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.DomainSimilaritySortField;
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.PrintableDomainSimilarity;
77 import org.forester.surfacing.PrintableDomainSimilarity.PRINT_OPTION;
78 import org.forester.surfacing.ProteinCountsBasedPairwiseDomainSimilarityCalculator;
79 import org.forester.surfacing.SurfacingUtil;
80 import org.forester.util.BasicDescriptiveStatistics;
81 import org.forester.util.BasicTable;
82 import org.forester.util.BasicTableParser;
83 import org.forester.util.CommandLineArguments;
84 import org.forester.util.DescriptiveStatistics;
85 import org.forester.util.ForesterConstants;
86 import org.forester.util.ForesterUtil;
88 public class surfacing {
90 private static final int MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING = 1000;
91 public final static String DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS = "graph_analysis_out";
92 public final static String DOMAIN_COMBINITONS_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_dc.dot";
93 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_fitch_present_dc.dot";
94 public final static String DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX = ".dcc";
96 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS = "_dollo_gl_d";
97 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_gl_dc";
98 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_DOMAINS = "_fitch_gl_d";
99 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_gl_dc";
101 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS = "_dollo_glc_d";
102 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_glc_dc";
103 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_DOMAINS = "_fitch_glc_d";
104 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_glc_dc";
106 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_BC = "_fitch_gains_dc";
107 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_HTML_BC = "_fitch_gains_dc.html";
108 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_BC = "_fitch_losses_dc";
109 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_HTML_BC = "_fitch_losses_dc.html";
110 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC = "_fitch_present_dc";
111 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_HTML_BC = "_fitch_present_dc.html";
112 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_D = "_dollo_gains_d";
113 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_HTML_D = "_dollo_gains_d.html";
114 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_D = "_dollo_losses_d";
115 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_HTML_D = "_dollo_losses_d.html";
116 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_D = "_dollo_present_d";
117 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_HTML_D = "_dollo_present_d.html";
118 public final static String DOMAINS_PRESENT_NEXUS = "_dom.nex";
119 public final static String BDC_PRESENT_NEXUS = "_dc.nex";
121 public final static String PRG_NAME = "surfacing";
122 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_d_dollo"
123 + ForesterConstants.PHYLO_XML_SUFFIX;
124 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_d_fitch"
125 + ForesterConstants.PHYLO_XML_SUFFIX;
126 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_dc_dollo"
127 + ForesterConstants.PHYLO_XML_SUFFIX;
128 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_dc_fitch"
129 + ForesterConstants.PHYLO_XML_SUFFIX;
130 public static final String NEXUS_EXTERNAL_DOMAINS = "_dom.nex";
131 public static final String NEXUS_EXTERNAL_DOMAIN_COMBINATIONS = "_dc.nex";
132 public static final String NEXUS_SECONDARY_FEATURES = "_secondary_features.nex";
133 public static final String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_gl_secondary_features";
134 public static final String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_glc_secondary_features";
135 public static final String PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES = "_dollo_gains_secondary_features";
136 public static final String PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES = "_dollo_losses_secondary_features";
137 public static final String PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES = "_dollo_present_secondary_features";
138 public static final String SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_secondary_features_dollo"
139 + ForesterConstants.PHYLO_XML_SUFFIX;
140 public static final String PARSIMONY_OUTPUT_DOLLO_ALL_GOID_D_ALL_NAMESPACES = "_dollo_goid_d";
141 public static final String PARSIMONY_OUTPUT_FITCH_ALL_GOID_BC_ALL_NAMESPACES = "_fitch_goid_dc";
142 final static private String HELP_OPTION_1 = "help";
143 final static private String HELP_OPTION_2 = "h";
144 final static private String OUTPUT_DIR_OPTION = "out_dir";
145 final static private String SCORING_OPTION = "scoring";
146 private static final DomainSimilarityScoring SCORING_DEFAULT = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
147 final static private String SCORING_DOMAIN_COUNT_BASED = "domains";
148 final static private String SCORING_PROTEIN_COUNT_BASED = "proteins";
149 final static private String SCORING_COMBINATION_BASED = "combinations";
150 final static private String DETAILEDNESS_OPTION = "detail";
151 private final static Detailedness DETAILEDNESS_DEFAULT = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
152 final static private String SPECIES_MATRIX_OPTION = "smatrix";
153 final static private String DETAILEDNESS_BASIC = "basic";
154 final static private String DETAILEDNESS_LIST_IDS = "list_ids";
155 final static private String DETAILEDNESS_PUNCTILIOUS = "punctilious";
156 final static private String DOMAIN_SIMILARITY_SORT_OPTION = "sort";
157 private static final DomainSimilaritySortField DOMAIN_SORT_FILD_DEFAULT = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
158 final static private String DOMAIN_SIMILARITY_SORT_MIN = "min";
159 final static private String DOMAIN_SIMILARITY_SORT_MAX = "max";
160 final static private String DOMAIN_SIMILARITY_SORT_SD = "sd";
161 final static private String DOMAIN_SIMILARITY_SORT_MEAN = "mean";
162 final static private String DOMAIN_SIMILARITY_SORT_DIFF = "diff";
163 final static private String DOMAIN_SIMILARITY_SORT_COUNTS_DIFF = "count_diff";
164 final static private String DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF = "abs_count_diff";
165 final static private String DOMAIN_SIMILARITY_SORT_SPECIES_COUNT = "species";
166 final static private String DOMAIN_SIMILARITY_SORT_ALPHA = "alpha";
167 final static private String DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION = "species_first";
168 final static private String DOMAIN_COUNT_SORT_OPTION = "dc_sort";
169 private static final GenomeWideCombinableDomainsSortOrder DOMAINS_SORT_ORDER_DEFAULT = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
170 final static private String DOMAIN_COUNT_SORT_ALPHA = "alpha";
171 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT = "dom";
172 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT = "prot";
173 final static private String DOMAIN_COUNT_SORT_COMBINATIONS_COUNT = "comb";
174 final static private String CUTOFF_SCORE_FILE_OPTION = "cos";
175 final static private String NOT_IGNORE_DUFS_OPTION = "dufs";
176 final static private String MAX_E_VALUE_OPTION = "e";
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 = PrintableDomainSimilarity.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 = "2.303";
219 final static private String PRG_DATE = "131022";
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 INDIVIDUAL_SCORE_CUTOFF INDIVIDUAL_SCORE_CUTOFF_DEFAULT = INDIVIDUAL_SCORE_CUTOFF.FULL_SEQUENCE; //TODO look at me! change?
260 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts.txt";
261 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists.txt";
262 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping.txt";
263 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";
264 public static final String LIMIT_SPEC_FOR_PROT_EX = null; // e.g. "HUMAN"; set to null for not using this feature (default).
265 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH_MAPPED = "_dc_MAPPED_secondary_features_fitch"
266 + ForesterConstants.PHYLO_XML_SUFFIX;
267 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts_MAPPED.txt";
268 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_MAPPED.txt";
269 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";
270 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";
271 private static final boolean CALC_SIMILARITY_SCORES = false;
273 public static void main( final String args[] ) {
274 final long start_time = new Date().getTime();
275 // final StringBuffer log = new StringBuffer();
276 final StringBuilder html_desc = new StringBuilder();
277 ForesterUtil.printProgramInformation( surfacing.PRG_NAME,
278 surfacing.PRG_VERSION,
282 final String nl = ForesterUtil.LINE_SEPARATOR;
283 html_desc.append( "<table>" + nl );
284 html_desc.append( "<tr><td>Produced by:</td><td>" + surfacing.PRG_NAME + "</td></tr>" + nl );
285 html_desc.append( "<tr><td>Version:</td><td>" + surfacing.PRG_VERSION + "</td></tr>" + nl );
286 html_desc.append( "<tr><td>Release Date:</td><td>" + surfacing.PRG_DATE + "</td></tr>" + nl );
287 html_desc.append( "<tr><td>Contact:</td><td>" + surfacing.E_MAIL + "</td></tr>" + nl );
288 html_desc.append( "<tr><td>WWW:</td><td>" + surfacing.WWW + "</td></tr>" + nl );
289 CommandLineArguments cla = null;
291 cla = new CommandLineArguments( args );
293 catch ( final Exception e ) {
294 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
296 if ( cla.isOptionSet( surfacing.HELP_OPTION_1 ) || cla.isOptionSet( surfacing.HELP_OPTION_2 ) ) {
297 surfacing.printHelp();
300 if ( ( args.length < 1 ) ) {
301 surfacing.printHelp();
304 final List<String> allowed_options = new ArrayList<String>();
305 allowed_options.add( surfacing.NOT_IGNORE_DUFS_OPTION );
306 allowed_options.add( surfacing.MAX_E_VALUE_OPTION );
307 allowed_options.add( surfacing.DETAILEDNESS_OPTION );
308 allowed_options.add( surfacing.OUTPUT_FILE_OPTION );
309 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_OPTION );
310 allowed_options.add( surfacing.SPECIES_MATRIX_OPTION );
311 allowed_options.add( surfacing.SCORING_OPTION );
312 allowed_options.add( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
313 allowed_options.add( surfacing.NO_ENGULFING_OVERLAP_OPTION );
314 allowed_options.add( surfacing.DOMAIN_COUNT_SORT_OPTION );
315 allowed_options.add( surfacing.CUTOFF_SCORE_FILE_OPTION );
316 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION );
317 allowed_options.add( surfacing.OUTPUT_DIR_OPTION );
318 allowed_options.add( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION );
319 allowed_options.add( surfacing.PFAM_TO_GO_FILE_USE_OPTION );
320 allowed_options.add( surfacing.GO_OBO_FILE_USE_OPTION );
321 allowed_options.add( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION );
322 allowed_options.add( surfacing.GO_NAMESPACE_LIMIT_OPTION );
323 allowed_options.add( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
324 allowed_options.add( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION );
325 allowed_options.add( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS );
326 allowed_options.add( INPUT_SPECIES_TREE_OPTION );
327 allowed_options.add( FILTER_POSITIVE_OPTION );
328 allowed_options.add( FILTER_NEGATIVE_OPTION );
329 allowed_options.add( INPUT_GENOMES_FILE_OPTION );
330 allowed_options.add( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
331 allowed_options.add( FILTER_NEGATIVE_DOMAINS_OPTION );
332 allowed_options.add( IGNORE_VIRAL_IDS );
333 allowed_options.add( SEQ_EXTRACT_OPTION );
334 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
335 allowed_options.add( SECONDARY_FEATURES_PARSIMONY_MAP_FILE );
336 allowed_options.add( PLUS_MINUS_ANALYSIS_OPTION );
337 allowed_options.add( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS );
338 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS );
339 allowed_options.add( CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY );
340 allowed_options.add( WRITE_TO_NEXUS_OPTION );
341 allowed_options.add( PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION );
342 allowed_options.add( DA_ANALYSIS_OPTION );
343 allowed_options.add( USE_LAST_IN_FITCH_OPTION );
344 boolean ignore_dufs = surfacing.IGNORE_DUFS_DEFAULT;
345 boolean ignore_combination_with_same = surfacing.IGNORE_COMBINATION_WITH_SAME_DEFAULLT;
346 double e_value_max = surfacing.MAX_E_VALUE_DEFAULT;
347 int max_allowed_overlap = surfacing.MAX_ALLOWED_OVERLAP_DEFAULT;
348 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
349 if ( dissallowed_options.length() > 0 ) {
350 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown option(s): " + dissallowed_options );
352 boolean use_last_in_fitch_parsimony = false;
353 if ( cla.isOptionSet( USE_LAST_IN_FITCH_OPTION ) ) {
354 use_last_in_fitch_parsimony = true;
356 boolean write_to_nexus = false;
357 if ( cla.isOptionSet( WRITE_TO_NEXUS_OPTION ) ) {
358 write_to_nexus = true;
360 boolean perform_dc_regain_proteins_stats = false;
361 if ( cla.isOptionSet( PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION ) ) {
362 perform_dc_regain_proteins_stats = true;
364 boolean da_analysis = false;
365 if ( cla.isOptionSet( DA_ANALYSIS_OPTION ) ) {
368 boolean output_binary_domain_combinationsfor_graph_analysis = false;
369 if ( cla.isOptionSet( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS ) ) {
370 output_binary_domain_combinationsfor_graph_analysis = true;
372 if ( cla.isOptionSet( surfacing.MAX_E_VALUE_OPTION ) ) {
374 e_value_max = cla.getOptionValueAsDouble( surfacing.MAX_E_VALUE_OPTION );
376 catch ( final Exception e ) {
377 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for E-value maximum" );
380 if ( cla.isOptionSet( surfacing.MAX_ALLOWED_OVERLAP_OPTION ) ) {
382 max_allowed_overlap = cla.getOptionValueAsInt( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
384 catch ( final Exception e ) {
385 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for maximal allowed domain overlap" );
388 boolean no_engulfing_overlaps = false;
389 if ( cla.isOptionSet( surfacing.NO_ENGULFING_OVERLAP_OPTION ) ) {
390 no_engulfing_overlaps = true;
392 boolean ignore_virus_like_ids = false;
393 if ( cla.isOptionSet( surfacing.IGNORE_VIRAL_IDS ) ) {
394 ignore_virus_like_ids = true;
396 if ( cla.isOptionSet( surfacing.NOT_IGNORE_DUFS_OPTION ) ) {
399 if ( cla.isOptionSet( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION ) ) {
400 ignore_combination_with_same = true;
402 boolean ignore_domains_without_combs_in_all_spec = IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT;
403 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION ) ) {
404 ignore_domains_without_combs_in_all_spec = true;
406 boolean ignore_species_specific_domains = IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT;
407 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION ) ) {
408 ignore_species_specific_domains = true;
413 if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
414 ForesterUtil.fatalError( surfacing.PRG_NAME, "no input species tree file given: "
415 + surfacing.INPUT_SPECIES_TREE_OPTION + "=<file>" );
421 File output_file = null;
422 if ( cla.isOptionSet( surfacing.OUTPUT_FILE_OPTION ) ) {
423 if ( !cla.isOptionValueSet( surfacing.OUTPUT_FILE_OPTION ) ) {
424 ForesterUtil.fatalError( surfacing.PRG_NAME,
425 "no value for domain combinations similarities output file: -"
426 + surfacing.OUTPUT_FILE_OPTION + "=<file>" );
428 output_file = new File( cla.getOptionValue( surfacing.OUTPUT_FILE_OPTION ) );
429 SurfacingUtil.checkForOutputFileWriteability( output_file );
431 File cutoff_scores_file = null;
432 Map<String, Double> individual_score_cutoffs = null;
433 if ( cla.isOptionSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
434 if ( !cla.isOptionValueSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
435 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for individual domain score cutoffs file: -"
436 + surfacing.CUTOFF_SCORE_FILE_OPTION + "=<file>" );
438 cutoff_scores_file = new File( cla.getOptionValue( surfacing.CUTOFF_SCORE_FILE_OPTION ) );
439 final String error = ForesterUtil.isReadableFile( cutoff_scores_file );
440 if ( !ForesterUtil.isEmpty( error ) ) {
441 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read individual domain score cutoffs file: "
445 final BasicTable<String> scores_table = BasicTableParser.parse( cutoff_scores_file, ' ' );
446 individual_score_cutoffs = scores_table.getColumnsAsMapDouble( 0, 1 );
448 catch ( final IOException e ) {
449 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from individual score cutoffs file: " + e );
452 BinaryDomainCombination.DomainCombinationType dc_type = BinaryDomainCombination.DomainCombinationType.BASIC;
453 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS ) ) {
454 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED;
456 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY ) ) {
457 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT;
460 if ( cla.isOptionSet( surfacing.OUTPUT_DIR_OPTION ) ) {
461 if ( !cla.isOptionValueSet( surfacing.OUTPUT_DIR_OPTION ) ) {
462 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for output directory: -"
463 + surfacing.OUTPUT_DIR_OPTION + "=<dir>" );
465 out_dir = new File( cla.getOptionValue( surfacing.OUTPUT_DIR_OPTION ) );
466 if ( out_dir.exists() && ( out_dir.listFiles().length > 0 ) ) {
467 ForesterUtil.fatalError( surfacing.PRG_NAME, "\"" + out_dir + "\" aready exists and is not empty" );
469 if ( !out_dir.exists() ) {
470 final boolean success = out_dir.mkdir();
471 if ( !success || !out_dir.exists() ) {
472 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to create \"" + out_dir + "\"" );
475 if ( !out_dir.canWrite() ) {
476 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot write to \"" + out_dir + "\"" );
479 File positive_filter_file = null;
480 File negative_filter_file = null;
481 File negative_domains_filter_file = null;
482 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) && cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
483 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use both negative and positive protein filter" );
485 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION )
486 && ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) || cla
487 .isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) ) {
489 .fatalError( surfacing.PRG_NAME,
490 "attempt to use both negative or positive protein filter together wirh a negative domains filter" );
492 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
493 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
494 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative filter: -"
495 + surfacing.FILTER_NEGATIVE_OPTION + "=<file>" );
497 negative_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_OPTION ) );
498 final String msg = ForesterUtil.isReadableFile( negative_filter_file );
499 if ( !ForesterUtil.isEmpty( msg ) ) {
500 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_filter_file + "\": "
504 else if ( cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
505 if ( !cla.isOptionValueSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
506 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for positive filter: -"
507 + surfacing.FILTER_POSITIVE_OPTION + "=<file>" );
509 positive_filter_file = new File( cla.getOptionValue( surfacing.FILTER_POSITIVE_OPTION ) );
510 final String msg = ForesterUtil.isReadableFile( positive_filter_file );
511 if ( !ForesterUtil.isEmpty( msg ) ) {
512 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + positive_filter_file + "\": "
516 else if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
517 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
518 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative domains filter: -"
519 + surfacing.FILTER_NEGATIVE_DOMAINS_OPTION + "=<file>" );
521 negative_domains_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) );
522 final String msg = ForesterUtil.isReadableFile( negative_domains_filter_file );
523 if ( !ForesterUtil.isEmpty( msg ) ) {
524 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_domains_filter_file
528 final List<String> plus_minus_analysis_high_copy_base_species = new ArrayList<String>();
529 final List<String> plus_minus_analysis_high_copy_target_species = new ArrayList<String>();
530 final List<String> plus_minus_analysis_high_low_copy_species = new ArrayList<String>();
531 final List<Object> plus_minus_analysis_numbers = new ArrayList<Object>();
532 SurfacingUtil.processPlusMinusAnalysisOption( cla,
533 plus_minus_analysis_high_copy_base_species,
534 plus_minus_analysis_high_copy_target_species,
535 plus_minus_analysis_high_low_copy_species,
536 plus_minus_analysis_numbers );
537 File input_genomes_file = null;
538 if ( cla.isOptionSet( surfacing.INPUT_GENOMES_FILE_OPTION ) ) {
539 if ( !cla.isOptionValueSet( surfacing.INPUT_GENOMES_FILE_OPTION ) ) {
540 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input genomes file: -"
541 + surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>" );
543 input_genomes_file = new File( cla.getOptionValue( surfacing.INPUT_GENOMES_FILE_OPTION ) );
544 final String msg = ForesterUtil.isReadableFile( input_genomes_file );
545 if ( !ForesterUtil.isEmpty( msg ) ) {
547 .fatalError( surfacing.PRG_NAME, "can not read from \"" + input_genomes_file + "\": " + msg );
551 ForesterUtil.fatalError( surfacing.PRG_NAME, "no input genomes file given: "
552 + surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>" );
557 DomainSimilarity.DomainSimilarityScoring scoring = SCORING_DEFAULT;
558 if ( cla.isOptionSet( surfacing.SCORING_OPTION ) ) {
559 if ( !cla.isOptionValueSet( surfacing.SCORING_OPTION ) ) {
560 ForesterUtil.fatalError( surfacing.PRG_NAME,
561 "no value for scoring method for domain combinations similarity calculation: -"
562 + surfacing.SCORING_OPTION + "=<"
563 + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
564 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|"
565 + surfacing.SCORING_COMBINATION_BASED + ">\"" );
567 final String scoring_str = cla.getOptionValue( surfacing.SCORING_OPTION );
568 if ( scoring_str.equals( surfacing.SCORING_DOMAIN_COUNT_BASED ) ) {
569 scoring = DomainSimilarity.DomainSimilarityScoring.DOMAINS;
571 else if ( scoring_str.equals( surfacing.SCORING_COMBINATION_BASED ) ) {
572 scoring = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
574 else if ( scoring_str.equals( surfacing.SCORING_PROTEIN_COUNT_BASED ) ) {
575 scoring = DomainSimilarity.DomainSimilarityScoring.PROTEINS;
578 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + scoring_str
579 + "\" for scoring method for domain combinations similarity calculation: \"-"
580 + surfacing.SCORING_OPTION + "=<" + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
581 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|" + surfacing.SCORING_COMBINATION_BASED + ">\"" );
584 boolean sort_by_species_count_first = false;
585 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION ) ) {
586 sort_by_species_count_first = true;
588 boolean species_matrix = false;
589 if ( cla.isOptionSet( surfacing.SPECIES_MATRIX_OPTION ) ) {
590 species_matrix = true;
592 boolean output_protein_lists_for_all_domains = false;
593 double output_list_of_all_proteins_per_domain_e_value_max = -1;
594 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS ) ) {
595 output_protein_lists_for_all_domains = true;
596 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION ) ) {
598 output_list_of_all_proteins_per_domain_e_value_max = cla
599 .getOptionValueAsDouble( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
601 catch ( final Exception e ) {
602 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for per domain E-value maximum" );
606 Detailedness detailedness = DETAILEDNESS_DEFAULT;
607 if ( cla.isOptionSet( surfacing.DETAILEDNESS_OPTION ) ) {
608 if ( !cla.isOptionValueSet( surfacing.DETAILEDNESS_OPTION ) ) {
609 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for -" + surfacing.DETAILEDNESS_OPTION + "=<"
610 + surfacing.DETAILEDNESS_BASIC + "|" + surfacing.DETAILEDNESS_LIST_IDS + "|"
611 + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
613 final String detness = cla.getOptionValue( surfacing.DETAILEDNESS_OPTION ).toLowerCase();
614 if ( detness.equals( surfacing.DETAILEDNESS_BASIC ) ) {
615 detailedness = DomainSimilarityCalculator.Detailedness.BASIC;
617 else if ( detness.equals( surfacing.DETAILEDNESS_LIST_IDS ) ) {
618 detailedness = DomainSimilarityCalculator.Detailedness.LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES;
620 else if ( detness.equals( surfacing.DETAILEDNESS_PUNCTILIOUS ) ) {
621 detailedness = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
624 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + detness + "\" for detailedness: \"-"
625 + surfacing.DETAILEDNESS_OPTION + "=<" + surfacing.DETAILEDNESS_BASIC + "|"
626 + surfacing.DETAILEDNESS_LIST_IDS + "|" + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
629 String automated_pairwise_comparison_suffix = null;
630 boolean perform_pwc = false;
631 boolean write_pwc_files = false;
632 if ( cla.isOptionSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
634 if ( !cla.isOptionValueSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
635 write_pwc_files = false;
638 write_pwc_files = true;
639 automated_pairwise_comparison_suffix = "_"
640 + cla.getOptionValue( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
643 String query_domain_ids = null;
644 if ( cla.isOptionSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
645 if ( !cla.isOptionValueSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
647 .fatalError( surfacing.PRG_NAME,
648 "no domain ids given for sequences with given domains to be extracted : -"
649 + surfacing.SEQ_EXTRACT_OPTION
650 + "=<ordered domain sequences, domain ids separated by '~', sequences separated by '#'>" );
652 query_domain_ids = cla.getOptionValue( surfacing.SEQ_EXTRACT_OPTION );
654 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field = DOMAIN_SORT_FILD_DEFAULT;
655 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field_for_automated_pwc = DOMAIN_SORT_FILD_DEFAULT;
656 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
657 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
658 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for domain combinations similarities sorting: -"
659 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
660 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
661 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
662 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
663 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|"
664 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
667 final String sort_str = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ).toLowerCase();
668 if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ALPHA ) ) {
669 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
670 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
672 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MAX ) ) {
673 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX;
674 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
676 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MIN ) ) {
677 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MIN;
678 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
680 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MEAN ) ) {
681 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MEAN;
682 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MEAN;
684 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT ) ) {
685 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SPECIES_COUNT;
686 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
688 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SD ) ) {
689 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SD;
690 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
692 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_DIFF ) ) {
693 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
694 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
696 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF ) ) {
697 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
698 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
700 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF ) ) {
701 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
702 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
705 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort_str
706 + "\" for domain combinations similarities sorting: \"-"
707 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
708 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
709 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
710 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
711 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|" + "|"
712 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
716 PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option = DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT;
717 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
718 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
719 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for print option: -"
720 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
721 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
722 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
724 final String sort = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ).toLowerCase();
725 if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML ) ) {
726 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.HTML;
728 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML ) ) {
729 ForesterUtil.fatalError( surfacing.PRG_NAME, "simple HTML output not implemented yet :(" );
731 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED ) ) {
732 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.SIMPLE_TAB_DELIMITED;
735 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort + "\" for print option: -"
736 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
737 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
738 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
741 GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order = DOMAINS_SORT_ORDER_DEFAULT;
742 if ( cla.isOptionSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
743 if ( !cla.isOptionValueSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
744 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for sorting of domain counts: -"
745 + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<" + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|"
746 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
747 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
748 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
750 final String sort = cla.getOptionValue( surfacing.DOMAIN_COUNT_SORT_OPTION ).toLowerCase();
751 if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_ALPHA ) ) {
752 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
754 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT ) ) {
755 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_COUNT;
757 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT ) ) {
758 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_PROTEINS_COUNT;
760 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT ) ) {
761 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.COMBINATIONS_COUNT;
764 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort
765 + "\" for sorting of domain counts: \"-" + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<"
766 + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|" + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
767 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
768 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
771 final String[][] input_file_properties = SurfacingUtil.processInputGenomesFile( input_genomes_file );
772 final int number_of_genomes = input_file_properties.length;
773 if ( number_of_genomes < 2 ) {
774 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot analyze less than two files" );
776 if ( ( number_of_genomes < 3 ) && perform_pwc ) {
777 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use : -"
778 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
779 + "=<suffix> to turn on pairwise analyses with less than three input files" );
781 SurfacingUtil.checkWriteabilityForPairwiseComparisons( domain_similarity_print_option,
782 input_file_properties,
783 automated_pairwise_comparison_suffix,
785 for( int i = 0; i < number_of_genomes; i++ ) {
786 File dcc_outfile = new File( input_file_properties[ i ][ 1 ]
787 + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
788 if ( out_dir != null ) {
789 dcc_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + dcc_outfile );
791 SurfacingUtil.checkForOutputFileWriteability( dcc_outfile );
793 File pfam_to_go_file = null;
794 Map<String, List<GoId>> domain_id_to_go_ids_map = null;
795 int domain_id_to_go_ids_count = 0;
796 if ( cla.isOptionSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
797 if ( !cla.isOptionValueSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
798 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for Pfam to GO mapping file: -"
799 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>" );
801 pfam_to_go_file = new File( cla.getOptionValue( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) );
802 final String error = ForesterUtil.isReadableFile( pfam_to_go_file );
803 if ( !ForesterUtil.isEmpty( error ) ) {
804 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read Pfam to GO mapping file: " + error );
807 final PfamToGoParser parser = new PfamToGoParser( pfam_to_go_file );
808 final List<PfamToGoMapping> pfam_to_go_mappings = parser.parse();
809 domain_id_to_go_ids_map = SurfacingUtil.createDomainIdToGoIdMap( pfam_to_go_mappings );
810 if ( parser.getMappingCount() < domain_id_to_go_ids_map.size() ) {
811 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME,
812 "parser.getMappingCount() < domain_id_to_go_ids_map.size()" );
814 domain_id_to_go_ids_count = parser.getMappingCount();
816 catch ( final IOException e ) {
817 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from Pfam to GO mapping file: " + e );
820 File go_obo_file = null;
821 List<GoTerm> go_terms = null;
822 if ( cla.isOptionSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
823 if ( !cla.isOptionValueSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
824 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO OBO file: -"
825 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>" );
827 if ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) {
828 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO OBO file (-"
829 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>) without Pfam to GO mapping file ("
830 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
832 go_obo_file = new File( cla.getOptionValue( surfacing.GO_OBO_FILE_USE_OPTION ) );
833 final String error = ForesterUtil.isReadableFile( go_obo_file );
834 if ( !ForesterUtil.isEmpty( error ) ) {
835 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read GO OBO file: " + error );
838 final OBOparser parser = new OBOparser( go_obo_file, OBOparser.ReturnType.BASIC_GO_TERM );
839 go_terms = parser.parse();
840 if ( parser.getGoTermCount() != go_terms.size() ) {
842 .unexpectedFatalError( surfacing.PRG_NAME, "parser.getGoTermCount() != go_terms.size()" );
845 catch ( final IOException e ) {
846 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from GO OBO file: " + e );
849 Map<GoId, GoTerm> go_id_to_term_map = null;
850 if ( ( ( domain_id_to_go_ids_map != null ) && ( domain_id_to_go_ids_map.size() > 0 ) )
851 && ( ( go_terms != null ) && ( go_terms.size() > 0 ) ) ) {
852 go_id_to_term_map = GoUtils.createGoIdToGoTermMap( go_terms );
854 GoNameSpace go_namespace_limit = null;
855 if ( cla.isOptionSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
856 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
857 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO namespace limit (-"
858 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<namespace>) without Pfam to GO mapping file ("
859 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>) and GO OBO file (-"
860 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
862 if ( !cla.isOptionValueSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
863 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO namespace limit: \"-"
864 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
865 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
866 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
867 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
869 final String go_namespace_limit_str = cla.getOptionValue( surfacing.GO_NAMESPACE_LIMIT_OPTION )
871 if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION ) ) {
872 go_namespace_limit = GoNameSpace.createMolecularFunction();
874 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS ) ) {
875 go_namespace_limit = GoNameSpace.createBiologicalProcess();
877 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT ) ) {
878 go_namespace_limit = GoNameSpace.createCellularComponent();
881 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + go_namespace_limit_str
882 + "\" for GO namespace limit: \"-" + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
883 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
884 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
885 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
888 if ( ( domain_similarity_sort_field == DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE )
889 && ( number_of_genomes > 2 ) ) {
890 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
892 File[] intree_files = null;
893 Phylogeny[] intrees = null;
894 if ( cla.isOptionSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
895 if ( number_of_genomes < 3 ) {
896 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer gains and losses on input species trees (-"
897 + surfacing.INPUT_SPECIES_TREE_OPTION + " without pairwise analyses ("
898 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
899 + "=<suffix for pairwise comparison output files>)" );
901 if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
902 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input tree: -"
903 + surfacing.INPUT_SPECIES_TREE_OPTION + "=<tree file in phyloXML format>" );
905 final String intrees_str = cla.getOptionValue( surfacing.INPUT_SPECIES_TREE_OPTION );
906 if ( intrees_str.indexOf( "#" ) > 0 ) {
907 final String[] intrees_strs = intrees_str.split( "#" );
908 intree_files = new File[ intrees_strs.length ];
910 for( final String s : intrees_strs ) {
911 intree_files[ i++ ] = new File( s.trim() );
915 intree_files = new File[ 1 ];
916 intree_files[ 0 ] = new File( intrees_str );
918 intrees = SurfacingUtil.obtainAndPreProcessIntrees( intree_files, number_of_genomes, input_file_properties );
921 final Phylogeny intree_0_orig = SurfacingUtil.obtainFirstIntree( intree_files[ 0 ]);
922 long random_number_seed_for_fitch_parsimony = 0l;
923 boolean radomize_fitch_parsimony = false;
924 if ( cla.isOptionSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
925 if ( !cla.isOptionValueSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
926 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for random number seed: -"
927 + surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION + "=<seed>" );
930 random_number_seed_for_fitch_parsimony = cla
931 .getOptionValueAsLong( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
933 catch ( final IOException e ) {
934 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
936 radomize_fitch_parsimony = true;
938 SortedSet<String> filter = null;
939 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
940 || ( negative_domains_filter_file != null ) ) {
941 filter = new TreeSet<String>();
942 if ( positive_filter_file != null ) {
943 SurfacingUtil.processFilter( positive_filter_file, filter );
945 else if ( negative_filter_file != null ) {
946 SurfacingUtil.processFilter( negative_filter_file, filter );
948 else if ( negative_domains_filter_file != null ) {
949 SurfacingUtil.processFilter( negative_domains_filter_file, filter );
952 Map<String, Set<String>>[] domain_id_to_secondary_features_maps = null;
953 File[] secondary_features_map_files = null;
954 final File domain_lengths_analysis_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
955 + DOMAIN_LENGTHS_ANALYSIS_SUFFIX );
956 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
957 SurfacingUtil.checkForOutputFileWriteability( domain_lengths_analysis_outfile );
959 if ( cla.isOptionSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
960 if ( !cla.isOptionValueSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
961 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for secondary features map file: -"
962 + surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE + "=<file>" );
964 final String[] secondary_features_map_files_strs = cla
965 .getOptionValue( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ).split( "#" );
966 secondary_features_map_files = new File[ secondary_features_map_files_strs.length ];
967 domain_id_to_secondary_features_maps = new Map[ secondary_features_map_files_strs.length ];
969 for( final String secondary_features_map_files_str : secondary_features_map_files_strs ) {
970 secondary_features_map_files[ i ] = new File( secondary_features_map_files_str );
971 final String error = ForesterUtil.isReadableFile( secondary_features_map_files[ i ] );
972 if ( !ForesterUtil.isEmpty( error ) ) {
973 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read secondary features map file: " + error );
976 domain_id_to_secondary_features_maps[ i ] = SurfacingUtil
977 .createDomainIdToSecondaryFeaturesMap( secondary_features_map_files[ i ] );
979 catch ( final IOException e ) {
980 ForesterUtil.fatalError( surfacing.PRG_NAME,
981 "cannot read secondary features map file: " + e.getMessage() );
983 catch ( final Exception e ) {
984 ForesterUtil.fatalError( surfacing.PRG_NAME, "problem with contents of features map file ["
985 + secondary_features_map_files[ i ] + "]: " + e.getMessage() );
990 if ( out_dir == null ) {
991 ForesterUtil.fatalError( surfacing.PRG_NAME, "no output directory indicated (-"
992 + surfacing.OUTPUT_DIR_OPTION + "=<dir>)" );
994 if ( output_file == null ) {
995 ForesterUtil.fatalError( surfacing.PRG_NAME, "no name for (main) output file indicated (-"
996 + surfacing.OUTPUT_FILE_OPTION + "=<file>)" );
998 if ( ( domain_id_to_go_ids_map == null ) || domain_id_to_go_ids_map.isEmpty() ) {
999 ForesterUtil.fatalError( surfacing.PRG_NAME,
1000 "no (acceptable) Pfam to GO id mapping file provided ('pfam2go file') (-"
1001 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1003 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1004 ForesterUtil.fatalError( surfacing.PRG_NAME,
1005 "no (acceptable) go id to term mapping file provided ('GO OBO file') (-"
1006 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1008 System.out.println( "Output directory : " + out_dir );
1009 System.out.println( "Input genomes from : " + input_genomes_file );
1010 html_desc.append( "<tr><td>Input genomes from:</td><td>" + input_genomes_file + "</td></tr>" + nl );
1011 if ( positive_filter_file != null ) {
1012 final int filter_size = filter.size();
1013 System.out.println( "Positive protein filter : " + positive_filter_file + " [" + filter_size
1015 html_desc.append( "<tr><td>Positive protein filter:</td><td>" + positive_filter_file + " [" + filter_size
1016 + " domain ids]</td></tr>" + nl );
1018 if ( negative_filter_file != null ) {
1019 final int filter_size = filter.size();
1020 System.out.println( "Negative protein filter : " + negative_filter_file + " [" + filter_size
1022 html_desc.append( "<tr><td>Negative protein filter:</td><td>" + negative_filter_file + " [" + filter_size
1023 + " domain ids]</td></tr>" + nl );
1025 if ( negative_domains_filter_file != null ) {
1026 final int filter_size = filter.size();
1027 System.out.println( "Negative domain filter : " + negative_domains_filter_file + " [" + filter_size
1029 html_desc.append( "<tr><td>Negative domain filter:</td><td>" + negative_domains_filter_file + " ["
1030 + filter_size + " domain ids]</td></tr>" + nl );
1032 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
1034 for( final String s : plus_minus_analysis_high_copy_base_species ) {
1035 plus0 += "+" + s + " ";
1038 for( final String s : plus_minus_analysis_high_copy_target_species ) {
1039 plus1 += "*" + s + " ";
1042 for( final String s : plus_minus_analysis_high_low_copy_species ) {
1043 minus += "-" + s + " ";
1045 System.out.println( "Plus-minus analysis : " + plus1 + "&& " + plus0 + "&& " + minus );
1046 html_desc.append( "<tr><td>Plus-minus analysis:</td><td>" + plus1 + "&& " + plus0 + "&& " + minus
1047 + "</td></tr>" + nl );
1049 if ( cutoff_scores_file != null ) {
1050 System.out.println( "Cutoff scores file : " + cutoff_scores_file );
1051 html_desc.append( "<tr><td>Cutoff scores file:</td><td>" + cutoff_scores_file + "</td></tr>" + nl );
1053 if ( e_value_max >= 0.0 ) {
1054 System.out.println( "E-value maximum (inclusive) : " + e_value_max );
1055 html_desc.append( "<tr><td>E-value maximum (inclusive):</td><td>" + e_value_max + "</td></tr>" + nl );
1057 if ( output_protein_lists_for_all_domains ) {
1058 System.out.println( "Domain E-value max : " + output_list_of_all_proteins_per_domain_e_value_max );
1059 html_desc.append( "<tr><td>Protein lists: E-value maximum per domain (inclusive):</td><td>"
1060 + output_list_of_all_proteins_per_domain_e_value_max + "</td></tr>" + nl );
1062 System.out.println( "Ignore DUFs : " + ignore_dufs );
1063 if ( ignore_virus_like_ids ) {
1064 System.out.println( "Ignore virus like ids : " + ignore_virus_like_ids );
1065 html_desc.append( "<tr><td>Ignore virus, phage, transposition related ids:</td><td>"
1066 + ignore_virus_like_ids + "</td></tr>" + nl );
1068 html_desc.append( "<tr><td>Ignore DUFs:</td><td>" + ignore_dufs + "</td></tr>" + nl );
1069 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1070 System.out.println( "Max allowed domain overlap : " + max_allowed_overlap );
1071 html_desc.append( "<tr><td>Max allowed domain overlap:</td><td>" + max_allowed_overlap + "</td></tr>" + nl );
1073 if ( no_engulfing_overlaps ) {
1074 System.out.println( "Ignore engulfed domains : " + no_engulfing_overlaps );
1075 html_desc.append( "<tr><td>Ignore (lower confidence) engulfed domains:</td><td>" + no_engulfing_overlaps
1076 + "</td></tr>" + nl );
1078 System.out.println( "Ignore singlet domains : " + ignore_domains_without_combs_in_all_spec );
1080 .append( "<tr><td>Ignore singlet domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1081 + ignore_domains_without_combs_in_all_spec + "</td></tr>" + nl );
1082 System.out.println( "Ignore species specific doms: " + ignore_species_specific_domains );
1084 .append( "<tr><td>Ignore species specific domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1085 + ignore_species_specific_domains + "</td></tr>" + nl );
1086 System.out.println( "Ignore combination with self: " + ignore_combination_with_same );
1087 html_desc.append( "<tr><td>Ignore combination with self for domain combination similarity analyses:</td><td>"
1088 + ignore_combination_with_same + "</td></tr>" + nl );
1089 System.out.println( "Consider directedness : "
1090 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) );
1091 html_desc.append( "<tr><td>Consider directedness of binary domain combinations:</td><td>"
1092 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) + "</td></tr>" + nl );
1093 if ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) {
1094 System.out.println( "Consider adjacency : "
1095 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) );
1096 html_desc.append( "<tr><td>Consider djacency of binary domain combinations:</td><td>"
1097 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) + "</td></tr>"
1100 System.out.println( "Use last in Fitch parimony : " + use_last_in_fitch_parsimony );
1101 html_desc.append( "<tr><td>Use last in Fitch parimon:</td><td>" + use_last_in_fitch_parsimony + "</td></tr>"
1103 System.out.println( "Write to Nexus files : " + write_to_nexus );
1104 html_desc.append( "<tr><td>Write to Nexus files:</td><td>" + write_to_nexus + "</td></tr>" + nl );
1105 System.out.println( "DC regain prot stats : " + perform_dc_regain_proteins_stats );
1106 html_desc.append( "<tr><td>DC regain prot stats:</td><td>" + perform_dc_regain_proteins_stats + "</td></tr>"
1108 System.out.println( "DA analysis : " + da_analysis );
1109 html_desc.append( "<tr><td>DA analysis :</td><td>" + da_analysis + "</td></tr>" + nl );
1110 System.out.print( "Domain counts sort order : " );
1111 html_desc.append( "<tr><td>Domain counts sort order:</td><td>" );
1112 switch ( dc_sort_order ) {
1113 case ALPHABETICAL_KEY_ID:
1114 System.out.println( "alphabetical" );
1115 html_desc.append( "alphabetical" + "</td></tr>" + nl );
1117 case KEY_DOMAIN_COUNT:
1118 System.out.println( "domain count" );
1119 html_desc.append( "domain count" + "</td></tr>" + nl );
1121 case KEY_DOMAIN_PROTEINS_COUNT:
1122 System.out.println( "domain proteins count" );
1123 html_desc.append( "domain proteins count" + "</td></tr>" + nl );
1125 case COMBINATIONS_COUNT:
1126 System.out.println( "domain combinations count" );
1127 html_desc.append( "domain combinations count" + "</td></tr>" + nl );
1130 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for dc sort order" );
1132 if ( domain_id_to_go_ids_map != null ) {
1133 System.out.println( "Pfam to GO mappings from : " + pfam_to_go_file + " [" + domain_id_to_go_ids_count
1135 html_desc.append( "<tr><td>Pfam to GO mappings from:</td><td>" + pfam_to_go_file + " ["
1136 + domain_id_to_go_ids_count + " mappings]" + "</td></tr>" + nl );
1138 if ( go_terms != null ) {
1139 System.out.println( "GO terms from : " + go_obo_file + " [" + go_terms.size() + " terms]" );
1140 html_desc.append( "<tr><td>GO terms from:</td><td>" + go_obo_file + " [" + go_terms.size() + " terms]"
1141 + "</td></tr>" + nl );
1143 if ( go_namespace_limit != null ) {
1144 System.out.println( "Limit GO terms to : " + go_namespace_limit.toString() );
1145 html_desc.append( "<tr><td>Limit GO terms to</td><td>" + go_namespace_limit + "</td></tr>" + nl );
1147 if ( perform_pwc ) {
1148 System.out.println( "Suffix for PWC files : " + automated_pairwise_comparison_suffix );
1149 html_desc.append( "<tr><td>Suffix for PWC files</td><td>" + automated_pairwise_comparison_suffix
1150 + "</td></tr>" + nl );
1152 if ( out_dir != null ) {
1153 System.out.println( "Output directory : " + out_dir );
1155 if ( query_domain_ids != null ) {
1156 System.out.println( "Query domains (ordered) : " + query_domain_ids );
1157 html_desc.append( "<tr><td></td><td>" + query_domain_ids + "</td></tr>" + nl );
1159 System.out.println( "Write similarities to : " + output_file );
1160 System.out.print( " Scoring method : " );
1161 html_desc.append( "<tr><td>Scoring method:</td><td>" );
1162 switch ( scoring ) {
1164 System.out.println( "domain combinations based" );
1165 html_desc.append( "domain combinations based" + "</td></tr>" + nl );
1168 System.out.println( "domain counts based" );
1169 html_desc.append( "domain counts based" + "</td></tr>" + nl );
1172 System.out.println( "domain proteins counts based" );
1173 html_desc.append( "domain proteins counts based" + "</td></tr>" + nl );
1176 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
1178 System.out.print( " Sort by : " );
1179 html_desc.append( "<tr><td>Sort by:</td><td>" );
1180 switch ( domain_similarity_sort_field ) {
1182 System.out.print( "score minimum" );
1183 html_desc.append( "score minimum" );
1186 System.out.print( "score maximum" );
1187 html_desc.append( "score maximum" );
1190 System.out.print( "score mean" );
1191 html_desc.append( "score mean" );
1194 System.out.print( "score standard deviation" );
1195 html_desc.append( "score standard deviation" );
1198 System.out.print( "species number" );
1199 html_desc.append( "species number" );
1202 System.out.print( "alphabetical domain identifier" );
1203 html_desc.append( "alphabetical domain identifier" );
1205 case MAX_DIFFERENCE:
1206 System.out.print( "(maximal) difference" );
1207 html_desc.append( "(maximal) difference" );
1209 case ABS_MAX_COUNTS_DIFFERENCE:
1210 System.out.print( "absolute (maximal) counts difference" );
1211 html_desc.append( "absolute (maximal) counts difference" );
1213 case MAX_COUNTS_DIFFERENCE:
1214 System.out.print( "(maximal) counts difference" );
1215 html_desc.append( "(maximal) counts difference" );
1218 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1220 if ( sort_by_species_count_first ) {
1221 System.out.println( " (sort by species count first)" );
1222 html_desc.append( " (sort by species count first)" );
1225 System.out.println();
1227 html_desc.append( "</td></tr>" + nl );
1228 System.out.print( " Detailedness : " );
1229 switch ( detailedness ) {
1231 System.out.println( "basic" );
1233 case LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES:
1234 System.out.println( "list combining domains for each species" );
1237 System.out.println( "punctilious" );
1240 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for detailedness" );
1242 System.out.print( " Print option : " );
1243 switch ( domain_similarity_print_option ) {
1245 System.out.println( "HTML" );
1247 case SIMPLE_TAB_DELIMITED:
1248 System.out.println( "simple tab delimited" );
1251 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for print option" );
1253 System.out.print( " Species matrix : " + species_matrix );
1254 System.out.println();
1255 final File dc_data_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + DATA_FILE_SUFFIX );
1256 System.out.println( "Domain comb data output : " + dc_data_file );
1257 html_desc.append( "<tr><td>Domain combination data output:</td><td> " + dc_data_file + " </td></tr>" );
1258 System.out.println();
1259 if ( perform_pwc ) {
1260 System.out.println( "Pairwise comparisons: " );
1261 html_desc.append( "<tr><td>Pairwise comparisons:</td><td></td></tr>" );
1262 System.out.print( " Sort by : " );
1263 html_desc.append( "<tr><td>Sort by:</td><td>" );
1264 switch ( domain_similarity_sort_field_for_automated_pwc ) {
1266 System.out.print( "score mean" );
1267 html_desc.append( "score mean" );
1270 System.out.print( "alphabetical domain identifier" );
1271 html_desc.append( "alphabetical domain identifier" );
1273 case MAX_DIFFERENCE:
1274 System.out.print( "difference" );
1275 html_desc.append( "difference" );
1277 case ABS_MAX_COUNTS_DIFFERENCE:
1278 System.out.print( "absolute counts difference" );
1279 html_desc.append( "absolute counts difference" );
1281 case MAX_COUNTS_DIFFERENCE:
1282 System.out.print( "counts difference" );
1283 html_desc.append( "counts difference" );
1287 .unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1289 System.out.println();
1290 html_desc.append( "</td></tr>" + nl );
1291 if ( ( intrees != null ) && ( intrees.length > 0 ) ) {
1292 for( final File intree_file : intree_files ) {
1293 html_desc.append( "<tr><td>Intree for gain/loss parsimony analysis:</td><td>" + intree_file
1294 + "</td></tr>" + nl );
1295 System.out.println( " Intree for gain/loss pars.: " + intree_file );
1298 if ( radomize_fitch_parsimony ) {
1299 html_desc.append( "<tr><td> Random number seed for Fitch parsimony analysis:</td><td>"
1300 + random_number_seed_for_fitch_parsimony + "</td></tr>" + nl );
1301 System.out.println( " Random number seed : " + random_number_seed_for_fitch_parsimony );
1303 if ( ( domain_id_to_secondary_features_maps != null ) && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
1304 for( int i = 0; i < secondary_features_map_files.length; i++ ) {
1305 html_desc.append( "<tr><td>Secondary features map file:</td><td>"
1306 + secondary_features_map_files[ i ] + "</td></tr>" + nl );
1307 System.out.println( "Secondary features map file : " + secondary_features_map_files[ i ]
1308 + " [mappings for " + domain_id_to_secondary_features_maps[ i ].size() + " domain ids]" );
1310 System.out.println();
1311 System.out.println( "Domain ids to secondary features map:" );
1312 for( final String domain_id : domain_id_to_secondary_features_maps[ i ].keySet() ) {
1313 System.out.print( domain_id );
1314 System.out.print( " => " );
1315 for( final String sec : domain_id_to_secondary_features_maps[ i ].get( domain_id ) ) {
1316 System.out.print( sec );
1317 System.out.print( " " );
1319 System.out.println();
1324 } // if ( perform_pwc ) {
1325 System.out.println();
1326 html_desc.append( "<tr><td>Command line:</td><td>\n" + cla.getCommandLineArgsAsString() + "\n</td></tr>" + nl );
1327 System.out.println( "Command line : " + cla.getCommandLineArgsAsString() );
1328 BufferedWriter[] query_domains_writer_ary = null;
1329 List<String>[] query_domain_ids_array = null;
1330 if ( query_domain_ids != null ) {
1331 final String[] query_domain_ids_str_array = query_domain_ids.split( "#" );
1332 query_domain_ids_array = new ArrayList[ query_domain_ids_str_array.length ];
1333 query_domains_writer_ary = new BufferedWriter[ query_domain_ids_str_array.length ];
1334 for( int i = 0; i < query_domain_ids_str_array.length; i++ ) {
1335 String query_domain_ids_str = query_domain_ids_str_array[ i ];
1336 final String[] query_domain_ids_str_ary = query_domain_ids_str.split( "~" );
1337 final List<String> query = new ArrayList<String>();
1338 for( final String element : query_domain_ids_str_ary ) {
1339 query.add( element );
1341 query_domain_ids_array[ i ] = query;
1342 query_domain_ids_str = query_domain_ids_str.replace( '~', '_' );
1343 String protein_names_writer_str = query_domain_ids_str + surfacing.SEQ_EXTRACT_SUFFIX;
1344 if ( out_dir != null ) {
1345 protein_names_writer_str = out_dir + ForesterUtil.FILE_SEPARATOR + protein_names_writer_str;
1348 query_domains_writer_ary[ i ] = new BufferedWriter( new FileWriter( protein_names_writer_str ) );
1350 catch ( final IOException e ) {
1351 ForesterUtil.fatalError( surfacing.PRG_NAME, "Could not open [" + protein_names_writer_str + "]: "
1352 + e.getLocalizedMessage() );
1356 SortedMap<Species, List<Protein>> protein_lists_per_species = null; //This will only be created if neede.
1357 boolean need_protein_lists_per_species = false;
1358 if ( ( plus_minus_analysis_high_copy_base_species.size() > 0 ) || output_protein_lists_for_all_domains ) {
1359 need_protein_lists_per_species = true;
1361 if ( need_protein_lists_per_species ) {
1362 protein_lists_per_species = new TreeMap<Species, List<Protein>>();
1364 List<GenomeWideCombinableDomains> gwcd_list = new ArrayList<GenomeWideCombinableDomains>( number_of_genomes );
1365 final SortedSet<String> all_domains_encountered = new TreeSet<String>();
1366 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered = new TreeSet<BinaryDomainCombination>();
1367 List<BinaryDomainCombination> all_bin_domain_combinations_gained_fitch = null;
1368 List<BinaryDomainCombination> all_bin_domain_combinations_lost_fitch = null;
1369 if ( ( intrees != null ) && ( intrees.length == 1 ) ) {
1370 all_bin_domain_combinations_gained_fitch = new ArrayList<BinaryDomainCombination>();
1371 all_bin_domain_combinations_lost_fitch = new ArrayList<BinaryDomainCombination>();
1373 DomainLengthsTable domain_lengths_table = new DomainLengthsTable();
1374 final File per_genome_domain_promiscuity_statistics_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR
1375 + output_file + D_PROMISCUITY_FILE_SUFFIX );
1376 BufferedWriter per_genome_domain_promiscuity_statistics_writer = null;
1378 per_genome_domain_promiscuity_statistics_writer = new BufferedWriter( new FileWriter( per_genome_domain_promiscuity_statistics_file ) );
1379 per_genome_domain_promiscuity_statistics_writer.write( "Species:\t" );
1380 per_genome_domain_promiscuity_statistics_writer.write( "Mean:\t" );
1381 per_genome_domain_promiscuity_statistics_writer.write( "SD:\t" );
1382 per_genome_domain_promiscuity_statistics_writer.write( "Median:\t" );
1383 per_genome_domain_promiscuity_statistics_writer.write( "Min:\t" );
1384 per_genome_domain_promiscuity_statistics_writer.write( "Max:\t" );
1385 per_genome_domain_promiscuity_statistics_writer.write( "N:\t" );
1386 per_genome_domain_promiscuity_statistics_writer.write( "Max Promiscuous Domains:"
1387 + ForesterUtil.LINE_SEPARATOR );
1389 catch ( final IOException e2 ) {
1390 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1392 final File log_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + LOG_FILE_SUFFIX );
1393 BufferedWriter log_writer = null;
1395 log_writer = new BufferedWriter( new FileWriter( log_file ) );
1397 catch ( final IOException e2 ) {
1398 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1400 BufferedWriter dc_data_writer = null;
1402 dc_data_writer = new BufferedWriter( new FileWriter( dc_data_file ) );
1403 dc_data_writer.write( DATA_FILE_DESC );
1404 dc_data_writer.write( ForesterUtil.LINE_SEPARATOR );
1406 catch ( final IOException e2 ) {
1407 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1409 final DescriptiveStatistics protein_coverage_stats = new BasicDescriptiveStatistics();
1410 final DescriptiveStatistics all_genomes_domains_per_potein_stats = new BasicDescriptiveStatistics();
1411 final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo = new TreeMap<Integer, Integer>();
1412 final SortedSet<String> domains_which_are_always_single = new TreeSet<String>();
1413 final SortedSet<String> domains_which_are_sometimes_single_sometimes_not = new TreeSet<String>();
1414 final SortedSet<String> domains_which_never_single = new TreeSet<String>();
1415 BufferedWriter domains_per_potein_stats_writer = null;
1417 domains_per_potein_stats_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
1418 + output_file + "_domains_per_potein_stats.txt" ) );
1419 domains_per_potein_stats_writer.write( "Genome" );
1420 domains_per_potein_stats_writer.write( "\t" );
1421 domains_per_potein_stats_writer.write( "Mean" );
1422 domains_per_potein_stats_writer.write( "\t" );
1423 domains_per_potein_stats_writer.write( "SD" );
1424 domains_per_potein_stats_writer.write( "\t" );
1425 domains_per_potein_stats_writer.write( "Median" );
1426 domains_per_potein_stats_writer.write( "\t" );
1427 domains_per_potein_stats_writer.write( "N" );
1428 domains_per_potein_stats_writer.write( "\t" );
1429 domains_per_potein_stats_writer.write( "Min" );
1430 domains_per_potein_stats_writer.write( "\t" );
1431 domains_per_potein_stats_writer.write( "Max" );
1432 domains_per_potein_stats_writer.write( "\n" );
1434 catch ( final IOException e3 ) {
1435 e3.printStackTrace();
1437 Map<String, DescriptiveStatistics> protein_length_stats_by_dc = null;
1438 Map<String, DescriptiveStatistics> domain_number_stats_by_dc = null;
1439 final Map<String, DescriptiveStatistics> domain_length_stats_by_domain = new HashMap<String, DescriptiveStatistics>();
1440 if ( perform_dc_regain_proteins_stats ) {
1441 protein_length_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1442 domain_number_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1445 final SortedMap<String, Set<String>> distinct_domain_architecutures_per_genome = new TreeMap<String, Set<String>>();
1446 final SortedMap<String, Integer> distinct_domain_architecuture_counts = new TreeMap<String, Integer>();
1447 for( int i = 0; i < number_of_genomes; ++i ) {
1448 System.out.println();
1449 System.out.println( ( i + 1 ) + "/" + number_of_genomes );
1450 SurfacingUtil.log( ( i + 1 ) + "/" + number_of_genomes, log_writer );
1451 System.out.println( "Processing : " + input_file_properties[ i ][ 1 ]
1452 + " [" + input_file_properties[ i ][ 0 ] + "]" );
1453 SurfacingUtil.log( "Genome : " + input_file_properties[ i ][ 1 ] + " ["
1454 + input_file_properties[ i ][ 0 ] + "]", log_writer );
1455 HmmscanPerDomainTableParser parser = null;
1456 INDIVIDUAL_SCORE_CUTOFF ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF.NONE;
1457 if ( individual_score_cutoffs != null ) {
1458 ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF_DEFAULT;
1460 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1461 || ( negative_domains_filter_file != null ) ) {
1462 HmmscanPerDomainTableParser.FilterType filter_type = HmmscanPerDomainTableParser.FilterType.NONE;
1463 if ( positive_filter_file != null ) {
1464 filter_type = HmmscanPerDomainTableParser.FilterType.POSITIVE_PROTEIN;
1466 else if ( negative_filter_file != null ) {
1467 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_PROTEIN;
1469 else if ( negative_domains_filter_file != null ) {
1470 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_DOMAIN;
1472 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1473 input_file_properties[ i ][ 1 ],
1480 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1481 input_file_properties[ i ][ 1 ],
1485 if ( e_value_max >= 0.0 ) {
1486 parser.setEValueMaximum( e_value_max );
1488 parser.setIgnoreDufs( ignore_dufs );
1489 parser.setIgnoreVirusLikeIds( ignore_virus_like_ids );
1490 parser.setIgnoreEngulfedDomains( no_engulfing_overlaps );
1491 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1492 parser.setMaxAllowedOverlap( max_allowed_overlap );
1494 parser.setReturnType( HmmscanPerDomainTableParser.ReturnType.UNORDERED_PROTEIN_DOMAIN_COLLECTION_PER_PROTEIN );
1495 if ( individual_score_cutoffs != null ) {
1496 parser.setIndividualScoreCutoffs( individual_score_cutoffs );
1498 List<Protein> protein_list = null;
1500 protein_list = parser.parse();
1502 catch ( final IOException e ) {
1503 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1505 catch ( final Exception e ) {
1506 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, e.getMessage(), e );
1509 System.out.println( "Domains ignored due to negative domain filter: " );
1510 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToNegativeDomainFilterCountsMap() );
1511 System.out.println( "Domains ignored due to virus like id: " );
1512 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToVirusLikeIdCountsMap() );
1514 final double coverage = ( double ) protein_list.size() / parser.getProteinsEncountered();
1515 protein_coverage_stats.addValue( coverage );
1516 int distinct_das = -1;
1517 if ( da_analysis ) {
1518 final String genome = input_file_properties[ i ][ 0 ];
1519 distinct_das = SurfacingUtil.storeDomainArchitectures( genome,
1520 distinct_domain_architecutures_per_genome,
1522 distinct_domain_architecuture_counts );
1524 System.out.println( "Number of proteins encountered : " + parser.getProteinsEncountered() );
1525 SurfacingUtil.log( "Number of proteins encountered : " + parser.getProteinsEncountered(), log_writer );
1526 System.out.println( "Number of proteins stored : " + protein_list.size() );
1527 SurfacingUtil.log( "Number of proteins stored : " + protein_list.size(), log_writer );
1528 System.out.println( "Coverage : "
1529 + ForesterUtil.roundToInt( 100.0 * coverage ) + "%" );
1530 SurfacingUtil.log( "Coverage : " + ForesterUtil.roundToInt( 100.0 * coverage )
1531 + "%", log_writer );
1532 System.out.println( "Domains encountered : " + parser.getDomainsEncountered() );
1533 SurfacingUtil.log( "Domains encountered : " + parser.getDomainsEncountered(), log_writer );
1534 System.out.println( "Domains stored : " + parser.getDomainsStored() );
1535 SurfacingUtil.log( "Domains stored : " + parser.getDomainsStored(), log_writer );
1536 System.out.println( "Distinct domains stored : "
1537 + parser.getDomainsStoredSet().size() );
1538 SurfacingUtil.log( "Distinct domains stored : " + parser.getDomainsStoredSet().size(), log_writer );
1539 System.out.println( "Domains ignored due to individual score cutoffs: "
1540 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() );
1541 SurfacingUtil.log( "Domains ignored due to individual score cutoffs: "
1542 + parser.getDomainsIgnoredDueToIndividualScoreCutoff(),
1544 System.out.println( "Domains ignored due to E-value : "
1545 + parser.getDomainsIgnoredDueToEval() );
1546 SurfacingUtil.log( "Domains ignored due to E-value : " + parser.getDomainsIgnoredDueToEval(), log_writer );
1547 System.out.println( "Domains ignored due to DUF designation : "
1548 + parser.getDomainsIgnoredDueToDuf() );
1549 SurfacingUtil.log( "Domains ignored due to DUF designation : " + parser.getDomainsIgnoredDueToDuf(), log_writer );
1550 if ( ignore_virus_like_ids ) {
1551 System.out.println( "Domains ignored due virus like ids : "
1552 + parser.getDomainsIgnoredDueToVirusLikeIds() );
1553 SurfacingUtil.log( "Domains ignored due virus like ids : " + parser.getDomainsIgnoredDueToVirusLikeIds(),
1556 System.out.println( "Domains ignored due negative domain filter : "
1557 + parser.getDomainsIgnoredDueToNegativeDomainFilter() );
1558 SurfacingUtil.log( "Domains ignored due negative domain filter : "
1559 + parser.getDomainsIgnoredDueToNegativeDomainFilter(),
1561 System.out.println( "Domains ignored due to overlap : "
1562 + parser.getDomainsIgnoredDueToOverlap() );
1563 SurfacingUtil.log( "Domains ignored due to overlap : " + parser.getDomainsIgnoredDueToOverlap(),
1565 if ( negative_filter_file != null ) {
1566 System.out.println( "Proteins ignored due to negative filter : "
1567 + parser.getProteinsIgnoredDueToFilter() );
1568 SurfacingUtil.log( "Proteins ignored due to negative filter : " + parser.getProteinsIgnoredDueToFilter(),
1571 if ( positive_filter_file != null ) {
1572 System.out.println( "Proteins ignored due to positive filter : "
1573 + parser.getProteinsIgnoredDueToFilter() );
1574 SurfacingUtil.log( "Proteins ignored due to positive filter : " + parser.getProteinsIgnoredDueToFilter(),
1577 if ( da_analysis ) {
1578 System.out.println( "Distinct domain architectures stored : " + distinct_das );
1579 SurfacingUtil.log( "Distinct domain architectures stored : " + distinct_das, log_writer );
1581 System.out.println( "Time for processing : " + parser.getTime() + "ms" );
1582 SurfacingUtil.log( "", log_writer );
1585 for( final Protein protein : protein_list ) {
1586 dc_data_writer.write( SurfacingUtil.proteinToDomainCombinations( protein, count + "", "\t" )
1589 for( final Domain d : protein.getProteinDomains() ) {
1590 final String d_str = d.getDomainId().toString();
1591 if ( !domain_length_stats_by_domain.containsKey( d_str ) ) {
1592 domain_length_stats_by_domain.put( d_str, new BasicDescriptiveStatistics() );
1594 domain_length_stats_by_domain.get( d_str ).addValue( d.getLength() );
1598 catch ( final IOException e ) {
1599 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1601 SurfacingUtil.domainsPerProteinsStatistics( input_file_properties[ i ][ 1 ],
1603 all_genomes_domains_per_potein_stats,
1604 all_genomes_domains_per_potein_histo,
1605 domains_which_are_always_single,
1606 domains_which_are_sometimes_single_sometimes_not,
1607 domains_which_never_single,
1608 domains_per_potein_stats_writer );
1609 domain_lengths_table.addLengths( protein_list );
1610 if ( !da_analysis ) {
1611 gwcd_list.add( BasicGenomeWideCombinableDomains
1612 .createInstance( protein_list,
1613 ignore_combination_with_same,
1614 new BasicSpecies( input_file_properties[ i ][ 1 ] ),
1615 domain_id_to_go_ids_map,
1617 protein_length_stats_by_dc,
1618 domain_number_stats_by_dc ) );
1619 if ( gwcd_list.get( i ).getSize() > 0 ) {
1620 SurfacingUtil.writeDomainCombinationsCountsFile( input_file_properties,
1622 per_genome_domain_promiscuity_statistics_writer,
1626 if ( output_binary_domain_combinationsfor_graph_analysis ) {
1627 SurfacingUtil.writeBinaryDomainCombinationsFileForGraphAnalysis( input_file_properties,
1633 SurfacingUtil.addAllDomainIdsToSet( gwcd_list.get( i ), all_domains_encountered );
1634 SurfacingUtil.addAllBinaryDomainCombinationToSet( gwcd_list.get( i ),
1635 all_bin_domain_combinations_encountered );
1638 if ( query_domains_writer_ary != null ) {
1639 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1641 SurfacingUtil.extractProteinNames( protein_list,
1642 query_domain_ids_array[ j ],
1643 query_domains_writer_ary[ j ],
1645 LIMIT_SPEC_FOR_PROT_EX );
1646 query_domains_writer_ary[ j ].flush();
1648 catch ( final IOException e ) {
1649 e.printStackTrace();
1653 if ( need_protein_lists_per_species ) {
1654 protein_lists_per_species.put( new BasicSpecies( input_file_properties[ i ][ 1 ] ), protein_list );
1659 catch ( final IOException e2 ) {
1660 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1663 } // for( int i = 0; i < number_of_genomes; ++i ) {
1664 ForesterUtil.programMessage( PRG_NAME, "Wrote domain promiscuities to: "
1665 + per_genome_domain_promiscuity_statistics_file );
1667 if ( da_analysis ) {
1668 SurfacingUtil.performDomainArchitectureAnalysis( distinct_domain_architecutures_per_genome,
1669 distinct_domain_architecuture_counts,
1671 new File( out_dir.toString() + "/" + output_file
1672 + "_DA_counts.txt" ),
1673 new File( out_dir.toString() + "/" + output_file
1674 + "_unique_DAs.txt" ) );
1675 distinct_domain_architecutures_per_genome.clear();
1676 distinct_domain_architecuture_counts.clear();
1680 domains_per_potein_stats_writer.write( "ALL" );
1681 domains_per_potein_stats_writer.write( "\t" );
1682 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.arithmeticMean() + "" );
1683 domains_per_potein_stats_writer.write( "\t" );
1684 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.sampleStandardDeviation() + "" );
1685 domains_per_potein_stats_writer.write( "\t" );
1686 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.median() + "" );
1687 domains_per_potein_stats_writer.write( "\t" );
1688 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getN() + "" );
1689 domains_per_potein_stats_writer.write( "\t" );
1690 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMin() + "" );
1691 domains_per_potein_stats_writer.write( "\t" );
1692 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMax() + "" );
1693 domains_per_potein_stats_writer.write( "\n" );
1694 domains_per_potein_stats_writer.close();
1695 SurfacingUtil.printOutPercentageOfMultidomainProteins( all_genomes_domains_per_potein_histo, log_writer );
1696 ForesterUtil.map2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1697 + "_all_genomes_domains_per_potein_histo.txt" ), all_genomes_domains_per_potein_histo, "\t", "\n" );
1698 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1699 + "_domains_always_single_.txt" ), domains_which_are_always_single, "\n" );
1700 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1701 + "_domains_single_or_combined.txt" ), domains_which_are_sometimes_single_sometimes_not, "\n" );
1702 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1703 + "_domains_always_combined.txt" ), domains_which_never_single, "\n" );
1704 ForesterUtil.programMessage( PRG_NAME,
1705 "Average of proteins with a least one domain assigned: "
1706 + ( 100 * protein_coverage_stats.arithmeticMean() ) + "% (+/-"
1707 + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)" );
1708 ForesterUtil.programMessage( PRG_NAME, "Range of proteins with a least one domain assigned: "
1709 + ( 100 * protein_coverage_stats.getMin() ) + "%-" + ( 100 * protein_coverage_stats.getMax() )
1711 SurfacingUtil.log( "Average of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.arithmeticMean() )
1712 + "% (+/-" + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)", log_writer );
1713 SurfacingUtil.log( "Range of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.getMin() ) + "%-"
1714 + ( 100 * protein_coverage_stats.getMax() ) + "%", log_writer );
1716 catch ( final IOException e2 ) {
1717 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1719 if ( query_domains_writer_ary != null ) {
1720 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1722 query_domains_writer_ary[ j ].close();
1724 catch ( final IOException e ) {
1725 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1730 per_genome_domain_promiscuity_statistics_writer.close();
1731 dc_data_writer.close();
1734 catch ( final IOException e2 ) {
1735 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1737 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
1739 SurfacingUtil.executeDomainLengthAnalysis( input_file_properties,
1741 domain_lengths_table,
1742 domain_lengths_analysis_outfile );
1744 catch ( final IOException e1 ) {
1745 ForesterUtil.fatalError( surfacing.PRG_NAME, e1.toString() );
1747 System.out.println();
1748 ForesterUtil.programMessage( PRG_NAME, "Wrote domain length data to: " + domain_lengths_analysis_outfile );
1749 System.out.println();
1751 domain_lengths_table = null;
1752 final long analysis_start_time = new Date().getTime();
1753 PairwiseDomainSimilarityCalculator pw_calc = null;
1754 final DomainSimilarityCalculator calc = new BasicDomainSimilarityCalculator( domain_similarity_sort_field,
1755 sort_by_species_count_first,
1756 number_of_genomes == 2,
1757 CALC_SIMILARITY_SCORES );
1758 switch ( scoring ) {
1760 pw_calc = new CombinationsBasedPairwiseDomainSimilarityCalculator();
1763 pw_calc = new DomainCountsBasedPairwiseSimilarityCalculator();
1766 pw_calc = new ProteinCountsBasedPairwiseDomainSimilarityCalculator();
1769 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
1771 DomainSimilarityCalculator.GoAnnotationOutput go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.NONE;
1772 if ( domain_id_to_go_ids_map != null ) {
1773 go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.ALL;
1775 final SortedSet<DomainSimilarity> similarities = calc
1776 .calculateSimilarities( pw_calc,
1778 ignore_domains_without_combs_in_all_spec,
1779 ignore_species_specific_domains );
1780 SurfacingUtil.decoratePrintableDomainSimilarities( similarities, detailedness );
1781 final Map<String, Integer> tax_code_to_id_map = SurfacingUtil.createTaxCodeToIdMap( intrees[ 0 ] );
1783 String my_outfile = output_file.toString();
1784 Map<Character, Writer> split_writers = null;
1785 Writer writer = null;
1786 if ( similarities.size() > MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING ) {
1787 if ( my_outfile.endsWith( ".html" ) ) {
1788 my_outfile = my_outfile.substring( 0, my_outfile.length() - 5 );
1790 split_writers = new HashMap<Character, Writer>();
1791 SurfacingUtil.createSplitWriters( out_dir, my_outfile, split_writers );
1793 else if ( !my_outfile.endsWith( ".html" ) ) {
1794 my_outfile += ".html";
1795 writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) );
1797 List<Species> species_order = null;
1798 if ( species_matrix ) {
1799 species_order = new ArrayList<Species>();
1800 for( int i = 0; i < number_of_genomes; i++ ) {
1801 species_order.add( new BasicSpecies( input_file_properties[ i ][ 1 ] ) );
1804 html_desc.append( "<tr><td>Sum of all distinct binary combinations:</td><td>"
1805 + all_bin_domain_combinations_encountered.size() + "</td></tr>" + nl );
1806 html_desc.append( "<tr><td>Sum of all distinct domains:</td><td>" + all_domains_encountered.size()
1807 + "</td></tr>" + nl );
1808 html_desc.append( "<tr><td>Analysis date/time:</td><td>"
1809 + new java.text.SimpleDateFormat( "yyyy.MM.dd HH:mm:ss" ).format( new java.util.Date() )
1810 + "</td></tr>" + nl );
1811 html_desc.append( "</table>" + nl );
1812 final Writer simple_tab_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
1813 + my_outfile + ".tsv" ) );
1814 SurfacingUtil.writeDomainSimilaritiesToFile( html_desc,
1815 new StringBuilder( number_of_genomes + " genomes" ),
1820 number_of_genomes == 2,
1822 domain_similarity_print_option,
1827 simple_tab_writer.close();
1828 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote main output (includes domain similarities) to: \""
1829 + ( out_dir == null ? my_outfile : out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) + "\"" );
1831 catch ( final IOException e ) {
1832 ForesterUtil.fatalError( surfacing.PRG_NAME, "Failed to write similarites to: \"" + output_file + "\" ["
1833 + e.getMessage() + "]" );
1835 System.out.println();
1836 final Species[] species = new Species[ number_of_genomes ];
1837 for( int i = 0; i < number_of_genomes; ++i ) {
1838 species[ i ] = new BasicSpecies( input_file_properties[ i ][ 1 ] );
1840 List<Phylogeny> inferred_trees = null;
1841 if ( ( number_of_genomes > 2 ) && perform_pwc ) {
1842 final PairwiseGenomeComparator pwgc = new PairwiseGenomeComparator();
1843 pwgc.performPairwiseComparisons( html_desc,
1844 sort_by_species_count_first,
1846 ignore_domains_without_combs_in_all_spec,
1847 ignore_species_specific_domains,
1848 domain_similarity_sort_field_for_automated_pwc,
1849 domain_similarity_print_option,
1851 domain_id_to_go_ids_map,
1858 automated_pairwise_comparison_suffix,
1860 surfacing.PAIRWISE_DOMAIN_COMPARISONS_PREFIX,
1865 CALC_SIMILARITY_SCORES,
1867 String matrix_output_file = new String( output_file.toString() );
1868 if ( matrix_output_file.indexOf( '.' ) > 1 ) {
1869 matrix_output_file = matrix_output_file.substring( 0, matrix_output_file.indexOf( '.' ) );
1871 if ( out_dir != null ) {
1872 matrix_output_file = out_dir + ForesterUtil.FILE_SEPARATOR + matrix_output_file;
1873 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
1875 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
1876 + surfacing.MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans() );
1878 .writeMatrixToFile( new File( matrix_output_file
1879 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
1880 pwgc.getSharedBinaryCombinationsBasedDistances() );
1881 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
1882 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
1883 pwgc.getSharedDomainsBasedDistances() );
1884 final Phylogeny nj_gd = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
1885 + surfacing.NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans()
1887 final Phylogeny nj_bc = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
1888 + surfacing.NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
1889 .getSharedBinaryCombinationsBasedDistances().get( 0 ) );
1890 final Phylogeny nj_d = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
1891 + surfacing.NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
1892 .getSharedDomainsBasedDistances().get( 0 ) );
1893 inferred_trees = new ArrayList<Phylogeny>();
1894 inferred_trees.add( nj_gd );
1895 inferred_trees.add( nj_bc );
1896 inferred_trees.add( nj_d );
1897 } // if ( ( output_file != null ) && ( number_of_genomes > 2 ) && !isEmpty( automated_pairwise_comparison_suffix ) )
1898 if ( ( out_dir != null ) && ( !perform_pwc ) ) {
1899 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
1901 if ( write_to_nexus ) {
1902 SurfacingUtil.writePresentToNexus( output_file, positive_filter_file, filter, gwcd_list );
1904 if ( ( ( intrees != null ) && ( intrees.length > 0 ) ) && ( number_of_genomes > 2 ) ) {
1905 final StringBuilder parameters_sb = SurfacingUtil.createParametersAsString( ignore_dufs,
1907 max_allowed_overlap,
1908 no_engulfing_overlaps,
1912 if ( radomize_fitch_parsimony ) {
1913 s += random_number_seed_for_fitch_parsimony + "_";
1916 for( final Phylogeny intree : intrees ) {
1917 final String outfile_name = ForesterUtil.removeSuffix( output_file.toString() ) + s
1918 + ForesterUtil.removeSuffix( intree_files[ i ].toString() );
1919 final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator.createInstance( intree,
1921 SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
1922 radomize_fitch_parsimony,
1926 domain_id_to_go_ids_map,
1929 parameters_sb.toString(),
1930 domain_id_to_secondary_features_maps,
1931 positive_filter_file == null ? null : filter,
1932 output_binary_domain_combinationsfor_graph_analysis,
1933 all_bin_domain_combinations_gained_fitch,
1934 all_bin_domain_combinations_lost_fitch,
1936 protein_length_stats_by_dc,
1937 domain_number_stats_by_dc,
1938 domain_length_stats_by_domain,
1941 use_last_in_fitch_parsimony );
1942 // Listing of all domain combinations gained is only done if only one input tree is used.
1943 if ( ( domain_id_to_secondary_features_maps != null )
1944 && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
1946 for( final Map<String, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
1947 final Map<Species, MappingResults> mapping_results_map = new TreeMap<Species, MappingResults>();
1948 final DomainParsimonyCalculator secondary_features_parsimony = DomainParsimonyCalculator
1949 .createInstance( intree, gwcd_list, domain_id_to_secondary_features_map );
1951 .executeParsimonyAnalysisForSecondaryFeatures( outfile_name
1953 + secondary_features_map_files[ j++ ],
1954 secondary_features_parsimony,
1956 parameters_sb.toString(),
1957 mapping_results_map,
1958 use_last_in_fitch_parsimony );
1960 System.out.println();
1961 System.out.println( "Mapping to secondary features:" );
1962 for( final Species spec : mapping_results_map.keySet() ) {
1963 final MappingResults mapping_results = mapping_results_map.get( spec );
1964 final int total_domains = mapping_results.getSumOfFailures()
1965 + mapping_results.getSumOfSuccesses();
1966 System.out.print( spec + ":" );
1967 System.out.print( " mapped domains = " + mapping_results.getSumOfSuccesses() );
1968 System.out.print( ", not mapped domains = " + mapping_results.getSumOfFailures() );
1969 if ( total_domains > 0 ) {
1970 System.out.println( ", mapped ratio = "
1971 + ( ( 100 * mapping_results.getSumOfSuccesses() ) / total_domains ) + "%" );
1974 System.out.println( ", mapped ratio = n/a (total domains = 0 )" );
1981 } // for( final Phylogeny intree : intrees ) {
1983 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
1984 SurfacingUtil.executePlusMinusAnalysis( output_file,
1985 plus_minus_analysis_high_copy_base_species,
1986 plus_minus_analysis_high_copy_target_species,
1987 plus_minus_analysis_high_low_copy_species,
1989 protein_lists_per_species,
1990 domain_id_to_go_ids_map,
1992 plus_minus_analysis_numbers );
1994 if ( output_protein_lists_for_all_domains ) {
1995 SurfacingUtil.writeProteinListsForAllSpecies( out_dir,
1996 protein_lists_per_species,
1998 output_list_of_all_proteins_per_domain_e_value_max );
2001 if ( all_bin_domain_combinations_gained_fitch != null ) {
2003 SurfacingUtil.executeFitchGainsAnalysis( new File( output_file
2004 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2005 all_bin_domain_combinations_gained_fitch,
2006 all_domains_encountered.size(),
2007 all_bin_domain_combinations_encountered,
2010 catch ( final IOException e ) {
2011 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2014 if ( all_bin_domain_combinations_lost_fitch != null ) {
2016 SurfacingUtil.executeFitchGainsAnalysis( new File( output_file
2017 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2018 all_bin_domain_combinations_lost_fitch,
2019 all_domains_encountered.size(),
2020 all_bin_domain_combinations_encountered,
2023 catch ( final IOException e ) {
2024 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2027 final Runtime rt = java.lang.Runtime.getRuntime();
2028 final long free_memory = rt.freeMemory() / 1000000;
2029 final long total_memory = rt.totalMemory() / 1000000;
2030 ForesterUtil.programMessage( PRG_NAME, "Time for analysis : " + ( new Date().getTime() - analysis_start_time )
2032 ForesterUtil.programMessage( PRG_NAME, "Total running time: " + ( new Date().getTime() - start_time ) + "ms " );
2033 ForesterUtil.programMessage( PRG_NAME, "Free memory : " + free_memory + "MB, total memory: "
2034 + total_memory + "MB" );
2035 ForesterUtil.programMessage( PRG_NAME, "If this application is useful to you, please cite:" );
2036 ForesterUtil.programMessage( PRG_NAME, surfacing.WWW );
2037 ForesterUtil.programMessage( PRG_NAME, "OK" );
2038 System.out.println();
2041 private static void printHelp() {
2042 System.out.println();
2043 System.out.println( "Usage:" );
2044 System.out.println();
2045 System.out.println( "% java -Xms256m -Xmx512m -cp forester.jar org.forester.applications." + surfacing.PRG_NAME
2046 + " [options] <phylogen(y|ies) infile> [external node name 1] [name 2] ... [name n]" );
2047 System.out.println();
2048 System.out.println( " Note: This software might need a significant amount of memory (heap space);" );
2050 .println( " hence use \"-Xms128m -Xmx512m\" (or more) to prevent a \"java.lang.OutOfMemoryError\"." );
2051 System.out.println();
2052 System.out.println( " Options: " );
2053 System.out.println( surfacing.DETAILEDNESS_OPTION + ": level of detail for similarities output file (default:"
2054 + DETAILEDNESS_DEFAULT + ")" );
2055 System.out.println( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION
2056 + ": to ignore combinations with self (default: not to ignore)" );
2058 .println( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION
2059 + ": to ignore domains without combinations in any species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2061 .println( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION
2062 + ": to ignore domains specific to one species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2063 System.out.println( surfacing.NOT_IGNORE_DUFS_OPTION
2064 + ": to _not_ ignore DUFs (domains with unknown function) (default: ignore DUFs)" );
2066 .println( surfacing.IGNORE_VIRAL_IDS
2067 + ": to ignore domains with ids containing 'vir', 'retro', 'transpos', 'phage', or starting with 'rv' or 'gag_'" );
2068 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_OPTION + ": sorting for similarities (default: "
2069 + DOMAIN_SORT_FILD_DEFAULT + ")" );
2070 System.out.println( surfacing.OUTPUT_FILE_OPTION + ": name for (main) output file (mandatory)" );
2071 System.out.println( surfacing.MAX_E_VALUE_OPTION + ": max (inclusive) E-value" );
2072 System.out.println( surfacing.MAX_ALLOWED_OVERLAP_OPTION + ": maximal allowed domain overlap" );
2073 System.out.println( surfacing.NO_ENGULFING_OVERLAP_OPTION + ": to ignore engulfed lower confidence domains" );
2074 System.out.println( surfacing.SPECIES_MATRIX_OPTION + ": species matrix" );
2075 System.out.println( surfacing.SCORING_OPTION + ": scoring (default:" + SCORING_DEFAULT + ")" );
2076 System.out.println( surfacing.DOMAIN_COUNT_SORT_OPTION + ": sorting for domain counts (default:"
2077 + DOMAINS_SORT_ORDER_DEFAULT + ")" );
2078 System.out.println( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION + ": domain similarity print option (default:"
2079 + DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT + ")" );
2080 System.out.println( surfacing.CUTOFF_SCORE_FILE_OPTION + ": cutoff score file" );
2081 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION
2082 + ": sort by species count first" );
2083 System.out.println( surfacing.OUTPUT_DIR_OPTION + ": output directory" );
2084 System.out.println( surfacing.PFAM_TO_GO_FILE_USE_OPTION + ": Pfam to GO mapping file" );
2085 System.out.println( surfacing.GO_OBO_FILE_USE_OPTION + ": GO terms file (OBO format)" );
2086 System.out.println( surfacing.GO_NAMESPACE_LIMIT_OPTION + ": limit GO term to one GO namespace" );
2087 System.out.println( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
2088 + "[=<suffix for pairwise comparison output files>]: to perform pairwise comparison based analyses" );
2089 System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION
2090 + ": species tree, to perform (Dollo, Fitch) parismony analyses" );
2092 .println( surfacing.INPUT_SPECIES_TREE_OPTION
2093 + "=<treefiles in phyloXML format, separated by #>: to infer domain/binary domain combination gains/losses on given species trees" );
2094 System.out.println( surfacing.FILTER_POSITIVE_OPTION
2095 + "=<file>: to filter out proteins not containing at least one domain listed in <file>" );
2096 System.out.println( surfacing.FILTER_NEGATIVE_OPTION
2097 + "=<file>: to filter out proteins containing at least one domain listed in <file>" );
2098 System.out.println( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION
2099 + "=<file>: to filter out (ignore) domains listed in <file>" );
2100 System.out.println( surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>: to read input files from <file>" );
2102 .println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION
2103 + "=<seed>: seed for random number generator for Fitch Parsimony analysis (type: long, default: no randomization - given a choice, prefer absence" );
2104 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS
2105 + ": to consider directedness in binary combinations: e.g. A-B != B-A" );
2106 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY
2107 + ": to consider directedness and adjacency in binary combinations" );
2109 .println( surfacing.SEQ_EXTRACT_OPTION
2110 + "=<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')" );
2111 System.out.println( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE
2112 + "=<file>: to perfom parsimony analysis on secondary features" );
2113 System.out.println( surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>: to presence/absence genome analysis" );
2114 System.out.println( surfacing.DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS
2115 + ": to output binary domain combinations for (downstream) graph analysis" );
2116 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS + ": to output all proteins per domain" );
2117 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION
2118 + ": e value max per domain for output of all proteins per domain" );
2119 System.out.println( surfacing.USE_LAST_IN_FITCH_OPTION + ": to use last in Fitch parsimony" );
2120 System.out.println( surfacing.WRITE_TO_NEXUS_OPTION + ": to output in Nexus format" );
2121 System.out.println( PERFORM_DC_REGAIN_PROTEINS_STATS_OPTION + ": to perform DC regain protein statistics" );
2122 System.out.println( DA_ANALYSIS_OPTION + ": to do DA analysis" );
2123 System.out.println();
2124 System.out.println( "Example 1: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2125 + " org.forester.application.surfacing p2g=pfam2go_2012_02_07.txt -dufs -cos=Pfam_260_NC1"
2126 + " -no_eo -mo=0 -genomes=eukaryotes.txt -out_dir=out -o=o "
2127 + " -species_tree=tol.xml -obo=gene_ontology_2012_02_07.obo -pos_filter=f.txt -all_prot" );
2128 System.out.println();
2129 System.out.println( "Example 2: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2130 + " org.forester.application.surfacing -detail=punctilious -o=TEST.html -pwc=TEST"
2131 + " -cos=Pfam_ls_22_TC2 -p2g=pfam2go -obo=gene_ontology_edit.obo "
2132 + "-dc_sort=dom -ignore_with_self -no_singles -e=0.001 -mo=1 -no_eo -genomes=eukaryotes.txt "
2133 + "-ds_output=detailed_html -scoring=domains -sort=alpha " );
2134 System.out.println();