : " + plus1 + "&& " + plus0 + "&& " + minus );
1307 html_desc.append( "<tr><td>Plus-minus analysis:</td><td>" + plus1 + "&& " + plus0 + "&& " + minus
1308 + "</td></tr>" + nl );
1310 if ( cutoff_scores_file != null ) {
1311 System.out.println( "Cutoff scores file : " + cutoff_scores_file );
1312 html_desc.append( "<tr><td>Cutoff scores file:</td><td>" + cutoff_scores_file + "</td></tr>" + nl );
1314 if ( e_value_max >= 0.0 ) {
1315 System.out.println( "E-value maximum (inclusive) : " + e_value_max );
1316 html_desc.append( "<tr><td>E-value maximum (inclusive):</td><td>" + e_value_max + "</td></tr>" + nl );
1318 if ( output_protein_lists_for_all_domains ) {
1319 System.out.println( "Domain E-value max : " + output_list_of_all_proteins_per_domain_e_value_max );
1320 html_desc.append( "<tr><td>Protein lists: E-value maximum per domain (inclusive):</td><td>"
1321 + output_list_of_all_proteins_per_domain_e_value_max + "</td></tr>" + nl );
1323 System.out.println( "Ignore DUFs : " + ignore_dufs );
1324 if ( ignore_virus_like_ids ) {
1325 System.out.println( "Ignore virus like ids : " + ignore_virus_like_ids );
1326 html_desc.append( "<tr><td>Ignore virus, phage, transposition related ids:</td><td>"
1327 + ignore_virus_like_ids + "</td></tr>" + nl );
1329 html_desc.append( "<tr><td>Ignore DUFs:</td><td>" + ignore_dufs + "</td></tr>" + nl );
1330 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1331 System.out.println( "Max allowed domain overlap : " + max_allowed_overlap );
1332 html_desc.append( "<tr><td>Max allowed domain overlap:</td><td>" + max_allowed_overlap + "</td></tr>" + nl );
1334 if ( no_engulfing_overlaps ) {
1335 System.out.println( "Ignore engulfed domains : " + no_engulfing_overlaps );
1336 html_desc.append( "<tr><td>Ignore (lower confidence) engulfed domains:</td><td>" + no_engulfing_overlaps
1337 + "</td></tr>" + nl );
1339 System.out.println( "Ignore singlet domains : " + ignore_domains_without_combs_in_all_spec );
1341 .append( "<tr><td>Ignore singlet domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1342 + ignore_domains_without_combs_in_all_spec + "</td></tr>" + nl );
1343 System.out.println( "Ignore species specific doms: " + ignore_species_specific_domains );
1345 .append( "<tr><td>Ignore species specific domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1346 + ignore_species_specific_domains + "</td></tr>" + nl );
1347 System.out.println( "Ignore combination with self: " + ignore_combination_with_same );
1348 html_desc.append( "<tr><td>Ignore combination with self for domain combination similarity analyses:</td><td>"
1349 + ignore_combination_with_same + "</td></tr>" + nl );
1350 System.out.println( "Consider directedness : "
1351 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) );
1352 html_desc.append( "<tr><td>Consider directedness of binary domain combinations:</td><td>"
1353 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) + "</td></tr>" + nl );
1354 if ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) {
1355 System.out.println( "Consider adjacency : "
1356 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) );
1357 html_desc.append( "<tr><td>Consider djacency of binary domain combinations:</td><td>"
1358 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) + "</td></tr>"
1361 System.out.println( "Use last in Fitch parimony : " + use_last_in_fitch_parsimony );
1362 html_desc.append( "<tr><td>Use last in Fitch parimon:</td><td>" + use_last_in_fitch_parsimony + "</td></tr>"
1364 System.out.println( "Write to Nexus files : " + write_to_nexus );
1365 html_desc.append( "<tr><td>Write to Nexus files:</td><td>" + write_to_nexus + "</td></tr>" + nl );
1366 System.out.println( "DC regain prot stats : " + perform_dc_regain_proteins_stats );
1367 html_desc.append( "<tr><td>DC regain prot stats:</td><td>" + perform_dc_regain_proteins_stats + "</td></tr>"
1369 System.out.println( "DA analysis : " + da_analysis );
1370 html_desc.append( "<tr><td>DA analysis :</td><td>" + da_analysis + "</td></tr>" + nl );
1371 System.out.print( "Domain counts sort order : " );
1372 html_desc.append( "<tr><td>Domain counts sort order:</td><td>" );
1373 switch ( dc_sort_order ) {
1374 case ALPHABETICAL_KEY_ID:
1375 System.out.println( "alphabetical" );
1376 html_desc.append( "alphabetical" + "</td></tr>" + nl );
1378 case KEY_DOMAIN_COUNT:
1379 System.out.println( "domain count" );
1380 html_desc.append( "domain count" + "</td></tr>" + nl );
1382 case KEY_DOMAIN_PROTEINS_COUNT:
1383 System.out.println( "domain proteins count" );
1384 html_desc.append( "domain proteins count" + "</td></tr>" + nl );
1386 case COMBINATIONS_COUNT:
1387 System.out.println( "domain combinations count" );
1388 html_desc.append( "domain combinations count" + "</td></tr>" + nl );
1391 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for dc sort order" );
1393 if ( domain_id_to_go_ids_map != null ) {
1394 System.out.println( "Pfam to GO mappings from : " + pfam_to_go_file + " [" + domain_id_to_go_ids_count
1396 html_desc.append( "<tr><td>Pfam to GO mappings from:</td><td>" + pfam_to_go_file + " ["
1397 + domain_id_to_go_ids_count + " mappings]" + "</td></tr>" + nl );
1399 if ( go_terms != null ) {
1400 System.out.println( "GO terms from : " + go_obo_file + " [" + go_terms.size() + " terms]" );
1401 html_desc.append( "<tr><td>GO terms from:</td><td>" + go_obo_file + " [" + go_terms.size() + " terms]"
1402 + "</td></tr>" + nl );
1404 if ( go_namespace_limit != null ) {
1405 System.out.println( "Limit GO terms to : " + go_namespace_limit.toString() );
1406 html_desc.append( "<tr><td>Limit GO terms to</td><td>" + go_namespace_limit + "</td></tr>" + nl );
1408 if ( perform_pwc ) {
1409 System.out.println( "Suffix for PWC files : " + automated_pairwise_comparison_suffix );
1410 html_desc.append( "<tr><td>Suffix for PWC files</td><td>" + automated_pairwise_comparison_suffix
1411 + "</td></tr>" + nl );
1413 if ( out_dir != null ) {
1414 System.out.println( "Output directory : " + out_dir );
1416 if ( query_domain_ids != null ) {
1417 System.out.println( "Query domains (ordered) : " + query_domain_ids );
1418 html_desc.append( "<tr><td></td><td>" + query_domain_ids + "</td></tr>" + nl );
1420 System.out.println( "Write similarities to : " + output_file );
1421 System.out.print( " Scoring method : " );
1422 html_desc.append( "<tr><td>Scoring method:</td><td>" );
1423 switch ( scoring ) {
1425 System.out.println( "domain combinations based" );
1426 html_desc.append( "domain combinations based" + "</td></tr>" + nl );
1429 System.out.println( "domain counts based" );
1430 html_desc.append( "domain counts based" + "</td></tr>" + nl );
1433 System.out.println( "domain proteins counts based" );
1434 html_desc.append( "domain proteins counts based" + "</td></tr>" + nl );
1437 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
1439 System.out.print( " Sort by : " );
1440 html_desc.append( "<tr><td>Sort by:</td><td>" );
1441 switch ( domain_similarity_sort_field ) {
1443 System.out.print( "score minimum" );
1444 html_desc.append( "score minimum" );
1447 System.out.print( "score maximum" );
1448 html_desc.append( "score maximum" );
1451 System.out.print( "score mean" );
1452 html_desc.append( "score mean" );
1455 System.out.print( "score standard deviation" );
1456 html_desc.append( "score standard deviation" );
1459 System.out.print( "species number" );
1460 html_desc.append( "species number" );
1463 System.out.print( "alphabetical domain identifier" );
1464 html_desc.append( "alphabetical domain identifier" );
1466 case MAX_DIFFERENCE:
1467 System.out.print( "(maximal) difference" );
1468 html_desc.append( "(maximal) difference" );
1470 case ABS_MAX_COUNTS_DIFFERENCE:
1471 System.out.print( "absolute (maximal) counts difference" );
1472 html_desc.append( "absolute (maximal) counts difference" );
1474 case MAX_COUNTS_DIFFERENCE:
1475 System.out.print( "(maximal) counts difference" );
1476 html_desc.append( "(maximal) counts difference" );
1479 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1481 if ( sort_by_species_count_first ) {
1482 System.out.println( " (sort by species count first)" );
1483 html_desc.append( " (sort by species count first)" );
1486 System.out.println();
1488 html_desc.append( "</td></tr>" + nl );
1489 System.out.print( " Detailedness : " );
1490 switch ( detailedness ) {
1492 System.out.println( "basic" );
1494 case LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES:
1495 System.out.println( "list combining domains for each species" );
1498 System.out.println( "punctilious" );
1501 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for detailedness" );
1503 System.out.print( " Print option : " );
1504 switch ( domain_similarity_print_option ) {
1506 System.out.println( "HTML" );
1508 case SIMPLE_TAB_DELIMITED:
1509 System.out.println( "simple tab delimited" );
1512 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for print option" );
1514 System.out.print( " Species matrix : " + species_matrix );
1515 System.out.println();
1516 final File dc_data_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + DATA_FILE_SUFFIX );
1517 System.out.println( "Domain comb data output : " + dc_data_file );
1518 html_desc.append( "<tr><td>Domain combination data output:</td><td> " + dc_data_file + " </td></tr>" );
1519 System.out.println();
1520 if ( perform_pwc ) {
1521 System.out.println( "Pairwise comparisons: " );
1522 html_desc.append( "<tr><td>Pairwise comparisons:</td><td></td></tr>" );
1523 System.out.print( " Sort by : " );
1524 html_desc.append( "<tr><td>Sort by:</td><td>" );
1525 switch ( domain_similarity_sort_field_for_automated_pwc ) {
1527 System.out.print( "score mean" );
1528 html_desc.append( "score mean" );
1531 System.out.print( "alphabetical domain identifier" );
1532 html_desc.append( "alphabetical domain identifier" );
1534 case MAX_DIFFERENCE:
1535 System.out.print( "difference" );
1536 html_desc.append( "difference" );
1538 case ABS_MAX_COUNTS_DIFFERENCE:
1539 System.out.print( "absolute counts difference" );
1540 html_desc.append( "absolute counts difference" );
1542 case MAX_COUNTS_DIFFERENCE:
1543 System.out.print( "counts difference" );
1544 html_desc.append( "counts difference" );
1548 .unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1550 System.out.println();
1551 html_desc.append( "</td></tr>" + nl );
1552 if ( ( intrees != null ) && ( intrees.length > 0 ) ) {
1553 for( final File intree_file : intree_files ) {
1554 html_desc.append( "<tr><td>Intree for gain/loss parsimony analysis:</td><td>" + intree_file
1555 + "</td></tr>" + nl );
1556 System.out.println( " Intree for gain/loss pars.: " + intree_file );
1559 if ( radomize_fitch_parsimony ) {
1560 html_desc.append( "<tr><td> Random number seed for Fitch parsimony analysis:</td><td>"
1561 + random_number_seed_for_fitch_parsimony + "</td></tr>" + nl );
1562 System.out.println( " Random number seed : " + random_number_seed_for_fitch_parsimony );
1564 if ( ( domain_id_to_secondary_features_maps != null ) && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
1565 for( int i = 0; i < secondary_features_map_files.length; i++ ) {
1566 html_desc.append( "<tr><td>Secondary features map file:</td><td>"
1567 + secondary_features_map_files[ i ] + "</td></tr>" + nl );
1568 System.out.println( "Secondary features map file : " + secondary_features_map_files[ i ]
1569 + " [mappings for " + domain_id_to_secondary_features_maps[ i ].size() + " domain ids]" );
1571 System.out.println();
1572 System.out.println( "Domain ids to secondary features map:" );
1573 for( final String domain_id : domain_id_to_secondary_features_maps[ i ].keySet() ) {
1574 System.out.print( domain_id );
1575 System.out.print( " => " );
1576 for( final String sec : domain_id_to_secondary_features_maps[ i ].get( domain_id ) ) {
1577 System.out.print( sec );
1578 System.out.print( " " );
1580 System.out.println();
1585 } // if ( perform_pwc ) {
1586 System.out.println();
1587 html_desc.append( "<tr><td>Command line:</td><td>\n" + cla.getCommandLineArgsAsString() + "\n</td></tr>" + nl );
1588 System.out.println( "Command line : " + cla.getCommandLineArgsAsString() );
1589 BufferedWriter[] query_domains_writer_ary = null;
1590 List<String>[] query_domain_ids_array = null;
1591 if ( query_domain_ids != null ) {
1592 final String[] query_domain_ids_str_array = query_domain_ids.split( "#" );
1593 query_domain_ids_array = new ArrayList[ query_domain_ids_str_array.length ];
1594 query_domains_writer_ary = new BufferedWriter[ query_domain_ids_str_array.length ];
1595 for( int i = 0; i < query_domain_ids_str_array.length; i++ ) {
1596 String query_domain_ids_str = query_domain_ids_str_array[ i ];
1597 final String[] query_domain_ids_str_ary = query_domain_ids_str.split( "~" );
1598 final List<String> query = new ArrayList<String>();
1599 for( final String element : query_domain_ids_str_ary ) {
1600 query.add( element );
1602 query_domain_ids_array[ i ] = query;
1603 query_domain_ids_str = query_domain_ids_str.replace( '~', '_' );
1604 String protein_names_writer_str = query_domain_ids_str + surfacing.SEQ_EXTRACT_SUFFIX;
1605 if ( out_dir != null ) {
1606 protein_names_writer_str = out_dir + ForesterUtil.FILE_SEPARATOR + protein_names_writer_str;
1609 query_domains_writer_ary[ i ] = new BufferedWriter( new FileWriter( protein_names_writer_str ) );
1611 catch ( final IOException e ) {
1612 ForesterUtil.fatalError( surfacing.PRG_NAME, "Could not open [" + protein_names_writer_str + "]: "
1613 + e.getLocalizedMessage() );
1617 SortedMap<Species, List<Protein>> protein_lists_per_species = null; //This will only be created if neede.
1618 boolean need_protein_lists_per_species = false;
1619 if ( ( plus_minus_analysis_high_copy_base_species.size() > 0 ) || output_protein_lists_for_all_domains ) {
1620 need_protein_lists_per_species = true;
1622 if ( need_protein_lists_per_species ) {
1623 protein_lists_per_species = new TreeMap<Species, List<Protein>>();
1625 List<GenomeWideCombinableDomains> gwcd_list = new ArrayList<GenomeWideCombinableDomains>( number_of_genomes );
1626 final SortedSet<String> all_domains_encountered = new TreeSet<String>();
1627 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered = new TreeSet<BinaryDomainCombination>();
1628 List<BinaryDomainCombination> all_bin_domain_combinations_gained_fitch = null;
1629 List<BinaryDomainCombination> all_bin_domain_combinations_lost_fitch = null;
1630 if ( ( intrees != null ) && ( intrees.length == 1 ) ) {
1631 all_bin_domain_combinations_gained_fitch = new ArrayList<BinaryDomainCombination>();
1632 all_bin_domain_combinations_lost_fitch = new ArrayList<BinaryDomainCombination>();
1634 final DomainLengthsTable domain_lengths_table = new DomainLengthsTable();
1635 final File per_genome_domain_promiscuity_statistics_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR
1636 + output_file + D_PROMISCUITY_FILE_SUFFIX );
1637 BufferedWriter per_genome_domain_promiscuity_statistics_writer = null;
1639 per_genome_domain_promiscuity_statistics_writer = new BufferedWriter( new FileWriter( per_genome_domain_promiscuity_statistics_file ) );
1640 per_genome_domain_promiscuity_statistics_writer.write( "Species:\t" );
1641 per_genome_domain_promiscuity_statistics_writer.write( "Mean:\t" );
1642 per_genome_domain_promiscuity_statistics_writer.write( "SD:\t" );
1643 per_genome_domain_promiscuity_statistics_writer.write( "Median:\t" );
1644 per_genome_domain_promiscuity_statistics_writer.write( "Min:\t" );
1645 per_genome_domain_promiscuity_statistics_writer.write( "Max:\t" );
1646 per_genome_domain_promiscuity_statistics_writer.write( "N:\t" );
1647 per_genome_domain_promiscuity_statistics_writer.write( "Max Promiscuous Domains:"
1648 + ForesterUtil.LINE_SEPARATOR );
1650 catch ( final IOException e2 ) {
1651 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1653 final File log_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + LOG_FILE_SUFFIX );
1654 BufferedWriter log_writer = null;
1656 log_writer = new BufferedWriter( new FileWriter( log_file ) );
1658 catch ( final IOException e2 ) {
1659 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1661 BufferedWriter dc_data_writer = null;
1663 dc_data_writer = new BufferedWriter( new FileWriter( dc_data_file ) );
1664 dc_data_writer.write( DATA_FILE_DESC );
1665 dc_data_writer.write( ForesterUtil.LINE_SEPARATOR );
1667 catch ( final IOException e2 ) {
1668 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1670 final DescriptiveStatistics protein_coverage_stats = new BasicDescriptiveStatistics();
1671 final DescriptiveStatistics all_genomes_domains_per_potein_stats = new BasicDescriptiveStatistics();
1672 final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo = new TreeMap<Integer, Integer>();
1673 final SortedSet<String> domains_which_are_always_single = new TreeSet<String>();
1674 final SortedSet<String> domains_which_are_sometimes_single_sometimes_not = new TreeSet<String>();
1675 final SortedSet<String> domains_which_never_single = new TreeSet<String>();
1676 BufferedWriter domains_per_potein_stats_writer = null;
1678 domains_per_potein_stats_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
1679 + output_file + "_domains_per_potein_stats.txt" ) );
1680 domains_per_potein_stats_writer.write( "Genome" );
1681 domains_per_potein_stats_writer.write( "\t" );
1682 domains_per_potein_stats_writer.write( "Mean" );
1683 domains_per_potein_stats_writer.write( "\t" );
1684 domains_per_potein_stats_writer.write( "SD" );
1685 domains_per_potein_stats_writer.write( "\t" );
1686 domains_per_potein_stats_writer.write( "Median" );
1687 domains_per_potein_stats_writer.write( "\t" );
1688 domains_per_potein_stats_writer.write( "N" );
1689 domains_per_potein_stats_writer.write( "\t" );
1690 domains_per_potein_stats_writer.write( "Min" );
1691 domains_per_potein_stats_writer.write( "\t" );
1692 domains_per_potein_stats_writer.write( "Max" );
1693 domains_per_potein_stats_writer.write( "\n" );
1695 catch ( final IOException e3 ) {
1696 e3.printStackTrace();
1698 Map<String, DescriptiveStatistics> protein_length_stats_by_dc = null;
1699 Map<String, DescriptiveStatistics> domain_number_stats_by_dc = null;
1700 final Map<String, DescriptiveStatistics> domain_length_stats_by_domain = new HashMap<String, DescriptiveStatistics>();
1701 if ( perform_dc_regain_proteins_stats ) {
1702 protein_length_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1703 domain_number_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1706 final SortedMap<String, Set<String>> distinct_domain_architecutures_per_genome = new TreeMap<String, Set<String>>();
1707 final SortedMap<String, Integer> distinct_domain_architecuture_counts = new TreeMap<String, Integer>();
1708 for( int i = 0; i < number_of_genomes; ++i ) {
1709 System.out.println();
1710 System.out.println( ( i + 1 ) + "/" + number_of_genomes );
1711 log( ( i + 1 ) + "/" + number_of_genomes, log_writer );
1712 System.out.println( "Processing : " + input_file_properties[ i ][ 1 ]
1713 + " [" + input_file_properties[ i ][ 0 ] + "]" );
1714 log( "Genome : " + input_file_properties[ i ][ 1 ] + " ["
1715 + input_file_properties[ i ][ 0 ] + "]", log_writer );
1716 HmmscanPerDomainTableParser parser = null;
1717 INDIVIDUAL_SCORE_CUTOFF ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF.NONE;
1718 if ( individual_score_cutoffs != null ) {
1719 ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF_DEFAULT;
1721 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1722 || ( negative_domains_filter_file != null ) ) {
1723 HmmscanPerDomainTableParser.FilterType filter_type = HmmscanPerDomainTableParser.FilterType.NONE;
1724 if ( positive_filter_file != null ) {
1725 filter_type = HmmscanPerDomainTableParser.FilterType.POSITIVE_PROTEIN;
1727 else if ( negative_filter_file != null ) {
1728 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_PROTEIN;
1730 else if ( negative_domains_filter_file != null ) {
1731 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_DOMAIN;
1733 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1734 input_file_properties[ i ][ 1 ],
1741 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1742 input_file_properties[ i ][ 1 ],
1746 if ( e_value_max >= 0.0 ) {
1747 parser.setEValueMaximum( e_value_max );
1749 parser.setIgnoreDufs( ignore_dufs );
1750 parser.setIgnoreVirusLikeIds( ignore_virus_like_ids );
1751 parser.setIgnoreEngulfedDomains( no_engulfing_overlaps );
1752 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1753 parser.setMaxAllowedOverlap( max_allowed_overlap );
1755 parser.setReturnType( HmmscanPerDomainTableParser.ReturnType.UNORDERED_PROTEIN_DOMAIN_COLLECTION_PER_PROTEIN );
1756 if ( individual_score_cutoffs != null ) {
1757 parser.setIndividualScoreCutoffs( individual_score_cutoffs );
1759 List<Protein> protein_list = null;
1761 protein_list = parser.parse();
1763 catch ( final IOException e ) {
1764 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1766 catch ( final Exception e ) {
1767 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, e.getMessage(), e );
1770 System.out.println( "Domains ignored due to negative domain filter: " );
1771 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToNegativeDomainFilterCountsMap() );
1772 System.out.println( "Domains ignored due to virus like id: " );
1773 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToVirusLikeIdCountsMap() );
1775 final double coverage = ( double ) protein_list.size() / parser.getProteinsEncountered();
1776 protein_coverage_stats.addValue( coverage );
1777 int distinct_das = -1;
1778 if ( da_analysis ) {
1779 final String genome = input_file_properties[ i ][ 0 ];
1780 distinct_das = SurfacingUtil.storeDomainArchitectures( genome,
1781 distinct_domain_architecutures_per_genome,
1783 distinct_domain_architecuture_counts );
1785 System.out.println( "Number of proteins encountered : " + parser.getProteinsEncountered() );
1786 log( "Number of proteins encountered : " + parser.getProteinsEncountered(), log_writer );
1787 System.out.println( "Number of proteins stored : " + protein_list.size() );
1788 log( "Number of proteins stored : " + protein_list.size(), log_writer );
1789 System.out.println( "Coverage : "
1790 + ForesterUtil.roundToInt( 100.0 * coverage ) + "%" );
1791 log( "Coverage : " + ForesterUtil.roundToInt( 100.0 * coverage )
1792 + "%", log_writer );
1793 System.out.println( "Domains encountered : " + parser.getDomainsEncountered() );
1794 log( "Domains encountered : " + parser.getDomainsEncountered(), log_writer );
1795 System.out.println( "Domains stored : " + parser.getDomainsStored() );
1796 log( "Domains stored : " + parser.getDomainsStored(), log_writer );
1797 System.out.println( "Distinct domains stored : "
1798 + parser.getDomainsStoredSet().size() );
1799 log( "Distinct domains stored : " + parser.getDomainsStoredSet().size(), log_writer );
1800 System.out.println( "Domains ignored due to individual score cutoffs: "
1801 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() );
1802 log( "Domains ignored due to individual score cutoffs: "
1803 + parser.getDomainsIgnoredDueToIndividualScoreCutoff(),
1805 System.out.println( "Domains ignored due to E-value : "
1806 + parser.getDomainsIgnoredDueToEval() );
1807 log( "Domains ignored due to E-value : " + parser.getDomainsIgnoredDueToEval(), log_writer );
1808 System.out.println( "Domains ignored due to DUF designation : "
1809 + parser.getDomainsIgnoredDueToDuf() );
1810 log( "Domains ignored due to DUF designation : " + parser.getDomainsIgnoredDueToDuf(), log_writer );
1811 if ( ignore_virus_like_ids ) {
1812 System.out.println( "Domains ignored due virus like ids : "
1813 + parser.getDomainsIgnoredDueToVirusLikeIds() );
1814 log( "Domains ignored due virus like ids : " + parser.getDomainsIgnoredDueToVirusLikeIds(),
1817 System.out.println( "Domains ignored due negative domain filter : "
1818 + parser.getDomainsIgnoredDueToNegativeDomainFilter() );
1819 log( "Domains ignored due negative domain filter : "
1820 + parser.getDomainsIgnoredDueToNegativeDomainFilter(),
1822 System.out.println( "Domains ignored due to overlap : "
1823 + parser.getDomainsIgnoredDueToOverlap() );
1824 log( "Domains ignored due to overlap : " + parser.getDomainsIgnoredDueToOverlap(),
1826 if ( negative_filter_file != null ) {
1827 System.out.println( "Proteins ignored due to negative filter : "
1828 + parser.getProteinsIgnoredDueToFilter() );
1829 log( "Proteins ignored due to negative filter : " + parser.getProteinsIgnoredDueToFilter(),
1832 if ( positive_filter_file != null ) {
1833 System.out.println( "Proteins ignored due to positive filter : "
1834 + parser.getProteinsIgnoredDueToFilter() );
1835 log( "Proteins ignored due to positive filter : " + parser.getProteinsIgnoredDueToFilter(),
1838 if ( da_analysis ) {
1839 System.out.println( "Distinct domain architectures stored : " + distinct_das );
1840 log( "Distinct domain architectures stored : " + distinct_das, log_writer );
1842 System.out.println( "Time for processing : " + parser.getTime() + "ms" );
1843 log( "", log_writer );
1846 for( final Protein protein : protein_list ) {
1847 dc_data_writer.write( SurfacingUtil.proteinToDomainCombinations( protein, count + "", "\t" )
1850 for( final Domain d : protein.getProteinDomains() ) {
1851 final String d_str = d.getDomainId().toString();
1852 if ( !domain_length_stats_by_domain.containsKey( d_str ) ) {
1853 domain_length_stats_by_domain.put( d_str, new BasicDescriptiveStatistics() );
1855 domain_length_stats_by_domain.get( d_str ).addValue( d.getLength() );
1859 catch ( final IOException e ) {
1860 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1862 SurfacingUtil.domainsPerProteinsStatistics( input_file_properties[ i ][ 1 ],
1864 all_genomes_domains_per_potein_stats,
1865 all_genomes_domains_per_potein_histo,
1866 domains_which_are_always_single,
1867 domains_which_are_sometimes_single_sometimes_not,
1868 domains_which_never_single,
1869 domains_per_potein_stats_writer );
1870 domain_lengths_table.addLengths( protein_list );
1871 if ( !da_analysis ) {
1872 gwcd_list.add( BasicGenomeWideCombinableDomains
1873 .createInstance( protein_list,
1874 ignore_combination_with_same,
1875 new BasicSpecies( input_file_properties[ i ][ 1 ] ),
1876 domain_id_to_go_ids_map,
1878 protein_length_stats_by_dc,
1879 domain_number_stats_by_dc ) );
1880 if ( gwcd_list.get( i ).getSize() > 0 ) {
1881 SurfacingUtil.writeDomainCombinationsCountsFile( input_file_properties,
1883 per_genome_domain_promiscuity_statistics_writer,
1887 if ( output_binary_domain_combinationsfor_graph_analysis ) {
1888 SurfacingUtil.writeBinaryDomainCombinationsFileForGraphAnalysis( input_file_properties,
1894 SurfacingUtil.addAllDomainIdsToSet( gwcd_list.get( i ), all_domains_encountered );
1895 SurfacingUtil.addAllBinaryDomainCombinationToSet( gwcd_list.get( i ),
1896 all_bin_domain_combinations_encountered );
1899 if ( query_domains_writer_ary != null ) {
1900 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1902 SurfacingUtil.extractProteinNames( protein_list,
1903 query_domain_ids_array[ j ],
1904 query_domains_writer_ary[ j ],
1906 LIMIT_SPEC_FOR_PROT_EX );
1907 query_domains_writer_ary[ j ].flush();
1909 catch ( final IOException e ) {
1910 e.printStackTrace();
1914 if ( need_protein_lists_per_species ) {
1915 protein_lists_per_species.put( new BasicSpecies( input_file_properties[ i ][ 1 ] ), protein_list );
1920 catch ( final IOException e2 ) {
1921 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1924 } // for( int i = 0; i < number_of_genomes; ++i ) {
1925 ForesterUtil.programMessage( PRG_NAME, "Wrote domain promiscuities to: "
1926 + per_genome_domain_promiscuity_statistics_file );
1928 if ( da_analysis ) {
1929 SurfacingUtil.performDomainArchitectureAnalysis( distinct_domain_architecutures_per_genome,
1930 distinct_domain_architecuture_counts,
1932 new File( out_dir.toString() + "/" + output_file
1933 + "_DA_counts.txt" ),
1934 new File( out_dir.toString() + "/" + output_file
1935 + "_unique_DAs.txt" ) );
1936 distinct_domain_architecutures_per_genome.clear();
1937 distinct_domain_architecuture_counts.clear();
1941 domains_per_potein_stats_writer.write( "ALL" );
1942 domains_per_potein_stats_writer.write( "\t" );
1943 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.arithmeticMean() + "" );
1944 domains_per_potein_stats_writer.write( "\t" );
1945 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.sampleStandardDeviation() + "" );
1946 domains_per_potein_stats_writer.write( "\t" );
1947 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.median() + "" );
1948 domains_per_potein_stats_writer.write( "\t" );
1949 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getN() + "" );
1950 domains_per_potein_stats_writer.write( "\t" );
1951 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMin() + "" );
1952 domains_per_potein_stats_writer.write( "\t" );
1953 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMax() + "" );
1954 domains_per_potein_stats_writer.write( "\n" );
1955 domains_per_potein_stats_writer.close();
1956 printOutPercentageOfMultidomainProteins( all_genomes_domains_per_potein_histo, log_writer );
1957 ForesterUtil.map2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1958 + "_all_genomes_domains_per_potein_histo.txt" ), all_genomes_domains_per_potein_histo, "\t", "\n" );
1959 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1960 + "_domains_always_single_.txt" ), domains_which_are_always_single, "\n" );
1961 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1962 + "_domains_single_or_combined.txt" ), domains_which_are_sometimes_single_sometimes_not, "\n" );
1963 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1964 + "_domains_always_combined.txt" ), domains_which_never_single, "\n" );
1965 ForesterUtil.programMessage( PRG_NAME,
1966 "Average of proteins with a least one domain assigned: "
1967 + ( 100 * protein_coverage_stats.arithmeticMean() ) + "% (+/-"
1968 + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)" );
1969 ForesterUtil.programMessage( PRG_NAME, "Range of proteins with a least one domain assigned: "
1970 + ( 100 * protein_coverage_stats.getMin() ) + "%-" + ( 100 * protein_coverage_stats.getMax() )
1972 log( "Average of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.arithmeticMean() )
1973 + "% (+/-" + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)", log_writer );
1974 log( "Range of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.getMin() ) + "%-"
1975 + ( 100 * protein_coverage_stats.getMax() ) + "%", log_writer );
1977 catch ( final IOException e2 ) {
1978 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1980 if ( query_domains_writer_ary != null ) {
1981 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1983 query_domains_writer_ary[ j ].close();
1985 catch ( final IOException e ) {
1986 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1991 per_genome_domain_promiscuity_statistics_writer.close();
1992 dc_data_writer.close();
1995 catch ( final IOException e2 ) {
1996 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1998 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
2000 SurfacingUtil.executeDomainLengthAnalysis( input_file_properties,
2002 domain_lengths_table,
2003 domain_lengths_analysis_outfile );
2005 catch ( final IOException e1 ) {
2006 ForesterUtil.fatalError( surfacing.PRG_NAME, e1.toString() );
2008 System.out.println();
2009 ForesterUtil.programMessage( PRG_NAME, "Wrote domain length data to: " + domain_lengths_analysis_outfile );
2010 System.out.println();
2012 final long analysis_start_time = new Date().getTime();
2013 PairwiseDomainSimilarityCalculator pw_calc = null;
2014 // double[] values_for_all_scores_histogram = null;
2015 final DomainSimilarityCalculator calc = new BasicDomainSimilarityCalculator( domain_similarity_sort_field,
2016 sort_by_species_count_first,
2017 number_of_genomes == 2 );
2018 switch ( scoring ) {
2020 pw_calc = new CombinationsBasedPairwiseDomainSimilarityCalculator();
2023 pw_calc = new DomainCountsBasedPairwiseSimilarityCalculator();
2026 pw_calc = new ProteinCountsBasedPairwiseDomainSimilarityCalculator();
2029 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
2031 DomainSimilarityCalculator.GoAnnotationOutput go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.NONE;
2032 if ( domain_id_to_go_ids_map != null ) {
2033 go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.ALL;
2035 final SortedSet<DomainSimilarity> similarities = calc
2036 .calculateSimilarities( pw_calc,
2038 ignore_domains_without_combs_in_all_spec,
2039 ignore_species_specific_domains );
2040 SurfacingUtil.decoratePrintableDomainSimilarities( similarities, detailedness );
2041 final Map<String, Integer> tax_code_to_id_map = SurfacingUtil.createTaxCodeToIdMap( intrees[ 0 ] );
2043 String my_outfile = output_file.toString();
2044 Map<Character, Writer> split_writers = null;
2045 Writer writer = null;
2046 if ( similarities.size() > MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING ) {
2047 if ( my_outfile.endsWith( ".html" ) ) {
2048 my_outfile = my_outfile.substring( 0, my_outfile.length() - 5 );
2050 split_writers = new HashMap<Character, Writer>();
2051 createSplitWriters( out_dir, my_outfile, split_writers );
2053 else if ( !my_outfile.endsWith( ".html" ) ) {
2054 my_outfile += ".html";
2055 writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) );
2057 List<Species> species_order = null;
2058 if ( species_matrix ) {
2059 species_order = new ArrayList<Species>();
2060 for( int i = 0; i < number_of_genomes; i++ ) {
2061 species_order.add( new BasicSpecies( input_file_properties[ i ][ 1 ] ) );
2064 html_desc.append( "<tr><td>Sum of all distinct binary combinations:</td><td>"
2065 + all_bin_domain_combinations_encountered.size() + "</td></tr>" + nl );
2066 html_desc.append( "<tr><td>Sum of all distinct domains:</td><td>" + all_domains_encountered.size()
2067 + "</td></tr>" + nl );
2068 html_desc.append( "<tr><td>Analysis date/time:</td><td>"
2069 + new java.text.SimpleDateFormat( "yyyy.MM.dd HH:mm:ss" ).format( new java.util.Date() )
2070 + "</td></tr>" + nl );
2071 html_desc.append( "</table>" + nl );
2072 final DescriptiveStatistics pw_stats = SurfacingUtil
2073 .writeDomainSimilaritiesToFile( html_desc,
2074 new StringBuilder( number_of_genomes + " genomes" ),
2078 number_of_genomes == 2,
2080 domain_similarity_print_option,
2085 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote main output (includes domain similarities) to: \""
2086 + ( out_dir == null ? my_outfile : out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) + "\"" );
2088 catch ( final IOException e ) {
2089 ForesterUtil.fatalError( surfacing.PRG_NAME, "Failed to write similarites to: \"" + output_file + "\" ["
2090 + e.getMessage() + "]" );
2092 System.out.println();
2093 final Species[] species = new Species[ number_of_genomes ];
2094 for( int i = 0; i < number_of_genomes; ++i ) {
2095 species[ i ] = new BasicSpecies( input_file_properties[ i ][ 1 ] );
2097 List<Phylogeny> inferred_trees = null;
2098 if ( ( number_of_genomes > 2 ) && perform_pwc ) {
2099 final PairwiseGenomeComparator pwgc = new PairwiseGenomeComparator();
2100 pwgc.performPairwiseComparisons( html_desc,
2101 sort_by_species_count_first,
2103 ignore_domains_without_combs_in_all_spec,
2104 ignore_species_specific_domains,
2105 domain_similarity_sort_field_for_automated_pwc,
2106 domain_similarity_print_option,
2108 domain_id_to_go_ids_map,
2115 automated_pairwise_comparison_suffix,
2117 surfacing.PAIRWISE_DOMAIN_COMPARISONS_PREFIX,
2121 tax_code_to_id_map );
2122 String matrix_output_file = new String( output_file.toString() );
2123 if ( matrix_output_file.indexOf( '.' ) > 1 ) {
2124 matrix_output_file = matrix_output_file.substring( 0, matrix_output_file.indexOf( '.' ) );
2126 if ( out_dir != null ) {
2127 matrix_output_file = out_dir + ForesterUtil.FILE_SEPARATOR + matrix_output_file;
2128 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2130 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2131 + surfacing.MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans() );
2133 .writeMatrixToFile( new File( matrix_output_file
2134 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2135 pwgc.getSharedBinaryCombinationsBasedDistances() );
2136 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2137 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2138 pwgc.getSharedDomainsBasedDistances() );
2139 final Phylogeny nj_gd = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2140 + surfacing.NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans()
2142 final Phylogeny nj_bc = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2143 + surfacing.NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2144 .getSharedBinaryCombinationsBasedDistances().get( 0 ) );
2145 final Phylogeny nj_d = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2146 + surfacing.NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2147 .getSharedDomainsBasedDistances().get( 0 ) );
2148 inferred_trees = new ArrayList<Phylogeny>();
2149 inferred_trees.add( nj_gd );
2150 inferred_trees.add( nj_bc );
2151 inferred_trees.add( nj_d );
2152 } // if ( ( output_file != null ) && ( number_of_genomes > 2 ) && !isEmpty( automated_pairwise_comparison_suffix ) )
2153 if ( ( out_dir != null ) && ( !perform_pwc ) ) {
2154 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2156 if ( write_to_nexus ) {
2157 writePresentToNexus( output_file, positive_filter_file, filter, gwcd_list );
2159 if ( ( ( intrees != null ) && ( intrees.length > 0 ) ) && ( number_of_genomes > 2 ) ) {
2160 final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
2162 max_allowed_overlap,
2163 no_engulfing_overlaps,
2167 if ( radomize_fitch_parsimony ) {
2168 s += random_number_seed_for_fitch_parsimony + "_";
2171 for( final Phylogeny intree : intrees ) {
2172 final String outfile_name = ForesterUtil.removeSuffix( output_file.toString() ) + s
2173 + ForesterUtil.removeSuffix( intree_files[ i ].toString() );
2174 final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator.createInstance( intree,
2176 SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
2177 radomize_fitch_parsimony,
2181 domain_id_to_go_ids_map,
2184 parameters_sb.toString(),
2185 domain_id_to_secondary_features_maps,
2186 positive_filter_file == null ? null : filter,
2187 output_binary_domain_combinationsfor_graph_analysis,
2188 all_bin_domain_combinations_gained_fitch,
2189 all_bin_domain_combinations_lost_fitch,
2191 protein_length_stats_by_dc,
2192 domain_number_stats_by_dc,
2193 domain_length_stats_by_domain,
2196 use_last_in_fitch_parsimony );
2197 // Listing of all domain combinations gained is only done if only one input tree is used.
2198 if ( ( domain_id_to_secondary_features_maps != null )
2199 && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
2201 for( final Map<String, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
2202 final Map<Species, MappingResults> mapping_results_map = new TreeMap<Species, MappingResults>();
2203 final DomainParsimonyCalculator secondary_features_parsimony = DomainParsimonyCalculator
2204 .createInstance( intree, gwcd_list, domain_id_to_secondary_features_map );
2206 .executeParsimonyAnalysisForSecondaryFeatures( outfile_name
2208 + secondary_features_map_files[ j++ ],
2209 secondary_features_parsimony,
2211 parameters_sb.toString(),
2212 mapping_results_map,
2213 use_last_in_fitch_parsimony );
2215 System.out.println();
2216 System.out.println( "Mapping to secondary features:" );
2217 for( final Species spec : mapping_results_map.keySet() ) {
2218 final MappingResults mapping_results = mapping_results_map.get( spec );
2219 final int total_domains = mapping_results.getSumOfFailures()
2220 + mapping_results.getSumOfSuccesses();
2221 System.out.print( spec + ":" );
2222 System.out.print( " mapped domains = " + mapping_results.getSumOfSuccesses() );
2223 System.out.print( ", not mapped domains = " + mapping_results.getSumOfFailures() );
2224 if ( total_domains > 0 ) {
2225 System.out.println( ", mapped ratio = "
2226 + ( ( 100 * mapping_results.getSumOfSuccesses() ) / total_domains ) + "%" );
2229 System.out.println( ", mapped ratio = n/a (total domains = 0 )" );
2236 } // for( final Phylogeny intree : intrees ) {
2238 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
2239 executePlusMinusAnalysis( output_file,
2240 plus_minus_analysis_high_copy_base_species,
2241 plus_minus_analysis_high_copy_target_species,
2242 plus_minus_analysis_high_low_copy_species,
2244 protein_lists_per_species,
2245 domain_id_to_go_ids_map,
2247 plus_minus_analysis_numbers );
2249 if ( output_protein_lists_for_all_domains ) {
2250 writeProteinListsForAllSpecies( out_dir,
2251 protein_lists_per_species,
2253 output_list_of_all_proteins_per_domain_e_value_max );
2256 if ( all_bin_domain_combinations_gained_fitch != null ) {
2258 executeFitchGainsAnalysis( new File( output_file
2259 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2260 all_bin_domain_combinations_gained_fitch,
2261 all_domains_encountered.size(),
2262 all_bin_domain_combinations_encountered,
2265 catch ( final IOException e ) {
2266 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2269 if ( all_bin_domain_combinations_lost_fitch != null ) {
2271 executeFitchGainsAnalysis( new File( output_file
2272 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2273 all_bin_domain_combinations_lost_fitch,
2274 all_domains_encountered.size(),
2275 all_bin_domain_combinations_encountered,
2278 catch ( final IOException e ) {
2279 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2282 final Runtime rt = java.lang.Runtime.getRuntime();
2283 final long free_memory = rt.freeMemory() / 1000000;
2284 final long total_memory = rt.totalMemory() / 1000000;
2285 ForesterUtil.programMessage( PRG_NAME, "Time for analysis : " + ( new Date().getTime() - analysis_start_time )
2287 ForesterUtil.programMessage( PRG_NAME, "Total running time: " + ( new Date().getTime() - start_time ) + "ms " );
2288 ForesterUtil.programMessage( PRG_NAME, "Free memory : " + free_memory + "MB, total memory: "
2289 + total_memory + "MB" );
2290 ForesterUtil.programMessage( PRG_NAME, "If this application is useful to you, please cite:" );
2291 ForesterUtil.programMessage( PRG_NAME, surfacing.WWW );
2292 ForesterUtil.programMessage( PRG_NAME, "OK" );
2293 System.out.println();
2296 private static void createSplitWriters( final File out_dir,
2297 final String my_outfile,
2298 final Map<Character, Writer> split_writers ) throws IOException {
2299 split_writers.put( 'a', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2300 + "_domains_A.html" ) ) );
2301 split_writers.put( 'b', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2302 + "_domains_B.html" ) ) );
2303 split_writers.put( 'c', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2304 + "_domains_C.html" ) ) );
2305 split_writers.put( 'd', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2306 + "_domains_D.html" ) ) );
2307 split_writers.put( 'e', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2308 + "_domains_E.html" ) ) );
2309 split_writers.put( 'f', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2310 + "_domains_F.html" ) ) );
2311 split_writers.put( 'g', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2312 + "_domains_G.html" ) ) );
2313 split_writers.put( 'h', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2314 + "_domains_H.html" ) ) );
2315 split_writers.put( 'i', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2316 + "_domains_I.html" ) ) );
2317 split_writers.put( 'j', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2318 + "_domains_J.html" ) ) );
2319 split_writers.put( 'k', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2320 + "_domains_K.html" ) ) );
2321 split_writers.put( 'l', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2322 + "_domains_L.html" ) ) );
2323 split_writers.put( 'm', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2324 + "_domains_M.html" ) ) );
2325 split_writers.put( 'n', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2326 + "_domains_N.html" ) ) );
2327 split_writers.put( 'o', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2328 + "_domains_O.html" ) ) );
2329 split_writers.put( 'p', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2330 + "_domains_P.html" ) ) );
2331 split_writers.put( 'q', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2332 + "_domains_Q.html" ) ) );
2333 split_writers.put( 'r', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2334 + "_domains_R.html" ) ) );
2335 split_writers.put( 's', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2336 + "_domains_S.html" ) ) );
2337 split_writers.put( 't', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2338 + "_domains_T.html" ) ) );
2339 split_writers.put( 'u', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2340 + "_domains_U.html" ) ) );
2341 split_writers.put( 'v', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2342 + "_domains_V.html" ) ) );
2343 split_writers.put( 'w', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2344 + "_domains_W.html" ) ) );
2345 split_writers.put( 'x', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2346 + "_domains_X.html" ) ) );
2347 split_writers.put( 'y', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2348 + "_domains_Y.html" ) ) );
2349 split_writers.put( 'z', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2350 + "_domains_Z.html" ) ) );
2351 split_writers.put( '0', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2352 + "_domains_0.html" ) ) );
2355 private static void printOutPercentageOfMultidomainProteins( final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo,
2356 final Writer log_writer ) {
2358 for( final Entry<Integer, Integer> entry : all_genomes_domains_per_potein_histo.entrySet() ) {
2359 sum += entry.getValue();
2361 final double percentage = ( 100.0 * ( sum - all_genomes_domains_per_potein_histo.get( 1 ) ) ) / sum;
2362 ForesterUtil.programMessage( PRG_NAME, "Percentage of multidomain proteins: " + percentage + "%" );
2363 log( "Percentage of multidomain proteins: : " + percentage + "%", log_writer );
2366 private static void preparePhylogenyForParsimonyAnalyses( final Phylogeny intree,
2367 final String[][] input_file_properties ) {
2368 final String[] genomes = new String[ input_file_properties.length ];
2369 for( int i = 0; i < input_file_properties.length; ++i ) {
2370 if ( intree.getNodes( input_file_properties[ i ][ 1 ] ).size() > 1 ) {
2371 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
2372 + "] is not unique in input tree " + intree.getName() );
2374 genomes[ i ] = input_file_properties[ i ][ 1 ];
2377 final PhylogenyNodeIterator it = intree.iteratorPostorder();
2378 while ( it.hasNext() ) {
2379 final PhylogenyNode n = it.next();
2380 if ( ForesterUtil.isEmpty( n.getName() ) ) {
2381 if ( n.getNodeData().isHasTaxonomy()
2382 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getTaxonomyCode() ) ) {
2383 n.setName( n.getNodeData().getTaxonomy().getTaxonomyCode() );
2385 else if ( n.getNodeData().isHasTaxonomy()
2386 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
2387 n.setName( n.getNodeData().getTaxonomy().getScientificName() );
2389 else if ( n.getNodeData().isHasTaxonomy()
2390 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getCommonName() ) ) {
2391 n.setName( n.getNodeData().getTaxonomy().getCommonName() );
2395 .fatalError( surfacing.PRG_NAME,
2396 "node with no name, scientific name, common name, or taxonomy code present" );
2401 final List<String> igns = PhylogenyMethods.deleteExternalNodesPositiveSelection( genomes, intree );
2402 if ( igns.size() > 0 ) {
2403 System.out.println( "Not using the following " + igns.size() + " nodes:" );
2404 for( int i = 0; i < igns.size(); ++i ) {
2405 System.out.println( " " + i + ": " + igns.get( i ) );
2407 System.out.println( "--" );
2409 for( final String[] input_file_propertie : input_file_properties ) {
2411 intree.getNode( input_file_propertie[ 1 ] );
2413 catch ( final IllegalArgumentException e ) {
2414 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_propertie[ 1 ]
2415 + "] not present/not unique in input tree" );
2420 private static void printHelp() {
2421 System.out.println();
2422 System.out.println( "Usage:" );
2423 System.out.println();
2424 System.out.println( "% java -Xms256m -Xmx512m -cp forester.jar org.forester.applications." + surfacing.PRG_NAME
2425 + " [options] <phylogen(y|ies) infile> [external node name 1] [name 2] ... [name n]" );
2426 System.out.println();
2427 System.out.println( " Note: This software might need a significant amount of memory (heap space);" );
2429 .println( " hence use \"-Xms128m -Xmx512m\" (or more) to prevent a \"java.lang.OutOfMemoryError\"." );
2430 System.out.println();
2431 System.out.println( " Options: " );
2432 System.out.println( surfacing.DETAILEDNESS_OPTION + ": level of detail for similarities output file (default:"
2433 + DETAILEDNESS_DEFAULT + ")" );
2434 System.out.println( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION
2435 + ": to ignore combinations with self (default: not to ignore)" );
2437 .println( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION
2438 + ": to ignore domains without combinations in any species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2440 .println( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION
2441 + ": to ignore domains specific to one species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2442 System.out.println( surfacing.NOT_IGNORE_DUFS_OPTION
2443 + ": to _not_ ignore DUFs (domains with unknown function) (default: ignore DUFs)" );
2445 .println( surfacing.IGNORE_VIRAL_IDS
2446 + ": to ignore domains with ids containing 'vir', 'retro', 'transpos', 'phage', or starting with 'rv' or 'gag_'" );
2447 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_OPTION + ": sorting for similarities (default: "
2448 + DOMAIN_SORT_FILD_DEFAULT + ")" );
2449 System.out.println( surfacing.OUTPUT_FILE_OPTION + ": name for (main) output file (mandatory)" );
2450 System.out.println( surfacing.MAX_E_VALUE_OPTION + ": max (inclusive) E-value" );
2451 System.out.println( surfacing.MAX_ALLOWED_OVERLAP_OPTION + ": maximal allowed domain overlap" );
2452 System.out.println( surfacing.NO_ENGULFING_OVERLAP_OPTION + ": to ignore engulfed lower confidence domains" );
2453 System.out.println( surfacing.SPECIES_MATRIX_OPTION + ": species matrix" );
2454 System.out.println( surfacing.SCORING_OPTION + ": scoring (default:" + SCORING_DEFAULT + ")" );
2455 System.out.println( surfacing.DOMAIN_COUNT_SORT_OPTION + ": sorting for domain counts (default:"
2456 + DOMAINS_SORT_ORDER_DEFAULT + ")" );
2457 System.out.println( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION + ": domain similarity print option (default:"
2458 + DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT + ")" );
2459 System.out.println( surfacing.CUTOFF_SCORE_FILE_OPTION + ": cutoff score file" );
2460 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION
2461 + ": sort by species count first" );
2462 System.out.println( surfacing.OUTPUT_DIR_OPTION + ": output directory" );
2463 System.out.println( surfacing.PFAM_TO_GO_FILE_USE_OPTION + ": Pfam to GO mapping file" );
2464 System.out.println( surfacing.GO_OBO_FILE_USE_OPTION + ": GO terms file (OBO format)" );
2465 System.out.println( surfacing.GO_NAMESPACE_LIMIT_OPTION + ": limit GO term to one GO namespace" );
2466 System.out.println( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
2467 + "[=<suffix for pairwise comparison output files>]: to perform pairwise comparison based analyses" );
2468 System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION
2469 + ": species tree, to perform (Dollo, Fitch) parismony analyses" );
2471 .println( surfacing.INPUT_SPECIES_TREE_OPTION
2472 + "=<treefiles in phyloXML format, separated by #>: to infer domain/binary domain combination gains/losses on given species trees" );
2473 System.out.println( surfacing.FILTER_POSITIVE_OPTION
2474 + "=<file>: to filter out proteins not containing at least one domain listed in <file>" );
2475 System.out.println( surfacing.FILTER_NEGATIVE_OPTION
2476 + "=<file>: to filter out proteins containing at least one domain listed in <file>" );
2477 System.out.println( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION
2478 + "=<file>: to filter out (ignore) domains listed in <file>" );
2479 System.out.println( surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>: to read input files from <file>" );
2481 .println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION
2482 + "=<seed>: seed for random number generator for Fitch Parsimony analysis (type: long, default: no randomization - given a choice, prefer absence" );
2483 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS
2484 + ": to consider directedness in binary combinations: e.g. A-B != B-A" );
2485 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY
2486 + ": to consider directedness and adjacency in binary combinations" );
2488 .println( surfacing.SEQ_EXTRACT_OPTION
2489 + "=<domain ids (Pfam names)>: to extract sequence names of sequences containing matching domains and/or domain-sequences (order N to C) (domain separator: '~', domain sequences speparator: '#', e.g. 'NACHT#BIR~CARD')" );
2490 System.out.println( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE
2491 + "=<file>: to perfom parsimony analysis on secondary features" );
2492 System.out.println( surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>: to presence/absence genome analysis" );
2493 System.out.println( surfacing.DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS
2494 + ": to output binary domain combinations for (downstream) graph analysis" );
2495 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS + ": to output all proteins per domain" );
2496 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION
2497 + ": e value max per domain for output of all proteins per domain" );
2498 System.out.println( surfacing.USE_LAST_IN_FITCH_OPTION + ": to use last in Fitch parsimony" );
2499 System.out.println( surfacing.WRITE_TO_NEXUS_OPTION + ": to output in Nexus format" );
2500 System.out.println( PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION + ": to perform DC regain protein statistics" );
2501 System.out.println( DA_ANALYSIS_OPTION + ": to do DA analysis" );
2502 System.out.println();
2503 System.out.println( "Example 1: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2504 + " org.forester.application.surfacing p2g=pfam2go_2012_02_07.txt -dufs -cos=Pfam_260_NC1"
2505 + " -no_eo -mo=0 -genomes=eukaryotes.txt -out_dir=out -o=o "
2506 + " -species_tree=tol.xml -obo=gene_ontology_2012_02_07.obo -pos_filter=f.txt -all_prot" );
2507 System.out.println();
2508 System.out.println( "Example 2: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2509 + " org.forester.application.surfacing -detail=punctilious -o=TEST.html -pwc=TEST"
2510 + " -cos=Pfam_ls_22_TC2 -p2g=pfam2go -obo=gene_ontology_edit.obo "
2511 + "-dc_sort=dom -ignore_with_self -no_singles -e=0.001 -mo=1 -no_eo -genomes=eukaryotes.txt "
2512 + "-ds_output=detailed_html -scoring=domains -sort=alpha " );
2513 System.out.println();
2516 private static void processFilter( final File filter_file, final SortedSet<String> filter ) {
2517 SortedSet<String> filter_str = null;
2519 filter_str = ForesterUtil.file2set( filter_file );
2521 catch ( final IOException e ) {
2522 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2524 if ( filter_str != null ) {
2525 for( final String string : filter_str ) {
2526 filter.add( string );
2530 System.out.println( "Filter:" );
2531 for( final String domainId : filter ) {
2532 System.out.println( domainId );
2537 private static String[][] processInputGenomesFile( final File input_genomes ) {
2538 String[][] input_file_properties = null;
2540 input_file_properties = ForesterUtil.file22dArray( input_genomes );
2542 catch ( final IOException e ) {
2543 ForesterUtil.fatalError( surfacing.PRG_NAME,
2544 "genomes files is to be in the following format \"<hmmpfam output file> <species>\": "
2545 + e.getLocalizedMessage() );
2547 final Set<String> specs = new HashSet<String>();
2548 final Set<String> paths = new HashSet<String>();
2549 for( int i = 0; i < input_file_properties.length; ++i ) {
2550 if ( !PhyloXmlUtil.TAXOMONY_CODE_PATTERN.matcher( input_file_properties[ i ][ 1 ] ).matches() ) {
2551 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for species code: "
2552 + input_file_properties[ i ][ 1 ] );
2554 if ( specs.contains( input_file_properties[ i ][ 1 ] ) ) {
2555 ForesterUtil.fatalError( surfacing.PRG_NAME, "species code " + input_file_properties[ i ][ 1 ]
2556 + " is not unique" );
2558 specs.add( input_file_properties[ i ][ 1 ] );
2559 if ( paths.contains( input_file_properties[ i ][ 0 ] ) ) {
2560 ForesterUtil.fatalError( surfacing.PRG_NAME, "path " + input_file_properties[ i ][ 0 ]
2561 + " is not unique" );
2563 paths.add( input_file_properties[ i ][ 0 ] );
2564 final String error = ForesterUtil.isReadableFile( new File( input_file_properties[ i ][ 0 ] ) );
2565 if ( !ForesterUtil.isEmpty( error ) ) {
2566 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
2569 return input_file_properties;
2572 private static void processPlusMinusAnalysisOption( final CommandLineArguments cla,
2573 final List<String> high_copy_base,
2574 final List<String> high_copy_target,
2575 final List<String> low_copy,
2576 final List<Object> numbers ) {
2577 if ( cla.isOptionSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2578 if ( !cla.isOptionValueSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2579 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for 'plus-minus' file: -"
2580 + surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>" );
2582 final File plus_minus_file = new File( cla.getOptionValue( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) );
2583 final String msg = ForesterUtil.isReadableFile( plus_minus_file );
2584 if ( !ForesterUtil.isEmpty( msg ) ) {
2585 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + plus_minus_file + "\": " + msg );
2587 processPlusMinusFile( plus_minus_file, high_copy_base, high_copy_target, low_copy, numbers );
2591 // First numbers is minimal difference, second is factor.
2592 private static void processPlusMinusFile( final File plus_minus_file,
2593 final List<String> high_copy_base,
2594 final List<String> high_copy_target,
2595 final List<String> low_copy,
2596 final List<Object> numbers ) {
2597 Set<String> species_set = null;
2598 int min_diff = PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT;
2599 double factor = PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT;
2601 species_set = ForesterUtil.file2set( plus_minus_file );
2603 catch ( final IOException e ) {
2604 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2606 if ( species_set != null ) {
2607 for( final String species : species_set ) {
2608 final String species_trimmed = species.substring( 1 );
2609 if ( species.startsWith( "+" ) ) {
2610 if ( low_copy.contains( species_trimmed ) ) {
2611 ForesterUtil.fatalError( surfacing.PRG_NAME,
2612 "species/genome names can not appear with both '+' and '-' suffix, as appears the case for: \""
2613 + species_trimmed + "\"" );
2615 high_copy_base.add( species_trimmed );
2617 else if ( species.startsWith( "*" ) ) {
2618 if ( low_copy.contains( species_trimmed ) ) {
2619 ForesterUtil.fatalError( surfacing.PRG_NAME,
2620 "species/genome names can not appear with both '*' and '-' suffix, as appears the case for: \""
2621 + species_trimmed + "\"" );
2623 high_copy_target.add( species_trimmed );
2625 else if ( species.startsWith( "-" ) ) {
2626 if ( high_copy_base.contains( species_trimmed ) || high_copy_target.contains( species_trimmed ) ) {
2627 ForesterUtil.fatalError( surfacing.PRG_NAME,
2628 "species/genome names can not appear with both '+' or '*' and '-' suffix, as appears the case for: \""
2629 + species_trimmed + "\"" );
2631 low_copy.add( species_trimmed );
2633 else if ( species.startsWith( "$D" ) ) {
2635 min_diff = Integer.parseInt( species.substring( 3 ) );
2637 catch ( final NumberFormatException e ) {
2638 ForesterUtil.fatalError( surfacing.PRG_NAME,
2639 "could not parse integer value for minimal difference from: \""
2640 + species.substring( 3 ) + "\"" );
2643 else if ( species.startsWith( "$F" ) ) {
2645 factor = Double.parseDouble( species.substring( 3 ) );
2647 catch ( final NumberFormatException e ) {
2648 ForesterUtil.fatalError( surfacing.PRG_NAME, "could not parse double value for factor from: \""
2649 + species.substring( 3 ) + "\"" );
2652 else if ( species.startsWith( "#" ) ) {
2657 .fatalError( surfacing.PRG_NAME,
2658 "species/genome names in 'plus minus' file must begin with '*' (high copy target genome), '+' (high copy base genomes), '-' (low copy genomes), '$D=<integer>' minimal Difference (default is 1), '$F=<double>' factor (default is 1.0), double), or '#' (ignore) suffix, encountered: \""
2661 numbers.add( new Integer( min_diff + "" ) );
2662 numbers.add( new Double( factor + "" ) );
2666 ForesterUtil.fatalError( surfacing.PRG_NAME, "'plus minus' file [" + plus_minus_file + "] appears empty" );
2670 private static void writePresentToNexus( final File output_file,
2671 final File positive_filter_file,
2672 final SortedSet<String> filter,
2673 final List<GenomeWideCombinableDomains> gwcd_list ) {
2676 .writeMatrixToFile( DomainParsimonyCalculator
2677 .createMatrixOfDomainPresenceOrAbsence( gwcd_list, positive_filter_file == null ? null
2678 : filter ), output_file + DOMAINS_PRESENT_NEXUS, Format.NEXUS_BINARY );
2679 SurfacingUtil.writeMatrixToFile( DomainParsimonyCalculator
2680 .createMatrixOfBinaryDomainCombinationPresenceOrAbsence( gwcd_list ), output_file
2681 + BDC_PRESENT_NEXUS, Format.NEXUS_BINARY );
2683 catch ( final Exception e ) {
2684 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2688 private static void writeProteinListsForAllSpecies( final File output_dir,
2689 final SortedMap<Species, List<Protein>> protein_lists_per_species,
2690 final List<GenomeWideCombinableDomains> gwcd_list,
2691 final double domain_e_cutoff ) {
2692 final SortedSet<String> all_domains = new TreeSet<String>();
2693 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
2694 all_domains.addAll( gwcd.getAllDomainIds() );
2696 for( final String domain : all_domains ) {
2697 final File out = new File( output_dir + ForesterUtil.FILE_SEPARATOR + domain + SEQ_EXTRACT_SUFFIX );
2698 SurfacingUtil.checkForOutputFileWriteability( out );
2700 final Writer proteins_file_writer = new BufferedWriter( new FileWriter( out ) );
2701 SurfacingUtil.extractProteinNames( protein_lists_per_species,
2703 proteins_file_writer,
2705 LIMIT_SPEC_FOR_PROT_EX,
2707 proteins_file_writer.close();
2709 catch ( final IOException e ) {
2710 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2712 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote proteins list to \"" + out + "\"" );