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.phyloxml.PhyloXmlUtil;
58 import org.forester.io.parsers.util.ParserUtils;
59 import org.forester.phylogeny.Phylogeny;
60 import org.forester.phylogeny.PhylogenyMethods;
61 import org.forester.phylogeny.PhylogenyNode;
62 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
63 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
64 import org.forester.protein.BinaryDomainCombination;
65 import org.forester.protein.Domain;
66 import org.forester.protein.DomainId;
67 import org.forester.protein.Protein;
68 import org.forester.species.BasicSpecies;
69 import org.forester.species.Species;
70 import org.forester.surfacing.BasicDomainSimilarityCalculator;
71 import org.forester.surfacing.BasicGenomeWideCombinableDomains;
72 import org.forester.surfacing.CombinationsBasedPairwiseDomainSimilarityCalculator;
73 import org.forester.surfacing.DomainCountsBasedPairwiseSimilarityCalculator;
74 import org.forester.surfacing.DomainCountsDifferenceUtil;
75 import org.forester.surfacing.DomainLengthsTable;
76 import org.forester.surfacing.DomainParsimonyCalculator;
77 import org.forester.surfacing.DomainSimilarity;
78 import org.forester.surfacing.DomainSimilarity.DomainSimilarityScoring;
79 import org.forester.surfacing.DomainSimilarity.DomainSimilaritySortField;
80 import org.forester.surfacing.DomainSimilarityCalculator;
81 import org.forester.surfacing.DomainSimilarityCalculator.Detailedness;
82 import org.forester.surfacing.GenomeWideCombinableDomains;
83 import org.forester.surfacing.GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder;
84 import org.forester.surfacing.MappingResults;
85 import org.forester.surfacing.PairwiseDomainSimilarityCalculator;
86 import org.forester.surfacing.PairwiseGenomeComparator;
87 import org.forester.surfacing.PrintableDomainSimilarity;
88 import org.forester.surfacing.PrintableDomainSimilarity.PRINT_OPTION;
89 import org.forester.surfacing.ProteinCountsBasedPairwiseDomainSimilarityCalculator;
90 import org.forester.surfacing.SurfacingUtil;
91 import org.forester.util.BasicDescriptiveStatistics;
92 import org.forester.util.BasicTable;
93 import org.forester.util.BasicTableParser;
94 import org.forester.util.CommandLineArguments;
95 import org.forester.util.DescriptiveStatistics;
96 import org.forester.util.ForesterConstants;
97 import org.forester.util.ForesterUtil;
99 public class surfacing {
101 private static final int MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING = 1000;
102 public final static String DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS = "graph_analysis_out";
103 public final static String DOMAIN_COMBINITONS_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_dc.dot";
104 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_fitch_present_dc.dot";
105 public final static String DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX = ".dcc";
107 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS = "_dollo_gl_d";
108 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_gl_dc";
109 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_DOMAINS = "_fitch_gl_d";
110 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_gl_dc";
112 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS = "_dollo_glc_d";
113 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_glc_dc";
114 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_DOMAINS = "_fitch_glc_d";
115 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_glc_dc";
117 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_BC = "_fitch_gains_dc";
118 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_HTML_BC = "_fitch_gains_dc.html";
119 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_BC = "_fitch_losses_dc";
120 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_HTML_BC = "_fitch_losses_dc.html";
121 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC = "_fitch_present_dc";
122 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_HTML_BC = "_fitch_present_dc.html";
123 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_D = "_dollo_gains_d";
124 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_HTML_D = "_dollo_gains_d.html";
125 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_D = "_dollo_losses_d";
126 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_HTML_D = "_dollo_losses_d.html";
127 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_D = "_dollo_present_d";
128 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_HTML_D = "_dollo_present_d.html";
129 public final static String DOMAINS_PRESENT_NEXUS = "_dom.nex";
130 public final static String BDC_PRESENT_NEXUS = "_dc.nex";
132 public final static String PRG_NAME = "surfacing";
133 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_d_dollo"
134 + ForesterConstants.PHYLO_XML_SUFFIX;
135 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_d_fitch"
136 + ForesterConstants.PHYLO_XML_SUFFIX;
137 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_dc_dollo"
138 + ForesterConstants.PHYLO_XML_SUFFIX;
139 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_dc_fitch"
140 + ForesterConstants.PHYLO_XML_SUFFIX;
141 public static final String NEXUS_EXTERNAL_DOMAINS = "_dom.nex";
142 public static final String NEXUS_EXTERNAL_DOMAIN_COMBINATIONS = "_dc.nex";
143 public static final String NEXUS_SECONDARY_FEATURES = "_secondary_features.nex";
144 public static final String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_gl_secondary_features";
145 public static final String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_glc_secondary_features";
146 public static final String PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES = "_dollo_gains_secondary_features";
147 public static final String PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES = "_dollo_losses_secondary_features";
148 public static final String PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES = "_dollo_present_secondary_features";
149 public static final String SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_secondary_features_dollo"
150 + ForesterConstants.PHYLO_XML_SUFFIX;
151 public static final String PARSIMONY_OUTPUT_DOLLO_ALL_GOID_D_ALL_NAMESPACES = "_dollo_goid_d";
152 public static final String PARSIMONY_OUTPUT_FITCH_ALL_GOID_BC_ALL_NAMESPACES = "_fitch_goid_dc";
153 final static private String HELP_OPTION_1 = "help";
154 final static private String HELP_OPTION_2 = "h";
155 final static private String OUTPUT_DIR_OPTION = "out_dir";
156 final static private String SCORING_OPTION = "scoring";
157 private static final DomainSimilarityScoring SCORING_DEFAULT = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
158 final static private String SCORING_DOMAIN_COUNT_BASED = "domains";
159 final static private String SCORING_PROTEIN_COUNT_BASED = "proteins";
160 final static private String SCORING_COMBINATION_BASED = "combinations";
161 final static private String DETAILEDNESS_OPTION = "detail";
162 private final static Detailedness DETAILEDNESS_DEFAULT = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
163 final static private String SPECIES_MATRIX_OPTION = "smatrix";
164 final static private String DETAILEDNESS_BASIC = "basic";
165 final static private String DETAILEDNESS_LIST_IDS = "list_ids";
166 final static private String DETAILEDNESS_PUNCTILIOUS = "punctilious";
167 final static private String DOMAIN_SIMILARITY_SORT_OPTION = "sort";
168 private static final DomainSimilaritySortField DOMAIN_SORT_FILD_DEFAULT = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
169 final static private String DOMAIN_SIMILARITY_SORT_MIN = "min";
170 final static private String DOMAIN_SIMILARITY_SORT_MAX = "max";
171 final static private String DOMAIN_SIMILARITY_SORT_SD = "sd";
172 final static private String DOMAIN_SIMILARITY_SORT_MEAN = "mean";
173 final static private String DOMAIN_SIMILARITY_SORT_DIFF = "diff";
174 final static private String DOMAIN_SIMILARITY_SORT_COUNTS_DIFF = "count_diff";
175 final static private String DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF = "abs_count_diff";
176 final static private String DOMAIN_SIMILARITY_SORT_SPECIES_COUNT = "species";
177 final static private String DOMAIN_SIMILARITY_SORT_ALPHA = "alpha";
178 final static private String DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION = "species_first";
179 final static private String DOMAIN_COUNT_SORT_OPTION = "dc_sort";
180 private static final GenomeWideCombinableDomainsSortOrder DOMAINS_SORT_ORDER_DEFAULT = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
181 final static private String DOMAIN_COUNT_SORT_ALPHA = "alpha";
182 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT = "dom";
183 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT = "prot";
184 final static private String DOMAIN_COUNT_SORT_COMBINATIONS_COUNT = "comb";
185 final static private String CUTOFF_SCORE_FILE_OPTION = "cos";
186 final static private String NOT_IGNORE_DUFS_OPTION = "dufs";
187 final static private String MAX_E_VALUE_OPTION = "e";
188 final static private String MAX_ALLOWED_OVERLAP_OPTION = "mo";
189 final static private String NO_ENGULFING_OVERLAP_OPTION = "no_eo";
190 final static private String IGNORE_COMBINATION_WITH_SAME_OPTION = "ignore_self_comb";
191 final static private String PAIRWISE_DOMAIN_COMPARISONS_PREFIX = "pwc_";
192 final static private String PAIRWISE_DOMAIN_COMPARISONS_OPTION = "pwc";
193 final static private String OUTPUT_FILE_OPTION = "o";
194 final static private String PFAM_TO_GO_FILE_USE_OPTION = "p2g";
195 final static private String GO_OBO_FILE_USE_OPTION = "obo";
196 final static private String GO_NAMESPACE_LIMIT_OPTION = "go_namespace";
197 final static private String GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION = "molecular_function";
198 final static private String GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS = "biological_process";
199 final static private String GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT = "cellular_component";
200 final static private String SECONDARY_FEATURES_PARSIMONY_MAP_FILE = "secondary";
201 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED = "simple_tab";
202 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML = "simple_html";
203 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML = "detailed_html";
204 final static private String DOMAIN_SIMILARITY_PRINT_OPTION = "ds_output";
205 private static final PRINT_OPTION DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT = PrintableDomainSimilarity.PRINT_OPTION.HTML;
206 final static private String IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION = "ignore_singlet_domains";
207 final static private String IGNORE_VIRAL_IDS = "ignore_viral_ids";
208 final static private boolean IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT = false;
209 final static private String IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION = "ignore_species_specific_domains";
210 final static private boolean IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT = false;
211 final static private String MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score.pwd";
212 final static private String MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains.pwd";
213 final static private String MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations.pwd";
214 final static private String NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score_NJ"
215 + ForesterConstants.PHYLO_XML_SUFFIX;
216 final static private String NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains_NJ"
217 + ForesterConstants.PHYLO_XML_SUFFIX;
218 final static private String NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations_NJ"
219 + ForesterConstants.PHYLO_XML_SUFFIX;
220 final static private String JACKNIFE_OPTION = "jack";
221 final static private String JACKNIFE_RANDOM_SEED_OPTION = "seed";
222 final static private String JACKNIFE_RATIO_OPTION = "jack_ratio";
223 private static final int JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT = 100;
224 final static private long JACKNIFE_RANDOM_SEED_DEFAULT = 19;
225 final static private double JACKNIFE_RATIO_DEFAULT = 0.5;
226 final static private String FILTER_POSITIVE_OPTION = "pos_filter";
227 final static private String FILTER_NEGATIVE_OPTION = "neg_filter";
228 final static private String FILTER_NEGATIVE_DOMAINS_OPTION = "neg_dom_filter";
229 final static private String INPUT_GENOMES_FILE_OPTION = "genomes";
230 final static private String INPUT_SPECIES_TREE_OPTION = "species_tree";
231 final static private String SEQ_EXTRACT_OPTION = "prot_extract";
232 final static private String PRG_VERSION = "2.270";
233 final static private String PRG_DATE = "130628";
234 final static private String E_MAIL = "czmasek@burnham.org";
235 final static private String WWW = "www.phylosoft.org/forester/applications/surfacing";
236 final static private boolean IGNORE_DUFS_DEFAULT = true;
237 final static private boolean IGNORE_COMBINATION_WITH_SAME_DEFAULLT = false;
238 final static private double MAX_E_VALUE_DEFAULT = -1;
239 final static private int MAX_ALLOWED_OVERLAP_DEFAULT = -1;
240 private static final String RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION = "random_seed";
241 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS = "consider_bdc_direction";
242 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY = "consider_bdc_adj";
243 private static final String SEQ_EXTRACT_SUFFIX = ".prot";
244 private static final String PLUS_MINUS_ANALYSIS_OPTION = "plus_minus";
245 private static final String PLUS_MINUS_DOM_SUFFIX = "_plus_minus_dom.txt";
246 private static final String PLUS_MINUS_DOM_SUFFIX_HTML = "_plus_minus_dom.html";
247 private static final String PLUS_MINUS_DC_SUFFIX_HTML = "_plus_minus_dc.html";
248 private static final int PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT = 0;
249 private static final double PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT = 1.0;
250 private static final String PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_all.txt";
251 private static final String PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_passing.txt";
252 private static final String OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS = "all_prot";
253 final static private String OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION = "all_prot_e";
254 private static final boolean VERBOSE = false;
255 private static final String OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_gains_counts";
256 private static final String OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_losses_counts";
257 private static final String DOMAIN_LENGTHS_ANALYSIS_SUFFIX = "_domain_lengths_analysis";
258 private static final boolean PERFORM_DOMAIN_LENGTH_ANALYSIS = true;
259 public static final String ALL_PFAMS_ENCOUNTERED_SUFFIX = "_all_encountered_pfams";
260 public static final String ALL_PFAMS_ENCOUNTERED_WITH_GO_ANNOTATION_SUFFIX = "_all_encountered_pfams_with_go_annotation";
261 public static final String ENCOUNTERED_PFAMS_SUMMARY_SUFFIX = "_encountered_pfams_summary";
262 public static final String ALL_PFAMS_GAINED_AS_DOMAINS_SUFFIX = "_all_pfams_gained_as_domains";
263 public static final String ALL_PFAMS_LOST_AS_DOMAINS_SUFFIX = "_all_pfams_lost_as_domains";
264 public static final String ALL_PFAMS_GAINED_AS_DC_SUFFIX = "_all_pfams_gained_as_dc";
265 public static final String ALL_PFAMS_LOST_AS_DC_SUFFIX = "_all_pfams_lost_as_dc";
266 public static final String BASE_DIRECTORY_PER_NODE_DOMAIN_GAIN_LOSS_FILES = "PER_NODE_EVENTS";
267 public static final String BASE_DIRECTORY_PER_SUBTREE_DOMAIN_GAIN_LOSS_FILES = "PER_SUBTREE_EVENTS";
268 public static final String D_PROMISCUITY_FILE_SUFFIX = "_domain_promiscuities";
269 private static final String LOG_FILE_SUFFIX = "_log.txt";
270 private static final String DATA_FILE_SUFFIX = "_domain_combination_data.txt";
271 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";
272 private static final String WRITE_TO_NEXUS_OPTION = "nexus";
273 private static final INDIVIDUAL_SCORE_CUTOFF INDIVIDUAL_SCORE_CUTOFF_DEFAULT = INDIVIDUAL_SCORE_CUTOFF.FULL_SEQUENCE; //TODO look at me! change?
274 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts.txt";
275 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists.txt";
276 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping.txt";
277 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_UNIQUE_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping_unique.txt";
278 public static final String LIMIT_SPEC_FOR_PROT_EX = null; // e.g. "HUMAN"; set to null for not using this feature (default).
279 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH_MAPPED = "_dc_MAPPED_secondary_features_fitch"
280 + ForesterConstants.PHYLO_XML_SUFFIX;
281 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts_MAPPED.txt";
282 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_MAPPED.txt";
283 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping_MAPPED.txt";
284 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_MAPPED_OUTPUT_UNIQUE_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping_unique_MAPPED.txt";
285 private static final boolean PERFORM_DC_REGAIN_PROTEINS_STATS = true;
286 private static final boolean DA_ANALYSIS = false;
288 private static void checkWriteabilityForPairwiseComparisons( final PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option,
289 final String[][] input_file_properties,
290 final String automated_pairwise_comparison_suffix,
291 final File outdir ) {
292 for( int i = 0; i < input_file_properties.length; ++i ) {
293 for( int j = 0; j < i; ++j ) {
294 final String species_i = input_file_properties[ i ][ 1 ];
295 final String species_j = input_file_properties[ j ][ 1 ];
296 String pairwise_similarities_output_file_str = PAIRWISE_DOMAIN_COMPARISONS_PREFIX + species_i + "_"
297 + species_j + automated_pairwise_comparison_suffix;
298 switch ( domain_similarity_print_option ) {
300 if ( !pairwise_similarities_output_file_str.endsWith( ".html" ) ) {
301 pairwise_similarities_output_file_str += ".html";
305 final String error = ForesterUtil
306 .isWritableFile( new File( outdir == null ? pairwise_similarities_output_file_str : outdir
307 + ForesterUtil.FILE_SEPARATOR + pairwise_similarities_output_file_str ) );
308 if ( !ForesterUtil.isEmpty( error ) ) {
309 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
315 private static StringBuilder createParametersAsString( final boolean ignore_dufs,
316 final double e_value_max,
317 final int max_allowed_overlap,
318 final boolean no_engulfing_overlaps,
319 final File cutoff_scores_file,
320 final BinaryDomainCombination.DomainCombinationType dc_type ) {
321 final StringBuilder parameters_sb = new StringBuilder();
322 parameters_sb.append( "E-value: " + e_value_max );
323 if ( cutoff_scores_file != null ) {
324 parameters_sb.append( ", Cutoff-scores-file: " + cutoff_scores_file );
327 parameters_sb.append( ", Cutoff-scores-file: not-set" );
329 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
330 parameters_sb.append( ", Max-overlap: " + max_allowed_overlap );
333 parameters_sb.append( ", Max-overlap: not-set" );
335 if ( no_engulfing_overlaps ) {
336 parameters_sb.append( ", Engulfing-overlaps: not-allowed" );
339 parameters_sb.append( ", Engulfing-overlaps: allowed" );
342 parameters_sb.append( ", Ignore-dufs: true" );
345 parameters_sb.append( ", Ignore-dufs: false" );
347 parameters_sb.append( ", DC type (if applicable): " + dc_type );
348 return parameters_sb;
352 * Warning: This side-effects 'all_bin_domain_combinations_encountered'!
356 * @param all_bin_domain_combinations_changed
357 * @param sum_of_all_domains_encountered
358 * @param all_bin_domain_combinations_encountered
359 * @param is_gains_analysis
360 * @param protein_length_stats_by_dc
361 * @throws IOException
363 private static void executeFitchGainsAnalysis( final File output_file,
364 final List<BinaryDomainCombination> all_bin_domain_combinations_changed,
365 final int sum_of_all_domains_encountered,
366 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered,
367 final boolean is_gains_analysis ) throws IOException {
368 SurfacingUtil.checkForOutputFileWriteability( output_file );
369 final Writer out = ForesterUtil.createBufferedWriter( output_file );
370 final SortedMap<Object, Integer> bdc_to_counts = ForesterUtil
371 .listToSortedCountsMap( all_bin_domain_combinations_changed );
372 final SortedSet<DomainId> all_domains_in_combination_changed_more_than_once = new TreeSet<DomainId>();
373 final SortedSet<DomainId> all_domains_in_combination_changed_only_once = new TreeSet<DomainId>();
376 for( final Object bdc_object : bdc_to_counts.keySet() ) {
377 final BinaryDomainCombination bdc = ( BinaryDomainCombination ) bdc_object;
378 final int count = bdc_to_counts.get( bdc_object );
380 ForesterUtil.unexpectedFatalError( PRG_NAME, "count < 1 " );
382 out.write( bdc + "\t" + count + ForesterUtil.LINE_SEPARATOR );
384 all_domains_in_combination_changed_more_than_once.add( bdc.getId0() );
385 all_domains_in_combination_changed_more_than_once.add( bdc.getId1() );
388 else if ( count == 1 ) {
389 all_domains_in_combination_changed_only_once.add( bdc.getId0() );
390 all_domains_in_combination_changed_only_once.add( bdc.getId1() );
394 final int all = all_bin_domain_combinations_encountered.size();
396 if ( !is_gains_analysis ) {
397 all_bin_domain_combinations_encountered.removeAll( all_bin_domain_combinations_changed );
398 never_lost = all_bin_domain_combinations_encountered.size();
399 for( final BinaryDomainCombination bdc : all_bin_domain_combinations_encountered ) {
400 out.write( bdc + "\t" + "0" + ForesterUtil.LINE_SEPARATOR );
403 if ( is_gains_analysis ) {
404 out.write( "Sum of all distinct domain combinations appearing once : " + one
405 + ForesterUtil.LINE_SEPARATOR );
406 out.write( "Sum of all distinct domain combinations appearing more than once : " + above_one
407 + ForesterUtil.LINE_SEPARATOR );
408 out.write( "Sum of all distinct domains in combinations apppearing only once : "
409 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
410 out.write( "Sum of all distinct domains in combinations apppearing more than once: "
411 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
414 out.write( "Sum of all distinct domain combinations never lost : " + never_lost
415 + ForesterUtil.LINE_SEPARATOR );
416 out.write( "Sum of all distinct domain combinations lost once : " + one
417 + ForesterUtil.LINE_SEPARATOR );
418 out.write( "Sum of all distinct domain combinations lost more than once : " + above_one
419 + ForesterUtil.LINE_SEPARATOR );
420 out.write( "Sum of all distinct domains in combinations lost only once : "
421 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
422 out.write( "Sum of all distinct domains in combinations lost more than once: "
423 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
425 out.write( "All binary combinations : " + all
426 + ForesterUtil.LINE_SEPARATOR );
427 out.write( "All domains : "
428 + sum_of_all_domains_encountered );
430 ForesterUtil.programMessage( surfacing.PRG_NAME,
431 "Wrote fitch domain combination dynamics counts analysis to \"" + output_file
435 private static void executePlusMinusAnalysis( final File output_file,
436 final List<String> plus_minus_analysis_high_copy_base,
437 final List<String> plus_minus_analysis_high_copy_target,
438 final List<String> plus_minus_analysis_low_copy,
439 final List<GenomeWideCombinableDomains> gwcd_list,
440 final SortedMap<Species, List<Protein>> protein_lists_per_species,
441 final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
442 final Map<GoId, GoTerm> go_id_to_term_map,
443 final List<Object> plus_minus_analysis_numbers ) {
444 final Set<String> all_spec = new HashSet<String>();
445 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
446 all_spec.add( gwcd.getSpecies().getSpeciesId() );
448 final File html_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX_HTML );
449 final File plain_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX );
450 final File html_out_dc = new File( output_file + PLUS_MINUS_DC_SUFFIX_HTML );
451 final File all_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX );
452 final File passing_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX );
453 final File proteins_file_base = new File( output_file + "" );
454 final int min_diff = ( ( Integer ) plus_minus_analysis_numbers.get( 0 ) ).intValue();
455 final double factor = ( ( Double ) plus_minus_analysis_numbers.get( 1 ) ).doubleValue();
457 DomainCountsDifferenceUtil.calculateCopyNumberDifferences( gwcd_list,
458 protein_lists_per_species,
459 plus_minus_analysis_high_copy_base,
460 plus_minus_analysis_high_copy_target,
461 plus_minus_analysis_low_copy,
467 domain_id_to_go_ids_map,
469 all_domains_go_ids_out_dom,
470 passing_domains_go_ids_out_dom,
471 proteins_file_base );
473 catch ( final IOException e ) {
474 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
476 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
477 + html_out_dom + "\"" );
478 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
479 + plain_out_dom + "\"" );
480 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \"" + html_out_dc
482 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based passing GO ids to \""
483 + passing_domains_go_ids_out_dom + "\"" );
484 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based all GO ids to \""
485 + all_domains_go_ids_out_dom + "\"" );
488 private static Phylogeny[] getIntrees( final File[] intree_files,
489 final int number_of_genomes,
490 final String[][] input_file_properties ) {
491 final Phylogeny[] intrees = new Phylogeny[ intree_files.length ];
493 for( final File intree_file : intree_files ) {
494 Phylogeny intree = null;
495 final String error = ForesterUtil.isReadableFile( intree_file );
496 if ( !ForesterUtil.isEmpty( error ) ) {
497 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read input tree file [" + intree_file + "]: "
501 final Phylogeny[] p_array = ParserBasedPhylogenyFactory.getInstance()
502 .create( intree_file, ParserUtils.createParserDependingOnFileType( intree_file, true ) );
503 if ( p_array.length < 1 ) {
504 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
505 + "] does not contain any phylogeny in phyloXML format" );
507 else if ( p_array.length > 1 ) {
508 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
509 + "] contains more than one phylogeny in phyloXML format" );
511 intree = p_array[ 0 ];
513 catch ( final Exception e ) {
514 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read input tree from file [" + intree_file
517 if ( ( intree == null ) || intree.isEmpty() ) {
518 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" );
520 if ( !intree.isRooted() ) {
521 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is not rooted" );
523 if ( intree.getNumberOfExternalNodes() < number_of_genomes ) {
524 ForesterUtil.fatalError( surfacing.PRG_NAME,
525 "number of external nodes [" + intree.getNumberOfExternalNodes()
526 + "] of input tree [" + intree_file
527 + "] is smaller than the number of genomes the be analyzed ["
528 + number_of_genomes + "]" );
530 final StringBuilder parent_names = new StringBuilder();
531 final int nodes_lacking_name = SurfacingUtil.getNumberOfNodesLackingName( intree, parent_names );
532 if ( nodes_lacking_name > 0 ) {
533 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] has "
534 + nodes_lacking_name + " node(s) lacking a name [parent names:" + parent_names + "]" );
536 preparePhylogenyForParsimonyAnalyses( intree, input_file_properties );
537 if ( !intree.isCompletelyBinary() ) {
538 ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "input tree [" + intree_file
539 + "] is not completely binary" );
541 intrees[ i++ ] = intree;
546 private static void log( final String msg, final Writer w ) {
549 w.write( ForesterUtil.LINE_SEPARATOR );
551 catch ( final IOException e ) {
552 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
556 public static void main( final String args[] ) {
557 final long start_time = new Date().getTime();
558 // final StringBuffer log = new StringBuffer();
559 final StringBuilder html_desc = new StringBuilder();
560 ForesterUtil.printProgramInformation( surfacing.PRG_NAME,
561 surfacing.PRG_VERSION,
565 final String nl = ForesterUtil.LINE_SEPARATOR;
566 html_desc.append( "<table>" + nl );
567 html_desc.append( "<tr><td>Produced by:</td><td>" + surfacing.PRG_NAME + "</td></tr>" + nl );
568 html_desc.append( "<tr><td>Version:</td><td>" + surfacing.PRG_VERSION + "</td></tr>" + nl );
569 html_desc.append( "<tr><td>Release Date:</td><td>" + surfacing.PRG_DATE + "</td></tr>" + nl );
570 html_desc.append( "<tr><td>Contact:</td><td>" + surfacing.E_MAIL + "</td></tr>" + nl );
571 html_desc.append( "<tr><td>WWW:</td><td>" + surfacing.WWW + "</td></tr>" + nl );
572 CommandLineArguments cla = null;
574 cla = new CommandLineArguments( args );
576 catch ( final Exception e ) {
577 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
579 if ( cla.isOptionSet( surfacing.HELP_OPTION_1 ) || cla.isOptionSet( surfacing.HELP_OPTION_2 ) ) {
580 surfacing.printHelp();
583 if ( ( args.length < 1 ) ) {
584 surfacing.printHelp();
587 final List<String> allowed_options = new ArrayList<String>();
588 allowed_options.add( surfacing.NOT_IGNORE_DUFS_OPTION );
589 allowed_options.add( surfacing.MAX_E_VALUE_OPTION );
590 allowed_options.add( surfacing.DETAILEDNESS_OPTION );
591 allowed_options.add( surfacing.OUTPUT_FILE_OPTION );
592 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_OPTION );
593 allowed_options.add( surfacing.SPECIES_MATRIX_OPTION );
594 allowed_options.add( surfacing.SCORING_OPTION );
595 allowed_options.add( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
596 allowed_options.add( surfacing.NO_ENGULFING_OVERLAP_OPTION );
597 allowed_options.add( surfacing.DOMAIN_COUNT_SORT_OPTION );
598 allowed_options.add( surfacing.CUTOFF_SCORE_FILE_OPTION );
599 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION );
600 allowed_options.add( surfacing.OUTPUT_DIR_OPTION );
601 allowed_options.add( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION );
602 allowed_options.add( surfacing.PFAM_TO_GO_FILE_USE_OPTION );
603 allowed_options.add( surfacing.GO_OBO_FILE_USE_OPTION );
604 allowed_options.add( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION );
605 allowed_options.add( surfacing.GO_NAMESPACE_LIMIT_OPTION );
606 allowed_options.add( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
607 allowed_options.add( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION );
608 allowed_options.add( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS );
609 allowed_options.add( JACKNIFE_OPTION );
610 allowed_options.add( JACKNIFE_RANDOM_SEED_OPTION );
611 allowed_options.add( JACKNIFE_RATIO_OPTION );
612 allowed_options.add( INPUT_SPECIES_TREE_OPTION );
613 allowed_options.add( FILTER_POSITIVE_OPTION );
614 allowed_options.add( FILTER_NEGATIVE_OPTION );
615 allowed_options.add( INPUT_GENOMES_FILE_OPTION );
616 allowed_options.add( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
617 allowed_options.add( FILTER_NEGATIVE_DOMAINS_OPTION );
618 allowed_options.add( IGNORE_VIRAL_IDS );
619 allowed_options.add( SEQ_EXTRACT_OPTION );
620 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
621 allowed_options.add( SECONDARY_FEATURES_PARSIMONY_MAP_FILE );
622 allowed_options.add( PLUS_MINUS_ANALYSIS_OPTION );
623 allowed_options.add( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS );
624 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS );
625 allowed_options.add( CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY );
626 allowed_options.add( WRITE_TO_NEXUS_OPTION );
627 boolean ignore_dufs = surfacing.IGNORE_DUFS_DEFAULT;
628 boolean ignore_combination_with_same = surfacing.IGNORE_COMBINATION_WITH_SAME_DEFAULLT;
629 double e_value_max = surfacing.MAX_E_VALUE_DEFAULT;
630 int max_allowed_overlap = surfacing.MAX_ALLOWED_OVERLAP_DEFAULT;
631 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
632 if ( dissallowed_options.length() > 0 ) {
633 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown option(s): " + dissallowed_options );
635 boolean write_to_nexus = false;
636 if ( cla.isOptionSet( WRITE_TO_NEXUS_OPTION ) ) {
637 write_to_nexus = true;
639 boolean output_binary_domain_combinationsfor_graph_analysis = false;
640 if ( cla.isOptionSet( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS ) ) {
641 output_binary_domain_combinationsfor_graph_analysis = true;
643 if ( cla.isOptionSet( surfacing.MAX_E_VALUE_OPTION ) ) {
645 e_value_max = cla.getOptionValueAsDouble( surfacing.MAX_E_VALUE_OPTION );
647 catch ( final Exception e ) {
648 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for E-value maximum" );
651 if ( cla.isOptionSet( surfacing.MAX_ALLOWED_OVERLAP_OPTION ) ) {
653 max_allowed_overlap = cla.getOptionValueAsInt( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
655 catch ( final Exception e ) {
656 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for maximal allowed domain overlap" );
659 boolean no_engulfing_overlaps = false;
660 if ( cla.isOptionSet( surfacing.NO_ENGULFING_OVERLAP_OPTION ) ) {
661 no_engulfing_overlaps = true;
663 boolean ignore_virus_like_ids = false;
664 if ( cla.isOptionSet( surfacing.IGNORE_VIRAL_IDS ) ) {
665 ignore_virus_like_ids = true;
667 if ( cla.isOptionSet( surfacing.NOT_IGNORE_DUFS_OPTION ) ) {
670 if ( cla.isOptionSet( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION ) ) {
671 ignore_combination_with_same = true;
673 boolean ignore_domains_without_combs_in_all_spec = IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT;
674 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION ) ) {
675 ignore_domains_without_combs_in_all_spec = true;
677 boolean ignore_species_specific_domains = IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT;
678 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION ) ) {
679 ignore_species_specific_domains = true;
681 File output_file = null;
682 if ( cla.isOptionSet( surfacing.OUTPUT_FILE_OPTION ) ) {
683 if ( !cla.isOptionValueSet( surfacing.OUTPUT_FILE_OPTION ) ) {
684 ForesterUtil.fatalError( surfacing.PRG_NAME,
685 "no value for domain combinations similarities output file: -"
686 + surfacing.OUTPUT_FILE_OPTION + "=<file>" );
688 output_file = new File( cla.getOptionValue( surfacing.OUTPUT_FILE_OPTION ) );
689 SurfacingUtil.checkForOutputFileWriteability( output_file );
691 File cutoff_scores_file = null;
692 Map<String, Double> individual_score_cutoffs = null;
693 if ( cla.isOptionSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
694 if ( !cla.isOptionValueSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
695 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for individual domain score cutoffs file: -"
696 + surfacing.CUTOFF_SCORE_FILE_OPTION + "=<file>" );
698 cutoff_scores_file = new File( cla.getOptionValue( surfacing.CUTOFF_SCORE_FILE_OPTION ) );
699 final String error = ForesterUtil.isReadableFile( cutoff_scores_file );
700 if ( !ForesterUtil.isEmpty( error ) ) {
701 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read individual domain score cutoffs file: "
705 final BasicTable<String> scores_table = BasicTableParser.parse( cutoff_scores_file, ' ' );
706 individual_score_cutoffs = scores_table.getColumnsAsMapDouble( 0, 1 );
708 catch ( final IOException e ) {
709 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from individual score cutoffs file: " + e );
712 BinaryDomainCombination.DomainCombinationType dc_type = BinaryDomainCombination.DomainCombinationType.BASIC;
713 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS ) ) {
714 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED;
716 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY ) ) {
717 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT;
720 if ( cla.isOptionSet( surfacing.OUTPUT_DIR_OPTION ) ) {
721 if ( !cla.isOptionValueSet( surfacing.OUTPUT_DIR_OPTION ) ) {
722 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for output directory: -"
723 + surfacing.OUTPUT_DIR_OPTION + "=<dir>" );
725 out_dir = new File( cla.getOptionValue( surfacing.OUTPUT_DIR_OPTION ) );
726 if ( out_dir.exists() && ( out_dir.listFiles().length > 0 ) ) {
727 ForesterUtil.fatalError( surfacing.PRG_NAME, "\"" + out_dir + "\" aready exists and is not empty" );
729 if ( !out_dir.exists() ) {
730 final boolean success = out_dir.mkdir();
731 if ( !success || !out_dir.exists() ) {
732 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to create \"" + out_dir + "\"" );
735 if ( !out_dir.canWrite() ) {
736 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot write to \"" + out_dir + "\"" );
739 File positive_filter_file = null;
740 File negative_filter_file = null;
741 File negative_domains_filter_file = null;
742 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) && cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
743 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use both negative and positive protein filter" );
745 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION )
746 && ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) || cla
747 .isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) ) {
749 .fatalError( surfacing.PRG_NAME,
750 "attempt to use both negative or positive protein filter together wirh a negative domains filter" );
752 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
753 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
754 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative filter: -"
755 + surfacing.FILTER_NEGATIVE_OPTION + "=<file>" );
757 negative_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_OPTION ) );
758 final String msg = ForesterUtil.isReadableFile( negative_filter_file );
759 if ( !ForesterUtil.isEmpty( msg ) ) {
760 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_filter_file + "\": "
764 else if ( cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
765 if ( !cla.isOptionValueSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
766 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for positive filter: -"
767 + surfacing.FILTER_POSITIVE_OPTION + "=<file>" );
769 positive_filter_file = new File( cla.getOptionValue( surfacing.FILTER_POSITIVE_OPTION ) );
770 final String msg = ForesterUtil.isReadableFile( positive_filter_file );
771 if ( !ForesterUtil.isEmpty( msg ) ) {
772 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + positive_filter_file + "\": "
776 else if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
777 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
778 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative domains filter: -"
779 + surfacing.FILTER_NEGATIVE_DOMAINS_OPTION + "=<file>" );
781 negative_domains_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) );
782 final String msg = ForesterUtil.isReadableFile( negative_domains_filter_file );
783 if ( !ForesterUtil.isEmpty( msg ) ) {
784 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_domains_filter_file
788 final List<String> plus_minus_analysis_high_copy_base_species = new ArrayList<String>();
789 final List<String> plus_minus_analysis_high_copy_target_species = new ArrayList<String>();
790 final List<String> plus_minus_analysis_high_low_copy_species = new ArrayList<String>();
791 final List<Object> plus_minus_analysis_numbers = new ArrayList<Object>();
792 processPlusMinusAnalysisOption( cla,
793 plus_minus_analysis_high_copy_base_species,
794 plus_minus_analysis_high_copy_target_species,
795 plus_minus_analysis_high_low_copy_species,
796 plus_minus_analysis_numbers );
797 File input_genomes_file = null;
798 if ( cla.isOptionSet( surfacing.INPUT_GENOMES_FILE_OPTION ) ) {
799 if ( !cla.isOptionValueSet( surfacing.INPUT_GENOMES_FILE_OPTION ) ) {
800 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input genomes file: -"
801 + surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>" );
803 input_genomes_file = new File( cla.getOptionValue( surfacing.INPUT_GENOMES_FILE_OPTION ) );
804 final String msg = ForesterUtil.isReadableFile( input_genomes_file );
805 if ( !ForesterUtil.isEmpty( msg ) ) {
807 .fatalError( surfacing.PRG_NAME, "can not read from \"" + input_genomes_file + "\": " + msg );
811 ForesterUtil.fatalError( surfacing.PRG_NAME, "no input genomes file given: "
812 + surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>" );
814 DomainSimilarity.DomainSimilarityScoring scoring = SCORING_DEFAULT;
815 if ( cla.isOptionSet( surfacing.SCORING_OPTION ) ) {
816 if ( !cla.isOptionValueSet( surfacing.SCORING_OPTION ) ) {
817 ForesterUtil.fatalError( surfacing.PRG_NAME,
818 "no value for scoring method for domain combinations similarity calculation: -"
819 + surfacing.SCORING_OPTION + "=<"
820 + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
821 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|"
822 + surfacing.SCORING_COMBINATION_BASED + ">\"" );
824 final String scoring_str = cla.getOptionValue( surfacing.SCORING_OPTION );
825 if ( scoring_str.equals( surfacing.SCORING_DOMAIN_COUNT_BASED ) ) {
826 scoring = DomainSimilarity.DomainSimilarityScoring.DOMAINS;
828 else if ( scoring_str.equals( surfacing.SCORING_COMBINATION_BASED ) ) {
829 scoring = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
831 else if ( scoring_str.equals( surfacing.SCORING_PROTEIN_COUNT_BASED ) ) {
832 scoring = DomainSimilarity.DomainSimilarityScoring.PROTEINS;
835 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + scoring_str
836 + "\" for scoring method for domain combinations similarity calculation: \"-"
837 + surfacing.SCORING_OPTION + "=<" + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
838 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|" + surfacing.SCORING_COMBINATION_BASED + ">\"" );
841 boolean sort_by_species_count_first = false;
842 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION ) ) {
843 sort_by_species_count_first = true;
845 boolean species_matrix = false;
846 if ( cla.isOptionSet( surfacing.SPECIES_MATRIX_OPTION ) ) {
847 species_matrix = true;
849 boolean output_protein_lists_for_all_domains = false;
850 double output_list_of_all_proteins_per_domain_e_value_max = -1;
851 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS ) ) {
852 output_protein_lists_for_all_domains = true;
853 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION ) ) {
855 output_list_of_all_proteins_per_domain_e_value_max = cla
856 .getOptionValueAsDouble( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
858 catch ( final Exception e ) {
859 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for per domain E-value maximum" );
863 Detailedness detailedness = DETAILEDNESS_DEFAULT;
864 if ( cla.isOptionSet( surfacing.DETAILEDNESS_OPTION ) ) {
865 if ( !cla.isOptionValueSet( surfacing.DETAILEDNESS_OPTION ) ) {
866 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for -" + surfacing.DETAILEDNESS_OPTION + "=<"
867 + surfacing.DETAILEDNESS_BASIC + "|" + surfacing.DETAILEDNESS_LIST_IDS + "|"
868 + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
870 final String detness = cla.getOptionValue( surfacing.DETAILEDNESS_OPTION ).toLowerCase();
871 if ( detness.equals( surfacing.DETAILEDNESS_BASIC ) ) {
872 detailedness = DomainSimilarityCalculator.Detailedness.BASIC;
874 else if ( detness.equals( surfacing.DETAILEDNESS_LIST_IDS ) ) {
875 detailedness = DomainSimilarityCalculator.Detailedness.LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES;
877 else if ( detness.equals( surfacing.DETAILEDNESS_PUNCTILIOUS ) ) {
878 detailedness = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
881 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + detness + "\" for detailedness: \"-"
882 + surfacing.DETAILEDNESS_OPTION + "=<" + surfacing.DETAILEDNESS_BASIC + "|"
883 + surfacing.DETAILEDNESS_LIST_IDS + "|" + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
886 String automated_pairwise_comparison_suffix = null;
887 boolean perform_pwc = false;
888 boolean write_pwc_files = false;
889 if ( cla.isOptionSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
891 if ( !cla.isOptionValueSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
892 write_pwc_files = false;
895 write_pwc_files = true;
896 automated_pairwise_comparison_suffix = "_"
897 + cla.getOptionValue( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
900 String query_domain_ids = null;
901 if ( cla.isOptionSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
902 if ( !cla.isOptionValueSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
904 .fatalError( surfacing.PRG_NAME,
905 "no domain ids given for sequences with given domains to be extracted : -"
906 + surfacing.SEQ_EXTRACT_OPTION
907 + "=<ordered domain sequences, domain ids separated by '~', sequences separated by '#'>" );
909 query_domain_ids = cla.getOptionValue( surfacing.SEQ_EXTRACT_OPTION );
911 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field = DOMAIN_SORT_FILD_DEFAULT;
912 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field_for_automated_pwc = DOMAIN_SORT_FILD_DEFAULT;
913 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
914 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
915 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for domain combinations similarities sorting: -"
916 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
917 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
918 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
919 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
920 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|"
921 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
924 final String sort_str = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ).toLowerCase();
925 if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ALPHA ) ) {
926 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
927 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
929 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MAX ) ) {
930 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX;
931 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
933 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MIN ) ) {
934 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MIN;
935 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
937 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MEAN ) ) {
938 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MEAN;
939 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MEAN;
941 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT ) ) {
942 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SPECIES_COUNT;
943 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
945 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SD ) ) {
946 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SD;
947 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
949 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_DIFF ) ) {
950 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
951 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
953 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF ) ) {
954 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
955 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
957 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF ) ) {
958 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
959 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
962 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort_str
963 + "\" for domain combinations similarities sorting: \"-"
964 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
965 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
966 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
967 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
968 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|" + "|"
969 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
973 PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option = DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT;
974 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
975 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
976 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for print option: -"
977 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
978 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
979 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
981 final String sort = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ).toLowerCase();
982 if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML ) ) {
983 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.HTML;
985 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML ) ) {
986 ForesterUtil.fatalError( surfacing.PRG_NAME, "simple HTML output not implemented yet :(" );
988 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED ) ) {
989 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.SIMPLE_TAB_DELIMITED;
992 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort + "\" for print option: -"
993 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
994 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
995 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
998 GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order = DOMAINS_SORT_ORDER_DEFAULT;
999 if ( cla.isOptionSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
1000 if ( !cla.isOptionValueSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
1001 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for sorting of domain counts: -"
1002 + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<" + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|"
1003 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1004 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1005 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1007 final String sort = cla.getOptionValue( surfacing.DOMAIN_COUNT_SORT_OPTION ).toLowerCase();
1008 if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_ALPHA ) ) {
1009 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
1011 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT ) ) {
1012 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_COUNT;
1014 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT ) ) {
1015 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_PROTEINS_COUNT;
1017 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT ) ) {
1018 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.COMBINATIONS_COUNT;
1021 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort
1022 + "\" for sorting of domain counts: \"-" + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<"
1023 + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|" + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1024 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1025 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1028 final String[][] input_file_properties = processInputGenomesFile( input_genomes_file );
1029 final int number_of_genomes = input_file_properties.length;
1030 if ( number_of_genomes < 2 ) {
1031 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot analyze less than two files" );
1033 if ( ( number_of_genomes < 3 ) && perform_pwc ) {
1034 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use : -"
1035 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1036 + "=<suffix> to turn on pairwise analyses with less than three input files" );
1038 checkWriteabilityForPairwiseComparisons( domain_similarity_print_option,
1039 input_file_properties,
1040 automated_pairwise_comparison_suffix,
1042 for( int i = 0; i < number_of_genomes; i++ ) {
1043 File dcc_outfile = new File( input_file_properties[ i ][ 1 ]
1044 + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
1045 if ( out_dir != null ) {
1046 dcc_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + dcc_outfile );
1048 SurfacingUtil.checkForOutputFileWriteability( dcc_outfile );
1050 File pfam_to_go_file = null;
1051 Map<DomainId, List<GoId>> domain_id_to_go_ids_map = null;
1052 int domain_id_to_go_ids_count = 0;
1053 if ( cla.isOptionSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1054 if ( !cla.isOptionValueSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1055 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for Pfam to GO mapping file: -"
1056 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>" );
1058 pfam_to_go_file = new File( cla.getOptionValue( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) );
1059 final String error = ForesterUtil.isReadableFile( pfam_to_go_file );
1060 if ( !ForesterUtil.isEmpty( error ) ) {
1061 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read Pfam to GO mapping file: " + error );
1064 final PfamToGoParser parser = new PfamToGoParser( pfam_to_go_file );
1065 final List<PfamToGoMapping> pfam_to_go_mappings = parser.parse();
1066 domain_id_to_go_ids_map = SurfacingUtil.createDomainIdToGoIdMap( pfam_to_go_mappings );
1067 if ( parser.getMappingCount() < domain_id_to_go_ids_map.size() ) {
1068 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME,
1069 "parser.getMappingCount() < domain_id_to_go_ids_map.size()" );
1071 domain_id_to_go_ids_count = parser.getMappingCount();
1073 catch ( final IOException e ) {
1074 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from Pfam to GO mapping file: " + e );
1077 File go_obo_file = null;
1078 List<GoTerm> go_terms = null;
1079 if ( cla.isOptionSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1080 if ( !cla.isOptionValueSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1081 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO OBO file: -"
1082 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>" );
1084 if ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) {
1085 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO OBO file (-"
1086 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>) without Pfam to GO mapping file ("
1087 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1089 go_obo_file = new File( cla.getOptionValue( surfacing.GO_OBO_FILE_USE_OPTION ) );
1090 final String error = ForesterUtil.isReadableFile( go_obo_file );
1091 if ( !ForesterUtil.isEmpty( error ) ) {
1092 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read GO OBO file: " + error );
1095 final OBOparser parser = new OBOparser( go_obo_file, OBOparser.ReturnType.BASIC_GO_TERM );
1096 go_terms = parser.parse();
1097 if ( parser.getGoTermCount() != go_terms.size() ) {
1099 .unexpectedFatalError( surfacing.PRG_NAME, "parser.getGoTermCount() != go_terms.size()" );
1102 catch ( final IOException e ) {
1103 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from GO OBO file: " + e );
1106 Map<GoId, GoTerm> go_id_to_term_map = null;
1107 if ( ( ( domain_id_to_go_ids_map != null ) && ( domain_id_to_go_ids_map.size() > 0 ) )
1108 && ( ( go_terms != null ) && ( go_terms.size() > 0 ) ) ) {
1109 go_id_to_term_map = GoUtils.createGoIdToGoTermMap( go_terms );
1111 GoNameSpace go_namespace_limit = null;
1112 if ( cla.isOptionSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1113 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1114 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO namespace limit (-"
1115 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<namespace>) without Pfam to GO mapping file ("
1116 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>) and GO OBO file (-"
1117 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1119 if ( !cla.isOptionValueSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1120 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO namespace limit: \"-"
1121 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1122 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1123 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1124 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1126 final String go_namespace_limit_str = cla.getOptionValue( surfacing.GO_NAMESPACE_LIMIT_OPTION )
1128 if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION ) ) {
1129 go_namespace_limit = GoNameSpace.createMolecularFunction();
1131 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS ) ) {
1132 go_namespace_limit = GoNameSpace.createBiologicalProcess();
1134 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT ) ) {
1135 go_namespace_limit = GoNameSpace.createCellularComponent();
1138 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + go_namespace_limit_str
1139 + "\" for GO namespace limit: \"-" + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1140 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1141 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1142 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1145 if ( ( domain_similarity_sort_field == DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE )
1146 && ( number_of_genomes > 2 ) ) {
1147 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
1149 boolean jacknifed_distances = false;
1150 int jacknife_resamplings = JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT;
1151 double jacknife_ratio = JACKNIFE_RATIO_DEFAULT;
1152 long random_seed = JACKNIFE_RANDOM_SEED_DEFAULT;
1153 if ( cla.isOptionSet( surfacing.JACKNIFE_OPTION ) ) {
1154 if ( ( number_of_genomes < 3 ) || !perform_pwc ) {
1155 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use jacknife resampling analysis (-"
1156 + surfacing.JACKNIFE_OPTION + "[=<number of resamplings>]) without pairwise analyses ("
1157 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1158 + "=<suffix for pairwise comparison output files>)" );
1160 jacknifed_distances = true;
1161 if ( cla.isOptionHasAValue( surfacing.JACKNIFE_OPTION ) ) {
1163 jacknife_resamplings = cla.getOptionValueAsInt( surfacing.JACKNIFE_OPTION );
1165 catch ( final IOException e ) {
1166 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for number of resamplings" );
1168 if ( jacknife_resamplings < 2 ) {
1169 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use less than 2 resamplings" );
1172 if ( cla.isOptionSet( surfacing.JACKNIFE_RATIO_OPTION )
1173 && cla.isOptionHasAValue( surfacing.JACKNIFE_RATIO_OPTION ) ) {
1175 jacknife_ratio = cla.getOptionValueAsDouble( surfacing.JACKNIFE_RATIO_OPTION );
1177 catch ( final IOException e ) {
1178 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for jacknife ratio" );
1180 if ( ( jacknife_ratio <= 0.0 ) || ( jacknife_ratio >= 1.0 ) ) {
1181 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use illegal value for jacknife ratio: "
1185 if ( cla.isOptionSet( surfacing.JACKNIFE_RANDOM_SEED_OPTION )
1186 && cla.isOptionHasAValue( surfacing.JACKNIFE_RANDOM_SEED_OPTION ) ) {
1188 random_seed = cla.getOptionValueAsLong( surfacing.JACKNIFE_RANDOM_SEED_OPTION );
1190 catch ( final IOException e ) {
1191 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for random generator seed" );
1195 File[] intree_files = null;
1196 Phylogeny[] intrees = null;
1197 if ( cla.isOptionSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1198 // TODO FIXME if jacknife.... maybe not
1199 if ( number_of_genomes < 3 ) {
1200 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer gains and losses on input species trees (-"
1201 + surfacing.INPUT_SPECIES_TREE_OPTION + " without pairwise analyses ("
1202 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1203 + "=<suffix for pairwise comparison output files>)" );
1205 if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1206 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input tree: -"
1207 + surfacing.INPUT_SPECIES_TREE_OPTION + "=<tree file in phyloXML format>" );
1209 final String intrees_str = cla.getOptionValue( surfacing.INPUT_SPECIES_TREE_OPTION );
1210 if ( intrees_str.indexOf( "#" ) > 0 ) {
1211 final String[] intrees_strs = intrees_str.split( "#" );
1212 intree_files = new File[ intrees_strs.length ];
1214 for( final String s : intrees_strs ) {
1215 intree_files[ i++ ] = new File( s.trim() );
1219 intree_files = new File[ 1 ];
1220 intree_files[ 0 ] = new File( intrees_str );
1222 intrees = getIntrees( intree_files, number_of_genomes, input_file_properties );
1224 long random_number_seed_for_fitch_parsimony = 0l;
1225 boolean radomize_fitch_parsimony = false;
1226 if ( cla.isOptionSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1227 if ( !cla.isOptionValueSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1228 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for random number seed: -"
1229 + surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION + "=<seed>" );
1232 random_number_seed_for_fitch_parsimony = cla
1233 .getOptionValueAsLong( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
1235 catch ( final IOException e ) {
1236 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1238 radomize_fitch_parsimony = true;
1240 SortedSet<DomainId> filter = null;
1241 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1242 || ( negative_domains_filter_file != null ) ) {
1243 filter = new TreeSet<DomainId>();
1244 if ( positive_filter_file != null ) {
1245 processFilter( positive_filter_file, filter );
1247 else if ( negative_filter_file != null ) {
1248 processFilter( negative_filter_file, filter );
1250 else if ( negative_domains_filter_file != null ) {
1251 processFilter( negative_domains_filter_file, filter );
1254 Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps = null;
1255 File[] secondary_features_map_files = null;
1256 final File domain_lengths_analysis_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1257 + DOMAIN_LENGTHS_ANALYSIS_SUFFIX );
1258 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
1259 SurfacingUtil.checkForOutputFileWriteability( domain_lengths_analysis_outfile );
1261 if ( cla.isOptionSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1262 if ( !cla.isOptionValueSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1263 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for secondary features map file: -"
1264 + surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE + "=<file>" );
1266 final String[] secondary_features_map_files_strs = cla
1267 .getOptionValue( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ).split( "#" );
1268 secondary_features_map_files = new File[ secondary_features_map_files_strs.length ];
1269 domain_id_to_secondary_features_maps = new Map[ secondary_features_map_files_strs.length ];
1271 for( final String secondary_features_map_files_str : secondary_features_map_files_strs ) {
1272 secondary_features_map_files[ i ] = new File( secondary_features_map_files_str );
1273 final String error = ForesterUtil.isReadableFile( secondary_features_map_files[ i ] );
1274 if ( !ForesterUtil.isEmpty( error ) ) {
1275 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read secondary features map file: " + error );
1278 domain_id_to_secondary_features_maps[ i ] = SurfacingUtil
1279 .createDomainIdToSecondaryFeaturesMap( secondary_features_map_files[ i ] );
1281 catch ( final IOException e ) {
1282 ForesterUtil.fatalError( surfacing.PRG_NAME,
1283 "cannot read secondary features map file: " + e.getMessage() );
1285 catch ( final Exception e ) {
1286 ForesterUtil.fatalError( surfacing.PRG_NAME, "problem with contents of features map file ["
1287 + secondary_features_map_files[ i ] + "]: " + e.getMessage() );
1292 if ( out_dir == null ) {
1293 ForesterUtil.fatalError( surfacing.PRG_NAME, "no output directory indicated (-"
1294 + surfacing.OUTPUT_DIR_OPTION + "=<dir>)" );
1296 if ( output_file == null ) {
1297 ForesterUtil.fatalError( surfacing.PRG_NAME, "no name for (main) output file indicated (-"
1298 + surfacing.OUTPUT_FILE_OPTION + "=<file>)" );
1300 if ( ( domain_id_to_go_ids_map == null ) || domain_id_to_go_ids_map.isEmpty() ) {
1301 ForesterUtil.fatalError( surfacing.PRG_NAME,
1302 "no (acceptable) Pfam to GO id mapping file provided ('pfam2go file') (-"
1303 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1305 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1306 ForesterUtil.fatalError( surfacing.PRG_NAME,
1307 "no (acceptable) go id to term mapping file provided ('GO OBO file') (-"
1308 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1310 System.out.println( "Output directory : " + out_dir );
1311 System.out.println( "Input genomes from : " + input_genomes_file );
1312 html_desc.append( "<tr><td>Input genomes from:</td><td>" + input_genomes_file + "</td></tr>" + nl );
1313 if ( positive_filter_file != null ) {
1314 final int filter_size = filter.size();
1315 System.out.println( "Positive protein filter : " + positive_filter_file + " [" + filter_size
1317 html_desc.append( "<tr><td>Positive protein filter:</td><td>" + positive_filter_file + " [" + filter_size
1318 + " domain ids]</td></tr>" + nl );
1320 if ( negative_filter_file != null ) {
1321 final int filter_size = filter.size();
1322 System.out.println( "Negative protein filter : " + negative_filter_file + " [" + filter_size
1324 html_desc.append( "<tr><td>Negative protein filter:</td><td>" + negative_filter_file + " [" + filter_size
1325 + " domain ids]</td></tr>" + nl );
1327 if ( negative_domains_filter_file != null ) {
1328 final int filter_size = filter.size();
1329 System.out.println( "Negative domain filter : " + negative_domains_filter_file + " [" + filter_size
1331 html_desc.append( "<tr><td>Negative domain filter:</td><td>" + negative_domains_filter_file + " ["
1332 + filter_size + " domain ids]</td></tr>" + nl );
1334 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
1336 for( final String s : plus_minus_analysis_high_copy_base_species ) {
1337 plus0 += "+" + s + " ";
1340 for( final String s : plus_minus_analysis_high_copy_target_species ) {
1341 plus1 += "*" + s + " ";
1344 for( final String s : plus_minus_analysis_high_low_copy_species ) {
1345 minus += "-" + s + " ";
1347 System.out.println( "Plus-minus analysis : " + plus1 + "&& " + plus0 + "&& " + minus );
1348 html_desc.append( "<tr><td>Plus-minus analysis:</td><td>" + plus1 + "&& " + plus0 + "&& " + minus
1349 + "</td></tr>" + nl );
1351 if ( cutoff_scores_file != null ) {
1352 System.out.println( "Cutoff scores file : " + cutoff_scores_file );
1353 html_desc.append( "<tr><td>Cutoff scores file:</td><td>" + cutoff_scores_file + "</td></tr>" + nl );
1355 if ( e_value_max >= 0.0 ) {
1356 System.out.println( "E-value maximum (inclusive) : " + e_value_max );
1357 html_desc.append( "<tr><td>E-value maximum (inclusive):</td><td>" + e_value_max + "</td></tr>" + nl );
1359 if ( output_protein_lists_for_all_domains ) {
1360 System.out.println( "Domain E-value max : " + output_list_of_all_proteins_per_domain_e_value_max );
1361 html_desc.append( "<tr><td>Protein lists: E-value maximum per domain (inclusive):</td><td>"
1362 + output_list_of_all_proteins_per_domain_e_value_max + "</td></tr>" + nl );
1364 System.out.println( "Ignore DUFs : " + ignore_dufs );
1365 if ( ignore_virus_like_ids ) {
1366 System.out.println( "Ignore virus like ids : " + ignore_virus_like_ids );
1367 html_desc.append( "<tr><td>Ignore virus, phage, transposition related ids:</td><td>"
1368 + ignore_virus_like_ids + "</td></tr>" + nl );
1370 html_desc.append( "<tr><td>Ignore DUFs:</td><td>" + ignore_dufs + "</td></tr>" + nl );
1371 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1372 System.out.println( "Max allowed domain overlap : " + max_allowed_overlap );
1373 html_desc.append( "<tr><td>Max allowed domain overlap:</td><td>" + max_allowed_overlap + "</td></tr>" + nl );
1375 if ( no_engulfing_overlaps ) {
1376 System.out.println( "Ignore engulfed domains : " + no_engulfing_overlaps );
1377 html_desc.append( "<tr><td>Ignore (lower confidence) engulfed domains:</td><td>" + no_engulfing_overlaps
1378 + "</td></tr>" + nl );
1380 System.out.println( "Ignore singlet domains : " + ignore_domains_without_combs_in_all_spec );
1382 .append( "<tr><td>Ignore singlet domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1383 + ignore_domains_without_combs_in_all_spec + "</td></tr>" + nl );
1384 System.out.println( "Ignore species specific doms: " + ignore_species_specific_domains );
1386 .append( "<tr><td>Ignore species specific domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1387 + ignore_species_specific_domains + "</td></tr>" + nl );
1388 System.out.println( "Ignore combination with self: " + ignore_combination_with_same );
1389 html_desc.append( "<tr><td>Ignore combination with self for domain combination similarity analyses:</td><td>"
1390 + ignore_combination_with_same + "</td></tr>" + nl );
1391 System.out.println( "Consider directedness : "
1392 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) );
1393 html_desc.append( "<tr><td>Consider directedness of binary domain combinations:</td><td>"
1394 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) + "</td></tr>" + nl );
1395 if ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) {
1396 System.out.println( "Consider adjacency : "
1397 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) );
1398 html_desc.append( "<tr><td>Consider djacency of binary domain combinations:</td><td>"
1399 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) + "</td></tr>"
1402 System.out.println( "Write to Nexus files : " + write_to_nexus );
1403 System.out.print( "Domain counts sort order : " );
1404 switch ( dc_sort_order ) {
1405 case ALPHABETICAL_KEY_ID:
1406 System.out.println( "alphabetical" );
1408 case KEY_DOMAIN_COUNT:
1409 System.out.println( "domain count" );
1411 case KEY_DOMAIN_PROTEINS_COUNT:
1412 System.out.println( "domain proteins count" );
1414 case COMBINATIONS_COUNT:
1415 System.out.println( "domain combinations count" );
1418 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for dc sort order" );
1420 if ( domain_id_to_go_ids_map != null ) {
1421 System.out.println( "Pfam to GO mappings from : " + pfam_to_go_file + " [" + domain_id_to_go_ids_count
1423 html_desc.append( "<tr><td>Pfam to GO mappings from:</td><td>" + pfam_to_go_file + " ["
1424 + domain_id_to_go_ids_count + " mappings]" + "</td></tr>" + nl );
1426 if ( go_terms != null ) {
1427 System.out.println( "GO terms from : " + go_obo_file + " [" + go_terms.size() + " terms]" );
1428 html_desc.append( "<tr><td>GO terms from:</td><td>" + go_obo_file + " [" + go_terms.size() + " terms]"
1429 + "</td></tr>" + nl );
1431 if ( go_namespace_limit != null ) {
1432 System.out.println( "Limit GO terms to : " + go_namespace_limit.toString() );
1433 html_desc.append( "<tr><td>Limit GO terms to</td><td>" + go_namespace_limit + "</td></tr>" + nl );
1435 if ( perform_pwc ) {
1436 System.out.println( "Suffix for PWC files : " + automated_pairwise_comparison_suffix );
1437 html_desc.append( "<tr><td>Suffix for PWC files</td><td>" + automated_pairwise_comparison_suffix
1438 + "</td></tr>" + nl );
1440 if ( out_dir != null ) {
1441 System.out.println( "Output directory : " + out_dir );
1443 if ( query_domain_ids != null ) {
1444 System.out.println( "Query domains (ordered) : " + query_domain_ids );
1445 html_desc.append( "<tr><td></td><td>" + query_domain_ids + "</td></tr>" + nl );
1447 System.out.println( "Write similarities to : " + output_file );
1448 System.out.print( " Scoring method : " );
1449 html_desc.append( "<tr><td>Scoring method:</td><td>" );
1450 switch ( scoring ) {
1452 System.out.println( "domain combinations based" );
1453 html_desc.append( "domain combinations based" + "</td></tr>" + nl );
1456 System.out.println( "domain counts based" );
1457 html_desc.append( "domain counts based" + "</td></tr>" + nl );
1460 System.out.println( "domain proteins counts based" );
1461 html_desc.append( "domain proteins counts based" + "</td></tr>" + nl );
1464 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
1466 System.out.print( " Sort by : " );
1467 html_desc.append( "<tr><td>Sort by:</td><td>" );
1468 switch ( domain_similarity_sort_field ) {
1470 System.out.print( "score minimum" );
1471 html_desc.append( "score minimum" );
1474 System.out.print( "score maximum" );
1475 html_desc.append( "score maximum" );
1478 System.out.print( "score mean" );
1479 html_desc.append( "score mean" );
1482 System.out.print( "score standard deviation" );
1483 html_desc.append( "score standard deviation" );
1486 System.out.print( "species number" );
1487 html_desc.append( "species number" );
1490 System.out.print( "alphabetical domain identifier" );
1491 html_desc.append( "alphabetical domain identifier" );
1493 case MAX_DIFFERENCE:
1494 System.out.print( "(maximal) difference" );
1495 html_desc.append( "(maximal) difference" );
1497 case ABS_MAX_COUNTS_DIFFERENCE:
1498 System.out.print( "absolute (maximal) counts difference" );
1499 html_desc.append( "absolute (maximal) counts difference" );
1501 case MAX_COUNTS_DIFFERENCE:
1502 System.out.print( "(maximal) counts difference" );
1503 html_desc.append( "(maximal) counts difference" );
1506 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1508 if ( sort_by_species_count_first ) {
1509 System.out.println( " (sort by species count first)" );
1510 html_desc.append( " (sort by species count first)" );
1513 System.out.println();
1515 html_desc.append( "</td></tr>" + nl );
1516 System.out.print( " Detailedness : " );
1517 switch ( detailedness ) {
1519 System.out.println( "basic" );
1521 case LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES:
1522 System.out.println( "list combining domains for each species" );
1525 System.out.println( "punctilious" );
1528 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for detailedness" );
1530 System.out.print( " Print option : " );
1531 switch ( domain_similarity_print_option ) {
1533 System.out.println( "HTML" );
1535 case SIMPLE_TAB_DELIMITED:
1536 System.out.println( "simple tab delimited" );
1539 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for print option" );
1541 System.out.print( " Species matrix : " + species_matrix );
1542 System.out.println();
1543 final File dc_data_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + DATA_FILE_SUFFIX );
1544 System.out.println( "Domain comb data output : " + dc_data_file );
1545 html_desc.append( "<tr><td>Domain combination data output:</td><td> " + dc_data_file + " </td></tr>" );
1546 System.out.println();
1547 if ( perform_pwc ) {
1548 System.out.println( "Pairwise comparisons: " );
1549 html_desc.append( "<tr><td>Pairwise comparisons:</td><td></td></tr>" );
1550 System.out.print( " Sort by : " );
1551 html_desc.append( "<tr><td>Sort by:</td><td>" );
1552 switch ( domain_similarity_sort_field_for_automated_pwc ) {
1554 System.out.print( "score mean" );
1555 html_desc.append( "score mean" );
1558 System.out.print( "alphabetical domain identifier" );
1559 html_desc.append( "alphabetical domain identifier" );
1561 case MAX_DIFFERENCE:
1562 System.out.print( "difference" );
1563 html_desc.append( "difference" );
1565 case ABS_MAX_COUNTS_DIFFERENCE:
1566 System.out.print( "absolute counts difference" );
1567 html_desc.append( "absolute counts difference" );
1569 case MAX_COUNTS_DIFFERENCE:
1570 System.out.print( "counts difference" );
1571 html_desc.append( "counts difference" );
1575 .unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1577 System.out.println();
1578 html_desc.append( "</td></tr>" + nl );
1579 if ( jacknifed_distances ) {
1580 html_desc.append( "<tr><td>Jacknife:</td><td>" + jacknife_resamplings + " resamplings</td></tr>" + nl );
1581 html_desc.append( "<tr><td>Jacknife ratio:</td><td>" + ForesterUtil.round( jacknife_ratio, 2 )
1582 + "</td></tr>" + nl );
1583 html_desc.append( "<tr><td>Jacknife random number seed:</td><td>" + random_seed + "</td></tr>" + nl );
1584 System.out.println( " Jacknife : " + jacknife_resamplings + " resamplings" );
1585 System.out.println( " Ratio : " + ForesterUtil.round( jacknife_ratio, 2 ) );
1586 System.out.println( " Random number seed : " + random_seed );
1588 if ( ( intrees != null ) && ( intrees.length > 0 ) ) {
1589 for( final File intree_file : intree_files ) {
1590 html_desc.append( "<tr><td>Intree for gain/loss parsimony analysis:</td><td>" + intree_file
1591 + "</td></tr>" + nl );
1592 System.out.println( " Intree for gain/loss pars.: " + intree_file );
1595 if ( radomize_fitch_parsimony ) {
1596 html_desc.append( "<tr><td> Random number seed for Fitch parsimony analysis:</td><td>"
1597 + random_number_seed_for_fitch_parsimony + "</td></tr>" + nl );
1598 System.out.println( " Random number seed : " + random_number_seed_for_fitch_parsimony );
1600 if ( ( domain_id_to_secondary_features_maps != null ) && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
1601 for( int i = 0; i < secondary_features_map_files.length; i++ ) {
1602 html_desc.append( "<tr><td>Secondary features map file:</td><td>"
1603 + secondary_features_map_files[ i ] + "</td></tr>" + nl );
1604 System.out.println( "Secondary features map file : " + secondary_features_map_files[ i ]
1605 + " [mappings for " + domain_id_to_secondary_features_maps[ i ].size() + " domain ids]" );
1607 System.out.println();
1608 System.out.println( "Domain ids to secondary features map:" );
1609 for( final DomainId domain_id : domain_id_to_secondary_features_maps[ i ].keySet() ) {
1610 System.out.print( domain_id.getId() );
1611 System.out.print( " => " );
1612 for( final String sec : domain_id_to_secondary_features_maps[ i ].get( domain_id ) ) {
1613 System.out.print( sec );
1614 System.out.print( " " );
1616 System.out.println();
1621 } // if ( perform_pwc ) {
1622 System.out.println();
1623 html_desc.append( "<tr><td>Command line:</td><td>\n" + cla.getCommandLineArgsAsString() + "\n</td></tr>" + nl );
1624 System.out.println( "Command line : " + cla.getCommandLineArgsAsString() );
1625 BufferedWriter[] query_domains_writer_ary = null;
1626 List<DomainId>[] query_domain_ids_array = null;
1627 if ( query_domain_ids != null ) {
1628 final String[] query_domain_ids_str_array = query_domain_ids.split( "#" );
1629 query_domain_ids_array = new ArrayList[ query_domain_ids_str_array.length ];
1630 query_domains_writer_ary = new BufferedWriter[ query_domain_ids_str_array.length ];
1631 for( int i = 0; i < query_domain_ids_str_array.length; i++ ) {
1632 String query_domain_ids_str = query_domain_ids_str_array[ i ];
1633 final String[] query_domain_ids_str_ary = query_domain_ids_str.split( "~" );
1634 final List<DomainId> query = new ArrayList<DomainId>();
1635 for( final String element : query_domain_ids_str_ary ) {
1636 query.add( new DomainId( element ) );
1638 query_domain_ids_array[ i ] = query;
1639 query_domain_ids_str = query_domain_ids_str.replace( '~', '_' );
1640 String protein_names_writer_str = query_domain_ids_str + surfacing.SEQ_EXTRACT_SUFFIX;
1641 if ( out_dir != null ) {
1642 protein_names_writer_str = out_dir + ForesterUtil.FILE_SEPARATOR + protein_names_writer_str;
1645 query_domains_writer_ary[ i ] = new BufferedWriter( new FileWriter( protein_names_writer_str ) );
1647 catch ( final IOException e ) {
1648 ForesterUtil.fatalError( surfacing.PRG_NAME, "Could not open [" + protein_names_writer_str + "]: "
1649 + e.getLocalizedMessage() );
1653 SortedMap<Species, List<Protein>> protein_lists_per_species = null; //This will only be created if neede.
1654 boolean need_protein_lists_per_species = false;
1655 if ( ( plus_minus_analysis_high_copy_base_species.size() > 0 ) || output_protein_lists_for_all_domains ) {
1656 need_protein_lists_per_species = true;
1658 if ( need_protein_lists_per_species ) {
1659 protein_lists_per_species = new TreeMap<Species, List<Protein>>();
1661 final List<GenomeWideCombinableDomains> gwcd_list = new ArrayList<GenomeWideCombinableDomains>( number_of_genomes );
1662 final SortedSet<DomainId> all_domains_encountered = new TreeSet<DomainId>();
1663 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered = new TreeSet<BinaryDomainCombination>();
1664 List<BinaryDomainCombination> all_bin_domain_combinations_gained_fitch = null;
1665 List<BinaryDomainCombination> all_bin_domain_combinations_lost_fitch = null;
1666 if ( ( intrees != null ) && ( intrees.length == 1 ) ) {
1667 all_bin_domain_combinations_gained_fitch = new ArrayList<BinaryDomainCombination>();
1668 all_bin_domain_combinations_lost_fitch = new ArrayList<BinaryDomainCombination>();
1670 final DomainLengthsTable domain_lengths_table = new DomainLengthsTable();
1671 final File per_genome_domain_promiscuity_statistics_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR
1672 + output_file + D_PROMISCUITY_FILE_SUFFIX );
1673 BufferedWriter per_genome_domain_promiscuity_statistics_writer = null;
1675 per_genome_domain_promiscuity_statistics_writer = new BufferedWriter( new FileWriter( per_genome_domain_promiscuity_statistics_file ) );
1676 per_genome_domain_promiscuity_statistics_writer.write( "Species:\t" );
1677 per_genome_domain_promiscuity_statistics_writer.write( "Mean:\t" );
1678 per_genome_domain_promiscuity_statistics_writer.write( "SD:\t" );
1679 per_genome_domain_promiscuity_statistics_writer.write( "Median:\t" );
1680 per_genome_domain_promiscuity_statistics_writer.write( "Min:\t" );
1681 per_genome_domain_promiscuity_statistics_writer.write( "Max:\t" );
1682 per_genome_domain_promiscuity_statistics_writer.write( "N:\t" );
1683 per_genome_domain_promiscuity_statistics_writer.write( "Max Promiscuous Domains:"
1684 + ForesterUtil.LINE_SEPARATOR );
1686 catch ( final IOException e2 ) {
1687 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1689 final File log_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + LOG_FILE_SUFFIX );
1690 BufferedWriter log_writer = null;
1692 log_writer = new BufferedWriter( new FileWriter( log_file ) );
1694 catch ( final IOException e2 ) {
1695 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1697 BufferedWriter dc_data_writer = null;
1699 dc_data_writer = new BufferedWriter( new FileWriter( dc_data_file ) );
1700 dc_data_writer.write( DATA_FILE_DESC );
1701 dc_data_writer.write( ForesterUtil.LINE_SEPARATOR );
1703 catch ( final IOException e2 ) {
1704 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1706 final DescriptiveStatistics protein_coverage_stats = new BasicDescriptiveStatistics();
1707 final DescriptiveStatistics all_genomes_domains_per_potein_stats = new BasicDescriptiveStatistics();
1708 final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo = new TreeMap<Integer, Integer>();
1709 final SortedSet<String> domains_which_are_always_single = new TreeSet<String>();
1710 final SortedSet<String> domains_which_are_sometimes_single_sometimes_not = new TreeSet<String>();
1711 final SortedSet<String> domains_which_never_single = new TreeSet<String>();
1712 BufferedWriter domains_per_potein_stats_writer = null;
1714 domains_per_potein_stats_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
1715 + output_file + "_domains_per_potein_stats.txt" ) );
1716 domains_per_potein_stats_writer.write( "Genome" );
1717 domains_per_potein_stats_writer.write( "\t" );
1718 domains_per_potein_stats_writer.write( "Mean" );
1719 domains_per_potein_stats_writer.write( "\t" );
1720 domains_per_potein_stats_writer.write( "SD" );
1721 domains_per_potein_stats_writer.write( "\t" );
1722 domains_per_potein_stats_writer.write( "Median" );
1723 domains_per_potein_stats_writer.write( "\t" );
1724 domains_per_potein_stats_writer.write( "N" );
1725 domains_per_potein_stats_writer.write( "\t" );
1726 domains_per_potein_stats_writer.write( "Min" );
1727 domains_per_potein_stats_writer.write( "\t" );
1728 domains_per_potein_stats_writer.write( "Max" );
1729 domains_per_potein_stats_writer.write( "\n" );
1731 catch ( final IOException e3 ) {
1732 e3.printStackTrace();
1734 Map<String, DescriptiveStatistics> protein_length_stats_by_dc = null;
1735 Map<String, DescriptiveStatistics> domain_number_stats_by_dc = null;
1736 final Map<String, DescriptiveStatistics> domain_length_stats_by_domain = new HashMap<String, DescriptiveStatistics>();
1737 if ( PERFORM_DC_REGAIN_PROTEINS_STATS ) {
1738 protein_length_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1739 domain_number_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1742 final SortedMap<String, Set<String>> distinct_domain_architecutures_per_genome = new TreeMap<String, Set<String>>();
1743 final SortedMap<String, Integer> distinct_domain_architecuture_counts = new TreeMap<String, Integer>();
1744 for( int i = 0; i < number_of_genomes; ++i ) {
1745 System.out.println();
1746 System.out.println( ( i + 1 ) + "/" + number_of_genomes );
1747 log( ( i + 1 ) + "/" + number_of_genomes, log_writer );
1748 System.out.println( "Processing : " + input_file_properties[ i ][ 1 ]
1749 + " [" + input_file_properties[ i ][ 0 ] + "]" );
1750 log( "Genome : " + input_file_properties[ i ][ 1 ] + " ["
1751 + input_file_properties[ i ][ 0 ] + "]", log_writer );
1752 HmmscanPerDomainTableParser parser = null;
1753 INDIVIDUAL_SCORE_CUTOFF ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF.NONE;
1754 if ( individual_score_cutoffs != null ) {
1755 ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF_DEFAULT;
1757 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1758 || ( negative_domains_filter_file != null ) ) {
1759 HmmscanPerDomainTableParser.FilterType filter_type = HmmscanPerDomainTableParser.FilterType.NONE;
1760 if ( positive_filter_file != null ) {
1761 filter_type = HmmscanPerDomainTableParser.FilterType.POSITIVE_PROTEIN;
1763 else if ( negative_filter_file != null ) {
1764 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_PROTEIN;
1766 else if ( negative_domains_filter_file != null ) {
1767 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_DOMAIN;
1769 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1770 input_file_properties[ i ][ 1 ],
1777 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1778 input_file_properties[ i ][ 1 ],
1782 if ( e_value_max >= 0.0 ) {
1783 parser.setEValueMaximum( e_value_max );
1785 parser.setIgnoreDufs( ignore_dufs );
1786 parser.setIgnoreVirusLikeIds( ignore_virus_like_ids );
1787 parser.setIgnoreEngulfedDomains( no_engulfing_overlaps );
1788 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1789 parser.setMaxAllowedOverlap( max_allowed_overlap );
1791 parser.setReturnType( HmmscanPerDomainTableParser.ReturnType.UNORDERED_PROTEIN_DOMAIN_COLLECTION_PER_PROTEIN );
1792 if ( individual_score_cutoffs != null ) {
1793 parser.setIndividualScoreCutoffs( individual_score_cutoffs );
1795 List<Protein> protein_list = null;
1797 protein_list = parser.parse();
1799 catch ( final IOException e ) {
1800 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1802 catch ( final Exception e ) {
1803 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, e.getMessage(), e );
1806 System.out.println( "Domains ignored due to negative domain filter: " );
1807 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToNegativeDomainFilterCountsMap() );
1808 System.out.println( "Domains ignored due to virus like id: " );
1809 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToVirusLikeIdCountsMap() );
1811 final double coverage = ( double ) protein_list.size() / parser.getProteinsEncountered();
1812 protein_coverage_stats.addValue( coverage );
1813 int distinct_das = -1;
1814 if ( DA_ANALYSIS ) {
1815 final String genome = input_file_properties[ i ][ 0 ];
1816 distinct_das = SurfacingUtil.storeDomainArchitectures( genome,
1817 distinct_domain_architecutures_per_genome,
1819 distinct_domain_architecuture_counts );
1821 System.out.println( "Number of proteins encountered : " + parser.getProteinsEncountered() );
1822 log( "Number of proteins encountered : " + parser.getProteinsEncountered(), log_writer );
1823 System.out.println( "Number of proteins stored : " + protein_list.size() );
1824 log( "Number of proteins stored : " + protein_list.size(), log_writer );
1825 System.out.println( "Coverage : "
1826 + ForesterUtil.roundToInt( 100.0 * coverage ) + "%" );
1827 log( "Coverage : " + ForesterUtil.roundToInt( 100.0 * coverage )
1828 + "%", log_writer );
1829 System.out.println( "Domains encountered : " + parser.getDomainsEncountered() );
1830 log( "Domains encountered : " + parser.getDomainsEncountered(), log_writer );
1831 System.out.println( "Domains stored : " + parser.getDomainsStored() );
1832 log( "Domains stored : " + parser.getDomainsStored(), log_writer );
1833 System.out.println( "Distinct domains stored : "
1834 + parser.getDomainsStoredSet().size() );
1835 log( "Distinct domains stored : " + parser.getDomainsStoredSet().size(), log_writer );
1836 System.out.println( "Domains ignored due to individual score cutoffs: "
1837 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() );
1838 log( "Domains ignored due to individual score cutoffs: "
1839 + parser.getDomainsIgnoredDueToIndividualScoreCutoff(),
1841 System.out.println( "Domains ignored due to E-value : "
1842 + parser.getDomainsIgnoredDueToEval() );
1843 log( "Domains ignored due to E-value : " + parser.getDomainsIgnoredDueToEval(), log_writer );
1844 System.out.println( "Domains ignored due to DUF designation : "
1845 + parser.getDomainsIgnoredDueToDuf() );
1846 log( "Domains ignored due to DUF designation : " + parser.getDomainsIgnoredDueToDuf(), log_writer );
1847 if ( ignore_virus_like_ids ) {
1848 System.out.println( "Domains ignored due virus like ids : "
1849 + parser.getDomainsIgnoredDueToVirusLikeIds() );
1850 log( "Domains ignored due virus like ids : " + parser.getDomainsIgnoredDueToVirusLikeIds(),
1853 System.out.println( "Domains ignored due negative domain filter : "
1854 + parser.getDomainsIgnoredDueToNegativeDomainFilter() );
1855 log( "Domains ignored due negative domain filter : "
1856 + parser.getDomainsIgnoredDueToNegativeDomainFilter(),
1858 System.out.println( "Domains ignored due to overlap : "
1859 + parser.getDomainsIgnoredDueToOverlap() );
1860 log( "Domains ignored due to overlap : " + parser.getDomainsIgnoredDueToOverlap(),
1862 if ( negative_filter_file != null ) {
1863 System.out.println( "Proteins ignored due to negative filter : "
1864 + parser.getProteinsIgnoredDueToFilter() );
1865 log( "Proteins ignored due to negative filter : " + parser.getProteinsIgnoredDueToFilter(),
1868 if ( positive_filter_file != null ) {
1869 System.out.println( "Proteins ignored due to positive filter : "
1870 + parser.getProteinsIgnoredDueToFilter() );
1871 log( "Proteins ignored due to positive filter : " + parser.getProteinsIgnoredDueToFilter(),
1874 if ( DA_ANALYSIS ) {
1875 System.out.println( "Distinct domain architectures stored : " + distinct_das );
1876 log( "Distinct domain architectures stored : " + distinct_das, log_writer );
1878 System.out.println( "Time for processing : " + parser.getTime() + "ms" );
1879 log( "", log_writer );
1880 html_desc.append( "<tr><td>" + input_file_properties[ i ][ 0 ] + " [species: "
1881 + input_file_properties[ i ][ 1 ] + "]" + ":</td><td>domains analyzed: "
1882 + parser.getDomainsStored() + "; domains ignored: [ind score cutoffs: "
1883 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() + "] [E-value cutoff: "
1884 + parser.getDomainsIgnoredDueToEval() + "] [DUF: " + parser.getDomainsIgnoredDueToDuf()
1885 + "] [virus like ids: " + parser.getDomainsIgnoredDueToVirusLikeIds()
1886 + "] [negative domain filter: " + parser.getDomainsIgnoredDueToNegativeDomainFilter()
1887 + "] [overlap: " + parser.getDomainsIgnoredDueToOverlap() + "]" );
1888 if ( negative_filter_file != null ) {
1889 html_desc.append( "; proteins ignored due to negative filter: "
1890 + parser.getProteinsIgnoredDueToFilter() );
1892 if ( positive_filter_file != null ) {
1893 html_desc.append( "; proteins ignored due to positive filter: "
1894 + parser.getProteinsIgnoredDueToFilter() );
1896 html_desc.append( "</td></tr>" + nl );
1899 for( final Protein protein : protein_list ) {
1900 dc_data_writer.write( SurfacingUtil.proteinToDomainCombinations( protein, count + "", "\t" )
1903 for( final Domain d : protein.getProteinDomains() ) {
1904 final String d_str = d.getDomainId().toString();
1905 if ( !domain_length_stats_by_domain.containsKey( d_str ) ) {
1906 domain_length_stats_by_domain.put( d_str, new BasicDescriptiveStatistics() );
1908 domain_length_stats_by_domain.get( d_str ).addValue( d.getLength() );
1912 catch ( final IOException e ) {
1913 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1915 SurfacingUtil.domainsPerProteinsStatistics( input_file_properties[ i ][ 1 ],
1917 all_genomes_domains_per_potein_stats,
1918 all_genomes_domains_per_potein_histo,
1919 domains_which_are_always_single,
1920 domains_which_are_sometimes_single_sometimes_not,
1921 domains_which_never_single,
1922 domains_per_potein_stats_writer );
1923 domain_lengths_table.addLengths( protein_list );
1924 if ( !DA_ANALYSIS ) {
1925 gwcd_list.add( BasicGenomeWideCombinableDomains
1926 .createInstance( protein_list,
1927 ignore_combination_with_same,
1928 new BasicSpecies( input_file_properties[ i ][ 1 ] ),
1929 domain_id_to_go_ids_map,
1931 protein_length_stats_by_dc,
1932 domain_number_stats_by_dc ) );
1933 if ( gwcd_list.get( i ).getSize() > 0 ) {
1934 SurfacingUtil.writeDomainCombinationsCountsFile( input_file_properties,
1936 per_genome_domain_promiscuity_statistics_writer,
1940 if ( output_binary_domain_combinationsfor_graph_analysis ) {
1941 SurfacingUtil.writeBinaryDomainCombinationsFileForGraphAnalysis( input_file_properties,
1947 SurfacingUtil.addAllDomainIdsToSet( gwcd_list.get( i ), all_domains_encountered );
1948 SurfacingUtil.addAllBinaryDomainCombinationToSet( gwcd_list.get( i ),
1949 all_bin_domain_combinations_encountered );
1952 if ( query_domains_writer_ary != null ) {
1953 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1955 SurfacingUtil.extractProteinNames( protein_list,
1956 query_domain_ids_array[ j ],
1957 query_domains_writer_ary[ j ],
1959 LIMIT_SPEC_FOR_PROT_EX );
1960 query_domains_writer_ary[ j ].flush();
1962 catch ( final IOException e ) {
1963 e.printStackTrace();
1967 if ( need_protein_lists_per_species ) {
1968 protein_lists_per_species.put( new BasicSpecies( input_file_properties[ i ][ 1 ] ), protein_list );
1973 catch ( final IOException e2 ) {
1974 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1977 } // for( int i = 0; i < number_of_genomes; ++i ) {
1978 ForesterUtil.programMessage( PRG_NAME, "Wrote domain promiscuities to: "
1979 + per_genome_domain_promiscuity_statistics_file );
1981 if ( DA_ANALYSIS ) {
1982 SurfacingUtil.performDomainArchitectureAnalysis( distinct_domain_architecutures_per_genome,
1983 distinct_domain_architecuture_counts,
1985 new File( out_dir.toString() + "/" + output_file
1986 + "_DA_counts.txt" ),
1987 new File( out_dir.toString() + "/" + output_file
1988 + "_unique_DAs.txt" ) );
1989 distinct_domain_architecutures_per_genome.clear();
1990 distinct_domain_architecuture_counts.clear();
1994 domains_per_potein_stats_writer.write( "ALL" );
1995 domains_per_potein_stats_writer.write( "\t" );
1996 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.arithmeticMean() + "" );
1997 domains_per_potein_stats_writer.write( "\t" );
1998 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.sampleStandardDeviation() + "" );
1999 domains_per_potein_stats_writer.write( "\t" );
2000 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.median() + "" );
2001 domains_per_potein_stats_writer.write( "\t" );
2002 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getN() + "" );
2003 domains_per_potein_stats_writer.write( "\t" );
2004 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMin() + "" );
2005 domains_per_potein_stats_writer.write( "\t" );
2006 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMax() + "" );
2007 domains_per_potein_stats_writer.write( "\n" );
2008 domains_per_potein_stats_writer.close();
2009 printOutPercentageOfMultidomainProteins( all_genomes_domains_per_potein_histo, log_writer );
2010 ForesterUtil.map2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2011 + "_all_genomes_domains_per_potein_histo.txt" ), all_genomes_domains_per_potein_histo, "\t", "\n" );
2012 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2013 + "_domains_always_single_.txt" ), domains_which_are_always_single, "\n" );
2014 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2015 + "_domains_single_or_combined.txt" ), domains_which_are_sometimes_single_sometimes_not, "\n" );
2016 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2017 + "_domains_always_combined.txt" ), domains_which_never_single, "\n" );
2018 ForesterUtil.programMessage( PRG_NAME,
2019 "Average of proteins with a least one domain assigned: "
2020 + ( 100 * protein_coverage_stats.arithmeticMean() ) + "% (+/-"
2021 + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)" );
2022 ForesterUtil.programMessage( PRG_NAME, "Range of proteins with a least one domain assigned: "
2023 + ( 100 * protein_coverage_stats.getMin() ) + "%-" + ( 100 * protein_coverage_stats.getMax() )
2025 log( "Average of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.arithmeticMean() )
2026 + "% (+/-" + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)", log_writer );
2027 log( "Range of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.getMin() ) + "%-"
2028 + ( 100 * protein_coverage_stats.getMax() ) + "%", log_writer );
2030 catch ( final IOException e2 ) {
2031 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
2033 if ( query_domains_writer_ary != null ) {
2034 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
2036 query_domains_writer_ary[ j ].close();
2038 catch ( final IOException e ) {
2039 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
2044 per_genome_domain_promiscuity_statistics_writer.close();
2045 dc_data_writer.close();
2048 catch ( final IOException e2 ) {
2049 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
2051 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
2053 SurfacingUtil.executeDomainLengthAnalysis( input_file_properties,
2055 domain_lengths_table,
2056 domain_lengths_analysis_outfile );
2058 catch ( final IOException e1 ) {
2059 ForesterUtil.fatalError( surfacing.PRG_NAME, e1.toString() );
2061 System.out.println();
2062 ForesterUtil.programMessage( PRG_NAME, "Wrote domain length data to: " + domain_lengths_analysis_outfile );
2063 System.out.println();
2065 final long analysis_start_time = new Date().getTime();
2066 PairwiseDomainSimilarityCalculator pw_calc = null;
2067 // double[] values_for_all_scores_histogram = null;
2068 final DomainSimilarityCalculator calc = new BasicDomainSimilarityCalculator( domain_similarity_sort_field,
2069 sort_by_species_count_first,
2070 number_of_genomes == 2 );
2071 switch ( scoring ) {
2073 pw_calc = new CombinationsBasedPairwiseDomainSimilarityCalculator();
2076 pw_calc = new DomainCountsBasedPairwiseSimilarityCalculator();
2079 pw_calc = new ProteinCountsBasedPairwiseDomainSimilarityCalculator();
2082 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
2084 DomainSimilarityCalculator.GoAnnotationOutput go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.NONE;
2085 if ( domain_id_to_go_ids_map != null ) {
2086 go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.ALL;
2088 final SortedSet<DomainSimilarity> similarities = calc
2089 .calculateSimilarities( pw_calc,
2091 ignore_domains_without_combs_in_all_spec,
2092 ignore_species_specific_domains );
2093 SurfacingUtil.decoratePrintableDomainSimilarities( similarities,
2095 go_annotation_output,
2097 go_namespace_limit );
2098 final Map<String, Integer> tax_code_to_id_map = SurfacingUtil.createTaxCodeToIdMap( intrees[ 0 ] );
2100 String my_outfile = output_file.toString();
2101 Map<Character, Writer> split_writers = null;
2102 Writer writer = null;
2103 if ( similarities.size() > MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING ) {
2104 if ( my_outfile.endsWith( ".html" ) ) {
2105 my_outfile = my_outfile.substring( 0, my_outfile.length() - 5 );
2107 split_writers = new HashMap<Character, Writer>();
2108 createSplitWriters( out_dir, my_outfile, split_writers );
2110 else if ( !my_outfile.endsWith( ".html" ) ) {
2111 my_outfile += ".html";
2112 writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) );
2114 List<Species> species_order = null;
2115 if ( species_matrix ) {
2116 species_order = new ArrayList<Species>();
2117 for( int i = 0; i < number_of_genomes; i++ ) {
2118 species_order.add( new BasicSpecies( input_file_properties[ i ][ 1 ] ) );
2121 html_desc.append( "<tr><td>Sum of all distinct binary combinations:</td><td>"
2122 + all_bin_domain_combinations_encountered.size() + "</td></tr>" + nl );
2123 html_desc.append( "<tr><td>Sum of all distinct domains:</td><td>" + all_domains_encountered.size()
2124 + "</td></tr>" + nl );
2125 html_desc.append( "<tr><td>Analysis date/time:</td><td>"
2126 + new java.text.SimpleDateFormat( "yyyy.MM.dd HH:mm:ss" ).format( new java.util.Date() )
2127 + "</td></tr>" + nl );
2128 html_desc.append( "</table>" + nl );
2129 final DescriptiveStatistics pw_stats = SurfacingUtil
2130 .writeDomainSimilaritiesToFile( html_desc,
2131 new StringBuilder( number_of_genomes + " genomes" ),
2135 number_of_genomes == 2,
2137 domain_similarity_print_option,
2138 domain_similarity_sort_field,
2141 tax_code_to_id_map );
2142 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote main output (includes domain similarities) to: \""
2143 + ( out_dir == null ? my_outfile : out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) + "\"" );
2145 catch ( final IOException e ) {
2146 ForesterUtil.fatalError( surfacing.PRG_NAME, "Failed to write similarites to: \"" + output_file + "\" ["
2147 + e.getMessage() + "]" );
2149 System.out.println();
2150 final Species[] species = new Species[ number_of_genomes ];
2151 for( int i = 0; i < number_of_genomes; ++i ) {
2152 species[ i ] = new BasicSpecies( input_file_properties[ i ][ 1 ] );
2154 List<Phylogeny> inferred_trees = null;
2155 if ( ( number_of_genomes > 2 ) && perform_pwc ) {
2156 final PairwiseGenomeComparator pwgc = new PairwiseGenomeComparator();
2157 pwgc.performPairwiseComparisons( html_desc,
2158 sort_by_species_count_first,
2160 ignore_domains_without_combs_in_all_spec,
2161 ignore_species_specific_domains,
2162 domain_similarity_sort_field_for_automated_pwc,
2163 domain_similarity_print_option,
2165 domain_id_to_go_ids_map,
2172 automated_pairwise_comparison_suffix,
2174 surfacing.PAIRWISE_DOMAIN_COMPARISONS_PREFIX,
2178 tax_code_to_id_map );
2179 String matrix_output_file = new String( output_file.toString() );
2180 if ( matrix_output_file.indexOf( '.' ) > 1 ) {
2181 matrix_output_file = matrix_output_file.substring( 0, matrix_output_file.indexOf( '.' ) );
2183 if ( out_dir != null ) {
2184 matrix_output_file = out_dir + ForesterUtil.FILE_SEPARATOR + matrix_output_file;
2185 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2187 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2188 + surfacing.MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans() );
2190 .writeMatrixToFile( new File( matrix_output_file
2191 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2192 pwgc.getSharedBinaryCombinationsBasedDistances() );
2193 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2194 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2195 pwgc.getSharedDomainsBasedDistances() );
2196 final Phylogeny nj_gd = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2197 + surfacing.NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans()
2199 final Phylogeny nj_bc = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2200 + surfacing.NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2201 .getSharedBinaryCombinationsBasedDistances().get( 0 ) );
2202 final Phylogeny nj_d = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2203 + surfacing.NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2204 .getSharedDomainsBasedDistances().get( 0 ) );
2205 inferred_trees = new ArrayList<Phylogeny>();
2206 inferred_trees.add( nj_gd );
2207 inferred_trees.add( nj_bc );
2208 inferred_trees.add( nj_d );
2209 if ( jacknifed_distances ) {
2210 pwgc.performPairwiseComparisonsJacknifed( species,
2214 jacknife_resamplings,
2218 .writeMatrixToFile( new File( matrix_output_file
2220 + ForesterUtil.round( jacknife_ratio, 2 )
2222 + jacknife_resamplings
2223 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2224 pwgc.getSharedBinaryCombinationsBasedDistances() );
2226 .writeMatrixToFile( new File( matrix_output_file + "_" + ForesterUtil.round( jacknife_ratio, 2 )
2227 + "_" + jacknife_resamplings
2228 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2229 pwgc.getSharedDomainsBasedDistances() );
2230 // if ( infer_species_trees ) {
2231 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2232 // + INFERRED_SBC_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc
2233 // .getSharedBinaryCombinationsBasedDistances() );
2234 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2235 // + INFERRED_SD_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc.getSharedDomainsBasedDistances() );
2238 } // if ( ( output_file != null ) && ( number_of_genomes > 2 ) && !isEmpty( automated_pairwise_comparison_suffix ) )
2239 if ( ( out_dir != null ) && ( !perform_pwc ) ) {
2240 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2242 if ( write_to_nexus ) {
2243 writePresentToNexus( output_file, positive_filter_file, filter, gwcd_list );
2245 if ( ( ( intrees != null ) && ( intrees.length > 0 ) ) && ( number_of_genomes > 2 ) ) {
2246 final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
2248 max_allowed_overlap,
2249 no_engulfing_overlaps,
2253 if ( radomize_fitch_parsimony ) {
2254 s += random_number_seed_for_fitch_parsimony + "_";
2257 for( final Phylogeny intree : intrees ) {
2258 final String outfile_name = ForesterUtil.removeSuffix( output_file.toString() ) + s
2259 + ForesterUtil.removeSuffix( intree_files[ i ].toString() );
2260 final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator.createInstance( intree,
2262 SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
2263 radomize_fitch_parsimony,
2267 domain_id_to_go_ids_map,
2270 parameters_sb.toString(),
2271 domain_id_to_secondary_features_maps,
2272 positive_filter_file == null ? null : filter,
2273 output_binary_domain_combinationsfor_graph_analysis,
2274 all_bin_domain_combinations_gained_fitch,
2275 all_bin_domain_combinations_lost_fitch,
2277 protein_length_stats_by_dc,
2278 domain_number_stats_by_dc,
2279 domain_length_stats_by_domain,
2282 // Listing of all domain combinations gained is only done if only one input tree is used.
2283 if ( ( domain_id_to_secondary_features_maps != null )
2284 && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
2286 for( final Map<DomainId, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
2287 final Map<Species, MappingResults> mapping_results_map = new TreeMap<Species, MappingResults>();
2288 final DomainParsimonyCalculator secondary_features_parsimony = DomainParsimonyCalculator
2289 .createInstance( intree, gwcd_list, domain_id_to_secondary_features_map );
2291 .executeParsimonyAnalysisForSecondaryFeatures( outfile_name
2293 + secondary_features_map_files[ j++ ],
2294 secondary_features_parsimony,
2296 parameters_sb.toString(),
2297 mapping_results_map );
2299 System.out.println();
2300 System.out.println( "Mapping to secondary features:" );
2301 for( final Species spec : mapping_results_map.keySet() ) {
2302 final MappingResults mapping_results = mapping_results_map.get( spec );
2303 final int total_domains = mapping_results.getSumOfFailures()
2304 + mapping_results.getSumOfSuccesses();
2305 System.out.print( spec + ":" );
2306 System.out.print( " mapped domains = " + mapping_results.getSumOfSuccesses() );
2307 System.out.print( ", not mapped domains = " + mapping_results.getSumOfFailures() );
2308 if ( total_domains > 0 ) {
2309 System.out.println( ", mapped ratio = "
2310 + ( ( 100 * mapping_results.getSumOfSuccesses() ) / total_domains ) + "%" );
2313 System.out.println( ", mapped ratio = n/a (total domains = 0 )" );
2320 } // for( final Phylogeny intree : intrees ) {
2322 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
2323 executePlusMinusAnalysis( output_file,
2324 plus_minus_analysis_high_copy_base_species,
2325 plus_minus_analysis_high_copy_target_species,
2326 plus_minus_analysis_high_low_copy_species,
2328 protein_lists_per_species,
2329 domain_id_to_go_ids_map,
2331 plus_minus_analysis_numbers );
2333 if ( output_protein_lists_for_all_domains ) {
2334 writeProteinListsForAllSpecies( out_dir,
2335 protein_lists_per_species,
2337 output_list_of_all_proteins_per_domain_e_value_max );
2339 if ( all_bin_domain_combinations_gained_fitch != null ) {
2341 executeFitchGainsAnalysis( new File( output_file
2342 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2343 all_bin_domain_combinations_gained_fitch,
2344 all_domains_encountered.size(),
2345 all_bin_domain_combinations_encountered,
2348 catch ( final IOException e ) {
2349 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2352 if ( all_bin_domain_combinations_lost_fitch != null ) {
2354 executeFitchGainsAnalysis( new File( output_file
2355 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2356 all_bin_domain_combinations_lost_fitch,
2357 all_domains_encountered.size(),
2358 all_bin_domain_combinations_encountered,
2361 catch ( final IOException e ) {
2362 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2365 final Runtime rt = java.lang.Runtime.getRuntime();
2366 final long free_memory = rt.freeMemory() / 1000000;
2367 final long total_memory = rt.totalMemory() / 1000000;
2368 ForesterUtil.programMessage( PRG_NAME, "Time for analysis : " + ( new Date().getTime() - analysis_start_time )
2370 ForesterUtil.programMessage( PRG_NAME, "Total running time: " + ( new Date().getTime() - start_time ) + "ms " );
2371 ForesterUtil.programMessage( PRG_NAME, "Free memory : " + free_memory + "MB, total memory: "
2372 + total_memory + "MB" );
2373 ForesterUtil.programMessage( PRG_NAME, "If this application is useful to you, please cite:" );
2374 ForesterUtil.programMessage( PRG_NAME, surfacing.WWW );
2375 ForesterUtil.programMessage( PRG_NAME, "OK" );
2376 System.out.println();
2379 private static void createSplitWriters( final File out_dir,
2380 final String my_outfile,
2381 final Map<Character, Writer> split_writers ) throws IOException {
2382 split_writers.put( 'a', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2383 + "_domains_A.html" ) ) );
2384 split_writers.put( 'b', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2385 + "_domains_B.html" ) ) );
2386 split_writers.put( 'c', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2387 + "_domains_C.html" ) ) );
2388 split_writers.put( 'd', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2389 + "_domains_D.html" ) ) );
2390 split_writers.put( 'e', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2391 + "_domains_E.html" ) ) );
2392 split_writers.put( 'f', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2393 + "_domains_F.html" ) ) );
2394 split_writers.put( 'g', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2395 + "_domains_G.html" ) ) );
2396 split_writers.put( 'h', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2397 + "_domains_H.html" ) ) );
2398 split_writers.put( 'i', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2399 + "_domains_I.html" ) ) );
2400 split_writers.put( 'j', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2401 + "_domains_J.html" ) ) );
2402 split_writers.put( 'k', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2403 + "_domains_K.html" ) ) );
2404 split_writers.put( 'l', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2405 + "_domains_L.html" ) ) );
2406 split_writers.put( 'm', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2407 + "_domains_M.html" ) ) );
2408 split_writers.put( 'n', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2409 + "_domains_N.html" ) ) );
2410 split_writers.put( 'o', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2411 + "_domains_O.html" ) ) );
2412 split_writers.put( 'p', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2413 + "_domains_P.html" ) ) );
2414 split_writers.put( 'q', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2415 + "_domains_Q.html" ) ) );
2416 split_writers.put( 'r', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2417 + "_domains_R.html" ) ) );
2418 split_writers.put( 's', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2419 + "_domains_S.html" ) ) );
2420 split_writers.put( 't', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2421 + "_domains_T.html" ) ) );
2422 split_writers.put( 'u', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2423 + "_domains_U.html" ) ) );
2424 split_writers.put( 'v', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2425 + "_domains_V.html" ) ) );
2426 split_writers.put( 'w', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2427 + "_domains_W.html" ) ) );
2428 split_writers.put( 'x', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2429 + "_domains_X.html" ) ) );
2430 split_writers.put( 'y', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2431 + "_domains_Y.html" ) ) );
2432 split_writers.put( 'z', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2433 + "_domains_Z.html" ) ) );
2434 split_writers.put( '0', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2435 + "_domains_0.html" ) ) );
2438 private static void printOutPercentageOfMultidomainProteins( final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo,
2439 final Writer log_writer ) {
2441 for( final Entry<Integer, Integer> entry : all_genomes_domains_per_potein_histo.entrySet() ) {
2442 sum += entry.getValue();
2444 final double percentage = ( 100.0 * ( sum - all_genomes_domains_per_potein_histo.get( 1 ) ) ) / sum;
2445 ForesterUtil.programMessage( PRG_NAME, "Percentage of multidomain proteins: " + percentage + "%" );
2446 log( "Percentage of multidomain proteins: : " + percentage + "%", log_writer );
2449 private static void preparePhylogenyForParsimonyAnalyses( final Phylogeny intree,
2450 final String[][] input_file_properties ) {
2451 final String[] genomes = new String[ input_file_properties.length ];
2452 for( int i = 0; i < input_file_properties.length; ++i ) {
2453 if ( intree.getNodes( input_file_properties[ i ][ 1 ] ).size() > 1 ) {
2454 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
2455 + "] is not unique in input tree " + intree.getName() );
2457 genomes[ i ] = input_file_properties[ i ][ 1 ];
2460 final PhylogenyNodeIterator it = intree.iteratorPostorder();
2461 while ( it.hasNext() ) {
2462 final PhylogenyNode n = it.next();
2463 if ( ForesterUtil.isEmpty( n.getName() ) ) {
2464 if ( n.getNodeData().isHasTaxonomy()
2465 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getTaxonomyCode() ) ) {
2466 n.setName( n.getNodeData().getTaxonomy().getTaxonomyCode() );
2468 else if ( n.getNodeData().isHasTaxonomy()
2469 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
2470 n.setName( n.getNodeData().getTaxonomy().getScientificName() );
2472 else if ( n.getNodeData().isHasTaxonomy()
2473 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getCommonName() ) ) {
2474 n.setName( n.getNodeData().getTaxonomy().getCommonName() );
2478 .fatalError( surfacing.PRG_NAME,
2479 "node with no name, scientific name, common name, or taxonomy code present" );
2484 final List<String> igns = PhylogenyMethods.deleteExternalNodesPositiveSelection( genomes, intree );
2485 if ( igns.size() > 0 ) {
2486 System.out.println( "Not using the following " + igns.size() + " nodes:" );
2487 for( int i = 0; i < igns.size(); ++i ) {
2488 System.out.println( " " + i + ": " + igns.get( i ) );
2490 System.out.println( "--" );
2492 for( final String[] input_file_propertie : input_file_properties ) {
2494 intree.getNode( input_file_propertie[ 1 ] );
2496 catch ( final IllegalArgumentException e ) {
2497 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_propertie[ 1 ]
2498 + "] not present/not unique in input tree" );
2503 private static void printHelp() {
2504 System.out.println();
2505 System.out.println( "Usage:" );
2506 System.out.println();
2507 System.out.println( "% java -Xms256m -Xmx512m -cp forester.jar org.forester.applications." + surfacing.PRG_NAME
2508 + " [options] <phylogen(y|ies) infile> [external node name 1] [name 2] ... [name n]" );
2509 System.out.println();
2510 System.out.println( " Note: This software might need a significant amount of memory (heap space);" );
2512 .println( " hence use \"-Xms128m -Xmx512m\" (or more) to prevent a \"java.lang.OutOfMemoryError\"." );
2513 System.out.println();
2514 System.out.println( " Options: " );
2515 System.out.println( surfacing.DETAILEDNESS_OPTION + ": level of detail for similarities output file (default:"
2516 + DETAILEDNESS_DEFAULT + ")" );
2517 System.out.println( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION
2518 + ": to ignore combinations with self (default: not to ignore)" );
2520 .println( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION
2521 + ": to ignore domains without combinations in any species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2523 .println( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION
2524 + ": to ignore domains specific to one species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2525 System.out.println( surfacing.NOT_IGNORE_DUFS_OPTION
2526 + ": to _not_ ignore DUFs (domains with unknown function) (default: ignore DUFs)" );
2528 .println( surfacing.IGNORE_VIRAL_IDS
2529 + ": to ignore domains with ids containing 'vir', 'retro', 'transpos', 'phage', or starting with 'rv' or 'gag_'" );
2530 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_OPTION + ": sorting for similarities (default: "
2531 + DOMAIN_SORT_FILD_DEFAULT + ")" );
2532 System.out.println( surfacing.OUTPUT_FILE_OPTION + ": name for (main) output file (mandatory)" );
2533 System.out.println( surfacing.MAX_E_VALUE_OPTION + ": max (inclusive) E-value" );
2534 System.out.println( surfacing.MAX_ALLOWED_OVERLAP_OPTION + ": maximal allowed domain overlap" );
2535 System.out.println( surfacing.NO_ENGULFING_OVERLAP_OPTION + ": to ignore engulfed lower confidence domains" );
2536 System.out.println( surfacing.SPECIES_MATRIX_OPTION + ": species matrix" );
2537 System.out.println( surfacing.SCORING_OPTION + ": scoring (default:" + SCORING_DEFAULT + ")" );
2538 System.out.println( surfacing.DOMAIN_COUNT_SORT_OPTION + ": sorting for domain counts (default:"
2539 + DOMAINS_SORT_ORDER_DEFAULT + ")" );
2540 System.out.println( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION + ": domain similarity print option (default:"
2541 + DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT + ")" );
2542 System.out.println( surfacing.CUTOFF_SCORE_FILE_OPTION + ": cutoff score file" );
2543 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION
2544 + ": sort by species count first" );
2545 System.out.println( surfacing.OUTPUT_DIR_OPTION + ": output directory" );
2546 System.out.println( surfacing.PFAM_TO_GO_FILE_USE_OPTION + ": Pfam to GO mapping file" );
2547 System.out.println( surfacing.GO_OBO_FILE_USE_OPTION + ": GO terms file (OBO format)" );
2548 System.out.println( surfacing.GO_NAMESPACE_LIMIT_OPTION + ": limit GO term to one GO namespace" );
2549 System.out.println( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
2550 + "[=<suffix for pairwise comparison output files>]: to perform pairwise comparison based analyses" );
2551 System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION
2552 + ": species tree, to perform (Dollo, Fitch) parismony analyses" );
2554 .println( JACKNIFE_OPTION
2555 + ": perform jacknife resampling for domain and binary domain combination based distance matrices [default resamplings: "
2556 + JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT + "]" );
2557 System.out.println( JACKNIFE_RATIO_OPTION + ": ratio for jacknife resampling [default: "
2558 + JACKNIFE_RATIO_DEFAULT + "]" );
2559 System.out.println( JACKNIFE_RANDOM_SEED_OPTION
2560 + ": seed for random number generator for jacknife resampling [default: "
2561 + JACKNIFE_RANDOM_SEED_DEFAULT + "]" );
2562 // System.out.println( surfacing.INFER_SPECIES_TREES_OPTION
2563 // + ": to infer NJ species trees based on shared domains/binary domain combinations" );
2565 .println( surfacing.INPUT_SPECIES_TREE_OPTION
2566 + "=<treefiles in phyloXML format, separated by #>: to infer domain/binary domain combination gains/losses on given species trees" );
2567 System.out.println( surfacing.FILTER_POSITIVE_OPTION
2568 + "=<file>: to filter out proteins not containing at least one domain listed in <file>" );
2569 System.out.println( surfacing.FILTER_NEGATIVE_OPTION
2570 + "=<file>: to filter out proteins containing at least one domain listed in <file>" );
2571 System.out.println( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION
2572 + "=<file>: to filter out (ignore) domains listed in <file>" );
2573 System.out.println( surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>: to read input files from <file>" );
2575 .println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION
2576 + "=<seed>: seed for random number generator for Fitch Parsimony analysis (type: long, default: no randomization - given a choice, prefer absence" );
2577 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS
2578 + ": to consider directedness in binary combinations: e.g. A-B != B-A" );
2579 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY
2580 + ": to consider directedness and adjacency in binary combinations" );
2582 .println( surfacing.SEQ_EXTRACT_OPTION
2583 + "=<domain ids (Pfam names)>: to extract sequence names of sequences containing matching domains and/or domain-sequences (order N to C) (domain separator: '~', domain sequences speparator: '#', e.g. 'NACHT#BIR~CARD')" );
2584 System.out.println( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE
2585 + "=<file>: to perfom parsimony analysis on secondary features" );
2586 System.out.println( surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>: to presence/absence genome analysis" );
2587 System.out.println( surfacing.DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS
2588 + ": to output binary domain combinations for (downstream) graph analysis" );
2589 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS + ": to output all proteins per domain" );
2590 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION
2591 + ": e value max per domain for output of all proteins per domain" );
2592 System.out.println( surfacing.WRITE_TO_NEXUS_OPTION + ": to output in Nexus format" );
2593 System.out.println();
2594 System.out.println( "Example 1: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2595 + " org.forester.application.surfacing p2g=pfam2go_2012_02_07.txt -dufs -cos=Pfam_260_NC1"
2596 + " -no_eo -mo=0 -genomes=eukaryotes.txt -out_dir=out -o=o "
2597 + " -species_tree=tol.xml -obo=gene_ontology_2012_02_07.obo -pos_filter=f.txt -all_prot" );
2598 System.out.println();
2599 System.out.println( "Example 2: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2600 + " org.forester.application.surfacing -detail=punctilious -o=TEST.html -pwc=TEST"
2601 + " -cos=Pfam_ls_22_TC2 -p2g=pfam2go -obo=gene_ontology_edit.obo "
2602 + "-dc_sort=dom -ignore_with_self -no_singles -e=0.001 -mo=1 -no_eo -genomes=eukaryotes.txt "
2603 + "-ds_output=detailed_html -scoring=domains -sort=alpha " );
2604 System.out.println();
2607 private static void processFilter( final File filter_file, final SortedSet<DomainId> filter ) {
2608 SortedSet<String> filter_str = null;
2610 filter_str = ForesterUtil.file2set( filter_file );
2612 catch ( final IOException e ) {
2613 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2615 if ( filter_str != null ) {
2616 for( final String string : filter_str ) {
2617 filter.add( new DomainId( string ) );
2621 System.out.println( "Filter:" );
2622 for( final DomainId domainId : filter ) {
2623 System.out.println( domainId.getId() );
2628 private static String[][] processInputGenomesFile( final File input_genomes ) {
2629 String[][] input_file_properties = null;
2631 input_file_properties = ForesterUtil.file22dArray( input_genomes );
2633 catch ( final IOException e ) {
2634 ForesterUtil.fatalError( surfacing.PRG_NAME,
2635 "genomes files is to be in the following format \"<hmmpfam output file> <species>\": "
2636 + e.getLocalizedMessage() );
2638 final Set<String> specs = new HashSet<String>();
2639 final Set<String> paths = new HashSet<String>();
2640 for( int i = 0; i < input_file_properties.length; ++i ) {
2641 if ( !PhyloXmlUtil.TAXOMONY_CODE_PATTERN.matcher( input_file_properties[ i ][ 1 ] ).matches() ) {
2642 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for species code: "
2643 + input_file_properties[ i ][ 1 ] );
2645 if ( specs.contains( input_file_properties[ i ][ 1 ] ) ) {
2646 ForesterUtil.fatalError( surfacing.PRG_NAME, "species code " + input_file_properties[ i ][ 1 ]
2647 + " is not unique" );
2649 specs.add( input_file_properties[ i ][ 1 ] );
2650 if ( paths.contains( input_file_properties[ i ][ 0 ] ) ) {
2651 ForesterUtil.fatalError( surfacing.PRG_NAME, "path " + input_file_properties[ i ][ 0 ]
2652 + " is not unique" );
2654 paths.add( input_file_properties[ i ][ 0 ] );
2655 final String error = ForesterUtil.isReadableFile( new File( input_file_properties[ i ][ 0 ] ) );
2656 if ( !ForesterUtil.isEmpty( error ) ) {
2657 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
2660 return input_file_properties;
2663 private static void processPlusMinusAnalysisOption( final CommandLineArguments cla,
2664 final List<String> high_copy_base,
2665 final List<String> high_copy_target,
2666 final List<String> low_copy,
2667 final List<Object> numbers ) {
2668 if ( cla.isOptionSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2669 if ( !cla.isOptionValueSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2670 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for 'plus-minus' file: -"
2671 + surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>" );
2673 final File plus_minus_file = new File( cla.getOptionValue( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) );
2674 final String msg = ForesterUtil.isReadableFile( plus_minus_file );
2675 if ( !ForesterUtil.isEmpty( msg ) ) {
2676 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + plus_minus_file + "\": " + msg );
2678 processPlusMinusFile( plus_minus_file, high_copy_base, high_copy_target, low_copy, numbers );
2682 // First numbers is minimal difference, second is factor.
2683 private static void processPlusMinusFile( final File plus_minus_file,
2684 final List<String> high_copy_base,
2685 final List<String> high_copy_target,
2686 final List<String> low_copy,
2687 final List<Object> numbers ) {
2688 Set<String> species_set = null;
2689 int min_diff = PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT;
2690 double factor = PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT;
2692 species_set = ForesterUtil.file2set( plus_minus_file );
2694 catch ( final IOException e ) {
2695 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2697 if ( species_set != null ) {
2698 for( final String species : species_set ) {
2699 final String species_trimmed = species.substring( 1 );
2700 if ( species.startsWith( "+" ) ) {
2701 if ( low_copy.contains( species_trimmed ) ) {
2702 ForesterUtil.fatalError( surfacing.PRG_NAME,
2703 "species/genome names can not appear with both '+' and '-' suffix, as appears the case for: \""
2704 + species_trimmed + "\"" );
2706 high_copy_base.add( species_trimmed );
2708 else if ( species.startsWith( "*" ) ) {
2709 if ( low_copy.contains( species_trimmed ) ) {
2710 ForesterUtil.fatalError( surfacing.PRG_NAME,
2711 "species/genome names can not appear with both '*' and '-' suffix, as appears the case for: \""
2712 + species_trimmed + "\"" );
2714 high_copy_target.add( species_trimmed );
2716 else if ( species.startsWith( "-" ) ) {
2717 if ( high_copy_base.contains( species_trimmed ) || high_copy_target.contains( species_trimmed ) ) {
2718 ForesterUtil.fatalError( surfacing.PRG_NAME,
2719 "species/genome names can not appear with both '+' or '*' and '-' suffix, as appears the case for: \""
2720 + species_trimmed + "\"" );
2722 low_copy.add( species_trimmed );
2724 else if ( species.startsWith( "$D" ) ) {
2726 min_diff = Integer.parseInt( species.substring( 3 ) );
2728 catch ( final NumberFormatException e ) {
2729 ForesterUtil.fatalError( surfacing.PRG_NAME,
2730 "could not parse integer value for minimal difference from: \""
2731 + species.substring( 3 ) + "\"" );
2734 else if ( species.startsWith( "$F" ) ) {
2736 factor = Double.parseDouble( species.substring( 3 ) );
2738 catch ( final NumberFormatException e ) {
2739 ForesterUtil.fatalError( surfacing.PRG_NAME, "could not parse double value for factor from: \""
2740 + species.substring( 3 ) + "\"" );
2743 else if ( species.startsWith( "#" ) ) {
2748 .fatalError( surfacing.PRG_NAME,
2749 "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: \""
2752 numbers.add( new Integer( min_diff + "" ) );
2753 numbers.add( new Double( factor + "" ) );
2757 ForesterUtil.fatalError( surfacing.PRG_NAME, "'plus minus' file [" + plus_minus_file + "] appears empty" );
2761 private static void writePresentToNexus( final File output_file,
2762 final File positive_filter_file,
2763 final SortedSet<DomainId> filter,
2764 final List<GenomeWideCombinableDomains> gwcd_list ) {
2767 .writeMatrixToFile( DomainParsimonyCalculator
2768 .createMatrixOfDomainPresenceOrAbsence( gwcd_list, positive_filter_file == null ? null
2769 : filter ), output_file + DOMAINS_PRESENT_NEXUS, Format.NEXUS_BINARY );
2770 SurfacingUtil.writeMatrixToFile( DomainParsimonyCalculator
2771 .createMatrixOfBinaryDomainCombinationPresenceOrAbsence( gwcd_list ), output_file
2772 + BDC_PRESENT_NEXUS, Format.NEXUS_BINARY );
2774 catch ( final Exception e ) {
2775 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2779 private static void writeProteinListsForAllSpecies( final File output_dir,
2780 final SortedMap<Species, List<Protein>> protein_lists_per_species,
2781 final List<GenomeWideCombinableDomains> gwcd_list,
2782 final double domain_e_cutoff ) {
2783 final SortedSet<DomainId> all_domains = new TreeSet<DomainId>();
2784 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
2785 all_domains.addAll( gwcd.getAllDomainIds() );
2787 for( final DomainId domain : all_domains ) {
2788 final File out = new File( output_dir + ForesterUtil.FILE_SEPARATOR + domain + SEQ_EXTRACT_SUFFIX );
2789 SurfacingUtil.checkForOutputFileWriteability( out );
2791 final Writer proteins_file_writer = new BufferedWriter( new FileWriter( out ) );
2792 SurfacingUtil.extractProteinNames( protein_lists_per_species,
2794 proteins_file_writer,
2796 LIMIT_SPEC_FOR_PROT_EX,
2798 proteins_file_writer.close();
2800 catch ( final IOException e ) {
2801 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2803 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote proteins list to \"" + out + "\"" );