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.PairwiseDomainSimilarityCalculator;
75 import org.forester.surfacing.PairwiseGenomeComparator;
76 import org.forester.surfacing.ProteinCountsBasedPairwiseDomainSimilarityCalculator;
77 import org.forester.surfacing.SurfacingUtil;
78 import org.forester.util.BasicDescriptiveStatistics;
79 import org.forester.util.BasicTable;
80 import org.forester.util.BasicTableParser;
81 import org.forester.util.CommandLineArguments;
82 import org.forester.util.DescriptiveStatistics;
83 import org.forester.util.ForesterConstants;
84 import org.forester.util.ForesterUtil;
86 public class surfacing {
88 private static final int MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING = 1000;
89 public final static String DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS = "graph_analysis_out";
90 public final static String DOMAIN_COMBINITONS_COUNTS_OUTPUT_OPTION = "dcc";
91 public final static String DOMAIN_COMBINITONS_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_dc.dot";
92 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_fitch_present_dc.dot";
93 public final static String DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX = ".dcc";
95 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS = "_dollo_gl_d";
96 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_gl_dc";
97 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_DOMAINS = "_fitch_gl_d";
98 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_gl_dc";
100 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS = "_dollo_glc_d";
101 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_glc_dc";
102 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_DOMAINS = "_fitch_glc_d";
103 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_glc_dc";
105 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_BC = "_fitch_gains_dc";
106 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_HTML_BC = "_fitch_gains_dc.html";
107 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_BC = "_fitch_losses_dc";
108 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_HTML_BC = "_fitch_losses_dc.html";
109 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC = "_fitch_present_dc";
110 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_HTML_BC = "_fitch_present_dc.html";
111 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_D = "_dollo_gains_d";
112 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_HTML_D = "_dollo_gains_d.html";
113 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_D = "_dollo_losses_d";
114 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_HTML_D = "_dollo_losses_d.html";
115 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_D = "_dollo_present_d";
116 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_HTML_D = "_dollo_present_d.html";
117 public final static String DOMAINS_PRESENT_NEXUS = "_dom.nex";
118 public final static String BDC_PRESENT_NEXUS = "_dc.nex";
120 public final static String PRG_NAME = "surfacing";
121 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_d_dollo"
122 + ForesterConstants.PHYLO_XML_SUFFIX;
123 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_d_fitch"
124 + ForesterConstants.PHYLO_XML_SUFFIX;
125 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_dc_dollo"
126 + ForesterConstants.PHYLO_XML_SUFFIX;
127 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_dc_fitch"
128 + ForesterConstants.PHYLO_XML_SUFFIX;
129 public static final String NEXUS_EXTERNAL_DOMAINS = "_dom.nex";
130 public static final String NEXUS_EXTERNAL_DOMAIN_COMBINATIONS = "_dc.nex";
131 public static final String NEXUS_SECONDARY_FEATURES = "_secondary_features.nex";
132 public static final String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_gl_secondary_features";
133 public static final String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_glc_secondary_features";
134 public static final String PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES = "_dollo_gains_secondary_features";
135 public static final String PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES = "_dollo_losses_secondary_features";
136 public static final String PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES = "_dollo_present_secondary_features";
137 public static final String SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_secondary_features_dollo"
138 + ForesterConstants.PHYLO_XML_SUFFIX;
139 public static final String PARSIMONY_OUTPUT_DOLLO_ALL_GOID_D_ALL_NAMESPACES = "_dollo_goid_d";
140 public static final String PARSIMONY_OUTPUT_FITCH_ALL_GOID_BC_ALL_NAMESPACES = "_fitch_goid_dc";
141 final static private String HELP_OPTION_1 = "help";
142 final static private String HELP_OPTION_2 = "h";
143 final static private String OUTPUT_DIR_OPTION = "out_dir";
144 final static private String SCORING_OPTION = "scoring";
145 private static final DomainSimilarityScoring SCORING_DEFAULT = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
146 final static private String SCORING_DOMAIN_COUNT_BASED = "domains";
147 final static private String SCORING_PROTEIN_COUNT_BASED = "proteins";
148 final static private String SCORING_COMBINATION_BASED = "combinations";
149 final static private String DETAILEDNESS_OPTION = "detail";
150 private final static Detailedness DETAILEDNESS_DEFAULT = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
151 final static private String SPECIES_MATRIX_OPTION = "smatrix";
152 final static private String DETAILEDNESS_BASIC = "basic";
153 final static private String DETAILEDNESS_LIST_IDS = "list_ids";
154 final static private String DETAILEDNESS_PUNCTILIOUS = "punctilious";
155 final static private String DOMAIN_SIMILARITY_SORT_OPTION = "sort";
156 private static final DomainSimilarity.DomainSimilaritySortField DOMAIN_SORT_FILD_DEFAULT = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
157 final static private String DOMAIN_SIMILARITY_SORT_MIN = "min";
158 final static private String DOMAIN_SIMILARITY_SORT_MAX = "max";
159 final static private String DOMAIN_SIMILARITY_SORT_SD = "sd";
160 final static private String DOMAIN_SIMILARITY_SORT_MEAN = "mean";
161 final static private String DOMAIN_SIMILARITY_SORT_DIFF = "diff";
162 final static private String DOMAIN_SIMILARITY_SORT_COUNTS_DIFF = "count_diff";
163 final static private String DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF = "abs_count_diff";
164 final static private String DOMAIN_SIMILARITY_SORT_SPECIES_COUNT = "species";
165 final static private String DOMAIN_SIMILARITY_SORT_ALPHA = "alpha";
166 final static private String DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION = "species_first";
167 final static private String DOMAIN_COUNT_SORT_OPTION = "dc_sort";
168 private static final GenomeWideCombinableDomainsSortOrder DOMAINS_SORT_ORDER_DEFAULT = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
169 final static private String DOMAIN_COUNT_SORT_ALPHA = "alpha";
170 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT = "dom";
171 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT = "prot";
172 final static private String DOMAIN_COUNT_SORT_COMBINATIONS_COUNT = "comb";
173 final static private String CUTOFF_SCORE_FILE_OPTION = "cos";
174 final static private String NOT_IGNORE_DUFS_OPTION = "dufs";
175 final static private String MAX_FS_E_VALUE_OPTION = "fs_e";
176 final static private String MAX_I_E_VALUE_OPTION = "ie";
177 final static private String MAX_ALLOWED_OVERLAP_OPTION = "mo";
178 final static private String NO_ENGULFING_OVERLAP_OPTION = "no_eo";
179 final static private String IGNORE_COMBINATION_WITH_SAME_OPTION = "ignore_self_comb";
180 final static private String PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION = "dc_regain_stats";
181 final static private String DA_ANALYSIS_OPTION = "DA_analyis";
182 final static private String USE_LAST_IN_FITCH_OPTION = "last";
183 public final static String PAIRWISE_DOMAIN_COMPARISONS_PREFIX = "pwc_";
184 final static private String PAIRWISE_DOMAIN_COMPARISONS_OPTION = "pwc";
185 final static private String OUTPUT_FILE_OPTION = "o";
186 final static private String PFAM_TO_GO_FILE_USE_OPTION = "p2g";
187 final static private String GO_OBO_FILE_USE_OPTION = "obo";
188 final static private String GO_NAMESPACE_LIMIT_OPTION = "go_namespace";
189 final static private String GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION = "molecular_function";
190 final static private String GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS = "biological_process";
191 final static private String GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT = "cellular_component";
192 final static private String SECONDARY_FEATURES_PARSIMONY_MAP_FILE = "secondary";
193 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED = "simple_tab";
194 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML = "simple_html";
195 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML = "detailed_html";
196 final static private String DOMAIN_SIMILARITY_PRINT_OPTION = "ds_output";
197 private static final PRINT_OPTION DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT = DomainSimilarity.PRINT_OPTION.HTML;
198 final static private String IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION = "ignore_singlet_domains";
199 final static private String IGNORE_VIRAL_IDS = "ignore_viral_ids";
200 final static private boolean IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT = false;
201 final static private String IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION = "ignore_species_specific_domains";
202 final static private boolean IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT = false;
203 final static private String MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score.pwd";
204 final static private String MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains.pwd";
205 final static private String MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations.pwd";
206 final static private String NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score_NJ"
207 + ForesterConstants.PHYLO_XML_SUFFIX;
208 final static private String NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains_NJ"
209 + ForesterConstants.PHYLO_XML_SUFFIX;
210 final static private String NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations_NJ"
211 + ForesterConstants.PHYLO_XML_SUFFIX;
212 final static private String FILTER_POSITIVE_OPTION = "pos_filter";
213 final static private String FILTER_NEGATIVE_OPTION = "neg_filter";
214 final static private String FILTER_NEGATIVE_DOMAINS_OPTION = "neg_dom_filter";
215 final static private String INPUT_GENOMES_FILE_OPTION = "genomes";
216 final static private String INPUT_SPECIES_TREE_OPTION = "species_tree";
217 final static private String SEQ_EXTRACT_OPTION = "prot_extract";
218 final static private String PRG_VERSION = "2.403";
219 final static private String PRG_DATE = "131127";
220 final static private String E_MAIL = "czmasek@burnham.org";
221 final static private String WWW = "https://sites.google.com/site/cmzmasek/home/software/forester/surfacing";
222 final static private boolean IGNORE_DUFS_DEFAULT = true;
223 final static private boolean IGNORE_COMBINATION_WITH_SAME_DEFAULLT = false;
224 final static private double MAX_E_VALUE_DEFAULT = -1;
225 public final static int MAX_ALLOWED_OVERLAP_DEFAULT = -1;
226 private static final String RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION = "random_seed";
227 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS = "consider_bdc_direction";
228 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY = "consider_bdc_adj";
229 public static final String SEQ_EXTRACT_SUFFIX = ".prot";
230 public static final String PLUS_MINUS_ANALYSIS_OPTION = "plus_minus";
231 public static final String PLUS_MINUS_DOM_SUFFIX = "_plus_minus_dom.txt";
232 public static final String PLUS_MINUS_DOM_SUFFIX_HTML = "_plus_minus_dom.html";
233 public static final String PLUS_MINUS_DC_SUFFIX_HTML = "_plus_minus_dc.html";
234 public static final int PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT = 0;
235 public static final double PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT = 1.0;
236 public static final String PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_all.txt";
237 public static final String PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_passing.txt";
238 private static final String OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS = "all_prot";
239 final static private String OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION = "all_prot_e";
240 public static final boolean VERBOSE = false;
241 private static final String OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_gains_counts";
242 private static final String OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_losses_counts";
243 private static final String DOMAIN_LENGTHS_ANALYSIS_SUFFIX = "_domain_lengths_analysis";
244 private static final boolean PERFORM_DOMAIN_LENGTH_ANALYSIS = true;
245 public static final String ALL_PFAMS_ENCOUNTERED_SUFFIX = "_all_encountered_pfams";
246 public static final String ALL_PFAMS_ENCOUNTERED_WITH_GO_ANNOTATION_SUFFIX = "_all_encountered_pfams_with_go_annotation";
247 public static final String ENCOUNTERED_PFAMS_SUMMARY_SUFFIX = "_encountered_pfams_summary";
248 public static final String ALL_PFAMS_GAINED_AS_DOMAINS_SUFFIX = "_all_pfams_gained_as_domains";
249 public static final String ALL_PFAMS_LOST_AS_DOMAINS_SUFFIX = "_all_pfams_lost_as_domains";
250 public static final String ALL_PFAMS_GAINED_AS_DC_SUFFIX = "_all_pfams_gained_as_dc";
251 public static final String ALL_PFAMS_LOST_AS_DC_SUFFIX = "_all_pfams_lost_as_dc";
252 public static final String BASE_DIRECTORY_PER_NODE_DOMAIN_GAIN_LOSS_FILES = "PER_NODE_EVENTS";
253 public static final String BASE_DIRECTORY_PER_SUBTREE_DOMAIN_GAIN_LOSS_FILES = "PER_SUBTREE_EVENTS";
254 public static final String D_PROMISCUITY_FILE_SUFFIX = "_domain_promiscuities";
255 private static final String LOG_FILE_SUFFIX = "_log.txt";
256 private static final String DATA_FILE_SUFFIX = "_domain_combination_data.txt";
257 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";
258 private static final String WRITE_TO_NEXUS_OPTION = "nexus";
259 private static final String PERFORM_DC_FITCH = "dc_pars";
260 private static final INDIVIDUAL_SCORE_CUTOFF INDIVIDUAL_SCORE_CUTOFF_DEFAULT = INDIVIDUAL_SCORE_CUTOFF.FULL_SEQUENCE; //TODO look at me! change?
261 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts.txt";
262 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists.txt";
263 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping.txt";
264 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";
265 public static final String LIMIT_SPEC_FOR_PROT_EX = null; // e.g. "HUMAN"; set to null for not using this feature (default).
266 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH_MAPPED = "_dc_MAPPED_secondary_features_fitch"
267 + ForesterConstants.PHYLO_XML_SUFFIX;
268 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts_MAPPED.txt";
269 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_MAPPED.txt";
270 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";
271 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";
272 private static final boolean CALC_SIMILARITY_SCORES = false;
274 public static void main( final String args[] ) {
275 final long start_time = new Date().getTime();
276 // final StringBuffer log = new StringBuffer();
277 final StringBuilder html_desc = new StringBuilder();
278 ForesterUtil.printProgramInformation( surfacing.PRG_NAME,
279 surfacing.PRG_VERSION,
283 final String nl = ForesterUtil.LINE_SEPARATOR;
284 html_desc.append( "<table>" + nl );
285 html_desc.append( "<tr><td>Produced by:</td><td>" + surfacing.PRG_NAME + "</td></tr>" + nl );
286 html_desc.append( "<tr><td>Version:</td><td>" + surfacing.PRG_VERSION + "</td></tr>" + nl );
287 html_desc.append( "<tr><td>Release Date:</td><td>" + surfacing.PRG_DATE + "</td></tr>" + nl );
288 html_desc.append( "<tr><td>Contact:</td><td>" + surfacing.E_MAIL + "</td></tr>" + nl );
289 html_desc.append( "<tr><td>WWW:</td><td>" + surfacing.WWW + "</td></tr>" + nl );
290 CommandLineArguments cla = null;
292 cla = new CommandLineArguments( args );
294 catch ( final Exception e ) {
295 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
297 if ( cla.isOptionSet( surfacing.HELP_OPTION_1 ) || cla.isOptionSet( surfacing.HELP_OPTION_2 ) ) {
298 surfacing.printHelp();
301 if ( ( args.length < 1 ) ) {
302 surfacing.printHelp();
305 final List<String> allowed_options = new ArrayList<String>();
306 allowed_options.add( surfacing.NOT_IGNORE_DUFS_OPTION );
307 allowed_options.add( surfacing.MAX_FS_E_VALUE_OPTION );
308 allowed_options.add( surfacing.MAX_I_E_VALUE_OPTION );
309 allowed_options.add( surfacing.DETAILEDNESS_OPTION );
310 allowed_options.add( surfacing.OUTPUT_FILE_OPTION );
311 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_OPTION );
312 allowed_options.add( surfacing.SPECIES_MATRIX_OPTION );
313 allowed_options.add( surfacing.SCORING_OPTION );
314 allowed_options.add( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
315 allowed_options.add( surfacing.NO_ENGULFING_OVERLAP_OPTION );
316 allowed_options.add( surfacing.DOMAIN_COUNT_SORT_OPTION );
317 allowed_options.add( surfacing.CUTOFF_SCORE_FILE_OPTION );
318 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION );
319 allowed_options.add( surfacing.OUTPUT_DIR_OPTION );
320 allowed_options.add( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION );
321 allowed_options.add( surfacing.PFAM_TO_GO_FILE_USE_OPTION );
322 allowed_options.add( surfacing.GO_OBO_FILE_USE_OPTION );
323 allowed_options.add( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION );
324 allowed_options.add( surfacing.GO_NAMESPACE_LIMIT_OPTION );
325 allowed_options.add( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
326 allowed_options.add( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION );
327 allowed_options.add( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS );
328 allowed_options.add( INPUT_SPECIES_TREE_OPTION );
329 allowed_options.add( FILTER_POSITIVE_OPTION );
330 allowed_options.add( FILTER_NEGATIVE_OPTION );
331 allowed_options.add( INPUT_GENOMES_FILE_OPTION );
332 allowed_options.add( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
333 allowed_options.add( FILTER_NEGATIVE_DOMAINS_OPTION );
334 allowed_options.add( IGNORE_VIRAL_IDS );
335 allowed_options.add( SEQ_EXTRACT_OPTION );
336 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
337 allowed_options.add( SECONDARY_FEATURES_PARSIMONY_MAP_FILE );
338 allowed_options.add( PLUS_MINUS_ANALYSIS_OPTION );
339 allowed_options.add( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS );
340 allowed_options.add( DOMAIN_COMBINITONS_COUNTS_OUTPUT_OPTION );
341 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS );
342 allowed_options.add( CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY );
343 allowed_options.add( WRITE_TO_NEXUS_OPTION );
344 allowed_options.add( PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION );
345 allowed_options.add( DA_ANALYSIS_OPTION );
346 allowed_options.add( USE_LAST_IN_FITCH_OPTION );
347 allowed_options.add( PERFORM_DC_FITCH );
348 boolean ignore_dufs = surfacing.IGNORE_DUFS_DEFAULT;
349 boolean ignore_combination_with_same = surfacing.IGNORE_COMBINATION_WITH_SAME_DEFAULLT;
350 double fs_e_value_max = surfacing.MAX_E_VALUE_DEFAULT;
351 double ie_value_max = surfacing.MAX_E_VALUE_DEFAULT;
352 int max_allowed_overlap = surfacing.MAX_ALLOWED_OVERLAP_DEFAULT;
353 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
354 if ( dissallowed_options.length() > 0 ) {
355 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown option(s): " + dissallowed_options );
357 boolean use_last_in_fitch_parsimony = false;
358 if ( cla.isOptionSet( USE_LAST_IN_FITCH_OPTION ) ) {
359 use_last_in_fitch_parsimony = true;
361 boolean write_to_nexus = false;
362 if ( cla.isOptionSet( WRITE_TO_NEXUS_OPTION ) ) {
363 write_to_nexus = true;
365 boolean perform_dc_fich = false;
366 if ( cla.isOptionSet( PERFORM_DC_FITCH ) ) {
367 perform_dc_fich = true;
369 boolean perform_dc_regain_proteins_stats = false;
370 if ( cla.isOptionSet( PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION ) ) {
371 perform_dc_regain_proteins_stats = true;
373 boolean da_analysis = false;
374 if ( cla.isOptionSet( DA_ANALYSIS_OPTION ) ) {
377 boolean output_binary_domain_combinationsfor_graph_analysis = false;
378 if ( cla.isOptionSet( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS ) ) {
379 output_binary_domain_combinationsfor_graph_analysis = true;
381 final boolean output_binary_domain_combinationsfor_counts = false;
382 if ( cla.isOptionSet( DOMAIN_COMBINITONS_COUNTS_OUTPUT_OPTION ) ) {
383 output_binary_domain_combinationsfor_graph_analysis = true;
385 if ( cla.isOptionSet( surfacing.MAX_FS_E_VALUE_OPTION ) ) {
387 fs_e_value_max = cla.getOptionValueAsDouble( surfacing.MAX_FS_E_VALUE_OPTION );
389 catch ( final Exception e ) {
390 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for E-value maximum" );
393 if ( cla.isOptionSet( surfacing.MAX_I_E_VALUE_OPTION ) ) {
395 ie_value_max = cla.getOptionValueAsDouble( surfacing.MAX_I_E_VALUE_OPTION );
397 catch ( final Exception e ) {
398 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for E-value maximum" );
401 if ( cla.isOptionSet( surfacing.MAX_ALLOWED_OVERLAP_OPTION ) ) {
403 max_allowed_overlap = cla.getOptionValueAsInt( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
405 catch ( final Exception e ) {
406 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for maximal allowed domain overlap" );
409 boolean no_engulfing_overlaps = false;
410 if ( cla.isOptionSet( surfacing.NO_ENGULFING_OVERLAP_OPTION ) ) {
411 no_engulfing_overlaps = true;
413 boolean ignore_virus_like_ids = false;
414 if ( cla.isOptionSet( surfacing.IGNORE_VIRAL_IDS ) ) {
415 ignore_virus_like_ids = true;
417 if ( cla.isOptionSet( surfacing.NOT_IGNORE_DUFS_OPTION ) ) {
420 if ( cla.isOptionSet( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION ) ) {
421 ignore_combination_with_same = true;
423 boolean ignore_domains_without_combs_in_all_spec = IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT;
424 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION ) ) {
425 ignore_domains_without_combs_in_all_spec = true;
427 boolean ignore_species_specific_domains = IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT;
428 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION ) ) {
429 ignore_species_specific_domains = true;
431 if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
432 ForesterUtil.fatalError( surfacing.PRG_NAME, "no input species tree file given: "
433 + surfacing.INPUT_SPECIES_TREE_OPTION + "=<file>" );
435 File output_file = null;
436 if ( cla.isOptionSet( surfacing.OUTPUT_FILE_OPTION ) ) {
437 if ( !cla.isOptionValueSet( surfacing.OUTPUT_FILE_OPTION ) ) {
438 ForesterUtil.fatalError( surfacing.PRG_NAME,
439 "no value for domain combinations similarities output file: -"
440 + surfacing.OUTPUT_FILE_OPTION + "=<file>" );
442 output_file = new File( cla.getOptionValue( surfacing.OUTPUT_FILE_OPTION ) );
443 SurfacingUtil.checkForOutputFileWriteability( output_file );
445 File cutoff_scores_file = null;
446 Map<String, Double> individual_score_cutoffs = null;
447 if ( cla.isOptionSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
448 if ( !cla.isOptionValueSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
449 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for individual domain score cutoffs file: -"
450 + surfacing.CUTOFF_SCORE_FILE_OPTION + "=<file>" );
452 cutoff_scores_file = new File( cla.getOptionValue( surfacing.CUTOFF_SCORE_FILE_OPTION ) );
453 final String error = ForesterUtil.isReadableFile( cutoff_scores_file );
454 if ( !ForesterUtil.isEmpty( error ) ) {
455 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read individual domain score cutoffs file: "
459 final BasicTable<String> scores_table = BasicTableParser.parse( cutoff_scores_file, ' ' );
460 individual_score_cutoffs = scores_table.getColumnsAsMapDouble( 0, 1 );
462 catch ( final IOException e ) {
463 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from individual score cutoffs file: " + e );
466 BinaryDomainCombination.DomainCombinationType dc_type = BinaryDomainCombination.DomainCombinationType.BASIC;
467 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS ) ) {
468 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED;
470 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY ) ) {
471 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT;
474 if ( cla.isOptionSet( surfacing.OUTPUT_DIR_OPTION ) ) {
475 if ( !cla.isOptionValueSet( surfacing.OUTPUT_DIR_OPTION ) ) {
476 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for output directory: -"
477 + surfacing.OUTPUT_DIR_OPTION + "=<dir>" );
479 out_dir = new File( cla.getOptionValue( surfacing.OUTPUT_DIR_OPTION ) );
480 if ( out_dir.exists() && ( out_dir.listFiles().length > 0 ) ) {
481 ForesterUtil.fatalError( surfacing.PRG_NAME, "\"" + out_dir + "\" aready exists and is not empty" );
483 if ( !out_dir.exists() ) {
484 final boolean success = out_dir.mkdir();
485 if ( !success || !out_dir.exists() ) {
486 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to create \"" + out_dir + "\"" );
489 if ( !out_dir.canWrite() ) {
490 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot write to \"" + out_dir + "\"" );
493 File positive_filter_file = null;
494 File negative_filter_file = null;
495 File negative_domains_filter_file = null;
496 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) && cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
497 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use both negative and positive protein filter" );
499 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION )
500 && ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) || cla
501 .isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) ) {
503 .fatalError( surfacing.PRG_NAME,
504 "attempt to use both negative or positive protein filter together wirh a negative domains filter" );
506 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
507 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
508 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative filter: -"
509 + surfacing.FILTER_NEGATIVE_OPTION + "=<file>" );
511 negative_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_OPTION ) );
512 final String msg = ForesterUtil.isReadableFile( negative_filter_file );
513 if ( !ForesterUtil.isEmpty( msg ) ) {
514 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_filter_file + "\": "
518 else if ( cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
519 if ( !cla.isOptionValueSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
520 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for positive filter: -"
521 + surfacing.FILTER_POSITIVE_OPTION + "=<file>" );
523 positive_filter_file = new File( cla.getOptionValue( surfacing.FILTER_POSITIVE_OPTION ) );
524 final String msg = ForesterUtil.isReadableFile( positive_filter_file );
525 if ( !ForesterUtil.isEmpty( msg ) ) {
526 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + positive_filter_file + "\": "
530 else if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
531 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
532 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative domains filter: -"
533 + surfacing.FILTER_NEGATIVE_DOMAINS_OPTION + "=<file>" );
535 negative_domains_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) );
536 final String msg = ForesterUtil.isReadableFile( negative_domains_filter_file );
537 if ( !ForesterUtil.isEmpty( msg ) ) {
538 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_domains_filter_file
542 final List<String> plus_minus_analysis_high_copy_base_species = new ArrayList<String>();
543 final List<String> plus_minus_analysis_high_copy_target_species = new ArrayList<String>();
544 final List<String> plus_minus_analysis_high_low_copy_species = new ArrayList<String>();
545 final List<Object> plus_minus_analysis_numbers = new ArrayList<Object>();
546 SurfacingUtil.processPlusMinusAnalysisOption( cla,
547 plus_minus_analysis_high_copy_base_species,
548 plus_minus_analysis_high_copy_target_species,
549 plus_minus_analysis_high_low_copy_species,
550 plus_minus_analysis_numbers );
551 File input_genomes_file = null;
552 if ( cla.isOptionSet( surfacing.INPUT_GENOMES_FILE_OPTION ) ) {
553 if ( !cla.isOptionValueSet( surfacing.INPUT_GENOMES_FILE_OPTION ) ) {
554 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input genomes file: -"
555 + surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>" );
557 input_genomes_file = new File( cla.getOptionValue( surfacing.INPUT_GENOMES_FILE_OPTION ) );
558 final String msg = ForesterUtil.isReadableFile( input_genomes_file );
559 if ( !ForesterUtil.isEmpty( msg ) ) {
561 .fatalError( surfacing.PRG_NAME, "can not read from \"" + input_genomes_file + "\": " + msg );
565 ForesterUtil.fatalError( surfacing.PRG_NAME, "no input genomes file given: "
566 + surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>" );
568 DomainSimilarity.DomainSimilarityScoring scoring = SCORING_DEFAULT;
569 if ( cla.isOptionSet( surfacing.SCORING_OPTION ) ) {
570 if ( !cla.isOptionValueSet( surfacing.SCORING_OPTION ) ) {
571 ForesterUtil.fatalError( surfacing.PRG_NAME,
572 "no value for scoring method for domain combinations similarity calculation: -"
573 + surfacing.SCORING_OPTION + "=<"
574 + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
575 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|"
576 + surfacing.SCORING_COMBINATION_BASED + ">\"" );
578 final String scoring_str = cla.getOptionValue( surfacing.SCORING_OPTION );
579 if ( scoring_str.equals( surfacing.SCORING_DOMAIN_COUNT_BASED ) ) {
580 scoring = DomainSimilarity.DomainSimilarityScoring.DOMAINS;
582 else if ( scoring_str.equals( surfacing.SCORING_COMBINATION_BASED ) ) {
583 scoring = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
585 else if ( scoring_str.equals( surfacing.SCORING_PROTEIN_COUNT_BASED ) ) {
586 scoring = DomainSimilarity.DomainSimilarityScoring.PROTEINS;
589 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + scoring_str
590 + "\" for scoring method for domain combinations similarity calculation: \"-"
591 + surfacing.SCORING_OPTION + "=<" + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
592 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|" + surfacing.SCORING_COMBINATION_BASED + ">\"" );
595 boolean sort_by_species_count_first = false;
596 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION ) ) {
597 sort_by_species_count_first = true;
599 boolean species_matrix = false;
600 if ( cla.isOptionSet( surfacing.SPECIES_MATRIX_OPTION ) ) {
601 species_matrix = true;
603 boolean output_protein_lists_for_all_domains = false;
604 double output_list_of_all_proteins_per_domain_e_value_max = -1;
605 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS ) ) {
606 output_protein_lists_for_all_domains = true;
607 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION ) ) {
609 output_list_of_all_proteins_per_domain_e_value_max = cla
610 .getOptionValueAsDouble( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
612 catch ( final Exception e ) {
613 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for per domain E-value maximum" );
617 Detailedness detailedness = DETAILEDNESS_DEFAULT;
618 if ( cla.isOptionSet( surfacing.DETAILEDNESS_OPTION ) ) {
619 if ( !cla.isOptionValueSet( surfacing.DETAILEDNESS_OPTION ) ) {
620 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for -" + surfacing.DETAILEDNESS_OPTION + "=<"
621 + surfacing.DETAILEDNESS_BASIC + "|" + surfacing.DETAILEDNESS_LIST_IDS + "|"
622 + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
624 final String detness = cla.getOptionValue( surfacing.DETAILEDNESS_OPTION ).toLowerCase();
625 if ( detness.equals( surfacing.DETAILEDNESS_BASIC ) ) {
626 detailedness = DomainSimilarityCalculator.Detailedness.BASIC;
628 else if ( detness.equals( surfacing.DETAILEDNESS_LIST_IDS ) ) {
629 detailedness = DomainSimilarityCalculator.Detailedness.LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES;
631 else if ( detness.equals( surfacing.DETAILEDNESS_PUNCTILIOUS ) ) {
632 detailedness = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
635 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + detness + "\" for detailedness: \"-"
636 + surfacing.DETAILEDNESS_OPTION + "=<" + surfacing.DETAILEDNESS_BASIC + "|"
637 + surfacing.DETAILEDNESS_LIST_IDS + "|" + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
640 String automated_pairwise_comparison_suffix = null;
641 boolean perform_pwc = false;
642 boolean write_pwc_files = false;
643 if ( cla.isOptionSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
645 if ( !cla.isOptionValueSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
646 write_pwc_files = false;
649 write_pwc_files = true;
650 automated_pairwise_comparison_suffix = "_"
651 + cla.getOptionValue( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
654 String query_domain_ids = null;
655 if ( cla.isOptionSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
656 if ( !cla.isOptionValueSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
658 .fatalError( surfacing.PRG_NAME,
659 "no domain ids given for sequences with given domains to be extracted : -"
660 + surfacing.SEQ_EXTRACT_OPTION
661 + "=<ordered domain sequences, domain ids separated by '~', sequences separated by '#'>" );
663 query_domain_ids = cla.getOptionValue( surfacing.SEQ_EXTRACT_OPTION );
665 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field = DOMAIN_SORT_FILD_DEFAULT;
666 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field_for_automated_pwc = DOMAIN_SORT_FILD_DEFAULT;
667 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
668 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
669 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for domain combinations similarities sorting: -"
670 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
671 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
672 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
673 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
674 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|"
675 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
678 final String sort_str = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ).toLowerCase();
679 if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ALPHA ) ) {
680 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
681 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
683 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MAX ) ) {
684 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX;
685 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
687 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MIN ) ) {
688 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MIN;
689 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
691 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MEAN ) ) {
692 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MEAN;
693 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MEAN;
695 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT ) ) {
696 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SPECIES_COUNT;
697 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
699 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SD ) ) {
700 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SD;
701 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
703 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_DIFF ) ) {
704 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
705 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
707 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF ) ) {
708 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
709 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
711 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF ) ) {
712 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
713 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
716 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort_str
717 + "\" for domain combinations similarities sorting: \"-"
718 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
719 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
720 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
721 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
722 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|" + "|"
723 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
727 DomainSimilarity.PRINT_OPTION domain_similarity_print_option = DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT;
728 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
729 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
730 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for print option: -"
731 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
732 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
733 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
735 final String sort = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ).toLowerCase();
736 if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML ) ) {
737 domain_similarity_print_option = DomainSimilarity.PRINT_OPTION.HTML;
739 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML ) ) {
740 ForesterUtil.fatalError( surfacing.PRG_NAME, "simple HTML output not implemented yet :(" );
742 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED ) ) {
743 domain_similarity_print_option = DomainSimilarity.PRINT_OPTION.SIMPLE_TAB_DELIMITED;
746 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort + "\" for print option: -"
747 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
748 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
749 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
752 GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order = DOMAINS_SORT_ORDER_DEFAULT;
753 if ( cla.isOptionSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
754 if ( !cla.isOptionValueSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
755 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for sorting of domain counts: -"
756 + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<" + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|"
757 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
758 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
759 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
761 final String sort = cla.getOptionValue( surfacing.DOMAIN_COUNT_SORT_OPTION ).toLowerCase();
762 if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_ALPHA ) ) {
763 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
765 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT ) ) {
766 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_COUNT;
768 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT ) ) {
769 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_PROTEINS_COUNT;
771 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT ) ) {
772 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.COMBINATIONS_COUNT;
775 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort
776 + "\" for sorting of domain counts: \"-" + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<"
777 + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|" + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
778 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
779 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
782 final String[][] input_file_properties = SurfacingUtil.processInputGenomesFile( input_genomes_file );
783 final int number_of_genomes = input_file_properties.length;
784 if ( number_of_genomes < 2 ) {
785 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot analyze less than two files" );
787 if ( ( number_of_genomes < 3 ) && perform_pwc ) {
788 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use : -"
789 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
790 + "=<suffix> to turn on pairwise analyses with less than three input files" );
792 SurfacingUtil.checkWriteabilityForPairwiseComparisons( domain_similarity_print_option,
793 input_file_properties,
794 automated_pairwise_comparison_suffix,
796 for( int i = 0; i < number_of_genomes; i++ ) {
797 File dcc_outfile = new File( input_file_properties[ i ][ 1 ]
798 + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
799 if ( out_dir != null ) {
800 dcc_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + dcc_outfile );
802 SurfacingUtil.checkForOutputFileWriteability( dcc_outfile );
804 File pfam_to_go_file = null;
805 Map<String, List<GoId>> domain_id_to_go_ids_map = null;
806 int domain_id_to_go_ids_count = 0;
807 if ( cla.isOptionSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
808 if ( !cla.isOptionValueSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
809 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for Pfam to GO mapping file: -"
810 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>" );
812 pfam_to_go_file = new File( cla.getOptionValue( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) );
813 final String error = ForesterUtil.isReadableFile( pfam_to_go_file );
814 if ( !ForesterUtil.isEmpty( error ) ) {
815 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read Pfam to GO mapping file: " + error );
818 final PfamToGoParser parser = new PfamToGoParser( pfam_to_go_file );
819 final List<PfamToGoMapping> pfam_to_go_mappings = parser.parse();
820 domain_id_to_go_ids_map = SurfacingUtil.createDomainIdToGoIdMap( pfam_to_go_mappings );
821 if ( parser.getMappingCount() < domain_id_to_go_ids_map.size() ) {
822 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME,
823 "parser.getMappingCount() < domain_id_to_go_ids_map.size()" );
825 domain_id_to_go_ids_count = parser.getMappingCount();
827 catch ( final IOException e ) {
828 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from Pfam to GO mapping file: " + e );
831 File go_obo_file = null;
832 List<GoTerm> go_terms = null;
833 if ( cla.isOptionSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
834 if ( !cla.isOptionValueSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
835 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO OBO file: -"
836 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>" );
838 if ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) {
839 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO OBO file (-"
840 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>) without Pfam to GO mapping file ("
841 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
843 go_obo_file = new File( cla.getOptionValue( surfacing.GO_OBO_FILE_USE_OPTION ) );
844 final String error = ForesterUtil.isReadableFile( go_obo_file );
845 if ( !ForesterUtil.isEmpty( error ) ) {
846 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read GO OBO file: " + error );
849 final OBOparser parser = new OBOparser( go_obo_file, OBOparser.ReturnType.BASIC_GO_TERM );
850 go_terms = parser.parse();
851 if ( parser.getGoTermCount() != go_terms.size() ) {
853 .unexpectedFatalError( surfacing.PRG_NAME, "parser.getGoTermCount() != go_terms.size()" );
856 catch ( final IOException e ) {
857 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from GO OBO file: " + e );
860 Map<GoId, GoTerm> go_id_to_term_map = null;
861 if ( ( ( domain_id_to_go_ids_map != null ) && ( domain_id_to_go_ids_map.size() > 0 ) )
862 && ( ( go_terms != null ) && ( go_terms.size() > 0 ) ) ) {
863 go_id_to_term_map = GoUtils.createGoIdToGoTermMap( go_terms );
865 GoNameSpace go_namespace_limit = null;
866 if ( cla.isOptionSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
867 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
868 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO namespace limit (-"
869 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<namespace>) without Pfam to GO mapping file ("
870 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>) and GO OBO file (-"
871 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
873 if ( !cla.isOptionValueSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
874 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO namespace limit: \"-"
875 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
876 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
877 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
878 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
880 final String go_namespace_limit_str = cla.getOptionValue( surfacing.GO_NAMESPACE_LIMIT_OPTION )
882 if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION ) ) {
883 go_namespace_limit = GoNameSpace.createMolecularFunction();
885 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS ) ) {
886 go_namespace_limit = GoNameSpace.createBiologicalProcess();
888 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT ) ) {
889 go_namespace_limit = GoNameSpace.createCellularComponent();
892 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + go_namespace_limit_str
893 + "\" for GO namespace limit: \"-" + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
894 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
895 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
896 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
899 if ( ( domain_similarity_sort_field == DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE )
900 && ( number_of_genomes > 2 ) ) {
901 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
903 File[] intree_files = null;
904 Phylogeny[] intrees = null;
905 if ( cla.isOptionSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
906 if ( number_of_genomes < 3 ) {
907 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer gains and losses on input species trees (-"
908 + surfacing.INPUT_SPECIES_TREE_OPTION + " without pairwise analyses ("
909 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
910 + "=<suffix for pairwise comparison output files>)" );
912 if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
913 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input tree: -"
914 + surfacing.INPUT_SPECIES_TREE_OPTION + "=<tree file in phyloXML format>" );
916 final String intrees_str = cla.getOptionValue( surfacing.INPUT_SPECIES_TREE_OPTION );
917 if ( intrees_str.indexOf( "#" ) > 0 ) {
918 final String[] intrees_strs = intrees_str.split( "#" );
919 intree_files = new File[ intrees_strs.length ];
921 for( final String s : intrees_strs ) {
922 intree_files[ i++ ] = new File( s.trim() );
926 intree_files = new File[ 1 ];
927 intree_files[ 0 ] = new File( intrees_str );
929 intrees = SurfacingUtil.obtainAndPreProcessIntrees( intree_files, number_of_genomes, input_file_properties );
931 final Phylogeny intree_0_orig = SurfacingUtil.obtainFirstIntree( intree_files[ 0 ] );
932 long random_number_seed_for_fitch_parsimony = 0l;
933 boolean radomize_fitch_parsimony = false;
934 if ( cla.isOptionSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
935 if ( !cla.isOptionValueSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
936 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for random number seed: -"
937 + surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION + "=<seed>" );
940 random_number_seed_for_fitch_parsimony = cla
941 .getOptionValueAsLong( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
943 catch ( final IOException e ) {
944 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
946 radomize_fitch_parsimony = true;
948 SortedSet<String> filter = null;
949 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
950 || ( negative_domains_filter_file != null ) ) {
951 filter = new TreeSet<String>();
952 if ( positive_filter_file != null ) {
953 SurfacingUtil.processFilter( positive_filter_file, filter );
955 else if ( negative_filter_file != null ) {
956 SurfacingUtil.processFilter( negative_filter_file, filter );
958 else if ( negative_domains_filter_file != null ) {
959 SurfacingUtil.processFilter( negative_domains_filter_file, filter );
962 Map<String, Set<String>>[] domain_id_to_secondary_features_maps = null;
963 File[] secondary_features_map_files = null;
964 final File domain_lengths_analysis_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
965 + DOMAIN_LENGTHS_ANALYSIS_SUFFIX );
966 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
967 SurfacingUtil.checkForOutputFileWriteability( domain_lengths_analysis_outfile );
969 if ( cla.isOptionSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
970 if ( !cla.isOptionValueSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
971 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for secondary features map file: -"
972 + surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE + "=<file>" );
974 final String[] secondary_features_map_files_strs = cla
975 .getOptionValue( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ).split( "#" );
976 secondary_features_map_files = new File[ secondary_features_map_files_strs.length ];
977 domain_id_to_secondary_features_maps = new Map[ secondary_features_map_files_strs.length ];
979 for( final String secondary_features_map_files_str : secondary_features_map_files_strs ) {
980 secondary_features_map_files[ i ] = new File( secondary_features_map_files_str );
981 final String error = ForesterUtil.isReadableFile( secondary_features_map_files[ i ] );
982 if ( !ForesterUtil.isEmpty( error ) ) {
983 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read secondary features map file: " + error );
986 domain_id_to_secondary_features_maps[ i ] = SurfacingUtil
987 .createDomainIdToSecondaryFeaturesMap( secondary_features_map_files[ i ] );
989 catch ( final IOException e ) {
990 ForesterUtil.fatalError( surfacing.PRG_NAME,
991 "cannot read secondary features map file: " + e.getMessage() );
993 catch ( final Exception e ) {
994 ForesterUtil.fatalError( surfacing.PRG_NAME, "problem with contents of features map file ["
995 + secondary_features_map_files[ i ] + "]: " + e.getMessage() );
1000 if ( out_dir == null ) {
1001 ForesterUtil.fatalError( surfacing.PRG_NAME, "no output directory indicated (-"
1002 + surfacing.OUTPUT_DIR_OPTION + "=<dir>)" );
1004 if ( output_file == null ) {
1005 ForesterUtil.fatalError( surfacing.PRG_NAME, "no name for (main) output file indicated (-"
1006 + surfacing.OUTPUT_FILE_OPTION + "=<file>)" );
1008 if ( ( domain_id_to_go_ids_map == null ) || domain_id_to_go_ids_map.isEmpty() ) {
1009 ForesterUtil.fatalError( surfacing.PRG_NAME,
1010 "no (acceptable) Pfam to GO id mapping file provided ('pfam2go file') (-"
1011 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1013 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1014 ForesterUtil.fatalError( surfacing.PRG_NAME,
1015 "no (acceptable) go id to term mapping file provided ('GO OBO file') (-"
1016 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1018 System.out.println( "Output directory : " + out_dir );
1019 System.out.println( "Input genomes from : " + input_genomes_file );
1020 html_desc.append( "<tr><td>Input genomes from:</td><td>" + input_genomes_file + "</td></tr>" + nl );
1021 if ( positive_filter_file != null ) {
1022 final int filter_size = filter.size();
1023 System.out.println( "Positive protein filter : " + positive_filter_file + " [" + filter_size
1025 html_desc.append( "<tr><td>Positive protein filter:</td><td>" + positive_filter_file + " [" + filter_size
1026 + " domain ids]</td></tr>" + nl );
1028 if ( negative_filter_file != null ) {
1029 final int filter_size = filter.size();
1030 System.out.println( "Negative protein filter : " + negative_filter_file + " [" + filter_size
1032 html_desc.append( "<tr><td>Negative protein filter:</td><td>" + negative_filter_file + " [" + filter_size
1033 + " domain ids]</td></tr>" + nl );
1035 if ( negative_domains_filter_file != null ) {
1036 final int filter_size = filter.size();
1037 System.out.println( "Negative domain filter : " + negative_domains_filter_file + " [" + filter_size
1039 html_desc.append( "<tr><td>Negative domain filter:</td><td>" + negative_domains_filter_file + " ["
1040 + filter_size + " domain ids]</td></tr>" + nl );
1042 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
1044 for( final String s : plus_minus_analysis_high_copy_base_species ) {
1045 plus0 += "+" + s + " ";
1048 for( final String s : plus_minus_analysis_high_copy_target_species ) {
1049 plus1 += "*" + s + " ";
1052 for( final String s : plus_minus_analysis_high_low_copy_species ) {
1053 minus += "-" + s + " ";
1055 System.out.println( "Plus-minus analysis : " + plus1 + "&& " + plus0 + "&& " + minus );
1056 html_desc.append( "<tr><td>Plus-minus analysis:</td><td>" + plus1 + "&& " + plus0 + "&& " + minus
1057 + "</td></tr>" + nl );
1059 if ( cutoff_scores_file != null ) {
1060 System.out.println( "Cutoff scores file : " + cutoff_scores_file );
1061 html_desc.append( "<tr><td>Cutoff scores file:</td><td>" + cutoff_scores_file + "</td></tr>" + nl );
1063 if ( ie_value_max >= 0.0 ) {
1064 System.out.println( "iE-value maximum (incl) : " + ie_value_max );
1065 html_desc.append( "<tr><td>iE-value maximum (inclusive):</td><td>" + ie_value_max + "</td></tr>" + nl );
1067 if ( fs_e_value_max >= 0.0 ) {
1068 System.out.println( "FS E-value maximum (incl) : " + fs_e_value_max );
1069 html_desc.append( "<tr><td>FS E-value maximum (inclusive):</td><td>" + fs_e_value_max + "</td></tr>" + nl );
1071 if ( output_protein_lists_for_all_domains ) {
1072 System.out.println( "Domain E-value max : " + output_list_of_all_proteins_per_domain_e_value_max );
1073 html_desc.append( "<tr><td>Protein lists: E-value maximum per domain (inclusive):</td><td>"
1074 + output_list_of_all_proteins_per_domain_e_value_max + "</td></tr>" + nl );
1076 System.out.println( "Ignore DUFs : " + ignore_dufs );
1077 if ( ignore_virus_like_ids ) {
1078 System.out.println( "Ignore virus like ids : " + ignore_virus_like_ids );
1079 html_desc.append( "<tr><td>Ignore virus, phage, transposition related ids:</td><td>"
1080 + ignore_virus_like_ids + "</td></tr>" + nl );
1082 html_desc.append( "<tr><td>Ignore DUFs:</td><td>" + ignore_dufs + "</td></tr>" + nl );
1083 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1084 System.out.println( "Max allowed domain overlap : " + max_allowed_overlap );
1085 html_desc.append( "<tr><td>Max allowed domain overlap:</td><td>" + max_allowed_overlap + "</td></tr>" + nl );
1087 if ( no_engulfing_overlaps ) {
1088 System.out.println( "Ignore engulfed domains : " + no_engulfing_overlaps );
1089 html_desc.append( "<tr><td>Ignore (lower confidence) engulfed domains:</td><td>" + no_engulfing_overlaps
1090 + "</td></tr>" + nl );
1092 System.out.println( "Ignore singlet domains : " + ignore_domains_without_combs_in_all_spec );
1094 .append( "<tr><td>Ignore singlet domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1095 + ignore_domains_without_combs_in_all_spec + "</td></tr>" + nl );
1096 System.out.println( "Ignore species specific doms: " + ignore_species_specific_domains );
1098 .append( "<tr><td>Ignore species specific domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1099 + ignore_species_specific_domains + "</td></tr>" + nl );
1100 System.out.println( "Ignore combination with self: " + ignore_combination_with_same );
1101 html_desc.append( "<tr><td>Ignore combination with self for domain combination similarity analyses:</td><td>"
1102 + ignore_combination_with_same + "</td></tr>" + nl );
1103 System.out.println( "Consider directedness : "
1104 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) );
1105 html_desc.append( "<tr><td>Consider directedness of binary domain combinations:</td><td>"
1106 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) + "</td></tr>" + nl );
1107 if ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) {
1108 System.out.println( "Consider adjacency : "
1109 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) );
1110 html_desc.append( "<tr><td>Consider djacency of binary domain combinations:</td><td>"
1111 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) + "</td></tr>"
1114 System.out.println( "Fitch parsimony of DCs : " + perform_dc_fich );
1115 html_desc.append( "<tr><td>Fitch parsimony of DCs:</td><td>" + perform_dc_fich + "</td></tr>" + nl );
1116 if ( perform_dc_fich ) {
1117 System.out.println( "Use last in Fitch parsimony : " + use_last_in_fitch_parsimony );
1118 html_desc.append( "<tr><td>Use last in Fitch parsimony:</td><td>" + use_last_in_fitch_parsimony
1119 + "</td></tr>" + nl );
1121 System.out.println( "Write to Nexus files : " + write_to_nexus );
1122 html_desc.append( "<tr><td>Write to Nexus files:</td><td>" + write_to_nexus + "</td></tr>" + nl );
1123 if ( perform_dc_fich ) {
1124 System.out.println( "DC regain prot stats : " + perform_dc_regain_proteins_stats );
1125 html_desc.append( "<tr><td>DC regain prot stats:</td><td>" + perform_dc_regain_proteins_stats
1126 + "</td></tr>" + nl );
1128 System.out.println( "DA analysis : " + da_analysis );
1129 html_desc.append( "<tr><td>DA analysis :</td><td>" + da_analysis + "</td></tr>" + nl );
1130 System.out.print( "Domain counts sort order : " );
1131 html_desc.append( "<tr><td>Domain counts sort order:</td><td>" );
1132 switch ( dc_sort_order ) {
1133 case ALPHABETICAL_KEY_ID:
1134 System.out.println( "alphabetical" );
1135 html_desc.append( "alphabetical" + "</td></tr>" + nl );
1137 case KEY_DOMAIN_COUNT:
1138 System.out.println( "domain count" );
1139 html_desc.append( "domain count" + "</td></tr>" + nl );
1141 case KEY_DOMAIN_PROTEINS_COUNT:
1142 System.out.println( "domain proteins count" );
1143 html_desc.append( "domain proteins count" + "</td></tr>" + nl );
1145 case COMBINATIONS_COUNT:
1146 System.out.println( "domain combinations count" );
1147 html_desc.append( "domain combinations count" + "</td></tr>" + nl );
1150 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for dc sort order" );
1152 if ( domain_id_to_go_ids_map != null ) {
1153 System.out.println( "Pfam to GO mappings from : " + pfam_to_go_file + " [" + domain_id_to_go_ids_count
1155 html_desc.append( "<tr><td>Pfam to GO mappings from:</td><td>" + pfam_to_go_file + " ["
1156 + domain_id_to_go_ids_count + " mappings]" + "</td></tr>" + nl );
1158 if ( go_terms != null ) {
1159 System.out.println( "GO terms from : " + go_obo_file + " [" + go_terms.size() + " terms]" );
1160 html_desc.append( "<tr><td>GO terms from:</td><td>" + go_obo_file + " [" + go_terms.size() + " terms]"
1161 + "</td></tr>" + nl );
1163 if ( go_namespace_limit != null ) {
1164 System.out.println( "Limit GO terms to : " + go_namespace_limit.toString() );
1165 html_desc.append( "<tr><td>Limit GO terms to</td><td>" + go_namespace_limit + "</td></tr>" + nl );
1167 if ( perform_pwc ) {
1168 System.out.println( "Suffix for PWC files : " + automated_pairwise_comparison_suffix );
1169 html_desc.append( "<tr><td>Suffix for PWC files</td><td>" + automated_pairwise_comparison_suffix
1170 + "</td></tr>" + nl );
1172 if ( out_dir != null ) {
1173 System.out.println( "Output directory : " + out_dir );
1175 if ( query_domain_ids != null ) {
1176 System.out.println( "Query domains (ordered) : " + query_domain_ids );
1177 html_desc.append( "<tr><td></td><td>" + query_domain_ids + "</td></tr>" + nl );
1179 System.out.println( "Write similarities to : " + output_file );
1180 System.out.print( " Scoring method : " );
1181 html_desc.append( "<tr><td>Scoring method:</td><td>" );
1182 switch ( scoring ) {
1184 System.out.println( "domain combinations based" );
1185 html_desc.append( "domain combinations based" + "</td></tr>" + nl );
1188 System.out.println( "domain counts based" );
1189 html_desc.append( "domain counts based" + "</td></tr>" + nl );
1192 System.out.println( "domain proteins counts based" );
1193 html_desc.append( "domain proteins counts based" + "</td></tr>" + nl );
1196 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
1198 System.out.print( " Sort by : " );
1199 html_desc.append( "<tr><td>Sort by:</td><td>" );
1200 switch ( domain_similarity_sort_field ) {
1202 System.out.print( "score minimum" );
1203 html_desc.append( "score minimum" );
1206 System.out.print( "score maximum" );
1207 html_desc.append( "score maximum" );
1210 System.out.print( "score mean" );
1211 html_desc.append( "score mean" );
1214 System.out.print( "score standard deviation" );
1215 html_desc.append( "score standard deviation" );
1218 System.out.print( "species number" );
1219 html_desc.append( "species number" );
1222 System.out.print( "alphabetical domain identifier" );
1223 html_desc.append( "alphabetical domain identifier" );
1225 case MAX_DIFFERENCE:
1226 System.out.print( "(maximal) difference" );
1227 html_desc.append( "(maximal) difference" );
1229 case ABS_MAX_COUNTS_DIFFERENCE:
1230 System.out.print( "absolute (maximal) counts difference" );
1231 html_desc.append( "absolute (maximal) counts difference" );
1233 case MAX_COUNTS_DIFFERENCE:
1234 System.out.print( "(maximal) counts difference" );
1235 html_desc.append( "(maximal) counts difference" );
1238 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1240 if ( sort_by_species_count_first ) {
1241 System.out.println( " (sort by species count first)" );
1242 html_desc.append( " (sort by species count first)" );
1245 System.out.println();
1247 html_desc.append( "</td></tr>" + nl );
1248 System.out.print( " Detailedness : " );
1249 switch ( detailedness ) {
1251 System.out.println( "basic" );
1253 case LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES:
1254 System.out.println( "list combining domains for each species" );
1257 System.out.println( "punctilious" );
1260 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for detailedness" );
1262 System.out.print( " Print option : " );
1263 switch ( domain_similarity_print_option ) {
1265 System.out.println( "HTML" );
1267 case SIMPLE_TAB_DELIMITED:
1268 System.out.println( "simple tab delimited" );
1271 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for print option" );
1273 System.out.print( " Species matrix : " + species_matrix );
1274 System.out.println();
1275 final File dc_data_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + DATA_FILE_SUFFIX );
1276 System.out.println( "Domain comb data output : " + dc_data_file );
1277 html_desc.append( "<tr><td>Domain combination data output:</td><td> " + dc_data_file + " </td></tr>" );
1278 System.out.println();
1279 if ( perform_pwc ) {
1280 System.out.println( "Pairwise comparisons: " );
1281 html_desc.append( "<tr><td>Pairwise comparisons:</td><td></td></tr>" );
1282 System.out.print( " Sort by : " );
1283 html_desc.append( "<tr><td>Sort by:</td><td>" );
1284 switch ( domain_similarity_sort_field_for_automated_pwc ) {
1286 System.out.print( "score mean" );
1287 html_desc.append( "score mean" );
1290 System.out.print( "alphabetical domain identifier" );
1291 html_desc.append( "alphabetical domain identifier" );
1293 case MAX_DIFFERENCE:
1294 System.out.print( "difference" );
1295 html_desc.append( "difference" );
1297 case ABS_MAX_COUNTS_DIFFERENCE:
1298 System.out.print( "absolute counts difference" );
1299 html_desc.append( "absolute counts difference" );
1301 case MAX_COUNTS_DIFFERENCE:
1302 System.out.print( "counts difference" );
1303 html_desc.append( "counts difference" );
1307 .unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1309 System.out.println();
1310 html_desc.append( "</td></tr>" + nl );
1311 if ( ( intrees != null ) && ( intrees.length > 0 ) ) {
1312 for( final File intree_file : intree_files ) {
1313 html_desc.append( "<tr><td>Intree for gain/loss parsimony analysis:</td><td>" + intree_file
1314 + "</td></tr>" + nl );
1315 System.out.println( " Intree for gain/loss pars.: " + intree_file );
1318 if ( radomize_fitch_parsimony ) {
1319 html_desc.append( "<tr><td> Random number seed for Fitch parsimony analysis:</td><td>"
1320 + random_number_seed_for_fitch_parsimony + "</td></tr>" + nl );
1321 System.out.println( " Random number seed : " + random_number_seed_for_fitch_parsimony );
1323 if ( ( domain_id_to_secondary_features_maps != null ) && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
1324 for( int i = 0; i < secondary_features_map_files.length; i++ ) {
1325 html_desc.append( "<tr><td>Secondary features map file:</td><td>"
1326 + secondary_features_map_files[ i ] + "</td></tr>" + nl );
1327 System.out.println( "Secondary features map file : " + secondary_features_map_files[ i ]
1328 + " [mappings for " + domain_id_to_secondary_features_maps[ i ].size() + " domain ids]" );
1330 System.out.println();
1331 System.out.println( "Domain ids to secondary features map:" );
1332 for( final String domain_id : domain_id_to_secondary_features_maps[ i ].keySet() ) {
1333 System.out.print( domain_id );
1334 System.out.print( " => " );
1335 for( final String sec : domain_id_to_secondary_features_maps[ i ].get( domain_id ) ) {
1336 System.out.print( sec );
1337 System.out.print( " " );
1339 System.out.println();
1344 } // if ( perform_pwc ) {
1345 System.out.println();
1346 html_desc.append( "<tr><td>Command line:</td><td>" + nl + nl + cla.getCommandLineArgsAsString() + nl + nl
1347 + "</td></tr>" + nl );
1348 System.out.println( "Command line : " + cla.getCommandLineArgsAsString() );
1349 BufferedWriter[] query_domains_writer_ary = null;
1350 List<String>[] query_domain_ids_array = null;
1351 if ( query_domain_ids != null ) {
1352 final String[] query_domain_ids_str_array = query_domain_ids.split( "#" );
1353 query_domain_ids_array = new ArrayList[ query_domain_ids_str_array.length ];
1354 query_domains_writer_ary = new BufferedWriter[ query_domain_ids_str_array.length ];
1355 for( int i = 0; i < query_domain_ids_str_array.length; i++ ) {
1356 String query_domain_ids_str = query_domain_ids_str_array[ i ];
1357 final String[] query_domain_ids_str_ary = query_domain_ids_str.split( "~" );
1358 final List<String> query = new ArrayList<String>();
1359 for( final String element : query_domain_ids_str_ary ) {
1360 query.add( element );
1362 query_domain_ids_array[ i ] = query;
1363 query_domain_ids_str = query_domain_ids_str.replace( '~', '_' );
1364 String protein_names_writer_str = query_domain_ids_str + surfacing.SEQ_EXTRACT_SUFFIX;
1365 if ( out_dir != null ) {
1366 protein_names_writer_str = out_dir + ForesterUtil.FILE_SEPARATOR + protein_names_writer_str;
1369 query_domains_writer_ary[ i ] = new BufferedWriter( new FileWriter( protein_names_writer_str ) );
1371 catch ( final IOException e ) {
1372 ForesterUtil.fatalError( surfacing.PRG_NAME, "Could not open [" + protein_names_writer_str + "]: "
1373 + e.getLocalizedMessage() );
1377 SortedMap<Species, List<Protein>> protein_lists_per_species = null; //This will only be created if neede.
1378 boolean need_protein_lists_per_species = false;
1379 if ( ( plus_minus_analysis_high_copy_base_species.size() > 0 ) || output_protein_lists_for_all_domains ) {
1380 need_protein_lists_per_species = true;
1382 if ( need_protein_lists_per_species ) {
1383 protein_lists_per_species = new TreeMap<Species, List<Protein>>();
1385 List<GenomeWideCombinableDomains> gwcd_list = new ArrayList<GenomeWideCombinableDomains>( number_of_genomes );
1386 final SortedSet<String> all_domains_encountered = new TreeSet<String>();
1387 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered = new TreeSet<BinaryDomainCombination>();
1388 List<BinaryDomainCombination> all_bin_domain_combinations_gained_fitch = null;
1389 List<BinaryDomainCombination> all_bin_domain_combinations_lost_fitch = null;
1390 if ( ( intrees != null ) && ( intrees.length == 1 ) ) {
1391 all_bin_domain_combinations_gained_fitch = new ArrayList<BinaryDomainCombination>();
1392 all_bin_domain_combinations_lost_fitch = new ArrayList<BinaryDomainCombination>();
1394 DomainLengthsTable domain_lengths_table = new DomainLengthsTable();
1395 final File per_genome_domain_promiscuity_statistics_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR
1396 + output_file + D_PROMISCUITY_FILE_SUFFIX );
1397 BufferedWriter per_genome_domain_promiscuity_statistics_writer = null;
1399 per_genome_domain_promiscuity_statistics_writer = new BufferedWriter( new FileWriter( per_genome_domain_promiscuity_statistics_file ) );
1400 per_genome_domain_promiscuity_statistics_writer.write( "Species:\t" );
1401 per_genome_domain_promiscuity_statistics_writer.write( "Mean:\t" );
1402 per_genome_domain_promiscuity_statistics_writer.write( "SD:\t" );
1403 per_genome_domain_promiscuity_statistics_writer.write( "Median:\t" );
1404 per_genome_domain_promiscuity_statistics_writer.write( "Min:\t" );
1405 per_genome_domain_promiscuity_statistics_writer.write( "Max:\t" );
1406 per_genome_domain_promiscuity_statistics_writer.write( "N:\t" );
1407 per_genome_domain_promiscuity_statistics_writer.write( "Max Promiscuous Domains:"
1408 + ForesterUtil.LINE_SEPARATOR );
1410 catch ( final IOException e2 ) {
1411 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1413 final File log_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + LOG_FILE_SUFFIX );
1414 BufferedWriter log_writer = null;
1416 log_writer = new BufferedWriter( new FileWriter( log_file ) );
1418 catch ( final IOException e2 ) {
1419 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1421 BufferedWriter dc_data_writer = null;
1423 dc_data_writer = new BufferedWriter( new FileWriter( dc_data_file ) );
1424 dc_data_writer.write( DATA_FILE_DESC );
1425 dc_data_writer.write( ForesterUtil.LINE_SEPARATOR );
1427 catch ( final IOException e2 ) {
1428 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1430 final DescriptiveStatistics protein_coverage_stats = new BasicDescriptiveStatistics();
1431 final DescriptiveStatistics all_genomes_domains_per_potein_stats = new BasicDescriptiveStatistics();
1432 final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo = new TreeMap<Integer, Integer>();
1433 final SortedSet<String> domains_which_are_always_single = new TreeSet<String>();
1434 final SortedSet<String> domains_which_are_sometimes_single_sometimes_not = new TreeSet<String>();
1435 final SortedSet<String> domains_which_never_single = new TreeSet<String>();
1436 BufferedWriter domains_per_potein_stats_writer = null;
1438 domains_per_potein_stats_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
1439 + output_file + "_domains_per_potein_stats.txt" ) );
1440 domains_per_potein_stats_writer.write( "Genome" );
1441 domains_per_potein_stats_writer.write( "\t" );
1442 domains_per_potein_stats_writer.write( "Mean" );
1443 domains_per_potein_stats_writer.write( "\t" );
1444 domains_per_potein_stats_writer.write( "SD" );
1445 domains_per_potein_stats_writer.write( "\t" );
1446 domains_per_potein_stats_writer.write( "Median" );
1447 domains_per_potein_stats_writer.write( "\t" );
1448 domains_per_potein_stats_writer.write( "N" );
1449 domains_per_potein_stats_writer.write( "\t" );
1450 domains_per_potein_stats_writer.write( "Min" );
1451 domains_per_potein_stats_writer.write( "\t" );
1452 domains_per_potein_stats_writer.write( "Max" );
1453 domains_per_potein_stats_writer.write( "\n" );
1455 catch ( final IOException e3 ) {
1456 e3.printStackTrace();
1458 Map<String, DescriptiveStatistics> protein_length_stats_by_dc = null;
1459 Map<String, DescriptiveStatistics> domain_number_stats_by_dc = null;
1460 final Map<String, DescriptiveStatistics> domain_length_stats_by_domain = new HashMap<String, DescriptiveStatistics>();
1461 if ( perform_dc_regain_proteins_stats ) {
1462 protein_length_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1463 domain_number_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1466 final SortedMap<String, Set<String>> distinct_domain_architecutures_per_genome = new TreeMap<String, Set<String>>();
1467 final SortedMap<String, Integer> distinct_domain_architecuture_counts = new TreeMap<String, Integer>();
1468 for( int i = 0; i < number_of_genomes; ++i ) {
1469 System.out.println();
1470 System.out.println( ( i + 1 ) + "/" + number_of_genomes );
1471 SurfacingUtil.log( ( i + 1 ) + "/" + number_of_genomes, log_writer );
1472 System.out.println( "Processing : " + input_file_properties[ i ][ 1 ]
1473 + " [" + input_file_properties[ i ][ 0 ] + "]" );
1474 SurfacingUtil.log( "Genome : " + input_file_properties[ i ][ 1 ]
1475 + " [" + input_file_properties[ i ][ 0 ] + "]", log_writer );
1476 HmmscanPerDomainTableParser parser = null;
1477 INDIVIDUAL_SCORE_CUTOFF ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF.NONE;
1478 if ( individual_score_cutoffs != null ) {
1479 ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF_DEFAULT;
1481 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1482 || ( negative_domains_filter_file != null ) ) {
1483 HmmscanPerDomainTableParser.FilterType filter_type = HmmscanPerDomainTableParser.FilterType.NONE;
1484 if ( positive_filter_file != null ) {
1485 filter_type = HmmscanPerDomainTableParser.FilterType.POSITIVE_PROTEIN;
1487 else if ( negative_filter_file != null ) {
1488 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_PROTEIN;
1490 else if ( negative_domains_filter_file != null ) {
1491 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_DOMAIN;
1493 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1494 input_file_properties[ i ][ 1 ],
1501 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1502 input_file_properties[ i ][ 1 ],
1506 if ( fs_e_value_max >= 0.0 ) {
1507 parser.setFsEValueMaximum( fs_e_value_max );
1509 if ( ie_value_max >= 0.0 ) {
1510 parser.setIEValueMaximum( ie_value_max );
1512 parser.setIgnoreDufs( ignore_dufs );
1513 parser.setIgnoreVirusLikeIds( ignore_virus_like_ids );
1514 parser.setIgnoreEngulfedDomains( no_engulfing_overlaps );
1515 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1516 parser.setMaxAllowedOverlap( max_allowed_overlap );
1518 parser.setReturnType( HmmscanPerDomainTableParser.ReturnType.UNORDERED_PROTEIN_DOMAIN_COLLECTION_PER_PROTEIN );
1519 if ( individual_score_cutoffs != null ) {
1520 parser.setIndividualScoreCutoffs( individual_score_cutoffs );
1522 List<Protein> protein_list = null;
1524 protein_list = parser.parse();
1526 catch ( final IOException e ) {
1527 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1529 catch ( final Exception e ) {
1530 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, e.getMessage(), e );
1533 System.out.println( "Domains ignored due to negative domain filter: " );
1534 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToNegativeDomainFilterCountsMap() );
1535 System.out.println( "Domains ignored due to virus like id: " );
1536 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToVirusLikeIdCountsMap() );
1538 final double coverage = ( double ) protein_list.size() / parser.getProteinsEncountered();
1539 protein_coverage_stats.addValue( coverage );
1540 int distinct_das = -1;
1541 if ( da_analysis ) {
1542 final String genome = input_file_properties[ i ][ 0 ];
1543 distinct_das = SurfacingUtil.storeDomainArchitectures( genome,
1544 distinct_domain_architecutures_per_genome,
1546 distinct_domain_architecuture_counts );
1548 System.out.println( "Number of proteins encountered : " + parser.getProteinsEncountered() );
1549 SurfacingUtil.log( "Number of proteins encountered : " + parser.getProteinsEncountered(),
1551 System.out.println( "Number of proteins stored : " + protein_list.size() );
1552 SurfacingUtil.log( "Number of proteins stored : " + protein_list.size(), log_writer );
1553 System.out.println( "Coverage : "
1554 + ForesterUtil.roundToInt( 100.0 * coverage ) + "%" );
1555 SurfacingUtil.log( "Coverage : "
1556 + ForesterUtil.roundToInt( 100.0 * coverage ) + "%",
1558 System.out.println( "Domains encountered : " + parser.getDomainsEncountered() );
1559 SurfacingUtil.log( "Domains encountered : " + parser.getDomainsEncountered(),
1561 System.out.println( "Domains stored : " + parser.getDomainsStored() );
1562 SurfacingUtil.log( "Domains stored : " + parser.getDomainsStored(),
1564 System.out.println( "Distinct domains stored : "
1565 + parser.getDomainsStoredSet().size() );
1566 SurfacingUtil.log( "Distinct domains stored : "
1567 + parser.getDomainsStoredSet().size(), log_writer );
1568 System.out.println( "Domains ignored due to individual score cutoffs: "
1569 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() );
1570 SurfacingUtil.log( "Domains ignored due to individual score cutoffs: "
1571 + parser.getDomainsIgnoredDueToIndividualScoreCutoff(),
1573 System.out.println( "Domains ignored due to FS E-value : "
1574 + parser.getDomainsIgnoredDueToFsEval() );
1575 SurfacingUtil.log( "Domains ignored due to FS E-value : "
1576 + parser.getDomainsIgnoredDueToFsEval(),
1578 System.out.println( "Domains ignored due to iE-value : "
1579 + parser.getDomainsIgnoredDueToIEval() );
1580 SurfacingUtil.log( "Domains ignored due to iE-value : "
1581 + parser.getDomainsIgnoredDueToIEval(),
1583 System.out.println( "Domains ignored due to DUF designation : "
1584 + parser.getDomainsIgnoredDueToDuf() );
1586 .log( "Domains ignored due to DUF designation : " + parser.getDomainsIgnoredDueToDuf(),
1588 if ( ignore_virus_like_ids ) {
1589 System.out.println( "Domains ignored due virus like ids : "
1590 + parser.getDomainsIgnoredDueToVirusLikeIds() );
1591 SurfacingUtil.log( "Domains ignored due virus like ids : "
1592 + parser.getDomainsIgnoredDueToVirusLikeIds(),
1595 System.out.println( "Domains ignored due negative domain filter : "
1596 + parser.getDomainsIgnoredDueToNegativeDomainFilter() );
1597 SurfacingUtil.log( "Domains ignored due negative domain filter : "
1598 + parser.getDomainsIgnoredDueToNegativeDomainFilter(),
1600 System.out.println( "Domains ignored due to overlap : "
1601 + parser.getDomainsIgnoredDueToOverlap() );
1602 SurfacingUtil.log( "Domains ignored due to overlap : "
1603 + parser.getDomainsIgnoredDueToOverlap(),
1605 if ( negative_filter_file != null ) {
1606 System.out.println( "Proteins ignored due to negative filter : "
1607 + parser.getProteinsIgnoredDueToFilter() );
1608 SurfacingUtil.log( "Proteins ignored due to negative filter : "
1609 + parser.getProteinsIgnoredDueToFilter(),
1612 if ( positive_filter_file != null ) {
1613 System.out.println( "Proteins ignored due to positive filter : "
1614 + parser.getProteinsIgnoredDueToFilter() );
1615 SurfacingUtil.log( "Proteins ignored due to positive filter : "
1616 + parser.getProteinsIgnoredDueToFilter(),
1619 if ( da_analysis ) {
1620 System.out.println( "Distinct domain architectures stored : " + distinct_das );
1621 SurfacingUtil.log( "Distinct domain architectures stored : " + distinct_das, log_writer );
1623 System.out.println( "Time for processing : " + parser.getTime() + "ms" );
1624 SurfacingUtil.log( "", log_writer );
1627 for( final Protein protein : protein_list ) {
1628 dc_data_writer.write( SurfacingUtil.proteinToDomainCombinations( protein, count + "", "\t" )
1631 for( final Domain d : protein.getProteinDomains() ) {
1632 final String d_str = d.getDomainId().toString();
1633 if ( !domain_length_stats_by_domain.containsKey( d_str ) ) {
1634 domain_length_stats_by_domain.put( d_str, new BasicDescriptiveStatistics() );
1636 domain_length_stats_by_domain.get( d_str ).addValue( d.getLength() );
1640 catch ( final IOException e ) {
1641 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1643 SurfacingUtil.domainsPerProteinsStatistics( input_file_properties[ i ][ 1 ],
1645 all_genomes_domains_per_potein_stats,
1646 all_genomes_domains_per_potein_histo,
1647 domains_which_are_always_single,
1648 domains_which_are_sometimes_single_sometimes_not,
1649 domains_which_never_single,
1650 domains_per_potein_stats_writer );
1651 domain_lengths_table.addLengths( protein_list );
1652 if ( !da_analysis ) {
1653 gwcd_list.add( BasicGenomeWideCombinableDomains
1654 .createInstance( protein_list,
1655 ignore_combination_with_same,
1656 new BasicSpecies( input_file_properties[ i ][ 1 ] ),
1657 domain_id_to_go_ids_map,
1659 protein_length_stats_by_dc,
1660 domain_number_stats_by_dc ) );
1661 if ( gwcd_list.get( i ).getSize() > 0 ) {
1662 if ( output_binary_domain_combinationsfor_counts ) {
1664 .writeDomainCombinationsCountsFile( input_file_properties,
1666 per_genome_domain_promiscuity_statistics_writer,
1671 if ( output_binary_domain_combinationsfor_graph_analysis ) {
1672 SurfacingUtil.writeBinaryDomainCombinationsFileForGraphAnalysis( input_file_properties,
1678 SurfacingUtil.addAllDomainIdsToSet( gwcd_list.get( i ), all_domains_encountered );
1679 SurfacingUtil.addAllBinaryDomainCombinationToSet( gwcd_list.get( i ),
1680 all_bin_domain_combinations_encountered );
1683 if ( query_domains_writer_ary != null ) {
1684 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1686 SurfacingUtil.extractProteinNames( protein_list,
1687 query_domain_ids_array[ j ],
1688 query_domains_writer_ary[ j ],
1690 LIMIT_SPEC_FOR_PROT_EX );
1691 query_domains_writer_ary[ j ].flush();
1693 catch ( final IOException e ) {
1694 e.printStackTrace();
1698 if ( need_protein_lists_per_species ) {
1699 protein_lists_per_species.put( new BasicSpecies( input_file_properties[ i ][ 1 ] ), protein_list );
1704 catch ( final IOException e2 ) {
1705 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1708 } // for( int i = 0; i < number_of_genomes; ++i ) {
1709 ForesterUtil.programMessage( PRG_NAME, "Wrote domain promiscuities to: "
1710 + per_genome_domain_promiscuity_statistics_file );
1712 if ( da_analysis ) {
1713 SurfacingUtil.performDomainArchitectureAnalysis( distinct_domain_architecutures_per_genome,
1714 distinct_domain_architecuture_counts,
1716 new File( out_dir.toString() + "/" + output_file
1717 + "_DA_counts.txt" ),
1718 new File( out_dir.toString() + "/" + output_file
1719 + "_unique_DAs.txt" ) );
1720 distinct_domain_architecutures_per_genome.clear();
1721 distinct_domain_architecuture_counts.clear();
1725 domains_per_potein_stats_writer.write( "ALL" );
1726 domains_per_potein_stats_writer.write( "\t" );
1727 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.arithmeticMean() + "" );
1728 domains_per_potein_stats_writer.write( "\t" );
1729 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.sampleStandardDeviation() + "" );
1730 domains_per_potein_stats_writer.write( "\t" );
1731 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.median() + "" );
1732 domains_per_potein_stats_writer.write( "\t" );
1733 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getN() + "" );
1734 domains_per_potein_stats_writer.write( "\t" );
1735 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMin() + "" );
1736 domains_per_potein_stats_writer.write( "\t" );
1737 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMax() + "" );
1738 domains_per_potein_stats_writer.write( "\n" );
1739 domains_per_potein_stats_writer.close();
1740 SurfacingUtil.printOutPercentageOfMultidomainProteins( all_genomes_domains_per_potein_histo, log_writer );
1741 ForesterUtil.map2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1742 + "_all_genomes_domains_per_potein_histo.txt" ), all_genomes_domains_per_potein_histo, "\t", "\n" );
1743 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1744 + "_domains_always_single_.txt" ), domains_which_are_always_single, "\n" );
1745 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1746 + "_domains_single_or_combined.txt" ), domains_which_are_sometimes_single_sometimes_not, "\n" );
1747 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1748 + "_domains_always_combined.txt" ), domains_which_never_single, "\n" );
1749 ForesterUtil.programMessage( PRG_NAME,
1750 "Average of proteins with a least one domain assigned: "
1751 + ( 100 * protein_coverage_stats.arithmeticMean() ) + "% (+/-"
1752 + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)" );
1753 ForesterUtil.programMessage( PRG_NAME, "Range of proteins with a least one domain assigned: "
1754 + ( 100 * protein_coverage_stats.getMin() ) + "%-" + ( 100 * protein_coverage_stats.getMax() )
1756 SurfacingUtil.log( "Average of prot with a least one dom assigned : "
1757 + ( 100 * protein_coverage_stats.arithmeticMean() ) + "% (+/-"
1758 + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)",
1760 SurfacingUtil.log( "Range of prot with a least one dom assigned : "
1761 + ( 100 * protein_coverage_stats.getMin() ) + "%-"
1762 + ( 100 * protein_coverage_stats.getMax() ) + "%",
1765 catch ( final IOException e2 ) {
1766 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1768 if ( query_domains_writer_ary != null ) {
1769 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1771 query_domains_writer_ary[ j ].close();
1773 catch ( final IOException e ) {
1774 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1779 per_genome_domain_promiscuity_statistics_writer.close();
1780 dc_data_writer.close();
1783 catch ( final IOException e2 ) {
1784 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1786 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
1788 SurfacingUtil.executeDomainLengthAnalysis( input_file_properties,
1790 domain_lengths_table,
1791 domain_lengths_analysis_outfile );
1793 catch ( final IOException e1 ) {
1794 ForesterUtil.fatalError( surfacing.PRG_NAME, e1.toString() );
1796 System.out.println();
1797 ForesterUtil.programMessage( PRG_NAME, "Wrote domain length data to: " + domain_lengths_analysis_outfile );
1798 System.out.println();
1800 domain_lengths_table = null;
1801 final long analysis_start_time = new Date().getTime();
1802 PairwiseDomainSimilarityCalculator pw_calc = null;
1803 final DomainSimilarityCalculator calc = new BasicDomainSimilarityCalculator( domain_similarity_sort_field,
1804 sort_by_species_count_first,
1805 number_of_genomes == 2,
1806 CALC_SIMILARITY_SCORES );
1807 switch ( scoring ) {
1809 pw_calc = new CombinationsBasedPairwiseDomainSimilarityCalculator();
1812 pw_calc = new DomainCountsBasedPairwiseSimilarityCalculator();
1815 pw_calc = new ProteinCountsBasedPairwiseDomainSimilarityCalculator();
1818 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
1820 DomainSimilarityCalculator.GoAnnotationOutput go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.NONE;
1821 if ( domain_id_to_go_ids_map != null ) {
1822 go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.ALL;
1824 final SortedSet<DomainSimilarity> similarities = calc
1825 .calculateSimilarities( pw_calc,
1827 ignore_domains_without_combs_in_all_spec,
1828 ignore_species_specific_domains );
1829 SurfacingUtil.decoratePrintableDomainSimilarities( similarities, detailedness );
1830 final Map<String, Integer> tax_code_to_id_map = SurfacingUtil.createTaxCodeToIdMap( intrees[ 0 ] );
1832 String my_outfile = output_file.toString();
1833 Map<Character, Writer> split_writers = null;
1834 Writer writer = null;
1835 if ( similarities.size() > MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING ) {
1836 if ( my_outfile.endsWith( ".html" ) ) {
1837 my_outfile = my_outfile.substring( 0, my_outfile.length() - 5 );
1839 split_writers = new HashMap<Character, Writer>();
1840 SurfacingUtil.createSplitWriters( out_dir, my_outfile, split_writers );
1842 else if ( !my_outfile.endsWith( ".html" ) ) {
1843 my_outfile += ".html";
1844 writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) );
1846 List<Species> species_order = null;
1847 if ( species_matrix ) {
1848 species_order = new ArrayList<Species>();
1849 for( int i = 0; i < number_of_genomes; i++ ) {
1850 species_order.add( new BasicSpecies( input_file_properties[ i ][ 1 ] ) );
1853 html_desc.append( "<tr><td>Sum of all distinct binary combinations:</td><td>"
1854 + all_bin_domain_combinations_encountered.size() + "</td></tr>" + nl );
1855 html_desc.append( "<tr><td>Sum of all distinct domains:</td><td>" + all_domains_encountered.size()
1856 + "</td></tr>" + nl );
1857 html_desc.append( "<tr><td>Analysis date/time:</td><td>"
1858 + new java.text.SimpleDateFormat( "yyyy.MM.dd HH:mm:ss" ).format( new java.util.Date() )
1859 + "</td></tr>" + nl );
1860 html_desc.append( "</table>" + nl );
1861 final Writer simple_tab_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
1862 + my_outfile + ".tsv" ) );
1863 SurfacingUtil.writeDomainSimilaritiesToFile( html_desc,
1864 new StringBuilder( number_of_genomes + " genomes" ),
1869 number_of_genomes == 2,
1871 domain_similarity_print_option,
1876 positive_filter_file != null ? filter : null );
1877 simple_tab_writer.close();
1878 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote main output (includes domain similarities) to: \""
1879 + ( out_dir == null ? my_outfile : out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) + "\"" );
1881 catch ( final IOException e ) {
1882 ForesterUtil.fatalError( surfacing.PRG_NAME, "Failed to write similarites to: \"" + output_file + "\" ["
1883 + e.getMessage() + "]" );
1885 System.out.println();
1886 final Species[] species = new Species[ number_of_genomes ];
1887 for( int i = 0; i < number_of_genomes; ++i ) {
1888 species[ i ] = new BasicSpecies( input_file_properties[ i ][ 1 ] );
1890 List<Phylogeny> inferred_trees = null;
1891 if ( ( number_of_genomes > 2 ) && perform_pwc ) {
1892 final PairwiseGenomeComparator pwgc = new PairwiseGenomeComparator();
1893 pwgc.performPairwiseComparisons( html_desc,
1894 sort_by_species_count_first,
1896 ignore_domains_without_combs_in_all_spec,
1897 ignore_species_specific_domains,
1898 domain_similarity_sort_field_for_automated_pwc,
1899 domain_similarity_print_option,
1901 domain_id_to_go_ids_map,
1908 automated_pairwise_comparison_suffix,
1910 surfacing.PAIRWISE_DOMAIN_COMPARISONS_PREFIX,
1915 CALC_SIMILARITY_SCORES,
1917 String matrix_output_file = new String( output_file.toString() );
1918 if ( matrix_output_file.indexOf( '.' ) > 1 ) {
1919 matrix_output_file = matrix_output_file.substring( 0, matrix_output_file.indexOf( '.' ) );
1921 if ( out_dir != null ) {
1922 matrix_output_file = out_dir + ForesterUtil.FILE_SEPARATOR + matrix_output_file;
1923 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
1925 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
1926 + surfacing.MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans() );
1928 .writeMatrixToFile( new File( matrix_output_file
1929 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
1930 pwgc.getSharedBinaryCombinationsBasedDistances() );
1931 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
1932 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
1933 pwgc.getSharedDomainsBasedDistances() );
1934 final Phylogeny nj_gd = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
1935 + surfacing.NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans()
1937 final Phylogeny nj_bc = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
1938 + surfacing.NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
1939 .getSharedBinaryCombinationsBasedDistances().get( 0 ) );
1940 final Phylogeny nj_d = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
1941 + surfacing.NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
1942 .getSharedDomainsBasedDistances().get( 0 ) );
1943 inferred_trees = new ArrayList<Phylogeny>();
1944 inferred_trees.add( nj_gd );
1945 inferred_trees.add( nj_bc );
1946 inferred_trees.add( nj_d );
1947 } // if ( ( output_file != null ) && ( number_of_genomes > 2 ) && !isEmpty( automated_pairwise_comparison_suffix ) )
1948 if ( ( out_dir != null ) && ( !perform_pwc ) ) {
1949 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
1951 if ( write_to_nexus ) {
1952 SurfacingUtil.writePresentToNexus( output_file, positive_filter_file, filter, gwcd_list );
1954 if ( ( ( intrees != null ) && ( intrees.length > 0 ) ) && ( number_of_genomes > 2 ) ) {
1955 final StringBuilder parameters_sb = SurfacingUtil.createParametersAsString( ignore_dufs,
1958 max_allowed_overlap,
1959 no_engulfing_overlaps,
1963 if ( radomize_fitch_parsimony ) {
1964 s += random_number_seed_for_fitch_parsimony + "_";
1967 for( final Phylogeny intree : intrees ) {
1968 final String outfile_name = ForesterUtil.removeSuffix( output_file.toString() ) + s
1969 + ForesterUtil.removeSuffix( intree_files[ i ].toString() );
1970 final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator.createInstance( intree,
1972 SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
1973 radomize_fitch_parsimony,
1977 domain_id_to_go_ids_map,
1980 parameters_sb.toString(),
1981 domain_id_to_secondary_features_maps,
1982 positive_filter_file == null ? null : filter,
1983 output_binary_domain_combinationsfor_graph_analysis,
1984 all_bin_domain_combinations_gained_fitch,
1985 all_bin_domain_combinations_lost_fitch,
1987 protein_length_stats_by_dc,
1988 domain_number_stats_by_dc,
1989 domain_length_stats_by_domain,
1992 use_last_in_fitch_parsimony,
1994 // Listing of all domain combinations gained is only done if only one input tree is used.
1995 if ( ( domain_id_to_secondary_features_maps != null )
1996 && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
1998 for( final Map<String, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
1999 final Map<Species, MappingResults> mapping_results_map = new TreeMap<Species, MappingResults>();
2000 final DomainParsimonyCalculator secondary_features_parsimony = DomainParsimonyCalculator
2001 .createInstance( intree, gwcd_list, domain_id_to_secondary_features_map );
2003 .executeParsimonyAnalysisForSecondaryFeatures( outfile_name
2005 + secondary_features_map_files[ j++ ],
2006 secondary_features_parsimony,
2008 parameters_sb.toString(),
2009 mapping_results_map,
2010 use_last_in_fitch_parsimony );
2012 System.out.println();
2013 System.out.println( "Mapping to secondary features:" );
2014 for( final Species spec : mapping_results_map.keySet() ) {
2015 final MappingResults mapping_results = mapping_results_map.get( spec );
2016 final int total_domains = mapping_results.getSumOfFailures()
2017 + mapping_results.getSumOfSuccesses();
2018 System.out.print( spec + ":" );
2019 System.out.print( " mapped domains = " + mapping_results.getSumOfSuccesses() );
2020 System.out.print( ", not mapped domains = " + mapping_results.getSumOfFailures() );
2021 if ( total_domains > 0 ) {
2022 System.out.println( ", mapped ratio = "
2023 + ( ( 100 * mapping_results.getSumOfSuccesses() ) / total_domains ) + "%" );
2026 System.out.println( ", mapped ratio = n/a (total domains = 0 )" );
2033 } // for( final Phylogeny intree : intrees ) {
2035 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
2036 SurfacingUtil.executePlusMinusAnalysis( output_file,
2037 plus_minus_analysis_high_copy_base_species,
2038 plus_minus_analysis_high_copy_target_species,
2039 plus_minus_analysis_high_low_copy_species,
2041 protein_lists_per_species,
2042 domain_id_to_go_ids_map,
2044 plus_minus_analysis_numbers );
2046 if ( output_protein_lists_for_all_domains ) {
2047 SurfacingUtil.writeProteinListsForAllSpecies( out_dir,
2048 protein_lists_per_species,
2050 output_list_of_all_proteins_per_domain_e_value_max );
2053 if ( all_bin_domain_combinations_gained_fitch != null ) {
2056 .executeFitchGainsAnalysis( new File( output_file
2057 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2058 all_bin_domain_combinations_gained_fitch,
2059 all_domains_encountered.size(),
2060 all_bin_domain_combinations_encountered,
2063 catch ( final IOException e ) {
2064 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2067 if ( all_bin_domain_combinations_lost_fitch != null ) {
2070 .executeFitchGainsAnalysis( new File( output_file
2071 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2072 all_bin_domain_combinations_lost_fitch,
2073 all_domains_encountered.size(),
2074 all_bin_domain_combinations_encountered,
2077 catch ( final IOException e ) {
2078 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2081 final Runtime rt = java.lang.Runtime.getRuntime();
2082 final long free_memory = rt.freeMemory() / 1000000;
2083 final long total_memory = rt.totalMemory() / 1000000;
2084 ForesterUtil.programMessage( PRG_NAME, "Time for analysis : " + ( new Date().getTime() - analysis_start_time )
2086 ForesterUtil.programMessage( PRG_NAME, "Total running time: " + ( new Date().getTime() - start_time ) + "ms " );
2087 ForesterUtil.programMessage( PRG_NAME, "Free memory : " + free_memory + "MB, total memory: "
2088 + total_memory + "MB" );
2089 ForesterUtil.programMessage( PRG_NAME, "If this application is useful to you, please cite:" );
2090 ForesterUtil.programMessage( PRG_NAME, surfacing.WWW );
2091 ForesterUtil.programMessage( PRG_NAME, "OK" );
2092 System.out.println();
2095 private static void printHelp() {
2096 System.out.println();
2097 System.out.println( "Usage:" );
2098 System.out.println();
2099 System.out.println( "% java -Xms256m -Xmx512m -cp forester.jar org.forester.applications." + surfacing.PRG_NAME
2100 + " [options] <phylogen(y|ies) infile> [external node name 1] [name 2] ... [name n]" );
2101 System.out.println();
2102 System.out.println( " Note: This software might need a significant amount of memory (heap space);" );
2104 .println( " hence use \"-Xms128m -Xmx512m\" (or more) to prevent a \"java.lang.OutOfMemoryError\"." );
2105 System.out.println();
2106 System.out.println( " Options: " );
2107 System.out.println( surfacing.DETAILEDNESS_OPTION + ": level of detail for similarities output file (default:"
2108 + DETAILEDNESS_DEFAULT + ")" );
2109 System.out.println( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION
2110 + ": to ignore combinations with self (default: not to ignore)" );
2112 .println( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION
2113 + ": to ignore domains without combinations in any species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2115 .println( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION
2116 + ": to ignore domains specific to one species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2117 System.out.println( surfacing.NOT_IGNORE_DUFS_OPTION
2118 + ": to _not_ ignore DUFs (domains with unknown function) (default: ignore DUFs)" );
2120 .println( surfacing.IGNORE_VIRAL_IDS
2121 + ": to ignore domains with ids containing 'vir', 'retro', 'transpos', 'phage', or starting with 'rv' or 'gag_'" );
2122 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_OPTION + ": sorting for similarities (default: "
2123 + DOMAIN_SORT_FILD_DEFAULT + ")" );
2124 System.out.println( surfacing.OUTPUT_FILE_OPTION + ": name for (main) output file (mandatory)" );
2125 System.out.println( surfacing.MAX_I_E_VALUE_OPTION + ": max (inclusive) iE-value" );
2126 System.out.println( surfacing.MAX_FS_E_VALUE_OPTION + ": max (inclusive) FS E-value" );
2127 System.out.println( surfacing.MAX_ALLOWED_OVERLAP_OPTION + ": maximal allowed domain overlap" );
2128 System.out.println( surfacing.NO_ENGULFING_OVERLAP_OPTION + ": to ignore engulfed lower confidence domains" );
2129 System.out.println( surfacing.SPECIES_MATRIX_OPTION + ": species matrix" );
2130 System.out.println( surfacing.SCORING_OPTION + ": scoring (default:" + SCORING_DEFAULT + ")" );
2131 System.out.println( surfacing.DOMAIN_COUNT_SORT_OPTION + ": sorting for domain counts (default:"
2132 + DOMAINS_SORT_ORDER_DEFAULT + ")" );
2133 System.out.println( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION + ": domain similarity print option (default:"
2134 + DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT + ")" );
2135 System.out.println( surfacing.CUTOFF_SCORE_FILE_OPTION + ": cutoff score file" );
2136 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION
2137 + ": sort by species count first" );
2138 System.out.println( surfacing.OUTPUT_DIR_OPTION + ": output directory" );
2139 System.out.println( surfacing.PFAM_TO_GO_FILE_USE_OPTION + ": Pfam to GO mapping file" );
2140 System.out.println( surfacing.GO_OBO_FILE_USE_OPTION + ": GO terms file (OBO format)" );
2141 System.out.println( surfacing.GO_NAMESPACE_LIMIT_OPTION + ": limit GO term to one GO namespace" );
2142 System.out.println( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
2143 + "[=<suffix for pairwise comparison output files>]: to perform pairwise comparison based analyses" );
2144 System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION
2145 + ": species tree, to perform (Dollo, Fitch) parismony analyses" );
2147 .println( surfacing.INPUT_SPECIES_TREE_OPTION
2148 + "=<treefiles in phyloXML format, separated by #>: to infer domain/binary domain combination gains/losses on given species trees" );
2149 System.out.println( surfacing.FILTER_POSITIVE_OPTION
2150 + "=<file>: to filter out proteins not containing at least one domain listed in <file>" );
2151 System.out.println( surfacing.FILTER_NEGATIVE_OPTION
2152 + "=<file>: to filter out proteins containing at least one domain listed in <file>" );
2153 System.out.println( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION
2154 + "=<file>: to filter out (ignore) domains listed in <file>" );
2155 System.out.println( surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>: to read input files from <file>" );
2157 .println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION
2158 + "=<seed>: seed for random number generator for Fitch Parsimony analysis (type: long, default: no randomization - given a choice, prefer absence" );
2159 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS
2160 + ": to consider directedness in binary combinations: e.g. A-B != B-A" );
2161 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY
2162 + ": to consider directedness and adjacency in binary combinations" );
2164 .println( surfacing.SEQ_EXTRACT_OPTION
2165 + "=<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')" );
2166 System.out.println( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE
2167 + "=<file>: to perfom parsimony analysis on secondary features" );
2168 System.out.println( surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>: to presence/absence genome analysis" );
2169 System.out.println( surfacing.DOMAIN_COMBINITONS_COUNTS_OUTPUT_OPTION
2170 + ": to output binary domain counts (as individual files)" );
2171 System.out.println( surfacing.DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS
2172 + ": to output binary domain combinations for (downstream) graph analysis" );
2173 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS + ": to output all proteins per domain" );
2174 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION
2175 + ": e value max per domain for output of all proteins per domain" );
2176 System.out.println( surfacing.USE_LAST_IN_FITCH_OPTION + ": to use last in Fitch parsimony" );
2177 System.out.println( surfacing.WRITE_TO_NEXUS_OPTION + ": to output in Nexus format" );
2178 System.out.println( PERFORM_DC_FITCH + ": to perform DC Fitch parsimony" );
2179 System.out.println( PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION + ": to perform DC regain protein statistics" );
2180 System.out.println( DA_ANALYSIS_OPTION + ": to do DA analysis" );
2181 System.out.println();
2182 System.out.println( "Example 1: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2183 + " org.forester.application.surfacing p2g=pfam2go_2012_02_07.txt -dufs -cos=Pfam_260_NC1"
2184 + " -no_eo -mo=0 -genomes=eukaryotes.txt -out_dir=out -o=o "
2185 + " -species_tree=tol.xml -obo=gene_ontology_2012_02_07.obo -pos_filter=f.txt -all_prot" );
2186 System.out.println();
2187 System.out.println( "Example 2: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2188 + " org.forester.application.surfacing -detail=punctilious -o=TEST.html -pwc=TEST"
2189 + " -cos=Pfam_ls_22_TC2 -p2g=pfam2go -obo=gene_ontology_edit.obo "
2190 + "-dc_sort=dom -ignore_with_self -no_singles -ie=0.001 -mo=1 -no_eo -genomes=eukaryotes.txt "
2191 + "-ds_output=detailed_html -scoring=domains -sort=alpha " );
2192 System.out.println();