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.List;
40 import java.util.SortedMap;
41 import java.util.SortedSet;
42 import java.util.TreeMap;
43 import java.util.TreeSet;
45 import org.forester.go.GoId;
46 import org.forester.go.GoNameSpace;
47 import org.forester.go.GoTerm;
48 import org.forester.go.GoUtils;
49 import org.forester.go.OBOparser;
50 import org.forester.go.PfamToGoMapping;
51 import org.forester.go.PfamToGoParser;
52 import org.forester.io.parsers.HmmscanPerDomainTableParser;
53 import org.forester.io.parsers.HmmscanPerDomainTableParser.INDIVIDUAL_SCORE_CUTOFF;
54 import org.forester.phylogeny.Phylogeny;
55 import org.forester.protein.BinaryDomainCombination;
56 import org.forester.protein.Domain;
57 import org.forester.protein.Protein;
58 import org.forester.species.BasicSpecies;
59 import org.forester.species.Species;
60 import org.forester.surfacing.BasicDomainSimilarityCalculator;
61 import org.forester.surfacing.BasicGenomeWideCombinableDomains;
62 import org.forester.surfacing.CombinationsBasedPairwiseDomainSimilarityCalculator;
63 import org.forester.surfacing.DomainCountsBasedPairwiseSimilarityCalculator;
64 import org.forester.surfacing.DomainLengthsTable;
65 import org.forester.surfacing.DomainParsimonyCalculator;
66 import org.forester.surfacing.DomainSimilarity;
67 import org.forester.surfacing.DomainSimilarity.DomainSimilarityScoring;
68 import org.forester.surfacing.DomainSimilarity.PRINT_OPTION;
69 import org.forester.surfacing.DomainSimilarityCalculator;
70 import org.forester.surfacing.DomainSimilarityCalculator.Detailedness;
71 import org.forester.surfacing.GenomeWideCombinableDomains;
72 import org.forester.surfacing.GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder;
73 import org.forester.surfacing.MappingResults;
74 import org.forester.surfacing.MinimalDomainomeCalculator;
75 import org.forester.surfacing.PairwiseDomainSimilarityCalculator;
76 import org.forester.surfacing.PairwiseGenomeComparator;
77 import org.forester.surfacing.ProteinCountsBasedPairwiseDomainSimilarityCalculator;
78 import org.forester.surfacing.SurfacingUtil;
79 import org.forester.util.BasicDescriptiveStatistics;
80 import org.forester.util.BasicTable;
81 import org.forester.util.BasicTableParser;
82 import org.forester.util.CommandLineArguments;
83 import org.forester.util.DescriptiveStatistics;
84 import org.forester.util.ForesterConstants;
85 import org.forester.util.ForesterUtil;
87 public class surfacing {
89 private static final int MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING = 1000;
90 public final static String DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS = "graph_analysis_out";
91 public final static String DOMAIN_COMBINITONS_COUNTS_OUTPUT_OPTION = "dcc";
92 public final static String DOMAIN_COMBINITONS_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_dc.dot";
93 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_fitch_present_dc.dot";
94 public final static String DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX = ".dcc";
96 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS = "_dollo_gl_d";
97 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_gl_dc";
98 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_DOMAINS = "_fitch_gl_d";
99 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_gl_dc";
101 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS = "_dollo_glc_d";
102 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_glc_dc";
103 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_DOMAINS = "_fitch_glc_d";
104 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_glc_dc";
106 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_BC = "_fitch_gains_dc";
107 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_HTML_BC = "_fitch_gains_dc.html";
108 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_BC = "_fitch_losses_dc";
109 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_HTML_BC = "_fitch_losses_dc.html";
110 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC = "_fitch_present_dc";
111 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_HTML_BC = "_fitch_present_dc.html";
112 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_D = "_dollo_gains_d";
113 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_HTML_D = "_dollo_gains_d.html";
114 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_D = "_dollo_losses_d";
115 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_HTML_D = "_dollo_losses_d.html";
116 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_D = "_dollo_present_d";
117 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_HTML_D = "_dollo_present_d.html";
118 public final static String DOMAINS_PRESENT_NEXUS = "_dom.nex";
119 public final static String BDC_PRESENT_NEXUS = "_dc.nex";
121 public final static String PRG_NAME = "surfacing";
122 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_d_dollo"
123 + ForesterConstants.PHYLO_XML_SUFFIX;
124 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_d_fitch"
125 + ForesterConstants.PHYLO_XML_SUFFIX;
126 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_dc_dollo"
127 + ForesterConstants.PHYLO_XML_SUFFIX;
128 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_dc_fitch"
129 + ForesterConstants.PHYLO_XML_SUFFIX;
130 public static final String NEXUS_EXTERNAL_DOMAINS = "_dom.nex";
131 public static final String NEXUS_EXTERNAL_DOMAIN_COMBINATIONS = "_dc.nex";
132 public static final String NEXUS_SECONDARY_FEATURES = "_secondary_features.nex";
133 public static final String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_gl_secondary_features";
134 public static final String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_glc_secondary_features";
135 public static final String PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES = "_dollo_gains_secondary_features";
136 public static final String PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES = "_dollo_losses_secondary_features";
137 public static final String PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES = "_dollo_present_secondary_features";
138 public static final String SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_secondary_features_dollo"
139 + ForesterConstants.PHYLO_XML_SUFFIX;
140 public static final String PARSIMONY_OUTPUT_DOLLO_ALL_GOID_D_ALL_NAMESPACES = "_dollo_goid_d";
141 public static final String PARSIMONY_OUTPUT_FITCH_ALL_GOID_BC_ALL_NAMESPACES = "_fitch_goid_dc";
142 final static private String HELP_OPTION_1 = "help";
143 final static private String HELP_OPTION_2 = "h";
144 final static private String OUTPUT_DIR_OPTION = "out_dir";
145 final static private String SCORING_OPTION = "scoring";
146 private static final DomainSimilarityScoring SCORING_DEFAULT = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
147 final static private String SCORING_DOMAIN_COUNT_BASED = "domains";
148 final static private String SCORING_PROTEIN_COUNT_BASED = "proteins";
149 final static private String SCORING_COMBINATION_BASED = "combinations";
150 final static private String DETAILEDNESS_OPTION = "detail";
151 private final static Detailedness DETAILEDNESS_DEFAULT = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
152 final static private String SPECIES_MATRIX_OPTION = "smatrix";
153 final static private String DETAILEDNESS_BASIC = "basic";
154 final static private String DETAILEDNESS_LIST_IDS = "list_ids";
155 final static private String DETAILEDNESS_PUNCTILIOUS = "punctilious";
156 final static private String DOMAIN_SIMILARITY_SORT_OPTION = "sort";
157 private static final DomainSimilarity.DomainSimilaritySortField DOMAIN_SORT_FILD_DEFAULT = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
158 final static private String DOMAIN_SIMILARITY_SORT_MIN = "min";
159 final static private String DOMAIN_SIMILARITY_SORT_MAX = "max";
160 final static private String DOMAIN_SIMILARITY_SORT_SD = "sd";
161 final static private String DOMAIN_SIMILARITY_SORT_MEAN = "mean";
162 final static private String DOMAIN_SIMILARITY_SORT_DIFF = "diff";
163 final static private String DOMAIN_SIMILARITY_SORT_COUNTS_DIFF = "count_diff";
164 final static private String DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF = "abs_count_diff";
165 final static private String DOMAIN_SIMILARITY_SORT_SPECIES_COUNT = "species";
166 final static private String DOMAIN_SIMILARITY_SORT_ALPHA = "alpha";
167 final static private String DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION = "species_first";
168 final static private String DOMAIN_COUNT_SORT_OPTION = "dc_sort";
169 private static final GenomeWideCombinableDomainsSortOrder DOMAINS_SORT_ORDER_DEFAULT = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
170 final static private String DOMAIN_COUNT_SORT_ALPHA = "alpha";
171 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT = "dom";
172 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT = "prot";
173 final static private String DOMAIN_COUNT_SORT_COMBINATIONS_COUNT = "comb";
174 final static private String CUTOFF_SCORE_FILE_OPTION = "cos";
175 final static private String NOT_IGNORE_DUFS_OPTION = "dufs";
176 final static private String MAX_FS_E_VALUE_OPTION = "fs_e";
177 final static private String MAX_I_E_VALUE_OPTION = "ie";
178 final static private String MAX_ALLOWED_OVERLAP_OPTION = "mo";
179 final static private String NO_ENGULFING_OVERLAP_OPTION = "no_eo";
180 final static private String IGNORE_COMBINATION_WITH_SAME_OPTION = "ignore_self_comb";
181 final static private String PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION = "dc_regain_stats";
182 final static private String DA_ANALYSIS_OPTION = "da_analyis";
183 final static private String USE_LAST_IN_FITCH_OPTION = "last";
184 public final static String PAIRWISE_DOMAIN_COMPARISONS_PREFIX = "pwc_";
185 final static private String PAIRWISE_DOMAIN_COMPARISONS_OPTION = "pwc";
186 final static private String OUTPUT_FILE_OPTION = "o";
187 final static private String PFAM_TO_GO_FILE_USE_OPTION = "p2g";
188 final static private String GO_OBO_FILE_USE_OPTION = "obo";
189 final static private String GO_NAMESPACE_LIMIT_OPTION = "go_namespace";
190 final static private String GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION = "molecular_function";
191 final static private String GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS = "biological_process";
192 final static private String GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT = "cellular_component";
193 final static private String SECONDARY_FEATURES_PARSIMONY_MAP_FILE = "secondary";
194 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED = "simple_tab";
195 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML = "simple_html";
196 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML = "detailed_html";
197 final static private String DOMAIN_SIMILARITY_PRINT_OPTION = "ds_output";
198 private static final PRINT_OPTION DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT = DomainSimilarity.PRINT_OPTION.HTML;
199 final static private String IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION = "ignore_singlet_domains";
200 final static private String IGNORE_VIRAL_IDS = "ignore_viral_ids";
201 final static private boolean IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT = false;
202 final static private String IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION = "ignore_species_specific_domains";
203 final static private boolean IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT = false;
204 final static private String MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score.pwd";
205 final static private String MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains.pwd";
206 final static private String MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations.pwd";
207 final static private String NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score_NJ"
208 + ForesterConstants.PHYLO_XML_SUFFIX;
209 final static private String NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains_NJ"
210 + ForesterConstants.PHYLO_XML_SUFFIX;
211 final static private String NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations_NJ"
212 + ForesterConstants.PHYLO_XML_SUFFIX;
213 final static private String FILTER_POSITIVE_OPTION = "pos_filter";
214 final static private String FILTER_NEGATIVE_OPTION = "neg_filter";
215 final static private String FILTER_NEGATIVE_DOMAINS_OPTION = "neg_dom_filter";
216 final static private String INPUT_GENOMES_FILE_OPTION = "genomes";
217 final static private String INPUT_SPECIES_TREE_OPTION = "species_tree";
218 final static private String SEQ_EXTRACT_OPTION = "prot_extract";
219 final static private String PRG_VERSION = "2.405";
220 final static private String PRG_DATE = "170317";
221 final static private String E_MAIL = "czmasek@burnham.org";
222 final static private String WWW = "https://sites.google.com/site/cmzmasek/home/software/forester/surfacing";
223 final static private boolean IGNORE_DUFS_DEFAULT = true;
224 final static private boolean IGNORE_COMBINATION_WITH_SAME_DEFAULLT = false;
225 final static private double MAX_E_VALUE_DEFAULT = -1;
226 public final static int MAX_ALLOWED_OVERLAP_DEFAULT = -1;
227 private static final String RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION = "random_seed";
228 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS = "consider_bdc_direction";
229 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY = "consider_bdc_adj";
230 public static final String SEQ_EXTRACT_SUFFIX = ".prot";
231 public static final String PLUS_MINUS_ANALYSIS_OPTION = "plus_minus";
232 public static final String PLUS_MINUS_DOM_SUFFIX = "_plus_minus_dom.txt";
233 public static final String PLUS_MINUS_DOM_SUFFIX_HTML = "_plus_minus_dom.html";
234 public static final String PLUS_MINUS_DC_SUFFIX_HTML = "_plus_minus_dc.html";
235 public static final int PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT = 0;
236 public static final double PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT = 1.0;
237 public static final String PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_all.txt";
238 public static final String PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_passing.txt";
239 private static final String OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS = "all_prot";
240 final static private String OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION = "all_prot_e";
241 public static final boolean VERBOSE = false;
242 private static final String OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_gains_counts";
243 private static final String OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_losses_counts";
244 private static final String DOMAIN_LENGTHS_ANALYSIS_SUFFIX = "_domain_lengths_analysis";
245 private static final String PERFORM_DOMAIN_LENGTH_ANALYSIS_OPTION = "dla";
246 public static final String ALL_PFAMS_ENCOUNTERED_SUFFIX = "_all_encountered_pfams";
247 public static final String ALL_PFAMS_ENCOUNTERED_WITH_GO_ANNOTATION_SUFFIX = "_all_encountered_pfams_with_go_annotation";
248 public static final String ENCOUNTERED_PFAMS_SUMMARY_SUFFIX = "_encountered_pfams_summary";
249 public static final String ALL_PFAMS_GAINED_AS_DOMAINS_SUFFIX = "_all_pfams_gained_as_domains";
250 public static final String ALL_PFAMS_LOST_AS_DOMAINS_SUFFIX = "_all_pfams_lost_as_domains";
251 public static final String ALL_PFAMS_GAINED_AS_DC_SUFFIX = "_all_pfams_gained_as_dc";
252 public static final String ALL_PFAMS_LOST_AS_DC_SUFFIX = "_all_pfams_lost_as_dc";
253 public static final String BASE_DIRECTORY_PER_NODE_DOMAIN_GAIN_LOSS_FILES = "PER_NODE_EVENTS";
254 public static final String BASE_DIRECTORY_PER_SUBTREE_DOMAIN_GAIN_LOSS_FILES = "PER_SUBTREE_EVENTS";
255 public static final String D_PROMISCUITY_FILE_SUFFIX = "_domain_promiscuities";
256 private static final String LOG_FILE_SUFFIX = "_log.txt";
257 private static final String DATA_FILE_SUFFIX = "_domain_combination_data.txt";
258 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";
259 private static final String WRITE_TO_NEXUS_OPTION = "nexus";
260 private static final String PERFORM_DC_FITCH = "dc_pars";
261 private static final INDIVIDUAL_SCORE_CUTOFF INDIVIDUAL_SCORE_CUTOFF_DEFAULT = INDIVIDUAL_SCORE_CUTOFF.FULL_SEQUENCE; //TODO look at me! change?
262 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts.txt";
263 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists.txt";
264 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping.txt";
265 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";
266 public static final String LIMIT_SPEC_FOR_PROT_EX = null; // e.g. "HUMAN"; set to null for not using this feature (default).
267 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH_MAPPED = "_dc_MAPPED_secondary_features_fitch"
268 + ForesterConstants.PHYLO_XML_SUFFIX;
269 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts_MAPPED.txt";
270 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_MAPPED.txt";
271 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";
272 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";
273 private static final boolean CALC_SIMILARITY_SCORES = false;
275 @SuppressWarnings( "unchecked")
276 public static void main( final String args[] ) {
277 final long start_time = new Date().getTime();
278 // final StringBuffer log = new StringBuffer();
279 final StringBuilder html_desc = new StringBuilder();
280 ForesterUtil.printProgramInformation( surfacing.PRG_NAME,
281 surfacing.PRG_VERSION,
285 final String nl = ForesterUtil.LINE_SEPARATOR;
286 html_desc.append( "<table>" + nl );
287 html_desc.append( "<tr><td>Produced by:</td><td>" + surfacing.PRG_NAME + "</td></tr>" + nl );
288 html_desc.append( "<tr><td>Version:</td><td>" + surfacing.PRG_VERSION + "</td></tr>" + nl );
289 html_desc.append( "<tr><td>Release Date:</td><td>" + surfacing.PRG_DATE + "</td></tr>" + nl );
290 html_desc.append( "<tr><td>Contact:</td><td>" + surfacing.E_MAIL + "</td></tr>" + nl );
291 html_desc.append( "<tr><td>WWW:</td><td>" + surfacing.WWW + "</td></tr>" + nl );
292 CommandLineArguments cla = null;
294 cla = new CommandLineArguments( args );
296 catch ( final Exception e ) {
297 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
299 if ( cla.isOptionSet( surfacing.HELP_OPTION_1 ) || cla.isOptionSet( surfacing.HELP_OPTION_2 ) ) {
300 surfacing.printHelp();
303 if ( ( args.length < 1 ) ) {
304 surfacing.printHelp();
307 final List<String> allowed_options = new ArrayList<String>();
308 allowed_options.add( surfacing.NOT_IGNORE_DUFS_OPTION );
309 allowed_options.add( surfacing.MAX_FS_E_VALUE_OPTION );
310 allowed_options.add( surfacing.MAX_I_E_VALUE_OPTION );
311 allowed_options.add( surfacing.DETAILEDNESS_OPTION );
312 allowed_options.add( surfacing.OUTPUT_FILE_OPTION );
313 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_OPTION );
314 allowed_options.add( surfacing.SPECIES_MATRIX_OPTION );
315 allowed_options.add( surfacing.SCORING_OPTION );
316 allowed_options.add( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
317 allowed_options.add( surfacing.NO_ENGULFING_OVERLAP_OPTION );
318 allowed_options.add( surfacing.DOMAIN_COUNT_SORT_OPTION );
319 allowed_options.add( surfacing.CUTOFF_SCORE_FILE_OPTION );
320 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION );
321 allowed_options.add( surfacing.OUTPUT_DIR_OPTION );
322 allowed_options.add( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION );
323 allowed_options.add( surfacing.PFAM_TO_GO_FILE_USE_OPTION );
324 allowed_options.add( surfacing.GO_OBO_FILE_USE_OPTION );
325 allowed_options.add( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION );
326 allowed_options.add( surfacing.GO_NAMESPACE_LIMIT_OPTION );
327 allowed_options.add( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
328 allowed_options.add( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION );
329 allowed_options.add( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS );
330 allowed_options.add( INPUT_SPECIES_TREE_OPTION );
331 allowed_options.add( FILTER_POSITIVE_OPTION );
332 allowed_options.add( FILTER_NEGATIVE_OPTION );
333 allowed_options.add( INPUT_GENOMES_FILE_OPTION );
334 allowed_options.add( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
335 allowed_options.add( FILTER_NEGATIVE_DOMAINS_OPTION );
336 allowed_options.add( IGNORE_VIRAL_IDS );
337 allowed_options.add( SEQ_EXTRACT_OPTION );
338 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
339 allowed_options.add( SECONDARY_FEATURES_PARSIMONY_MAP_FILE );
340 allowed_options.add( PLUS_MINUS_ANALYSIS_OPTION );
341 allowed_options.add( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS );
342 allowed_options.add( DOMAIN_COMBINITONS_COUNTS_OUTPUT_OPTION );
343 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS );
344 allowed_options.add( CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY );
345 allowed_options.add( WRITE_TO_NEXUS_OPTION );
346 allowed_options.add( PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION );
347 allowed_options.add( DA_ANALYSIS_OPTION );
348 allowed_options.add( USE_LAST_IN_FITCH_OPTION );
349 allowed_options.add( PERFORM_DC_FITCH );
350 allowed_options.add( PERFORM_DOMAIN_LENGTH_ANALYSIS_OPTION );
351 boolean ignore_dufs = surfacing.IGNORE_DUFS_DEFAULT;
352 boolean ignore_combination_with_same = surfacing.IGNORE_COMBINATION_WITH_SAME_DEFAULLT;
353 double fs_e_value_max = surfacing.MAX_E_VALUE_DEFAULT;
354 double ie_value_max = surfacing.MAX_E_VALUE_DEFAULT;
355 int max_allowed_overlap = surfacing.MAX_ALLOWED_OVERLAP_DEFAULT;
356 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
357 if ( dissallowed_options.length() > 0 ) {
358 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown option(s): " + dissallowed_options );
360 boolean use_last_in_fitch_parsimony = false;
361 if ( cla.isOptionSet( USE_LAST_IN_FITCH_OPTION ) ) {
362 use_last_in_fitch_parsimony = true;
364 boolean write_to_nexus = false;
365 if ( cla.isOptionSet( WRITE_TO_NEXUS_OPTION ) ) {
366 write_to_nexus = true;
368 boolean perform_dc_fich = false;
369 if ( cla.isOptionSet( PERFORM_DC_FITCH ) ) {
370 perform_dc_fich = true;
372 boolean perform_dc_regain_proteins_stats = false;
373 if ( cla.isOptionSet( PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION ) ) {
374 perform_dc_regain_proteins_stats = true;
376 boolean da_analysis = false;
377 if ( cla.isOptionSet( DA_ANALYSIS_OPTION ) ) {
380 boolean output_binary_domain_combinationsfor_graph_analysis = false;
381 if ( cla.isOptionSet( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS ) ) {
382 output_binary_domain_combinationsfor_graph_analysis = true;
384 boolean output_binary_domain_combinationsfor_counts = false;
385 if ( cla.isOptionSet( DOMAIN_COMBINITONS_COUNTS_OUTPUT_OPTION ) ) {
386 output_binary_domain_combinationsfor_counts = true;
388 if ( cla.isOptionSet( surfacing.MAX_FS_E_VALUE_OPTION ) ) {
390 fs_e_value_max = cla.getOptionValueAsDouble( surfacing.MAX_FS_E_VALUE_OPTION );
392 catch ( final Exception e ) {
393 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for E-value maximum" );
396 if ( cla.isOptionSet( surfacing.MAX_I_E_VALUE_OPTION ) ) {
398 ie_value_max = cla.getOptionValueAsDouble( surfacing.MAX_I_E_VALUE_OPTION );
400 catch ( final Exception e ) {
401 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for E-value maximum" );
404 if ( cla.isOptionSet( surfacing.MAX_ALLOWED_OVERLAP_OPTION ) ) {
406 max_allowed_overlap = cla.getOptionValueAsInt( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
408 catch ( final Exception e ) {
409 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for maximal allowed domain overlap" );
412 boolean no_engulfing_overlaps = false;
413 if ( cla.isOptionSet( surfacing.NO_ENGULFING_OVERLAP_OPTION ) ) {
414 no_engulfing_overlaps = true;
416 boolean ignore_virus_like_ids = false;
417 if ( cla.isOptionSet( surfacing.IGNORE_VIRAL_IDS ) ) {
418 ignore_virus_like_ids = true;
420 if ( cla.isOptionSet( surfacing.NOT_IGNORE_DUFS_OPTION ) ) {
423 if ( cla.isOptionSet( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION ) ) {
424 ignore_combination_with_same = true;
426 boolean domain_length_analysis = false;
427 if ( cla.isOptionSet( surfacing.PERFORM_DOMAIN_LENGTH_ANALYSIS_OPTION ) ) {
428 domain_length_analysis = true;
430 boolean ignore_domains_without_combs_in_all_spec = IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT;
431 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION ) ) {
432 ignore_domains_without_combs_in_all_spec = true;
434 boolean ignore_species_specific_domains = IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT;
435 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION ) ) {
436 ignore_species_specific_domains = true;
438 if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
439 ForesterUtil.fatalError( surfacing.PRG_NAME,
440 "no input species tree file given: " + surfacing.INPUT_SPECIES_TREE_OPTION
443 File output_file = null;
444 if ( cla.isOptionSet( surfacing.OUTPUT_FILE_OPTION ) ) {
445 if ( !cla.isOptionValueSet( surfacing.OUTPUT_FILE_OPTION ) ) {
446 ForesterUtil.fatalError( surfacing.PRG_NAME,
447 "no value for domain combinations similarities output file: -"
448 + surfacing.OUTPUT_FILE_OPTION + "=<file>" );
450 output_file = new File( cla.getOptionValue( surfacing.OUTPUT_FILE_OPTION ) );
451 SurfacingUtil.checkForOutputFileWriteability( output_file );
453 File cutoff_scores_file = null;
454 Map<String, Double> individual_score_cutoffs = null;
455 if ( cla.isOptionSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
456 if ( !cla.isOptionValueSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
457 ForesterUtil.fatalError( surfacing.PRG_NAME,
458 "no value for individual domain score cutoffs file: -"
459 + surfacing.CUTOFF_SCORE_FILE_OPTION + "=<file>" );
461 cutoff_scores_file = new File( cla.getOptionValue( surfacing.CUTOFF_SCORE_FILE_OPTION ) );
462 final String error = ForesterUtil.isReadableFile( cutoff_scores_file );
463 if ( !ForesterUtil.isEmpty( error ) ) {
464 ForesterUtil.fatalError( surfacing.PRG_NAME,
465 "cannot read individual domain score cutoffs file: " + error );
468 final BasicTable<String> scores_table = BasicTableParser.parse( cutoff_scores_file, ' ' );
469 individual_score_cutoffs = scores_table.getColumnsAsMapDouble( 0, 1 );
471 catch ( final IOException e ) {
472 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from individual score cutoffs file: " + e );
475 BinaryDomainCombination.DomainCombinationType dc_type = BinaryDomainCombination.DomainCombinationType.BASIC;
476 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS ) ) {
477 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED;
479 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY ) ) {
480 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT;
483 if ( cla.isOptionSet( surfacing.OUTPUT_DIR_OPTION ) ) {
484 if ( !cla.isOptionValueSet( surfacing.OUTPUT_DIR_OPTION ) ) {
485 ForesterUtil.fatalError( surfacing.PRG_NAME,
486 "no value for output directory: -" + surfacing.OUTPUT_DIR_OPTION + "=<dir>" );
488 out_dir = new File( cla.getOptionValue( surfacing.OUTPUT_DIR_OPTION ) );
489 if ( out_dir.exists() && ( out_dir.listFiles().length > 0 ) ) {
490 ForesterUtil.fatalError( surfacing.PRG_NAME, "\"" + out_dir + "\" aready exists and is not empty" );
492 if ( !out_dir.exists() ) {
493 final boolean success = out_dir.mkdir();
494 if ( !success || !out_dir.exists() ) {
495 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to create \"" + out_dir + "\"" );
498 if ( !out_dir.canWrite() ) {
499 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot write to \"" + out_dir + "\"" );
502 File positive_filter_file = null;
503 File negative_filter_file = null;
504 File negative_domains_filter_file = null;
505 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION )
506 && cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
507 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use both negative and positive protein filter" );
509 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION )
510 && ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION )
511 || cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) ) {
513 .fatalError( surfacing.PRG_NAME,
514 "attempt to use both negative or positive protein filter together wirh a negative domains filter" );
516 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
517 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
519 .fatalError( surfacing.PRG_NAME,
520 "no value for negative filter: -" + surfacing.FILTER_NEGATIVE_OPTION + "=<file>" );
522 negative_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_OPTION ) );
523 final String msg = ForesterUtil.isReadableFile( negative_filter_file );
524 if ( !ForesterUtil.isEmpty( msg ) ) {
525 ForesterUtil.fatalError( surfacing.PRG_NAME,
526 "can not read from \"" + negative_filter_file + "\": " + msg );
529 else if ( cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
530 if ( !cla.isOptionValueSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
532 .fatalError( surfacing.PRG_NAME,
533 "no value for positive filter: -" + surfacing.FILTER_POSITIVE_OPTION + "=<file>" );
535 positive_filter_file = new File( cla.getOptionValue( surfacing.FILTER_POSITIVE_OPTION ) );
536 final String msg = ForesterUtil.isReadableFile( positive_filter_file );
537 if ( !ForesterUtil.isEmpty( msg ) ) {
538 ForesterUtil.fatalError( surfacing.PRG_NAME,
539 "can not read from \"" + positive_filter_file + "\": " + msg );
542 else if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
543 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
544 ForesterUtil.fatalError( surfacing.PRG_NAME,
545 "no value for negative domains filter: -"
546 + surfacing.FILTER_NEGATIVE_DOMAINS_OPTION + "=<file>" );
548 negative_domains_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) );
549 final String msg = ForesterUtil.isReadableFile( negative_domains_filter_file );
550 if ( !ForesterUtil.isEmpty( msg ) ) {
551 ForesterUtil.fatalError( surfacing.PRG_NAME,
552 "can not read from \"" + negative_domains_filter_file + "\": " + msg );
555 final List<String> plus_minus_analysis_high_copy_base_species = new ArrayList<String>();
556 final List<String> plus_minus_analysis_high_copy_target_species = new ArrayList<String>();
557 final List<String> plus_minus_analysis_high_low_copy_species = new ArrayList<String>();
558 final List<Object> plus_minus_analysis_numbers = new ArrayList<Object>();
559 SurfacingUtil.processPlusMinusAnalysisOption( cla,
560 plus_minus_analysis_high_copy_base_species,
561 plus_minus_analysis_high_copy_target_species,
562 plus_minus_analysis_high_low_copy_species,
563 plus_minus_analysis_numbers );
564 File input_genomes_file = null;
565 if ( cla.isOptionSet( surfacing.INPUT_GENOMES_FILE_OPTION ) ) {
566 if ( !cla.isOptionValueSet( surfacing.INPUT_GENOMES_FILE_OPTION ) ) {
567 ForesterUtil.fatalError( surfacing.PRG_NAME,
568 "no value for input genomes file: -" + surfacing.INPUT_GENOMES_FILE_OPTION
571 input_genomes_file = new File( cla.getOptionValue( surfacing.INPUT_GENOMES_FILE_OPTION ) );
572 final String msg = ForesterUtil.isReadableFile( input_genomes_file );
573 if ( !ForesterUtil.isEmpty( msg ) ) {
574 ForesterUtil.fatalError( surfacing.PRG_NAME,
575 "can not read from \"" + input_genomes_file + "\": " + msg );
580 .fatalError( surfacing.PRG_NAME,
581 "no input genomes file given: " + surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>" );
583 DomainSimilarity.DomainSimilarityScoring scoring = SCORING_DEFAULT;
584 if ( cla.isOptionSet( surfacing.SCORING_OPTION ) ) {
585 if ( !cla.isOptionValueSet( surfacing.SCORING_OPTION ) ) {
587 .fatalError( surfacing.PRG_NAME,
588 "no value for scoring method for domain combinations similarity calculation: -"
589 + surfacing.SCORING_OPTION + "=<" + surfacing.SCORING_DOMAIN_COUNT_BASED
590 + "|" + surfacing.SCORING_PROTEIN_COUNT_BASED + "|"
591 + surfacing.SCORING_COMBINATION_BASED + ">\"" );
593 final String scoring_str = cla.getOptionValue( surfacing.SCORING_OPTION );
594 if ( scoring_str.equals( surfacing.SCORING_DOMAIN_COUNT_BASED ) ) {
595 scoring = DomainSimilarity.DomainSimilarityScoring.DOMAINS;
597 else if ( scoring_str.equals( surfacing.SCORING_COMBINATION_BASED ) ) {
598 scoring = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
600 else if ( scoring_str.equals( surfacing.SCORING_PROTEIN_COUNT_BASED ) ) {
601 scoring = DomainSimilarity.DomainSimilarityScoring.PROTEINS;
605 .fatalError( surfacing.PRG_NAME,
606 "unknown value \"" + scoring_str
607 + "\" for scoring method for domain combinations similarity calculation: \"-"
608 + surfacing.SCORING_OPTION + "=<" + surfacing.SCORING_DOMAIN_COUNT_BASED
609 + "|" + surfacing.SCORING_PROTEIN_COUNT_BASED + "|"
610 + surfacing.SCORING_COMBINATION_BASED + ">\"" );
613 boolean sort_by_species_count_first = false;
614 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION ) ) {
615 sort_by_species_count_first = true;
617 boolean species_matrix = false;
618 if ( cla.isOptionSet( surfacing.SPECIES_MATRIX_OPTION ) ) {
619 species_matrix = true;
621 boolean output_protein_lists_for_all_domains = false;
622 double output_list_of_all_proteins_per_domain_e_value_max = -1;
623 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS ) ) {
624 output_protein_lists_for_all_domains = true;
625 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION ) ) {
627 output_list_of_all_proteins_per_domain_e_value_max = cla
628 .getOptionValueAsDouble( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
630 catch ( final Exception e ) {
631 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for per domain E-value maximum" );
635 Detailedness detailedness = DETAILEDNESS_DEFAULT;
636 if ( cla.isOptionSet( surfacing.DETAILEDNESS_OPTION ) ) {
637 if ( !cla.isOptionValueSet( surfacing.DETAILEDNESS_OPTION ) ) {
638 ForesterUtil.fatalError( surfacing.PRG_NAME,
639 "no value for -" + surfacing.DETAILEDNESS_OPTION + "=<"
640 + surfacing.DETAILEDNESS_BASIC + "|" + surfacing.DETAILEDNESS_LIST_IDS
641 + "|" + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
643 final String detness = cla.getOptionValue( surfacing.DETAILEDNESS_OPTION ).toLowerCase();
644 if ( detness.equals( surfacing.DETAILEDNESS_BASIC ) ) {
645 detailedness = DomainSimilarityCalculator.Detailedness.BASIC;
647 else if ( detness.equals( surfacing.DETAILEDNESS_LIST_IDS ) ) {
648 detailedness = DomainSimilarityCalculator.Detailedness.LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES;
650 else if ( detness.equals( surfacing.DETAILEDNESS_PUNCTILIOUS ) ) {
651 detailedness = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
654 ForesterUtil.fatalError( surfacing.PRG_NAME,
655 "unknown value \"" + detness + "\" for detailedness: \"-"
656 + surfacing.DETAILEDNESS_OPTION + "=<" + surfacing.DETAILEDNESS_BASIC
657 + "|" + surfacing.DETAILEDNESS_LIST_IDS + "|"
658 + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
661 String automated_pairwise_comparison_suffix = null;
662 boolean perform_pwc = false;
663 boolean write_pwc_files = false;
664 if ( cla.isOptionSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
666 if ( !cla.isOptionValueSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
667 write_pwc_files = false;
670 write_pwc_files = true;
671 automated_pairwise_comparison_suffix = "_"
672 + cla.getOptionValue( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
675 String query_domain_ids = null;
676 if ( cla.isOptionSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
677 if ( !cla.isOptionValueSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
679 .fatalError( surfacing.PRG_NAME,
680 "no domain ids given for sequences with given domains to be extracted : -"
681 + surfacing.SEQ_EXTRACT_OPTION
682 + "=<ordered domain sequences, domain ids separated by '~', sequences separated by '#'>" );
684 query_domain_ids = cla.getOptionValue( surfacing.SEQ_EXTRACT_OPTION );
686 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field = DOMAIN_SORT_FILD_DEFAULT;
687 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field_for_automated_pwc = DOMAIN_SORT_FILD_DEFAULT;
688 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
689 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
690 ForesterUtil.fatalError( surfacing.PRG_NAME,
691 "no value for domain combinations similarities sorting: -"
692 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<"
693 + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
694 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|"
695 + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
696 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|"
697 + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
698 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
699 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|"
700 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|"
701 + surfacing.DOMAIN_SIMILARITY_SORT_SD + ">\"" );
703 final String sort_str = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ).toLowerCase();
704 if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ALPHA ) ) {
705 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
706 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
708 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MAX ) ) {
709 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX;
710 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
712 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MIN ) ) {
713 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MIN;
714 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
716 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MEAN ) ) {
717 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MEAN;
718 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MEAN;
720 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT ) ) {
721 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SPECIES_COUNT;
722 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
724 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SD ) ) {
725 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SD;
726 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
728 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_DIFF ) ) {
729 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
730 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
732 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF ) ) {
733 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
734 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
736 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF ) ) {
737 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
738 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
741 ForesterUtil.fatalError( surfacing.PRG_NAME,
742 "unknown value \"" + sort_str
743 + "\" for domain combinations similarities sorting: \"-"
744 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<"
745 + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
746 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|"
747 + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
748 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|"
749 + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
750 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
751 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|" + "|"
752 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|"
753 + surfacing.DOMAIN_SIMILARITY_SORT_SD + ">\"" );
756 DomainSimilarity.PRINT_OPTION domain_similarity_print_option = DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT;
757 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
758 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
760 .fatalError( surfacing.PRG_NAME,
761 "no value for print option: -"
762 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
763 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
764 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
766 final String sort = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ).toLowerCase();
767 if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML ) ) {
768 domain_similarity_print_option = DomainSimilarity.PRINT_OPTION.HTML;
770 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML ) ) {
771 ForesterUtil.fatalError( surfacing.PRG_NAME, "simple HTML output not implemented yet :(" );
773 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED ) ) {
774 domain_similarity_print_option = DomainSimilarity.PRINT_OPTION.SIMPLE_TAB_DELIMITED;
778 .fatalError( surfacing.PRG_NAME,
779 "unknown value \"" + sort + "\" for print option: -"
780 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
781 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
782 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
785 GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order = DOMAINS_SORT_ORDER_DEFAULT;
786 if ( cla.isOptionSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
787 if ( !cla.isOptionValueSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
788 ForesterUtil.fatalError( surfacing.PRG_NAME,
789 "no value for sorting of domain counts: -" + surfacing.DOMAIN_COUNT_SORT_OPTION
790 + "=<" + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|"
791 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
792 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
793 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
795 final String sort = cla.getOptionValue( surfacing.DOMAIN_COUNT_SORT_OPTION ).toLowerCase();
796 if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_ALPHA ) ) {
797 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
799 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT ) ) {
800 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_COUNT;
802 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT ) ) {
803 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_PROTEINS_COUNT;
805 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT ) ) {
806 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.COMBINATIONS_COUNT;
809 ForesterUtil.fatalError( surfacing.PRG_NAME,
810 "unknown value \"" + sort + "\" for sorting of domain counts: \"-"
811 + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<"
812 + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|"
813 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
814 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
815 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
818 final String[][] input_file_properties = SurfacingUtil.processInputGenomesFile( input_genomes_file );
819 final int number_of_genomes = input_file_properties.length;
820 if ( number_of_genomes < 2 ) {
821 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot analyze less than two files" );
823 if ( ( number_of_genomes < 3 ) && perform_pwc ) {
825 .fatalError( surfacing.PRG_NAME,
826 "cannot use : -" + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
827 + "=<suffix> to turn on pairwise analyses with less than three input files" );
829 SurfacingUtil.checkWriteabilityForPairwiseComparisons( domain_similarity_print_option,
830 input_file_properties,
831 automated_pairwise_comparison_suffix,
833 for( int i = 0; i < number_of_genomes; i++ ) {
834 File dcc_outfile = new File( input_file_properties[ i ][ 1 ]
835 + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
836 if ( out_dir != null ) {
837 dcc_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + dcc_outfile );
839 SurfacingUtil.checkForOutputFileWriteability( dcc_outfile );
841 File pfam_to_go_file = new File( "pfam2go.txt" );
842 if ( cla.isOptionSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
843 if ( !cla.isOptionValueSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
844 ForesterUtil.fatalError( surfacing.PRG_NAME,
845 "no value for Pfam to GO mapping file: -"
846 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>" );
848 pfam_to_go_file = new File( cla.getOptionValue( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) );
850 final String error1 = ForesterUtil.isReadableFile( pfam_to_go_file );
851 if ( !ForesterUtil.isEmpty( error1 ) ) {
852 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read Pfam to GO mapping file: " + error1 );
854 Map<String, List<GoId>> domain_id_to_go_ids_map = null;
855 int domain_id_to_go_ids_count = 0;
857 final PfamToGoParser parser = new PfamToGoParser( pfam_to_go_file );
858 final List<PfamToGoMapping> pfam_to_go_mappings = parser.parse();
859 domain_id_to_go_ids_map = SurfacingUtil.createDomainIdToGoIdMap( pfam_to_go_mappings );
860 if ( parser.getMappingCount() < domain_id_to_go_ids_map.size() ) {
861 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME,
862 "parser.getMappingCount() < domain_id_to_go_ids_map.size()" );
864 domain_id_to_go_ids_count = parser.getMappingCount();
866 catch ( final IOException e ) {
867 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from Pfam to GO mapping file: " + e );
869 File go_obo_file = new File( "go.obo" );
870 if ( cla.isOptionSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
871 if ( !cla.isOptionValueSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
872 ForesterUtil.fatalError( surfacing.PRG_NAME,
873 "no value for GO OBO file: -" + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>" );
875 go_obo_file = new File( cla.getOptionValue( surfacing.GO_OBO_FILE_USE_OPTION ) );
877 final String error2 = ForesterUtil.isReadableFile( go_obo_file );
878 if ( !ForesterUtil.isEmpty( error2 ) ) {
879 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read GO OBO file: " + error2 );
881 List<GoTerm> go_terms = null;
883 final OBOparser parser = new OBOparser( go_obo_file, OBOparser.ReturnType.BASIC_GO_TERM );
884 go_terms = parser.parse();
885 if ( parser.getGoTermCount() != go_terms.size() ) {
886 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "parser.getGoTermCount() != go_terms.size()" );
889 catch ( final IOException e ) {
890 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from GO OBO file: " + e );
892 Map<GoId, GoTerm> go_id_to_term_map = null;
893 if ( ( ( domain_id_to_go_ids_map != null ) && ( domain_id_to_go_ids_map.size() > 0 ) )
894 && ( ( go_terms != null ) && ( go_terms.size() > 0 ) ) ) {
895 go_id_to_term_map = GoUtils.createGoIdToGoTermMap( go_terms );
897 GoNameSpace go_namespace_limit = null;
898 if ( cla.isOptionSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
899 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
900 ForesterUtil.fatalError( surfacing.PRG_NAME,
901 "cannot use GO namespace limit (-" + surfacing.GO_NAMESPACE_LIMIT_OPTION
902 + "=<namespace>) without Pfam to GO mapping file ("
903 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>) and GO OBO file (-"
904 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
906 if ( !cla.isOptionValueSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
907 ForesterUtil.fatalError( surfacing.PRG_NAME,
908 "no value for GO namespace limit: \"-" + surfacing.GO_NAMESPACE_LIMIT_OPTION
909 + "=<" + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
910 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
911 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
913 final String go_namespace_limit_str = cla.getOptionValue( surfacing.GO_NAMESPACE_LIMIT_OPTION )
915 if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION ) ) {
916 go_namespace_limit = GoNameSpace.createMolecularFunction();
918 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS ) ) {
919 go_namespace_limit = GoNameSpace.createBiologicalProcess();
921 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT ) ) {
922 go_namespace_limit = GoNameSpace.createCellularComponent();
925 ForesterUtil.fatalError( surfacing.PRG_NAME,
926 "unknown value \"" + go_namespace_limit_str + "\" for GO namespace limit: \"-"
927 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
928 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
929 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
930 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
933 if ( ( domain_similarity_sort_field == DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE )
934 && ( number_of_genomes > 2 ) ) {
935 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
937 File[] intree_files = null;
938 Phylogeny[] intrees = null;
939 if ( cla.isOptionSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
940 if ( number_of_genomes < 3 ) {
941 ForesterUtil.fatalError( surfacing.PRG_NAME,
942 "cannot infer gains and losses on input species trees (-"
943 + surfacing.INPUT_SPECIES_TREE_OPTION + " without pairwise analyses ("
944 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
945 + "=<suffix for pairwise comparison output files>)" );
947 if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
948 ForesterUtil.fatalError( surfacing.PRG_NAME,
949 "no value for input tree: -" + surfacing.INPUT_SPECIES_TREE_OPTION
950 + "=<tree file in phyloXML format>" );
952 final String intrees_str = cla.getOptionValue( surfacing.INPUT_SPECIES_TREE_OPTION );
953 if ( intrees_str.indexOf( "#" ) > 0 ) {
954 final String[] intrees_strs = intrees_str.split( "#" );
955 intree_files = new File[ intrees_strs.length ];
957 for( final String s : intrees_strs ) {
958 intree_files[ i++ ] = new File( s.trim() );
962 intree_files = new File[ 1 ];
963 intree_files[ 0 ] = new File( intrees_str );
965 intrees = SurfacingUtil.obtainAndPreProcessIntrees( intree_files,
967 input_file_properties );
969 final Phylogeny intree_0_orig = SurfacingUtil.obtainFirstIntree( intree_files[ 0 ] );
970 long random_number_seed_for_fitch_parsimony = 0l;
971 boolean radomize_fitch_parsimony = false;
972 if ( cla.isOptionSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
973 if ( !cla.isOptionValueSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
974 ForesterUtil.fatalError( surfacing.PRG_NAME,
975 "no value for random number seed: -"
976 + surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION + "=<seed>" );
979 random_number_seed_for_fitch_parsimony = cla
980 .getOptionValueAsLong( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
982 catch ( final IOException e ) {
983 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
985 radomize_fitch_parsimony = true;
987 SortedSet<String> filter = null;
988 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
989 || ( negative_domains_filter_file != null ) ) {
990 filter = new TreeSet<String>();
991 if ( positive_filter_file != null ) {
992 SurfacingUtil.processFilter( positive_filter_file, filter );
994 else if ( negative_filter_file != null ) {
995 SurfacingUtil.processFilter( negative_filter_file, filter );
997 else if ( negative_domains_filter_file != null ) {
998 SurfacingUtil.processFilter( negative_domains_filter_file, filter );
1001 Map<String, Set<String>>[] domain_id_to_secondary_features_maps = null;
1002 File[] secondary_features_map_files = null;
1003 final File domain_lengths_analysis_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1004 + DOMAIN_LENGTHS_ANALYSIS_SUFFIX );
1005 if ( domain_length_analysis ) {
1006 SurfacingUtil.checkForOutputFileWriteability( domain_lengths_analysis_outfile );
1008 if ( cla.isOptionSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1009 if ( !cla.isOptionValueSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1010 ForesterUtil.fatalError( surfacing.PRG_NAME,
1011 "no value for secondary features map file: -"
1012 + surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE + "=<file>" );
1014 final String[] secondary_features_map_files_strs = cla
1015 .getOptionValue( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ).split( "#" );
1016 secondary_features_map_files = new File[ secondary_features_map_files_strs.length ];
1017 domain_id_to_secondary_features_maps = new Map[ secondary_features_map_files_strs.length ];
1019 for( final String secondary_features_map_files_str : secondary_features_map_files_strs ) {
1020 secondary_features_map_files[ i ] = new File( secondary_features_map_files_str );
1021 final String error = ForesterUtil.isReadableFile( secondary_features_map_files[ i ] );
1022 if ( !ForesterUtil.isEmpty( error ) ) {
1023 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read secondary features map file: " + error );
1026 domain_id_to_secondary_features_maps[ i ] = SurfacingUtil
1027 .createDomainIdToSecondaryFeaturesMap( secondary_features_map_files[ i ] );
1029 catch ( final IOException e ) {
1030 ForesterUtil.fatalError( surfacing.PRG_NAME,
1031 "cannot read secondary features map file: " + e.getMessage() );
1033 catch ( final Exception e ) {
1034 ForesterUtil.fatalError( surfacing.PRG_NAME,
1035 "problem with contents of features map file ["
1036 + secondary_features_map_files[ i ] + "]: " + e.getMessage() );
1041 if ( out_dir == null ) {
1042 ForesterUtil.fatalError( surfacing.PRG_NAME,
1043 "no output directory indicated (-" + surfacing.OUTPUT_DIR_OPTION + "=<dir>)" );
1045 if ( output_file == null ) {
1046 ForesterUtil.fatalError( surfacing.PRG_NAME,
1047 "no name for (main) output file indicated (-" + surfacing.OUTPUT_FILE_OPTION
1050 if ( ( domain_id_to_go_ids_map == null ) || domain_id_to_go_ids_map.isEmpty() ) {
1051 ForesterUtil.fatalError( surfacing.PRG_NAME,
1052 "no (acceptable) Pfam to GO id mapping file provided ('pfam2go file') (-"
1053 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1055 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1056 ForesterUtil.fatalError( surfacing.PRG_NAME,
1057 "no (acceptable) go id to term mapping file provided ('GO OBO file') (-"
1058 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1060 System.out.println( "Output directory : " + out_dir );
1061 System.out.println( "Input genomes from : " + input_genomes_file );
1062 html_desc.append( "<tr><td>Input genomes from:</td><td>" + input_genomes_file + "</td></tr>" + nl );
1063 if ( positive_filter_file != null ) {
1064 final int filter_size = filter.size();
1065 System.out.println( "Positive protein filter : " + positive_filter_file + " [" + filter_size
1067 html_desc.append( "<tr><td>Positive protein filter:</td><td>" + positive_filter_file + " [" + filter_size
1068 + " domain ids]</td></tr>" + nl );
1070 if ( negative_filter_file != null ) {
1071 final int filter_size = filter.size();
1072 System.out.println( "Negative protein filter : " + negative_filter_file + " [" + filter_size
1074 html_desc.append( "<tr><td>Negative protein filter:</td><td>" + negative_filter_file + " [" + filter_size
1075 + " domain ids]</td></tr>" + nl );
1077 if ( negative_domains_filter_file != null ) {
1078 final int filter_size = filter.size();
1079 System.out.println( "Negative domain filter : " + negative_domains_filter_file + " [" + filter_size
1081 html_desc.append( "<tr><td>Negative domain filter:</td><td>" + negative_domains_filter_file + " ["
1082 + filter_size + " domain ids]</td></tr>" + nl );
1084 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
1086 for( final String s : plus_minus_analysis_high_copy_base_species ) {
1087 plus0 += "+" + s + " ";
1090 for( final String s : plus_minus_analysis_high_copy_target_species ) {
1091 plus1 += "*" + s + " ";
1094 for( final String s : plus_minus_analysis_high_low_copy_species ) {
1095 minus += "-" + s + " ";
1097 System.out.println( "Plus-minus analysis : " + plus1 + "&& " + plus0 + "&& " + minus );
1098 html_desc.append( "<tr><td>Plus-minus analysis:</td><td>" + plus1 + "&& " + plus0 + "&& " + minus
1099 + "</td></tr>" + nl );
1101 if ( cutoff_scores_file != null ) {
1102 System.out.println( "Cutoff scores file : " + cutoff_scores_file );
1103 html_desc.append( "<tr><td>Cutoff scores file:</td><td>" + cutoff_scores_file + "</td></tr>" + nl );
1105 if ( ie_value_max >= 0.0 ) {
1106 System.out.println( "iE-value maximum (incl) : " + ie_value_max );
1107 html_desc.append( "<tr><td>iE-value maximum (inclusive):</td><td>" + ie_value_max + "</td></tr>" + nl );
1109 if ( fs_e_value_max >= 0.0 ) {
1110 System.out.println( "FS E-value maximum (incl) : " + fs_e_value_max );
1111 html_desc.append( "<tr><td>FS E-value maximum (inclusive):</td><td>" + fs_e_value_max + "</td></tr>" + nl );
1113 if ( output_protein_lists_for_all_domains ) {
1114 System.out.println( "Domain E-value max : " + output_list_of_all_proteins_per_domain_e_value_max );
1115 html_desc.append( "<tr><td>Protein lists: E-value maximum per domain (inclusive):</td><td>"
1116 + output_list_of_all_proteins_per_domain_e_value_max + "</td></tr>" + nl );
1118 System.out.println( "Ignore DUFs : " + ignore_dufs );
1119 if ( ignore_virus_like_ids ) {
1120 System.out.println( "Ignore virus like ids : " + ignore_virus_like_ids );
1121 html_desc.append( "<tr><td>Ignore virus, phage, transposition related ids:</td><td>" + ignore_virus_like_ids
1122 + "</td></tr>" + nl );
1124 html_desc.append( "<tr><td>Ignore DUFs:</td><td>" + ignore_dufs + "</td></tr>" + nl );
1125 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1126 System.out.println( "Max allowed domain overlap : " + max_allowed_overlap );
1128 .append( "<tr><td>Max allowed domain overlap:</td><td>" + max_allowed_overlap + "</td></tr>" + nl );
1130 if ( no_engulfing_overlaps ) {
1131 System.out.println( "Ignore engulfed domains : " + no_engulfing_overlaps );
1132 html_desc.append( "<tr><td>Ignore (lower confidence) engulfed domains:</td><td>" + no_engulfing_overlaps
1133 + "</td></tr>" + nl );
1135 System.out.println( "Ignore singlet domains : " + ignore_domains_without_combs_in_all_spec );
1137 .append( "<tr><td>Ignore singlet domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1138 + ignore_domains_without_combs_in_all_spec + "</td></tr>" + nl );
1139 System.out.println( "Ignore species specific doms: " + ignore_species_specific_domains );
1141 .append( "<tr><td>Ignore species specific domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1142 + ignore_species_specific_domains + "</td></tr>" + nl );
1143 System.out.println( "Ignore combination with self: " + ignore_combination_with_same );
1144 html_desc.append( "<tr><td>Ignore combination with self for domain combination similarity analyses:</td><td>"
1145 + ignore_combination_with_same + "</td></tr>" + nl );
1146 System.out.println( "Consider directedness : "
1147 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) );
1148 html_desc.append( "<tr><td>Consider directedness of binary domain combinations:</td><td>"
1149 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) + "</td></tr>" + nl );
1150 if ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) {
1151 System.out.println( "Consider adjacency : "
1152 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) );
1153 html_desc.append( "<tr><td>Consider djacency of binary domain combinations:</td><td>"
1154 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) + "</td></tr>"
1157 System.out.println( "Fitch parsimony of DCs : " + perform_dc_fich );
1158 html_desc.append( "<tr><td>Fitch parsimony of DCs:</td><td>" + perform_dc_fich + "</td></tr>" + nl );
1159 if ( perform_dc_fich ) {
1160 System.out.println( "Use last in Fitch parsimony : " + use_last_in_fitch_parsimony );
1161 html_desc.append( "<tr><td>Use last in Fitch parsimony:</td><td>" + use_last_in_fitch_parsimony
1162 + "</td></tr>" + nl );
1164 System.out.println( "Write to Nexus files : " + write_to_nexus );
1165 html_desc.append( "<tr><td>Write to Nexus files:</td><td>" + write_to_nexus + "</td></tr>" + nl );
1166 if ( perform_dc_fich ) {
1167 System.out.println( "DC regain prot stats : " + perform_dc_regain_proteins_stats );
1168 html_desc.append( "<tr><td>DC regain prot stats:</td><td>" + perform_dc_regain_proteins_stats + "</td></tr>"
1171 System.out.println( "DA analysis : " + da_analysis );
1172 html_desc.append( "<tr><td>DA analysis :</td><td>" + da_analysis + "</td></tr>" + nl );
1173 System.out.print( "Domain counts sort order : " );
1174 html_desc.append( "<tr><td>Domain counts sort order:</td><td>" );
1175 switch ( dc_sort_order ) {
1176 case ALPHABETICAL_KEY_ID:
1177 System.out.println( "alphabetical" );
1178 html_desc.append( "alphabetical" + "</td></tr>" + nl );
1180 case KEY_DOMAIN_COUNT:
1181 System.out.println( "domain count" );
1182 html_desc.append( "domain count" + "</td></tr>" + nl );
1184 case KEY_DOMAIN_PROTEINS_COUNT:
1185 System.out.println( "domain proteins count" );
1186 html_desc.append( "domain proteins count" + "</td></tr>" + nl );
1188 case COMBINATIONS_COUNT:
1189 System.out.println( "domain combinations count" );
1190 html_desc.append( "domain combinations count" + "</td></tr>" + nl );
1193 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for dc sort order" );
1195 if ( domain_id_to_go_ids_map != null ) {
1196 System.out.println( "Pfam to GO mappings from : " + pfam_to_go_file + " [" + domain_id_to_go_ids_count
1198 html_desc.append( "<tr><td>Pfam to GO mappings from:</td><td>" + pfam_to_go_file + " ["
1199 + domain_id_to_go_ids_count + " mappings]" + "</td></tr>" + nl );
1201 if ( go_terms != null ) {
1202 System.out.println( "GO terms from : " + go_obo_file + " [" + go_terms.size() + " terms]" );
1203 html_desc.append( "<tr><td>GO terms from:</td><td>" + go_obo_file + " [" + go_terms.size() + " terms]"
1204 + "</td></tr>" + nl );
1206 if ( go_namespace_limit != null ) {
1207 System.out.println( "Limit GO terms to : " + go_namespace_limit.toString() );
1208 html_desc.append( "<tr><td>Limit GO terms to</td><td>" + go_namespace_limit + "</td></tr>" + nl );
1210 if ( perform_pwc ) {
1211 System.out.println( "Suffix for PWC files : " + automated_pairwise_comparison_suffix );
1212 html_desc.append( "<tr><td>Suffix for PWC files</td><td>" + automated_pairwise_comparison_suffix
1213 + "</td></tr>" + nl );
1215 if ( out_dir != null ) {
1216 System.out.println( "Output directory : " + out_dir );
1218 if ( query_domain_ids != null ) {
1219 System.out.println( "Query domains (ordered) : " + query_domain_ids );
1220 html_desc.append( "<tr><td></td><td>" + query_domain_ids + "</td></tr>" + nl );
1222 System.out.println( "Write similarities to : " + output_file );
1223 System.out.print( " Scoring method : " );
1224 html_desc.append( "<tr><td>Scoring method:</td><td>" );
1225 switch ( scoring ) {
1227 System.out.println( "domain combinations based" );
1228 html_desc.append( "domain combinations based" + "</td></tr>" + nl );
1231 System.out.println( "domain counts based" );
1232 html_desc.append( "domain counts based" + "</td></tr>" + nl );
1235 System.out.println( "domain proteins counts based" );
1236 html_desc.append( "domain proteins counts based" + "</td></tr>" + nl );
1239 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
1241 System.out.print( " Sort by : " );
1242 html_desc.append( "<tr><td>Sort by:</td><td>" );
1243 switch ( domain_similarity_sort_field ) {
1245 System.out.print( "score minimum" );
1246 html_desc.append( "score minimum" );
1249 System.out.print( "score maximum" );
1250 html_desc.append( "score maximum" );
1253 System.out.print( "score mean" );
1254 html_desc.append( "score mean" );
1257 System.out.print( "score standard deviation" );
1258 html_desc.append( "score standard deviation" );
1261 System.out.print( "species number" );
1262 html_desc.append( "species number" );
1265 System.out.print( "alphabetical domain identifier" );
1266 html_desc.append( "alphabetical domain identifier" );
1268 case MAX_DIFFERENCE:
1269 System.out.print( "(maximal) difference" );
1270 html_desc.append( "(maximal) difference" );
1272 case ABS_MAX_COUNTS_DIFFERENCE:
1273 System.out.print( "absolute (maximal) counts difference" );
1274 html_desc.append( "absolute (maximal) counts difference" );
1276 case MAX_COUNTS_DIFFERENCE:
1277 System.out.print( "(maximal) counts difference" );
1278 html_desc.append( "(maximal) counts difference" );
1281 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1283 if ( sort_by_species_count_first ) {
1284 System.out.println( " (sort by species count first)" );
1285 html_desc.append( " (sort by species count first)" );
1288 System.out.println();
1290 html_desc.append( "</td></tr>" + nl );
1291 System.out.print( " Detailedness : " );
1292 switch ( detailedness ) {
1294 System.out.println( "basic" );
1296 case LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES:
1297 System.out.println( "list combining domains for each species" );
1300 System.out.println( "punctilious" );
1303 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for detailedness" );
1305 System.out.print( " Print option : " );
1306 switch ( domain_similarity_print_option ) {
1308 System.out.println( "HTML" );
1310 case SIMPLE_TAB_DELIMITED:
1311 System.out.println( "simple tab delimited" );
1314 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for print option" );
1316 System.out.print( " Species matrix : " + species_matrix );
1317 System.out.println();
1318 final File dc_data_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + DATA_FILE_SUFFIX );
1319 System.out.println( "Domain comb data output : " + dc_data_file );
1320 html_desc.append( "<tr><td>Domain combination data output:</td><td> " + dc_data_file + " </td></tr>" );
1321 System.out.println();
1322 if ( perform_pwc ) {
1323 System.out.println( "Pairwise comparisons: " );
1324 html_desc.append( "<tr><td>Pairwise comparisons:</td><td></td></tr>" );
1325 System.out.print( " Sort by : " );
1326 html_desc.append( "<tr><td>Sort by:</td><td>" );
1327 switch ( domain_similarity_sort_field_for_automated_pwc ) {
1329 System.out.print( "score mean" );
1330 html_desc.append( "score mean" );
1333 System.out.print( "alphabetical domain identifier" );
1334 html_desc.append( "alphabetical domain identifier" );
1336 case MAX_DIFFERENCE:
1337 System.out.print( "difference" );
1338 html_desc.append( "difference" );
1340 case ABS_MAX_COUNTS_DIFFERENCE:
1341 System.out.print( "absolute counts difference" );
1342 html_desc.append( "absolute counts difference" );
1344 case MAX_COUNTS_DIFFERENCE:
1345 System.out.print( "counts difference" );
1346 html_desc.append( "counts difference" );
1349 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME,
1350 "unknown value for sorting for similarities" );
1352 System.out.println();
1353 html_desc.append( "</td></tr>" + nl );
1354 if ( ( intrees != null ) && ( intrees.length > 0 ) ) {
1355 for( final File intree_file : intree_files ) {
1356 html_desc.append( "<tr><td>Intree for gain/loss parsimony analysis:</td><td>" + intree_file
1357 + "</td></tr>" + nl );
1358 System.out.println( " Intree for gain/loss pars.: " + intree_file );
1361 if ( radomize_fitch_parsimony ) {
1362 html_desc.append( "<tr><td> Random number seed for Fitch parsimony analysis:</td><td>"
1363 + random_number_seed_for_fitch_parsimony + "</td></tr>" + nl );
1364 System.out.println( " Random number seed : " + random_number_seed_for_fitch_parsimony );
1366 if ( ( domain_id_to_secondary_features_maps != null )
1367 && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
1368 for( int i = 0; i < secondary_features_map_files.length; i++ ) {
1369 html_desc.append( "<tr><td>Secondary features map file:</td><td>"
1370 + secondary_features_map_files[ i ] + "</td></tr>" + nl );
1371 System.out.println( "Secondary features map file : " + secondary_features_map_files[ i ]
1372 + " [mappings for " + domain_id_to_secondary_features_maps[ i ].size() + " domain ids]" );
1374 System.out.println();
1375 System.out.println( "Domain ids to secondary features map:" );
1376 for( final String domain_id : domain_id_to_secondary_features_maps[ i ].keySet() ) {
1377 System.out.print( domain_id );
1378 System.out.print( " => " );
1379 for( final String sec : domain_id_to_secondary_features_maps[ i ].get( domain_id ) ) {
1380 System.out.print( sec );
1381 System.out.print( " " );
1383 System.out.println();
1388 } // if ( perform_pwc ) {
1389 System.out.println();
1390 html_desc.append( "<tr><td>Command line:</td><td>" + nl + nl + cla.getCommandLineArgsAsString() + nl + nl
1391 + "</td></tr>" + nl );
1392 System.out.println( "Command line : " + cla.getCommandLineArgsAsString() );
1393 BufferedWriter[] query_domains_writer_ary = null;
1394 List<String>[] query_domain_ids_array = null;
1395 if ( query_domain_ids != null ) {
1396 final String[] query_domain_ids_str_array = query_domain_ids.split( "#" );
1397 query_domain_ids_array = new ArrayList[ query_domain_ids_str_array.length ];
1398 query_domains_writer_ary = new BufferedWriter[ query_domain_ids_str_array.length ];
1399 for( int i = 0; i < query_domain_ids_str_array.length; i++ ) {
1400 String query_domain_ids_str = query_domain_ids_str_array[ i ];
1401 final String[] query_domain_ids_str_ary = query_domain_ids_str.split( "~" );
1402 final List<String> query = new ArrayList<String>();
1403 for( final String element : query_domain_ids_str_ary ) {
1404 query.add( element );
1406 query_domain_ids_array[ i ] = query;
1407 query_domain_ids_str = query_domain_ids_str.replace( '~', '_' );
1408 String protein_names_writer_str = query_domain_ids_str + surfacing.SEQ_EXTRACT_SUFFIX;
1409 if ( out_dir != null ) {
1410 protein_names_writer_str = out_dir + ForesterUtil.FILE_SEPARATOR + protein_names_writer_str;
1413 query_domains_writer_ary[ i ] = new BufferedWriter( new FileWriter( protein_names_writer_str ) );
1415 catch ( final IOException e ) {
1416 ForesterUtil.fatalError( surfacing.PRG_NAME,
1417 "Could not open [" + protein_names_writer_str + "]: "
1418 + e.getLocalizedMessage() );
1422 SortedMap<Species, List<Protein>> protein_lists_per_species = null; //This will only be created if needed.
1423 boolean need_protein_lists_per_species = false;
1424 if ( ( plus_minus_analysis_high_copy_base_species.size() > 0 ) || output_protein_lists_for_all_domains
1426 need_protein_lists_per_species = true;
1428 if ( need_protein_lists_per_species ) {
1429 protein_lists_per_species = new TreeMap<Species, List<Protein>>();
1431 List<GenomeWideCombinableDomains> gwcd_list = new ArrayList<GenomeWideCombinableDomains>( number_of_genomes );
1432 final SortedSet<String> all_domains_encountered = new TreeSet<String>();
1433 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered = new TreeSet<BinaryDomainCombination>();
1434 List<BinaryDomainCombination> all_bin_domain_combinations_gained_fitch = null;
1435 List<BinaryDomainCombination> all_bin_domain_combinations_lost_fitch = null;
1436 if ( ( intrees != null ) && ( intrees.length == 1 ) ) {
1437 all_bin_domain_combinations_gained_fitch = new ArrayList<BinaryDomainCombination>();
1438 all_bin_domain_combinations_lost_fitch = new ArrayList<BinaryDomainCombination>();
1440 final File per_genome_domain_promiscuity_statistics_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR
1441 + output_file + D_PROMISCUITY_FILE_SUFFIX );
1442 BufferedWriter per_genome_domain_promiscuity_statistics_writer = null;
1444 per_genome_domain_promiscuity_statistics_writer = new BufferedWriter( new FileWriter( per_genome_domain_promiscuity_statistics_file ) );
1445 per_genome_domain_promiscuity_statistics_writer.write( "Species:\t" );
1446 per_genome_domain_promiscuity_statistics_writer.write( "Mean:\t" );
1447 per_genome_domain_promiscuity_statistics_writer.write( "SD:\t" );
1448 per_genome_domain_promiscuity_statistics_writer.write( "Median:\t" );
1449 per_genome_domain_promiscuity_statistics_writer.write( "Min:\t" );
1450 per_genome_domain_promiscuity_statistics_writer.write( "Max:\t" );
1451 per_genome_domain_promiscuity_statistics_writer.write( "N:\t" );
1452 per_genome_domain_promiscuity_statistics_writer
1453 .write( "Max Promiscuous Domains:" + ForesterUtil.LINE_SEPARATOR );
1455 catch ( final IOException e2 ) {
1456 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1458 final File log_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + LOG_FILE_SUFFIX );
1459 BufferedWriter log_writer = null;
1461 log_writer = new BufferedWriter( new FileWriter( log_file ) );
1463 catch ( final IOException e2 ) {
1464 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1466 BufferedWriter dc_data_writer = null;
1468 dc_data_writer = new BufferedWriter( new FileWriter( dc_data_file ) );
1469 dc_data_writer.write( DATA_FILE_DESC );
1470 dc_data_writer.write( ForesterUtil.LINE_SEPARATOR );
1472 catch ( final IOException e2 ) {
1473 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1475 DescriptiveStatistics protein_coverage_stats = new BasicDescriptiveStatistics();
1476 DescriptiveStatistics all_genomes_domains_per_potein_stats = new BasicDescriptiveStatistics();
1477 final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo = new TreeMap<Integer, Integer>();
1478 final SortedSet<String> domains_which_are_always_single = new TreeSet<String>();
1479 final SortedSet<String> domains_which_are_sometimes_single_sometimes_not = new TreeSet<String>();
1480 final SortedSet<String> domains_which_never_single = new TreeSet<String>();
1481 BufferedWriter domains_per_potein_stats_writer = null;
1483 domains_per_potein_stats_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
1484 + output_file + "_domains_per_potein_stats.txt" ) );
1485 domains_per_potein_stats_writer.write( "Genome" );
1486 domains_per_potein_stats_writer.write( "\t" );
1487 domains_per_potein_stats_writer.write( "Mean" );
1488 domains_per_potein_stats_writer.write( "\t" );
1489 domains_per_potein_stats_writer.write( "SD" );
1490 domains_per_potein_stats_writer.write( "\t" );
1491 domains_per_potein_stats_writer.write( "Median" );
1492 domains_per_potein_stats_writer.write( "\t" );
1493 domains_per_potein_stats_writer.write( "N" );
1494 domains_per_potein_stats_writer.write( "\t" );
1495 domains_per_potein_stats_writer.write( "Min" );
1496 domains_per_potein_stats_writer.write( "\t" );
1497 domains_per_potein_stats_writer.write( "Max" );
1498 domains_per_potein_stats_writer.write( "\n" );
1500 catch ( final IOException e3 ) {
1501 e3.printStackTrace();
1503 Map<String, DescriptiveStatistics> protein_length_stats_by_dc = null;
1504 Map<String, DescriptiveStatistics> domain_number_stats_by_dc = null;
1505 final Map<String, DescriptiveStatistics> domain_length_stats_by_domain = new HashMap<String, DescriptiveStatistics>();
1506 if ( perform_dc_regain_proteins_stats ) {
1507 protein_length_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1508 domain_number_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1510 DomainLengthsTable domain_lengths_table = null;
1511 if ( domain_length_analysis ) {
1512 domain_lengths_table = new DomainLengthsTable();
1515 final SortedMap<String, Set<String>> distinct_domain_architecutures_per_genome = new TreeMap<String, Set<String>>();
1516 final SortedMap<String, Integer> distinct_domain_architecuture_counts = new TreeMap<String, Integer>();
1517 for( int i = 0; i < number_of_genomes; ++i ) {
1518 System.out.println();
1519 System.out.println( ( i + 1 ) + "/" + number_of_genomes );
1520 SurfacingUtil.log( ( i + 1 ) + "/" + number_of_genomes, log_writer );
1521 System.out.println( "Processing : " + input_file_properties[ i ][ 1 ]
1522 + " [" + input_file_properties[ i ][ 0 ] + "]" );
1523 SurfacingUtil.log( "Genome : " + input_file_properties[ i ][ 1 ]
1524 + " [" + input_file_properties[ i ][ 0 ] + "]", log_writer );
1525 HmmscanPerDomainTableParser parser = null;
1526 INDIVIDUAL_SCORE_CUTOFF ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF.NONE;
1527 if ( individual_score_cutoffs != null ) {
1528 ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF_DEFAULT;
1530 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1531 || ( negative_domains_filter_file != null ) ) {
1532 HmmscanPerDomainTableParser.FilterType filter_type = HmmscanPerDomainTableParser.FilterType.NONE;
1533 if ( positive_filter_file != null ) {
1534 filter_type = HmmscanPerDomainTableParser.FilterType.POSITIVE_PROTEIN;
1536 else if ( negative_filter_file != null ) {
1537 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_PROTEIN;
1539 else if ( negative_domains_filter_file != null ) {
1540 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_DOMAIN;
1542 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1543 input_file_properties[ i ][ 1 ],
1550 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1551 input_file_properties[ i ][ 1 ],
1555 if ( fs_e_value_max >= 0.0 ) {
1556 parser.setFsEValueMaximum( fs_e_value_max );
1558 if ( ie_value_max >= 0.0 ) {
1559 parser.setIEValueMaximum( ie_value_max );
1561 parser.setIgnoreDufs( ignore_dufs );
1562 parser.setIgnoreVirusLikeIds( ignore_virus_like_ids );
1563 parser.setIgnoreEngulfedDomains( no_engulfing_overlaps );
1564 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1565 parser.setMaxAllowedOverlap( max_allowed_overlap );
1567 parser.setReturnType( HmmscanPerDomainTableParser.ReturnType.UNORDERED_PROTEIN_DOMAIN_COLLECTION_PER_PROTEIN );
1568 if ( individual_score_cutoffs != null ) {
1569 parser.setIndividualScoreCutoffs( individual_score_cutoffs );
1571 List<Protein> protein_list = null;
1573 protein_list = parser.parse();
1575 catch ( final IOException e ) {
1576 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1578 catch ( final Exception e ) {
1579 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, e.getMessage(), e );
1582 System.out.println( "Domains ignored due to negative domain filter: " );
1583 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToNegativeDomainFilterCountsMap() );
1584 System.out.println( "Domains ignored due to virus like id: " );
1585 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToVirusLikeIdCountsMap() );
1587 final double coverage = ( double ) protein_list.size() / parser.getProteinsEncountered();
1588 protein_coverage_stats.addValue( coverage );
1589 int distinct_das = -1;
1590 if ( da_analysis ) {
1591 final String genome = input_file_properties[ i ][ 0 ];
1592 distinct_das = SurfacingUtil.storeDomainArchitectures( genome,
1593 distinct_domain_architecutures_per_genome,
1595 distinct_domain_architecuture_counts );
1597 System.out.println( "Number of proteins encountered : " + parser.getProteinsEncountered() );
1598 SurfacingUtil.log( "Number of proteins encountered : " + parser.getProteinsEncountered(),
1600 System.out.println( "Number of proteins stored : " + protein_list.size() );
1601 SurfacingUtil.log( "Number of proteins stored : " + protein_list.size(), log_writer );
1602 System.out.println( "Coverage : "
1603 + ForesterUtil.roundToInt( 100.0 * coverage ) + "%" );
1604 SurfacingUtil.log( "Coverage : "
1605 + ForesterUtil.roundToInt( 100.0 * coverage ) + "%", log_writer );
1606 System.out.println( "Domains encountered : " + parser.getDomainsEncountered() );
1607 SurfacingUtil.log( "Domains encountered : " + parser.getDomainsEncountered(),
1609 System.out.println( "Domains stored : " + parser.getDomainsStored() );
1610 SurfacingUtil.log( "Domains stored : " + parser.getDomainsStored(),
1612 System.out.println( "Distinct domains stored : "
1613 + parser.getDomainsStoredSet().size() );
1615 .log( "Distinct domains stored : " + parser.getDomainsStoredSet().size(),
1617 System.out.println( "Domains ignored due to individual score cutoffs: "
1618 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() );
1619 SurfacingUtil.log( "Domains ignored due to individual score cutoffs: "
1620 + parser.getDomainsIgnoredDueToIndividualScoreCutoff(), log_writer );
1621 System.out.println( "Domains ignored due to FS E-value : "
1622 + parser.getDomainsIgnoredDueToFsEval() );
1624 .log( "Domains ignored due to FS E-value : " + parser.getDomainsIgnoredDueToFsEval(),
1626 System.out.println( "Domains ignored due to iE-value : "
1627 + parser.getDomainsIgnoredDueToIEval() );
1629 .log( "Domains ignored due to iE-value : " + parser.getDomainsIgnoredDueToIEval(),
1631 System.out.println( "Domains ignored due to DUF designation : "
1632 + parser.getDomainsIgnoredDueToDuf() );
1633 SurfacingUtil.log( "Domains ignored due to DUF designation : " + parser.getDomainsIgnoredDueToDuf(),
1635 if ( ignore_virus_like_ids ) {
1636 System.out.println( "Domains ignored due virus like ids : "
1637 + parser.getDomainsIgnoredDueToVirusLikeIds() );
1638 SurfacingUtil.log( "Domains ignored due virus like ids : "
1639 + parser.getDomainsIgnoredDueToVirusLikeIds(), log_writer );
1641 System.out.println( "Domains ignored due negative domain filter : "
1642 + parser.getDomainsIgnoredDueToNegativeDomainFilter() );
1643 SurfacingUtil.log( "Domains ignored due negative domain filter : "
1644 + parser.getDomainsIgnoredDueToNegativeDomainFilter(), log_writer );
1645 System.out.println( "Domains ignored due to overlap : "
1646 + parser.getDomainsIgnoredDueToOverlap() );
1648 .log( "Domains ignored due to overlap : " + parser.getDomainsIgnoredDueToOverlap(),
1650 if ( negative_filter_file != null ) {
1651 System.out.println( "Proteins ignored due to negative filter : "
1652 + parser.getProteinsIgnoredDueToFilter() );
1653 SurfacingUtil.log( "Proteins ignored due to negative filter : "
1654 + parser.getProteinsIgnoredDueToFilter(), log_writer );
1656 if ( positive_filter_file != null ) {
1657 System.out.println( "Proteins ignored due to positive filter : "
1658 + parser.getProteinsIgnoredDueToFilter() );
1659 SurfacingUtil.log( "Proteins ignored due to positive filter : "
1660 + parser.getProteinsIgnoredDueToFilter(), log_writer );
1662 if ( da_analysis ) {
1663 System.out.println( "Distinct domain architectures stored : " + distinct_das );
1664 SurfacingUtil.log( "Distinct domain architectures stored : " + distinct_das, log_writer );
1666 System.out.println( "Time for processing : " + parser.getTime() + "ms" );
1667 SurfacingUtil.log( "", log_writer );
1670 for( final Protein protein : protein_list ) {
1672 .write( SurfacingUtil.proteinToDomainCombinations( protein, count + "", "\t" ).toString() );
1674 for( final Domain d : protein.getProteinDomains() ) {
1675 final String d_str = d.getDomainId().toString();
1676 if ( !domain_length_stats_by_domain.containsKey( d_str ) ) {
1677 domain_length_stats_by_domain.put( d_str, new BasicDescriptiveStatistics() );
1679 domain_length_stats_by_domain.get( d_str ).addValue( d.getLength() );
1683 catch ( final IOException e ) {
1684 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1686 SurfacingUtil.domainsPerProteinsStatistics( input_file_properties[ i ][ 1 ],
1688 all_genomes_domains_per_potein_stats,
1689 all_genomes_domains_per_potein_histo,
1690 domains_which_are_always_single,
1691 domains_which_are_sometimes_single_sometimes_not,
1692 domains_which_never_single,
1693 domains_per_potein_stats_writer );
1694 if ( domain_length_analysis ) {
1695 domain_lengths_table.addLengths( protein_list );
1697 if ( !da_analysis ) {
1698 gwcd_list.add( BasicGenomeWideCombinableDomains.createInstance( protein_list,
1699 ignore_combination_with_same,
1700 new BasicSpecies( input_file_properties[ i ][ 1 ] ),
1701 domain_id_to_go_ids_map,
1703 protein_length_stats_by_dc,
1704 domain_number_stats_by_dc ) );
1705 if ( gwcd_list.get( i ).getSize() > 0 ) {
1706 if ( output_binary_domain_combinationsfor_counts ) {
1707 SurfacingUtil.writeDomainCombinationsCountsFile( input_file_properties,
1709 per_genome_domain_promiscuity_statistics_writer,
1714 if ( output_binary_domain_combinationsfor_graph_analysis ) {
1715 SurfacingUtil.writeBinaryDomainCombinationsFileForGraphAnalysis( input_file_properties,
1721 SurfacingUtil.addAllDomainIdsToSet( gwcd_list.get( i ), all_domains_encountered );
1722 SurfacingUtil.addAllBinaryDomainCombinationToSet( gwcd_list.get( i ),
1723 all_bin_domain_combinations_encountered );
1726 if ( query_domains_writer_ary != null ) {
1727 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1729 SurfacingUtil.extractProteinNames( protein_list,
1730 query_domain_ids_array[ j ],
1731 query_domains_writer_ary[ j ],
1733 LIMIT_SPEC_FOR_PROT_EX );
1734 query_domains_writer_ary[ j ].flush();
1736 catch ( final IOException e ) {
1737 e.printStackTrace();
1741 if ( need_protein_lists_per_species ) {
1742 protein_lists_per_species.put( new BasicSpecies( input_file_properties[ i ][ 1 ] ), protein_list );
1747 catch ( final IOException e2 ) {
1748 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1751 } // for( int i = 0; i < number_of_genomes; ++i ) {
1753 .programMessage( PRG_NAME,
1754 "Wrote domain promiscuities to: " + per_genome_domain_promiscuity_statistics_file );
1756 if ( true ) { //TODO
1757 MinimalDomainomeCalculator.calcDomainome( intree_0_orig, protein_lists_per_species, -1 );
1759 if ( true ) { //TODO
1761 MinimalDomainomeCalculator.calcDAome( intree_0_orig,
1762 protein_lists_per_species,
1765 out_dir.toString() + "/" + output_file );
1767 catch ( IOException e ) {
1768 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
1771 if ( da_analysis ) {
1772 SurfacingUtil.performDomainArchitectureAnalysis( distinct_domain_architecutures_per_genome,
1773 distinct_domain_architecuture_counts,
1775 new File( out_dir.toString() + "/" + output_file
1776 + "_DA_counts.txt" ),
1777 new File( out_dir.toString() + "/" + output_file
1778 + "_unique_DAs.txt" ) );
1779 distinct_domain_architecutures_per_genome.clear();
1780 distinct_domain_architecuture_counts.clear();
1784 domains_per_potein_stats_writer.write( "ALL" );
1785 domains_per_potein_stats_writer.write( "\t" );
1786 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.arithmeticMean() + "" );
1787 domains_per_potein_stats_writer.write( "\t" );
1788 domains_per_potein_stats_writer
1789 .write( all_genomes_domains_per_potein_stats.sampleStandardDeviation() + "" );
1790 domains_per_potein_stats_writer.write( "\t" );
1791 if ( all_genomes_domains_per_potein_stats.getN() <= 300 ) {
1792 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.median() + "" );
1793 domains_per_potein_stats_writer.write( "\t" );
1795 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getN() + "" );
1796 domains_per_potein_stats_writer.write( "\t" );
1797 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMin() + "" );
1798 domains_per_potein_stats_writer.write( "\t" );
1799 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMax() + "" );
1800 domains_per_potein_stats_writer.write( "\n" );
1801 domains_per_potein_stats_writer.close();
1802 all_genomes_domains_per_potein_stats = null;
1803 SurfacingUtil.printOutPercentageOfMultidomainProteins( all_genomes_domains_per_potein_histo, log_writer );
1804 ForesterUtil.map2file(
1805 new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1806 + "_all_genomes_domains_per_potein_histo.txt" ),
1807 all_genomes_domains_per_potein_histo,
1810 ForesterUtil.collection2file(
1811 new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1812 + "_domains_always_single_.txt" ),
1813 domains_which_are_always_single,
1815 ForesterUtil.collection2file(
1816 new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1817 + "_domains_single_or_combined.txt" ),
1818 domains_which_are_sometimes_single_sometimes_not,
1820 ForesterUtil.collection2file(
1821 new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1822 + "_domains_always_combined.txt" ),
1823 domains_which_never_single,
1825 ForesterUtil.programMessage( PRG_NAME,
1826 "Average of proteins with a least one domain assigned: "
1827 + ( 100 * protein_coverage_stats.arithmeticMean() ) + "% (+/-"
1828 + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)" );
1829 ForesterUtil.programMessage( PRG_NAME,
1830 "Range of proteins with a least one domain assigned: "
1831 + ( 100 * protein_coverage_stats.getMin() ) + "%-"
1832 + ( 100 * protein_coverage_stats.getMax() ) + "%" );
1834 "Average of prot with a least one dom assigned : "
1835 + ( 100 * protein_coverage_stats.arithmeticMean() ) + "% (+/-"
1836 + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)",
1838 SurfacingUtil.log( "Range of prot with a least one dom assigned : "
1839 + ( 100 * protein_coverage_stats.getMin() ) + "%-" + ( 100 * protein_coverage_stats.getMax() )
1840 + "%", log_writer );
1841 protein_coverage_stats = null;
1843 catch ( final IOException e2 ) {
1844 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1846 if ( query_domains_writer_ary != null ) {
1847 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1849 query_domains_writer_ary[ j ].close();
1851 catch ( final IOException e ) {
1852 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1857 per_genome_domain_promiscuity_statistics_writer.close();
1858 dc_data_writer.close();
1861 catch ( final IOException e2 ) {
1862 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1864 if ( domain_length_analysis ) {
1866 SurfacingUtil.executeDomainLengthAnalysis( input_file_properties,
1868 domain_lengths_table,
1869 domain_lengths_analysis_outfile );
1871 catch ( final IOException e1 ) {
1872 ForesterUtil.fatalError( surfacing.PRG_NAME, e1.toString() );
1874 System.out.println();
1875 ForesterUtil.programMessage( PRG_NAME, "Wrote domain length data to: " + domain_lengths_analysis_outfile );
1876 System.out.println();
1878 domain_lengths_table = null;
1879 final long analysis_start_time = new Date().getTime();
1880 PairwiseDomainSimilarityCalculator pw_calc = null;
1881 final DomainSimilarityCalculator calc = new BasicDomainSimilarityCalculator( domain_similarity_sort_field,
1882 sort_by_species_count_first,
1883 number_of_genomes == 2,
1884 CALC_SIMILARITY_SCORES,
1886 switch ( scoring ) {
1888 pw_calc = new CombinationsBasedPairwiseDomainSimilarityCalculator();
1891 pw_calc = new DomainCountsBasedPairwiseSimilarityCalculator();
1894 pw_calc = new ProteinCountsBasedPairwiseDomainSimilarityCalculator();
1897 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
1899 DomainSimilarityCalculator.GoAnnotationOutput go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.NONE;
1900 if ( domain_id_to_go_ids_map != null ) {
1901 go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.ALL;
1903 final SortedSet<DomainSimilarity> similarities = calc.calculateSimilarities( pw_calc,
1905 ignore_domains_without_combs_in_all_spec,
1906 ignore_species_specific_domains );
1907 SurfacingUtil.decoratePrintableDomainSimilarities( similarities, detailedness );
1908 final Map<String, Integer> tax_code_to_id_map = SurfacingUtil.createTaxCodeToIdMap( intrees[ 0 ] );
1910 String my_outfile = output_file.toString();
1911 Map<Character, Writer> split_writers = null;
1912 Writer writer = null;
1913 if ( similarities.size() > MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING ) {
1914 if ( my_outfile.endsWith( ".html" ) ) {
1915 my_outfile = my_outfile.substring( 0, my_outfile.length() - 5 );
1917 split_writers = new HashMap<Character, Writer>();
1918 SurfacingUtil.createSplitWriters( out_dir, my_outfile, split_writers );
1920 else if ( !my_outfile.endsWith( ".html" ) ) {
1921 my_outfile += ".html";
1922 writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) );
1924 List<Species> species_order = null;
1925 if ( species_matrix ) {
1926 species_order = new ArrayList<Species>();
1927 for( int i = 0; i < number_of_genomes; i++ ) {
1928 species_order.add( new BasicSpecies( input_file_properties[ i ][ 1 ] ) );
1931 html_desc.append( "<tr><td>Sum of all distinct binary combinations:</td><td>"
1932 + all_bin_domain_combinations_encountered.size() + "</td></tr>" + nl );
1933 html_desc.append( "<tr><td>Sum of all distinct domains:</td><td>" + all_domains_encountered.size()
1934 + "</td></tr>" + nl );
1935 html_desc.append( "<tr><td>Analysis date/time:</td><td>"
1936 + new java.text.SimpleDateFormat( "yyyy.MM.dd HH:mm:ss" ).format( new java.util.Date() )
1937 + "</td></tr>" + nl );
1938 html_desc.append( "</table>" + nl );
1939 final Writer simple_tab_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
1940 + my_outfile.replaceFirst( ".html", ".tsv" ) ) );
1941 SurfacingUtil.writeDomainSimilaritiesToFile( html_desc,
1942 new StringBuilder( number_of_genomes + " genomes" ),
1947 number_of_genomes == 2,
1949 domain_similarity_print_option,
1954 positive_filter_file != null ? filter : null );
1955 simple_tab_writer.close();
1956 ForesterUtil.programMessage( surfacing.PRG_NAME,
1957 "Wrote main output (includes domain similarities) to: \""
1958 + ( out_dir == null ? my_outfile
1959 : out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile )
1962 catch ( final IOException e ) {
1964 .fatalError( surfacing.PRG_NAME,
1965 "Failed to write similarites to: \"" + output_file + "\" [" + e.getMessage() + "]" );
1967 System.out.println();
1968 final Species[] species = new Species[ number_of_genomes ];
1969 for( int i = 0; i < number_of_genomes; ++i ) {
1970 species[ i ] = new BasicSpecies( input_file_properties[ i ][ 1 ] );
1972 List<Phylogeny> inferred_trees = null;
1973 if ( ( number_of_genomes > 2 ) && perform_pwc ) {
1974 final PairwiseGenomeComparator pwgc = new PairwiseGenomeComparator();
1975 pwgc.performPairwiseComparisons( html_desc,
1976 sort_by_species_count_first,
1978 ignore_domains_without_combs_in_all_spec,
1979 ignore_species_specific_domains,
1980 domain_similarity_sort_field_for_automated_pwc,
1981 domain_similarity_print_option,
1983 domain_id_to_go_ids_map,
1990 automated_pairwise_comparison_suffix,
1992 surfacing.PAIRWISE_DOMAIN_COMPARISONS_PREFIX,
1997 CALC_SIMILARITY_SCORES,
1999 String matrix_output_file = new String( output_file.toString() );
2000 if ( matrix_output_file.indexOf( '.' ) > 1 ) {
2001 matrix_output_file = matrix_output_file.substring( 0, matrix_output_file.indexOf( '.' ) );
2003 if ( out_dir != null ) {
2004 matrix_output_file = out_dir + ForesterUtil.FILE_SEPARATOR + matrix_output_file;
2005 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2007 SurfacingUtil.writeMatrixToFile(
2008 new File( matrix_output_file
2009 + surfacing.MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ),
2010 pwgc.getDomainDistanceScoresMeans() );
2011 SurfacingUtil.writeMatrixToFile(
2012 new File( matrix_output_file
2013 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2014 pwgc.getSharedBinaryCombinationsBasedDistances() );
2015 SurfacingUtil.writeMatrixToFile(
2016 new File( matrix_output_file
2017 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2018 pwgc.getSharedDomainsBasedDistances() );
2019 final Phylogeny nj_gd = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2020 + surfacing.NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ),
2021 pwgc.getDomainDistanceScoresMeans()
2023 final Phylogeny nj_bc = SurfacingUtil.createNjTreeBasedOnMatrixToFile(
2024 new File( matrix_output_file
2025 + surfacing.NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2026 pwgc.getSharedBinaryCombinationsBasedDistances()
2028 final Phylogeny nj_d = SurfacingUtil.createNjTreeBasedOnMatrixToFile(
2029 new File( matrix_output_file
2030 + surfacing.NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2031 pwgc.getSharedDomainsBasedDistances()
2033 inferred_trees = new ArrayList<Phylogeny>();
2034 inferred_trees.add( nj_gd );
2035 inferred_trees.add( nj_bc );
2036 inferred_trees.add( nj_d );
2037 } // if ( ( output_file != null ) && ( number_of_genomes > 2 ) && !isEmpty( automated_pairwise_comparison_suffix ) )
2038 if ( ( out_dir != null ) && ( !perform_pwc ) ) {
2039 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2041 if ( write_to_nexus ) {
2042 SurfacingUtil.writePresentToNexus( output_file, positive_filter_file, filter, gwcd_list );
2044 if ( ( ( intrees != null ) && ( intrees.length > 0 ) ) && ( number_of_genomes > 2 ) ) {
2045 final StringBuilder parameters_sb = SurfacingUtil.createParametersAsString( ignore_dufs,
2048 max_allowed_overlap,
2049 no_engulfing_overlaps,
2053 if ( radomize_fitch_parsimony ) {
2054 s += random_number_seed_for_fitch_parsimony + "_";
2057 for( final Phylogeny intree : intrees ) {
2058 final String outfile_name = ForesterUtil.removeSuffix( output_file.toString() ) + s
2059 + ForesterUtil.removeSuffix( intree_files[ i ].toString() );
2060 final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator
2061 .createInstance( intree, gwcd_list );
2062 SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
2063 radomize_fitch_parsimony,
2067 domain_id_to_go_ids_map,
2070 parameters_sb.toString(),
2071 domain_id_to_secondary_features_maps,
2072 positive_filter_file == null ? null : filter,
2073 output_binary_domain_combinationsfor_graph_analysis,
2074 all_bin_domain_combinations_gained_fitch,
2075 all_bin_domain_combinations_lost_fitch,
2077 protein_length_stats_by_dc,
2078 domain_number_stats_by_dc,
2079 domain_length_stats_by_domain,
2082 use_last_in_fitch_parsimony,
2084 // Listing of all domain combinations gained is only done if only one input tree is used.
2085 if ( ( domain_id_to_secondary_features_maps != null )
2086 && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
2088 for( final Map<String, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
2089 final Map<Species, MappingResults> mapping_results_map = new TreeMap<Species, MappingResults>();
2090 final DomainParsimonyCalculator secondary_features_parsimony = DomainParsimonyCalculator
2091 .createInstance( intree, gwcd_list, domain_id_to_secondary_features_map );
2092 SurfacingUtil.executeParsimonyAnalysisForSecondaryFeatures( outfile_name + "_"
2093 + secondary_features_map_files[ j++ ],
2094 secondary_features_parsimony,
2096 parameters_sb.toString(),
2097 mapping_results_map,
2098 use_last_in_fitch_parsimony );
2100 System.out.println();
2101 System.out.println( "Mapping to secondary features:" );
2102 for( final Species spec : mapping_results_map.keySet() ) {
2103 final MappingResults mapping_results = mapping_results_map.get( spec );
2104 final int total_domains = mapping_results.getSumOfFailures()
2105 + mapping_results.getSumOfSuccesses();
2106 System.out.print( spec + ":" );
2107 System.out.print( " mapped domains = " + mapping_results.getSumOfSuccesses() );
2108 System.out.print( ", not mapped domains = " + mapping_results.getSumOfFailures() );
2109 if ( total_domains > 0 ) {
2110 System.out.println( ", mapped ratio = "
2111 + ( ( 100 * mapping_results.getSumOfSuccesses() ) / total_domains ) + "%" );
2114 System.out.println( ", mapped ratio = n/a (total domains = 0 )" );
2121 } // for( final Phylogeny intree : intrees ) {
2123 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
2124 SurfacingUtil.executePlusMinusAnalysis( output_file,
2125 plus_minus_analysis_high_copy_base_species,
2126 plus_minus_analysis_high_copy_target_species,
2127 plus_minus_analysis_high_low_copy_species,
2129 protein_lists_per_species,
2130 domain_id_to_go_ids_map,
2132 plus_minus_analysis_numbers );
2134 if ( output_protein_lists_for_all_domains ) {
2135 SurfacingUtil.writeProteinListsForAllSpecies( out_dir,
2136 protein_lists_per_species,
2138 output_list_of_all_proteins_per_domain_e_value_max,
2139 positive_filter_file != null ? filter : null );
2142 if ( all_bin_domain_combinations_gained_fitch != null ) {
2144 SurfacingUtil.executeFitchGainsAnalysis(
2145 new File( output_file
2146 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2147 all_bin_domain_combinations_gained_fitch,
2148 all_domains_encountered.size(),
2149 all_bin_domain_combinations_encountered,
2152 catch ( final IOException e ) {
2153 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2156 if ( all_bin_domain_combinations_lost_fitch != null ) {
2158 SurfacingUtil.executeFitchGainsAnalysis(
2159 new File( output_file
2160 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2161 all_bin_domain_combinations_lost_fitch,
2162 all_domains_encountered.size(),
2163 all_bin_domain_combinations_encountered,
2166 catch ( final IOException e ) {
2167 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2170 final Runtime rt = java.lang.Runtime.getRuntime();
2171 final long free_memory = rt.freeMemory() / 1000000;
2172 final long total_memory = rt.totalMemory() / 1000000;
2173 ForesterUtil.programMessage( PRG_NAME,
2174 "Time for analysis : " + ( new Date().getTime() - analysis_start_time ) + "ms" );
2175 ForesterUtil.programMessage( PRG_NAME, "Total running time: " + ( new Date().getTime() - start_time ) + "ms " );
2177 .programMessage( PRG_NAME,
2178 "Free memory : " + free_memory + "MB, total memory: " + total_memory + "MB" );
2179 ForesterUtil.programMessage( PRG_NAME, "If this application is useful to you, please cite:" );
2180 ForesterUtil.programMessage( PRG_NAME, surfacing.WWW );
2181 ForesterUtil.programMessage( PRG_NAME, "OK" );
2182 System.out.println();
2185 private static void printHelp() {
2186 System.out.println();
2187 System.out.println( "Usage:" );
2188 System.out.println();
2189 System.out.println( "% java -Xms256m -Xmx512m -cp forester.jar org.forester.applications." + surfacing.PRG_NAME
2190 + " [options] <phylogen(y|ies) infile> [external node name 1] [name 2] ... [name n]" );
2191 System.out.println();
2192 System.out.println( " Note: This software might need a significant amount of memory (heap space);" );
2194 .println( " hence use \"-Xms128m -Xmx512m\" (or more) to prevent a \"java.lang.OutOfMemoryError\"." );
2195 System.out.println();
2196 System.out.println( " Options: " );
2197 System.out.println( surfacing.DETAILEDNESS_OPTION + ": level of detail for similarities output file (default:"
2198 + DETAILEDNESS_DEFAULT + ")" );
2199 System.out.println( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION
2200 + ": to ignore combinations with self (default: not to ignore)" );
2201 System.out.println( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION
2202 + ": to ignore domains without combinations in any species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2203 System.out.println( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION
2204 + ": to ignore domains specific to one species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2205 System.out.println( surfacing.NOT_IGNORE_DUFS_OPTION
2206 + ": to _not_ ignore DUFs (domains with unknown function) (default: ignore DUFs)" );
2207 System.out.println( surfacing.IGNORE_VIRAL_IDS
2208 + ": to ignore domains with ids containing 'vir', 'retro', 'transpos', 'phage', or starting with 'rv' or 'gag_'" );
2209 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_OPTION + ": sorting for similarities (default: "
2210 + DOMAIN_SORT_FILD_DEFAULT + ")" );
2211 System.out.println( surfacing.OUTPUT_FILE_OPTION + ": name for (main) output file (mandatory)" );
2212 System.out.println( surfacing.MAX_I_E_VALUE_OPTION + ": max (inclusive) iE-value" );
2213 System.out.println( surfacing.MAX_FS_E_VALUE_OPTION + ": max (inclusive) FS E-value" );
2214 System.out.println( surfacing.MAX_ALLOWED_OVERLAP_OPTION + ": maximal allowed domain overlap" );
2215 System.out.println( surfacing.NO_ENGULFING_OVERLAP_OPTION + ": to ignore engulfed lower confidence domains" );
2216 System.out.println( surfacing.SPECIES_MATRIX_OPTION + ": species matrix" );
2217 System.out.println( surfacing.SCORING_OPTION + ": scoring (default:" + SCORING_DEFAULT + ")" );
2218 System.out.println( surfacing.DOMAIN_COUNT_SORT_OPTION + ": sorting for domain counts (default:"
2219 + DOMAINS_SORT_ORDER_DEFAULT + ")" );
2220 System.out.println( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION + ": domain similarity print option (default:"
2221 + DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT + ")" );
2222 System.out.println( surfacing.CUTOFF_SCORE_FILE_OPTION + ": cutoff score file" );
2223 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION
2224 + ": sort by species count first" );
2225 System.out.println( surfacing.OUTPUT_DIR_OPTION + ": output directory" );
2226 System.out.println( surfacing.PFAM_TO_GO_FILE_USE_OPTION + ": Pfam to GO mapping file" );
2227 System.out.println( surfacing.GO_OBO_FILE_USE_OPTION + ": GO terms file (OBO format)" );
2228 System.out.println( surfacing.GO_NAMESPACE_LIMIT_OPTION + ": limit GO term to one GO namespace" );
2229 System.out.println( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
2230 + "[=<suffix for pairwise comparison output files>]: to perform pairwise comparison based analyses" );
2231 System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION
2232 + ": species tree, to perform (Dollo, Fitch) parismony analyses" );
2233 System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION
2234 + "=<treefiles in phyloXML format, separated by #>: to infer domain/binary domain combination gains/losses on given species trees" );
2235 System.out.println( surfacing.FILTER_POSITIVE_OPTION
2236 + "=<file>: to filter out proteins not containing at least one domain listed in <file>" );
2237 System.out.println( surfacing.FILTER_NEGATIVE_OPTION
2238 + "=<file>: to filter out proteins containing at least one domain listed in <file>" );
2239 System.out.println( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION
2240 + "=<file>: to filter out (ignore) domains listed in <file>" );
2241 System.out.println( surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>: to read input files from <file>" );
2242 System.out.println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION
2243 + "=<seed>: seed for random number generator for Fitch Parsimony analysis (type: long, default: no randomization - given a choice, prefer absence" );
2244 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS
2245 + ": to consider directedness in binary combinations: e.g. A-B != B-A" );
2246 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY
2247 + ": to consider directedness and adjacency in binary combinations" );
2248 System.out.println( surfacing.SEQ_EXTRACT_OPTION
2249 + "=<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')" );
2250 System.out.println( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE
2251 + "=<file>: to perfom parsimony analysis on secondary features" );
2252 System.out.println( surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>: to presence/absence genome analysis" );
2253 System.out.println( surfacing.DOMAIN_COMBINITONS_COUNTS_OUTPUT_OPTION
2254 + ": to output binary domain counts (as individual files)" );
2255 System.out.println( surfacing.DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS
2256 + ": to output binary domain combinations for (downstream) graph analysis" );
2257 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS + ": to output all proteins per domain" );
2258 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION
2259 + ": e value max per domain for output of all proteins per domain" );
2260 System.out.println( surfacing.USE_LAST_IN_FITCH_OPTION + ": to use last in Fitch parsimony" );
2261 System.out.println( surfacing.WRITE_TO_NEXUS_OPTION + ": to output in Nexus format" );
2262 System.out.println( PERFORM_DC_FITCH + ": to perform DC Fitch parsimony" );
2263 System.out.println( PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION + ": to perform DC regain protein statistics" );
2264 System.out.println( DA_ANALYSIS_OPTION + ": to perform DA analysis" );
2265 System.out.println( PERFORM_DOMAIN_LENGTH_ANALYSIS_OPTION + ": to perform domain length analysis" );
2266 System.out.println();
2267 System.out.println();
2269 .println( "Example 1: surfacing -p2g=pfam2go.txt -obo=go.obo -species_tree=tol_156.xml -no_eo -ie=0.01 -dufs -genomes=genomes_all.txt -pos_filter=tf_1.txt -out_dir=_tf1 -o=tf1" );
2270 System.out.println();
2272 .println( "Example 2: surfacing -p2g=pfam2go.txt -obo=go.obo -species_tree=tol_156.xml -last -ignore_viral_ids -no_eo -ie=0.1 -dufs -genomes=genomes_all.txt -pos_filter=tf_1.txt -all_prot -all_prot_e=0.1 -out_dir=_tf1_e01_ape01 -o=tf1_e01_ape01" );
2273 System.out.println();