3 // FORESTER -- software libraries and applications
4 // for evolutionary biology research and applications.
6 // Copyright (C) 2008-2009 Christian M. Zmasek
7 // Copyright (C) 2008-2009 Burnham Institute for Medical Research
10 // This library is free software; you can redistribute it and/or
11 // modify it under the terms of the GNU Lesser General Public
12 // License as published by the Free Software Foundation; either
13 // version 2.1 of the License, or (at your option) any later version.
15 // This library is distributed in the hope that it will be useful,
16 // but WITHOUT ANY WARRANTY; without even the implied warranty of
17 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
18 // Lesser General Public License for more details.
20 // You should have received a copy of the GNU Lesser General Public
21 // License along with this library; if not, write to the Free Software
22 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
24 // Contact: phylosoft @ gmail . com
25 // WWW: https://sites.google.com/site/cmzmasek/home/software/forester
27 package org.forester.application;
29 import java.io.BufferedWriter;
31 import java.io.FileWriter;
32 import java.io.IOException;
33 import java.io.Writer;
34 import java.util.ArrayList;
35 import java.util.Date;
36 import java.util.HashMap;
37 import java.util.HashSet;
38 import java.util.List;
40 import java.util.Map.Entry;
42 import java.util.SortedMap;
43 import java.util.SortedSet;
44 import java.util.TreeMap;
45 import java.util.TreeSet;
47 import org.forester.evoinference.matrix.character.CharacterStateMatrix.Format;
48 import org.forester.go.GoId;
49 import org.forester.go.GoNameSpace;
50 import org.forester.go.GoTerm;
51 import org.forester.go.GoUtils;
52 import org.forester.go.OBOparser;
53 import org.forester.go.PfamToGoMapping;
54 import org.forester.go.PfamToGoParser;
55 import org.forester.io.parsers.HmmscanPerDomainTableParser;
56 import org.forester.io.parsers.HmmscanPerDomainTableParser.INDIVIDUAL_SCORE_CUTOFF;
57 import org.forester.io.parsers.util.ParserUtils;
58 import org.forester.phylogeny.Phylogeny;
59 import org.forester.phylogeny.PhylogenyMethods;
60 import org.forester.phylogeny.PhylogenyNode;
61 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
62 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
63 import org.forester.protein.BinaryDomainCombination;
64 import org.forester.protein.Domain;
65 import org.forester.protein.DomainId;
66 import org.forester.protein.Protein;
67 import org.forester.species.BasicSpecies;
68 import org.forester.species.Species;
69 import org.forester.surfacing.BasicDomainSimilarityCalculator;
70 import org.forester.surfacing.BasicGenomeWideCombinableDomains;
71 import org.forester.surfacing.CombinationsBasedPairwiseDomainSimilarityCalculator;
72 import org.forester.surfacing.DomainCountsBasedPairwiseSimilarityCalculator;
73 import org.forester.surfacing.DomainCountsDifferenceUtil;
74 import org.forester.surfacing.DomainLengthsTable;
75 import org.forester.surfacing.DomainParsimonyCalculator;
76 import org.forester.surfacing.DomainSimilarity;
77 import org.forester.surfacing.DomainSimilarity.DomainSimilarityScoring;
78 import org.forester.surfacing.DomainSimilarity.DomainSimilaritySortField;
79 import org.forester.surfacing.DomainSimilarityCalculator;
80 import org.forester.surfacing.DomainSimilarityCalculator.Detailedness;
81 import org.forester.surfacing.GenomeWideCombinableDomains;
82 import org.forester.surfacing.GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder;
83 import org.forester.surfacing.MappingResults;
84 import org.forester.surfacing.PairwiseDomainSimilarityCalculator;
85 import org.forester.surfacing.PairwiseGenomeComparator;
86 import org.forester.surfacing.PrintableDomainSimilarity;
87 import org.forester.surfacing.PrintableDomainSimilarity.PRINT_OPTION;
88 import org.forester.surfacing.ProteinCountsBasedPairwiseDomainSimilarityCalculator;
89 import org.forester.surfacing.SurfacingUtil;
90 import org.forester.util.BasicDescriptiveStatistics;
91 import org.forester.util.BasicTable;
92 import org.forester.util.BasicTableParser;
93 import org.forester.util.CommandLineArguments;
94 import org.forester.util.DescriptiveStatistics;
95 import org.forester.util.ForesterConstants;
96 import org.forester.util.ForesterUtil;
98 public class surfacing {
100 private static final int MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING = 1000;
101 public final static String DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS = "graph_analysis_out";
102 public final static String DOMAIN_COMBINITONS_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_dc.dot";
103 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_fitch_present_dc.dot";
104 public final static String DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX = ".dcc";
106 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS = "_dollo_gl_d";
107 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_gl_dc";
108 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_DOMAINS = "_fitch_gl_d";
109 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_gl_dc";
111 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS = "_dollo_glc_d";
112 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_glc_dc";
113 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_DOMAINS = "_fitch_glc_d";
114 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_glc_dc";
116 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_BC = "_fitch_gains_dc";
117 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_HTML_BC = "_fitch_gains_dc.html";
118 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_BC = "_fitch_losses_dc";
119 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_HTML_BC = "_fitch_losses_dc.html";
120 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC = "_fitch_present_dc";
121 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_HTML_BC = "_fitch_present_dc.html";
122 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_D = "_dollo_gains_d";
123 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_HTML_D = "_dollo_gains_d.html";
124 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_D = "_dollo_losses_d";
125 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_HTML_D = "_dollo_losses_d.html";
126 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_D = "_dollo_present_d";
127 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_HTML_D = "_dollo_present_d.html";
128 public final static String DOMAINS_PRESENT_NEXUS = "_dom.nex";
129 public final static String BDC_PRESENT_NEXUS = "_dc.nex";
131 public final static String PRG_NAME = "surfacing";
132 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_d_dollo"
133 + ForesterConstants.PHYLO_XML_SUFFIX;
134 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_d_fitch"
135 + ForesterConstants.PHYLO_XML_SUFFIX;
136 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_dc_dollo"
137 + ForesterConstants.PHYLO_XML_SUFFIX;
138 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_dc_fitch"
139 + ForesterConstants.PHYLO_XML_SUFFIX;
140 public static final String NEXUS_EXTERNAL_DOMAINS = "_dom.nex";
141 public static final String NEXUS_EXTERNAL_DOMAIN_COMBINATIONS = "_dc.nex";
142 public static final String NEXUS_SECONDARY_FEATURES = "_secondary_features.nex";
143 public static final String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_gl_secondary_features";
144 public static final String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_glc_secondary_features";
145 public static final String PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES = "_dollo_gains_secondary_features";
146 public static final String PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES = "_dollo_losses_secondary_features";
147 public static final String PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES = "_dollo_present_secondary_features";
148 public static final String SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_secondary_features_dollo"
149 + ForesterConstants.PHYLO_XML_SUFFIX;
150 public static final String PARSIMONY_OUTPUT_DOLLO_ALL_GOID_D_ALL_NAMESPACES = "_dollo_goid_d";
151 public static final String PARSIMONY_OUTPUT_FITCH_ALL_GOID_BC_ALL_NAMESPACES = "_fitch_goid_dc";
152 final static private String HELP_OPTION_1 = "help";
153 final static private String HELP_OPTION_2 = "h";
154 final static private String OUTPUT_DIR_OPTION = "out_dir";
155 final static private String SCORING_OPTION = "scoring";
156 private static final DomainSimilarityScoring SCORING_DEFAULT = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
157 final static private String SCORING_DOMAIN_COUNT_BASED = "domains";
158 final static private String SCORING_PROTEIN_COUNT_BASED = "proteins";
159 final static private String SCORING_COMBINATION_BASED = "combinations";
160 final static private String DETAILEDNESS_OPTION = "detail";
161 private final static Detailedness DETAILEDNESS_DEFAULT = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
162 final static private String SPECIES_MATRIX_OPTION = "smatrix";
163 final static private String DETAILEDNESS_BASIC = "basic";
164 final static private String DETAILEDNESS_LIST_IDS = "list_ids";
165 final static private String DETAILEDNESS_PUNCTILIOUS = "punctilious";
166 final static private String DOMAIN_SIMILARITY_SORT_OPTION = "sort";
167 private static final DomainSimilaritySortField DOMAIN_SORT_FILD_DEFAULT = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
168 final static private String DOMAIN_SIMILARITY_SORT_MIN = "min";
169 final static private String DOMAIN_SIMILARITY_SORT_MAX = "max";
170 final static private String DOMAIN_SIMILARITY_SORT_SD = "sd";
171 final static private String DOMAIN_SIMILARITY_SORT_MEAN = "mean";
172 final static private String DOMAIN_SIMILARITY_SORT_DIFF = "diff";
173 final static private String DOMAIN_SIMILARITY_SORT_COUNTS_DIFF = "count_diff";
174 final static private String DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF = "abs_count_diff";
175 final static private String DOMAIN_SIMILARITY_SORT_SPECIES_COUNT = "species";
176 final static private String DOMAIN_SIMILARITY_SORT_ALPHA = "alpha";
177 final static private String DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION = "species_first";
178 final static private String DOMAIN_COUNT_SORT_OPTION = "dc_sort";
179 private static final GenomeWideCombinableDomainsSortOrder DOMAINS_SORT_ORDER_DEFAULT = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
180 final static private String DOMAIN_COUNT_SORT_ALPHA = "alpha";
181 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT = "dom";
182 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT = "prot";
183 final static private String DOMAIN_COUNT_SORT_COMBINATIONS_COUNT = "comb";
184 final static private String CUTOFF_SCORE_FILE_OPTION = "cos";
185 final static private String NOT_IGNORE_DUFS_OPTION = "dufs";
186 final static private String MAX_E_VALUE_OPTION = "e";
187 final static private String MAX_ALLOWED_OVERLAP_OPTION = "mo";
188 final static private String NO_ENGULFING_OVERLAP_OPTION = "no_eo";
189 final static private String IGNORE_COMBINATION_WITH_SAME_OPTION = "ignore_self_comb";
190 final static private String PAIRWISE_DOMAIN_COMPARISONS_PREFIX = "pwc_";
191 final static private String PAIRWISE_DOMAIN_COMPARISONS_OPTION = "pwc";
192 final static private String OUTPUT_FILE_OPTION = "o";
193 final static private String PFAM_TO_GO_FILE_USE_OPTION = "p2g";
194 final static private String GO_OBO_FILE_USE_OPTION = "obo";
195 final static private String GO_NAMESPACE_LIMIT_OPTION = "go_namespace";
196 final static private String GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION = "molecular_function";
197 final static private String GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS = "biological_process";
198 final static private String GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT = "cellular_component";
199 final static private String SECONDARY_FEATURES_PARSIMONY_MAP_FILE = "secondary";
200 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED = "simple_tab";
201 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML = "simple_html";
202 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML = "detailed_html";
203 final static private String DOMAIN_SIMILARITY_PRINT_OPTION = "ds_output";
204 private static final PRINT_OPTION DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT = PrintableDomainSimilarity.PRINT_OPTION.HTML;
205 final static private String IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION = "ignore_singlet_domains";
206 final static private String IGNORE_VIRAL_IDS = "ignore_viral_ids";
207 final static private boolean IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT = false;
208 final static private String IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION = "ignore_species_specific_domains";
209 final static private boolean IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT = false;
210 final static private String MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score.pwd";
211 final static private String MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains.pwd";
212 final static private String MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations.pwd";
213 final static private String NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score_NJ"
214 + ForesterConstants.PHYLO_XML_SUFFIX;
215 final static private String NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains_NJ"
216 + ForesterConstants.PHYLO_XML_SUFFIX;
217 final static private String NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations_NJ"
218 + ForesterConstants.PHYLO_XML_SUFFIX;
219 final static private String JACKNIFE_OPTION = "jack";
220 final static private String JACKNIFE_RANDOM_SEED_OPTION = "seed";
221 final static private String JACKNIFE_RATIO_OPTION = "jack_ratio";
222 private static final int JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT = 100;
223 final static private long JACKNIFE_RANDOM_SEED_DEFAULT = 19;
224 final static private double JACKNIFE_RATIO_DEFAULT = 0.5;
225 //final static private String INFER_SPECIES_TREES_OPTION = "species_tree_inference";
226 final static private String FILTER_POSITIVE_OPTION = "pos_filter";
227 final static private String FILTER_NEGATIVE_OPTION = "neg_filter";
228 final static private String FILTER_NEGATIVE_DOMAINS_OPTION = "neg_dom_filter";
229 final static private String INPUT_FILES_FROM_FILE_OPTION = "input";
230 final static private String INPUT_SPECIES_TREE_OPTION = "species_tree";
231 final static private String SEQ_EXTRACT_OPTION = "prot_extract";
232 final static private char SEPARATOR_FOR_INPUT_VALUES = '#';
233 final static private String PRG_VERSION = "2.252";
234 final static private String PRG_DATE = "2012.08.01";
235 final static private String E_MAIL = "czmasek@burnham.org";
236 final static private String WWW = "www.phylosoft.org/forester/applications/surfacing";
237 final static private boolean IGNORE_DUFS_DEFAULT = true;
238 final static private boolean IGNORE_COMBINATION_WITH_SAME_DEFAULLT = false;
239 final static private double MAX_E_VALUE_DEFAULT = -1;
240 final static private int MAX_ALLOWED_OVERLAP_DEFAULT = -1;
241 private static final String RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION = "random_seed";
242 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS = "consider_bdc_direction";
243 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY = "consider_bdc_adj";
244 private static final String SEQ_EXTRACT_SUFFIX = ".prot";
245 private static final String PLUS_MINUS_ANALYSIS_OPTION = "plus_minus";
246 private static final String PLUS_MINUS_DOM_SUFFIX = "_plus_minus_dom.txt";
247 private static final String PLUS_MINUS_DOM_SUFFIX_HTML = "_plus_minus_dom.html";
248 private static final String PLUS_MINUS_DC_SUFFIX_HTML = "_plus_minus_dc.html";
249 private static final int PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT = 0;
250 private static final double PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT = 1.0;
251 private static final String PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_all.txt";
252 private static final String PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_passing.txt";
253 private static final String OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS = "all_prot";
254 final static private String OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION = "all_prot_e";
255 private static final boolean VERBOSE = false;
256 private static final String OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_gains_counts";
257 private static final String OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_losses_counts";
258 private static final String DOMAIN_LENGTHS_ANALYSIS_SUFFIX = "_domain_lengths_analysis";
259 private static final boolean PERFORM_DOMAIN_LENGTH_ANALYSIS = true;
260 public static final String ALL_PFAMS_ENCOUNTERED_SUFFIX = "_all_encountered_pfams";
261 public static final String ALL_PFAMS_ENCOUNTERED_WITH_GO_ANNOTATION_SUFFIX = "_all_encountered_pfams_with_go_annotation";
262 public static final String ENCOUNTERED_PFAMS_SUMMARY_SUFFIX = "_encountered_pfams_summary";
263 public static final String ALL_PFAMS_GAINED_AS_DOMAINS_SUFFIX = "_all_pfams_gained_as_domains";
264 public static final String ALL_PFAMS_LOST_AS_DOMAINS_SUFFIX = "_all_pfams_lost_as_domains";
265 public static final String ALL_PFAMS_GAINED_AS_DC_SUFFIX = "_all_pfams_gained_as_dc";
266 public static final String ALL_PFAMS_LOST_AS_DC_SUFFIX = "_all_pfams_lost_as_dc";
267 public static final String BASE_DIRECTORY_PER_NODE_DOMAIN_GAIN_LOSS_FILES = "PER_NODE_EVENTS";
268 public static final String BASE_DIRECTORY_PER_SUBTREE_DOMAIN_GAIN_LOSS_FILES = "PER_SUBTREE_EVENTS";
269 public static final String D_PROMISCUITY_FILE_SUFFIX = "_domain_promiscuities";
270 private static final String LOG_FILE_SUFFIX = "_log.txt";
271 private static final String DATA_FILE_SUFFIX = "_domain_combination_data.txt";
272 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";
273 private static final INDIVIDUAL_SCORE_CUTOFF INDIVIDUAL_SCORE_CUTOFF_DEFAULT = INDIVIDUAL_SCORE_CUTOFF.FULL_SEQUENCE; //TODO look at me! change?
274 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts.txt";
275 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists.txt";
276 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping.txt";
277 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";
278 public static final String LIMIT_SPEC_FOR_PROT_EX = null; // e.g. "HUMAN"; set to null for not using this feature (default).
279 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH_MAPPED = "_dc_MAPPED_secondary_features_fitch"
280 + ForesterConstants.PHYLO_XML_SUFFIX;
281 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts_MAPPED.txt";
282 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_MAPPED.txt";
283 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";
284 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";
285 private static final boolean PERFORM_DC_REGAIN_PROTEINS_STATS = true;
287 private static void checkWriteabilityForPairwiseComparisons( final PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option,
288 final String[][] input_file_properties,
289 final String automated_pairwise_comparison_suffix,
290 final File outdir ) {
291 for( int i = 0; i < input_file_properties.length; ++i ) {
292 for( int j = 0; j < i; ++j ) {
293 final String species_i = input_file_properties[ i ][ 1 ];
294 final String species_j = input_file_properties[ j ][ 1 ];
295 String pairwise_similarities_output_file_str = PAIRWISE_DOMAIN_COMPARISONS_PREFIX + species_i + "_"
296 + species_j + automated_pairwise_comparison_suffix;
297 switch ( domain_similarity_print_option ) {
299 if ( !pairwise_similarities_output_file_str.endsWith( ".html" ) ) {
300 pairwise_similarities_output_file_str += ".html";
304 final String error = ForesterUtil
305 .isWritableFile( new File( outdir == null ? pairwise_similarities_output_file_str : outdir
306 + ForesterUtil.FILE_SEPARATOR + pairwise_similarities_output_file_str ) );
307 if ( !ForesterUtil.isEmpty( error ) ) {
308 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
314 private static StringBuilder createParametersAsString( final boolean ignore_dufs,
315 final double e_value_max,
316 final int max_allowed_overlap,
317 final boolean no_engulfing_overlaps,
318 final File cutoff_scores_file,
319 final BinaryDomainCombination.DomainCombinationType dc_type ) {
320 final StringBuilder parameters_sb = new StringBuilder();
321 parameters_sb.append( "E-value: " + e_value_max );
322 if ( cutoff_scores_file != null ) {
323 parameters_sb.append( ", Cutoff-scores-file: " + cutoff_scores_file );
326 parameters_sb.append( ", Cutoff-scores-file: not-set" );
328 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
329 parameters_sb.append( ", Max-overlap: " + max_allowed_overlap );
332 parameters_sb.append( ", Max-overlap: not-set" );
334 if ( no_engulfing_overlaps ) {
335 parameters_sb.append( ", Engulfing-overlaps: not-allowed" );
338 parameters_sb.append( ", Engulfing-overlaps: allowed" );
341 parameters_sb.append( ", Ignore-dufs: true" );
344 parameters_sb.append( ", Ignore-dufs: false" );
346 parameters_sb.append( ", DC type (if applicable): " + dc_type );
347 return parameters_sb;
351 * Warning: This side-effects 'all_bin_domain_combinations_encountered'!
355 * @param all_bin_domain_combinations_changed
356 * @param sum_of_all_domains_encountered
357 * @param all_bin_domain_combinations_encountered
358 * @param is_gains_analysis
359 * @param protein_length_stats_by_dc
360 * @throws IOException
362 private static void executeFitchGainsAnalysis( final File output_file,
363 final List<BinaryDomainCombination> all_bin_domain_combinations_changed,
364 final int sum_of_all_domains_encountered,
365 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered,
366 final boolean is_gains_analysis ) throws IOException {
367 SurfacingUtil.checkForOutputFileWriteability( output_file );
368 final Writer out = ForesterUtil.createBufferedWriter( output_file );
369 final SortedMap<Object, Integer> bdc_to_counts = ForesterUtil
370 .listToSortedCountsMap( all_bin_domain_combinations_changed );
371 final SortedSet<DomainId> all_domains_in_combination_changed_more_than_once = new TreeSet<DomainId>();
372 final SortedSet<DomainId> all_domains_in_combination_changed_only_once = new TreeSet<DomainId>();
375 for( final Object bdc_object : bdc_to_counts.keySet() ) {
376 final BinaryDomainCombination bdc = ( BinaryDomainCombination ) bdc_object;
377 final int count = bdc_to_counts.get( bdc_object );
379 ForesterUtil.unexpectedFatalError( PRG_NAME, "count < 1 " );
381 out.write( bdc + "\t" + count + ForesterUtil.LINE_SEPARATOR );
383 all_domains_in_combination_changed_more_than_once.add( bdc.getId0() );
384 all_domains_in_combination_changed_more_than_once.add( bdc.getId1() );
387 else if ( count == 1 ) {
388 all_domains_in_combination_changed_only_once.add( bdc.getId0() );
389 all_domains_in_combination_changed_only_once.add( bdc.getId1() );
393 final int all = all_bin_domain_combinations_encountered.size();
395 if ( !is_gains_analysis ) {
396 all_bin_domain_combinations_encountered.removeAll( all_bin_domain_combinations_changed );
397 never_lost = all_bin_domain_combinations_encountered.size();
398 for( final BinaryDomainCombination bdc : all_bin_domain_combinations_encountered ) {
399 out.write( bdc + "\t" + "0" + ForesterUtil.LINE_SEPARATOR );
402 if ( is_gains_analysis ) {
403 out.write( "Sum of all distinct domain combinations appearing once : " + one
404 + ForesterUtil.LINE_SEPARATOR );
405 out.write( "Sum of all distinct domain combinations appearing more than once : " + above_one
406 + ForesterUtil.LINE_SEPARATOR );
407 out.write( "Sum of all distinct domains in combinations apppearing only once : "
408 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
409 out.write( "Sum of all distinct domains in combinations apppearing more than once: "
410 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
413 out.write( "Sum of all distinct domain combinations never lost : " + never_lost
414 + ForesterUtil.LINE_SEPARATOR );
415 out.write( "Sum of all distinct domain combinations lost once : " + one
416 + ForesterUtil.LINE_SEPARATOR );
417 out.write( "Sum of all distinct domain combinations lost more than once : " + above_one
418 + ForesterUtil.LINE_SEPARATOR );
419 out.write( "Sum of all distinct domains in combinations lost only once : "
420 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
421 out.write( "Sum of all distinct domains in combinations lost more than once: "
422 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
424 out.write( "All binary combinations : " + all
425 + ForesterUtil.LINE_SEPARATOR );
426 out.write( "All domains : "
427 + sum_of_all_domains_encountered );
429 ForesterUtil.programMessage( surfacing.PRG_NAME,
430 "Wrote fitch domain combination dynamics counts analysis to \"" + output_file
434 private static void executePlusMinusAnalysis( final File output_file,
435 final List<String> plus_minus_analysis_high_copy_base,
436 final List<String> plus_minus_analysis_high_copy_target,
437 final List<String> plus_minus_analysis_low_copy,
438 final List<GenomeWideCombinableDomains> gwcd_list,
439 final SortedMap<Species, List<Protein>> protein_lists_per_species,
440 final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
441 final Map<GoId, GoTerm> go_id_to_term_map,
442 final List<Object> plus_minus_analysis_numbers ) {
443 final Set<String> all_spec = new HashSet<String>();
444 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
445 all_spec.add( gwcd.getSpecies().getSpeciesId() );
447 final File html_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX_HTML );
448 final File plain_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX );
449 final File html_out_dc = new File( output_file + PLUS_MINUS_DC_SUFFIX_HTML );
450 final File all_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX );
451 final File passing_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX );
452 final File proteins_file_base = new File( output_file + "" );
453 final int min_diff = ( ( Integer ) plus_minus_analysis_numbers.get( 0 ) ).intValue();
454 final double factor = ( ( Double ) plus_minus_analysis_numbers.get( 1 ) ).doubleValue();
456 DomainCountsDifferenceUtil.calculateCopyNumberDifferences( gwcd_list,
457 protein_lists_per_species,
458 plus_minus_analysis_high_copy_base,
459 plus_minus_analysis_high_copy_target,
460 plus_minus_analysis_low_copy,
466 domain_id_to_go_ids_map,
468 all_domains_go_ids_out_dom,
469 passing_domains_go_ids_out_dom,
470 proteins_file_base );
472 catch ( final IOException e ) {
473 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
475 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
476 + html_out_dom + "\"" );
477 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
478 + plain_out_dom + "\"" );
479 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \"" + html_out_dc
481 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based passing GO ids to \""
482 + passing_domains_go_ids_out_dom + "\"" );
483 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based all GO ids to \""
484 + all_domains_go_ids_out_dom + "\"" );
487 private static Phylogeny[] getIntrees( final File[] intree_files,
488 final int number_of_genomes,
489 final String[][] input_file_properties ) {
490 final Phylogeny[] intrees = new Phylogeny[ intree_files.length ];
492 for( final File intree_file : intree_files ) {
493 Phylogeny intree = null;
494 final String error = ForesterUtil.isReadableFile( intree_file );
495 if ( !ForesterUtil.isEmpty( error ) ) {
496 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read input tree file [" + intree_file + "]: "
500 final Phylogeny[] p_array = ParserBasedPhylogenyFactory.getInstance()
501 .create( intree_file, ParserUtils.createParserDependingOnFileType( intree_file, true ) );
502 if ( p_array.length < 1 ) {
503 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
504 + "] does not contain any phylogeny in phyloXML format" );
506 else if ( p_array.length > 1 ) {
507 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
508 + "] contains more than one phylogeny in phyloXML format" );
510 intree = p_array[ 0 ];
512 catch ( final Exception e ) {
513 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read input tree from file [" + intree_file
516 if ( ( intree == null ) || intree.isEmpty() ) {
517 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" );
519 if ( !intree.isRooted() ) {
520 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is not rooted" );
522 if ( intree.getNumberOfExternalNodes() < number_of_genomes ) {
523 ForesterUtil.fatalError( surfacing.PRG_NAME,
524 "number of external nodes [" + intree.getNumberOfExternalNodes()
525 + "] of input tree [" + intree_file
526 + "] is smaller than the number of genomes the be analyzed ["
527 + number_of_genomes + "]" );
529 final StringBuilder parent_names = new StringBuilder();
530 final int nodes_lacking_name = SurfacingUtil.getNumberOfNodesLackingName( intree, parent_names );
531 if ( nodes_lacking_name > 0 ) {
532 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] has "
533 + nodes_lacking_name + " node(s) lacking a name [parent names:" + parent_names + "]" );
535 preparePhylogenyForParsimonyAnalyses( intree, input_file_properties );
536 if ( !intree.isCompletelyBinary() ) {
537 ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "input tree [" + intree_file
538 + "] is not completely binary" );
540 intrees[ i++ ] = intree;
545 private static void log( final String msg, final Writer w ) {
548 w.write( ForesterUtil.LINE_SEPARATOR );
550 catch ( final IOException e ) {
551 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
555 public static void main( final String args[] ) {
556 final long start_time = new Date().getTime();
557 // final StringBuffer log = new StringBuffer();
558 final StringBuilder html_desc = new StringBuilder();
559 ForesterUtil.printProgramInformation( surfacing.PRG_NAME,
560 surfacing.PRG_VERSION,
564 final String nl = ForesterUtil.LINE_SEPARATOR;
565 html_desc.append( "<table>" + nl );
566 html_desc.append( "<tr><td>Produced by:</td><td>" + surfacing.PRG_NAME + "</td></tr>" + nl );
567 html_desc.append( "<tr><td>Version:</td><td>" + surfacing.PRG_VERSION + "</td></tr>" + nl );
568 html_desc.append( "<tr><td>Release Date:</td><td>" + surfacing.PRG_DATE + "</td></tr>" + nl );
569 html_desc.append( "<tr><td>Contact:</td><td>" + surfacing.E_MAIL + "</td></tr>" + nl );
570 html_desc.append( "<tr><td>WWW:</td><td>" + surfacing.WWW + "</td></tr>" + nl );
571 CommandLineArguments cla = null;
573 cla = new CommandLineArguments( args );
575 catch ( final Exception e ) {
576 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
578 if ( cla.isOptionSet( surfacing.HELP_OPTION_1 ) || cla.isOptionSet( surfacing.HELP_OPTION_2 ) ) {
579 surfacing.printHelp();
582 if ( ( args.length < 1 ) ) {
583 surfacing.printHelp();
586 final List<String> allowed_options = new ArrayList<String>();
587 allowed_options.add( surfacing.NOT_IGNORE_DUFS_OPTION );
588 allowed_options.add( surfacing.MAX_E_VALUE_OPTION );
589 allowed_options.add( surfacing.DETAILEDNESS_OPTION );
590 allowed_options.add( surfacing.OUTPUT_FILE_OPTION );
591 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_OPTION );
592 allowed_options.add( surfacing.SPECIES_MATRIX_OPTION );
593 allowed_options.add( surfacing.SCORING_OPTION );
594 allowed_options.add( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
595 allowed_options.add( surfacing.NO_ENGULFING_OVERLAP_OPTION );
596 allowed_options.add( surfacing.DOMAIN_COUNT_SORT_OPTION );
597 allowed_options.add( surfacing.CUTOFF_SCORE_FILE_OPTION );
598 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION );
599 allowed_options.add( surfacing.OUTPUT_DIR_OPTION );
600 allowed_options.add( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION );
601 allowed_options.add( surfacing.PFAM_TO_GO_FILE_USE_OPTION );
602 allowed_options.add( surfacing.GO_OBO_FILE_USE_OPTION );
603 allowed_options.add( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION );
604 allowed_options.add( surfacing.GO_NAMESPACE_LIMIT_OPTION );
605 allowed_options.add( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
606 allowed_options.add( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION );
607 allowed_options.add( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS );
608 allowed_options.add( JACKNIFE_OPTION );
609 allowed_options.add( JACKNIFE_RANDOM_SEED_OPTION );
610 allowed_options.add( JACKNIFE_RATIO_OPTION );
611 allowed_options.add( INPUT_SPECIES_TREE_OPTION );
612 //allowed_options.add( INFER_SPECIES_TREES_OPTION );
613 allowed_options.add( FILTER_POSITIVE_OPTION );
614 allowed_options.add( FILTER_NEGATIVE_OPTION );
615 allowed_options.add( INPUT_FILES_FROM_FILE_OPTION );
616 allowed_options.add( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
617 allowed_options.add( FILTER_NEGATIVE_DOMAINS_OPTION );
618 allowed_options.add( IGNORE_VIRAL_IDS );
619 allowed_options.add( SEQ_EXTRACT_OPTION );
620 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
621 allowed_options.add( SECONDARY_FEATURES_PARSIMONY_MAP_FILE );
622 allowed_options.add( PLUS_MINUS_ANALYSIS_OPTION );
623 allowed_options.add( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS );
624 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS );
625 allowed_options.add( CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY );
626 boolean ignore_dufs = surfacing.IGNORE_DUFS_DEFAULT;
627 boolean ignore_combination_with_same = surfacing.IGNORE_COMBINATION_WITH_SAME_DEFAULLT;
628 double e_value_max = surfacing.MAX_E_VALUE_DEFAULT;
629 int max_allowed_overlap = surfacing.MAX_ALLOWED_OVERLAP_DEFAULT;
630 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
631 if ( dissallowed_options.length() > 0 ) {
632 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown option(s): " + dissallowed_options );
634 boolean output_binary_domain_combinationsfor_graph_analysis = false;
635 if ( cla.isOptionSet( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS ) ) {
636 output_binary_domain_combinationsfor_graph_analysis = true;
638 if ( cla.isOptionSet( surfacing.MAX_E_VALUE_OPTION ) ) {
640 e_value_max = cla.getOptionValueAsDouble( surfacing.MAX_E_VALUE_OPTION );
642 catch ( final Exception e ) {
643 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for E-value maximum" );
646 if ( cla.isOptionSet( surfacing.MAX_ALLOWED_OVERLAP_OPTION ) ) {
648 max_allowed_overlap = cla.getOptionValueAsInt( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
650 catch ( final Exception e ) {
651 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for maximal allowed domain overlap" );
654 boolean no_engulfing_overlaps = false;
655 if ( cla.isOptionSet( surfacing.NO_ENGULFING_OVERLAP_OPTION ) ) {
656 no_engulfing_overlaps = true;
658 boolean ignore_virus_like_ids = false;
659 if ( cla.isOptionSet( surfacing.IGNORE_VIRAL_IDS ) ) {
660 ignore_virus_like_ids = true;
662 if ( cla.isOptionSet( surfacing.NOT_IGNORE_DUFS_OPTION ) ) {
665 if ( cla.isOptionSet( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION ) ) {
666 ignore_combination_with_same = true;
668 boolean ignore_domains_without_combs_in_all_spec = IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT;
669 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION ) ) {
670 ignore_domains_without_combs_in_all_spec = true;
672 boolean ignore_species_specific_domains = IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT;
673 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION ) ) {
674 ignore_species_specific_domains = true;
676 File output_file = null;
677 if ( cla.isOptionSet( surfacing.OUTPUT_FILE_OPTION ) ) {
678 if ( !cla.isOptionValueSet( surfacing.OUTPUT_FILE_OPTION ) ) {
679 ForesterUtil.fatalError( surfacing.PRG_NAME,
680 "no value for domain combinations similarities output file: -"
681 + surfacing.OUTPUT_FILE_OPTION + "=<file>" );
683 output_file = new File( cla.getOptionValue( surfacing.OUTPUT_FILE_OPTION ) );
684 SurfacingUtil.checkForOutputFileWriteability( output_file );
686 File cutoff_scores_file = null;
687 Map<String, Double> individual_score_cutoffs = null;
688 if ( cla.isOptionSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
689 if ( !cla.isOptionValueSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
690 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for individual domain score cutoffs file: -"
691 + surfacing.CUTOFF_SCORE_FILE_OPTION + "=<file>" );
693 cutoff_scores_file = new File( cla.getOptionValue( surfacing.CUTOFF_SCORE_FILE_OPTION ) );
694 final String error = ForesterUtil.isReadableFile( cutoff_scores_file );
695 if ( !ForesterUtil.isEmpty( error ) ) {
696 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read individual domain score cutoffs file: "
700 final BasicTable<String> scores_table = BasicTableParser.parse( cutoff_scores_file, " " );
701 individual_score_cutoffs = scores_table.getColumnsAsMapDouble( 0, 1 );
703 catch ( final IOException e ) {
704 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from individual score cutoffs file: " + e );
707 BinaryDomainCombination.DomainCombinationType dc_type = BinaryDomainCombination.DomainCombinationType.BASIC;
708 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS ) ) {
709 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED;
711 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY ) ) {
712 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT;
715 if ( cla.isOptionSet( surfacing.OUTPUT_DIR_OPTION ) ) {
716 if ( !cla.isOptionValueSet( surfacing.OUTPUT_DIR_OPTION ) ) {
717 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for output directory: -"
718 + surfacing.OUTPUT_DIR_OPTION + "=<dir>" );
720 out_dir = new File( cla.getOptionValue( surfacing.OUTPUT_DIR_OPTION ) );
721 if ( out_dir.exists() && ( out_dir.listFiles().length > 0 ) ) {
722 ForesterUtil.fatalError( surfacing.PRG_NAME, "\"" + out_dir + "\" aready exists and is not empty" );
724 if ( !out_dir.exists() ) {
725 final boolean success = out_dir.mkdir();
726 if ( !success || !out_dir.exists() ) {
727 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to create \"" + out_dir + "\"" );
730 if ( !out_dir.canWrite() ) {
731 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot write to \"" + out_dir + "\"" );
734 File positive_filter_file = null;
735 File negative_filter_file = null;
736 File negative_domains_filter_file = null;
737 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) && cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
738 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use both negative and positive protein filter" );
740 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION )
741 && ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) || cla
742 .isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) ) {
744 .fatalError( surfacing.PRG_NAME,
745 "attempt to use both negative or positive protein filter together wirh a negative domains filter" );
747 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
748 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
749 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative filter: -"
750 + surfacing.FILTER_NEGATIVE_OPTION + "=<file>" );
752 negative_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_OPTION ) );
753 final String msg = ForesterUtil.isReadableFile( negative_filter_file );
754 if ( !ForesterUtil.isEmpty( msg ) ) {
755 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_filter_file + "\": "
759 else if ( cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
760 if ( !cla.isOptionValueSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
761 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for positive filter: -"
762 + surfacing.FILTER_POSITIVE_OPTION + "=<file>" );
764 positive_filter_file = new File( cla.getOptionValue( surfacing.FILTER_POSITIVE_OPTION ) );
765 final String msg = ForesterUtil.isReadableFile( positive_filter_file );
766 if ( !ForesterUtil.isEmpty( msg ) ) {
767 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + positive_filter_file + "\": "
771 else if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
772 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
773 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative domains filter: -"
774 + surfacing.FILTER_NEGATIVE_DOMAINS_OPTION + "=<file>" );
776 negative_domains_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) );
777 final String msg = ForesterUtil.isReadableFile( negative_domains_filter_file );
778 if ( !ForesterUtil.isEmpty( msg ) ) {
779 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_domains_filter_file
783 final List<String> plus_minus_analysis_high_copy_base_species = new ArrayList<String>();
784 final List<String> plus_minus_analysis_high_copy_target_species = new ArrayList<String>();
785 final List<String> plus_minus_analysis_high_low_copy_species = new ArrayList<String>();
786 final List<Object> plus_minus_analysis_numbers = new ArrayList<Object>();
787 processPlusMinusAnalysisOption( cla,
788 plus_minus_analysis_high_copy_base_species,
789 plus_minus_analysis_high_copy_target_species,
790 plus_minus_analysis_high_low_copy_species,
791 plus_minus_analysis_numbers );
792 File input_files_file = null;
793 String[] input_file_names_from_file = null;
794 if ( cla.isOptionSet( surfacing.INPUT_FILES_FROM_FILE_OPTION ) ) {
795 if ( !cla.isOptionValueSet( surfacing.INPUT_FILES_FROM_FILE_OPTION ) ) {
796 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input files file: -"
797 + surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>" );
799 input_files_file = new File( cla.getOptionValue( surfacing.INPUT_FILES_FROM_FILE_OPTION ) );
800 final String msg = ForesterUtil.isReadableFile( input_files_file );
801 if ( !ForesterUtil.isEmpty( msg ) ) {
802 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + input_files_file + "\": " + msg );
805 input_file_names_from_file = ForesterUtil.file2array( input_files_file );
807 catch ( final IOException e ) {
808 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read from \"" + input_files_file + "\": " + e );
811 if ( ( cla.getNumberOfNames() < 1 )
812 && ( ( input_file_names_from_file == null ) || ( input_file_names_from_file.length < 1 ) ) ) {
813 ForesterUtil.fatalError( surfacing.PRG_NAME,
814 "No hmmpfam output file indicated is input: use comand line directly or "
815 + surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>" );
817 DomainSimilarity.DomainSimilarityScoring scoring = SCORING_DEFAULT;
818 if ( cla.isOptionSet( surfacing.SCORING_OPTION ) ) {
819 if ( !cla.isOptionValueSet( surfacing.SCORING_OPTION ) ) {
820 ForesterUtil.fatalError( surfacing.PRG_NAME,
821 "no value for scoring method for domain combinations similarity calculation: -"
822 + surfacing.SCORING_OPTION + "=<"
823 + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
824 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|"
825 + surfacing.SCORING_COMBINATION_BASED + ">\"" );
827 final String scoring_str = cla.getOptionValue( surfacing.SCORING_OPTION );
828 if ( scoring_str.equals( surfacing.SCORING_DOMAIN_COUNT_BASED ) ) {
829 scoring = DomainSimilarity.DomainSimilarityScoring.DOMAINS;
831 else if ( scoring_str.equals( surfacing.SCORING_COMBINATION_BASED ) ) {
832 scoring = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
834 else if ( scoring_str.equals( surfacing.SCORING_PROTEIN_COUNT_BASED ) ) {
835 scoring = DomainSimilarity.DomainSimilarityScoring.PROTEINS;
838 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + scoring_str
839 + "\" for scoring method for domain combinations similarity calculation: \"-"
840 + surfacing.SCORING_OPTION + "=<" + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
841 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|" + surfacing.SCORING_COMBINATION_BASED + ">\"" );
844 boolean sort_by_species_count_first = false;
845 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION ) ) {
846 sort_by_species_count_first = true;
848 boolean species_matrix = false;
849 if ( cla.isOptionSet( surfacing.SPECIES_MATRIX_OPTION ) ) {
850 species_matrix = true;
852 boolean output_protein_lists_for_all_domains = false;
853 double output_list_of_all_proteins_per_domain_e_value_max = -1;
854 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS ) ) {
855 output_protein_lists_for_all_domains = true;
857 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION ) ) {
859 output_list_of_all_proteins_per_domain_e_value_max = cla
860 .getOptionValueAsDouble( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
862 catch ( final Exception e ) {
863 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for per domain E-value maximum" );
868 Detailedness detailedness = DETAILEDNESS_DEFAULT;
869 if ( cla.isOptionSet( surfacing.DETAILEDNESS_OPTION ) ) {
870 if ( !cla.isOptionValueSet( surfacing.DETAILEDNESS_OPTION ) ) {
871 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for -" + surfacing.DETAILEDNESS_OPTION + "=<"
872 + surfacing.DETAILEDNESS_BASIC + "|" + surfacing.DETAILEDNESS_LIST_IDS + "|"
873 + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
875 final String detness = cla.getOptionValue( surfacing.DETAILEDNESS_OPTION ).toLowerCase();
876 if ( detness.equals( surfacing.DETAILEDNESS_BASIC ) ) {
877 detailedness = DomainSimilarityCalculator.Detailedness.BASIC;
879 else if ( detness.equals( surfacing.DETAILEDNESS_LIST_IDS ) ) {
880 detailedness = DomainSimilarityCalculator.Detailedness.LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES;
882 else if ( detness.equals( surfacing.DETAILEDNESS_PUNCTILIOUS ) ) {
883 detailedness = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
886 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + detness + "\" for detailedness: \"-"
887 + surfacing.DETAILEDNESS_OPTION + "=<" + surfacing.DETAILEDNESS_BASIC + "|"
888 + surfacing.DETAILEDNESS_LIST_IDS + "|" + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
891 String automated_pairwise_comparison_suffix = null;
892 boolean perform_pwc = false;
893 boolean write_pwc_files = false;
894 if ( cla.isOptionSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
896 if ( !cla.isOptionValueSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
897 write_pwc_files = false;
900 write_pwc_files = true;
901 automated_pairwise_comparison_suffix = "_"
902 + cla.getOptionValue( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
905 String query_domain_ids = null;
906 if ( cla.isOptionSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
907 if ( !cla.isOptionValueSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
909 .fatalError( surfacing.PRG_NAME,
910 "no domain ids given for sequences with given domains to be extracted : -"
911 + surfacing.SEQ_EXTRACT_OPTION
912 + "=<ordered domain sequences, domain ids separated by '~', sequences separated by '#'>" );
914 query_domain_ids = cla.getOptionValue( surfacing.SEQ_EXTRACT_OPTION );
916 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field = DOMAIN_SORT_FILD_DEFAULT;
917 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field_for_automated_pwc = DOMAIN_SORT_FILD_DEFAULT;
918 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
919 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
920 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for domain combinations similarities sorting: -"
921 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
922 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
923 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
924 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
925 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|"
926 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
929 final String sort_str = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ).toLowerCase();
930 if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ALPHA ) ) {
931 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
932 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
934 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MAX ) ) {
935 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX;
936 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
938 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MIN ) ) {
939 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MIN;
940 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
942 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MEAN ) ) {
943 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MEAN;
944 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MEAN;
946 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT ) ) {
947 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SPECIES_COUNT;
948 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
950 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SD ) ) {
951 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SD;
952 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
954 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_DIFF ) ) {
955 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
956 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
958 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF ) ) {
959 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
960 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
962 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF ) ) {
963 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
964 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
967 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort_str
968 + "\" for domain combinations similarities sorting: \"-"
969 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
970 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
971 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
972 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
973 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|" + "|"
974 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
978 PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option = DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT;
979 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
980 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
981 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for print option: -"
982 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
983 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
984 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
986 final String sort = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ).toLowerCase();
987 if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML ) ) {
988 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.HTML;
990 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML ) ) {
991 // domain_similarity_print_option =
992 // DomainSimilarity.PRINT_OPTION.SIMPLE_HTML;
993 ForesterUtil.fatalError( surfacing.PRG_NAME, "simple HTML output not implemented yet :(" );
995 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED ) ) {
996 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.SIMPLE_TAB_DELIMITED;
999 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort + "\" for print option: -"
1000 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
1001 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
1002 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
1005 GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order = DOMAINS_SORT_ORDER_DEFAULT;
1006 if ( cla.isOptionSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
1007 if ( !cla.isOptionValueSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
1008 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for sorting of domain counts: -"
1009 + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<" + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|"
1010 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1011 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1012 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1014 final String sort = cla.getOptionValue( surfacing.DOMAIN_COUNT_SORT_OPTION ).toLowerCase();
1015 if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_ALPHA ) ) {
1016 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
1018 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT ) ) {
1019 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_COUNT;
1021 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT ) ) {
1022 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_PROTEINS_COUNT;
1024 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT ) ) {
1025 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.COMBINATIONS_COUNT;
1028 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort
1029 + "\" for sorting of domain counts: \"-" + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<"
1030 + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|" + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1031 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1032 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1035 String[][] input_file_properties = null;
1036 if ( input_file_names_from_file != null ) {
1037 input_file_properties = surfacing.processInputFileNames( input_file_names_from_file );
1040 input_file_properties = surfacing.processInputFileNames( cla.getNames() );
1042 final int number_of_genomes = input_file_properties.length;
1043 if ( number_of_genomes < 2 ) {
1044 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot analyze less than two files" );
1046 if ( ( number_of_genomes < 3 ) && perform_pwc ) {
1047 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use : -"
1048 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1049 + "=<suffix> to turn on pairwise analyses with less than three input files" );
1051 checkWriteabilityForPairwiseComparisons( domain_similarity_print_option,
1052 input_file_properties,
1053 automated_pairwise_comparison_suffix,
1055 for( int i = 0; i < number_of_genomes; i++ ) {
1056 File dcc_outfile = new File( input_file_properties[ i ][ 0 ]
1057 + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
1058 if ( out_dir != null ) {
1059 dcc_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + dcc_outfile );
1061 SurfacingUtil.checkForOutputFileWriteability( dcc_outfile );
1063 File pfam_to_go_file = null;
1064 Map<DomainId, List<GoId>> domain_id_to_go_ids_map = null;
1065 int domain_id_to_go_ids_count = 0;
1066 if ( cla.isOptionSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1067 if ( !cla.isOptionValueSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1068 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for Pfam to GO mapping file: -"
1069 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>" );
1071 pfam_to_go_file = new File( cla.getOptionValue( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) );
1072 final String error = ForesterUtil.isReadableFile( pfam_to_go_file );
1073 if ( !ForesterUtil.isEmpty( error ) ) {
1074 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read Pfam to GO mapping file: " + error );
1077 final PfamToGoParser parser = new PfamToGoParser( pfam_to_go_file );
1078 final List<PfamToGoMapping> pfam_to_go_mappings = parser.parse();
1079 domain_id_to_go_ids_map = SurfacingUtil.createDomainIdToGoIdMap( pfam_to_go_mappings );
1080 if ( parser.getMappingCount() < domain_id_to_go_ids_map.size() ) {
1081 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME,
1082 "parser.getMappingCount() < domain_id_to_go_ids_map.size()" );
1084 domain_id_to_go_ids_count = parser.getMappingCount();
1086 catch ( final IOException e ) {
1087 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from Pfam to GO mapping file: " + e );
1090 File go_obo_file = null;
1091 List<GoTerm> go_terms = null;
1092 if ( cla.isOptionSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1093 if ( !cla.isOptionValueSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1094 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO OBO file: -"
1095 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>" );
1097 if ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) {
1098 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO OBO file (-"
1099 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>) without Pfam to GO mapping file ("
1100 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1102 go_obo_file = new File( cla.getOptionValue( surfacing.GO_OBO_FILE_USE_OPTION ) );
1103 final String error = ForesterUtil.isReadableFile( go_obo_file );
1104 if ( !ForesterUtil.isEmpty( error ) ) {
1105 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read GO OBO file: " + error );
1108 final OBOparser parser = new OBOparser( go_obo_file, OBOparser.ReturnType.BASIC_GO_TERM );
1109 go_terms = parser.parse();
1110 if ( parser.getGoTermCount() != go_terms.size() ) {
1112 .unexpectedFatalError( surfacing.PRG_NAME, "parser.getGoTermCount() != go_terms.size()" );
1115 catch ( final IOException e ) {
1116 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from GO OBO file: " + e );
1119 Map<GoId, GoTerm> go_id_to_term_map = null;
1120 if ( ( ( domain_id_to_go_ids_map != null ) && ( domain_id_to_go_ids_map.size() > 0 ) )
1121 && ( ( go_terms != null ) && ( go_terms.size() > 0 ) ) ) {
1122 go_id_to_term_map = GoUtils.createGoIdToGoTermMap( go_terms );
1124 GoNameSpace go_namespace_limit = null;
1125 if ( cla.isOptionSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1126 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1127 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO namespace limit (-"
1128 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<namespace>) without Pfam to GO mapping file ("
1129 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>) and GO OBO file (-"
1130 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1132 if ( !cla.isOptionValueSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1133 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO namespace limit: \"-"
1134 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1135 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1136 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1137 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1139 final String go_namespace_limit_str = cla.getOptionValue( surfacing.GO_NAMESPACE_LIMIT_OPTION )
1141 if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION ) ) {
1142 go_namespace_limit = GoNameSpace.createMolecularFunction();
1144 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS ) ) {
1145 go_namespace_limit = GoNameSpace.createBiologicalProcess();
1147 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT ) ) {
1148 go_namespace_limit = GoNameSpace.createCellularComponent();
1151 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + go_namespace_limit_str
1152 + "\" for GO namespace limit: \"-" + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1153 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1154 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1155 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1158 if ( ( domain_similarity_sort_field == DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE )
1159 && ( number_of_genomes > 2 ) ) {
1160 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
1162 boolean jacknifed_distances = false;
1163 int jacknife_resamplings = JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT;
1164 double jacknife_ratio = JACKNIFE_RATIO_DEFAULT;
1165 long random_seed = JACKNIFE_RANDOM_SEED_DEFAULT;
1166 if ( cla.isOptionSet( surfacing.JACKNIFE_OPTION ) ) {
1167 if ( ( number_of_genomes < 3 ) || !perform_pwc ) {
1168 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use jacknife resampling analysis (-"
1169 + surfacing.JACKNIFE_OPTION + "[=<number of resamplings>]) without pairwise analyses ("
1170 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1171 + "=<suffix for pairwise comparison output files>)" );
1173 jacknifed_distances = true;
1174 if ( cla.isOptionHasAValue( surfacing.JACKNIFE_OPTION ) ) {
1176 jacknife_resamplings = cla.getOptionValueAsInt( surfacing.JACKNIFE_OPTION );
1178 catch ( final IOException e ) {
1179 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for number of resamplings" );
1181 if ( jacknife_resamplings < 2 ) {
1182 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use less than 2 resamplings" );
1185 if ( cla.isOptionSet( surfacing.JACKNIFE_RATIO_OPTION )
1186 && cla.isOptionHasAValue( surfacing.JACKNIFE_RATIO_OPTION ) ) {
1188 jacknife_ratio = cla.getOptionValueAsDouble( surfacing.JACKNIFE_RATIO_OPTION );
1190 catch ( final IOException e ) {
1191 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for jacknife ratio" );
1193 if ( ( jacknife_ratio <= 0.0 ) || ( jacknife_ratio >= 1.0 ) ) {
1194 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use illegal value for jacknife ratio: "
1198 if ( cla.isOptionSet( surfacing.JACKNIFE_RANDOM_SEED_OPTION )
1199 && cla.isOptionHasAValue( surfacing.JACKNIFE_RANDOM_SEED_OPTION ) ) {
1201 random_seed = cla.getOptionValueAsLong( surfacing.JACKNIFE_RANDOM_SEED_OPTION );
1203 catch ( final IOException e ) {
1204 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for random generator seed" );
1208 // boolean infer_species_trees = false;
1209 // if ( cla.isOptionSet( surfacing.INFER_SPECIES_TREES_OPTION ) ) {
1210 // if ( ( output_file == null ) || ( number_of_genomes < 3 )
1211 // || ForesterUtil.isEmpty( automated_pairwise_comparison_suffix ) ) {
1212 // ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer species trees (-"
1213 // + surfacing.INFER_SPECIES_TREES_OPTION + " without pairwise analyses ("
1214 // + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1215 // + "=<suffix for pairwise comparison output files>)" );
1217 // infer_species_trees = true;
1219 File[] intree_files = null;
1220 Phylogeny[] intrees = null;
1221 if ( cla.isOptionSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1222 // TODO FIXME if jacknife.... maybe not
1223 if ( number_of_genomes < 3 ) {
1224 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer gains and losses on input species trees (-"
1225 + surfacing.INPUT_SPECIES_TREE_OPTION + " without pairwise analyses ("
1226 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1227 + "=<suffix for pairwise comparison output files>)" );
1229 if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1230 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input tree: -"
1231 + surfacing.INPUT_SPECIES_TREE_OPTION + "=<tree file in phyloXML format>" );
1233 final String intrees_str = cla.getOptionValue( surfacing.INPUT_SPECIES_TREE_OPTION );
1234 if ( intrees_str.indexOf( "#" ) > 0 ) {
1235 final String[] intrees_strs = intrees_str.split( "#" );
1236 intree_files = new File[ intrees_strs.length ];
1238 for( final String s : intrees_strs ) {
1239 intree_files[ i++ ] = new File( s.trim() );
1243 intree_files = new File[ 1 ];
1244 intree_files[ 0 ] = new File( intrees_str );
1246 intrees = getIntrees( intree_files, number_of_genomes, input_file_properties );
1248 long random_number_seed_for_fitch_parsimony = 0l;
1249 boolean radomize_fitch_parsimony = false;
1250 if ( cla.isOptionSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1251 if ( !cla.isOptionValueSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1252 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for random number seed: -"
1253 + surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION + "=<seed>" );
1256 random_number_seed_for_fitch_parsimony = cla
1257 .getOptionValueAsLong( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
1259 catch ( final IOException e ) {
1260 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1262 radomize_fitch_parsimony = true;
1264 SortedSet<DomainId> filter = null;
1265 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1266 || ( negative_domains_filter_file != null ) ) {
1267 filter = new TreeSet<DomainId>();
1268 if ( positive_filter_file != null ) {
1269 processFilter( positive_filter_file, filter );
1271 else if ( negative_filter_file != null ) {
1272 processFilter( negative_filter_file, filter );
1274 else if ( negative_domains_filter_file != null ) {
1275 processFilter( negative_domains_filter_file, filter );
1278 Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps = null;
1279 File[] secondary_features_map_files = null;
1280 final File domain_lengths_analysis_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1281 + DOMAIN_LENGTHS_ANALYSIS_SUFFIX );
1282 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
1283 SurfacingUtil.checkForOutputFileWriteability( domain_lengths_analysis_outfile );
1285 if ( cla.isOptionSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1286 if ( !cla.isOptionValueSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1287 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for secondary features map file: -"
1288 + surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE + "=<file>" );
1290 final String[] secondary_features_map_files_strs = cla
1291 .getOptionValue( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ).split( "#" );
1292 secondary_features_map_files = new File[ secondary_features_map_files_strs.length ];
1293 domain_id_to_secondary_features_maps = new Map[ secondary_features_map_files_strs.length ];
1295 for( final String secondary_features_map_files_str : secondary_features_map_files_strs ) {
1296 secondary_features_map_files[ i ] = new File( secondary_features_map_files_str );
1297 final String error = ForesterUtil.isReadableFile( secondary_features_map_files[ i ] );
1298 if ( !ForesterUtil.isEmpty( error ) ) {
1299 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read secondary features map file: " + error );
1302 domain_id_to_secondary_features_maps[ i ] = SurfacingUtil
1303 .createDomainIdToSecondaryFeaturesMap( secondary_features_map_files[ i ] );
1305 catch ( final IOException e ) {
1306 ForesterUtil.fatalError( surfacing.PRG_NAME,
1307 "cannot read secondary features map file: " + e.getMessage() );
1309 catch ( final Exception e ) {
1310 ForesterUtil.fatalError( surfacing.PRG_NAME, "problem with contents of features map file ["
1311 + secondary_features_map_files[ i ] + "]: " + e.getMessage() );
1316 if ( out_dir == null ) {
1317 ForesterUtil.fatalError( surfacing.PRG_NAME, "no output directory indicated (-"
1318 + surfacing.OUTPUT_DIR_OPTION + "=<dir>)" );
1320 if ( output_file == null ) {
1321 ForesterUtil.fatalError( surfacing.PRG_NAME, "no name for (main) output file indicated (-"
1322 + surfacing.OUTPUT_FILE_OPTION + "=<file>)" );
1324 if ( ( domain_id_to_go_ids_map == null ) || domain_id_to_go_ids_map.isEmpty() ) {
1325 ForesterUtil.fatalError( surfacing.PRG_NAME,
1326 "no (acceptable) Pfam to GO id mapping file provided ('pfam2go file') (-"
1327 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1329 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1330 ForesterUtil.fatalError( surfacing.PRG_NAME,
1331 "no (acceptable) go id to term mapping file provided ('GO OBO file') (-"
1332 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1334 System.out.println( "Output directory : " + out_dir );
1335 if ( input_file_names_from_file != null ) {
1336 System.out.println( "Input files names from : " + input_files_file + " ["
1337 + input_file_names_from_file.length + " input files]" );
1338 html_desc.append( "<tr><td>Input files names from:</td><td>" + input_files_file + " ["
1339 + input_file_names_from_file.length + " input files]</td></tr>" + nl );
1341 if ( positive_filter_file != null ) {
1342 final int filter_size = filter.size();
1343 System.out.println( "Positive protein filter : " + positive_filter_file + " [" + filter_size
1345 html_desc.append( "<tr><td>Positive protein filter:</td><td>" + positive_filter_file + " [" + filter_size
1346 + " domain ids]</td></tr>" + nl );
1348 if ( negative_filter_file != null ) {
1349 final int filter_size = filter.size();
1350 System.out.println( "Negative protein filter : " + negative_filter_file + " [" + filter_size
1352 html_desc.append( "<tr><td>Negative protein filter:</td><td>" + negative_filter_file + " [" + filter_size
1353 + " domain ids]</td></tr>" + nl );
1355 if ( negative_domains_filter_file != null ) {
1356 final int filter_size = filter.size();
1357 System.out.println( "Negative domain filter : " + negative_domains_filter_file + " [" + filter_size
1359 html_desc.append( "<tr><td>Negative domain filter:</td><td>" + negative_domains_filter_file + " ["
1360 + filter_size + " domain ids]</td></tr>" + nl );
1362 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
1364 for( final String s : plus_minus_analysis_high_copy_base_species ) {
1365 plus0 += "+" + s + " ";
1368 for( final String s : plus_minus_analysis_high_copy_target_species ) {
1369 plus1 += "*" + s + " ";
1372 for( final String s : plus_minus_analysis_high_low_copy_species ) {
1373 minus += "-" + s + " ";
1375 System.out.println( "Plus-minus analysis : " + plus1 + "&& " + plus0 + "&& " + minus );
1376 html_desc.append( "<tr><td>Plus-minus analysis:</td><td>" + plus1 + "&& " + plus0 + "&& " + minus
1377 + "</td></tr>" + nl );
1379 if ( cutoff_scores_file != null ) {
1380 System.out.println( "Cutoff scores file : " + cutoff_scores_file );
1381 html_desc.append( "<tr><td>Cutoff scores file:</td><td>" + cutoff_scores_file + "</td></tr>" + nl );
1383 if ( e_value_max >= 0.0 ) {
1384 System.out.println( "E-value maximum (inclusive) : " + e_value_max );
1385 html_desc.append( "<tr><td>E-value maximum (inclusive):</td><td>" + e_value_max + "</td></tr>" + nl );
1387 if ( output_protein_lists_for_all_domains ) {
1388 System.out.println( "Domain E-value max : " + output_list_of_all_proteins_per_domain_e_value_max );
1389 html_desc.append( "<tr><td>Protein lists: E-value maximum per domain (inclusive):</td><td>"
1390 + output_list_of_all_proteins_per_domain_e_value_max + "</td></tr>" + nl );
1392 System.out.println( "Ignore DUFs : " + ignore_dufs );
1393 if ( ignore_virus_like_ids ) {
1394 System.out.println( "Ignore virus like ids : " + ignore_virus_like_ids );
1395 html_desc.append( "<tr><td>Ignore virus, phage, transposition related ids:</td><td>"
1396 + ignore_virus_like_ids + "</td></tr>" + nl );
1398 html_desc.append( "<tr><td>Ignore DUFs:</td><td>" + ignore_dufs + "</td></tr>" + nl );
1399 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1400 System.out.println( "Max allowed domain overlap : " + max_allowed_overlap );
1401 html_desc.append( "<tr><td>Max allowed domain overlap:</td><td>" + max_allowed_overlap + "</td></tr>" + nl );
1403 if ( no_engulfing_overlaps ) {
1404 System.out.println( "Ignore engulfed domains : " + no_engulfing_overlaps );
1405 html_desc.append( "<tr><td>Ignore (lower confidence) engulfed domains:</td><td>" + no_engulfing_overlaps
1406 + "</td></tr>" + nl );
1408 System.out.println( "Ignore singlet domains : " + ignore_domains_without_combs_in_all_spec );
1410 .append( "<tr><td>Ignore singlet domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1411 + ignore_domains_without_combs_in_all_spec + "</td></tr>" + nl );
1412 System.out.println( "Ignore species specific doms: " + ignore_species_specific_domains );
1414 .append( "<tr><td>Ignore species specific domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1415 + ignore_species_specific_domains + "</td></tr>" + nl );
1416 System.out.println( "Ignore combination with self: " + ignore_combination_with_same );
1417 html_desc.append( "<tr><td>Ignore combination with self for domain combination similarity analyses:</td><td>"
1418 + ignore_combination_with_same + "</td></tr>" + nl );
1419 System.out.println( "Consider directedness : "
1420 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) );
1421 html_desc.append( "<tr><td>Consider directedness of binary domain combinations:</td><td>"
1422 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) + "</td></tr>" + nl );
1423 if ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) {
1424 System.out.println( "Consider adjacency : "
1425 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) );
1426 html_desc.append( "<tr><td>Consider djacency of binary domain combinations:</td><td>"
1427 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) + "</td></tr>"
1430 System.out.print( "Domain counts sort order : " );
1431 switch ( dc_sort_order ) {
1432 case ALPHABETICAL_KEY_ID:
1433 System.out.println( "alphabetical" );
1435 case KEY_DOMAIN_COUNT:
1436 System.out.println( "domain count" );
1438 case KEY_DOMAIN_PROTEINS_COUNT:
1439 System.out.println( "domain proteins count" );
1441 case COMBINATIONS_COUNT:
1442 System.out.println( "domain combinations count" );
1445 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for dc sort order" );
1447 if ( domain_id_to_go_ids_map != null ) {
1448 System.out.println( "Pfam to GO mappings from : " + pfam_to_go_file + " [" + domain_id_to_go_ids_count
1450 html_desc.append( "<tr><td>Pfam to GO mappings from:</td><td>" + pfam_to_go_file + " ["
1451 + domain_id_to_go_ids_count + " mappings]" + "</td></tr>" + nl );
1453 if ( go_terms != null ) {
1454 System.out.println( "GO terms from : " + go_obo_file + " [" + go_terms.size() + " terms]" );
1455 html_desc.append( "<tr><td>GO terms from:</td><td>" + go_obo_file + " [" + go_terms.size() + " terms]"
1456 + "</td></tr>" + nl );
1458 if ( go_namespace_limit != null ) {
1459 System.out.println( "Limit GO terms to : " + go_namespace_limit.toString() );
1460 html_desc.append( "<tr><td>Limit GO terms to</td><td>" + go_namespace_limit + "</td></tr>" + nl );
1462 if ( perform_pwc ) {
1463 System.out.println( "Suffix for PWC files : " + automated_pairwise_comparison_suffix );
1464 html_desc.append( "<tr><td>Suffix for PWC files</td><td>" + automated_pairwise_comparison_suffix
1465 + "</td></tr>" + nl );
1467 if ( out_dir != null ) {
1468 System.out.println( "Output directory : " + out_dir );
1470 if ( query_domain_ids != null ) {
1471 System.out.println( "Query domains (ordered) : " + query_domain_ids );
1472 html_desc.append( "<tr><td></td><td>" + query_domain_ids + "</td></tr>" + nl );
1474 System.out.println( "Write similarities to : " + output_file );
1475 System.out.print( " Scoring method : " );
1476 html_desc.append( "<tr><td>Scoring method:</td><td>" );
1477 switch ( scoring ) {
1479 System.out.println( "domain combinations based" );
1480 html_desc.append( "domain combinations based" + "</td></tr>" + nl );
1483 System.out.println( "domain counts based" );
1484 html_desc.append( "domain counts based" + "</td></tr>" + nl );
1487 System.out.println( "domain proteins counts based" );
1488 html_desc.append( "domain proteins counts based" + "</td></tr>" + nl );
1491 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
1493 System.out.print( " Sort by : " );
1494 html_desc.append( "<tr><td>Sort by:</td><td>" );
1495 switch ( domain_similarity_sort_field ) {
1497 System.out.print( "score minimum" );
1498 html_desc.append( "score minimum" );
1501 System.out.print( "score maximum" );
1502 html_desc.append( "score maximum" );
1505 System.out.print( "score mean" );
1506 html_desc.append( "score mean" );
1509 System.out.print( "score standard deviation" );
1510 html_desc.append( "score standard deviation" );
1513 System.out.print( "species number" );
1514 html_desc.append( "species number" );
1517 System.out.print( "alphabetical domain identifier" );
1518 html_desc.append( "alphabetical domain identifier" );
1520 case MAX_DIFFERENCE:
1521 System.out.print( "(maximal) difference" );
1522 html_desc.append( "(maximal) difference" );
1524 case ABS_MAX_COUNTS_DIFFERENCE:
1525 System.out.print( "absolute (maximal) counts difference" );
1526 html_desc.append( "absolute (maximal) counts difference" );
1528 case MAX_COUNTS_DIFFERENCE:
1529 System.out.print( "(maximal) counts difference" );
1530 html_desc.append( "(maximal) counts difference" );
1533 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1535 if ( sort_by_species_count_first ) {
1536 System.out.println( " (sort by species count first)" );
1537 html_desc.append( " (sort by species count first)" );
1540 System.out.println();
1542 html_desc.append( "</td></tr>" + nl );
1543 System.out.print( " Detailedness : " );
1544 switch ( detailedness ) {
1546 System.out.println( "basic" );
1548 case LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES:
1549 System.out.println( "list combining domains for each species" );
1552 System.out.println( "punctilious" );
1555 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for detailedness" );
1557 System.out.print( " Print option : " );
1558 switch ( domain_similarity_print_option ) {
1560 System.out.println( "HTML" );
1562 case SIMPLE_TAB_DELIMITED:
1563 System.out.println( "simple tab delimited" );
1566 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for print option" );
1568 System.out.print( " Species matrix : " + species_matrix );
1569 System.out.println();
1570 final File dc_data_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + DATA_FILE_SUFFIX );
1571 System.out.println( "Domain comb data output : " + dc_data_file );
1572 html_desc.append( "<tr><td>Domain combination data output:</td><td> " + dc_data_file + " </td></tr>" );
1573 System.out.println();
1574 if ( perform_pwc ) {
1575 System.out.println( "Pairwise comparisons: " );
1576 html_desc.append( "<tr><td>Pairwise comparisons:</td><td></td></tr>" );
1577 System.out.print( " Sort by : " );
1578 html_desc.append( "<tr><td>Sort by:</td><td>" );
1579 switch ( domain_similarity_sort_field_for_automated_pwc ) {
1581 System.out.print( "score mean" );
1582 html_desc.append( "score mean" );
1585 System.out.print( "alphabetical domain identifier" );
1586 html_desc.append( "alphabetical domain identifier" );
1588 case MAX_DIFFERENCE:
1589 System.out.print( "difference" );
1590 html_desc.append( "difference" );
1592 case ABS_MAX_COUNTS_DIFFERENCE:
1593 System.out.print( "absolute counts difference" );
1594 html_desc.append( "absolute counts difference" );
1596 case MAX_COUNTS_DIFFERENCE:
1597 System.out.print( "counts difference" );
1598 html_desc.append( "counts difference" );
1602 .unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1604 System.out.println();
1605 html_desc.append( "</td></tr>" + nl );
1606 if ( jacknifed_distances ) {
1607 html_desc.append( "<tr><td>Jacknife:</td><td>" + jacknife_resamplings + " resamplings</td></tr>" + nl );
1608 html_desc.append( "<tr><td>Jacknife ratio:</td><td>" + ForesterUtil.round( jacknife_ratio, 2 )
1609 + "</td></tr>" + nl );
1610 html_desc.append( "<tr><td>Jacknife random number seed:</td><td>" + random_seed + "</td></tr>" + nl );
1611 System.out.println( " Jacknife : " + jacknife_resamplings + " resamplings" );
1612 System.out.println( " Ratio : " + ForesterUtil.round( jacknife_ratio, 2 ) );
1613 System.out.println( " Random number seed : " + random_seed );
1615 // if ( infer_species_trees ) {
1616 // html_desc.append( "<tr><td>Infer species trees:</td><td>true</td></tr>" + nl );
1617 // System.out.println( " Infer species trees : true" );
1619 if ( ( intrees != null ) && ( intrees.length > 0 ) ) {
1620 for( final File intree_file : intree_files ) {
1621 html_desc.append( "<tr><td>Intree for gain/loss parsimony analysis:</td><td>" + intree_file
1622 + "</td></tr>" + nl );
1623 System.out.println( " Intree for gain/loss pars.: " + intree_file );
1626 if ( radomize_fitch_parsimony ) {
1627 html_desc.append( "<tr><td> Random number seed for Fitch parsimony analysis:</td><td>"
1628 + random_number_seed_for_fitch_parsimony + "</td></tr>" + nl );
1629 System.out.println( " Random number seed : " + random_number_seed_for_fitch_parsimony );
1631 if ( ( domain_id_to_secondary_features_maps != null ) && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
1632 for( int i = 0; i < secondary_features_map_files.length; i++ ) {
1633 html_desc.append( "<tr><td>Secondary features map file:</td><td>"
1634 + secondary_features_map_files[ i ] + "</td></tr>" + nl );
1635 System.out.println( "Secondary features map file : " + secondary_features_map_files[ i ]
1636 + " [mappings for " + domain_id_to_secondary_features_maps[ i ].size() + " domain ids]" );
1638 System.out.println();
1639 System.out.println( "Domain ids to secondary features map:" );
1640 for( final DomainId domain_id : domain_id_to_secondary_features_maps[ i ].keySet() ) {
1641 System.out.print( domain_id.getId() );
1642 System.out.print( " => " );
1643 for( final String sec : domain_id_to_secondary_features_maps[ i ].get( domain_id ) ) {
1644 System.out.print( sec );
1645 System.out.print( " " );
1647 System.out.println();
1652 } // if ( perform_pwc ) {
1653 System.out.println();
1654 html_desc.append( "<tr><td>Command line:</td><td>\n" + cla.getCommandLineArgsAsString() + "\n</td></tr>" + nl );
1655 System.out.println( "Command line : " + cla.getCommandLineArgsAsString() );
1656 BufferedWriter[] query_domains_writer_ary = null;
1657 List<DomainId>[] query_domain_ids_array = null;
1658 if ( query_domain_ids != null ) {
1659 final String[] query_domain_ids_str_array = query_domain_ids.split( "#" );
1660 query_domain_ids_array = new ArrayList[ query_domain_ids_str_array.length ];
1661 query_domains_writer_ary = new BufferedWriter[ query_domain_ids_str_array.length ];
1662 for( int i = 0; i < query_domain_ids_str_array.length; i++ ) {
1663 String query_domain_ids_str = query_domain_ids_str_array[ i ];
1664 final String[] query_domain_ids_str_ary = query_domain_ids_str.split( "~" );
1665 final List<DomainId> query = new ArrayList<DomainId>();
1666 for( final String element : query_domain_ids_str_ary ) {
1667 query.add( new DomainId( element ) );
1669 query_domain_ids_array[ i ] = query;
1670 query_domain_ids_str = query_domain_ids_str.replace( '~', '_' );
1671 String protein_names_writer_str = query_domain_ids_str + surfacing.SEQ_EXTRACT_SUFFIX;
1672 if ( out_dir != null ) {
1673 protein_names_writer_str = out_dir + ForesterUtil.FILE_SEPARATOR + protein_names_writer_str;
1676 query_domains_writer_ary[ i ] = new BufferedWriter( new FileWriter( protein_names_writer_str ) );
1678 catch ( final IOException e ) {
1679 ForesterUtil.fatalError( surfacing.PRG_NAME, "Could not open [" + protein_names_writer_str + "]: "
1680 + e.getLocalizedMessage() );
1684 SortedMap<Species, List<Protein>> protein_lists_per_species = null; //This will only be created if neede.
1685 boolean need_protein_lists_per_species = false;
1686 if ( ( plus_minus_analysis_high_copy_base_species.size() > 0 ) || output_protein_lists_for_all_domains ) {
1687 need_protein_lists_per_species = true;
1689 if ( need_protein_lists_per_species ) {
1690 protein_lists_per_species = new TreeMap<Species, List<Protein>>();
1692 final List<GenomeWideCombinableDomains> gwcd_list = new ArrayList<GenomeWideCombinableDomains>( number_of_genomes );
1693 final SortedSet<DomainId> all_domains_encountered = new TreeSet<DomainId>();
1694 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered = new TreeSet<BinaryDomainCombination>();
1695 List<BinaryDomainCombination> all_bin_domain_combinations_gained_fitch = null;
1696 List<BinaryDomainCombination> all_bin_domain_combinations_lost_fitch = null;
1697 if ( ( intrees != null ) && ( intrees.length == 1 ) ) {
1698 all_bin_domain_combinations_gained_fitch = new ArrayList<BinaryDomainCombination>();
1699 all_bin_domain_combinations_lost_fitch = new ArrayList<BinaryDomainCombination>();
1701 final DomainLengthsTable domain_lengths_table = new DomainLengthsTable();
1702 final File per_genome_domain_promiscuity_statistics_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR
1703 + output_file + D_PROMISCUITY_FILE_SUFFIX );
1704 BufferedWriter per_genome_domain_promiscuity_statistics_writer = null;
1706 per_genome_domain_promiscuity_statistics_writer = new BufferedWriter( new FileWriter( per_genome_domain_promiscuity_statistics_file ) );
1707 per_genome_domain_promiscuity_statistics_writer.write( "Species:\t" );
1708 per_genome_domain_promiscuity_statistics_writer.write( "Mean:\t" );
1709 per_genome_domain_promiscuity_statistics_writer.write( "SD:\t" );
1710 per_genome_domain_promiscuity_statistics_writer.write( "Median:\t" );
1711 per_genome_domain_promiscuity_statistics_writer.write( "Min:\t" );
1712 per_genome_domain_promiscuity_statistics_writer.write( "Max:\t" );
1713 per_genome_domain_promiscuity_statistics_writer.write( "N:\t" );
1714 per_genome_domain_promiscuity_statistics_writer.write( "Max Promiscuous Domains:"
1715 + ForesterUtil.LINE_SEPARATOR );
1717 catch ( final IOException e2 ) {
1718 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1720 final File log_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + LOG_FILE_SUFFIX );
1721 BufferedWriter log_writer = null;
1723 log_writer = new BufferedWriter( new FileWriter( log_file ) );
1725 catch ( final IOException e2 ) {
1726 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1728 BufferedWriter dc_data_writer = null;
1730 dc_data_writer = new BufferedWriter( new FileWriter( dc_data_file ) );
1731 dc_data_writer.write( DATA_FILE_DESC );
1732 dc_data_writer.write( ForesterUtil.LINE_SEPARATOR );
1734 catch ( final IOException e2 ) {
1735 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1737 final DescriptiveStatistics protein_coverage_stats = new BasicDescriptiveStatistics();
1738 final DescriptiveStatistics all_genomes_domains_per_potein_stats = new BasicDescriptiveStatistics();
1739 final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo = new TreeMap<Integer, Integer>();
1740 final SortedSet<String> domains_which_are_always_single = new TreeSet<String>();
1741 final SortedSet<String> domains_which_are_sometimes_single_sometimes_not = new TreeSet<String>();
1742 final SortedSet<String> domains_which_never_single = new TreeSet<String>();
1743 BufferedWriter domains_per_potein_stats_writer = null;
1745 domains_per_potein_stats_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
1746 + output_file + "__domains_per_potein_stats.txt" ) );
1747 domains_per_potein_stats_writer.write( "Genome" );
1748 domains_per_potein_stats_writer.write( "\t" );
1749 domains_per_potein_stats_writer.write( "Mean" );
1750 domains_per_potein_stats_writer.write( "\t" );
1751 domains_per_potein_stats_writer.write( "SD" );
1752 domains_per_potein_stats_writer.write( "\t" );
1753 domains_per_potein_stats_writer.write( "Median" );
1754 domains_per_potein_stats_writer.write( "\t" );
1755 domains_per_potein_stats_writer.write( "N" );
1756 domains_per_potein_stats_writer.write( "\t" );
1757 domains_per_potein_stats_writer.write( "Min" );
1758 domains_per_potein_stats_writer.write( "\t" );
1759 domains_per_potein_stats_writer.write( "Max" );
1760 domains_per_potein_stats_writer.write( "\n" );
1762 catch ( final IOException e3 ) {
1763 e3.printStackTrace();
1765 Map<String, DescriptiveStatistics> protein_length_stats_by_dc = null;
1766 Map<String, DescriptiveStatistics> domain_number_stats_by_dc = null;
1767 final Map<String, DescriptiveStatistics> domain_length_stats_by_domain = new HashMap<String, DescriptiveStatistics>();
1768 if ( PERFORM_DC_REGAIN_PROTEINS_STATS ) {
1769 protein_length_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1770 domain_number_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1773 for( int i = 0; i < number_of_genomes; ++i ) {
1774 System.out.println();
1775 System.out.println( ( i + 1 ) + "/" + number_of_genomes );
1776 log( ( i + 1 ) + "/" + number_of_genomes, log_writer );
1777 System.out.println( "Processing : " + input_file_properties[ i ][ 0 ] );
1778 log( "Genome : " + input_file_properties[ i ][ 0 ], log_writer );
1779 HmmscanPerDomainTableParser parser = null;
1780 INDIVIDUAL_SCORE_CUTOFF ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF.NONE;
1781 if ( individual_score_cutoffs != null ) {
1782 ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF_DEFAULT;
1784 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1785 || ( negative_domains_filter_file != null ) ) {
1786 HmmscanPerDomainTableParser.FilterType filter_type = HmmscanPerDomainTableParser.FilterType.NONE;
1787 if ( positive_filter_file != null ) {
1788 filter_type = HmmscanPerDomainTableParser.FilterType.POSITIVE_PROTEIN;
1790 else if ( negative_filter_file != null ) {
1791 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_PROTEIN;
1793 else if ( negative_domains_filter_file != null ) {
1794 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_DOMAIN;
1796 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1797 input_file_properties[ i ][ 1 ],
1804 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1805 input_file_properties[ i ][ 1 ],
1809 if ( e_value_max >= 0.0 ) {
1810 parser.setEValueMaximum( e_value_max );
1812 parser.setIgnoreDufs( ignore_dufs );
1813 parser.setIgnoreVirusLikeIds( ignore_virus_like_ids );
1814 parser.setIgnoreEngulfedDomains( no_engulfing_overlaps );
1815 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1816 parser.setMaxAllowedOverlap( max_allowed_overlap );
1818 parser.setReturnType( HmmscanPerDomainTableParser.ReturnType.UNORDERED_PROTEIN_DOMAIN_COLLECTION_PER_PROTEIN );
1819 if ( individual_score_cutoffs != null ) {
1820 parser.setIndividualScoreCutoffs( individual_score_cutoffs );
1822 List<Protein> protein_list = null;
1824 protein_list = parser.parse();
1826 catch ( final IOException e ) {
1827 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1829 catch ( final Exception e ) {
1830 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, e.getMessage(), e );
1833 System.out.println( "Domains ignored due to negative domain filter: " );
1834 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToNegativeDomainFilterCountsMap() );
1835 System.out.println( "Domains ignored due to virus like id: " );
1836 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToVirusLikeIdCountsMap() );
1838 final double coverage = ( double ) protein_list.size() / parser.getProteinsEncountered();
1839 protein_coverage_stats.addValue( coverage );
1840 System.out.println( "Number of proteins encountered : " + parser.getProteinsEncountered() );
1841 log( "Number of proteins encountered : " + parser.getProteinsEncountered(), log_writer );
1842 System.out.println( "Number of proteins stored : " + protein_list.size() );
1843 log( "Number of proteins stored : " + protein_list.size(), log_writer );
1844 System.out.println( "Coverage : "
1845 + ForesterUtil.roundToInt( 100.0 * coverage ) + "%" );
1846 log( "Coverage : " + ForesterUtil.roundToInt( 100.0 * coverage )
1847 + "%", log_writer );
1848 System.out.println( "Domains encountered : " + parser.getDomainsEncountered() );
1849 log( "Domains encountered : " + parser.getDomainsEncountered(), log_writer );
1850 System.out.println( "Domains stored : " + parser.getDomainsStored() );
1851 log( "Domains stored : " + parser.getDomainsStored(), log_writer );
1852 System.out.println( "Distinct domains stored : "
1853 + parser.getDomainsStoredSet().size() );
1854 log( "Distinct domains stored : " + parser.getDomainsStoredSet().size(), log_writer );
1855 System.out.println( "Domains ignored due to individual score cutoffs: "
1856 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() );
1857 log( "Domains ignored due to individual score cutoffs: "
1858 + parser.getDomainsIgnoredDueToIndividualScoreCutoff(),
1860 System.out.println( "Domains ignored due to E-value : "
1861 + parser.getDomainsIgnoredDueToEval() );
1862 log( "Domains ignored due to E-value : " + parser.getDomainsIgnoredDueToEval(), log_writer );
1863 System.out.println( "Domains ignored due to DUF designation : "
1864 + parser.getDomainsIgnoredDueToDuf() );
1865 log( "Domains ignored due to DUF designation : " + parser.getDomainsIgnoredDueToDuf(), log_writer );
1866 if ( ignore_virus_like_ids ) {
1867 System.out.println( "Domains ignored due virus like ids : "
1868 + parser.getDomainsIgnoredDueToVirusLikeIds() );
1869 log( "Domains ignored due virus like ids : " + parser.getDomainsIgnoredDueToVirusLikeIds(),
1872 System.out.println( "Domains ignored due negative domain filter : "
1873 + parser.getDomainsIgnoredDueToNegativeDomainFilter() );
1874 log( "Domains ignored due negative domain filter : "
1875 + parser.getDomainsIgnoredDueToNegativeDomainFilter(),
1877 System.out.println( "Domains ignored due to overlap : "
1878 + parser.getDomainsIgnoredDueToOverlap() );
1879 log( "Domains ignored due to overlap : " + parser.getDomainsIgnoredDueToOverlap(),
1881 if ( negative_filter_file != null ) {
1882 System.out.println( "Proteins ignored due to negative filter : "
1883 + parser.getProteinsIgnoredDueToFilter() );
1884 log( "Proteins ignored due to negative filter : " + parser.getProteinsIgnoredDueToFilter(),
1887 if ( positive_filter_file != null ) {
1888 System.out.println( "Proteins ignored due to positive filter : "
1889 + parser.getProteinsIgnoredDueToFilter() );
1890 log( "Proteins ignored due to positive filter : " + parser.getProteinsIgnoredDueToFilter(),
1893 System.out.println( "Time for processing : " + parser.getTime() + "ms" );
1894 log( "", log_writer );
1895 html_desc.append( "<tr><td>" + input_file_properties[ i ][ 0 ] + " [species: "
1896 + input_file_properties[ i ][ 1 ] + "]" + ":</td><td>domains analyzed: "
1897 + parser.getDomainsStored() + "; domains ignored: [ind score cutoffs: "
1898 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() + "] [E-value cutoff: "
1899 + parser.getDomainsIgnoredDueToEval() + "] [DUF: " + parser.getDomainsIgnoredDueToDuf()
1900 + "] [virus like ids: " + parser.getDomainsIgnoredDueToVirusLikeIds()
1901 + "] [negative domain filter: " + parser.getDomainsIgnoredDueToNegativeDomainFilter()
1902 + "] [overlap: " + parser.getDomainsIgnoredDueToOverlap() + "]" );
1903 if ( negative_filter_file != null ) {
1904 html_desc.append( "; proteins ignored due to negative filter: "
1905 + parser.getProteinsIgnoredDueToFilter() );
1907 if ( positive_filter_file != null ) {
1908 html_desc.append( "; proteins ignored due to positive filter: "
1909 + parser.getProteinsIgnoredDueToFilter() );
1911 html_desc.append( "</td></tr>" + nl );
1912 // domain_partner_counts_array[ i ] =
1913 // Methods.getDomainPartnerCounts( protein_domain_collections_array[
1915 // false, input_file_properties[ i ][ 1 ] );
1918 for( final Protein protein : protein_list ) {
1919 dc_data_writer.write( SurfacingUtil.proteinToDomainCombinations( protein, count + "", "\t" )
1922 for( final Domain d : protein.getProteinDomains() ) {
1923 final String d_str = d.getDomainId().toString();
1924 if ( !domain_length_stats_by_domain.containsKey( d_str ) ) {
1925 domain_length_stats_by_domain.put( d_str, new BasicDescriptiveStatistics() );
1927 domain_length_stats_by_domain.get( d_str ).addValue( d.getLength() );
1931 catch ( final IOException e ) {
1932 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1934 SurfacingUtil.domainsPerProteinsStatistics( input_file_properties[ i ][ 1 ],
1936 all_genomes_domains_per_potein_stats,
1937 all_genomes_domains_per_potein_histo,
1938 domains_which_are_always_single,
1939 domains_which_are_sometimes_single_sometimes_not,
1940 domains_which_never_single,
1941 domains_per_potein_stats_writer );
1942 gwcd_list.add( BasicGenomeWideCombinableDomains
1943 .createInstance( protein_list,
1944 ignore_combination_with_same,
1945 new BasicSpecies( input_file_properties[ i ][ 1 ] ),
1946 domain_id_to_go_ids_map,
1948 protein_length_stats_by_dc,
1949 domain_number_stats_by_dc ) );
1950 domain_lengths_table.addLengths( protein_list );
1951 if ( gwcd_list.get( i ).getSize() > 0 ) {
1952 SurfacingUtil.writeDomainCombinationsCountsFile( input_file_properties,
1954 per_genome_domain_promiscuity_statistics_writer,
1958 if ( output_binary_domain_combinationsfor_graph_analysis ) {
1959 SurfacingUtil.writeBinaryDomainCombinationsFileForGraphAnalysis( input_file_properties,
1965 SurfacingUtil.addAllDomainIdsToSet( gwcd_list.get( i ), all_domains_encountered );
1966 SurfacingUtil.addAllBinaryDomainCombinationToSet( gwcd_list.get( i ),
1967 all_bin_domain_combinations_encountered );
1969 if ( query_domains_writer_ary != null ) {
1970 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1972 SurfacingUtil.extractProteinNames( protein_list,
1973 query_domain_ids_array[ j ],
1974 query_domains_writer_ary[ j ],
1976 LIMIT_SPEC_FOR_PROT_EX );
1977 query_domains_writer_ary[ j ].flush();
1979 catch ( final IOException e ) {
1980 e.printStackTrace();
1984 if ( need_protein_lists_per_species ) {
1985 protein_lists_per_species.put( new BasicSpecies( input_file_properties[ i ][ 1 ] ), protein_list );
1990 catch ( final IOException e2 ) {
1991 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1994 } // for( int i = 0; i < number_of_genomes; ++i ) {
1995 ForesterUtil.programMessage( PRG_NAME, "Wrote domain promiscuities to: "
1996 + per_genome_domain_promiscuity_statistics_file );
1999 domains_per_potein_stats_writer.write( "ALL" );
2000 domains_per_potein_stats_writer.write( "\t" );
2001 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.arithmeticMean() + "" );
2002 domains_per_potein_stats_writer.write( "\t" );
2003 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.sampleStandardDeviation() + "" );
2004 domains_per_potein_stats_writer.write( "\t" );
2005 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.median() + "" );
2006 domains_per_potein_stats_writer.write( "\t" );
2007 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getN() + "" );
2008 domains_per_potein_stats_writer.write( "\t" );
2009 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMin() + "" );
2010 domains_per_potein_stats_writer.write( "\t" );
2011 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMax() + "" );
2012 domains_per_potein_stats_writer.write( "\n" );
2013 domains_per_potein_stats_writer.close();
2014 printOutPercentageOfMultidomainProteins( all_genomes_domains_per_potein_histo, log_writer );
2015 ForesterUtil.map2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2016 + "__all_genomes_domains_per_potein_histo.txt" ), all_genomes_domains_per_potein_histo, "\t", "\n" );
2017 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2018 + "__domains_always_single_.txt" ), domains_which_are_always_single, "\n" );
2019 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2020 + "__domains_single_or_combined.txt" ), domains_which_are_sometimes_single_sometimes_not, "\n" );
2021 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2022 + "__domains_always_combined.txt" ), domains_which_never_single, "\n" );
2023 ForesterUtil.programMessage( PRG_NAME,
2024 "Average of proteins with a least one domain assigned: "
2025 + ( 100 * protein_coverage_stats.arithmeticMean() ) + "% (+/-"
2026 + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)" );
2027 ForesterUtil.programMessage( PRG_NAME, "Range of proteins with a least one domain assigned: "
2028 + ( 100 * protein_coverage_stats.getMin() ) + "%-" + ( 100 * protein_coverage_stats.getMax() )
2030 log( "Average of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.arithmeticMean() )
2031 + "% (+/-" + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)", log_writer );
2032 log( "Range of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.getMin() ) + "%-"
2033 + ( 100 * protein_coverage_stats.getMax() ) + "%", log_writer );
2035 catch ( final IOException e2 ) {
2036 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
2038 if ( query_domains_writer_ary != null ) {
2039 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
2041 query_domains_writer_ary[ j ].close();
2043 catch ( final IOException e ) {
2044 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
2049 per_genome_domain_promiscuity_statistics_writer.close();
2050 dc_data_writer.close();
2053 catch ( final IOException e2 ) {
2054 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
2056 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
2058 SurfacingUtil.executeDomainLengthAnalysis( input_file_properties,
2060 domain_lengths_table,
2061 domain_lengths_analysis_outfile );
2063 catch ( final IOException e1 ) {
2064 ForesterUtil.fatalError( surfacing.PRG_NAME, e1.toString() );
2066 System.out.println();
2067 ForesterUtil.programMessage( PRG_NAME, "Wrote domain length data to: " + domain_lengths_analysis_outfile );
2068 System.out.println();
2070 final long analysis_start_time = new Date().getTime();
2071 PairwiseDomainSimilarityCalculator pw_calc = null;
2072 // double[] values_for_all_scores_histogram = null;
2073 final DomainSimilarityCalculator calc = new BasicDomainSimilarityCalculator( domain_similarity_sort_field,
2074 sort_by_species_count_first,
2075 number_of_genomes == 2 );
2076 switch ( scoring ) {
2078 pw_calc = new CombinationsBasedPairwiseDomainSimilarityCalculator();
2081 pw_calc = new DomainCountsBasedPairwiseSimilarityCalculator();
2084 pw_calc = new ProteinCountsBasedPairwiseDomainSimilarityCalculator();
2087 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
2089 DomainSimilarityCalculator.GoAnnotationOutput go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.NONE;
2090 if ( domain_id_to_go_ids_map != null ) {
2091 go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.ALL;
2093 final SortedSet<DomainSimilarity> similarities = calc
2094 .calculateSimilarities( pw_calc,
2096 ignore_domains_without_combs_in_all_spec,
2097 ignore_species_specific_domains );
2098 SurfacingUtil.decoratePrintableDomainSimilarities( similarities,
2100 go_annotation_output,
2102 go_namespace_limit );
2103 DescriptiveStatistics pw_stats = null;
2105 String my_outfile = output_file.toString();
2106 Map<Character, Writer> split_writers = null;
2107 Writer writer = null;
2108 if ( similarities.size() > MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING ) {
2109 if ( my_outfile.endsWith( ".html" ) ) {
2110 my_outfile = my_outfile.substring( 0, my_outfile.length() - 5 );
2112 split_writers = new HashMap<Character, Writer>();
2113 createSplitWriters( out_dir, my_outfile, split_writers );
2115 else if ( !my_outfile.endsWith( ".html" ) ) {
2116 my_outfile += ".html";
2117 writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) );
2119 List<Species> species_order = null;
2120 if ( species_matrix ) {
2121 species_order = new ArrayList<Species>();
2122 for( int i = 0; i < number_of_genomes; i++ ) {
2123 species_order.add( new BasicSpecies( input_file_properties[ i ][ 1 ] ) );
2126 html_desc.append( "<tr><td>Sum of all distinct binary combinations:</td><td>"
2127 + all_bin_domain_combinations_encountered.size() + "</td></tr>" + nl );
2128 html_desc.append( "<tr><td>Sum of all distinct domains:</td><td>" + all_domains_encountered.size()
2129 + "</td></tr>" + nl );
2130 html_desc.append( "<tr><td>Analysis date/time:</td><td>"
2131 + new java.text.SimpleDateFormat( "yyyy.MM.dd HH:mm:ss" ).format( new java.util.Date() )
2132 + "</td></tr>" + nl );
2133 html_desc.append( "</table>" + nl );
2134 pw_stats = SurfacingUtil
2135 .writeDomainSimilaritiesToFile( html_desc,
2136 new StringBuilder( number_of_genomes + " genomes" ),
2140 number_of_genomes == 2,
2142 domain_similarity_print_option,
2143 domain_similarity_sort_field,
2146 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote main output (includes domain similarities) to: \""
2147 + ( out_dir == null ? my_outfile : out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) + "\"" );
2149 catch ( final IOException e ) {
2150 ForesterUtil.fatalError( surfacing.PRG_NAME, "Failed to write similarites to: \"" + output_file + "\" ["
2151 + e.getMessage() + "]" );
2153 System.out.println();
2154 // values_for_all_scores_histogram = pw_stats.getDataAsDoubleArray();
2155 final Species[] species = new Species[ number_of_genomes ];
2156 for( int i = 0; i < number_of_genomes; ++i ) {
2157 species[ i ] = new BasicSpecies( input_file_properties[ i ][ 1 ] );
2159 List<Phylogeny> inferred_trees = null;
2160 if ( ( number_of_genomes > 2 ) && perform_pwc ) {
2161 final PairwiseGenomeComparator pwgc = new PairwiseGenomeComparator();
2162 pwgc.performPairwiseComparisons( html_desc,
2163 sort_by_species_count_first,
2165 ignore_domains_without_combs_in_all_spec,
2166 ignore_species_specific_domains,
2167 domain_similarity_sort_field_for_automated_pwc,
2168 domain_similarity_print_option,
2170 domain_id_to_go_ids_map,
2177 automated_pairwise_comparison_suffix,
2179 surfacing.PAIRWISE_DOMAIN_COMPARISONS_PREFIX,
2183 String matrix_output_file = new String( output_file.toString() );
2184 if ( matrix_output_file.indexOf( '.' ) > 1 ) {
2185 matrix_output_file = matrix_output_file.substring( 0, matrix_output_file.indexOf( '.' ) );
2187 if ( out_dir != null ) {
2188 matrix_output_file = out_dir + ForesterUtil.FILE_SEPARATOR + matrix_output_file;
2189 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2191 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2192 + surfacing.MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans() );
2194 .writeMatrixToFile( new File( matrix_output_file
2195 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2196 pwgc.getSharedBinaryCombinationsBasedDistances() );
2197 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2198 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2199 pwgc.getSharedDomainsBasedDistances() );
2200 final Phylogeny nj_gd = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2201 + surfacing.NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans()
2203 final Phylogeny nj_bc = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2204 + surfacing.NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2205 .getSharedBinaryCombinationsBasedDistances().get( 0 ) );
2206 final Phylogeny nj_d = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2207 + surfacing.NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2208 .getSharedDomainsBasedDistances().get( 0 ) );
2209 inferred_trees = new ArrayList<Phylogeny>();
2210 inferred_trees.add( nj_gd );
2211 inferred_trees.add( nj_bc );
2212 inferred_trees.add( nj_d );
2213 if ( jacknifed_distances ) {
2214 pwgc.performPairwiseComparisonsJacknifed( species,
2218 jacknife_resamplings,
2222 .writeMatrixToFile( new File( matrix_output_file
2224 + ForesterUtil.round( jacknife_ratio, 2 )
2226 + jacknife_resamplings
2227 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2228 pwgc.getSharedBinaryCombinationsBasedDistances() );
2230 .writeMatrixToFile( new File( matrix_output_file + "_" + ForesterUtil.round( jacknife_ratio, 2 )
2231 + "_" + jacknife_resamplings
2232 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2233 pwgc.getSharedDomainsBasedDistances() );
2234 // if ( infer_species_trees ) {
2235 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2236 // + INFERRED_SBC_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc
2237 // .getSharedBinaryCombinationsBasedDistances() );
2238 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2239 // + INFERRED_SD_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc.getSharedDomainsBasedDistances() );
2242 } // if ( ( output_file != null ) && ( number_of_genomes > 2 ) && !isEmpty( automated_pairwise_comparison_suffix ) )
2243 if ( ( out_dir != null ) && ( !perform_pwc ) ) {
2244 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2246 writePresentToNexus( output_file, positive_filter_file, filter, gwcd_list );
2247 if ( ( ( intrees != null ) && ( intrees.length > 0 ) ) && ( number_of_genomes > 2 ) ) {
2248 final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
2250 max_allowed_overlap,
2251 no_engulfing_overlaps,
2255 if ( radomize_fitch_parsimony ) {
2256 s += random_number_seed_for_fitch_parsimony + "_";
2259 for( final Phylogeny intree : intrees ) {
2260 final String outfile_name = ForesterUtil.removeSuffix( output_file.toString() ) + s
2261 + ForesterUtil.removeSuffix( intree_files[ i ].toString() );
2262 final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator.createInstance( intree,
2264 SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
2265 radomize_fitch_parsimony,
2269 domain_id_to_go_ids_map,
2272 parameters_sb.toString(),
2273 domain_id_to_secondary_features_maps,
2274 positive_filter_file == null ? null : filter,
2275 output_binary_domain_combinationsfor_graph_analysis,
2276 all_bin_domain_combinations_gained_fitch,
2277 all_bin_domain_combinations_lost_fitch,
2279 protein_length_stats_by_dc,
2280 domain_number_stats_by_dc,
2281 domain_length_stats_by_domain );
2282 // Listing of all domain combinations gained is only done if only one input tree is used.
2283 if ( ( domain_id_to_secondary_features_maps != null )
2284 && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
2286 for( final Map<DomainId, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
2287 final Map<Species, MappingResults> mapping_results_map = new TreeMap<Species, MappingResults>();
2288 final DomainParsimonyCalculator secondary_features_parsimony = DomainParsimonyCalculator
2289 .createInstance( intree, gwcd_list, domain_id_to_secondary_features_map );
2291 .executeParsimonyAnalysisForSecondaryFeatures( outfile_name
2293 + secondary_features_map_files[ j++ ],
2294 secondary_features_parsimony,
2296 parameters_sb.toString(),
2297 mapping_results_map );
2299 System.out.println();
2300 System.out.println( "Mapping to secondary features:" );
2301 for( final Species spec : mapping_results_map.keySet() ) {
2302 final MappingResults mapping_results = mapping_results_map.get( spec );
2303 final int total_domains = mapping_results.getSumOfFailures()
2304 + mapping_results.getSumOfSuccesses();
2305 System.out.print( spec + ":" );
2306 System.out.print( " mapped domains = " + mapping_results.getSumOfSuccesses() );
2307 System.out.print( ", not mapped domains = " + mapping_results.getSumOfFailures() );
2308 if ( total_domains > 0 ) {
2309 System.out.println( ", mapped ratio = "
2310 + ( ( 100 * mapping_results.getSumOfSuccesses() ) / total_domains ) + "%" );
2313 System.out.println( ", mapped ratio = n/a (total domains = 0 )" );
2320 } // for( final Phylogeny intree : intrees ) {
2322 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
2323 executePlusMinusAnalysis( output_file,
2324 plus_minus_analysis_high_copy_base_species,
2325 plus_minus_analysis_high_copy_target_species,
2326 plus_minus_analysis_high_low_copy_species,
2328 protein_lists_per_species,
2329 domain_id_to_go_ids_map,
2331 plus_minus_analysis_numbers );
2333 if ( output_protein_lists_for_all_domains ) {
2334 writeProteinListsForAllSpecies( out_dir,
2335 protein_lists_per_species,
2337 output_list_of_all_proteins_per_domain_e_value_max );
2339 if ( all_bin_domain_combinations_gained_fitch != null ) {
2341 executeFitchGainsAnalysis( new File( output_file
2342 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2343 all_bin_domain_combinations_gained_fitch,
2344 all_domains_encountered.size(),
2345 all_bin_domain_combinations_encountered,
2348 catch ( final IOException e ) {
2349 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2352 if ( all_bin_domain_combinations_lost_fitch != null ) {
2354 executeFitchGainsAnalysis( new File( output_file
2355 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2356 all_bin_domain_combinations_lost_fitch,
2357 all_domains_encountered.size(),
2358 all_bin_domain_combinations_encountered,
2361 catch ( final IOException e ) {
2362 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2365 final Runtime rt = java.lang.Runtime.getRuntime();
2366 final long free_memory = rt.freeMemory() / 1000000;
2367 final long total_memory = rt.totalMemory() / 1000000;
2368 ForesterUtil.programMessage( PRG_NAME, "Time for analysis : " + ( new Date().getTime() - analysis_start_time )
2370 ForesterUtil.programMessage( PRG_NAME, "Total running time: " + ( new Date().getTime() - start_time ) + "ms " );
2371 ForesterUtil.programMessage( PRG_NAME, "Free memory : " + free_memory + "MB, total memory: "
2372 + total_memory + "MB" );
2373 ForesterUtil.programMessage( PRG_NAME, "If this application is useful to you, please cite:" );
2374 ForesterUtil.programMessage( PRG_NAME, surfacing.WWW );
2375 ForesterUtil.programMessage( PRG_NAME, "OK" );
2376 System.out.println();
2379 private static void createSplitWriters( final File out_dir,
2380 final String my_outfile,
2381 final Map<Character, Writer> split_writers ) throws IOException {
2382 split_writers.put( 'a', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2383 + "_domains_A.html" ) ) );
2384 split_writers.put( 'b', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2385 + "_domains_B.html" ) ) );
2386 split_writers.put( 'c', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2387 + "_domains_C.html" ) ) );
2388 split_writers.put( 'd', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2389 + "_domains_D.html" ) ) );
2390 split_writers.put( 'e', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2391 + "_domains_E.html" ) ) );
2392 split_writers.put( 'f', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2393 + "_domains_F.html" ) ) );
2394 split_writers.put( 'g', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2395 + "_domains_G.html" ) ) );
2396 split_writers.put( 'h', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2397 + "_domains_H.html" ) ) );
2398 split_writers.put( 'i', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2399 + "_domains_I.html" ) ) );
2400 split_writers.put( 'j', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2401 + "_domains_J.html" ) ) );
2402 split_writers.put( 'k', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2403 + "_domains_K.html" ) ) );
2404 split_writers.put( 'l', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2405 + "_domains_L.html" ) ) );
2406 split_writers.put( 'm', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2407 + "_domains_M.html" ) ) );
2408 split_writers.put( 'n', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2409 + "_domains_N.html" ) ) );
2410 split_writers.put( 'o', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2411 + "_domains_O.html" ) ) );
2412 split_writers.put( 'p', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2413 + "_domains_P.html" ) ) );
2414 split_writers.put( 'q', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2415 + "_domains_Q.html" ) ) );
2416 split_writers.put( 'r', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2417 + "_domains_R.html" ) ) );
2418 split_writers.put( 's', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2419 + "_domains_S.html" ) ) );
2420 split_writers.put( 't', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2421 + "_domains_T.html" ) ) );
2422 split_writers.put( 'u', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2423 + "_domains_U.html" ) ) );
2424 split_writers.put( 'v', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2425 + "_domains_V.html" ) ) );
2426 split_writers.put( 'w', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2427 + "_domains_W.html" ) ) );
2428 split_writers.put( 'x', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2429 + "_domains_X.html" ) ) );
2430 split_writers.put( 'y', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2431 + "_domains_Y.html" ) ) );
2432 split_writers.put( 'z', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2433 + "_domains_Z.html" ) ) );
2434 split_writers.put( '0', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2435 + "_domains_0.html" ) ) );
2438 private static void printOutPercentageOfMultidomainProteins( final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo,
2439 final Writer log_writer ) {
2441 for( final Entry<Integer, Integer> entry : all_genomes_domains_per_potein_histo.entrySet() ) {
2442 sum += entry.getValue();
2444 final double percentage = ( 100.0 * ( sum - all_genomes_domains_per_potein_histo.get( 1 ) ) ) / sum;
2445 ForesterUtil.programMessage( PRG_NAME, "Percentage of multidomain proteins: " + percentage + "%" );
2446 log( "Percentage of multidomain proteins: : " + percentage + "%", log_writer );
2449 private static void preparePhylogenyForParsimonyAnalyses( final Phylogeny intree,
2450 final String[][] input_file_properties ) {
2451 final String[] genomes = new String[ input_file_properties.length ];
2452 for( int i = 0; i < input_file_properties.length; ++i ) {
2453 if ( intree.getNodes( input_file_properties[ i ][ 1 ] ).size() > 1 ) {
2454 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
2455 + "] is not unique in input tree " + intree.getName() );
2457 genomes[ i ] = input_file_properties[ i ][ 1 ];
2460 final PhylogenyNodeIterator it = intree.iteratorPostorder();
2461 while ( it.hasNext() ) {
2462 final PhylogenyNode n = it.next();
2463 if ( ForesterUtil.isEmpty( n.getName() ) ) {
2464 if ( n.getNodeData().isHasTaxonomy()
2465 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getTaxonomyCode() ) ) {
2466 n.setName( n.getNodeData().getTaxonomy().getTaxonomyCode() );
2468 else if ( n.getNodeData().isHasTaxonomy()
2469 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
2470 n.setName( n.getNodeData().getTaxonomy().getScientificName() );
2472 else if ( n.getNodeData().isHasTaxonomy()
2473 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getCommonName() ) ) {
2474 n.setName( n.getNodeData().getTaxonomy().getCommonName() );
2478 .fatalError( surfacing.PRG_NAME,
2479 "node with no name, scientific name, common name, or taxonomy code present" );
2484 final List<String> igns = PhylogenyMethods.deleteExternalNodesPositiveSelection( genomes, intree );
2485 if ( igns.size() > 0 ) {
2486 System.out.println( "Not using the following " + igns.size() + " nodes:" );
2487 for( int i = 0; i < igns.size(); ++i ) {
2488 System.out.println( " " + i + ": " + igns.get( i ) );
2490 System.out.println( "--" );
2492 for( final String[] input_file_propertie : input_file_properties ) {
2494 intree.getNode( input_file_propertie[ 1 ] );
2496 catch ( final IllegalArgumentException e ) {
2497 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_propertie[ 1 ]
2498 + "] not present/not unique in input tree" );
2503 private static void printHelp() {
2504 System.out.println();
2505 System.out.println( "Usage:" );
2506 System.out.println();
2507 System.out.println( "% java -Xms256m -Xmx512m -cp forester.jar org.forester.applications." + surfacing.PRG_NAME
2508 + " [options] <phylogen(y|ies) infile> [external node name 1] [name 2] ... [name n]" );
2509 System.out.println();
2510 System.out.println( " Note: This software might need a significant amount of memory (heap space);" );
2512 .println( " hence use \"-Xms128m -Xmx512m\" (or more) to prevent a \"java.lang.OutOfMemoryError\"." );
2513 System.out.println();
2514 System.out.println( " Options: " );
2515 System.out.println( surfacing.DETAILEDNESS_OPTION + ": level of detail for similarities output file (default:"
2516 + DETAILEDNESS_DEFAULT + ")" );
2517 System.out.println( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION
2518 + ": to ignore combinations with self (default: not to ignore)" );
2520 .println( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION
2521 + ": to ignore domains without combinations in any species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2523 .println( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION
2524 + ": to ignore domains specific to one species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2525 System.out.println( surfacing.NOT_IGNORE_DUFS_OPTION
2526 + ": to _not_ ignore DUFs (domains with unknown function) (default: ignore DUFs)" );
2528 .println( surfacing.IGNORE_VIRAL_IDS
2529 + ": to ignore domains with ids containing 'vir', 'retro', 'transpos', 'phage', or starting with 'rv' or 'gag_'" );
2530 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_OPTION + ": sorting for similarities (default: "
2531 + DOMAIN_SORT_FILD_DEFAULT + ")" );
2532 System.out.println( surfacing.OUTPUT_FILE_OPTION + ": name for (main) output file (mandatory)" );
2533 System.out.println( surfacing.MAX_E_VALUE_OPTION + ": max (inclusive) E-value" );
2534 System.out.println( surfacing.MAX_ALLOWED_OVERLAP_OPTION + ": maximal allowed domain overlap" );
2535 System.out.println( surfacing.NO_ENGULFING_OVERLAP_OPTION + ": to ignore engulfed lower confidence domains" );
2536 System.out.println( surfacing.SPECIES_MATRIX_OPTION + ": species matrix" );
2537 System.out.println( surfacing.SCORING_OPTION + ": scoring (default:" + SCORING_DEFAULT + ")" );
2538 System.out.println( surfacing.DOMAIN_COUNT_SORT_OPTION + ": sorting for domain counts (default:"
2539 + DOMAINS_SORT_ORDER_DEFAULT + ")" );
2540 System.out.println( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION + ": domain similarity print option (default:"
2541 + DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT + ")" );
2542 System.out.println( surfacing.CUTOFF_SCORE_FILE_OPTION + ": cutoff score file" );
2543 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION
2544 + ": sort by species count first" );
2545 System.out.println( surfacing.OUTPUT_DIR_OPTION + ": output directory" );
2546 System.out.println( surfacing.PFAM_TO_GO_FILE_USE_OPTION + ": Pfam to GO mapping file" );
2547 System.out.println( surfacing.GO_OBO_FILE_USE_OPTION + ": GO terms file (OBO format)" );
2548 System.out.println( surfacing.GO_NAMESPACE_LIMIT_OPTION + ": limit GO term to one GO namespace" );
2549 System.out.println( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
2550 + "[=<suffix for pairwise comparison output files>]: to perform pairwise comparison based analyses" );
2551 System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION
2552 + ": species tree, to perform (Dollo, Fitch) parismony analyses" );
2554 .println( JACKNIFE_OPTION
2555 + ": perform jacknife resampling for domain and binary domain combination based distance matrices [default resamplings: "
2556 + JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT + "]" );
2557 System.out.println( JACKNIFE_RATIO_OPTION + ": ratio for jacknife resampling [default: "
2558 + JACKNIFE_RATIO_DEFAULT + "]" );
2559 System.out.println( JACKNIFE_RANDOM_SEED_OPTION
2560 + ": seed for random number generator for jacknife resampling [default: "
2561 + JACKNIFE_RANDOM_SEED_DEFAULT + "]" );
2562 // System.out.println( surfacing.INFER_SPECIES_TREES_OPTION
2563 // + ": to infer NJ species trees based on shared domains/binary domain combinations" );
2565 .println( surfacing.INPUT_SPECIES_TREE_OPTION
2566 + "=<treefiles in phyloXML format, separated by #>: to infer domain/binary domain combination gains/losses on given species trees" );
2567 System.out.println( surfacing.FILTER_POSITIVE_OPTION
2568 + "=<file>: to filter out proteins not containing at least one domain listed in <file>" );
2569 System.out.println( surfacing.FILTER_NEGATIVE_OPTION
2570 + "=<file>: to filter out proteins containing at least one domain listed in <file>" );
2571 System.out.println( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION
2572 + "=<file>: to filter out (ignore) domains listed in <file>" );
2573 System.out.println( surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>: to read input files from <file>" );
2575 .println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION
2576 + "=<seed>: seed for random number generator for Fitch Parsimony analysis (type: long, default: no randomization - given a choice, prefer absence" );
2577 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS
2578 + ": to consider directedness in binary combinations: e.g. A-B != B-A" );
2579 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY
2580 + ": to consider directedness and adjacency in binary combinations" );
2582 .println( surfacing.SEQ_EXTRACT_OPTION
2583 + "=<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')" );
2584 System.out.println( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE
2585 + "=<file>: to perfom parsimony analysis on secondary features" );
2586 System.out.println( surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>: to presence/absence genome analysis" );
2587 System.out.println( surfacing.DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS
2588 + ": to output binary domain combinations for (downstream) graph analysis" );
2589 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS + ": to output all proteins per domain" );
2590 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION
2591 + ": e value max per domain for output of all proteins per domain" );
2592 System.out.println();
2593 System.out.println( "Example 1: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2594 + " org.forester.application.surfacing p2g=pfam2go_2012_02_07.txt -dufs -cos=Pfam_260_NC1"
2595 + " -no_eo -mo=0 -input=genomes_limited.txt -out_dir=out -o=o "
2596 + " -species_tree=tol.xml -obo=gene_ontology_2012_02_07.obo -pos_filter=f.txt -all_prot" );
2597 System.out.println();
2598 System.out.println( "Example 2: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2599 + " org.forester.application.surfacing -detail=punctilious -o=TEST.html -pwc=TEST"
2600 + " -cos=Pfam_ls_22_TC2 -p2g=pfam2go -obo=gene_ontology_edit.obo "
2601 + "-dc_sort=dom -ignore_with_self -no_singles -e=0.001 -mo=1 -no_eo "
2602 + "-ds_output=detailed_html -scoring=domains -sort=alpha human mouse brafl strpu" );
2603 System.out.println();
2606 private static void processFilter( final File filter_file, final SortedSet<DomainId> filter ) {
2607 SortedSet<String> filter_str = null;
2609 filter_str = ForesterUtil.file2set( filter_file );
2611 catch ( final IOException e ) {
2612 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2614 if ( filter_str != null ) {
2615 for( final String string : filter_str ) {
2616 filter.add( new DomainId( string ) );
2620 System.out.println( "Filter:" );
2621 for( final DomainId domainId : filter ) {
2622 System.out.println( domainId.getId() );
2627 private static String[][] processInputFileNames( final String[] names ) {
2628 final String[][] input_file_properties = new String[ names.length ][];
2629 for( int i = 0; i < names.length; ++i ) {
2630 if ( names[ i ].indexOf( SEPARATOR_FOR_INPUT_VALUES ) < 0 ) {
2631 input_file_properties[ i ] = new String[ 2 ];
2632 input_file_properties[ i ][ 0 ] = names[ i ];
2633 input_file_properties[ i ][ 1 ] = names[ i ];
2636 input_file_properties[ i ] = names[ i ].split( surfacing.SEPARATOR_FOR_INPUT_VALUES + "" );
2637 if ( input_file_properties[ i ].length != 3 ) {
2639 .fatalError( surfacing.PRG_NAME,
2640 "properties for the input files (hmmpfam output) are expected "
2641 + "to be in the following format \"<hmmpfam output file>#<species>\" (or just one word, which is both the filename and the species id), instead received \""
2642 + names[ i ] + "\"" );
2645 final String error = ForesterUtil.isReadableFile( new File( input_file_properties[ i ][ 0 ] ) );
2646 if ( !ForesterUtil.isEmpty( error ) ) {
2647 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
2650 return input_file_properties;
2653 private static void processPlusMinusAnalysisOption( final CommandLineArguments cla,
2654 final List<String> high_copy_base,
2655 final List<String> high_copy_target,
2656 final List<String> low_copy,
2657 final List<Object> numbers ) {
2658 if ( cla.isOptionSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2659 if ( !cla.isOptionValueSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2660 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for 'plus-minus' file: -"
2661 + surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>" );
2663 final File plus_minus_file = new File( cla.getOptionValue( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) );
2664 final String msg = ForesterUtil.isReadableFile( plus_minus_file );
2665 if ( !ForesterUtil.isEmpty( msg ) ) {
2666 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + plus_minus_file + "\": " + msg );
2668 processPlusMinusFile( plus_minus_file, high_copy_base, high_copy_target, low_copy, numbers );
2672 // First numbers is minimal difference, second is factor.
2673 private static void processPlusMinusFile( final File plus_minus_file,
2674 final List<String> high_copy_base,
2675 final List<String> high_copy_target,
2676 final List<String> low_copy,
2677 final List<Object> numbers ) {
2678 Set<String> species_set = null;
2679 int min_diff = PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT;
2680 double factor = PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT;
2682 species_set = ForesterUtil.file2set( plus_minus_file );
2684 catch ( final IOException e ) {
2685 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2687 if ( species_set != null ) {
2688 for( final String species : species_set ) {
2689 final String species_trimmed = species.substring( 1 );
2690 if ( species.startsWith( "+" ) ) {
2691 if ( low_copy.contains( species_trimmed ) ) {
2692 ForesterUtil.fatalError( surfacing.PRG_NAME,
2693 "species/genome names can not appear with both '+' and '-' suffix, as appears the case for: \""
2694 + species_trimmed + "\"" );
2696 high_copy_base.add( species_trimmed );
2698 else if ( species.startsWith( "*" ) ) {
2699 if ( low_copy.contains( species_trimmed ) ) {
2700 ForesterUtil.fatalError( surfacing.PRG_NAME,
2701 "species/genome names can not appear with both '*' and '-' suffix, as appears the case for: \""
2702 + species_trimmed + "\"" );
2704 high_copy_target.add( species_trimmed );
2706 else if ( species.startsWith( "-" ) ) {
2707 if ( high_copy_base.contains( species_trimmed ) || high_copy_target.contains( species_trimmed ) ) {
2708 ForesterUtil.fatalError( surfacing.PRG_NAME,
2709 "species/genome names can not appear with both '+' or '*' and '-' suffix, as appears the case for: \""
2710 + species_trimmed + "\"" );
2712 low_copy.add( species_trimmed );
2714 else if ( species.startsWith( "$D" ) ) {
2716 min_diff = Integer.parseInt( species.substring( 3 ) );
2718 catch ( final NumberFormatException e ) {
2719 ForesterUtil.fatalError( surfacing.PRG_NAME,
2720 "could not parse integer value for minimal difference from: \""
2721 + species.substring( 3 ) + "\"" );
2724 else if ( species.startsWith( "$F" ) ) {
2726 factor = Double.parseDouble( species.substring( 3 ) );
2728 catch ( final NumberFormatException e ) {
2729 ForesterUtil.fatalError( surfacing.PRG_NAME, "could not parse double value for factor from: \""
2730 + species.substring( 3 ) + "\"" );
2733 else if ( species.startsWith( "#" ) ) {
2738 .fatalError( surfacing.PRG_NAME,
2739 "species/genome names in 'plus minus' file must begin with '*' (high copy target genome), '+' (high copy base genomes), '-' (low copy genomes), '$D=<integer>' minimal Difference (default is 1), '$F=<double>' factor (default is 1.0), double), or '#' (ignore) suffix, encountered: \""
2742 numbers.add( new Integer( min_diff + "" ) );
2743 numbers.add( new Double( factor + "" ) );
2747 ForesterUtil.fatalError( surfacing.PRG_NAME, "'plus minus' file [" + plus_minus_file + "] appears empty" );
2751 private static void writePresentToNexus( final File output_file,
2752 final File positive_filter_file,
2753 final SortedSet<DomainId> filter,
2754 final List<GenomeWideCombinableDomains> gwcd_list ) {
2757 .writeMatrixToFile( DomainParsimonyCalculator
2758 .createMatrixOfDomainPresenceOrAbsence( gwcd_list, positive_filter_file == null ? null
2759 : filter ), output_file + DOMAINS_PRESENT_NEXUS, Format.NEXUS_BINARY );
2760 SurfacingUtil.writeMatrixToFile( DomainParsimonyCalculator
2761 .createMatrixOfBinaryDomainCombinationPresenceOrAbsence( gwcd_list ), output_file
2762 + BDC_PRESENT_NEXUS, Format.NEXUS_BINARY );
2764 catch ( final Exception e ) {
2765 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2769 private static void writeProteinListsForAllSpecies( final File output_dir,
2770 final SortedMap<Species, List<Protein>> protein_lists_per_species,
2771 final List<GenomeWideCombinableDomains> gwcd_list,
2772 final double domain_e_cutoff ) {
2773 final SortedSet<DomainId> all_domains = new TreeSet<DomainId>();
2774 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
2775 all_domains.addAll( gwcd.getAllDomainIds() );
2777 for( final DomainId domain : all_domains ) {
2778 final File out = new File( output_dir + ForesterUtil.FILE_SEPARATOR + domain + SEQ_EXTRACT_SUFFIX );
2779 SurfacingUtil.checkForOutputFileWriteability( out );
2781 final Writer proteins_file_writer = new BufferedWriter( new FileWriter( out ) );
2782 SurfacingUtil.extractProteinNames( protein_lists_per_species,
2784 proteins_file_writer,
2786 LIMIT_SPEC_FOR_PROT_EX,
2788 proteins_file_writer.close();
2790 catch ( final IOException e ) {
2791 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2793 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote proteins list to \"" + out + "\"" );