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 = "2.302";
229 final static private String PRG_DATE = "130715";
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";
281 private static final boolean CALC_SIMILARITY_SCORES = false;
283 private static void checkWriteabilityForPairwiseComparisons( final PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option,
284 final String[][] input_file_properties,
285 final String automated_pairwise_comparison_suffix,
286 final File outdir ) {
287 for( int i = 0; i < input_file_properties.length; ++i ) {
288 for( int j = 0; j < i; ++j ) {
289 final String species_i = input_file_properties[ i ][ 1 ];
290 final String species_j = input_file_properties[ j ][ 1 ];
291 String pairwise_similarities_output_file_str = PAIRWISE_DOMAIN_COMPARISONS_PREFIX + species_i + "_"
292 + species_j + automated_pairwise_comparison_suffix;
293 switch ( domain_similarity_print_option ) {
295 if ( !pairwise_similarities_output_file_str.endsWith( ".html" ) ) {
296 pairwise_similarities_output_file_str += ".html";
300 final String error = ForesterUtil
301 .isWritableFile( new File( outdir == null ? pairwise_similarities_output_file_str : outdir
302 + ForesterUtil.FILE_SEPARATOR + pairwise_similarities_output_file_str ) );
303 if ( !ForesterUtil.isEmpty( error ) ) {
304 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
310 private static StringBuilder createParametersAsString( final boolean ignore_dufs,
311 final double e_value_max,
312 final int max_allowed_overlap,
313 final boolean no_engulfing_overlaps,
314 final File cutoff_scores_file,
315 final BinaryDomainCombination.DomainCombinationType dc_type ) {
316 final StringBuilder parameters_sb = new StringBuilder();
317 parameters_sb.append( "E-value: " + e_value_max );
318 if ( cutoff_scores_file != null ) {
319 parameters_sb.append( ", Cutoff-scores-file: " + cutoff_scores_file );
322 parameters_sb.append( ", Cutoff-scores-file: not-set" );
324 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
325 parameters_sb.append( ", Max-overlap: " + max_allowed_overlap );
328 parameters_sb.append( ", Max-overlap: not-set" );
330 if ( no_engulfing_overlaps ) {
331 parameters_sb.append( ", Engulfing-overlaps: not-allowed" );
334 parameters_sb.append( ", Engulfing-overlaps: allowed" );
337 parameters_sb.append( ", Ignore-dufs: true" );
340 parameters_sb.append( ", Ignore-dufs: false" );
342 parameters_sb.append( ", DC type (if applicable): " + dc_type );
343 return parameters_sb;
347 * Warning: This side-effects 'all_bin_domain_combinations_encountered'!
351 * @param all_bin_domain_combinations_changed
352 * @param sum_of_all_domains_encountered
353 * @param all_bin_domain_combinations_encountered
354 * @param is_gains_analysis
355 * @param protein_length_stats_by_dc
356 * @throws IOException
358 private static void executeFitchGainsAnalysis( final File output_file,
359 final List<BinaryDomainCombination> all_bin_domain_combinations_changed,
360 final int sum_of_all_domains_encountered,
361 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered,
362 final boolean is_gains_analysis ) throws IOException {
363 SurfacingUtil.checkForOutputFileWriteability( output_file );
364 final Writer out = ForesterUtil.createBufferedWriter( output_file );
365 final SortedMap<Object, Integer> bdc_to_counts = ForesterUtil
366 .listToSortedCountsMap( all_bin_domain_combinations_changed );
367 final SortedSet<String> all_domains_in_combination_changed_more_than_once = new TreeSet<String>();
368 final SortedSet<String> all_domains_in_combination_changed_only_once = new TreeSet<String>();
371 for( final Object bdc_object : bdc_to_counts.keySet() ) {
372 final BinaryDomainCombination bdc = ( BinaryDomainCombination ) bdc_object;
373 final int count = bdc_to_counts.get( bdc_object );
375 ForesterUtil.unexpectedFatalError( PRG_NAME, "count < 1 " );
377 out.write( bdc + "\t" + count + ForesterUtil.LINE_SEPARATOR );
379 all_domains_in_combination_changed_more_than_once.add( bdc.getId0() );
380 all_domains_in_combination_changed_more_than_once.add( bdc.getId1() );
383 else if ( count == 1 ) {
384 all_domains_in_combination_changed_only_once.add( bdc.getId0() );
385 all_domains_in_combination_changed_only_once.add( bdc.getId1() );
389 final int all = all_bin_domain_combinations_encountered.size();
391 if ( !is_gains_analysis ) {
392 all_bin_domain_combinations_encountered.removeAll( all_bin_domain_combinations_changed );
393 never_lost = all_bin_domain_combinations_encountered.size();
394 for( final BinaryDomainCombination bdc : all_bin_domain_combinations_encountered ) {
395 out.write( bdc + "\t" + "0" + ForesterUtil.LINE_SEPARATOR );
398 if ( is_gains_analysis ) {
399 out.write( "Sum of all distinct domain combinations appearing once : " + one
400 + ForesterUtil.LINE_SEPARATOR );
401 out.write( "Sum of all distinct domain combinations appearing more than once : " + above_one
402 + ForesterUtil.LINE_SEPARATOR );
403 out.write( "Sum of all distinct domains in combinations apppearing only once : "
404 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
405 out.write( "Sum of all distinct domains in combinations apppearing more than once: "
406 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
409 out.write( "Sum of all distinct domain combinations never lost : " + never_lost
410 + ForesterUtil.LINE_SEPARATOR );
411 out.write( "Sum of all distinct domain combinations lost once : " + one
412 + ForesterUtil.LINE_SEPARATOR );
413 out.write( "Sum of all distinct domain combinations lost more than once : " + above_one
414 + ForesterUtil.LINE_SEPARATOR );
415 out.write( "Sum of all distinct domains in combinations lost only once : "
416 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
417 out.write( "Sum of all distinct domains in combinations lost more than once: "
418 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
420 out.write( "All binary combinations : " + all
421 + ForesterUtil.LINE_SEPARATOR );
422 out.write( "All domains : "
423 + sum_of_all_domains_encountered );
425 ForesterUtil.programMessage( surfacing.PRG_NAME,
426 "Wrote fitch domain combination dynamics counts analysis to \"" + output_file
430 private static void executePlusMinusAnalysis( final File output_file,
431 final List<String> plus_minus_analysis_high_copy_base,
432 final List<String> plus_minus_analysis_high_copy_target,
433 final List<String> plus_minus_analysis_low_copy,
434 final List<GenomeWideCombinableDomains> gwcd_list,
435 final SortedMap<Species, List<Protein>> protein_lists_per_species,
436 final Map<String, List<GoId>> domain_id_to_go_ids_map,
437 final Map<GoId, GoTerm> go_id_to_term_map,
438 final List<Object> plus_minus_analysis_numbers ) {
439 final Set<String> all_spec = new HashSet<String>();
440 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
441 all_spec.add( gwcd.getSpecies().getSpeciesId() );
443 final File html_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX_HTML );
444 final File plain_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX );
445 final File html_out_dc = new File( output_file + PLUS_MINUS_DC_SUFFIX_HTML );
446 final File all_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX );
447 final File passing_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX );
448 final File proteins_file_base = new File( output_file + "" );
449 final int min_diff = ( ( Integer ) plus_minus_analysis_numbers.get( 0 ) ).intValue();
450 final double factor = ( ( Double ) plus_minus_analysis_numbers.get( 1 ) ).doubleValue();
452 DomainCountsDifferenceUtil.calculateCopyNumberDifferences( gwcd_list,
453 protein_lists_per_species,
454 plus_minus_analysis_high_copy_base,
455 plus_minus_analysis_high_copy_target,
456 plus_minus_analysis_low_copy,
462 domain_id_to_go_ids_map,
464 all_domains_go_ids_out_dom,
465 passing_domains_go_ids_out_dom,
466 proteins_file_base );
468 catch ( final IOException e ) {
469 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
471 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
472 + html_out_dom + "\"" );
473 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
474 + plain_out_dom + "\"" );
475 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \"" + html_out_dc
477 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based passing GO ids to \""
478 + passing_domains_go_ids_out_dom + "\"" );
479 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based all GO ids to \""
480 + all_domains_go_ids_out_dom + "\"" );
483 private static Phylogeny[] getIntrees( final File[] intree_files,
484 final int number_of_genomes,
485 final String[][] input_file_properties ) {
486 final Phylogeny[] intrees = new Phylogeny[ intree_files.length ];
488 for( final File intree_file : intree_files ) {
489 Phylogeny intree = null;
490 final String error = ForesterUtil.isReadableFile( intree_file );
491 if ( !ForesterUtil.isEmpty( error ) ) {
492 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read input tree file [" + intree_file + "]: "
496 final Phylogeny[] p_array = ParserBasedPhylogenyFactory.getInstance()
497 .create( intree_file, ParserUtils.createParserDependingOnFileType( intree_file, true ) );
498 if ( p_array.length < 1 ) {
499 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
500 + "] does not contain any phylogeny in phyloXML format" );
502 else if ( p_array.length > 1 ) {
503 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
504 + "] contains more than one phylogeny in phyloXML format" );
506 intree = p_array[ 0 ];
508 catch ( final Exception e ) {
509 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read input tree from file [" + intree_file
512 if ( ( intree == null ) || intree.isEmpty() ) {
513 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" );
515 if ( !intree.isRooted() ) {
516 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is not rooted" );
518 if ( intree.getNumberOfExternalNodes() < number_of_genomes ) {
519 ForesterUtil.fatalError( surfacing.PRG_NAME,
520 "number of external nodes [" + intree.getNumberOfExternalNodes()
521 + "] of input tree [" + intree_file
522 + "] is smaller than the number of genomes the be analyzed ["
523 + number_of_genomes + "]" );
525 final StringBuilder parent_names = new StringBuilder();
526 final int nodes_lacking_name = SurfacingUtil.getNumberOfNodesLackingName( intree, parent_names );
527 if ( nodes_lacking_name > 0 ) {
528 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] has "
529 + nodes_lacking_name + " node(s) lacking a name [parent names:" + parent_names + "]" );
531 preparePhylogenyForParsimonyAnalyses( intree, input_file_properties );
532 if ( !intree.isCompletelyBinary() ) {
533 ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "input tree [" + intree_file
534 + "] is not completely binary" );
536 intrees[ i++ ] = intree;
541 private static void log( final String msg, final Writer w ) {
544 w.write( ForesterUtil.LINE_SEPARATOR );
546 catch ( final IOException e ) {
547 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
551 public static void main( final String args[] ) {
552 final long start_time = new Date().getTime();
553 // final StringBuffer log = new StringBuffer();
554 final StringBuilder html_desc = new StringBuilder();
555 ForesterUtil.printProgramInformation( surfacing.PRG_NAME,
556 surfacing.PRG_VERSION,
560 final String nl = ForesterUtil.LINE_SEPARATOR;
561 html_desc.append( "<table>" + nl );
562 html_desc.append( "<tr><td>Produced by:</td><td>" + surfacing.PRG_NAME + "</td></tr>" + nl );
563 html_desc.append( "<tr><td>Version:</td><td>" + surfacing.PRG_VERSION + "</td></tr>" + nl );
564 html_desc.append( "<tr><td>Release Date:</td><td>" + surfacing.PRG_DATE + "</td></tr>" + nl );
565 html_desc.append( "<tr><td>Contact:</td><td>" + surfacing.E_MAIL + "</td></tr>" + nl );
566 html_desc.append( "<tr><td>WWW:</td><td>" + surfacing.WWW + "</td></tr>" + nl );
567 CommandLineArguments cla = null;
569 cla = new CommandLineArguments( args );
571 catch ( final Exception e ) {
572 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
574 if ( cla.isOptionSet( surfacing.HELP_OPTION_1 ) || cla.isOptionSet( surfacing.HELP_OPTION_2 ) ) {
575 surfacing.printHelp();
578 if ( ( args.length < 1 ) ) {
579 surfacing.printHelp();
582 final List<String> allowed_options = new ArrayList<String>();
583 allowed_options.add( surfacing.NOT_IGNORE_DUFS_OPTION );
584 allowed_options.add( surfacing.MAX_E_VALUE_OPTION );
585 allowed_options.add( surfacing.DETAILEDNESS_OPTION );
586 allowed_options.add( surfacing.OUTPUT_FILE_OPTION );
587 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_OPTION );
588 allowed_options.add( surfacing.SPECIES_MATRIX_OPTION );
589 allowed_options.add( surfacing.SCORING_OPTION );
590 allowed_options.add( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
591 allowed_options.add( surfacing.NO_ENGULFING_OVERLAP_OPTION );
592 allowed_options.add( surfacing.DOMAIN_COUNT_SORT_OPTION );
593 allowed_options.add( surfacing.CUTOFF_SCORE_FILE_OPTION );
594 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION );
595 allowed_options.add( surfacing.OUTPUT_DIR_OPTION );
596 allowed_options.add( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION );
597 allowed_options.add( surfacing.PFAM_TO_GO_FILE_USE_OPTION );
598 allowed_options.add( surfacing.GO_OBO_FILE_USE_OPTION );
599 allowed_options.add( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION );
600 allowed_options.add( surfacing.GO_NAMESPACE_LIMIT_OPTION );
601 allowed_options.add( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
602 allowed_options.add( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION );
603 allowed_options.add( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS );
604 allowed_options.add( INPUT_SPECIES_TREE_OPTION );
605 allowed_options.add( FILTER_POSITIVE_OPTION );
606 allowed_options.add( FILTER_NEGATIVE_OPTION );
607 allowed_options.add( INPUT_GENOMES_FILE_OPTION );
608 allowed_options.add( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
609 allowed_options.add( FILTER_NEGATIVE_DOMAINS_OPTION );
610 allowed_options.add( IGNORE_VIRAL_IDS );
611 allowed_options.add( SEQ_EXTRACT_OPTION );
612 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
613 allowed_options.add( SECONDARY_FEATURES_PARSIMONY_MAP_FILE );
614 allowed_options.add( PLUS_MINUS_ANALYSIS_OPTION );
615 allowed_options.add( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS );
616 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS );
617 allowed_options.add( CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY );
618 allowed_options.add( WRITE_TO_NEXUS_OPTION );
619 allowed_options.add( PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION );
620 allowed_options.add( DA_ANALYSIS_OPTION );
621 allowed_options.add( USE_LAST_IN_FITCH_OPTION );
622 boolean ignore_dufs = surfacing.IGNORE_DUFS_DEFAULT;
623 boolean ignore_combination_with_same = surfacing.IGNORE_COMBINATION_WITH_SAME_DEFAULLT;
624 double e_value_max = surfacing.MAX_E_VALUE_DEFAULT;
625 int max_allowed_overlap = surfacing.MAX_ALLOWED_OVERLAP_DEFAULT;
626 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
627 if ( dissallowed_options.length() > 0 ) {
628 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown option(s): " + dissallowed_options );
630 boolean use_last_in_fitch_parsimony = false;
631 if ( cla.isOptionSet( USE_LAST_IN_FITCH_OPTION ) ) {
632 use_last_in_fitch_parsimony = true;
634 boolean write_to_nexus = false;
635 if ( cla.isOptionSet( WRITE_TO_NEXUS_OPTION ) ) {
636 write_to_nexus = true;
638 boolean perform_dc_regain_proteins_stats = false;
639 if ( cla.isOptionSet( PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION ) ) {
640 perform_dc_regain_proteins_stats = true;
642 boolean da_analysis = false;
643 if ( cla.isOptionSet( DA_ANALYSIS_OPTION ) ) {
646 boolean output_binary_domain_combinationsfor_graph_analysis = false;
647 if ( cla.isOptionSet( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS ) ) {
648 output_binary_domain_combinationsfor_graph_analysis = true;
650 if ( cla.isOptionSet( surfacing.MAX_E_VALUE_OPTION ) ) {
652 e_value_max = cla.getOptionValueAsDouble( surfacing.MAX_E_VALUE_OPTION );
654 catch ( final Exception e ) {
655 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for E-value maximum" );
658 if ( cla.isOptionSet( surfacing.MAX_ALLOWED_OVERLAP_OPTION ) ) {
660 max_allowed_overlap = cla.getOptionValueAsInt( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
662 catch ( final Exception e ) {
663 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for maximal allowed domain overlap" );
666 boolean no_engulfing_overlaps = false;
667 if ( cla.isOptionSet( surfacing.NO_ENGULFING_OVERLAP_OPTION ) ) {
668 no_engulfing_overlaps = true;
670 boolean ignore_virus_like_ids = false;
671 if ( cla.isOptionSet( surfacing.IGNORE_VIRAL_IDS ) ) {
672 ignore_virus_like_ids = true;
674 if ( cla.isOptionSet( surfacing.NOT_IGNORE_DUFS_OPTION ) ) {
677 if ( cla.isOptionSet( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION ) ) {
678 ignore_combination_with_same = true;
680 boolean ignore_domains_without_combs_in_all_spec = IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT;
681 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION ) ) {
682 ignore_domains_without_combs_in_all_spec = true;
684 boolean ignore_species_specific_domains = IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT;
685 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION ) ) {
686 ignore_species_specific_domains = true;
688 File output_file = null;
689 if ( cla.isOptionSet( surfacing.OUTPUT_FILE_OPTION ) ) {
690 if ( !cla.isOptionValueSet( surfacing.OUTPUT_FILE_OPTION ) ) {
691 ForesterUtil.fatalError( surfacing.PRG_NAME,
692 "no value for domain combinations similarities output file: -"
693 + surfacing.OUTPUT_FILE_OPTION + "=<file>" );
695 output_file = new File( cla.getOptionValue( surfacing.OUTPUT_FILE_OPTION ) );
696 SurfacingUtil.checkForOutputFileWriteability( output_file );
698 File cutoff_scores_file = null;
699 Map<String, Double> individual_score_cutoffs = null;
700 if ( cla.isOptionSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
701 if ( !cla.isOptionValueSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
702 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for individual domain score cutoffs file: -"
703 + surfacing.CUTOFF_SCORE_FILE_OPTION + "=<file>" );
705 cutoff_scores_file = new File( cla.getOptionValue( surfacing.CUTOFF_SCORE_FILE_OPTION ) );
706 final String error = ForesterUtil.isReadableFile( cutoff_scores_file );
707 if ( !ForesterUtil.isEmpty( error ) ) {
708 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read individual domain score cutoffs file: "
712 final BasicTable<String> scores_table = BasicTableParser.parse( cutoff_scores_file, ' ' );
713 individual_score_cutoffs = scores_table.getColumnsAsMapDouble( 0, 1 );
715 catch ( final IOException e ) {
716 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from individual score cutoffs file: " + e );
719 BinaryDomainCombination.DomainCombinationType dc_type = BinaryDomainCombination.DomainCombinationType.BASIC;
720 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS ) ) {
721 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED;
723 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY ) ) {
724 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT;
727 if ( cla.isOptionSet( surfacing.OUTPUT_DIR_OPTION ) ) {
728 if ( !cla.isOptionValueSet( surfacing.OUTPUT_DIR_OPTION ) ) {
729 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for output directory: -"
730 + surfacing.OUTPUT_DIR_OPTION + "=<dir>" );
732 out_dir = new File( cla.getOptionValue( surfacing.OUTPUT_DIR_OPTION ) );
733 if ( out_dir.exists() && ( out_dir.listFiles().length > 0 ) ) {
734 ForesterUtil.fatalError( surfacing.PRG_NAME, "\"" + out_dir + "\" aready exists and is not empty" );
736 if ( !out_dir.exists() ) {
737 final boolean success = out_dir.mkdir();
738 if ( !success || !out_dir.exists() ) {
739 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to create \"" + out_dir + "\"" );
742 if ( !out_dir.canWrite() ) {
743 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot write to \"" + out_dir + "\"" );
746 File positive_filter_file = null;
747 File negative_filter_file = null;
748 File negative_domains_filter_file = null;
749 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) && cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
750 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use both negative and positive protein filter" );
752 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION )
753 && ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) || cla
754 .isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) ) {
756 .fatalError( surfacing.PRG_NAME,
757 "attempt to use both negative or positive protein filter together wirh a negative domains filter" );
759 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
760 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
761 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative filter: -"
762 + surfacing.FILTER_NEGATIVE_OPTION + "=<file>" );
764 negative_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_OPTION ) );
765 final String msg = ForesterUtil.isReadableFile( negative_filter_file );
766 if ( !ForesterUtil.isEmpty( msg ) ) {
767 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_filter_file + "\": "
771 else if ( cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
772 if ( !cla.isOptionValueSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
773 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for positive filter: -"
774 + surfacing.FILTER_POSITIVE_OPTION + "=<file>" );
776 positive_filter_file = new File( cla.getOptionValue( surfacing.FILTER_POSITIVE_OPTION ) );
777 final String msg = ForesterUtil.isReadableFile( positive_filter_file );
778 if ( !ForesterUtil.isEmpty( msg ) ) {
779 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + positive_filter_file + "\": "
783 else if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
784 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
785 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative domains filter: -"
786 + surfacing.FILTER_NEGATIVE_DOMAINS_OPTION + "=<file>" );
788 negative_domains_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) );
789 final String msg = ForesterUtil.isReadableFile( negative_domains_filter_file );
790 if ( !ForesterUtil.isEmpty( msg ) ) {
791 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_domains_filter_file
795 final List<String> plus_minus_analysis_high_copy_base_species = new ArrayList<String>();
796 final List<String> plus_minus_analysis_high_copy_target_species = new ArrayList<String>();
797 final List<String> plus_minus_analysis_high_low_copy_species = new ArrayList<String>();
798 final List<Object> plus_minus_analysis_numbers = new ArrayList<Object>();
799 processPlusMinusAnalysisOption( cla,
800 plus_minus_analysis_high_copy_base_species,
801 plus_minus_analysis_high_copy_target_species,
802 plus_minus_analysis_high_low_copy_species,
803 plus_minus_analysis_numbers );
804 File input_genomes_file = null;
805 if ( cla.isOptionSet( surfacing.INPUT_GENOMES_FILE_OPTION ) ) {
806 if ( !cla.isOptionValueSet( surfacing.INPUT_GENOMES_FILE_OPTION ) ) {
807 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input genomes file: -"
808 + surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>" );
810 input_genomes_file = new File( cla.getOptionValue( surfacing.INPUT_GENOMES_FILE_OPTION ) );
811 final String msg = ForesterUtil.isReadableFile( input_genomes_file );
812 if ( !ForesterUtil.isEmpty( msg ) ) {
814 .fatalError( surfacing.PRG_NAME, "can not read from \"" + input_genomes_file + "\": " + msg );
818 ForesterUtil.fatalError( surfacing.PRG_NAME, "no input genomes file given: "
819 + surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>" );
821 DomainSimilarity.DomainSimilarityScoring scoring = SCORING_DEFAULT;
822 if ( cla.isOptionSet( surfacing.SCORING_OPTION ) ) {
823 if ( !cla.isOptionValueSet( surfacing.SCORING_OPTION ) ) {
824 ForesterUtil.fatalError( surfacing.PRG_NAME,
825 "no value for scoring method for domain combinations similarity calculation: -"
826 + surfacing.SCORING_OPTION + "=<"
827 + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
828 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|"
829 + surfacing.SCORING_COMBINATION_BASED + ">\"" );
831 final String scoring_str = cla.getOptionValue( surfacing.SCORING_OPTION );
832 if ( scoring_str.equals( surfacing.SCORING_DOMAIN_COUNT_BASED ) ) {
833 scoring = DomainSimilarity.DomainSimilarityScoring.DOMAINS;
835 else if ( scoring_str.equals( surfacing.SCORING_COMBINATION_BASED ) ) {
836 scoring = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
838 else if ( scoring_str.equals( surfacing.SCORING_PROTEIN_COUNT_BASED ) ) {
839 scoring = DomainSimilarity.DomainSimilarityScoring.PROTEINS;
842 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + scoring_str
843 + "\" for scoring method for domain combinations similarity calculation: \"-"
844 + surfacing.SCORING_OPTION + "=<" + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
845 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|" + surfacing.SCORING_COMBINATION_BASED + ">\"" );
848 boolean sort_by_species_count_first = false;
849 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION ) ) {
850 sort_by_species_count_first = true;
852 boolean species_matrix = false;
853 if ( cla.isOptionSet( surfacing.SPECIES_MATRIX_OPTION ) ) {
854 species_matrix = true;
856 boolean output_protein_lists_for_all_domains = false;
857 double output_list_of_all_proteins_per_domain_e_value_max = -1;
858 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS ) ) {
859 output_protein_lists_for_all_domains = true;
860 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION ) ) {
862 output_list_of_all_proteins_per_domain_e_value_max = cla
863 .getOptionValueAsDouble( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
865 catch ( final Exception e ) {
866 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for per domain E-value maximum" );
870 Detailedness detailedness = DETAILEDNESS_DEFAULT;
871 if ( cla.isOptionSet( surfacing.DETAILEDNESS_OPTION ) ) {
872 if ( !cla.isOptionValueSet( surfacing.DETAILEDNESS_OPTION ) ) {
873 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for -" + surfacing.DETAILEDNESS_OPTION + "=<"
874 + surfacing.DETAILEDNESS_BASIC + "|" + surfacing.DETAILEDNESS_LIST_IDS + "|"
875 + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
877 final String detness = cla.getOptionValue( surfacing.DETAILEDNESS_OPTION ).toLowerCase();
878 if ( detness.equals( surfacing.DETAILEDNESS_BASIC ) ) {
879 detailedness = DomainSimilarityCalculator.Detailedness.BASIC;
881 else if ( detness.equals( surfacing.DETAILEDNESS_LIST_IDS ) ) {
882 detailedness = DomainSimilarityCalculator.Detailedness.LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES;
884 else if ( detness.equals( surfacing.DETAILEDNESS_PUNCTILIOUS ) ) {
885 detailedness = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
888 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + detness + "\" for detailedness: \"-"
889 + surfacing.DETAILEDNESS_OPTION + "=<" + surfacing.DETAILEDNESS_BASIC + "|"
890 + surfacing.DETAILEDNESS_LIST_IDS + "|" + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
893 String automated_pairwise_comparison_suffix = null;
894 boolean perform_pwc = false;
895 boolean write_pwc_files = false;
896 if ( cla.isOptionSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
898 if ( !cla.isOptionValueSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
899 write_pwc_files = false;
902 write_pwc_files = true;
903 automated_pairwise_comparison_suffix = "_"
904 + cla.getOptionValue( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
907 String query_domain_ids = null;
908 if ( cla.isOptionSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
909 if ( !cla.isOptionValueSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
911 .fatalError( surfacing.PRG_NAME,
912 "no domain ids given for sequences with given domains to be extracted : -"
913 + surfacing.SEQ_EXTRACT_OPTION
914 + "=<ordered domain sequences, domain ids separated by '~', sequences separated by '#'>" );
916 query_domain_ids = cla.getOptionValue( surfacing.SEQ_EXTRACT_OPTION );
918 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field = DOMAIN_SORT_FILD_DEFAULT;
919 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field_for_automated_pwc = DOMAIN_SORT_FILD_DEFAULT;
920 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
921 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
922 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for domain combinations similarities sorting: -"
923 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
924 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
925 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
926 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
927 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|"
928 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
931 final String sort_str = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ).toLowerCase();
932 if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ALPHA ) ) {
933 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
934 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
936 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MAX ) ) {
937 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX;
938 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
940 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MIN ) ) {
941 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MIN;
942 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
944 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MEAN ) ) {
945 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MEAN;
946 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MEAN;
948 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT ) ) {
949 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SPECIES_COUNT;
950 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
952 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SD ) ) {
953 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SD;
954 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
956 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_DIFF ) ) {
957 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
958 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
960 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF ) ) {
961 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
962 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
964 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF ) ) {
965 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
966 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
969 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort_str
970 + "\" for domain combinations similarities sorting: \"-"
971 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
972 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
973 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
974 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
975 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|" + "|"
976 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
980 PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option = DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT;
981 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
982 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
983 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for print option: -"
984 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
985 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
986 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
988 final String sort = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ).toLowerCase();
989 if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML ) ) {
990 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.HTML;
992 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML ) ) {
993 ForesterUtil.fatalError( surfacing.PRG_NAME, "simple HTML output not implemented yet :(" );
995 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED ) ) {
996 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.SIMPLE_TAB_DELIMITED;
999 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort + "\" for print option: -"
1000 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
1001 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
1002 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
1005 GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order = DOMAINS_SORT_ORDER_DEFAULT;
1006 if ( cla.isOptionSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
1007 if ( !cla.isOptionValueSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
1008 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for sorting of domain counts: -"
1009 + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<" + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|"
1010 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1011 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1012 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1014 final String sort = cla.getOptionValue( surfacing.DOMAIN_COUNT_SORT_OPTION ).toLowerCase();
1015 if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_ALPHA ) ) {
1016 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
1018 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT ) ) {
1019 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_COUNT;
1021 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT ) ) {
1022 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_PROTEINS_COUNT;
1024 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT ) ) {
1025 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.COMBINATIONS_COUNT;
1028 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort
1029 + "\" for sorting of domain counts: \"-" + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<"
1030 + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|" + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1031 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1032 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1035 final String[][] input_file_properties = processInputGenomesFile( input_genomes_file );
1036 final int number_of_genomes = input_file_properties.length;
1037 if ( number_of_genomes < 2 ) {
1038 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot analyze less than two files" );
1040 if ( ( number_of_genomes < 3 ) && perform_pwc ) {
1041 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use : -"
1042 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1043 + "=<suffix> to turn on pairwise analyses with less than three input files" );
1045 checkWriteabilityForPairwiseComparisons( domain_similarity_print_option,
1046 input_file_properties,
1047 automated_pairwise_comparison_suffix,
1049 for( int i = 0; i < number_of_genomes; i++ ) {
1050 File dcc_outfile = new File( input_file_properties[ i ][ 1 ]
1051 + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
1052 if ( out_dir != null ) {
1053 dcc_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + dcc_outfile );
1055 SurfacingUtil.checkForOutputFileWriteability( dcc_outfile );
1057 File pfam_to_go_file = null;
1058 Map<String, List<GoId>> domain_id_to_go_ids_map = null;
1059 int domain_id_to_go_ids_count = 0;
1060 if ( cla.isOptionSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1061 if ( !cla.isOptionValueSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1062 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for Pfam to GO mapping file: -"
1063 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>" );
1065 pfam_to_go_file = new File( cla.getOptionValue( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) );
1066 final String error = ForesterUtil.isReadableFile( pfam_to_go_file );
1067 if ( !ForesterUtil.isEmpty( error ) ) {
1068 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read Pfam to GO mapping file: " + error );
1071 final PfamToGoParser parser = new PfamToGoParser( pfam_to_go_file );
1072 final List<PfamToGoMapping> pfam_to_go_mappings = parser.parse();
1073 domain_id_to_go_ids_map = SurfacingUtil.createDomainIdToGoIdMap( pfam_to_go_mappings );
1074 if ( parser.getMappingCount() < domain_id_to_go_ids_map.size() ) {
1075 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME,
1076 "parser.getMappingCount() < domain_id_to_go_ids_map.size()" );
1078 domain_id_to_go_ids_count = parser.getMappingCount();
1080 catch ( final IOException e ) {
1081 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from Pfam to GO mapping file: " + e );
1084 File go_obo_file = null;
1085 List<GoTerm> go_terms = null;
1086 if ( cla.isOptionSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1087 if ( !cla.isOptionValueSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1088 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO OBO file: -"
1089 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>" );
1091 if ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) {
1092 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO OBO file (-"
1093 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>) without Pfam to GO mapping file ("
1094 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1096 go_obo_file = new File( cla.getOptionValue( surfacing.GO_OBO_FILE_USE_OPTION ) );
1097 final String error = ForesterUtil.isReadableFile( go_obo_file );
1098 if ( !ForesterUtil.isEmpty( error ) ) {
1099 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read GO OBO file: " + error );
1102 final OBOparser parser = new OBOparser( go_obo_file, OBOparser.ReturnType.BASIC_GO_TERM );
1103 go_terms = parser.parse();
1104 if ( parser.getGoTermCount() != go_terms.size() ) {
1106 .unexpectedFatalError( surfacing.PRG_NAME, "parser.getGoTermCount() != go_terms.size()" );
1109 catch ( final IOException e ) {
1110 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from GO OBO file: " + e );
1113 Map<GoId, GoTerm> go_id_to_term_map = null;
1114 if ( ( ( domain_id_to_go_ids_map != null ) && ( domain_id_to_go_ids_map.size() > 0 ) )
1115 && ( ( go_terms != null ) && ( go_terms.size() > 0 ) ) ) {
1116 go_id_to_term_map = GoUtils.createGoIdToGoTermMap( go_terms );
1118 GoNameSpace go_namespace_limit = null;
1119 if ( cla.isOptionSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1120 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1121 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO namespace limit (-"
1122 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<namespace>) without Pfam to GO mapping file ("
1123 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>) and GO OBO file (-"
1124 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1126 if ( !cla.isOptionValueSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1127 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO namespace limit: \"-"
1128 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1129 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1130 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1131 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1133 final String go_namespace_limit_str = cla.getOptionValue( surfacing.GO_NAMESPACE_LIMIT_OPTION )
1135 if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION ) ) {
1136 go_namespace_limit = GoNameSpace.createMolecularFunction();
1138 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS ) ) {
1139 go_namespace_limit = GoNameSpace.createBiologicalProcess();
1141 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT ) ) {
1142 go_namespace_limit = GoNameSpace.createCellularComponent();
1145 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + go_namespace_limit_str
1146 + "\" for GO namespace limit: \"-" + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1147 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1148 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1149 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1152 if ( ( domain_similarity_sort_field == DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE )
1153 && ( number_of_genomes > 2 ) ) {
1154 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
1156 File[] intree_files = null;
1157 Phylogeny[] intrees = null;
1158 if ( cla.isOptionSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1159 if ( number_of_genomes < 3 ) {
1160 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer gains and losses on input species trees (-"
1161 + surfacing.INPUT_SPECIES_TREE_OPTION + " without pairwise analyses ("
1162 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1163 + "=<suffix for pairwise comparison output files>)" );
1165 if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1166 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input tree: -"
1167 + surfacing.INPUT_SPECIES_TREE_OPTION + "=<tree file in phyloXML format>" );
1169 final String intrees_str = cla.getOptionValue( surfacing.INPUT_SPECIES_TREE_OPTION );
1170 if ( intrees_str.indexOf( "#" ) > 0 ) {
1171 final String[] intrees_strs = intrees_str.split( "#" );
1172 intree_files = new File[ intrees_strs.length ];
1174 for( final String s : intrees_strs ) {
1175 intree_files[ i++ ] = new File( s.trim() );
1179 intree_files = new File[ 1 ];
1180 intree_files[ 0 ] = new File( intrees_str );
1182 intrees = getIntrees( intree_files, number_of_genomes, input_file_properties );
1184 long random_number_seed_for_fitch_parsimony = 0l;
1185 boolean radomize_fitch_parsimony = false;
1186 if ( cla.isOptionSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1187 if ( !cla.isOptionValueSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1188 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for random number seed: -"
1189 + surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION + "=<seed>" );
1192 random_number_seed_for_fitch_parsimony = cla
1193 .getOptionValueAsLong( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
1195 catch ( final IOException e ) {
1196 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1198 radomize_fitch_parsimony = true;
1200 SortedSet<String> filter = null;
1201 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1202 || ( negative_domains_filter_file != null ) ) {
1203 filter = new TreeSet<String>();
1204 if ( positive_filter_file != null ) {
1205 processFilter( positive_filter_file, filter );
1207 else if ( negative_filter_file != null ) {
1208 processFilter( negative_filter_file, filter );
1210 else if ( negative_domains_filter_file != null ) {
1211 processFilter( negative_domains_filter_file, filter );
1214 Map<String, Set<String>>[] domain_id_to_secondary_features_maps = null;
1215 File[] secondary_features_map_files = null;
1216 final File domain_lengths_analysis_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1217 + DOMAIN_LENGTHS_ANALYSIS_SUFFIX );
1218 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
1219 SurfacingUtil.checkForOutputFileWriteability( domain_lengths_analysis_outfile );
1221 if ( cla.isOptionSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1222 if ( !cla.isOptionValueSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1223 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for secondary features map file: -"
1224 + surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE + "=<file>" );
1226 final String[] secondary_features_map_files_strs = cla
1227 .getOptionValue( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ).split( "#" );
1228 secondary_features_map_files = new File[ secondary_features_map_files_strs.length ];
1229 domain_id_to_secondary_features_maps = new Map[ secondary_features_map_files_strs.length ];
1231 for( final String secondary_features_map_files_str : secondary_features_map_files_strs ) {
1232 secondary_features_map_files[ i ] = new File( secondary_features_map_files_str );
1233 final String error = ForesterUtil.isReadableFile( secondary_features_map_files[ i ] );
1234 if ( !ForesterUtil.isEmpty( error ) ) {
1235 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read secondary features map file: " + error );
1238 domain_id_to_secondary_features_maps[ i ] = SurfacingUtil
1239 .createDomainIdToSecondaryFeaturesMap( secondary_features_map_files[ i ] );
1241 catch ( final IOException e ) {
1242 ForesterUtil.fatalError( surfacing.PRG_NAME,
1243 "cannot read secondary features map file: " + e.getMessage() );
1245 catch ( final Exception e ) {
1246 ForesterUtil.fatalError( surfacing.PRG_NAME, "problem with contents of features map file ["
1247 + secondary_features_map_files[ i ] + "]: " + e.getMessage() );
1252 if ( out_dir == null ) {
1253 ForesterUtil.fatalError( surfacing.PRG_NAME, "no output directory indicated (-"
1254 + surfacing.OUTPUT_DIR_OPTION + "=<dir>)" );
1256 if ( output_file == null ) {
1257 ForesterUtil.fatalError( surfacing.PRG_NAME, "no name for (main) output file indicated (-"
1258 + surfacing.OUTPUT_FILE_OPTION + "=<file>)" );
1260 if ( ( domain_id_to_go_ids_map == null ) || domain_id_to_go_ids_map.isEmpty() ) {
1261 ForesterUtil.fatalError( surfacing.PRG_NAME,
1262 "no (acceptable) Pfam to GO id mapping file provided ('pfam2go file') (-"
1263 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1265 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1266 ForesterUtil.fatalError( surfacing.PRG_NAME,
1267 "no (acceptable) go id to term mapping file provided ('GO OBO file') (-"
1268 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1270 System.out.println( "Output directory : " + out_dir );
1271 System.out.println( "Input genomes from : " + input_genomes_file );
1272 html_desc.append( "<tr><td>Input genomes from:</td><td>" + input_genomes_file + "</td></tr>" + nl );
1273 if ( positive_filter_file != null ) {
1274 final int filter_size = filter.size();
1275 System.out.println( "Positive protein filter : " + positive_filter_file + " [" + filter_size
1277 html_desc.append( "<tr><td>Positive protein filter:</td><td>" + positive_filter_file + " [" + filter_size
1278 + " domain ids]</td></tr>" + nl );
1280 if ( negative_filter_file != null ) {
1281 final int filter_size = filter.size();
1282 System.out.println( "Negative protein filter : " + negative_filter_file + " [" + filter_size
1284 html_desc.append( "<tr><td>Negative protein filter:</td><td>" + negative_filter_file + " [" + filter_size
1285 + " domain ids]</td></tr>" + nl );
1287 if ( negative_domains_filter_file != null ) {
1288 final int filter_size = filter.size();
1289 System.out.println( "Negative domain filter : " + negative_domains_filter_file + " [" + filter_size
1291 html_desc.append( "<tr><td>Negative domain filter:</td><td>" + negative_domains_filter_file + " ["
1292 + filter_size + " domain ids]</td></tr>" + nl );
1294 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
1296 for( final String s : plus_minus_analysis_high_copy_base_species ) {
1297 plus0 += "+" + s + " ";
1300 for( final String s : plus_minus_analysis_high_copy_target_species ) {
1301 plus1 += "*" + s + " ";
1304 for( final String s : plus_minus_analysis_high_low_copy_species ) {
1305 minus += "-" + s + " ";
1307 System.out.println( "Plus-minus analysis : " + plus1 + "&& " + plus0 + "&& " + minus );
1308 html_desc.append( "<tr><td>Plus-minus analysis:</td><td>" + plus1 + "&& " + plus0 + "&& " + minus
1309 + "</td></tr>" + nl );
1311 if ( cutoff_scores_file != null ) {
1312 System.out.println( "Cutoff scores file : " + cutoff_scores_file );
1313 html_desc.append( "<tr><td>Cutoff scores file:</td><td>" + cutoff_scores_file + "</td></tr>" + nl );
1315 if ( e_value_max >= 0.0 ) {
1316 System.out.println( "E-value maximum (inclusive) : " + e_value_max );
1317 html_desc.append( "<tr><td>E-value maximum (inclusive):</td><td>" + e_value_max + "</td></tr>" + nl );
1319 if ( output_protein_lists_for_all_domains ) {
1320 System.out.println( "Domain E-value max : " + output_list_of_all_proteins_per_domain_e_value_max );
1321 html_desc.append( "<tr><td>Protein lists: E-value maximum per domain (inclusive):</td><td>"
1322 + output_list_of_all_proteins_per_domain_e_value_max + "</td></tr>" + nl );
1324 System.out.println( "Ignore DUFs : " + ignore_dufs );
1325 if ( ignore_virus_like_ids ) {
1326 System.out.println( "Ignore virus like ids : " + ignore_virus_like_ids );
1327 html_desc.append( "<tr><td>Ignore virus, phage, transposition related ids:</td><td>"
1328 + ignore_virus_like_ids + "</td></tr>" + nl );
1330 html_desc.append( "<tr><td>Ignore DUFs:</td><td>" + ignore_dufs + "</td></tr>" + nl );
1331 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1332 System.out.println( "Max allowed domain overlap : " + max_allowed_overlap );
1333 html_desc.append( "<tr><td>Max allowed domain overlap:</td><td>" + max_allowed_overlap + "</td></tr>" + nl );
1335 if ( no_engulfing_overlaps ) {
1336 System.out.println( "Ignore engulfed domains : " + no_engulfing_overlaps );
1337 html_desc.append( "<tr><td>Ignore (lower confidence) engulfed domains:</td><td>" + no_engulfing_overlaps
1338 + "</td></tr>" + nl );
1340 System.out.println( "Ignore singlet domains : " + ignore_domains_without_combs_in_all_spec );
1342 .append( "<tr><td>Ignore singlet domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1343 + ignore_domains_without_combs_in_all_spec + "</td></tr>" + nl );
1344 System.out.println( "Ignore species specific doms: " + ignore_species_specific_domains );
1346 .append( "<tr><td>Ignore species specific domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1347 + ignore_species_specific_domains + "</td></tr>" + nl );
1348 System.out.println( "Ignore combination with self: " + ignore_combination_with_same );
1349 html_desc.append( "<tr><td>Ignore combination with self for domain combination similarity analyses:</td><td>"
1350 + ignore_combination_with_same + "</td></tr>" + nl );
1351 System.out.println( "Consider directedness : "
1352 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) );
1353 html_desc.append( "<tr><td>Consider directedness of binary domain combinations:</td><td>"
1354 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) + "</td></tr>" + nl );
1355 if ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) {
1356 System.out.println( "Consider adjacency : "
1357 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) );
1358 html_desc.append( "<tr><td>Consider djacency of binary domain combinations:</td><td>"
1359 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) + "</td></tr>"
1362 System.out.println( "Use last in Fitch parimony : " + use_last_in_fitch_parsimony );
1363 html_desc.append( "<tr><td>Use last in Fitch parimon:</td><td>" + use_last_in_fitch_parsimony + "</td></tr>"
1365 System.out.println( "Write to Nexus files : " + write_to_nexus );
1366 html_desc.append( "<tr><td>Write to Nexus files:</td><td>" + write_to_nexus + "</td></tr>" + nl );
1367 System.out.println( "DC regain prot stats : " + perform_dc_regain_proteins_stats );
1368 html_desc.append( "<tr><td>DC regain prot stats:</td><td>" + perform_dc_regain_proteins_stats + "</td></tr>"
1370 System.out.println( "DA analysis : " + da_analysis );
1371 html_desc.append( "<tr><td>DA analysis :</td><td>" + da_analysis + "</td></tr>" + nl );
1372 System.out.print( "Domain counts sort order : " );
1373 html_desc.append( "<tr><td>Domain counts sort order:</td><td>" );
1374 switch ( dc_sort_order ) {
1375 case ALPHABETICAL_KEY_ID:
1376 System.out.println( "alphabetical" );
1377 html_desc.append( "alphabetical" + "</td></tr>" + nl );
1379 case KEY_DOMAIN_COUNT:
1380 System.out.println( "domain count" );
1381 html_desc.append( "domain count" + "</td></tr>" + nl );
1383 case KEY_DOMAIN_PROTEINS_COUNT:
1384 System.out.println( "domain proteins count" );
1385 html_desc.append( "domain proteins count" + "</td></tr>" + nl );
1387 case COMBINATIONS_COUNT:
1388 System.out.println( "domain combinations count" );
1389 html_desc.append( "domain combinations count" + "</td></tr>" + nl );
1392 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for dc sort order" );
1394 if ( domain_id_to_go_ids_map != null ) {
1395 System.out.println( "Pfam to GO mappings from : " + pfam_to_go_file + " [" + domain_id_to_go_ids_count
1397 html_desc.append( "<tr><td>Pfam to GO mappings from:</td><td>" + pfam_to_go_file + " ["
1398 + domain_id_to_go_ids_count + " mappings]" + "</td></tr>" + nl );
1400 if ( go_terms != null ) {
1401 System.out.println( "GO terms from : " + go_obo_file + " [" + go_terms.size() + " terms]" );
1402 html_desc.append( "<tr><td>GO terms from:</td><td>" + go_obo_file + " [" + go_terms.size() + " terms]"
1403 + "</td></tr>" + nl );
1405 if ( go_namespace_limit != null ) {
1406 System.out.println( "Limit GO terms to : " + go_namespace_limit.toString() );
1407 html_desc.append( "<tr><td>Limit GO terms to</td><td>" + go_namespace_limit + "</td></tr>" + nl );
1409 if ( perform_pwc ) {
1410 System.out.println( "Suffix for PWC files : " + automated_pairwise_comparison_suffix );
1411 html_desc.append( "<tr><td>Suffix for PWC files</td><td>" + automated_pairwise_comparison_suffix
1412 + "</td></tr>" + nl );
1414 if ( out_dir != null ) {
1415 System.out.println( "Output directory : " + out_dir );
1417 if ( query_domain_ids != null ) {
1418 System.out.println( "Query domains (ordered) : " + query_domain_ids );
1419 html_desc.append( "<tr><td></td><td>" + query_domain_ids + "</td></tr>" + nl );
1421 System.out.println( "Write similarities to : " + output_file );
1422 System.out.print( " Scoring method : " );
1423 html_desc.append( "<tr><td>Scoring method:</td><td>" );
1424 switch ( scoring ) {
1426 System.out.println( "domain combinations based" );
1427 html_desc.append( "domain combinations based" + "</td></tr>" + nl );
1430 System.out.println( "domain counts based" );
1431 html_desc.append( "domain counts based" + "</td></tr>" + nl );
1434 System.out.println( "domain proteins counts based" );
1435 html_desc.append( "domain proteins counts based" + "</td></tr>" + nl );
1438 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
1440 System.out.print( " Sort by : " );
1441 html_desc.append( "<tr><td>Sort by:</td><td>" );
1442 switch ( domain_similarity_sort_field ) {
1444 System.out.print( "score minimum" );
1445 html_desc.append( "score minimum" );
1448 System.out.print( "score maximum" );
1449 html_desc.append( "score maximum" );
1452 System.out.print( "score mean" );
1453 html_desc.append( "score mean" );
1456 System.out.print( "score standard deviation" );
1457 html_desc.append( "score standard deviation" );
1460 System.out.print( "species number" );
1461 html_desc.append( "species number" );
1464 System.out.print( "alphabetical domain identifier" );
1465 html_desc.append( "alphabetical domain identifier" );
1467 case MAX_DIFFERENCE:
1468 System.out.print( "(maximal) difference" );
1469 html_desc.append( "(maximal) difference" );
1471 case ABS_MAX_COUNTS_DIFFERENCE:
1472 System.out.print( "absolute (maximal) counts difference" );
1473 html_desc.append( "absolute (maximal) counts difference" );
1475 case MAX_COUNTS_DIFFERENCE:
1476 System.out.print( "(maximal) counts difference" );
1477 html_desc.append( "(maximal) counts difference" );
1480 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1482 if ( sort_by_species_count_first ) {
1483 System.out.println( " (sort by species count first)" );
1484 html_desc.append( " (sort by species count first)" );
1487 System.out.println();
1489 html_desc.append( "</td></tr>" + nl );
1490 System.out.print( " Detailedness : " );
1491 switch ( detailedness ) {
1493 System.out.println( "basic" );
1495 case LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES:
1496 System.out.println( "list combining domains for each species" );
1499 System.out.println( "punctilious" );
1502 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for detailedness" );
1504 System.out.print( " Print option : " );
1505 switch ( domain_similarity_print_option ) {
1507 System.out.println( "HTML" );
1509 case SIMPLE_TAB_DELIMITED:
1510 System.out.println( "simple tab delimited" );
1513 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for print option" );
1515 System.out.print( " Species matrix : " + species_matrix );
1516 System.out.println();
1517 final File dc_data_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + DATA_FILE_SUFFIX );
1518 System.out.println( "Domain comb data output : " + dc_data_file );
1519 html_desc.append( "<tr><td>Domain combination data output:</td><td> " + dc_data_file + " </td></tr>" );
1520 System.out.println();
1521 if ( perform_pwc ) {
1522 System.out.println( "Pairwise comparisons: " );
1523 html_desc.append( "<tr><td>Pairwise comparisons:</td><td></td></tr>" );
1524 System.out.print( " Sort by : " );
1525 html_desc.append( "<tr><td>Sort by:</td><td>" );
1526 switch ( domain_similarity_sort_field_for_automated_pwc ) {
1528 System.out.print( "score mean" );
1529 html_desc.append( "score mean" );
1532 System.out.print( "alphabetical domain identifier" );
1533 html_desc.append( "alphabetical domain identifier" );
1535 case MAX_DIFFERENCE:
1536 System.out.print( "difference" );
1537 html_desc.append( "difference" );
1539 case ABS_MAX_COUNTS_DIFFERENCE:
1540 System.out.print( "absolute counts difference" );
1541 html_desc.append( "absolute counts difference" );
1543 case MAX_COUNTS_DIFFERENCE:
1544 System.out.print( "counts difference" );
1545 html_desc.append( "counts difference" );
1549 .unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1551 System.out.println();
1552 html_desc.append( "</td></tr>" + nl );
1553 if ( ( intrees != null ) && ( intrees.length > 0 ) ) {
1554 for( final File intree_file : intree_files ) {
1555 html_desc.append( "<tr><td>Intree for gain/loss parsimony analysis:</td><td>" + intree_file
1556 + "</td></tr>" + nl );
1557 System.out.println( " Intree for gain/loss pars.: " + intree_file );
1560 if ( radomize_fitch_parsimony ) {
1561 html_desc.append( "<tr><td> Random number seed for Fitch parsimony analysis:</td><td>"
1562 + random_number_seed_for_fitch_parsimony + "</td></tr>" + nl );
1563 System.out.println( " Random number seed : " + random_number_seed_for_fitch_parsimony );
1565 if ( ( domain_id_to_secondary_features_maps != null ) && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
1566 for( int i = 0; i < secondary_features_map_files.length; i++ ) {
1567 html_desc.append( "<tr><td>Secondary features map file:</td><td>"
1568 + secondary_features_map_files[ i ] + "</td></tr>" + nl );
1569 System.out.println( "Secondary features map file : " + secondary_features_map_files[ i ]
1570 + " [mappings for " + domain_id_to_secondary_features_maps[ i ].size() + " domain ids]" );
1572 System.out.println();
1573 System.out.println( "Domain ids to secondary features map:" );
1574 for( final String domain_id : domain_id_to_secondary_features_maps[ i ].keySet() ) {
1575 System.out.print( domain_id );
1576 System.out.print( " => " );
1577 for( final String sec : domain_id_to_secondary_features_maps[ i ].get( domain_id ) ) {
1578 System.out.print( sec );
1579 System.out.print( " " );
1581 System.out.println();
1586 } // if ( perform_pwc ) {
1587 System.out.println();
1588 html_desc.append( "<tr><td>Command line:</td><td>\n" + cla.getCommandLineArgsAsString() + "\n</td></tr>" + nl );
1589 System.out.println( "Command line : " + cla.getCommandLineArgsAsString() );
1590 BufferedWriter[] query_domains_writer_ary = null;
1591 List<String>[] query_domain_ids_array = null;
1592 if ( query_domain_ids != null ) {
1593 final String[] query_domain_ids_str_array = query_domain_ids.split( "#" );
1594 query_domain_ids_array = new ArrayList[ query_domain_ids_str_array.length ];
1595 query_domains_writer_ary = new BufferedWriter[ query_domain_ids_str_array.length ];
1596 for( int i = 0; i < query_domain_ids_str_array.length; i++ ) {
1597 String query_domain_ids_str = query_domain_ids_str_array[ i ];
1598 final String[] query_domain_ids_str_ary = query_domain_ids_str.split( "~" );
1599 final List<String> query = new ArrayList<String>();
1600 for( final String element : query_domain_ids_str_ary ) {
1601 query.add( element );
1603 query_domain_ids_array[ i ] = query;
1604 query_domain_ids_str = query_domain_ids_str.replace( '~', '_' );
1605 String protein_names_writer_str = query_domain_ids_str + surfacing.SEQ_EXTRACT_SUFFIX;
1606 if ( out_dir != null ) {
1607 protein_names_writer_str = out_dir + ForesterUtil.FILE_SEPARATOR + protein_names_writer_str;
1610 query_domains_writer_ary[ i ] = new BufferedWriter( new FileWriter( protein_names_writer_str ) );
1612 catch ( final IOException e ) {
1613 ForesterUtil.fatalError( surfacing.PRG_NAME, "Could not open [" + protein_names_writer_str + "]: "
1614 + e.getLocalizedMessage() );
1618 SortedMap<Species, List<Protein>> protein_lists_per_species = null; //This will only be created if neede.
1619 boolean need_protein_lists_per_species = false;
1620 if ( ( plus_minus_analysis_high_copy_base_species.size() > 0 ) || output_protein_lists_for_all_domains ) {
1621 need_protein_lists_per_species = true;
1623 if ( need_protein_lists_per_species ) {
1624 protein_lists_per_species = new TreeMap<Species, List<Protein>>();
1626 List<GenomeWideCombinableDomains> gwcd_list = new ArrayList<GenomeWideCombinableDomains>( number_of_genomes );
1627 final SortedSet<String> all_domains_encountered = new TreeSet<String>();
1628 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered = new TreeSet<BinaryDomainCombination>();
1629 List<BinaryDomainCombination> all_bin_domain_combinations_gained_fitch = null;
1630 List<BinaryDomainCombination> all_bin_domain_combinations_lost_fitch = null;
1631 if ( ( intrees != null ) && ( intrees.length == 1 ) ) {
1632 all_bin_domain_combinations_gained_fitch = new ArrayList<BinaryDomainCombination>();
1633 all_bin_domain_combinations_lost_fitch = new ArrayList<BinaryDomainCombination>();
1635 DomainLengthsTable domain_lengths_table = new DomainLengthsTable();
1636 final File per_genome_domain_promiscuity_statistics_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR
1637 + output_file + D_PROMISCUITY_FILE_SUFFIX );
1638 BufferedWriter per_genome_domain_promiscuity_statistics_writer = null;
1640 per_genome_domain_promiscuity_statistics_writer = new BufferedWriter( new FileWriter( per_genome_domain_promiscuity_statistics_file ) );
1641 per_genome_domain_promiscuity_statistics_writer.write( "Species:\t" );
1642 per_genome_domain_promiscuity_statistics_writer.write( "Mean:\t" );
1643 per_genome_domain_promiscuity_statistics_writer.write( "SD:\t" );
1644 per_genome_domain_promiscuity_statistics_writer.write( "Median:\t" );
1645 per_genome_domain_promiscuity_statistics_writer.write( "Min:\t" );
1646 per_genome_domain_promiscuity_statistics_writer.write( "Max:\t" );
1647 per_genome_domain_promiscuity_statistics_writer.write( "N:\t" );
1648 per_genome_domain_promiscuity_statistics_writer.write( "Max Promiscuous Domains:"
1649 + ForesterUtil.LINE_SEPARATOR );
1651 catch ( final IOException e2 ) {
1652 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1654 final File log_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + LOG_FILE_SUFFIX );
1655 BufferedWriter log_writer = null;
1657 log_writer = new BufferedWriter( new FileWriter( log_file ) );
1659 catch ( final IOException e2 ) {
1660 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1662 BufferedWriter dc_data_writer = null;
1664 dc_data_writer = new BufferedWriter( new FileWriter( dc_data_file ) );
1665 dc_data_writer.write( DATA_FILE_DESC );
1666 dc_data_writer.write( ForesterUtil.LINE_SEPARATOR );
1668 catch ( final IOException e2 ) {
1669 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1671 final DescriptiveStatistics protein_coverage_stats = new BasicDescriptiveStatistics();
1672 final DescriptiveStatistics all_genomes_domains_per_potein_stats = new BasicDescriptiveStatistics();
1673 final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo = new TreeMap<Integer, Integer>();
1674 final SortedSet<String> domains_which_are_always_single = new TreeSet<String>();
1675 final SortedSet<String> domains_which_are_sometimes_single_sometimes_not = new TreeSet<String>();
1676 final SortedSet<String> domains_which_never_single = new TreeSet<String>();
1677 BufferedWriter domains_per_potein_stats_writer = null;
1679 domains_per_potein_stats_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
1680 + output_file + "_domains_per_potein_stats.txt" ) );
1681 domains_per_potein_stats_writer.write( "Genome" );
1682 domains_per_potein_stats_writer.write( "\t" );
1683 domains_per_potein_stats_writer.write( "Mean" );
1684 domains_per_potein_stats_writer.write( "\t" );
1685 domains_per_potein_stats_writer.write( "SD" );
1686 domains_per_potein_stats_writer.write( "\t" );
1687 domains_per_potein_stats_writer.write( "Median" );
1688 domains_per_potein_stats_writer.write( "\t" );
1689 domains_per_potein_stats_writer.write( "N" );
1690 domains_per_potein_stats_writer.write( "\t" );
1691 domains_per_potein_stats_writer.write( "Min" );
1692 domains_per_potein_stats_writer.write( "\t" );
1693 domains_per_potein_stats_writer.write( "Max" );
1694 domains_per_potein_stats_writer.write( "\n" );
1696 catch ( final IOException e3 ) {
1697 e3.printStackTrace();
1699 Map<String, DescriptiveStatistics> protein_length_stats_by_dc = null;
1700 Map<String, DescriptiveStatistics> domain_number_stats_by_dc = null;
1701 final Map<String, DescriptiveStatistics> domain_length_stats_by_domain = new HashMap<String, DescriptiveStatistics>();
1702 if ( perform_dc_regain_proteins_stats ) {
1703 protein_length_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1704 domain_number_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1707 final SortedMap<String, Set<String>> distinct_domain_architecutures_per_genome = new TreeMap<String, Set<String>>();
1708 final SortedMap<String, Integer> distinct_domain_architecuture_counts = new TreeMap<String, Integer>();
1709 for( int i = 0; i < number_of_genomes; ++i ) {
1710 System.out.println();
1711 System.out.println( ( i + 1 ) + "/" + number_of_genomes );
1712 log( ( i + 1 ) + "/" + number_of_genomes, log_writer );
1713 System.out.println( "Processing : " + input_file_properties[ i ][ 1 ]
1714 + " [" + input_file_properties[ i ][ 0 ] + "]" );
1715 log( "Genome : " + input_file_properties[ i ][ 1 ] + " ["
1716 + input_file_properties[ i ][ 0 ] + "]", log_writer );
1717 HmmscanPerDomainTableParser parser = null;
1718 INDIVIDUAL_SCORE_CUTOFF ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF.NONE;
1719 if ( individual_score_cutoffs != null ) {
1720 ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF_DEFAULT;
1722 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1723 || ( negative_domains_filter_file != null ) ) {
1724 HmmscanPerDomainTableParser.FilterType filter_type = HmmscanPerDomainTableParser.FilterType.NONE;
1725 if ( positive_filter_file != null ) {
1726 filter_type = HmmscanPerDomainTableParser.FilterType.POSITIVE_PROTEIN;
1728 else if ( negative_filter_file != null ) {
1729 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_PROTEIN;
1731 else if ( negative_domains_filter_file != null ) {
1732 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_DOMAIN;
1734 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1735 input_file_properties[ i ][ 1 ],
1742 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1743 input_file_properties[ i ][ 1 ],
1747 if ( e_value_max >= 0.0 ) {
1748 parser.setEValueMaximum( e_value_max );
1750 parser.setIgnoreDufs( ignore_dufs );
1751 parser.setIgnoreVirusLikeIds( ignore_virus_like_ids );
1752 parser.setIgnoreEngulfedDomains( no_engulfing_overlaps );
1753 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1754 parser.setMaxAllowedOverlap( max_allowed_overlap );
1756 parser.setReturnType( HmmscanPerDomainTableParser.ReturnType.UNORDERED_PROTEIN_DOMAIN_COLLECTION_PER_PROTEIN );
1757 if ( individual_score_cutoffs != null ) {
1758 parser.setIndividualScoreCutoffs( individual_score_cutoffs );
1760 List<Protein> protein_list = null;
1762 protein_list = parser.parse();
1764 catch ( final IOException e ) {
1765 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1767 catch ( final Exception e ) {
1768 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, e.getMessage(), e );
1771 System.out.println( "Domains ignored due to negative domain filter: " );
1772 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToNegativeDomainFilterCountsMap() );
1773 System.out.println( "Domains ignored due to virus like id: " );
1774 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToVirusLikeIdCountsMap() );
1776 final double coverage = ( double ) protein_list.size() / parser.getProteinsEncountered();
1777 protein_coverage_stats.addValue( coverage );
1778 int distinct_das = -1;
1779 if ( da_analysis ) {
1780 final String genome = input_file_properties[ i ][ 0 ];
1781 distinct_das = SurfacingUtil.storeDomainArchitectures( genome,
1782 distinct_domain_architecutures_per_genome,
1784 distinct_domain_architecuture_counts );
1786 System.out.println( "Number of proteins encountered : " + parser.getProteinsEncountered() );
1787 log( "Number of proteins encountered : " + parser.getProteinsEncountered(), log_writer );
1788 System.out.println( "Number of proteins stored : " + protein_list.size() );
1789 log( "Number of proteins stored : " + protein_list.size(), log_writer );
1790 System.out.println( "Coverage : "
1791 + ForesterUtil.roundToInt( 100.0 * coverage ) + "%" );
1792 log( "Coverage : " + ForesterUtil.roundToInt( 100.0 * coverage )
1793 + "%", log_writer );
1794 System.out.println( "Domains encountered : " + parser.getDomainsEncountered() );
1795 log( "Domains encountered : " + parser.getDomainsEncountered(), log_writer );
1796 System.out.println( "Domains stored : " + parser.getDomainsStored() );
1797 log( "Domains stored : " + parser.getDomainsStored(), log_writer );
1798 System.out.println( "Distinct domains stored : "
1799 + parser.getDomainsStoredSet().size() );
1800 log( "Distinct domains stored : " + parser.getDomainsStoredSet().size(), log_writer );
1801 System.out.println( "Domains ignored due to individual score cutoffs: "
1802 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() );
1803 log( "Domains ignored due to individual score cutoffs: "
1804 + parser.getDomainsIgnoredDueToIndividualScoreCutoff(),
1806 System.out.println( "Domains ignored due to E-value : "
1807 + parser.getDomainsIgnoredDueToEval() );
1808 log( "Domains ignored due to E-value : " + parser.getDomainsIgnoredDueToEval(), log_writer );
1809 System.out.println( "Domains ignored due to DUF designation : "
1810 + parser.getDomainsIgnoredDueToDuf() );
1811 log( "Domains ignored due to DUF designation : " + parser.getDomainsIgnoredDueToDuf(), log_writer );
1812 if ( ignore_virus_like_ids ) {
1813 System.out.println( "Domains ignored due virus like ids : "
1814 + parser.getDomainsIgnoredDueToVirusLikeIds() );
1815 log( "Domains ignored due virus like ids : " + parser.getDomainsIgnoredDueToVirusLikeIds(),
1818 System.out.println( "Domains ignored due negative domain filter : "
1819 + parser.getDomainsIgnoredDueToNegativeDomainFilter() );
1820 log( "Domains ignored due negative domain filter : "
1821 + parser.getDomainsIgnoredDueToNegativeDomainFilter(),
1823 System.out.println( "Domains ignored due to overlap : "
1824 + parser.getDomainsIgnoredDueToOverlap() );
1825 log( "Domains ignored due to overlap : " + parser.getDomainsIgnoredDueToOverlap(),
1827 if ( negative_filter_file != null ) {
1828 System.out.println( "Proteins ignored due to negative filter : "
1829 + parser.getProteinsIgnoredDueToFilter() );
1830 log( "Proteins ignored due to negative filter : " + parser.getProteinsIgnoredDueToFilter(),
1833 if ( positive_filter_file != null ) {
1834 System.out.println( "Proteins ignored due to positive filter : "
1835 + parser.getProteinsIgnoredDueToFilter() );
1836 log( "Proteins ignored due to positive filter : " + parser.getProteinsIgnoredDueToFilter(),
1839 if ( da_analysis ) {
1840 System.out.println( "Distinct domain architectures stored : " + distinct_das );
1841 log( "Distinct domain architectures stored : " + distinct_das, log_writer );
1843 System.out.println( "Time for processing : " + parser.getTime() + "ms" );
1844 log( "", log_writer );
1847 for( final Protein protein : protein_list ) {
1848 dc_data_writer.write( SurfacingUtil.proteinToDomainCombinations( protein, count + "", "\t" )
1851 for( final Domain d : protein.getProteinDomains() ) {
1852 final String d_str = d.getDomainId().toString();
1853 if ( !domain_length_stats_by_domain.containsKey( d_str ) ) {
1854 domain_length_stats_by_domain.put( d_str, new BasicDescriptiveStatistics() );
1856 domain_length_stats_by_domain.get( d_str ).addValue( d.getLength() );
1860 catch ( final IOException e ) {
1861 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1863 SurfacingUtil.domainsPerProteinsStatistics( input_file_properties[ i ][ 1 ],
1865 all_genomes_domains_per_potein_stats,
1866 all_genomes_domains_per_potein_histo,
1867 domains_which_are_always_single,
1868 domains_which_are_sometimes_single_sometimes_not,
1869 domains_which_never_single,
1870 domains_per_potein_stats_writer );
1871 domain_lengths_table.addLengths( protein_list );
1872 if ( !da_analysis ) {
1873 gwcd_list.add( BasicGenomeWideCombinableDomains
1874 .createInstance( protein_list,
1875 ignore_combination_with_same,
1876 new BasicSpecies( input_file_properties[ i ][ 1 ] ),
1877 domain_id_to_go_ids_map,
1879 protein_length_stats_by_dc,
1880 domain_number_stats_by_dc ) );
1881 if ( gwcd_list.get( i ).getSize() > 0 ) {
1882 SurfacingUtil.writeDomainCombinationsCountsFile( input_file_properties,
1884 per_genome_domain_promiscuity_statistics_writer,
1888 if ( output_binary_domain_combinationsfor_graph_analysis ) {
1889 SurfacingUtil.writeBinaryDomainCombinationsFileForGraphAnalysis( input_file_properties,
1895 SurfacingUtil.addAllDomainIdsToSet( gwcd_list.get( i ), all_domains_encountered );
1896 SurfacingUtil.addAllBinaryDomainCombinationToSet( gwcd_list.get( i ),
1897 all_bin_domain_combinations_encountered );
1900 if ( query_domains_writer_ary != null ) {
1901 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1903 SurfacingUtil.extractProteinNames( protein_list,
1904 query_domain_ids_array[ j ],
1905 query_domains_writer_ary[ j ],
1907 LIMIT_SPEC_FOR_PROT_EX );
1908 query_domains_writer_ary[ j ].flush();
1910 catch ( final IOException e ) {
1911 e.printStackTrace();
1915 if ( need_protein_lists_per_species ) {
1916 protein_lists_per_species.put( new BasicSpecies( input_file_properties[ i ][ 1 ] ), protein_list );
1921 catch ( final IOException e2 ) {
1922 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1925 } // for( int i = 0; i < number_of_genomes; ++i ) {
1926 ForesterUtil.programMessage( PRG_NAME, "Wrote domain promiscuities to: "
1927 + per_genome_domain_promiscuity_statistics_file );
1929 if ( da_analysis ) {
1930 SurfacingUtil.performDomainArchitectureAnalysis( distinct_domain_architecutures_per_genome,
1931 distinct_domain_architecuture_counts,
1933 new File( out_dir.toString() + "/" + output_file
1934 + "_DA_counts.txt" ),
1935 new File( out_dir.toString() + "/" + output_file
1936 + "_unique_DAs.txt" ) );
1937 distinct_domain_architecutures_per_genome.clear();
1938 distinct_domain_architecuture_counts.clear();
1942 domains_per_potein_stats_writer.write( "ALL" );
1943 domains_per_potein_stats_writer.write( "\t" );
1944 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.arithmeticMean() + "" );
1945 domains_per_potein_stats_writer.write( "\t" );
1946 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.sampleStandardDeviation() + "" );
1947 domains_per_potein_stats_writer.write( "\t" );
1948 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.median() + "" );
1949 domains_per_potein_stats_writer.write( "\t" );
1950 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getN() + "" );
1951 domains_per_potein_stats_writer.write( "\t" );
1952 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMin() + "" );
1953 domains_per_potein_stats_writer.write( "\t" );
1954 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMax() + "" );
1955 domains_per_potein_stats_writer.write( "\n" );
1956 domains_per_potein_stats_writer.close();
1957 printOutPercentageOfMultidomainProteins( all_genomes_domains_per_potein_histo, log_writer );
1958 ForesterUtil.map2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1959 + "_all_genomes_domains_per_potein_histo.txt" ), all_genomes_domains_per_potein_histo, "\t", "\n" );
1960 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1961 + "_domains_always_single_.txt" ), domains_which_are_always_single, "\n" );
1962 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1963 + "_domains_single_or_combined.txt" ), domains_which_are_sometimes_single_sometimes_not, "\n" );
1964 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1965 + "_domains_always_combined.txt" ), domains_which_never_single, "\n" );
1966 ForesterUtil.programMessage( PRG_NAME,
1967 "Average of proteins with a least one domain assigned: "
1968 + ( 100 * protein_coverage_stats.arithmeticMean() ) + "% (+/-"
1969 + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)" );
1970 ForesterUtil.programMessage( PRG_NAME, "Range of proteins with a least one domain assigned: "
1971 + ( 100 * protein_coverage_stats.getMin() ) + "%-" + ( 100 * protein_coverage_stats.getMax() )
1973 log( "Average of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.arithmeticMean() )
1974 + "% (+/-" + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)", log_writer );
1975 log( "Range of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.getMin() ) + "%-"
1976 + ( 100 * protein_coverage_stats.getMax() ) + "%", log_writer );
1978 catch ( final IOException e2 ) {
1979 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1981 if ( query_domains_writer_ary != null ) {
1982 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1984 query_domains_writer_ary[ j ].close();
1986 catch ( final IOException e ) {
1987 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1992 per_genome_domain_promiscuity_statistics_writer.close();
1993 dc_data_writer.close();
1996 catch ( final IOException e2 ) {
1997 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1999 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
2001 SurfacingUtil.executeDomainLengthAnalysis( input_file_properties,
2003 domain_lengths_table,
2004 domain_lengths_analysis_outfile );
2006 catch ( final IOException e1 ) {
2007 ForesterUtil.fatalError( surfacing.PRG_NAME, e1.toString() );
2009 System.out.println();
2010 ForesterUtil.programMessage( PRG_NAME, "Wrote domain length data to: " + domain_lengths_analysis_outfile );
2011 System.out.println();
2013 domain_lengths_table = null;
2014 final long analysis_start_time = new Date().getTime();
2015 PairwiseDomainSimilarityCalculator pw_calc = null;
2016 final DomainSimilarityCalculator calc = new BasicDomainSimilarityCalculator( domain_similarity_sort_field,
2017 sort_by_species_count_first,
2018 number_of_genomes == 2,
2019 CALC_SIMILARITY_SCORES );
2020 switch ( scoring ) {
2022 pw_calc = new CombinationsBasedPairwiseDomainSimilarityCalculator();
2025 pw_calc = new DomainCountsBasedPairwiseSimilarityCalculator();
2028 pw_calc = new ProteinCountsBasedPairwiseDomainSimilarityCalculator();
2031 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
2033 DomainSimilarityCalculator.GoAnnotationOutput go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.NONE;
2034 if ( domain_id_to_go_ids_map != null ) {
2035 go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.ALL;
2037 final SortedSet<DomainSimilarity> similarities = calc
2038 .calculateSimilarities( pw_calc,
2040 ignore_domains_without_combs_in_all_spec,
2041 ignore_species_specific_domains );
2042 SurfacingUtil.decoratePrintableDomainSimilarities( similarities, detailedness );
2043 final Map<String, Integer> tax_code_to_id_map = SurfacingUtil.createTaxCodeToIdMap( intrees[ 0 ] );
2045 String my_outfile = output_file.toString();
2046 Map<Character, Writer> split_writers = null;
2047 Writer writer = null;
2048 if ( similarities.size() > MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING ) {
2049 if ( my_outfile.endsWith( ".html" ) ) {
2050 my_outfile = my_outfile.substring( 0, my_outfile.length() - 5 );
2052 split_writers = new HashMap<Character, Writer>();
2053 createSplitWriters( out_dir, my_outfile, split_writers );
2055 else if ( !my_outfile.endsWith( ".html" ) ) {
2056 my_outfile += ".html";
2057 writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) );
2059 List<Species> species_order = null;
2060 if ( species_matrix ) {
2061 species_order = new ArrayList<Species>();
2062 for( int i = 0; i < number_of_genomes; i++ ) {
2063 species_order.add( new BasicSpecies( input_file_properties[ i ][ 1 ] ) );
2066 html_desc.append( "<tr><td>Sum of all distinct binary combinations:</td><td>"
2067 + all_bin_domain_combinations_encountered.size() + "</td></tr>" + nl );
2068 html_desc.append( "<tr><td>Sum of all distinct domains:</td><td>" + all_domains_encountered.size()
2069 + "</td></tr>" + nl );
2070 html_desc.append( "<tr><td>Analysis date/time:</td><td>"
2071 + new java.text.SimpleDateFormat( "yyyy.MM.dd HH:mm:ss" ).format( new java.util.Date() )
2072 + "</td></tr>" + nl );
2073 html_desc.append( "</table>" + nl );
2074 final Writer simple_tab_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
2075 + my_outfile + ".tsv" ) );
2076 SurfacingUtil.writeDomainSimilaritiesToFile( html_desc,
2077 new StringBuilder( number_of_genomes + " genomes" ),
2082 number_of_genomes == 2,
2084 domain_similarity_print_option,
2087 tax_code_to_id_map );
2088 simple_tab_writer.close();
2089 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote main output (includes domain similarities) to: \""
2090 + ( out_dir == null ? my_outfile : out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) + "\"" );
2092 catch ( final IOException e ) {
2093 ForesterUtil.fatalError( surfacing.PRG_NAME, "Failed to write similarites to: \"" + output_file + "\" ["
2094 + e.getMessage() + "]" );
2096 System.out.println();
2097 final Species[] species = new Species[ number_of_genomes ];
2098 for( int i = 0; i < number_of_genomes; ++i ) {
2099 species[ i ] = new BasicSpecies( input_file_properties[ i ][ 1 ] );
2101 List<Phylogeny> inferred_trees = null;
2102 if ( ( number_of_genomes > 2 ) && perform_pwc ) {
2103 final PairwiseGenomeComparator pwgc = new PairwiseGenomeComparator();
2104 pwgc.performPairwiseComparisons( html_desc,
2105 sort_by_species_count_first,
2107 ignore_domains_without_combs_in_all_spec,
2108 ignore_species_specific_domains,
2109 domain_similarity_sort_field_for_automated_pwc,
2110 domain_similarity_print_option,
2112 domain_id_to_go_ids_map,
2119 automated_pairwise_comparison_suffix,
2121 surfacing.PAIRWISE_DOMAIN_COMPARISONS_PREFIX,
2126 CALC_SIMILARITY_SCORES );
2127 String matrix_output_file = new String( output_file.toString() );
2128 if ( matrix_output_file.indexOf( '.' ) > 1 ) {
2129 matrix_output_file = matrix_output_file.substring( 0, matrix_output_file.indexOf( '.' ) );
2131 if ( out_dir != null ) {
2132 matrix_output_file = out_dir + ForesterUtil.FILE_SEPARATOR + matrix_output_file;
2133 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2135 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2136 + surfacing.MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans() );
2138 .writeMatrixToFile( new File( matrix_output_file
2139 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2140 pwgc.getSharedBinaryCombinationsBasedDistances() );
2141 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2142 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2143 pwgc.getSharedDomainsBasedDistances() );
2144 final Phylogeny nj_gd = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2145 + surfacing.NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans()
2147 final Phylogeny nj_bc = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2148 + surfacing.NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2149 .getSharedBinaryCombinationsBasedDistances().get( 0 ) );
2150 final Phylogeny nj_d = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2151 + surfacing.NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2152 .getSharedDomainsBasedDistances().get( 0 ) );
2153 inferred_trees = new ArrayList<Phylogeny>();
2154 inferred_trees.add( nj_gd );
2155 inferred_trees.add( nj_bc );
2156 inferred_trees.add( nj_d );
2157 } // if ( ( output_file != null ) && ( number_of_genomes > 2 ) && !isEmpty( automated_pairwise_comparison_suffix ) )
2158 if ( ( out_dir != null ) && ( !perform_pwc ) ) {
2159 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2161 if ( write_to_nexus ) {
2162 writePresentToNexus( output_file, positive_filter_file, filter, gwcd_list );
2164 if ( ( ( intrees != null ) && ( intrees.length > 0 ) ) && ( number_of_genomes > 2 ) ) {
2165 final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
2167 max_allowed_overlap,
2168 no_engulfing_overlaps,
2172 if ( radomize_fitch_parsimony ) {
2173 s += random_number_seed_for_fitch_parsimony + "_";
2176 for( final Phylogeny intree : intrees ) {
2177 final String outfile_name = ForesterUtil.removeSuffix( output_file.toString() ) + s
2178 + ForesterUtil.removeSuffix( intree_files[ i ].toString() );
2179 final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator.createInstance( intree,
2181 SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
2182 radomize_fitch_parsimony,
2186 domain_id_to_go_ids_map,
2189 parameters_sb.toString(),
2190 domain_id_to_secondary_features_maps,
2191 positive_filter_file == null ? null : filter,
2192 output_binary_domain_combinationsfor_graph_analysis,
2193 all_bin_domain_combinations_gained_fitch,
2194 all_bin_domain_combinations_lost_fitch,
2196 protein_length_stats_by_dc,
2197 domain_number_stats_by_dc,
2198 domain_length_stats_by_domain,
2201 use_last_in_fitch_parsimony );
2202 // Listing of all domain combinations gained is only done if only one input tree is used.
2203 if ( ( domain_id_to_secondary_features_maps != null )
2204 && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
2206 for( final Map<String, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
2207 final Map<Species, MappingResults> mapping_results_map = new TreeMap<Species, MappingResults>();
2208 final DomainParsimonyCalculator secondary_features_parsimony = DomainParsimonyCalculator
2209 .createInstance( intree, gwcd_list, domain_id_to_secondary_features_map );
2211 .executeParsimonyAnalysisForSecondaryFeatures( outfile_name
2213 + secondary_features_map_files[ j++ ],
2214 secondary_features_parsimony,
2216 parameters_sb.toString(),
2217 mapping_results_map,
2218 use_last_in_fitch_parsimony );
2220 System.out.println();
2221 System.out.println( "Mapping to secondary features:" );
2222 for( final Species spec : mapping_results_map.keySet() ) {
2223 final MappingResults mapping_results = mapping_results_map.get( spec );
2224 final int total_domains = mapping_results.getSumOfFailures()
2225 + mapping_results.getSumOfSuccesses();
2226 System.out.print( spec + ":" );
2227 System.out.print( " mapped domains = " + mapping_results.getSumOfSuccesses() );
2228 System.out.print( ", not mapped domains = " + mapping_results.getSumOfFailures() );
2229 if ( total_domains > 0 ) {
2230 System.out.println( ", mapped ratio = "
2231 + ( ( 100 * mapping_results.getSumOfSuccesses() ) / total_domains ) + "%" );
2234 System.out.println( ", mapped ratio = n/a (total domains = 0 )" );
2241 } // for( final Phylogeny intree : intrees ) {
2243 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
2244 executePlusMinusAnalysis( output_file,
2245 plus_minus_analysis_high_copy_base_species,
2246 plus_minus_analysis_high_copy_target_species,
2247 plus_minus_analysis_high_low_copy_species,
2249 protein_lists_per_species,
2250 domain_id_to_go_ids_map,
2252 plus_minus_analysis_numbers );
2254 if ( output_protein_lists_for_all_domains ) {
2255 writeProteinListsForAllSpecies( out_dir,
2256 protein_lists_per_species,
2258 output_list_of_all_proteins_per_domain_e_value_max );
2261 if ( all_bin_domain_combinations_gained_fitch != null ) {
2263 executeFitchGainsAnalysis( new File( output_file
2264 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2265 all_bin_domain_combinations_gained_fitch,
2266 all_domains_encountered.size(),
2267 all_bin_domain_combinations_encountered,
2270 catch ( final IOException e ) {
2271 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2274 if ( all_bin_domain_combinations_lost_fitch != null ) {
2276 executeFitchGainsAnalysis( new File( output_file
2277 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2278 all_bin_domain_combinations_lost_fitch,
2279 all_domains_encountered.size(),
2280 all_bin_domain_combinations_encountered,
2283 catch ( final IOException e ) {
2284 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2287 final Runtime rt = java.lang.Runtime.getRuntime();
2288 final long free_memory = rt.freeMemory() / 1000000;
2289 final long total_memory = rt.totalMemory() / 1000000;
2290 ForesterUtil.programMessage( PRG_NAME, "Time for analysis : " + ( new Date().getTime() - analysis_start_time )
2292 ForesterUtil.programMessage( PRG_NAME, "Total running time: " + ( new Date().getTime() - start_time ) + "ms " );
2293 ForesterUtil.programMessage( PRG_NAME, "Free memory : " + free_memory + "MB, total memory: "
2294 + total_memory + "MB" );
2295 ForesterUtil.programMessage( PRG_NAME, "If this application is useful to you, please cite:" );
2296 ForesterUtil.programMessage( PRG_NAME, surfacing.WWW );
2297 ForesterUtil.programMessage( PRG_NAME, "OK" );
2298 System.out.println();
2301 private static void createSplitWriters( final File out_dir,
2302 final String my_outfile,
2303 final Map<Character, Writer> split_writers ) throws IOException {
2304 split_writers.put( 'a', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2305 + "_domains_A.html" ) ) );
2306 split_writers.put( 'b', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2307 + "_domains_B.html" ) ) );
2308 split_writers.put( 'c', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2309 + "_domains_C.html" ) ) );
2310 split_writers.put( 'd', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2311 + "_domains_D.html" ) ) );
2312 split_writers.put( 'e', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2313 + "_domains_E.html" ) ) );
2314 split_writers.put( 'f', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2315 + "_domains_F.html" ) ) );
2316 split_writers.put( 'g', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2317 + "_domains_G.html" ) ) );
2318 split_writers.put( 'h', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2319 + "_domains_H.html" ) ) );
2320 split_writers.put( 'i', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2321 + "_domains_I.html" ) ) );
2322 split_writers.put( 'j', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2323 + "_domains_J.html" ) ) );
2324 split_writers.put( 'k', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2325 + "_domains_K.html" ) ) );
2326 split_writers.put( 'l', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2327 + "_domains_L.html" ) ) );
2328 split_writers.put( 'm', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2329 + "_domains_M.html" ) ) );
2330 split_writers.put( 'n', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2331 + "_domains_N.html" ) ) );
2332 split_writers.put( 'o', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2333 + "_domains_O.html" ) ) );
2334 split_writers.put( 'p', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2335 + "_domains_P.html" ) ) );
2336 split_writers.put( 'q', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2337 + "_domains_Q.html" ) ) );
2338 split_writers.put( 'r', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2339 + "_domains_R.html" ) ) );
2340 split_writers.put( 's', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2341 + "_domains_S.html" ) ) );
2342 split_writers.put( 't', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2343 + "_domains_T.html" ) ) );
2344 split_writers.put( 'u', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2345 + "_domains_U.html" ) ) );
2346 split_writers.put( 'v', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2347 + "_domains_V.html" ) ) );
2348 split_writers.put( 'w', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2349 + "_domains_W.html" ) ) );
2350 split_writers.put( 'x', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2351 + "_domains_X.html" ) ) );
2352 split_writers.put( 'y', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2353 + "_domains_Y.html" ) ) );
2354 split_writers.put( 'z', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2355 + "_domains_Z.html" ) ) );
2356 split_writers.put( '0', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2357 + "_domains_0.html" ) ) );
2360 private static void printOutPercentageOfMultidomainProteins( final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo,
2361 final Writer log_writer ) {
2363 for( final Entry<Integer, Integer> entry : all_genomes_domains_per_potein_histo.entrySet() ) {
2364 sum += entry.getValue();
2366 final double percentage = ( 100.0 * ( sum - all_genomes_domains_per_potein_histo.get( 1 ) ) ) / sum;
2367 ForesterUtil.programMessage( PRG_NAME, "Percentage of multidomain proteins: " + percentage + "%" );
2368 log( "Percentage of multidomain proteins: : " + percentage + "%", log_writer );
2371 private static void preparePhylogenyForParsimonyAnalyses( final Phylogeny intree,
2372 final String[][] input_file_properties ) {
2373 final String[] genomes = new String[ input_file_properties.length ];
2374 for( int i = 0; i < input_file_properties.length; ++i ) {
2375 if ( intree.getNodes( input_file_properties[ i ][ 1 ] ).size() > 1 ) {
2376 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
2377 + "] is not unique in input tree " + intree.getName() );
2379 genomes[ i ] = input_file_properties[ i ][ 1 ];
2382 final PhylogenyNodeIterator it = intree.iteratorPostorder();
2383 while ( it.hasNext() ) {
2384 final PhylogenyNode n = it.next();
2385 if ( ForesterUtil.isEmpty( n.getName() ) ) {
2386 if ( n.getNodeData().isHasTaxonomy()
2387 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getTaxonomyCode() ) ) {
2388 n.setName( n.getNodeData().getTaxonomy().getTaxonomyCode() );
2390 else if ( n.getNodeData().isHasTaxonomy()
2391 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
2392 n.setName( n.getNodeData().getTaxonomy().getScientificName() );
2394 else if ( n.getNodeData().isHasTaxonomy()
2395 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getCommonName() ) ) {
2396 n.setName( n.getNodeData().getTaxonomy().getCommonName() );
2400 .fatalError( surfacing.PRG_NAME,
2401 "node with no name, scientific name, common name, or taxonomy code present" );
2406 final List<String> igns = PhylogenyMethods.deleteExternalNodesPositiveSelection( genomes, intree );
2407 if ( igns.size() > 0 ) {
2408 System.out.println( "Not using the following " + igns.size() + " nodes:" );
2409 for( int i = 0; i < igns.size(); ++i ) {
2410 System.out.println( " " + i + ": " + igns.get( i ) );
2412 System.out.println( "--" );
2414 for( final String[] input_file_propertie : input_file_properties ) {
2416 intree.getNode( input_file_propertie[ 1 ] );
2418 catch ( final IllegalArgumentException e ) {
2419 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_propertie[ 1 ]
2420 + "] not present/not unique in input tree" );
2425 private static void printHelp() {
2426 System.out.println();
2427 System.out.println( "Usage:" );
2428 System.out.println();
2429 System.out.println( "% java -Xms256m -Xmx512m -cp forester.jar org.forester.applications." + surfacing.PRG_NAME
2430 + " [options] <phylogen(y|ies) infile> [external node name 1] [name 2] ... [name n]" );
2431 System.out.println();
2432 System.out.println( " Note: This software might need a significant amount of memory (heap space);" );
2434 .println( " hence use \"-Xms128m -Xmx512m\" (or more) to prevent a \"java.lang.OutOfMemoryError\"." );
2435 System.out.println();
2436 System.out.println( " Options: " );
2437 System.out.println( surfacing.DETAILEDNESS_OPTION + ": level of detail for similarities output file (default:"
2438 + DETAILEDNESS_DEFAULT + ")" );
2439 System.out.println( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION
2440 + ": to ignore combinations with self (default: not to ignore)" );
2442 .println( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION
2443 + ": to ignore domains without combinations in any species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2445 .println( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION
2446 + ": to ignore domains specific to one species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2447 System.out.println( surfacing.NOT_IGNORE_DUFS_OPTION
2448 + ": to _not_ ignore DUFs (domains with unknown function) (default: ignore DUFs)" );
2450 .println( surfacing.IGNORE_VIRAL_IDS
2451 + ": to ignore domains with ids containing 'vir', 'retro', 'transpos', 'phage', or starting with 'rv' or 'gag_'" );
2452 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_OPTION + ": sorting for similarities (default: "
2453 + DOMAIN_SORT_FILD_DEFAULT + ")" );
2454 System.out.println( surfacing.OUTPUT_FILE_OPTION + ": name for (main) output file (mandatory)" );
2455 System.out.println( surfacing.MAX_E_VALUE_OPTION + ": max (inclusive) E-value" );
2456 System.out.println( surfacing.MAX_ALLOWED_OVERLAP_OPTION + ": maximal allowed domain overlap" );
2457 System.out.println( surfacing.NO_ENGULFING_OVERLAP_OPTION + ": to ignore engulfed lower confidence domains" );
2458 System.out.println( surfacing.SPECIES_MATRIX_OPTION + ": species matrix" );
2459 System.out.println( surfacing.SCORING_OPTION + ": scoring (default:" + SCORING_DEFAULT + ")" );
2460 System.out.println( surfacing.DOMAIN_COUNT_SORT_OPTION + ": sorting for domain counts (default:"
2461 + DOMAINS_SORT_ORDER_DEFAULT + ")" );
2462 System.out.println( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION + ": domain similarity print option (default:"
2463 + DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT + ")" );
2464 System.out.println( surfacing.CUTOFF_SCORE_FILE_OPTION + ": cutoff score file" );
2465 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION
2466 + ": sort by species count first" );
2467 System.out.println( surfacing.OUTPUT_DIR_OPTION + ": output directory" );
2468 System.out.println( surfacing.PFAM_TO_GO_FILE_USE_OPTION + ": Pfam to GO mapping file" );
2469 System.out.println( surfacing.GO_OBO_FILE_USE_OPTION + ": GO terms file (OBO format)" );
2470 System.out.println( surfacing.GO_NAMESPACE_LIMIT_OPTION + ": limit GO term to one GO namespace" );
2471 System.out.println( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
2472 + "[=<suffix for pairwise comparison output files>]: to perform pairwise comparison based analyses" );
2473 System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION
2474 + ": species tree, to perform (Dollo, Fitch) parismony analyses" );
2476 .println( surfacing.INPUT_SPECIES_TREE_OPTION
2477 + "=<treefiles in phyloXML format, separated by #>: to infer domain/binary domain combination gains/losses on given species trees" );
2478 System.out.println( surfacing.FILTER_POSITIVE_OPTION
2479 + "=<file>: to filter out proteins not containing at least one domain listed in <file>" );
2480 System.out.println( surfacing.FILTER_NEGATIVE_OPTION
2481 + "=<file>: to filter out proteins containing at least one domain listed in <file>" );
2482 System.out.println( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION
2483 + "=<file>: to filter out (ignore) domains listed in <file>" );
2484 System.out.println( surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>: to read input files from <file>" );
2486 .println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION
2487 + "=<seed>: seed for random number generator for Fitch Parsimony analysis (type: long, default: no randomization - given a choice, prefer absence" );
2488 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS
2489 + ": to consider directedness in binary combinations: e.g. A-B != B-A" );
2490 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY
2491 + ": to consider directedness and adjacency in binary combinations" );
2493 .println( surfacing.SEQ_EXTRACT_OPTION
2494 + "=<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')" );
2495 System.out.println( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE
2496 + "=<file>: to perfom parsimony analysis on secondary features" );
2497 System.out.println( surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>: to presence/absence genome analysis" );
2498 System.out.println( surfacing.DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS
2499 + ": to output binary domain combinations for (downstream) graph analysis" );
2500 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS + ": to output all proteins per domain" );
2501 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION
2502 + ": e value max per domain for output of all proteins per domain" );
2503 System.out.println( surfacing.USE_LAST_IN_FITCH_OPTION + ": to use last in Fitch parsimony" );
2504 System.out.println( surfacing.WRITE_TO_NEXUS_OPTION + ": to output in Nexus format" );
2505 System.out.println( PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION + ": to perform DC regain protein statistics" );
2506 System.out.println( DA_ANALYSIS_OPTION + ": to do DA analysis" );
2507 System.out.println();
2508 System.out.println( "Example 1: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2509 + " org.forester.application.surfacing p2g=pfam2go_2012_02_07.txt -dufs -cos=Pfam_260_NC1"
2510 + " -no_eo -mo=0 -genomes=eukaryotes.txt -out_dir=out -o=o "
2511 + " -species_tree=tol.xml -obo=gene_ontology_2012_02_07.obo -pos_filter=f.txt -all_prot" );
2512 System.out.println();
2513 System.out.println( "Example 2: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2514 + " org.forester.application.surfacing -detail=punctilious -o=TEST.html -pwc=TEST"
2515 + " -cos=Pfam_ls_22_TC2 -p2g=pfam2go -obo=gene_ontology_edit.obo "
2516 + "-dc_sort=dom -ignore_with_self -no_singles -e=0.001 -mo=1 -no_eo -genomes=eukaryotes.txt "
2517 + "-ds_output=detailed_html -scoring=domains -sort=alpha " );
2518 System.out.println();
2521 private static void processFilter( final File filter_file, final SortedSet<String> filter ) {
2522 SortedSet<String> filter_str = null;
2524 filter_str = ForesterUtil.file2set( filter_file );
2526 catch ( final IOException e ) {
2527 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2529 if ( filter_str != null ) {
2530 for( final String string : filter_str ) {
2531 filter.add( string );
2535 System.out.println( "Filter:" );
2536 for( final String domainId : filter ) {
2537 System.out.println( domainId );
2542 private static String[][] processInputGenomesFile( final File input_genomes ) {
2543 String[][] input_file_properties = null;
2545 input_file_properties = ForesterUtil.file22dArray( input_genomes );
2547 catch ( final IOException e ) {
2548 ForesterUtil.fatalError( surfacing.PRG_NAME,
2549 "genomes files is to be in the following format \"<hmmpfam output file> <species>\": "
2550 + e.getLocalizedMessage() );
2552 final Set<String> specs = new HashSet<String>();
2553 final Set<String> paths = new HashSet<String>();
2554 for( int i = 0; i < input_file_properties.length; ++i ) {
2555 if ( !PhyloXmlUtil.TAXOMONY_CODE_PATTERN.matcher( input_file_properties[ i ][ 1 ] ).matches() ) {
2556 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for species code: "
2557 + input_file_properties[ i ][ 1 ] );
2559 if ( specs.contains( input_file_properties[ i ][ 1 ] ) ) {
2560 ForesterUtil.fatalError( surfacing.PRG_NAME, "species code " + input_file_properties[ i ][ 1 ]
2561 + " is not unique" );
2563 specs.add( input_file_properties[ i ][ 1 ] );
2564 if ( paths.contains( input_file_properties[ i ][ 0 ] ) ) {
2565 ForesterUtil.fatalError( surfacing.PRG_NAME, "path " + input_file_properties[ i ][ 0 ]
2566 + " is not unique" );
2568 paths.add( input_file_properties[ i ][ 0 ] );
2569 final String error = ForesterUtil.isReadableFile( new File( input_file_properties[ i ][ 0 ] ) );
2570 if ( !ForesterUtil.isEmpty( error ) ) {
2571 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
2574 return input_file_properties;
2577 private static void processPlusMinusAnalysisOption( final CommandLineArguments cla,
2578 final List<String> high_copy_base,
2579 final List<String> high_copy_target,
2580 final List<String> low_copy,
2581 final List<Object> numbers ) {
2582 if ( cla.isOptionSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2583 if ( !cla.isOptionValueSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2584 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for 'plus-minus' file: -"
2585 + surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>" );
2587 final File plus_minus_file = new File( cla.getOptionValue( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) );
2588 final String msg = ForesterUtil.isReadableFile( plus_minus_file );
2589 if ( !ForesterUtil.isEmpty( msg ) ) {
2590 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + plus_minus_file + "\": " + msg );
2592 processPlusMinusFile( plus_minus_file, high_copy_base, high_copy_target, low_copy, numbers );
2596 // First numbers is minimal difference, second is factor.
2597 private static void processPlusMinusFile( final File plus_minus_file,
2598 final List<String> high_copy_base,
2599 final List<String> high_copy_target,
2600 final List<String> low_copy,
2601 final List<Object> numbers ) {
2602 Set<String> species_set = null;
2603 int min_diff = PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT;
2604 double factor = PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT;
2606 species_set = ForesterUtil.file2set( plus_minus_file );
2608 catch ( final IOException e ) {
2609 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2611 if ( species_set != null ) {
2612 for( final String species : species_set ) {
2613 final String species_trimmed = species.substring( 1 );
2614 if ( species.startsWith( "+" ) ) {
2615 if ( low_copy.contains( species_trimmed ) ) {
2616 ForesterUtil.fatalError( surfacing.PRG_NAME,
2617 "species/genome names can not appear with both '+' and '-' suffix, as appears the case for: \""
2618 + species_trimmed + "\"" );
2620 high_copy_base.add( species_trimmed );
2622 else if ( species.startsWith( "*" ) ) {
2623 if ( low_copy.contains( species_trimmed ) ) {
2624 ForesterUtil.fatalError( surfacing.PRG_NAME,
2625 "species/genome names can not appear with both '*' and '-' suffix, as appears the case for: \""
2626 + species_trimmed + "\"" );
2628 high_copy_target.add( species_trimmed );
2630 else if ( species.startsWith( "-" ) ) {
2631 if ( high_copy_base.contains( species_trimmed ) || high_copy_target.contains( species_trimmed ) ) {
2632 ForesterUtil.fatalError( surfacing.PRG_NAME,
2633 "species/genome names can not appear with both '+' or '*' and '-' suffix, as appears the case for: \""
2634 + species_trimmed + "\"" );
2636 low_copy.add( species_trimmed );
2638 else if ( species.startsWith( "$D" ) ) {
2640 min_diff = Integer.parseInt( species.substring( 3 ) );
2642 catch ( final NumberFormatException e ) {
2643 ForesterUtil.fatalError( surfacing.PRG_NAME,
2644 "could not parse integer value for minimal difference from: \""
2645 + species.substring( 3 ) + "\"" );
2648 else if ( species.startsWith( "$F" ) ) {
2650 factor = Double.parseDouble( species.substring( 3 ) );
2652 catch ( final NumberFormatException e ) {
2653 ForesterUtil.fatalError( surfacing.PRG_NAME, "could not parse double value for factor from: \""
2654 + species.substring( 3 ) + "\"" );
2657 else if ( species.startsWith( "#" ) ) {
2662 .fatalError( surfacing.PRG_NAME,
2663 "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: \""
2666 numbers.add( new Integer( min_diff + "" ) );
2667 numbers.add( new Double( factor + "" ) );
2671 ForesterUtil.fatalError( surfacing.PRG_NAME, "'plus minus' file [" + plus_minus_file + "] appears empty" );
2675 private static void writePresentToNexus( final File output_file,
2676 final File positive_filter_file,
2677 final SortedSet<String> filter,
2678 final List<GenomeWideCombinableDomains> gwcd_list ) {
2681 .writeMatrixToFile( DomainParsimonyCalculator
2682 .createMatrixOfDomainPresenceOrAbsence( gwcd_list, positive_filter_file == null ? null
2683 : filter ), output_file + DOMAINS_PRESENT_NEXUS, Format.NEXUS_BINARY );
2684 SurfacingUtil.writeMatrixToFile( DomainParsimonyCalculator
2685 .createMatrixOfBinaryDomainCombinationPresenceOrAbsence( gwcd_list ), output_file
2686 + BDC_PRESENT_NEXUS, Format.NEXUS_BINARY );
2688 catch ( final Exception e ) {
2689 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2693 private static void writeProteinListsForAllSpecies( final File output_dir,
2694 final SortedMap<Species, List<Protein>> protein_lists_per_species,
2695 final List<GenomeWideCombinableDomains> gwcd_list,
2696 final double domain_e_cutoff ) {
2697 final SortedSet<String> all_domains = new TreeSet<String>();
2698 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
2699 all_domains.addAll( gwcd.getAllDomainIds() );
2701 for( final String domain : all_domains ) {
2702 final File out = new File( output_dir + ForesterUtil.FILE_SEPARATOR + domain + SEQ_EXTRACT_SUFFIX );
2703 SurfacingUtil.checkForOutputFileWriteability( out );
2705 final Writer proteins_file_writer = new BufferedWriter( new FileWriter( out ) );
2706 SurfacingUtil.extractProteinNames( protein_lists_per_species,
2708 proteins_file_writer,
2710 LIMIT_SPEC_FOR_PROT_EX,
2712 proteins_file_writer.close();
2714 catch ( final IOException e ) {
2715 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2717 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote proteins list to \"" + out + "\"" );