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 FILTER_POSITIVE_OPTION = "pos_filter";
226 final static private String FILTER_NEGATIVE_OPTION = "neg_filter";
227 final static private String FILTER_NEGATIVE_DOMAINS_OPTION = "neg_dom_filter";
228 final static private String INPUT_GENOMES_FILE_OPTION = "genomes";
229 final static private String INPUT_SPECIES_TREE_OPTION = "species_tree";
230 final static private String SEQ_EXTRACT_OPTION = "prot_extract";
231 final static private String PRG_VERSION = "2.260";
232 final static private String PRG_DATE = "130721";
233 final static private String E_MAIL = "czmasek@burnham.org";
234 final static private String WWW = "www.phylosoft.org/forester/applications/surfacing";
235 final static private boolean IGNORE_DUFS_DEFAULT = true;
236 final static private boolean IGNORE_COMBINATION_WITH_SAME_DEFAULLT = false;
237 final static private double MAX_E_VALUE_DEFAULT = -1;
238 final static private int MAX_ALLOWED_OVERLAP_DEFAULT = -1;
239 private static final String RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION = "random_seed";
240 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS = "consider_bdc_direction";
241 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY = "consider_bdc_adj";
242 private static final String SEQ_EXTRACT_SUFFIX = ".prot";
243 private static final String PLUS_MINUS_ANALYSIS_OPTION = "plus_minus";
244 private static final String PLUS_MINUS_DOM_SUFFIX = "_plus_minus_dom.txt";
245 private static final String PLUS_MINUS_DOM_SUFFIX_HTML = "_plus_minus_dom.html";
246 private static final String PLUS_MINUS_DC_SUFFIX_HTML = "_plus_minus_dc.html";
247 private static final int PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT = 0;
248 private static final double PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT = 1.0;
249 private static final String PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_all.txt";
250 private static final String PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_passing.txt";
251 private static final String OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS = "all_prot";
252 final static private String OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION = "all_prot_e";
253 private static final boolean VERBOSE = false;
254 private static final String OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_gains_counts";
255 private static final String OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_losses_counts";
256 private static final String DOMAIN_LENGTHS_ANALYSIS_SUFFIX = "_domain_lengths_analysis";
257 private static final boolean PERFORM_DOMAIN_LENGTH_ANALYSIS = true;
258 public static final String ALL_PFAMS_ENCOUNTERED_SUFFIX = "_all_encountered_pfams";
259 public static final String ALL_PFAMS_ENCOUNTERED_WITH_GO_ANNOTATION_SUFFIX = "_all_encountered_pfams_with_go_annotation";
260 public static final String ENCOUNTERED_PFAMS_SUMMARY_SUFFIX = "_encountered_pfams_summary";
261 public static final String ALL_PFAMS_GAINED_AS_DOMAINS_SUFFIX = "_all_pfams_gained_as_domains";
262 public static final String ALL_PFAMS_LOST_AS_DOMAINS_SUFFIX = "_all_pfams_lost_as_domains";
263 public static final String ALL_PFAMS_GAINED_AS_DC_SUFFIX = "_all_pfams_gained_as_dc";
264 public static final String ALL_PFAMS_LOST_AS_DC_SUFFIX = "_all_pfams_lost_as_dc";
265 public static final String BASE_DIRECTORY_PER_NODE_DOMAIN_GAIN_LOSS_FILES = "PER_NODE_EVENTS";
266 public static final String BASE_DIRECTORY_PER_SUBTREE_DOMAIN_GAIN_LOSS_FILES = "PER_SUBTREE_EVENTS";
267 public static final String D_PROMISCUITY_FILE_SUFFIX = "_domain_promiscuities";
268 private static final String LOG_FILE_SUFFIX = "_log.txt";
269 private static final String DATA_FILE_SUFFIX = "_domain_combination_data.txt";
270 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";
271 private static final INDIVIDUAL_SCORE_CUTOFF INDIVIDUAL_SCORE_CUTOFF_DEFAULT = INDIVIDUAL_SCORE_CUTOFF.FULL_SEQUENCE; //TODO look at me! change?
272 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts.txt";
273 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists.txt";
274 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping.txt";
275 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";
276 public static final String LIMIT_SPEC_FOR_PROT_EX = null; // e.g. "HUMAN"; set to null for not using this feature (default).
277 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH_MAPPED = "_dc_MAPPED_secondary_features_fitch"
278 + ForesterConstants.PHYLO_XML_SUFFIX;
279 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts_MAPPED.txt";
280 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_MAPPED.txt";
281 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";
282 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";
283 private static final boolean PERFORM_DC_REGAIN_PROTEINS_STATS = true;
284 private static final boolean DA_ANALYSIS = false;
286 private static void checkWriteabilityForPairwiseComparisons( final PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option,
287 final String[][] input_file_properties,
288 final String automated_pairwise_comparison_suffix,
289 final File outdir ) {
290 for( int i = 0; i < input_file_properties.length; ++i ) {
291 for( int j = 0; j < i; ++j ) {
292 final String species_i = input_file_properties[ i ][ 1 ];
293 final String species_j = input_file_properties[ j ][ 1 ];
294 String pairwise_similarities_output_file_str = PAIRWISE_DOMAIN_COMPARISONS_PREFIX + species_i + "_"
295 + species_j + automated_pairwise_comparison_suffix;
296 switch ( domain_similarity_print_option ) {
298 if ( !pairwise_similarities_output_file_str.endsWith( ".html" ) ) {
299 pairwise_similarities_output_file_str += ".html";
303 final String error = ForesterUtil
304 .isWritableFile( new File( outdir == null ? pairwise_similarities_output_file_str : outdir
305 + ForesterUtil.FILE_SEPARATOR + pairwise_similarities_output_file_str ) );
306 if ( !ForesterUtil.isEmpty( error ) ) {
307 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
313 private static StringBuilder createParametersAsString( final boolean ignore_dufs,
314 final double e_value_max,
315 final int max_allowed_overlap,
316 final boolean no_engulfing_overlaps,
317 final File cutoff_scores_file,
318 final BinaryDomainCombination.DomainCombinationType dc_type ) {
319 final StringBuilder parameters_sb = new StringBuilder();
320 parameters_sb.append( "E-value: " + e_value_max );
321 if ( cutoff_scores_file != null ) {
322 parameters_sb.append( ", Cutoff-scores-file: " + cutoff_scores_file );
325 parameters_sb.append( ", Cutoff-scores-file: not-set" );
327 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
328 parameters_sb.append( ", Max-overlap: " + max_allowed_overlap );
331 parameters_sb.append( ", Max-overlap: not-set" );
333 if ( no_engulfing_overlaps ) {
334 parameters_sb.append( ", Engulfing-overlaps: not-allowed" );
337 parameters_sb.append( ", Engulfing-overlaps: allowed" );
340 parameters_sb.append( ", Ignore-dufs: true" );
343 parameters_sb.append( ", Ignore-dufs: false" );
345 parameters_sb.append( ", DC type (if applicable): " + dc_type );
346 return parameters_sb;
350 * Warning: This side-effects 'all_bin_domain_combinations_encountered'!
354 * @param all_bin_domain_combinations_changed
355 * @param sum_of_all_domains_encountered
356 * @param all_bin_domain_combinations_encountered
357 * @param is_gains_analysis
358 * @param protein_length_stats_by_dc
359 * @throws IOException
361 private static void executeFitchGainsAnalysis( final File output_file,
362 final List<BinaryDomainCombination> all_bin_domain_combinations_changed,
363 final int sum_of_all_domains_encountered,
364 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered,
365 final boolean is_gains_analysis ) throws IOException {
366 SurfacingUtil.checkForOutputFileWriteability( output_file );
367 final Writer out = ForesterUtil.createBufferedWriter( output_file );
368 final SortedMap<Object, Integer> bdc_to_counts = ForesterUtil
369 .listToSortedCountsMap( all_bin_domain_combinations_changed );
370 final SortedSet<DomainId> all_domains_in_combination_changed_more_than_once = new TreeSet<DomainId>();
371 final SortedSet<DomainId> all_domains_in_combination_changed_only_once = new TreeSet<DomainId>();
374 for( final Object bdc_object : bdc_to_counts.keySet() ) {
375 final BinaryDomainCombination bdc = ( BinaryDomainCombination ) bdc_object;
376 final int count = bdc_to_counts.get( bdc_object );
378 ForesterUtil.unexpectedFatalError( PRG_NAME, "count < 1 " );
380 out.write( bdc + "\t" + count + ForesterUtil.LINE_SEPARATOR );
382 all_domains_in_combination_changed_more_than_once.add( bdc.getId0() );
383 all_domains_in_combination_changed_more_than_once.add( bdc.getId1() );
386 else if ( count == 1 ) {
387 all_domains_in_combination_changed_only_once.add( bdc.getId0() );
388 all_domains_in_combination_changed_only_once.add( bdc.getId1() );
392 final int all = all_bin_domain_combinations_encountered.size();
394 if ( !is_gains_analysis ) {
395 all_bin_domain_combinations_encountered.removeAll( all_bin_domain_combinations_changed );
396 never_lost = all_bin_domain_combinations_encountered.size();
397 for( final BinaryDomainCombination bdc : all_bin_domain_combinations_encountered ) {
398 out.write( bdc + "\t" + "0" + ForesterUtil.LINE_SEPARATOR );
401 if ( is_gains_analysis ) {
402 out.write( "Sum of all distinct domain combinations appearing once : " + one
403 + ForesterUtil.LINE_SEPARATOR );
404 out.write( "Sum of all distinct domain combinations appearing more than once : " + above_one
405 + ForesterUtil.LINE_SEPARATOR );
406 out.write( "Sum of all distinct domains in combinations apppearing only once : "
407 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
408 out.write( "Sum of all distinct domains in combinations apppearing more than once: "
409 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
412 out.write( "Sum of all distinct domain combinations never lost : " + never_lost
413 + ForesterUtil.LINE_SEPARATOR );
414 out.write( "Sum of all distinct domain combinations lost once : " + one
415 + ForesterUtil.LINE_SEPARATOR );
416 out.write( "Sum of all distinct domain combinations lost more than once : " + above_one
417 + ForesterUtil.LINE_SEPARATOR );
418 out.write( "Sum of all distinct domains in combinations lost only once : "
419 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
420 out.write( "Sum of all distinct domains in combinations lost more than once: "
421 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
423 out.write( "All binary combinations : " + all
424 + ForesterUtil.LINE_SEPARATOR );
425 out.write( "All domains : "
426 + sum_of_all_domains_encountered );
428 ForesterUtil.programMessage( surfacing.PRG_NAME,
429 "Wrote fitch domain combination dynamics counts analysis to \"" + output_file
433 private static void executePlusMinusAnalysis( final File output_file,
434 final List<String> plus_minus_analysis_high_copy_base,
435 final List<String> plus_minus_analysis_high_copy_target,
436 final List<String> plus_minus_analysis_low_copy,
437 final List<GenomeWideCombinableDomains> gwcd_list,
438 final SortedMap<Species, List<Protein>> protein_lists_per_species,
439 final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
440 final Map<GoId, GoTerm> go_id_to_term_map,
441 final List<Object> plus_minus_analysis_numbers ) {
442 final Set<String> all_spec = new HashSet<String>();
443 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
444 all_spec.add( gwcd.getSpecies().getSpeciesId() );
446 final File html_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX_HTML );
447 final File plain_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX );
448 final File html_out_dc = new File( output_file + PLUS_MINUS_DC_SUFFIX_HTML );
449 final File all_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX );
450 final File passing_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX );
451 final File proteins_file_base = new File( output_file + "" );
452 final int min_diff = ( ( Integer ) plus_minus_analysis_numbers.get( 0 ) ).intValue();
453 final double factor = ( ( Double ) plus_minus_analysis_numbers.get( 1 ) ).doubleValue();
455 DomainCountsDifferenceUtil.calculateCopyNumberDifferences( gwcd_list,
456 protein_lists_per_species,
457 plus_minus_analysis_high_copy_base,
458 plus_minus_analysis_high_copy_target,
459 plus_minus_analysis_low_copy,
465 domain_id_to_go_ids_map,
467 all_domains_go_ids_out_dom,
468 passing_domains_go_ids_out_dom,
469 proteins_file_base );
471 catch ( final IOException e ) {
472 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
474 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
475 + html_out_dom + "\"" );
476 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
477 + plain_out_dom + "\"" );
478 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \"" + html_out_dc
480 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based passing GO ids to \""
481 + passing_domains_go_ids_out_dom + "\"" );
482 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based all GO ids to \""
483 + all_domains_go_ids_out_dom + "\"" );
486 private static Phylogeny[] getIntrees( final File[] intree_files,
487 final int number_of_genomes,
488 final String[][] input_file_properties ) {
489 final Phylogeny[] intrees = new Phylogeny[ intree_files.length ];
491 for( final File intree_file : intree_files ) {
492 Phylogeny intree = null;
493 final String error = ForesterUtil.isReadableFile( intree_file );
494 if ( !ForesterUtil.isEmpty( error ) ) {
495 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read input tree file [" + intree_file + "]: "
499 final Phylogeny[] p_array = ParserBasedPhylogenyFactory.getInstance()
500 .create( intree_file, ParserUtils.createParserDependingOnFileType( intree_file, true ) );
501 if ( p_array.length < 1 ) {
502 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
503 + "] does not contain any phylogeny in phyloXML format" );
505 else if ( p_array.length > 1 ) {
506 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
507 + "] contains more than one phylogeny in phyloXML format" );
509 intree = p_array[ 0 ];
511 catch ( final Exception e ) {
512 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read input tree from file [" + intree_file
515 if ( ( intree == null ) || intree.isEmpty() ) {
516 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" );
518 if ( !intree.isRooted() ) {
519 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is not rooted" );
521 if ( intree.getNumberOfExternalNodes() < number_of_genomes ) {
522 ForesterUtil.fatalError( surfacing.PRG_NAME,
523 "number of external nodes [" + intree.getNumberOfExternalNodes()
524 + "] of input tree [" + intree_file
525 + "] is smaller than the number of genomes the be analyzed ["
526 + number_of_genomes + "]" );
528 final StringBuilder parent_names = new StringBuilder();
529 final int nodes_lacking_name = SurfacingUtil.getNumberOfNodesLackingName( intree, parent_names );
530 if ( nodes_lacking_name > 0 ) {
531 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] has "
532 + nodes_lacking_name + " node(s) lacking a name [parent names:" + parent_names + "]" );
534 preparePhylogenyForParsimonyAnalyses( intree, input_file_properties );
535 if ( !intree.isCompletelyBinary() ) {
536 ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "input tree [" + intree_file
537 + "] is not completely binary" );
539 intrees[ i++ ] = intree;
544 private static void log( final String msg, final Writer w ) {
547 w.write( ForesterUtil.LINE_SEPARATOR );
549 catch ( final IOException e ) {
550 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
554 public static void main( final String args[] ) {
555 final long start_time = new Date().getTime();
556 // final StringBuffer log = new StringBuffer();
557 final StringBuilder html_desc = new StringBuilder();
558 ForesterUtil.printProgramInformation( surfacing.PRG_NAME,
559 surfacing.PRG_VERSION,
563 final String nl = ForesterUtil.LINE_SEPARATOR;
564 html_desc.append( "<table>" + nl );
565 html_desc.append( "<tr><td>Produced by:</td><td>" + surfacing.PRG_NAME + "</td></tr>" + nl );
566 html_desc.append( "<tr><td>Version:</td><td>" + surfacing.PRG_VERSION + "</td></tr>" + nl );
567 html_desc.append( "<tr><td>Release Date:</td><td>" + surfacing.PRG_DATE + "</td></tr>" + nl );
568 html_desc.append( "<tr><td>Contact:</td><td>" + surfacing.E_MAIL + "</td></tr>" + nl );
569 html_desc.append( "<tr><td>WWW:</td><td>" + surfacing.WWW + "</td></tr>" + nl );
570 CommandLineArguments cla = null;
572 cla = new CommandLineArguments( args );
574 catch ( final Exception e ) {
575 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
577 if ( cla.isOptionSet( surfacing.HELP_OPTION_1 ) || cla.isOptionSet( surfacing.HELP_OPTION_2 ) ) {
578 surfacing.printHelp();
581 if ( ( args.length < 1 ) ) {
582 surfacing.printHelp();
585 final List<String> allowed_options = new ArrayList<String>();
586 allowed_options.add( surfacing.NOT_IGNORE_DUFS_OPTION );
587 allowed_options.add( surfacing.MAX_E_VALUE_OPTION );
588 allowed_options.add( surfacing.DETAILEDNESS_OPTION );
589 allowed_options.add( surfacing.OUTPUT_FILE_OPTION );
590 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_OPTION );
591 allowed_options.add( surfacing.SPECIES_MATRIX_OPTION );
592 allowed_options.add( surfacing.SCORING_OPTION );
593 allowed_options.add( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
594 allowed_options.add( surfacing.NO_ENGULFING_OVERLAP_OPTION );
595 allowed_options.add( surfacing.DOMAIN_COUNT_SORT_OPTION );
596 allowed_options.add( surfacing.CUTOFF_SCORE_FILE_OPTION );
597 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION );
598 allowed_options.add( surfacing.OUTPUT_DIR_OPTION );
599 allowed_options.add( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION );
600 allowed_options.add( surfacing.PFAM_TO_GO_FILE_USE_OPTION );
601 allowed_options.add( surfacing.GO_OBO_FILE_USE_OPTION );
602 allowed_options.add( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION );
603 allowed_options.add( surfacing.GO_NAMESPACE_LIMIT_OPTION );
604 allowed_options.add( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
605 allowed_options.add( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION );
606 allowed_options.add( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS );
607 allowed_options.add( JACKNIFE_OPTION );
608 allowed_options.add( JACKNIFE_RANDOM_SEED_OPTION );
609 allowed_options.add( JACKNIFE_RATIO_OPTION );
610 allowed_options.add( INPUT_SPECIES_TREE_OPTION );
611 allowed_options.add( FILTER_POSITIVE_OPTION );
612 allowed_options.add( FILTER_NEGATIVE_OPTION );
613 allowed_options.add( INPUT_GENOMES_FILE_OPTION );
614 allowed_options.add( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
615 allowed_options.add( FILTER_NEGATIVE_DOMAINS_OPTION );
616 allowed_options.add( IGNORE_VIRAL_IDS );
617 allowed_options.add( SEQ_EXTRACT_OPTION );
618 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
619 allowed_options.add( SECONDARY_FEATURES_PARSIMONY_MAP_FILE );
620 allowed_options.add( PLUS_MINUS_ANALYSIS_OPTION );
621 allowed_options.add( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS );
622 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS );
623 allowed_options.add( CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY );
624 boolean ignore_dufs = surfacing.IGNORE_DUFS_DEFAULT;
625 boolean ignore_combination_with_same = surfacing.IGNORE_COMBINATION_WITH_SAME_DEFAULLT;
626 double e_value_max = surfacing.MAX_E_VALUE_DEFAULT;
627 int max_allowed_overlap = surfacing.MAX_ALLOWED_OVERLAP_DEFAULT;
628 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
629 if ( dissallowed_options.length() > 0 ) {
630 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown option(s): " + dissallowed_options );
632 boolean output_binary_domain_combinationsfor_graph_analysis = false;
633 if ( cla.isOptionSet( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS ) ) {
634 output_binary_domain_combinationsfor_graph_analysis = true;
636 if ( cla.isOptionSet( surfacing.MAX_E_VALUE_OPTION ) ) {
638 e_value_max = cla.getOptionValueAsDouble( surfacing.MAX_E_VALUE_OPTION );
640 catch ( final Exception e ) {
641 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for E-value maximum" );
644 if ( cla.isOptionSet( surfacing.MAX_ALLOWED_OVERLAP_OPTION ) ) {
646 max_allowed_overlap = cla.getOptionValueAsInt( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
648 catch ( final Exception e ) {
649 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for maximal allowed domain overlap" );
652 boolean no_engulfing_overlaps = false;
653 if ( cla.isOptionSet( surfacing.NO_ENGULFING_OVERLAP_OPTION ) ) {
654 no_engulfing_overlaps = true;
656 boolean ignore_virus_like_ids = false;
657 if ( cla.isOptionSet( surfacing.IGNORE_VIRAL_IDS ) ) {
658 ignore_virus_like_ids = true;
660 if ( cla.isOptionSet( surfacing.NOT_IGNORE_DUFS_OPTION ) ) {
663 if ( cla.isOptionSet( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION ) ) {
664 ignore_combination_with_same = true;
666 boolean ignore_domains_without_combs_in_all_spec = IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT;
667 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION ) ) {
668 ignore_domains_without_combs_in_all_spec = true;
670 boolean ignore_species_specific_domains = IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT;
671 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION ) ) {
672 ignore_species_specific_domains = true;
674 File output_file = null;
675 if ( cla.isOptionSet( surfacing.OUTPUT_FILE_OPTION ) ) {
676 if ( !cla.isOptionValueSet( surfacing.OUTPUT_FILE_OPTION ) ) {
677 ForesterUtil.fatalError( surfacing.PRG_NAME,
678 "no value for domain combinations similarities output file: -"
679 + surfacing.OUTPUT_FILE_OPTION + "=<file>" );
681 output_file = new File( cla.getOptionValue( surfacing.OUTPUT_FILE_OPTION ) );
682 SurfacingUtil.checkForOutputFileWriteability( output_file );
684 File cutoff_scores_file = null;
685 Map<String, Double> individual_score_cutoffs = null;
686 if ( cla.isOptionSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
687 if ( !cla.isOptionValueSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
688 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for individual domain score cutoffs file: -"
689 + surfacing.CUTOFF_SCORE_FILE_OPTION + "=<file>" );
691 cutoff_scores_file = new File( cla.getOptionValue( surfacing.CUTOFF_SCORE_FILE_OPTION ) );
692 final String error = ForesterUtil.isReadableFile( cutoff_scores_file );
693 if ( !ForesterUtil.isEmpty( error ) ) {
694 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read individual domain score cutoffs file: "
698 final BasicTable<String> scores_table = BasicTableParser.parse( cutoff_scores_file, ' ' );
699 individual_score_cutoffs = scores_table.getColumnsAsMapDouble( 0, 1 );
701 catch ( final IOException e ) {
702 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from individual score cutoffs file: " + e );
705 BinaryDomainCombination.DomainCombinationType dc_type = BinaryDomainCombination.DomainCombinationType.BASIC;
706 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS ) ) {
707 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED;
709 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY ) ) {
710 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT;
713 if ( cla.isOptionSet( surfacing.OUTPUT_DIR_OPTION ) ) {
714 if ( !cla.isOptionValueSet( surfacing.OUTPUT_DIR_OPTION ) ) {
715 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for output directory: -"
716 + surfacing.OUTPUT_DIR_OPTION + "=<dir>" );
718 out_dir = new File( cla.getOptionValue( surfacing.OUTPUT_DIR_OPTION ) );
719 if ( out_dir.exists() && ( out_dir.listFiles().length > 0 ) ) {
720 ForesterUtil.fatalError( surfacing.PRG_NAME, "\"" + out_dir + "\" aready exists and is not empty" );
722 if ( !out_dir.exists() ) {
723 final boolean success = out_dir.mkdir();
724 if ( !success || !out_dir.exists() ) {
725 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to create \"" + out_dir + "\"" );
728 if ( !out_dir.canWrite() ) {
729 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot write to \"" + out_dir + "\"" );
732 File positive_filter_file = null;
733 File negative_filter_file = null;
734 File negative_domains_filter_file = null;
735 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) && cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
736 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use both negative and positive protein filter" );
738 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION )
739 && ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) || cla
740 .isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) ) {
742 .fatalError( surfacing.PRG_NAME,
743 "attempt to use both negative or positive protein filter together wirh a negative domains filter" );
745 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
746 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
747 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative filter: -"
748 + surfacing.FILTER_NEGATIVE_OPTION + "=<file>" );
750 negative_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_OPTION ) );
751 final String msg = ForesterUtil.isReadableFile( negative_filter_file );
752 if ( !ForesterUtil.isEmpty( msg ) ) {
753 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_filter_file + "\": "
757 else if ( cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
758 if ( !cla.isOptionValueSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
759 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for positive filter: -"
760 + surfacing.FILTER_POSITIVE_OPTION + "=<file>" );
762 positive_filter_file = new File( cla.getOptionValue( surfacing.FILTER_POSITIVE_OPTION ) );
763 final String msg = ForesterUtil.isReadableFile( positive_filter_file );
764 if ( !ForesterUtil.isEmpty( msg ) ) {
765 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + positive_filter_file + "\": "
769 else if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
770 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
771 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative domains filter: -"
772 + surfacing.FILTER_NEGATIVE_DOMAINS_OPTION + "=<file>" );
774 negative_domains_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) );
775 final String msg = ForesterUtil.isReadableFile( negative_domains_filter_file );
776 if ( !ForesterUtil.isEmpty( msg ) ) {
777 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_domains_filter_file
781 final List<String> plus_minus_analysis_high_copy_base_species = new ArrayList<String>();
782 final List<String> plus_minus_analysis_high_copy_target_species = new ArrayList<String>();
783 final List<String> plus_minus_analysis_high_low_copy_species = new ArrayList<String>();
784 final List<Object> plus_minus_analysis_numbers = new ArrayList<Object>();
785 processPlusMinusAnalysisOption( cla,
786 plus_minus_analysis_high_copy_base_species,
787 plus_minus_analysis_high_copy_target_species,
788 plus_minus_analysis_high_low_copy_species,
789 plus_minus_analysis_numbers );
790 File input_genomes_file = null;
791 if ( cla.isOptionSet( surfacing.INPUT_GENOMES_FILE_OPTION ) ) {
792 if ( !cla.isOptionValueSet( surfacing.INPUT_GENOMES_FILE_OPTION ) ) {
793 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input genomes file: -"
794 + surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>" );
796 input_genomes_file = new File( cla.getOptionValue( surfacing.INPUT_GENOMES_FILE_OPTION ) );
797 final String msg = ForesterUtil.isReadableFile( input_genomes_file );
798 if ( !ForesterUtil.isEmpty( msg ) ) {
800 .fatalError( surfacing.PRG_NAME, "can not read from \"" + input_genomes_file + "\": " + msg );
804 ForesterUtil.fatalError( surfacing.PRG_NAME, "no input genomes file given: "
805 + surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>" );
807 DomainSimilarity.DomainSimilarityScoring scoring = SCORING_DEFAULT;
808 if ( cla.isOptionSet( surfacing.SCORING_OPTION ) ) {
809 if ( !cla.isOptionValueSet( surfacing.SCORING_OPTION ) ) {
810 ForesterUtil.fatalError( surfacing.PRG_NAME,
811 "no value for scoring method for domain combinations similarity calculation: -"
812 + surfacing.SCORING_OPTION + "=<"
813 + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
814 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|"
815 + surfacing.SCORING_COMBINATION_BASED + ">\"" );
817 final String scoring_str = cla.getOptionValue( surfacing.SCORING_OPTION );
818 if ( scoring_str.equals( surfacing.SCORING_DOMAIN_COUNT_BASED ) ) {
819 scoring = DomainSimilarity.DomainSimilarityScoring.DOMAINS;
821 else if ( scoring_str.equals( surfacing.SCORING_COMBINATION_BASED ) ) {
822 scoring = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
824 else if ( scoring_str.equals( surfacing.SCORING_PROTEIN_COUNT_BASED ) ) {
825 scoring = DomainSimilarity.DomainSimilarityScoring.PROTEINS;
828 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + scoring_str
829 + "\" for scoring method for domain combinations similarity calculation: \"-"
830 + surfacing.SCORING_OPTION + "=<" + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
831 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|" + surfacing.SCORING_COMBINATION_BASED + ">\"" );
834 boolean sort_by_species_count_first = false;
835 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION ) ) {
836 sort_by_species_count_first = true;
838 boolean species_matrix = false;
839 if ( cla.isOptionSet( surfacing.SPECIES_MATRIX_OPTION ) ) {
840 species_matrix = true;
842 boolean output_protein_lists_for_all_domains = false;
843 double output_list_of_all_proteins_per_domain_e_value_max = -1;
844 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS ) ) {
845 output_protein_lists_for_all_domains = true;
846 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION ) ) {
848 output_list_of_all_proteins_per_domain_e_value_max = cla
849 .getOptionValueAsDouble( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
851 catch ( final Exception e ) {
852 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for per domain E-value maximum" );
856 Detailedness detailedness = DETAILEDNESS_DEFAULT;
857 if ( cla.isOptionSet( surfacing.DETAILEDNESS_OPTION ) ) {
858 if ( !cla.isOptionValueSet( surfacing.DETAILEDNESS_OPTION ) ) {
859 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for -" + surfacing.DETAILEDNESS_OPTION + "=<"
860 + surfacing.DETAILEDNESS_BASIC + "|" + surfacing.DETAILEDNESS_LIST_IDS + "|"
861 + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
863 final String detness = cla.getOptionValue( surfacing.DETAILEDNESS_OPTION ).toLowerCase();
864 if ( detness.equals( surfacing.DETAILEDNESS_BASIC ) ) {
865 detailedness = DomainSimilarityCalculator.Detailedness.BASIC;
867 else if ( detness.equals( surfacing.DETAILEDNESS_LIST_IDS ) ) {
868 detailedness = DomainSimilarityCalculator.Detailedness.LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES;
870 else if ( detness.equals( surfacing.DETAILEDNESS_PUNCTILIOUS ) ) {
871 detailedness = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
874 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + detness + "\" for detailedness: \"-"
875 + surfacing.DETAILEDNESS_OPTION + "=<" + surfacing.DETAILEDNESS_BASIC + "|"
876 + surfacing.DETAILEDNESS_LIST_IDS + "|" + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
879 String automated_pairwise_comparison_suffix = null;
880 boolean perform_pwc = false;
881 boolean write_pwc_files = false;
882 if ( cla.isOptionSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
884 if ( !cla.isOptionValueSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
885 write_pwc_files = false;
888 write_pwc_files = true;
889 automated_pairwise_comparison_suffix = "_"
890 + cla.getOptionValue( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
893 String query_domain_ids = null;
894 if ( cla.isOptionSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
895 if ( !cla.isOptionValueSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
897 .fatalError( surfacing.PRG_NAME,
898 "no domain ids given for sequences with given domains to be extracted : -"
899 + surfacing.SEQ_EXTRACT_OPTION
900 + "=<ordered domain sequences, domain ids separated by '~', sequences separated by '#'>" );
902 query_domain_ids = cla.getOptionValue( surfacing.SEQ_EXTRACT_OPTION );
904 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field = DOMAIN_SORT_FILD_DEFAULT;
905 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field_for_automated_pwc = DOMAIN_SORT_FILD_DEFAULT;
906 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
907 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
908 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for domain combinations similarities sorting: -"
909 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
910 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
911 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
912 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
913 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|"
914 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
917 final String sort_str = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ).toLowerCase();
918 if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ALPHA ) ) {
919 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
920 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
922 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MAX ) ) {
923 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX;
924 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
926 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MIN ) ) {
927 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MIN;
928 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
930 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MEAN ) ) {
931 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MEAN;
932 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MEAN;
934 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT ) ) {
935 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SPECIES_COUNT;
936 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
938 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SD ) ) {
939 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SD;
940 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
942 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_DIFF ) ) {
943 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
944 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
946 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF ) ) {
947 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
948 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
950 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF ) ) {
951 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
952 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
955 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort_str
956 + "\" for domain combinations similarities sorting: \"-"
957 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
958 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
959 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
960 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
961 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|" + "|"
962 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
966 PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option = DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT;
967 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
968 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
969 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for print option: -"
970 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
971 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
972 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
974 final String sort = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ).toLowerCase();
975 if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML ) ) {
976 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.HTML;
978 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML ) ) {
979 ForesterUtil.fatalError( surfacing.PRG_NAME, "simple HTML output not implemented yet :(" );
981 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED ) ) {
982 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.SIMPLE_TAB_DELIMITED;
985 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort + "\" for print option: -"
986 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
987 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
988 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
991 GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order = DOMAINS_SORT_ORDER_DEFAULT;
992 if ( cla.isOptionSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
993 if ( !cla.isOptionValueSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
994 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for sorting of domain counts: -"
995 + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<" + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|"
996 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
997 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
998 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1000 final String sort = cla.getOptionValue( surfacing.DOMAIN_COUNT_SORT_OPTION ).toLowerCase();
1001 if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_ALPHA ) ) {
1002 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
1004 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT ) ) {
1005 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_COUNT;
1007 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT ) ) {
1008 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_PROTEINS_COUNT;
1010 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT ) ) {
1011 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.COMBINATIONS_COUNT;
1014 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort
1015 + "\" for sorting of domain counts: \"-" + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<"
1016 + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|" + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1017 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1018 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1021 final String[][] input_file_properties = processInputGenomesFile( input_genomes_file );
1022 for( final String[] input_file_propertie : input_file_properties ) {
1023 for( int j = 0; j < input_file_propertie.length; j++ ) {
1024 System.out.print( input_file_propertie[ j ] + " " );
1026 System.out.println();
1028 final int number_of_genomes = input_file_properties.length;
1029 if ( number_of_genomes < 2 ) {
1030 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot analyze less than two files" );
1032 if ( ( number_of_genomes < 3 ) && perform_pwc ) {
1033 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use : -"
1034 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1035 + "=<suffix> to turn on pairwise analyses with less than three input files" );
1037 checkWriteabilityForPairwiseComparisons( domain_similarity_print_option,
1038 input_file_properties,
1039 automated_pairwise_comparison_suffix,
1041 for( int i = 0; i < number_of_genomes; i++ ) {
1042 File dcc_outfile = new File( input_file_properties[ i ][ 1 ]
1043 + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
1044 if ( out_dir != null ) {
1045 dcc_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + dcc_outfile );
1047 SurfacingUtil.checkForOutputFileWriteability( dcc_outfile );
1049 File pfam_to_go_file = null;
1050 Map<DomainId, List<GoId>> domain_id_to_go_ids_map = null;
1051 int domain_id_to_go_ids_count = 0;
1052 if ( cla.isOptionSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1053 if ( !cla.isOptionValueSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1054 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for Pfam to GO mapping file: -"
1055 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>" );
1057 pfam_to_go_file = new File( cla.getOptionValue( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) );
1058 final String error = ForesterUtil.isReadableFile( pfam_to_go_file );
1059 if ( !ForesterUtil.isEmpty( error ) ) {
1060 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read Pfam to GO mapping file: " + error );
1063 final PfamToGoParser parser = new PfamToGoParser( pfam_to_go_file );
1064 final List<PfamToGoMapping> pfam_to_go_mappings = parser.parse();
1065 domain_id_to_go_ids_map = SurfacingUtil.createDomainIdToGoIdMap( pfam_to_go_mappings );
1066 if ( parser.getMappingCount() < domain_id_to_go_ids_map.size() ) {
1067 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME,
1068 "parser.getMappingCount() < domain_id_to_go_ids_map.size()" );
1070 domain_id_to_go_ids_count = parser.getMappingCount();
1072 catch ( final IOException e ) {
1073 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from Pfam to GO mapping file: " + e );
1076 File go_obo_file = null;
1077 List<GoTerm> go_terms = null;
1078 if ( cla.isOptionSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1079 if ( !cla.isOptionValueSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1080 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO OBO file: -"
1081 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>" );
1083 if ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) {
1084 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO OBO file (-"
1085 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>) without Pfam to GO mapping file ("
1086 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1088 go_obo_file = new File( cla.getOptionValue( surfacing.GO_OBO_FILE_USE_OPTION ) );
1089 final String error = ForesterUtil.isReadableFile( go_obo_file );
1090 if ( !ForesterUtil.isEmpty( error ) ) {
1091 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read GO OBO file: " + error );
1094 final OBOparser parser = new OBOparser( go_obo_file, OBOparser.ReturnType.BASIC_GO_TERM );
1095 go_terms = parser.parse();
1096 if ( parser.getGoTermCount() != go_terms.size() ) {
1098 .unexpectedFatalError( surfacing.PRG_NAME, "parser.getGoTermCount() != go_terms.size()" );
1101 catch ( final IOException e ) {
1102 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from GO OBO file: " + e );
1105 Map<GoId, GoTerm> go_id_to_term_map = null;
1106 if ( ( ( domain_id_to_go_ids_map != null ) && ( domain_id_to_go_ids_map.size() > 0 ) )
1107 && ( ( go_terms != null ) && ( go_terms.size() > 0 ) ) ) {
1108 go_id_to_term_map = GoUtils.createGoIdToGoTermMap( go_terms );
1110 GoNameSpace go_namespace_limit = null;
1111 if ( cla.isOptionSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1112 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1113 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO namespace limit (-"
1114 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<namespace>) without Pfam to GO mapping file ("
1115 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>) and GO OBO file (-"
1116 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1118 if ( !cla.isOptionValueSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1119 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO namespace limit: \"-"
1120 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1121 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1122 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1123 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1125 final String go_namespace_limit_str = cla.getOptionValue( surfacing.GO_NAMESPACE_LIMIT_OPTION )
1127 if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION ) ) {
1128 go_namespace_limit = GoNameSpace.createMolecularFunction();
1130 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS ) ) {
1131 go_namespace_limit = GoNameSpace.createBiologicalProcess();
1133 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT ) ) {
1134 go_namespace_limit = GoNameSpace.createCellularComponent();
1137 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + go_namespace_limit_str
1138 + "\" for GO namespace limit: \"-" + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1139 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1140 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1141 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1144 if ( ( domain_similarity_sort_field == DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE )
1145 && ( number_of_genomes > 2 ) ) {
1146 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
1148 boolean jacknifed_distances = false;
1149 int jacknife_resamplings = JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT;
1150 double jacknife_ratio = JACKNIFE_RATIO_DEFAULT;
1151 long random_seed = JACKNIFE_RANDOM_SEED_DEFAULT;
1152 if ( cla.isOptionSet( surfacing.JACKNIFE_OPTION ) ) {
1153 if ( ( number_of_genomes < 3 ) || !perform_pwc ) {
1154 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use jacknife resampling analysis (-"
1155 + surfacing.JACKNIFE_OPTION + "[=<number of resamplings>]) without pairwise analyses ("
1156 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1157 + "=<suffix for pairwise comparison output files>)" );
1159 jacknifed_distances = true;
1160 if ( cla.isOptionHasAValue( surfacing.JACKNIFE_OPTION ) ) {
1162 jacknife_resamplings = cla.getOptionValueAsInt( surfacing.JACKNIFE_OPTION );
1164 catch ( final IOException e ) {
1165 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for number of resamplings" );
1167 if ( jacknife_resamplings < 2 ) {
1168 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use less than 2 resamplings" );
1171 if ( cla.isOptionSet( surfacing.JACKNIFE_RATIO_OPTION )
1172 && cla.isOptionHasAValue( surfacing.JACKNIFE_RATIO_OPTION ) ) {
1174 jacknife_ratio = cla.getOptionValueAsDouble( surfacing.JACKNIFE_RATIO_OPTION );
1176 catch ( final IOException e ) {
1177 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for jacknife ratio" );
1179 if ( ( jacknife_ratio <= 0.0 ) || ( jacknife_ratio >= 1.0 ) ) {
1180 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use illegal value for jacknife ratio: "
1184 if ( cla.isOptionSet( surfacing.JACKNIFE_RANDOM_SEED_OPTION )
1185 && cla.isOptionHasAValue( surfacing.JACKNIFE_RANDOM_SEED_OPTION ) ) {
1187 random_seed = cla.getOptionValueAsLong( surfacing.JACKNIFE_RANDOM_SEED_OPTION );
1189 catch ( final IOException e ) {
1190 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for random generator seed" );
1194 File[] intree_files = null;
1195 Phylogeny[] intrees = null;
1196 if ( cla.isOptionSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1197 // TODO FIXME if jacknife.... maybe not
1198 if ( number_of_genomes < 3 ) {
1199 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer gains and losses on input species trees (-"
1200 + surfacing.INPUT_SPECIES_TREE_OPTION + " without pairwise analyses ("
1201 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1202 + "=<suffix for pairwise comparison output files>)" );
1204 if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1205 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input tree: -"
1206 + surfacing.INPUT_SPECIES_TREE_OPTION + "=<tree file in phyloXML format>" );
1208 final String intrees_str = cla.getOptionValue( surfacing.INPUT_SPECIES_TREE_OPTION );
1209 if ( intrees_str.indexOf( "#" ) > 0 ) {
1210 final String[] intrees_strs = intrees_str.split( "#" );
1211 intree_files = new File[ intrees_strs.length ];
1213 for( final String s : intrees_strs ) {
1214 intree_files[ i++ ] = new File( s.trim() );
1218 intree_files = new File[ 1 ];
1219 intree_files[ 0 ] = new File( intrees_str );
1221 intrees = getIntrees( intree_files, number_of_genomes, input_file_properties );
1223 long random_number_seed_for_fitch_parsimony = 0l;
1224 boolean radomize_fitch_parsimony = false;
1225 if ( cla.isOptionSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1226 if ( !cla.isOptionValueSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1227 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for random number seed: -"
1228 + surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION + "=<seed>" );
1231 random_number_seed_for_fitch_parsimony = cla
1232 .getOptionValueAsLong( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
1234 catch ( final IOException e ) {
1235 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1237 radomize_fitch_parsimony = true;
1239 SortedSet<DomainId> filter = null;
1240 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1241 || ( negative_domains_filter_file != null ) ) {
1242 filter = new TreeSet<DomainId>();
1243 if ( positive_filter_file != null ) {
1244 processFilter( positive_filter_file, filter );
1246 else if ( negative_filter_file != null ) {
1247 processFilter( negative_filter_file, filter );
1249 else if ( negative_domains_filter_file != null ) {
1250 processFilter( negative_domains_filter_file, filter );
1253 Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps = null;
1254 File[] secondary_features_map_files = null;
1255 final File domain_lengths_analysis_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1256 + DOMAIN_LENGTHS_ANALYSIS_SUFFIX );
1257 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
1258 SurfacingUtil.checkForOutputFileWriteability( domain_lengths_analysis_outfile );
1260 if ( cla.isOptionSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1261 if ( !cla.isOptionValueSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1262 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for secondary features map file: -"
1263 + surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE + "=<file>" );
1265 final String[] secondary_features_map_files_strs = cla
1266 .getOptionValue( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ).split( "#" );
1267 secondary_features_map_files = new File[ secondary_features_map_files_strs.length ];
1268 domain_id_to_secondary_features_maps = new Map[ secondary_features_map_files_strs.length ];
1270 for( final String secondary_features_map_files_str : secondary_features_map_files_strs ) {
1271 secondary_features_map_files[ i ] = new File( secondary_features_map_files_str );
1272 final String error = ForesterUtil.isReadableFile( secondary_features_map_files[ i ] );
1273 if ( !ForesterUtil.isEmpty( error ) ) {
1274 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read secondary features map file: " + error );
1277 domain_id_to_secondary_features_maps[ i ] = SurfacingUtil
1278 .createDomainIdToSecondaryFeaturesMap( secondary_features_map_files[ i ] );
1280 catch ( final IOException e ) {
1281 ForesterUtil.fatalError( surfacing.PRG_NAME,
1282 "cannot read secondary features map file: " + e.getMessage() );
1284 catch ( final Exception e ) {
1285 ForesterUtil.fatalError( surfacing.PRG_NAME, "problem with contents of features map file ["
1286 + secondary_features_map_files[ i ] + "]: " + e.getMessage() );
1291 if ( out_dir == null ) {
1292 ForesterUtil.fatalError( surfacing.PRG_NAME, "no output directory indicated (-"
1293 + surfacing.OUTPUT_DIR_OPTION + "=<dir>)" );
1295 if ( output_file == null ) {
1296 ForesterUtil.fatalError( surfacing.PRG_NAME, "no name for (main) output file indicated (-"
1297 + surfacing.OUTPUT_FILE_OPTION + "=<file>)" );
1299 if ( ( domain_id_to_go_ids_map == null ) || domain_id_to_go_ids_map.isEmpty() ) {
1300 ForesterUtil.fatalError( surfacing.PRG_NAME,
1301 "no (acceptable) Pfam to GO id mapping file provided ('pfam2go file') (-"
1302 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1304 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1305 ForesterUtil.fatalError( surfacing.PRG_NAME,
1306 "no (acceptable) go id to term mapping file provided ('GO OBO file') (-"
1307 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1309 System.out.println( "Output directory : " + out_dir );
1310 System.out.println( "Input genomes from : " + input_genomes_file );
1311 html_desc.append( "<tr><td>Input genomes from:</td><td>" + input_genomes_file + "</td></tr>" + nl );
1312 if ( positive_filter_file != null ) {
1313 final int filter_size = filter.size();
1314 System.out.println( "Positive protein filter : " + positive_filter_file + " [" + filter_size
1316 html_desc.append( "<tr><td>Positive protein filter:</td><td>" + positive_filter_file + " [" + filter_size
1317 + " domain ids]</td></tr>" + nl );
1319 if ( negative_filter_file != null ) {
1320 final int filter_size = filter.size();
1321 System.out.println( "Negative protein filter : " + negative_filter_file + " [" + filter_size
1323 html_desc.append( "<tr><td>Negative protein filter:</td><td>" + negative_filter_file + " [" + filter_size
1324 + " domain ids]</td></tr>" + nl );
1326 if ( negative_domains_filter_file != null ) {
1327 final int filter_size = filter.size();
1328 System.out.println( "Negative domain filter : " + negative_domains_filter_file + " [" + filter_size
1330 html_desc.append( "<tr><td>Negative domain filter:</td><td>" + negative_domains_filter_file + " ["
1331 + filter_size + " domain ids]</td></tr>" + nl );
1333 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
1335 for( final String s : plus_minus_analysis_high_copy_base_species ) {
1336 plus0 += "+" + s + " ";
1339 for( final String s : plus_minus_analysis_high_copy_target_species ) {
1340 plus1 += "*" + s + " ";
1343 for( final String s : plus_minus_analysis_high_low_copy_species ) {
1344 minus += "-" + s + " ";
1346 System.out.println( "Plus-minus analysis : " + plus1 + "&& " + plus0 + "&& " + minus );
1347 html_desc.append( "<tr><td>Plus-minus analysis:</td><td>" + plus1 + "&& " + plus0 + "&& " + minus
1348 + "</td></tr>" + nl );
1350 if ( cutoff_scores_file != null ) {
1351 System.out.println( "Cutoff scores file : " + cutoff_scores_file );
1352 html_desc.append( "<tr><td>Cutoff scores file:</td><td>" + cutoff_scores_file + "</td></tr>" + nl );
1354 if ( e_value_max >= 0.0 ) {
1355 System.out.println( "E-value maximum (inclusive) : " + e_value_max );
1356 html_desc.append( "<tr><td>E-value maximum (inclusive):</td><td>" + e_value_max + "</td></tr>" + nl );
1358 if ( output_protein_lists_for_all_domains ) {
1359 System.out.println( "Domain E-value max : " + output_list_of_all_proteins_per_domain_e_value_max );
1360 html_desc.append( "<tr><td>Protein lists: E-value maximum per domain (inclusive):</td><td>"
1361 + output_list_of_all_proteins_per_domain_e_value_max + "</td></tr>" + nl );
1363 System.out.println( "Ignore DUFs : " + ignore_dufs );
1364 if ( ignore_virus_like_ids ) {
1365 System.out.println( "Ignore virus like ids : " + ignore_virus_like_ids );
1366 html_desc.append( "<tr><td>Ignore virus, phage, transposition related ids:</td><td>"
1367 + ignore_virus_like_ids + "</td></tr>" + nl );
1369 html_desc.append( "<tr><td>Ignore DUFs:</td><td>" + ignore_dufs + "</td></tr>" + nl );
1370 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1371 System.out.println( "Max allowed domain overlap : " + max_allowed_overlap );
1372 html_desc.append( "<tr><td>Max allowed domain overlap:</td><td>" + max_allowed_overlap + "</td></tr>" + nl );
1374 if ( no_engulfing_overlaps ) {
1375 System.out.println( "Ignore engulfed domains : " + no_engulfing_overlaps );
1376 html_desc.append( "<tr><td>Ignore (lower confidence) engulfed domains:</td><td>" + no_engulfing_overlaps
1377 + "</td></tr>" + nl );
1379 System.out.println( "Ignore singlet domains : " + ignore_domains_without_combs_in_all_spec );
1381 .append( "<tr><td>Ignore singlet domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1382 + ignore_domains_without_combs_in_all_spec + "</td></tr>" + nl );
1383 System.out.println( "Ignore species specific doms: " + ignore_species_specific_domains );
1385 .append( "<tr><td>Ignore species specific domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1386 + ignore_species_specific_domains + "</td></tr>" + nl );
1387 System.out.println( "Ignore combination with self: " + ignore_combination_with_same );
1388 html_desc.append( "<tr><td>Ignore combination with self for domain combination similarity analyses:</td><td>"
1389 + ignore_combination_with_same + "</td></tr>" + nl );
1390 System.out.println( "Consider directedness : "
1391 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) );
1392 html_desc.append( "<tr><td>Consider directedness of binary domain combinations:</td><td>"
1393 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) + "</td></tr>" + nl );
1394 if ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) {
1395 System.out.println( "Consider adjacency : "
1396 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) );
1397 html_desc.append( "<tr><td>Consider djacency of binary domain combinations:</td><td>"
1398 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) + "</td></tr>"
1401 System.out.print( "Domain counts sort order : " );
1402 switch ( dc_sort_order ) {
1403 case ALPHABETICAL_KEY_ID:
1404 System.out.println( "alphabetical" );
1406 case KEY_DOMAIN_COUNT:
1407 System.out.println( "domain count" );
1409 case KEY_DOMAIN_PROTEINS_COUNT:
1410 System.out.println( "domain proteins count" );
1412 case COMBINATIONS_COUNT:
1413 System.out.println( "domain combinations count" );
1416 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for dc sort order" );
1418 if ( domain_id_to_go_ids_map != null ) {
1419 System.out.println( "Pfam to GO mappings from : " + pfam_to_go_file + " [" + domain_id_to_go_ids_count
1421 html_desc.append( "<tr><td>Pfam to GO mappings from:</td><td>" + pfam_to_go_file + " ["
1422 + domain_id_to_go_ids_count + " mappings]" + "</td></tr>" + nl );
1424 if ( go_terms != null ) {
1425 System.out.println( "GO terms from : " + go_obo_file + " [" + go_terms.size() + " terms]" );
1426 html_desc.append( "<tr><td>GO terms from:</td><td>" + go_obo_file + " [" + go_terms.size() + " terms]"
1427 + "</td></tr>" + nl );
1429 if ( go_namespace_limit != null ) {
1430 System.out.println( "Limit GO terms to : " + go_namespace_limit.toString() );
1431 html_desc.append( "<tr><td>Limit GO terms to</td><td>" + go_namespace_limit + "</td></tr>" + nl );
1433 if ( perform_pwc ) {
1434 System.out.println( "Suffix for PWC files : " + automated_pairwise_comparison_suffix );
1435 html_desc.append( "<tr><td>Suffix for PWC files</td><td>" + automated_pairwise_comparison_suffix
1436 + "</td></tr>" + nl );
1438 if ( out_dir != null ) {
1439 System.out.println( "Output directory : " + out_dir );
1441 if ( query_domain_ids != null ) {
1442 System.out.println( "Query domains (ordered) : " + query_domain_ids );
1443 html_desc.append( "<tr><td></td><td>" + query_domain_ids + "</td></tr>" + nl );
1445 System.out.println( "Write similarities to : " + output_file );
1446 System.out.print( " Scoring method : " );
1447 html_desc.append( "<tr><td>Scoring method:</td><td>" );
1448 switch ( scoring ) {
1450 System.out.println( "domain combinations based" );
1451 html_desc.append( "domain combinations based" + "</td></tr>" + nl );
1454 System.out.println( "domain counts based" );
1455 html_desc.append( "domain counts based" + "</td></tr>" + nl );
1458 System.out.println( "domain proteins counts based" );
1459 html_desc.append( "domain proteins counts based" + "</td></tr>" + nl );
1462 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
1464 System.out.print( " Sort by : " );
1465 html_desc.append( "<tr><td>Sort by:</td><td>" );
1466 switch ( domain_similarity_sort_field ) {
1468 System.out.print( "score minimum" );
1469 html_desc.append( "score minimum" );
1472 System.out.print( "score maximum" );
1473 html_desc.append( "score maximum" );
1476 System.out.print( "score mean" );
1477 html_desc.append( "score mean" );
1480 System.out.print( "score standard deviation" );
1481 html_desc.append( "score standard deviation" );
1484 System.out.print( "species number" );
1485 html_desc.append( "species number" );
1488 System.out.print( "alphabetical domain identifier" );
1489 html_desc.append( "alphabetical domain identifier" );
1491 case MAX_DIFFERENCE:
1492 System.out.print( "(maximal) difference" );
1493 html_desc.append( "(maximal) difference" );
1495 case ABS_MAX_COUNTS_DIFFERENCE:
1496 System.out.print( "absolute (maximal) counts difference" );
1497 html_desc.append( "absolute (maximal) counts difference" );
1499 case MAX_COUNTS_DIFFERENCE:
1500 System.out.print( "(maximal) counts difference" );
1501 html_desc.append( "(maximal) counts difference" );
1504 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1506 if ( sort_by_species_count_first ) {
1507 System.out.println( " (sort by species count first)" );
1508 html_desc.append( " (sort by species count first)" );
1511 System.out.println();
1513 html_desc.append( "</td></tr>" + nl );
1514 System.out.print( " Detailedness : " );
1515 switch ( detailedness ) {
1517 System.out.println( "basic" );
1519 case LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES:
1520 System.out.println( "list combining domains for each species" );
1523 System.out.println( "punctilious" );
1526 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for detailedness" );
1528 System.out.print( " Print option : " );
1529 switch ( domain_similarity_print_option ) {
1531 System.out.println( "HTML" );
1533 case SIMPLE_TAB_DELIMITED:
1534 System.out.println( "simple tab delimited" );
1537 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for print option" );
1539 System.out.print( " Species matrix : " + species_matrix );
1540 System.out.println();
1541 final File dc_data_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + DATA_FILE_SUFFIX );
1542 System.out.println( "Domain comb data output : " + dc_data_file );
1543 html_desc.append( "<tr><td>Domain combination data output:</td><td> " + dc_data_file + " </td></tr>" );
1544 System.out.println();
1545 if ( perform_pwc ) {
1546 System.out.println( "Pairwise comparisons: " );
1547 html_desc.append( "<tr><td>Pairwise comparisons:</td><td></td></tr>" );
1548 System.out.print( " Sort by : " );
1549 html_desc.append( "<tr><td>Sort by:</td><td>" );
1550 switch ( domain_similarity_sort_field_for_automated_pwc ) {
1552 System.out.print( "score mean" );
1553 html_desc.append( "score mean" );
1556 System.out.print( "alphabetical domain identifier" );
1557 html_desc.append( "alphabetical domain identifier" );
1559 case MAX_DIFFERENCE:
1560 System.out.print( "difference" );
1561 html_desc.append( "difference" );
1563 case ABS_MAX_COUNTS_DIFFERENCE:
1564 System.out.print( "absolute counts difference" );
1565 html_desc.append( "absolute counts difference" );
1567 case MAX_COUNTS_DIFFERENCE:
1568 System.out.print( "counts difference" );
1569 html_desc.append( "counts difference" );
1573 .unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1575 System.out.println();
1576 html_desc.append( "</td></tr>" + nl );
1577 if ( jacknifed_distances ) {
1578 html_desc.append( "<tr><td>Jacknife:</td><td>" + jacknife_resamplings + " resamplings</td></tr>" + nl );
1579 html_desc.append( "<tr><td>Jacknife ratio:</td><td>" + ForesterUtil.round( jacknife_ratio, 2 )
1580 + "</td></tr>" + nl );
1581 html_desc.append( "<tr><td>Jacknife random number seed:</td><td>" + random_seed + "</td></tr>" + nl );
1582 System.out.println( " Jacknife : " + jacknife_resamplings + " resamplings" );
1583 System.out.println( " Ratio : " + ForesterUtil.round( jacknife_ratio, 2 ) );
1584 System.out.println( " Random number seed : " + random_seed );
1586 if ( ( intrees != null ) && ( intrees.length > 0 ) ) {
1587 for( final File intree_file : intree_files ) {
1588 html_desc.append( "<tr><td>Intree for gain/loss parsimony analysis:</td><td>" + intree_file
1589 + "</td></tr>" + nl );
1590 System.out.println( " Intree for gain/loss pars.: " + intree_file );
1593 if ( radomize_fitch_parsimony ) {
1594 html_desc.append( "<tr><td> Random number seed for Fitch parsimony analysis:</td><td>"
1595 + random_number_seed_for_fitch_parsimony + "</td></tr>" + nl );
1596 System.out.println( " Random number seed : " + random_number_seed_for_fitch_parsimony );
1598 if ( ( domain_id_to_secondary_features_maps != null ) && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
1599 for( int i = 0; i < secondary_features_map_files.length; i++ ) {
1600 html_desc.append( "<tr><td>Secondary features map file:</td><td>"
1601 + secondary_features_map_files[ i ] + "</td></tr>" + nl );
1602 System.out.println( "Secondary features map file : " + secondary_features_map_files[ i ]
1603 + " [mappings for " + domain_id_to_secondary_features_maps[ i ].size() + " domain ids]" );
1605 System.out.println();
1606 System.out.println( "Domain ids to secondary features map:" );
1607 for( final DomainId domain_id : domain_id_to_secondary_features_maps[ i ].keySet() ) {
1608 System.out.print( domain_id.getId() );
1609 System.out.print( " => " );
1610 for( final String sec : domain_id_to_secondary_features_maps[ i ].get( domain_id ) ) {
1611 System.out.print( sec );
1612 System.out.print( " " );
1614 System.out.println();
1619 } // if ( perform_pwc ) {
1620 System.out.println();
1621 html_desc.append( "<tr><td>Command line:</td><td>\n" + cla.getCommandLineArgsAsString() + "\n</td></tr>" + nl );
1622 System.out.println( "Command line : " + cla.getCommandLineArgsAsString() );
1623 BufferedWriter[] query_domains_writer_ary = null;
1624 List<DomainId>[] query_domain_ids_array = null;
1625 if ( query_domain_ids != null ) {
1626 final String[] query_domain_ids_str_array = query_domain_ids.split( "#" );
1627 query_domain_ids_array = new ArrayList[ query_domain_ids_str_array.length ];
1628 query_domains_writer_ary = new BufferedWriter[ query_domain_ids_str_array.length ];
1629 for( int i = 0; i < query_domain_ids_str_array.length; i++ ) {
1630 String query_domain_ids_str = query_domain_ids_str_array[ i ];
1631 final String[] query_domain_ids_str_ary = query_domain_ids_str.split( "~" );
1632 final List<DomainId> query = new ArrayList<DomainId>();
1633 for( final String element : query_domain_ids_str_ary ) {
1634 query.add( new DomainId( element ) );
1636 query_domain_ids_array[ i ] = query;
1637 query_domain_ids_str = query_domain_ids_str.replace( '~', '_' );
1638 String protein_names_writer_str = query_domain_ids_str + surfacing.SEQ_EXTRACT_SUFFIX;
1639 if ( out_dir != null ) {
1640 protein_names_writer_str = out_dir + ForesterUtil.FILE_SEPARATOR + protein_names_writer_str;
1643 query_domains_writer_ary[ i ] = new BufferedWriter( new FileWriter( protein_names_writer_str ) );
1645 catch ( final IOException e ) {
1646 ForesterUtil.fatalError( surfacing.PRG_NAME, "Could not open [" + protein_names_writer_str + "]: "
1647 + e.getLocalizedMessage() );
1651 SortedMap<Species, List<Protein>> protein_lists_per_species = null; //This will only be created if neede.
1652 boolean need_protein_lists_per_species = false;
1653 if ( ( plus_minus_analysis_high_copy_base_species.size() > 0 ) || output_protein_lists_for_all_domains ) {
1654 need_protein_lists_per_species = true;
1656 if ( need_protein_lists_per_species ) {
1657 protein_lists_per_species = new TreeMap<Species, List<Protein>>();
1659 final List<GenomeWideCombinableDomains> gwcd_list = new ArrayList<GenomeWideCombinableDomains>( number_of_genomes );
1660 final SortedSet<DomainId> all_domains_encountered = new TreeSet<DomainId>();
1661 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered = new TreeSet<BinaryDomainCombination>();
1662 List<BinaryDomainCombination> all_bin_domain_combinations_gained_fitch = null;
1663 List<BinaryDomainCombination> all_bin_domain_combinations_lost_fitch = null;
1664 if ( ( intrees != null ) && ( intrees.length == 1 ) ) {
1665 all_bin_domain_combinations_gained_fitch = new ArrayList<BinaryDomainCombination>();
1666 all_bin_domain_combinations_lost_fitch = new ArrayList<BinaryDomainCombination>();
1668 final DomainLengthsTable domain_lengths_table = new DomainLengthsTable();
1669 final File per_genome_domain_promiscuity_statistics_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR
1670 + output_file + D_PROMISCUITY_FILE_SUFFIX );
1671 BufferedWriter per_genome_domain_promiscuity_statistics_writer = null;
1673 per_genome_domain_promiscuity_statistics_writer = new BufferedWriter( new FileWriter( per_genome_domain_promiscuity_statistics_file ) );
1674 per_genome_domain_promiscuity_statistics_writer.write( "Species:\t" );
1675 per_genome_domain_promiscuity_statistics_writer.write( "Mean:\t" );
1676 per_genome_domain_promiscuity_statistics_writer.write( "SD:\t" );
1677 per_genome_domain_promiscuity_statistics_writer.write( "Median:\t" );
1678 per_genome_domain_promiscuity_statistics_writer.write( "Min:\t" );
1679 per_genome_domain_promiscuity_statistics_writer.write( "Max:\t" );
1680 per_genome_domain_promiscuity_statistics_writer.write( "N:\t" );
1681 per_genome_domain_promiscuity_statistics_writer.write( "Max Promiscuous Domains:"
1682 + ForesterUtil.LINE_SEPARATOR );
1684 catch ( final IOException e2 ) {
1685 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1687 final File log_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + LOG_FILE_SUFFIX );
1688 BufferedWriter log_writer = null;
1690 log_writer = new BufferedWriter( new FileWriter( log_file ) );
1692 catch ( final IOException e2 ) {
1693 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1695 BufferedWriter dc_data_writer = null;
1697 dc_data_writer = new BufferedWriter( new FileWriter( dc_data_file ) );
1698 dc_data_writer.write( DATA_FILE_DESC );
1699 dc_data_writer.write( ForesterUtil.LINE_SEPARATOR );
1701 catch ( final IOException e2 ) {
1702 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1704 final DescriptiveStatistics protein_coverage_stats = new BasicDescriptiveStatistics();
1705 final DescriptiveStatistics all_genomes_domains_per_potein_stats = new BasicDescriptiveStatistics();
1706 final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo = new TreeMap<Integer, Integer>();
1707 final SortedSet<String> domains_which_are_always_single = new TreeSet<String>();
1708 final SortedSet<String> domains_which_are_sometimes_single_sometimes_not = new TreeSet<String>();
1709 final SortedSet<String> domains_which_never_single = new TreeSet<String>();
1710 BufferedWriter domains_per_potein_stats_writer = null;
1712 domains_per_potein_stats_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
1713 + output_file + "__domains_per_potein_stats.txt" ) );
1714 domains_per_potein_stats_writer.write( "Genome" );
1715 domains_per_potein_stats_writer.write( "\t" );
1716 domains_per_potein_stats_writer.write( "Mean" );
1717 domains_per_potein_stats_writer.write( "\t" );
1718 domains_per_potein_stats_writer.write( "SD" );
1719 domains_per_potein_stats_writer.write( "\t" );
1720 domains_per_potein_stats_writer.write( "Median" );
1721 domains_per_potein_stats_writer.write( "\t" );
1722 domains_per_potein_stats_writer.write( "N" );
1723 domains_per_potein_stats_writer.write( "\t" );
1724 domains_per_potein_stats_writer.write( "Min" );
1725 domains_per_potein_stats_writer.write( "\t" );
1726 domains_per_potein_stats_writer.write( "Max" );
1727 domains_per_potein_stats_writer.write( "\n" );
1729 catch ( final IOException e3 ) {
1730 e3.printStackTrace();
1732 Map<String, DescriptiveStatistics> protein_length_stats_by_dc = null;
1733 Map<String, DescriptiveStatistics> domain_number_stats_by_dc = null;
1734 final Map<String, DescriptiveStatistics> domain_length_stats_by_domain = new HashMap<String, DescriptiveStatistics>();
1735 if ( PERFORM_DC_REGAIN_PROTEINS_STATS ) {
1736 protein_length_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1737 domain_number_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1740 final SortedMap<String, Set<String>> distinct_domain_architecutures_per_genome = new TreeMap<String, Set<String>>();
1741 final SortedMap<String, Integer> distinct_domain_architecuture_counts = new TreeMap<String, Integer>();
1742 for( int i = 0; i < number_of_genomes; ++i ) {
1743 System.out.println();
1744 System.out.println( ( i + 1 ) + "/" + number_of_genomes );
1745 log( ( i + 1 ) + "/" + number_of_genomes, log_writer );
1746 System.out.println( "Processing : " + input_file_properties[ i ][ 1 ]
1747 + " [" + input_file_properties[ i ][ 0 ] + "]" );
1748 log( "Genome : " + input_file_properties[ i ][ 1 ] + " ["
1749 + input_file_properties[ i ][ 0 ] + "]", log_writer );
1750 HmmscanPerDomainTableParser parser = null;
1751 INDIVIDUAL_SCORE_CUTOFF ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF.NONE;
1752 if ( individual_score_cutoffs != null ) {
1753 ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF_DEFAULT;
1755 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1756 || ( negative_domains_filter_file != null ) ) {
1757 HmmscanPerDomainTableParser.FilterType filter_type = HmmscanPerDomainTableParser.FilterType.NONE;
1758 if ( positive_filter_file != null ) {
1759 filter_type = HmmscanPerDomainTableParser.FilterType.POSITIVE_PROTEIN;
1761 else if ( negative_filter_file != null ) {
1762 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_PROTEIN;
1764 else if ( negative_domains_filter_file != null ) {
1765 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_DOMAIN;
1767 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1768 input_file_properties[ i ][ 1 ],
1775 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1776 input_file_properties[ i ][ 1 ],
1780 if ( e_value_max >= 0.0 ) {
1781 parser.setEValueMaximum( e_value_max );
1783 parser.setIgnoreDufs( ignore_dufs );
1784 parser.setIgnoreVirusLikeIds( ignore_virus_like_ids );
1785 parser.setIgnoreEngulfedDomains( no_engulfing_overlaps );
1786 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1787 parser.setMaxAllowedOverlap( max_allowed_overlap );
1789 parser.setReturnType( HmmscanPerDomainTableParser.ReturnType.UNORDERED_PROTEIN_DOMAIN_COLLECTION_PER_PROTEIN );
1790 if ( individual_score_cutoffs != null ) {
1791 parser.setIndividualScoreCutoffs( individual_score_cutoffs );
1793 List<Protein> protein_list = null;
1795 protein_list = parser.parse();
1797 catch ( final IOException e ) {
1798 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1800 catch ( final Exception e ) {
1801 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, e.getMessage(), e );
1804 System.out.println( "Domains ignored due to negative domain filter: " );
1805 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToNegativeDomainFilterCountsMap() );
1806 System.out.println( "Domains ignored due to virus like id: " );
1807 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToVirusLikeIdCountsMap() );
1809 final double coverage = ( double ) protein_list.size() / parser.getProteinsEncountered();
1810 protein_coverage_stats.addValue( coverage );
1811 int distinct_das = -1;
1812 if ( DA_ANALYSIS ) {
1813 final String genome = input_file_properties[ i ][ 0 ];
1814 distinct_das = SurfacingUtil.storeDomainArchitectures( genome,
1815 distinct_domain_architecutures_per_genome,
1817 distinct_domain_architecuture_counts );
1819 System.out.println( "Number of proteins encountered : " + parser.getProteinsEncountered() );
1820 log( "Number of proteins encountered : " + parser.getProteinsEncountered(), log_writer );
1821 System.out.println( "Number of proteins stored : " + protein_list.size() );
1822 log( "Number of proteins stored : " + protein_list.size(), log_writer );
1823 System.out.println( "Coverage : "
1824 + ForesterUtil.roundToInt( 100.0 * coverage ) + "%" );
1825 log( "Coverage : " + ForesterUtil.roundToInt( 100.0 * coverage )
1826 + "%", log_writer );
1827 System.out.println( "Domains encountered : " + parser.getDomainsEncountered() );
1828 log( "Domains encountered : " + parser.getDomainsEncountered(), log_writer );
1829 System.out.println( "Domains stored : " + parser.getDomainsStored() );
1830 log( "Domains stored : " + parser.getDomainsStored(), log_writer );
1831 System.out.println( "Distinct domains stored : "
1832 + parser.getDomainsStoredSet().size() );
1833 log( "Distinct domains stored : " + parser.getDomainsStoredSet().size(), log_writer );
1834 System.out.println( "Domains ignored due to individual score cutoffs: "
1835 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() );
1836 log( "Domains ignored due to individual score cutoffs: "
1837 + parser.getDomainsIgnoredDueToIndividualScoreCutoff(),
1839 System.out.println( "Domains ignored due to E-value : "
1840 + parser.getDomainsIgnoredDueToEval() );
1841 log( "Domains ignored due to E-value : " + parser.getDomainsIgnoredDueToEval(), log_writer );
1842 System.out.println( "Domains ignored due to DUF designation : "
1843 + parser.getDomainsIgnoredDueToDuf() );
1844 log( "Domains ignored due to DUF designation : " + parser.getDomainsIgnoredDueToDuf(), log_writer );
1845 if ( ignore_virus_like_ids ) {
1846 System.out.println( "Domains ignored due virus like ids : "
1847 + parser.getDomainsIgnoredDueToVirusLikeIds() );
1848 log( "Domains ignored due virus like ids : " + parser.getDomainsIgnoredDueToVirusLikeIds(),
1851 System.out.println( "Domains ignored due negative domain filter : "
1852 + parser.getDomainsIgnoredDueToNegativeDomainFilter() );
1853 log( "Domains ignored due negative domain filter : "
1854 + parser.getDomainsIgnoredDueToNegativeDomainFilter(),
1856 System.out.println( "Domains ignored due to overlap : "
1857 + parser.getDomainsIgnoredDueToOverlap() );
1858 log( "Domains ignored due to overlap : " + parser.getDomainsIgnoredDueToOverlap(),
1860 if ( negative_filter_file != null ) {
1861 System.out.println( "Proteins ignored due to negative filter : "
1862 + parser.getProteinsIgnoredDueToFilter() );
1863 log( "Proteins ignored due to negative filter : " + parser.getProteinsIgnoredDueToFilter(),
1866 if ( positive_filter_file != null ) {
1867 System.out.println( "Proteins ignored due to positive filter : "
1868 + parser.getProteinsIgnoredDueToFilter() );
1869 log( "Proteins ignored due to positive filter : " + parser.getProteinsIgnoredDueToFilter(),
1872 if ( DA_ANALYSIS ) {
1873 System.out.println( "Distinct domain architectures stored : " + distinct_das );
1874 log( "Distinct domain architectures stored : " + distinct_das, log_writer );
1876 System.out.println( "Time for processing : " + parser.getTime() + "ms" );
1877 log( "", log_writer );
1878 html_desc.append( "<tr><td>" + input_file_properties[ i ][ 0 ] + " [species: "
1879 + input_file_properties[ i ][ 1 ] + "]" + ":</td><td>domains analyzed: "
1880 + parser.getDomainsStored() + "; domains ignored: [ind score cutoffs: "
1881 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() + "] [E-value cutoff: "
1882 + parser.getDomainsIgnoredDueToEval() + "] [DUF: " + parser.getDomainsIgnoredDueToDuf()
1883 + "] [virus like ids: " + parser.getDomainsIgnoredDueToVirusLikeIds()
1884 + "] [negative domain filter: " + parser.getDomainsIgnoredDueToNegativeDomainFilter()
1885 + "] [overlap: " + parser.getDomainsIgnoredDueToOverlap() + "]" );
1886 if ( negative_filter_file != null ) {
1887 html_desc.append( "; proteins ignored due to negative filter: "
1888 + parser.getProteinsIgnoredDueToFilter() );
1890 if ( positive_filter_file != null ) {
1891 html_desc.append( "; proteins ignored due to positive filter: "
1892 + parser.getProteinsIgnoredDueToFilter() );
1894 html_desc.append( "</td></tr>" + nl );
1897 for( final Protein protein : protein_list ) {
1898 dc_data_writer.write( SurfacingUtil.proteinToDomainCombinations( protein, count + "", "\t" )
1901 for( final Domain d : protein.getProteinDomains() ) {
1902 final String d_str = d.getDomainId().toString();
1903 if ( !domain_length_stats_by_domain.containsKey( d_str ) ) {
1904 domain_length_stats_by_domain.put( d_str, new BasicDescriptiveStatistics() );
1906 domain_length_stats_by_domain.get( d_str ).addValue( d.getLength() );
1910 catch ( final IOException e ) {
1911 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1913 SurfacingUtil.domainsPerProteinsStatistics( input_file_properties[ i ][ 1 ],
1915 all_genomes_domains_per_potein_stats,
1916 all_genomes_domains_per_potein_histo,
1917 domains_which_are_always_single,
1918 domains_which_are_sometimes_single_sometimes_not,
1919 domains_which_never_single,
1920 domains_per_potein_stats_writer );
1921 domain_lengths_table.addLengths( protein_list );
1922 if ( !DA_ANALYSIS ) {
1923 gwcd_list.add( BasicGenomeWideCombinableDomains
1924 .createInstance( protein_list,
1925 ignore_combination_with_same,
1926 new BasicSpecies( input_file_properties[ i ][ 1 ] ),
1927 domain_id_to_go_ids_map,
1929 protein_length_stats_by_dc,
1930 domain_number_stats_by_dc ) );
1931 if ( gwcd_list.get( i ).getSize() > 0 ) {
1932 SurfacingUtil.writeDomainCombinationsCountsFile( input_file_properties,
1934 per_genome_domain_promiscuity_statistics_writer,
1938 if ( output_binary_domain_combinationsfor_graph_analysis ) {
1939 SurfacingUtil.writeBinaryDomainCombinationsFileForGraphAnalysis( input_file_properties,
1945 SurfacingUtil.addAllDomainIdsToSet( gwcd_list.get( i ), all_domains_encountered );
1946 SurfacingUtil.addAllBinaryDomainCombinationToSet( gwcd_list.get( i ),
1947 all_bin_domain_combinations_encountered );
1950 if ( query_domains_writer_ary != null ) {
1951 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1953 SurfacingUtil.extractProteinNames( protein_list,
1954 query_domain_ids_array[ j ],
1955 query_domains_writer_ary[ j ],
1957 LIMIT_SPEC_FOR_PROT_EX );
1958 query_domains_writer_ary[ j ].flush();
1960 catch ( final IOException e ) {
1961 e.printStackTrace();
1965 if ( need_protein_lists_per_species ) {
1966 protein_lists_per_species.put( new BasicSpecies( input_file_properties[ i ][ 1 ] ), protein_list );
1971 catch ( final IOException e2 ) {
1972 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1975 } // for( int i = 0; i < number_of_genomes; ++i ) {
1976 ForesterUtil.programMessage( PRG_NAME, "Wrote domain promiscuities to: "
1977 + per_genome_domain_promiscuity_statistics_file );
1979 if ( DA_ANALYSIS ) {
1980 SurfacingUtil.performDomainArchitectureAnalysis( distinct_domain_architecutures_per_genome,
1981 distinct_domain_architecuture_counts,
1983 new File( out_dir.toString() + "/" + output_file
1984 + "_DA_counts.txt" ),
1985 new File( out_dir.toString() + "/" + output_file
1986 + "_unique_DAs.txt" ) );
1987 distinct_domain_architecutures_per_genome.clear();
1988 distinct_domain_architecuture_counts.clear();
1992 domains_per_potein_stats_writer.write( "ALL" );
1993 domains_per_potein_stats_writer.write( "\t" );
1994 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.arithmeticMean() + "" );
1995 domains_per_potein_stats_writer.write( "\t" );
1996 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.sampleStandardDeviation() + "" );
1997 domains_per_potein_stats_writer.write( "\t" );
1998 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.median() + "" );
1999 domains_per_potein_stats_writer.write( "\t" );
2000 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getN() + "" );
2001 domains_per_potein_stats_writer.write( "\t" );
2002 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMin() + "" );
2003 domains_per_potein_stats_writer.write( "\t" );
2004 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMax() + "" );
2005 domains_per_potein_stats_writer.write( "\n" );
2006 domains_per_potein_stats_writer.close();
2007 printOutPercentageOfMultidomainProteins( all_genomes_domains_per_potein_histo, log_writer );
2008 ForesterUtil.map2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2009 + "__all_genomes_domains_per_potein_histo.txt" ), all_genomes_domains_per_potein_histo, "\t", "\n" );
2010 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2011 + "__domains_always_single_.txt" ), domains_which_are_always_single, "\n" );
2012 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2013 + "__domains_single_or_combined.txt" ), domains_which_are_sometimes_single_sometimes_not, "\n" );
2014 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2015 + "__domains_always_combined.txt" ), domains_which_never_single, "\n" );
2016 ForesterUtil.programMessage( PRG_NAME,
2017 "Average of proteins with a least one domain assigned: "
2018 + ( 100 * protein_coverage_stats.arithmeticMean() ) + "% (+/-"
2019 + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)" );
2020 ForesterUtil.programMessage( PRG_NAME, "Range of proteins with a least one domain assigned: "
2021 + ( 100 * protein_coverage_stats.getMin() ) + "%-" + ( 100 * protein_coverage_stats.getMax() )
2023 log( "Average of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.arithmeticMean() )
2024 + "% (+/-" + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)", log_writer );
2025 log( "Range of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.getMin() ) + "%-"
2026 + ( 100 * protein_coverage_stats.getMax() ) + "%", log_writer );
2028 catch ( final IOException e2 ) {
2029 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
2031 if ( query_domains_writer_ary != null ) {
2032 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
2034 query_domains_writer_ary[ j ].close();
2036 catch ( final IOException e ) {
2037 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
2042 per_genome_domain_promiscuity_statistics_writer.close();
2043 dc_data_writer.close();
2046 catch ( final IOException e2 ) {
2047 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
2049 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
2051 SurfacingUtil.executeDomainLengthAnalysis( input_file_properties,
2053 domain_lengths_table,
2054 domain_lengths_analysis_outfile );
2056 catch ( final IOException e1 ) {
2057 ForesterUtil.fatalError( surfacing.PRG_NAME, e1.toString() );
2059 System.out.println();
2060 ForesterUtil.programMessage( PRG_NAME, "Wrote domain length data to: " + domain_lengths_analysis_outfile );
2061 System.out.println();
2063 final long analysis_start_time = new Date().getTime();
2064 PairwiseDomainSimilarityCalculator pw_calc = null;
2065 // double[] values_for_all_scores_histogram = null;
2066 final DomainSimilarityCalculator calc = new BasicDomainSimilarityCalculator( domain_similarity_sort_field,
2067 sort_by_species_count_first,
2068 number_of_genomes == 2 );
2069 switch ( scoring ) {
2071 pw_calc = new CombinationsBasedPairwiseDomainSimilarityCalculator();
2074 pw_calc = new DomainCountsBasedPairwiseSimilarityCalculator();
2077 pw_calc = new ProteinCountsBasedPairwiseDomainSimilarityCalculator();
2080 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
2082 DomainSimilarityCalculator.GoAnnotationOutput go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.NONE;
2083 if ( domain_id_to_go_ids_map != null ) {
2084 go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.ALL;
2086 final SortedSet<DomainSimilarity> similarities = calc
2087 .calculateSimilarities( pw_calc,
2089 ignore_domains_without_combs_in_all_spec,
2090 ignore_species_specific_domains );
2091 SurfacingUtil.decoratePrintableDomainSimilarities( similarities,
2093 go_annotation_output,
2095 go_namespace_limit );
2096 DescriptiveStatistics pw_stats = null;
2098 String my_outfile = output_file.toString();
2099 Map<Character, Writer> split_writers = null;
2100 Writer writer = null;
2101 if ( similarities.size() > MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING ) {
2102 if ( my_outfile.endsWith( ".html" ) ) {
2103 my_outfile = my_outfile.substring( 0, my_outfile.length() - 5 );
2105 split_writers = new HashMap<Character, Writer>();
2106 createSplitWriters( out_dir, my_outfile, split_writers );
2108 else if ( !my_outfile.endsWith( ".html" ) ) {
2109 my_outfile += ".html";
2110 writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) );
2112 List<Species> species_order = null;
2113 if ( species_matrix ) {
2114 species_order = new ArrayList<Species>();
2115 for( int i = 0; i < number_of_genomes; i++ ) {
2116 species_order.add( new BasicSpecies( input_file_properties[ i ][ 1 ] ) );
2119 html_desc.append( "<tr><td>Sum of all distinct binary combinations:</td><td>"
2120 + all_bin_domain_combinations_encountered.size() + "</td></tr>" + nl );
2121 html_desc.append( "<tr><td>Sum of all distinct domains:</td><td>" + all_domains_encountered.size()
2122 + "</td></tr>" + nl );
2123 html_desc.append( "<tr><td>Analysis date/time:</td><td>"
2124 + new java.text.SimpleDateFormat( "yyyy.MM.dd HH:mm:ss" ).format( new java.util.Date() )
2125 + "</td></tr>" + nl );
2126 html_desc.append( "</table>" + nl );
2127 pw_stats = SurfacingUtil
2128 .writeDomainSimilaritiesToFile( html_desc,
2129 new StringBuilder( number_of_genomes + " genomes" ),
2133 number_of_genomes == 2,
2135 domain_similarity_print_option,
2136 domain_similarity_sort_field,
2139 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote main output (includes domain similarities) to: \""
2140 + ( out_dir == null ? my_outfile : out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) + "\"" );
2142 catch ( final IOException e ) {
2143 ForesterUtil.fatalError( surfacing.PRG_NAME, "Failed to write similarites to: \"" + output_file + "\" ["
2144 + e.getMessage() + "]" );
2146 System.out.println();
2147 // values_for_all_scores_histogram = pw_stats.getDataAsDoubleArray();
2148 final Species[] species = new Species[ number_of_genomes ];
2149 for( int i = 0; i < number_of_genomes; ++i ) {
2150 species[ i ] = new BasicSpecies( input_file_properties[ i ][ 1 ] );
2152 List<Phylogeny> inferred_trees = null;
2153 if ( ( number_of_genomes > 2 ) && perform_pwc ) {
2154 final PairwiseGenomeComparator pwgc = new PairwiseGenomeComparator();
2155 pwgc.performPairwiseComparisons( html_desc,
2156 sort_by_species_count_first,
2158 ignore_domains_without_combs_in_all_spec,
2159 ignore_species_specific_domains,
2160 domain_similarity_sort_field_for_automated_pwc,
2161 domain_similarity_print_option,
2163 domain_id_to_go_ids_map,
2170 automated_pairwise_comparison_suffix,
2172 surfacing.PAIRWISE_DOMAIN_COMPARISONS_PREFIX,
2176 String matrix_output_file = new String( output_file.toString() );
2177 if ( matrix_output_file.indexOf( '.' ) > 1 ) {
2178 matrix_output_file = matrix_output_file.substring( 0, matrix_output_file.indexOf( '.' ) );
2180 if ( out_dir != null ) {
2181 matrix_output_file = out_dir + ForesterUtil.FILE_SEPARATOR + matrix_output_file;
2182 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2184 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2185 + surfacing.MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans() );
2187 .writeMatrixToFile( new File( matrix_output_file
2188 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2189 pwgc.getSharedBinaryCombinationsBasedDistances() );
2190 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2191 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2192 pwgc.getSharedDomainsBasedDistances() );
2193 final Phylogeny nj_gd = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2194 + surfacing.NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans()
2196 final Phylogeny nj_bc = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2197 + surfacing.NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2198 .getSharedBinaryCombinationsBasedDistances().get( 0 ) );
2199 final Phylogeny nj_d = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2200 + surfacing.NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2201 .getSharedDomainsBasedDistances().get( 0 ) );
2202 inferred_trees = new ArrayList<Phylogeny>();
2203 inferred_trees.add( nj_gd );
2204 inferred_trees.add( nj_bc );
2205 inferred_trees.add( nj_d );
2206 if ( jacknifed_distances ) {
2207 pwgc.performPairwiseComparisonsJacknifed( species,
2211 jacknife_resamplings,
2215 .writeMatrixToFile( new File( matrix_output_file
2217 + ForesterUtil.round( jacknife_ratio, 2 )
2219 + jacknife_resamplings
2220 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2221 pwgc.getSharedBinaryCombinationsBasedDistances() );
2223 .writeMatrixToFile( new File( matrix_output_file + "_" + ForesterUtil.round( jacknife_ratio, 2 )
2224 + "_" + jacknife_resamplings
2225 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2226 pwgc.getSharedDomainsBasedDistances() );
2227 // if ( infer_species_trees ) {
2228 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2229 // + INFERRED_SBC_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc
2230 // .getSharedBinaryCombinationsBasedDistances() );
2231 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2232 // + INFERRED_SD_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc.getSharedDomainsBasedDistances() );
2235 } // if ( ( output_file != null ) && ( number_of_genomes > 2 ) && !isEmpty( automated_pairwise_comparison_suffix ) )
2236 if ( ( out_dir != null ) && ( !perform_pwc ) ) {
2237 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2239 writePresentToNexus( output_file, positive_filter_file, filter, gwcd_list );
2240 if ( ( ( intrees != null ) && ( intrees.length > 0 ) ) && ( number_of_genomes > 2 ) ) {
2241 final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
2243 max_allowed_overlap,
2244 no_engulfing_overlaps,
2248 if ( radomize_fitch_parsimony ) {
2249 s += random_number_seed_for_fitch_parsimony + "_";
2252 for( final Phylogeny intree : intrees ) {
2253 final String outfile_name = ForesterUtil.removeSuffix( output_file.toString() ) + s
2254 + ForesterUtil.removeSuffix( intree_files[ i ].toString() );
2255 final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator.createInstance( intree,
2257 SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
2258 radomize_fitch_parsimony,
2262 domain_id_to_go_ids_map,
2265 parameters_sb.toString(),
2266 domain_id_to_secondary_features_maps,
2267 positive_filter_file == null ? null : filter,
2268 output_binary_domain_combinationsfor_graph_analysis,
2269 all_bin_domain_combinations_gained_fitch,
2270 all_bin_domain_combinations_lost_fitch,
2272 protein_length_stats_by_dc,
2273 domain_number_stats_by_dc,
2274 domain_length_stats_by_domain );
2275 // Listing of all domain combinations gained is only done if only one input tree is used.
2276 if ( ( domain_id_to_secondary_features_maps != null )
2277 && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
2279 for( final Map<DomainId, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
2280 final Map<Species, MappingResults> mapping_results_map = new TreeMap<Species, MappingResults>();
2281 final DomainParsimonyCalculator secondary_features_parsimony = DomainParsimonyCalculator
2282 .createInstance( intree, gwcd_list, domain_id_to_secondary_features_map );
2284 .executeParsimonyAnalysisForSecondaryFeatures( outfile_name
2286 + secondary_features_map_files[ j++ ],
2287 secondary_features_parsimony,
2289 parameters_sb.toString(),
2290 mapping_results_map );
2292 System.out.println();
2293 System.out.println( "Mapping to secondary features:" );
2294 for( final Species spec : mapping_results_map.keySet() ) {
2295 final MappingResults mapping_results = mapping_results_map.get( spec );
2296 final int total_domains = mapping_results.getSumOfFailures()
2297 + mapping_results.getSumOfSuccesses();
2298 System.out.print( spec + ":" );
2299 System.out.print( " mapped domains = " + mapping_results.getSumOfSuccesses() );
2300 System.out.print( ", not mapped domains = " + mapping_results.getSumOfFailures() );
2301 if ( total_domains > 0 ) {
2302 System.out.println( ", mapped ratio = "
2303 + ( ( 100 * mapping_results.getSumOfSuccesses() ) / total_domains ) + "%" );
2306 System.out.println( ", mapped ratio = n/a (total domains = 0 )" );
2313 } // for( final Phylogeny intree : intrees ) {
2315 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
2316 executePlusMinusAnalysis( output_file,
2317 plus_minus_analysis_high_copy_base_species,
2318 plus_minus_analysis_high_copy_target_species,
2319 plus_minus_analysis_high_low_copy_species,
2321 protein_lists_per_species,
2322 domain_id_to_go_ids_map,
2324 plus_minus_analysis_numbers );
2326 if ( output_protein_lists_for_all_domains ) {
2327 writeProteinListsForAllSpecies( out_dir,
2328 protein_lists_per_species,
2330 output_list_of_all_proteins_per_domain_e_value_max );
2332 if ( all_bin_domain_combinations_gained_fitch != null ) {
2334 executeFitchGainsAnalysis( new File( output_file
2335 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2336 all_bin_domain_combinations_gained_fitch,
2337 all_domains_encountered.size(),
2338 all_bin_domain_combinations_encountered,
2341 catch ( final IOException e ) {
2342 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2345 if ( all_bin_domain_combinations_lost_fitch != null ) {
2347 executeFitchGainsAnalysis( new File( output_file
2348 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2349 all_bin_domain_combinations_lost_fitch,
2350 all_domains_encountered.size(),
2351 all_bin_domain_combinations_encountered,
2354 catch ( final IOException e ) {
2355 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2358 final Runtime rt = java.lang.Runtime.getRuntime();
2359 final long free_memory = rt.freeMemory() / 1000000;
2360 final long total_memory = rt.totalMemory() / 1000000;
2361 ForesterUtil.programMessage( PRG_NAME, "Time for analysis : " + ( new Date().getTime() - analysis_start_time )
2363 ForesterUtil.programMessage( PRG_NAME, "Total running time: " + ( new Date().getTime() - start_time ) + "ms " );
2364 ForesterUtil.programMessage( PRG_NAME, "Free memory : " + free_memory + "MB, total memory: "
2365 + total_memory + "MB" );
2366 ForesterUtil.programMessage( PRG_NAME, "If this application is useful to you, please cite:" );
2367 ForesterUtil.programMessage( PRG_NAME, surfacing.WWW );
2368 ForesterUtil.programMessage( PRG_NAME, "OK" );
2369 System.out.println();
2372 private static void createSplitWriters( final File out_dir,
2373 final String my_outfile,
2374 final Map<Character, Writer> split_writers ) throws IOException {
2375 split_writers.put( 'a', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2376 + "_domains_A.html" ) ) );
2377 split_writers.put( 'b', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2378 + "_domains_B.html" ) ) );
2379 split_writers.put( 'c', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2380 + "_domains_C.html" ) ) );
2381 split_writers.put( 'd', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2382 + "_domains_D.html" ) ) );
2383 split_writers.put( 'e', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2384 + "_domains_E.html" ) ) );
2385 split_writers.put( 'f', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2386 + "_domains_F.html" ) ) );
2387 split_writers.put( 'g', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2388 + "_domains_G.html" ) ) );
2389 split_writers.put( 'h', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2390 + "_domains_H.html" ) ) );
2391 split_writers.put( 'i', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2392 + "_domains_I.html" ) ) );
2393 split_writers.put( 'j', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2394 + "_domains_J.html" ) ) );
2395 split_writers.put( 'k', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2396 + "_domains_K.html" ) ) );
2397 split_writers.put( 'l', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2398 + "_domains_L.html" ) ) );
2399 split_writers.put( 'm', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2400 + "_domains_M.html" ) ) );
2401 split_writers.put( 'n', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2402 + "_domains_N.html" ) ) );
2403 split_writers.put( 'o', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2404 + "_domains_O.html" ) ) );
2405 split_writers.put( 'p', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2406 + "_domains_P.html" ) ) );
2407 split_writers.put( 'q', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2408 + "_domains_Q.html" ) ) );
2409 split_writers.put( 'r', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2410 + "_domains_R.html" ) ) );
2411 split_writers.put( 's', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2412 + "_domains_S.html" ) ) );
2413 split_writers.put( 't', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2414 + "_domains_T.html" ) ) );
2415 split_writers.put( 'u', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2416 + "_domains_U.html" ) ) );
2417 split_writers.put( 'v', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2418 + "_domains_V.html" ) ) );
2419 split_writers.put( 'w', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2420 + "_domains_W.html" ) ) );
2421 split_writers.put( 'x', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2422 + "_domains_X.html" ) ) );
2423 split_writers.put( 'y', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2424 + "_domains_Y.html" ) ) );
2425 split_writers.put( 'z', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2426 + "_domains_Z.html" ) ) );
2427 split_writers.put( '0', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2428 + "_domains_0.html" ) ) );
2431 private static void printOutPercentageOfMultidomainProteins( final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo,
2432 final Writer log_writer ) {
2434 for( final Entry<Integer, Integer> entry : all_genomes_domains_per_potein_histo.entrySet() ) {
2435 sum += entry.getValue();
2437 final double percentage = ( 100.0 * ( sum - all_genomes_domains_per_potein_histo.get( 1 ) ) ) / sum;
2438 ForesterUtil.programMessage( PRG_NAME, "Percentage of multidomain proteins: " + percentage + "%" );
2439 log( "Percentage of multidomain proteins: : " + percentage + "%", log_writer );
2442 private static void preparePhylogenyForParsimonyAnalyses( final Phylogeny intree,
2443 final String[][] input_file_properties ) {
2444 final String[] genomes = new String[ input_file_properties.length ];
2445 for( int i = 0; i < input_file_properties.length; ++i ) {
2446 if ( intree.getNodes( input_file_properties[ i ][ 1 ] ).size() > 1 ) {
2447 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
2448 + "] is not unique in input tree " + intree.getName() );
2450 genomes[ i ] = input_file_properties[ i ][ 1 ];
2453 final PhylogenyNodeIterator it = intree.iteratorPostorder();
2454 while ( it.hasNext() ) {
2455 final PhylogenyNode n = it.next();
2456 if ( ForesterUtil.isEmpty( n.getName() ) ) {
2457 if ( n.getNodeData().isHasTaxonomy()
2458 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getTaxonomyCode() ) ) {
2459 n.setName( n.getNodeData().getTaxonomy().getTaxonomyCode() );
2461 else if ( n.getNodeData().isHasTaxonomy()
2462 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
2463 n.setName( n.getNodeData().getTaxonomy().getScientificName() );
2465 else if ( n.getNodeData().isHasTaxonomy()
2466 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getCommonName() ) ) {
2467 n.setName( n.getNodeData().getTaxonomy().getCommonName() );
2471 .fatalError( surfacing.PRG_NAME,
2472 "node with no name, scientific name, common name, or taxonomy code present" );
2477 final List<String> igns = PhylogenyMethods.deleteExternalNodesPositiveSelection( genomes, intree );
2478 if ( igns.size() > 0 ) {
2479 System.out.println( "Not using the following " + igns.size() + " nodes:" );
2480 for( int i = 0; i < igns.size(); ++i ) {
2481 System.out.println( " " + i + ": " + igns.get( i ) );
2483 System.out.println( "--" );
2485 for( final String[] input_file_propertie : input_file_properties ) {
2487 intree.getNode( input_file_propertie[ 1 ] );
2489 catch ( final IllegalArgumentException e ) {
2490 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_propertie[ 1 ]
2491 + "] not present/not unique in input tree" );
2496 private static void printHelp() {
2497 System.out.println();
2498 System.out.println( "Usage:" );
2499 System.out.println();
2500 System.out.println( "% java -Xms256m -Xmx512m -cp forester.jar org.forester.applications." + surfacing.PRG_NAME
2501 + " [options] <phylogen(y|ies) infile> [external node name 1] [name 2] ... [name n]" );
2502 System.out.println();
2503 System.out.println( " Note: This software might need a significant amount of memory (heap space);" );
2505 .println( " hence use \"-Xms128m -Xmx512m\" (or more) to prevent a \"java.lang.OutOfMemoryError\"." );
2506 System.out.println();
2507 System.out.println( " Options: " );
2508 System.out.println( surfacing.DETAILEDNESS_OPTION + ": level of detail for similarities output file (default:"
2509 + DETAILEDNESS_DEFAULT + ")" );
2510 System.out.println( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION
2511 + ": to ignore combinations with self (default: not to ignore)" );
2513 .println( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION
2514 + ": to ignore domains without combinations in any species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2516 .println( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION
2517 + ": to ignore domains specific to one species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2518 System.out.println( surfacing.NOT_IGNORE_DUFS_OPTION
2519 + ": to _not_ ignore DUFs (domains with unknown function) (default: ignore DUFs)" );
2521 .println( surfacing.IGNORE_VIRAL_IDS
2522 + ": to ignore domains with ids containing 'vir', 'retro', 'transpos', 'phage', or starting with 'rv' or 'gag_'" );
2523 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_OPTION + ": sorting for similarities (default: "
2524 + DOMAIN_SORT_FILD_DEFAULT + ")" );
2525 System.out.println( surfacing.OUTPUT_FILE_OPTION + ": name for (main) output file (mandatory)" );
2526 System.out.println( surfacing.MAX_E_VALUE_OPTION + ": max (inclusive) E-value" );
2527 System.out.println( surfacing.MAX_ALLOWED_OVERLAP_OPTION + ": maximal allowed domain overlap" );
2528 System.out.println( surfacing.NO_ENGULFING_OVERLAP_OPTION + ": to ignore engulfed lower confidence domains" );
2529 System.out.println( surfacing.SPECIES_MATRIX_OPTION + ": species matrix" );
2530 System.out.println( surfacing.SCORING_OPTION + ": scoring (default:" + SCORING_DEFAULT + ")" );
2531 System.out.println( surfacing.DOMAIN_COUNT_SORT_OPTION + ": sorting for domain counts (default:"
2532 + DOMAINS_SORT_ORDER_DEFAULT + ")" );
2533 System.out.println( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION + ": domain similarity print option (default:"
2534 + DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT + ")" );
2535 System.out.println( surfacing.CUTOFF_SCORE_FILE_OPTION + ": cutoff score file" );
2536 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION
2537 + ": sort by species count first" );
2538 System.out.println( surfacing.OUTPUT_DIR_OPTION + ": output directory" );
2539 System.out.println( surfacing.PFAM_TO_GO_FILE_USE_OPTION + ": Pfam to GO mapping file" );
2540 System.out.println( surfacing.GO_OBO_FILE_USE_OPTION + ": GO terms file (OBO format)" );
2541 System.out.println( surfacing.GO_NAMESPACE_LIMIT_OPTION + ": limit GO term to one GO namespace" );
2542 System.out.println( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
2543 + "[=<suffix for pairwise comparison output files>]: to perform pairwise comparison based analyses" );
2544 System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION
2545 + ": species tree, to perform (Dollo, Fitch) parismony analyses" );
2547 .println( JACKNIFE_OPTION
2548 + ": perform jacknife resampling for domain and binary domain combination based distance matrices [default resamplings: "
2549 + JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT + "]" );
2550 System.out.println( JACKNIFE_RATIO_OPTION + ": ratio for jacknife resampling [default: "
2551 + JACKNIFE_RATIO_DEFAULT + "]" );
2552 System.out.println( JACKNIFE_RANDOM_SEED_OPTION
2553 + ": seed for random number generator for jacknife resampling [default: "
2554 + JACKNIFE_RANDOM_SEED_DEFAULT + "]" );
2555 // System.out.println( surfacing.INFER_SPECIES_TREES_OPTION
2556 // + ": to infer NJ species trees based on shared domains/binary domain combinations" );
2558 .println( surfacing.INPUT_SPECIES_TREE_OPTION
2559 + "=<treefiles in phyloXML format, separated by #>: to infer domain/binary domain combination gains/losses on given species trees" );
2560 System.out.println( surfacing.FILTER_POSITIVE_OPTION
2561 + "=<file>: to filter out proteins not containing at least one domain listed in <file>" );
2562 System.out.println( surfacing.FILTER_NEGATIVE_OPTION
2563 + "=<file>: to filter out proteins containing at least one domain listed in <file>" );
2564 System.out.println( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION
2565 + "=<file>: to filter out (ignore) domains listed in <file>" );
2566 System.out.println( surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>: to read input files from <file>" );
2568 .println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION
2569 + "=<seed>: seed for random number generator for Fitch Parsimony analysis (type: long, default: no randomization - given a choice, prefer absence" );
2570 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS
2571 + ": to consider directedness in binary combinations: e.g. A-B != B-A" );
2572 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY
2573 + ": to consider directedness and adjacency in binary combinations" );
2575 .println( surfacing.SEQ_EXTRACT_OPTION
2576 + "=<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')" );
2577 System.out.println( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE
2578 + "=<file>: to perfom parsimony analysis on secondary features" );
2579 System.out.println( surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>: to presence/absence genome analysis" );
2580 System.out.println( surfacing.DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS
2581 + ": to output binary domain combinations for (downstream) graph analysis" );
2582 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS + ": to output all proteins per domain" );
2583 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION
2584 + ": e value max per domain for output of all proteins per domain" );
2585 System.out.println();
2586 System.out.println( "Example 1: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2587 + " org.forester.application.surfacing p2g=pfam2go_2012_02_07.txt -dufs -cos=Pfam_260_NC1"
2588 + " -no_eo -mo=0 -genomes=eukaryotes.txt -out_dir=out -o=o "
2589 + " -species_tree=tol.xml -obo=gene_ontology_2012_02_07.obo -pos_filter=f.txt -all_prot" );
2590 System.out.println();
2591 System.out.println( "Example 2: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2592 + " org.forester.application.surfacing -detail=punctilious -o=TEST.html -pwc=TEST"
2593 + " -cos=Pfam_ls_22_TC2 -p2g=pfam2go -obo=gene_ontology_edit.obo "
2594 + "-dc_sort=dom -ignore_with_self -no_singles -e=0.001 -mo=1 -no_eo -genomes=eukaryotes.txt "
2595 + "-ds_output=detailed_html -scoring=domains -sort=alpha " );
2596 System.out.println();
2599 private static void processFilter( final File filter_file, final SortedSet<DomainId> filter ) {
2600 SortedSet<String> filter_str = null;
2602 filter_str = ForesterUtil.file2set( filter_file );
2604 catch ( final IOException e ) {
2605 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2607 if ( filter_str != null ) {
2608 for( final String string : filter_str ) {
2609 filter.add( new DomainId( string ) );
2613 System.out.println( "Filter:" );
2614 for( final DomainId domainId : filter ) {
2615 System.out.println( domainId.getId() );
2620 private static String[][] processInputGenomesFile( final File input_genomes ) {
2621 String[][] input_file_properties = null;
2623 input_file_properties = ForesterUtil.file22dArray( input_genomes );
2625 catch ( final IOException e ) {
2626 ForesterUtil.fatalError( surfacing.PRG_NAME,
2627 "genomes files is to be in the following format \"<hmmpfam output file> <species>\": "
2628 + e.getLocalizedMessage() );
2630 for( int i = 0; i < input_file_properties.length; ++i ) {
2631 final String error = ForesterUtil.isReadableFile( new File( input_file_properties[ i ][ 0 ] ) );
2632 if ( !ForesterUtil.isEmpty( error ) ) {
2633 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
2636 return input_file_properties;
2639 private static void processPlusMinusAnalysisOption( final CommandLineArguments cla,
2640 final List<String> high_copy_base,
2641 final List<String> high_copy_target,
2642 final List<String> low_copy,
2643 final List<Object> numbers ) {
2644 if ( cla.isOptionSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2645 if ( !cla.isOptionValueSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2646 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for 'plus-minus' file: -"
2647 + surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>" );
2649 final File plus_minus_file = new File( cla.getOptionValue( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) );
2650 final String msg = ForesterUtil.isReadableFile( plus_minus_file );
2651 if ( !ForesterUtil.isEmpty( msg ) ) {
2652 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + plus_minus_file + "\": " + msg );
2654 processPlusMinusFile( plus_minus_file, high_copy_base, high_copy_target, low_copy, numbers );
2658 // First numbers is minimal difference, second is factor.
2659 private static void processPlusMinusFile( final File plus_minus_file,
2660 final List<String> high_copy_base,
2661 final List<String> high_copy_target,
2662 final List<String> low_copy,
2663 final List<Object> numbers ) {
2664 Set<String> species_set = null;
2665 int min_diff = PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT;
2666 double factor = PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT;
2668 species_set = ForesterUtil.file2set( plus_minus_file );
2670 catch ( final IOException e ) {
2671 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2673 if ( species_set != null ) {
2674 for( final String species : species_set ) {
2675 final String species_trimmed = species.substring( 1 );
2676 if ( species.startsWith( "+" ) ) {
2677 if ( low_copy.contains( species_trimmed ) ) {
2678 ForesterUtil.fatalError( surfacing.PRG_NAME,
2679 "species/genome names can not appear with both '+' and '-' suffix, as appears the case for: \""
2680 + species_trimmed + "\"" );
2682 high_copy_base.add( species_trimmed );
2684 else if ( species.startsWith( "*" ) ) {
2685 if ( low_copy.contains( species_trimmed ) ) {
2686 ForesterUtil.fatalError( surfacing.PRG_NAME,
2687 "species/genome names can not appear with both '*' and '-' suffix, as appears the case for: \""
2688 + species_trimmed + "\"" );
2690 high_copy_target.add( species_trimmed );
2692 else if ( species.startsWith( "-" ) ) {
2693 if ( high_copy_base.contains( species_trimmed ) || high_copy_target.contains( species_trimmed ) ) {
2694 ForesterUtil.fatalError( surfacing.PRG_NAME,
2695 "species/genome names can not appear with both '+' or '*' and '-' suffix, as appears the case for: \""
2696 + species_trimmed + "\"" );
2698 low_copy.add( species_trimmed );
2700 else if ( species.startsWith( "$D" ) ) {
2702 min_diff = Integer.parseInt( species.substring( 3 ) );
2704 catch ( final NumberFormatException e ) {
2705 ForesterUtil.fatalError( surfacing.PRG_NAME,
2706 "could not parse integer value for minimal difference from: \""
2707 + species.substring( 3 ) + "\"" );
2710 else if ( species.startsWith( "$F" ) ) {
2712 factor = Double.parseDouble( species.substring( 3 ) );
2714 catch ( final NumberFormatException e ) {
2715 ForesterUtil.fatalError( surfacing.PRG_NAME, "could not parse double value for factor from: \""
2716 + species.substring( 3 ) + "\"" );
2719 else if ( species.startsWith( "#" ) ) {
2724 .fatalError( surfacing.PRG_NAME,
2725 "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: \""
2728 numbers.add( new Integer( min_diff + "" ) );
2729 numbers.add( new Double( factor + "" ) );
2733 ForesterUtil.fatalError( surfacing.PRG_NAME, "'plus minus' file [" + plus_minus_file + "] appears empty" );
2737 private static void writePresentToNexus( final File output_file,
2738 final File positive_filter_file,
2739 final SortedSet<DomainId> filter,
2740 final List<GenomeWideCombinableDomains> gwcd_list ) {
2743 .writeMatrixToFile( DomainParsimonyCalculator
2744 .createMatrixOfDomainPresenceOrAbsence( gwcd_list, positive_filter_file == null ? null
2745 : filter ), output_file + DOMAINS_PRESENT_NEXUS, Format.NEXUS_BINARY );
2746 SurfacingUtil.writeMatrixToFile( DomainParsimonyCalculator
2747 .createMatrixOfBinaryDomainCombinationPresenceOrAbsence( gwcd_list ), output_file
2748 + BDC_PRESENT_NEXUS, Format.NEXUS_BINARY );
2750 catch ( final Exception e ) {
2751 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2755 private static void writeProteinListsForAllSpecies( final File output_dir,
2756 final SortedMap<Species, List<Protein>> protein_lists_per_species,
2757 final List<GenomeWideCombinableDomains> gwcd_list,
2758 final double domain_e_cutoff ) {
2759 final SortedSet<DomainId> all_domains = new TreeSet<DomainId>();
2760 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
2761 all_domains.addAll( gwcd.getAllDomainIds() );
2763 for( final DomainId domain : all_domains ) {
2764 final File out = new File( output_dir + ForesterUtil.FILE_SEPARATOR + domain + SEQ_EXTRACT_SUFFIX );
2765 SurfacingUtil.checkForOutputFileWriteability( out );
2767 final Writer proteins_file_writer = new BufferedWriter( new FileWriter( out ) );
2768 SurfacingUtil.extractProteinNames( protein_lists_per_species,
2770 proteins_file_writer,
2772 LIMIT_SPEC_FOR_PROT_EX,
2774 proteins_file_writer.close();
2776 catch ( final IOException e ) {
2777 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2779 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote proteins list to \"" + out + "\"" );