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: www.phylosoft.org/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;
48 import org.forester.evoinference.matrix.character.CharacterStateMatrix.Format;
49 import org.forester.go.GoId;
50 import org.forester.go.GoNameSpace;
51 import org.forester.go.GoTerm;
52 import org.forester.go.GoUtils;
53 import org.forester.go.OBOparser;
54 import org.forester.go.PfamToGoMapping;
55 import org.forester.go.PfamToGoParser;
56 import org.forester.io.parsers.HmmscanPerDomainTableParser;
57 import org.forester.io.parsers.HmmscanPerDomainTableParser.INDIVIDUAL_SCORE_CUTOFF;
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 INFER_SPECIES_TREES_OPTION = "species_tree_inference";
227 final static private String FILTER_POSITIVE_OPTION = "pos_filter";
228 final static private String FILTER_NEGATIVE_OPTION = "neg_filter";
229 final static private String FILTER_NEGATIVE_DOMAINS_OPTION = "neg_dom_filter";
230 final static private String INPUT_FILES_FROM_FILE_OPTION = "input";
231 final static private String INPUT_SPECIES_TREE_OPTION = "species_tree";
232 final static private String SEQ_EXTRACT_OPTION = "prot_extract";
233 final static private char SEPARATOR_FOR_INPUT_VALUES = '#';
234 final static private String PRG_VERSION = "2.252";
235 final static private String PRG_DATE = "2012.08.01";
236 final static private String E_MAIL = "czmasek@burnham.org";
237 final static private String WWW = "www.phylosoft.org/forester/applications/surfacing";
238 final static private boolean IGNORE_DUFS_DEFAULT = true;
239 final static private boolean IGNORE_COMBINATION_WITH_SAME_DEFAULLT = false;
240 final static private double MAX_E_VALUE_DEFAULT = -1;
241 final static private int MAX_ALLOWED_OVERLAP_DEFAULT = -1;
242 private static final String RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION = "random_seed";
243 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS = "consider_bdc_direction";
244 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY = "consider_bdc_adj";
245 private static final String SEQ_EXTRACT_SUFFIX = ".prot";
246 private static final String PLUS_MINUS_ANALYSIS_OPTION = "plus_minus";
247 private static final String PLUS_MINUS_DOM_SUFFIX = "_plus_minus_dom.txt";
248 private static final String PLUS_MINUS_DOM_SUFFIX_HTML = "_plus_minus_dom.html";
249 private static final String PLUS_MINUS_DC_SUFFIX_HTML = "_plus_minus_dc.html";
250 private static final int PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT = 0;
251 private static final double PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT = 1.0;
252 private static final String PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_all.txt";
253 private static final String PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_passing.txt";
254 private static final String OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS = "all_prot";
255 final static private String OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION = "all_prot_e";
258 private static final boolean VERBOSE = false;
259 private static final String OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_gains_counts";
260 private static final String OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_losses_counts";
261 private static final String DOMAIN_LENGTHS_ANALYSIS_SUFFIX = "_domain_lengths_analysis";
262 private static final boolean PERFORM_DOMAIN_LENGTH_ANALYSIS = true;
263 public static final String ALL_PFAMS_ENCOUNTERED_SUFFIX = "_all_encountered_pfams";
264 public static final String ALL_PFAMS_ENCOUNTERED_WITH_GO_ANNOTATION_SUFFIX = "_all_encountered_pfams_with_go_annotation";
265 public static final String ENCOUNTERED_PFAMS_SUMMARY_SUFFIX = "_encountered_pfams_summary";
266 public static final String ALL_PFAMS_GAINED_AS_DOMAINS_SUFFIX = "_all_pfams_gained_as_domains";
267 public static final String ALL_PFAMS_LOST_AS_DOMAINS_SUFFIX = "_all_pfams_lost_as_domains";
268 public static final String ALL_PFAMS_GAINED_AS_DC_SUFFIX = "_all_pfams_gained_as_dc";
269 public static final String ALL_PFAMS_LOST_AS_DC_SUFFIX = "_all_pfams_lost_as_dc";
270 public static final String BASE_DIRECTORY_PER_NODE_DOMAIN_GAIN_LOSS_FILES = "PER_NODE_EVENTS";
271 public static final String BASE_DIRECTORY_PER_SUBTREE_DOMAIN_GAIN_LOSS_FILES = "PER_SUBTREE_EVENTS";
272 public static final String D_PROMISCUITY_FILE_SUFFIX = "_domain_promiscuities";
273 private static final String LOG_FILE_SUFFIX = "_log.txt";
274 private static final String DATA_FILE_SUFFIX = "_domain_combination_data.txt";
275 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";
276 private static final INDIVIDUAL_SCORE_CUTOFF INDIVIDUAL_SCORE_CUTOFF_DEFAULT = INDIVIDUAL_SCORE_CUTOFF.FULL_SEQUENCE;
277 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts.txt";
278 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists.txt";
279 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping.txt";
280 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";
281 public static final String LIMIT_SPEC_FOR_PROT_EX = null; // e.g. "HUMAN"; set to null for not using this feature (default).
282 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH_MAPPED = "_dc_MAPPED_secondary_features_fitch"
283 + ForesterConstants.PHYLO_XML_SUFFIX;
284 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts_MAPPED.txt";
285 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_MAPPED.txt";
286 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";
287 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";
288 private static final boolean PERFORM_DC_REGAIN_PROTEINS_STATS = true;
290 private static void checkWriteabilityForPairwiseComparisons( final PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option,
291 final String[][] input_file_properties,
292 final String automated_pairwise_comparison_suffix,
293 final File outdir ) {
294 for( int i = 0; i < input_file_properties.length; ++i ) {
295 for( int j = 0; j < i; ++j ) {
296 final String species_i = input_file_properties[ i ][ 1 ];
297 final String species_j = input_file_properties[ j ][ 1 ];
298 String pairwise_similarities_output_file_str = PAIRWISE_DOMAIN_COMPARISONS_PREFIX + species_i + "_"
299 + species_j + automated_pairwise_comparison_suffix;
300 switch ( domain_similarity_print_option ) {
302 if ( !pairwise_similarities_output_file_str.endsWith( ".html" ) ) {
303 pairwise_similarities_output_file_str += ".html";
307 final String error = ForesterUtil
308 .isWritableFile( new File( outdir == null ? pairwise_similarities_output_file_str : outdir
309 + ForesterUtil.FILE_SEPARATOR + pairwise_similarities_output_file_str ) );
310 if ( !ForesterUtil.isEmpty( error ) ) {
311 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
317 private static StringBuilder createParametersAsString( final boolean ignore_dufs,
318 final double e_value_max,
319 final int max_allowed_overlap,
320 final boolean no_engulfing_overlaps,
321 final File cutoff_scores_file,
322 final BinaryDomainCombination.DomainCombinationType dc_type ) {
323 final StringBuilder parameters_sb = new StringBuilder();
324 parameters_sb.append( "E-value: " + e_value_max );
325 if ( cutoff_scores_file != null ) {
326 parameters_sb.append( ", Cutoff-scores-file: " + cutoff_scores_file );
329 parameters_sb.append( ", Cutoff-scores-file: not-set" );
331 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
332 parameters_sb.append( ", Max-overlap: " + max_allowed_overlap );
335 parameters_sb.append( ", Max-overlap: not-set" );
337 if ( no_engulfing_overlaps ) {
338 parameters_sb.append( ", Engulfing-overlaps: not-allowed" );
341 parameters_sb.append( ", Engulfing-overlaps: allowed" );
344 parameters_sb.append( ", Ignore-dufs: true" );
347 parameters_sb.append( ", Ignore-dufs: false" );
349 parameters_sb.append( ", DC type (if applicable): " + dc_type );
350 return parameters_sb;
354 * Warning: This side-effects 'all_bin_domain_combinations_encountered'!
358 * @param all_bin_domain_combinations_changed
359 * @param sum_of_all_domains_encountered
360 * @param all_bin_domain_combinations_encountered
361 * @param is_gains_analysis
362 * @param protein_length_stats_by_dc
363 * @throws IOException
365 private static void executeFitchGainsAnalysis( final File output_file,
366 final List<BinaryDomainCombination> all_bin_domain_combinations_changed,
367 final int sum_of_all_domains_encountered,
368 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered,
369 final boolean is_gains_analysis ) throws IOException {
370 SurfacingUtil.checkForOutputFileWriteability( output_file );
371 final Writer out = ForesterUtil.createBufferedWriter( output_file );
372 final SortedMap<Object, Integer> bdc_to_counts = ForesterUtil
373 .listToSortedCountsMap( all_bin_domain_combinations_changed );
374 final SortedSet<DomainId> all_domains_in_combination_changed_more_than_once = new TreeSet<DomainId>();
375 final SortedSet<DomainId> all_domains_in_combination_changed_only_once = new TreeSet<DomainId>();
378 for( final Object bdc_object : bdc_to_counts.keySet() ) {
379 final BinaryDomainCombination bdc = ( BinaryDomainCombination ) bdc_object;
380 final int count = bdc_to_counts.get( bdc_object );
382 ForesterUtil.unexpectedFatalError( PRG_NAME, "count < 1 " );
384 out.write( bdc + "\t" + count + ForesterUtil.LINE_SEPARATOR );
386 all_domains_in_combination_changed_more_than_once.add( bdc.getId0() );
387 all_domains_in_combination_changed_more_than_once.add( bdc.getId1() );
390 else if ( count == 1 ) {
391 all_domains_in_combination_changed_only_once.add( bdc.getId0() );
392 all_domains_in_combination_changed_only_once.add( bdc.getId1() );
396 final int all = all_bin_domain_combinations_encountered.size();
398 if ( !is_gains_analysis ) {
399 all_bin_domain_combinations_encountered.removeAll( all_bin_domain_combinations_changed );
400 never_lost = all_bin_domain_combinations_encountered.size();
401 for( final BinaryDomainCombination bdc : all_bin_domain_combinations_encountered ) {
402 out.write( bdc + "\t" + "0" + ForesterUtil.LINE_SEPARATOR );
405 if ( is_gains_analysis ) {
406 out.write( "Sum of all distinct domain combinations appearing once : " + one
407 + ForesterUtil.LINE_SEPARATOR );
408 out.write( "Sum of all distinct domain combinations appearing more than once : " + above_one
409 + ForesterUtil.LINE_SEPARATOR );
410 out.write( "Sum of all distinct domains in combinations apppearing only once : "
411 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
412 out.write( "Sum of all distinct domains in combinations apppearing more than once: "
413 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
416 out.write( "Sum of all distinct domain combinations never lost : " + never_lost
417 + ForesterUtil.LINE_SEPARATOR );
418 out.write( "Sum of all distinct domain combinations lost once : " + one
419 + ForesterUtil.LINE_SEPARATOR );
420 out.write( "Sum of all distinct domain combinations lost more than once : " + above_one
421 + ForesterUtil.LINE_SEPARATOR );
422 out.write( "Sum of all distinct domains in combinations lost only once : "
423 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
424 out.write( "Sum of all distinct domains in combinations lost more than once: "
425 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
427 out.write( "All binary combinations : " + all
428 + ForesterUtil.LINE_SEPARATOR );
429 out.write( "All domains : "
430 + sum_of_all_domains_encountered );
432 ForesterUtil.programMessage( surfacing.PRG_NAME,
433 "Wrote fitch domain combination dynamics counts analysis to \"" + output_file
437 private static void executePlusMinusAnalysis( final File output_file,
438 final List<String> plus_minus_analysis_high_copy_base,
439 final List<String> plus_minus_analysis_high_copy_target,
440 final List<String> plus_minus_analysis_low_copy,
441 final List<GenomeWideCombinableDomains> gwcd_list,
442 final SortedMap<Species, List<Protein>> protein_lists_per_species,
443 final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
444 final Map<GoId, GoTerm> go_id_to_term_map,
445 final List<Object> plus_minus_analysis_numbers ) {
446 final Set<String> all_spec = new HashSet<String>();
447 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
448 all_spec.add( gwcd.getSpecies().getSpeciesId() );
450 final File html_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX_HTML );
451 final File plain_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX );
452 final File html_out_dc = new File( output_file + PLUS_MINUS_DC_SUFFIX_HTML );
453 final File all_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX );
454 final File passing_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX );
455 final File proteins_file_base = new File( output_file + "" );
456 final int min_diff = ( ( Integer ) plus_minus_analysis_numbers.get( 0 ) ).intValue();
457 final double factor = ( ( Double ) plus_minus_analysis_numbers.get( 1 ) ).doubleValue();
459 DomainCountsDifferenceUtil.calculateCopyNumberDifferences( gwcd_list,
460 protein_lists_per_species,
461 plus_minus_analysis_high_copy_base,
462 plus_minus_analysis_high_copy_target,
463 plus_minus_analysis_low_copy,
469 domain_id_to_go_ids_map,
471 all_domains_go_ids_out_dom,
472 passing_domains_go_ids_out_dom,
473 proteins_file_base );
475 catch ( final IOException e ) {
476 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
478 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
479 + html_out_dom + "\"" );
480 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
481 + plain_out_dom + "\"" );
482 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \"" + html_out_dc
484 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based passing GO ids to \""
485 + passing_domains_go_ids_out_dom + "\"" );
486 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based all GO ids to \""
487 + all_domains_go_ids_out_dom + "\"" );
490 private static Phylogeny[] getIntrees( final File[] intree_files,
491 final int number_of_genomes,
492 final String[][] input_file_properties ) {
493 final Phylogeny[] intrees = new Phylogeny[ intree_files.length ];
495 for( final File intree_file : intree_files ) {
496 Phylogeny intree = null;
497 final String error = ForesterUtil.isReadableFile( intree_file );
498 if ( !ForesterUtil.isEmpty( error ) ) {
499 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read input tree file [" + intree_file + "]: "
503 final Phylogeny[] p_array = ParserBasedPhylogenyFactory.getInstance()
504 .create( intree_file, ParserUtils.createParserDependingOnFileType( intree_file, true ) );
505 if ( p_array.length < 1 ) {
506 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
507 + "] does not contain any phylogeny in phyloXML format" );
509 else if ( p_array.length > 1 ) {
510 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
511 + "] contains more than one phylogeny in phyloXML format" );
513 intree = p_array[ 0 ];
515 catch ( final Exception e ) {
516 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read input tree from file [" + intree_file
519 if ( ( intree == null ) || intree.isEmpty() ) {
520 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" );
522 if ( !intree.isRooted() ) {
523 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is not rooted" );
525 if ( intree.getNumberOfExternalNodes() < number_of_genomes ) {
526 ForesterUtil.fatalError( surfacing.PRG_NAME,
527 "number of external nodes [" + intree.getNumberOfExternalNodes()
528 + "] of input tree [" + intree_file
529 + "] is smaller than the number of genomes the be analyzed ["
530 + number_of_genomes + "]" );
532 final StringBuilder parent_names = new StringBuilder();
533 final int nodes_lacking_name = SurfacingUtil.getNumberOfNodesLackingName( intree, parent_names );
534 if ( nodes_lacking_name > 0 ) {
535 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] has "
536 + nodes_lacking_name + " node(s) lacking a name [parent names:" + parent_names + "]" );
538 preparePhylogenyForParsimonyAnalyses( intree, input_file_properties );
539 if ( !intree.isCompletelyBinary() ) {
540 ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "input tree [" + intree_file
541 + "] is not completely binary" );
543 intrees[ i++ ] = intree;
550 private static void log( final String msg, final Writer w ) {
553 w.write( ForesterUtil.LINE_SEPARATOR );
555 catch ( final IOException e ) {
556 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
560 public static void main( final String args[] ) {
561 final long start_time = new Date().getTime();
562 // final StringBuffer log = new StringBuffer();
563 final StringBuilder html_desc = new StringBuilder();
564 ForesterUtil.printProgramInformation( surfacing.PRG_NAME,
565 surfacing.PRG_VERSION,
569 final String nl = ForesterUtil.LINE_SEPARATOR;
570 html_desc.append( "<table>" + nl );
571 html_desc.append( "<tr><td>Produced by:</td><td>" + surfacing.PRG_NAME + "</td></tr>" + nl );
572 html_desc.append( "<tr><td>Version:</td><td>" + surfacing.PRG_VERSION + "</td></tr>" + nl );
573 html_desc.append( "<tr><td>Release Date:</td><td>" + surfacing.PRG_DATE + "</td></tr>" + nl );
574 html_desc.append( "<tr><td>Contact:</td><td>" + surfacing.E_MAIL + "</td></tr>" + nl );
575 html_desc.append( "<tr><td>WWW:</td><td>" + surfacing.WWW + "</td></tr>" + nl );
576 CommandLineArguments cla = null;
578 cla = new CommandLineArguments( args );
580 catch ( final Exception e ) {
581 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
583 if ( cla.isOptionSet( surfacing.HELP_OPTION_1 ) || cla.isOptionSet( surfacing.HELP_OPTION_2 ) ) {
584 surfacing.printHelp();
587 if ( ( args.length < 1 ) ) {
588 surfacing.printHelp();
591 final List<String> allowed_options = new ArrayList<String>();
592 allowed_options.add( surfacing.NOT_IGNORE_DUFS_OPTION );
593 allowed_options.add( surfacing.MAX_E_VALUE_OPTION );
594 allowed_options.add( surfacing.DETAILEDNESS_OPTION );
595 allowed_options.add( surfacing.OUTPUT_FILE_OPTION );
596 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_OPTION );
597 allowed_options.add( surfacing.SPECIES_MATRIX_OPTION );
598 allowed_options.add( surfacing.SCORING_OPTION );
599 allowed_options.add( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
600 allowed_options.add( surfacing.NO_ENGULFING_OVERLAP_OPTION );
601 allowed_options.add( surfacing.DOMAIN_COUNT_SORT_OPTION );
602 allowed_options.add( surfacing.CUTOFF_SCORE_FILE_OPTION );
603 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION );
604 allowed_options.add( surfacing.OUTPUT_DIR_OPTION );
605 allowed_options.add( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION );
606 allowed_options.add( surfacing.PFAM_TO_GO_FILE_USE_OPTION );
607 allowed_options.add( surfacing.GO_OBO_FILE_USE_OPTION );
608 allowed_options.add( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION );
609 allowed_options.add( surfacing.GO_NAMESPACE_LIMIT_OPTION );
610 allowed_options.add( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
611 allowed_options.add( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION );
612 allowed_options.add( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS );
613 allowed_options.add( JACKNIFE_OPTION );
614 allowed_options.add( JACKNIFE_RANDOM_SEED_OPTION );
615 allowed_options.add( JACKNIFE_RATIO_OPTION );
616 allowed_options.add( INPUT_SPECIES_TREE_OPTION );
617 //allowed_options.add( INFER_SPECIES_TREES_OPTION );
618 allowed_options.add( FILTER_POSITIVE_OPTION );
619 allowed_options.add( FILTER_NEGATIVE_OPTION );
620 allowed_options.add( INPUT_FILES_FROM_FILE_OPTION );
621 allowed_options.add( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
622 allowed_options.add( FILTER_NEGATIVE_DOMAINS_OPTION );
623 allowed_options.add( IGNORE_VIRAL_IDS );
624 allowed_options.add( SEQ_EXTRACT_OPTION );
625 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
626 allowed_options.add( SECONDARY_FEATURES_PARSIMONY_MAP_FILE );
627 allowed_options.add( PLUS_MINUS_ANALYSIS_OPTION );
628 allowed_options.add( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS );
629 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS );
630 allowed_options.add( CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY );
631 boolean ignore_dufs = surfacing.IGNORE_DUFS_DEFAULT;
632 boolean ignore_combination_with_same = surfacing.IGNORE_COMBINATION_WITH_SAME_DEFAULLT;
633 double e_value_max = surfacing.MAX_E_VALUE_DEFAULT;
634 int max_allowed_overlap = surfacing.MAX_ALLOWED_OVERLAP_DEFAULT;
635 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
636 if ( dissallowed_options.length() > 0 ) {
637 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown option(s): " + dissallowed_options );
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_files_file = null;
798 String[] input_file_names_from_file = null;
799 if ( cla.isOptionSet( surfacing.INPUT_FILES_FROM_FILE_OPTION ) ) {
800 if ( !cla.isOptionValueSet( surfacing.INPUT_FILES_FROM_FILE_OPTION ) ) {
801 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input files file: -"
802 + surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>" );
804 input_files_file = new File( cla.getOptionValue( surfacing.INPUT_FILES_FROM_FILE_OPTION ) );
805 final String msg = ForesterUtil.isReadableFile( input_files_file );
806 if ( !ForesterUtil.isEmpty( msg ) ) {
807 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + input_files_file + "\": " + msg );
810 input_file_names_from_file = ForesterUtil.file2array( input_files_file );
812 catch ( final IOException e ) {
813 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read from \"" + input_files_file + "\": " + e );
816 if ( ( cla.getNumberOfNames() < 1 )
817 && ( ( input_file_names_from_file == null ) || ( input_file_names_from_file.length < 1 ) ) ) {
818 ForesterUtil.fatalError( surfacing.PRG_NAME,
819 "No hmmpfam output file indicated is input: use comand line directly or "
820 + surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>" );
822 DomainSimilarity.DomainSimilarityScoring scoring = SCORING_DEFAULT;
823 if ( cla.isOptionSet( surfacing.SCORING_OPTION ) ) {
824 if ( !cla.isOptionValueSet( surfacing.SCORING_OPTION ) ) {
825 ForesterUtil.fatalError( surfacing.PRG_NAME,
826 "no value for scoring method for domain combinations similarity calculation: -"
827 + surfacing.SCORING_OPTION + "=<"
828 + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
829 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|"
830 + surfacing.SCORING_COMBINATION_BASED + ">\"" );
832 final String scoring_str = cla.getOptionValue( surfacing.SCORING_OPTION );
833 if ( scoring_str.equals( surfacing.SCORING_DOMAIN_COUNT_BASED ) ) {
834 scoring = DomainSimilarity.DomainSimilarityScoring.DOMAINS;
836 else if ( scoring_str.equals( surfacing.SCORING_COMBINATION_BASED ) ) {
837 scoring = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
839 else if ( scoring_str.equals( surfacing.SCORING_PROTEIN_COUNT_BASED ) ) {
840 scoring = DomainSimilarity.DomainSimilarityScoring.PROTEINS;
843 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + scoring_str
844 + "\" for scoring method for domain combinations similarity calculation: \"-"
845 + surfacing.SCORING_OPTION + "=<" + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
846 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|" + surfacing.SCORING_COMBINATION_BASED + ">\"" );
849 boolean sort_by_species_count_first = false;
850 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION ) ) {
851 sort_by_species_count_first = true;
853 boolean species_matrix = false;
854 if ( cla.isOptionSet( surfacing.SPECIES_MATRIX_OPTION ) ) {
855 species_matrix = true;
857 boolean output_protein_lists_for_all_domains = false;
858 double output_list_of_all_proteins_per_domain_e_value_max = -1;
859 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS ) ) {
860 output_protein_lists_for_all_domains = true;
862 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION ) ) {
864 output_list_of_all_proteins_per_domain_e_value_max = cla.getOptionValueAsDouble( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
866 catch ( final Exception e ) {
867 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for per domain E-value maximum" );
872 Detailedness detailedness = DETAILEDNESS_DEFAULT;
873 if ( cla.isOptionSet( surfacing.DETAILEDNESS_OPTION ) ) {
874 if ( !cla.isOptionValueSet( surfacing.DETAILEDNESS_OPTION ) ) {
875 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for -" + surfacing.DETAILEDNESS_OPTION + "=<"
876 + surfacing.DETAILEDNESS_BASIC + "|" + surfacing.DETAILEDNESS_LIST_IDS + "|"
877 + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
879 final String detness = cla.getOptionValue( surfacing.DETAILEDNESS_OPTION ).toLowerCase();
880 if ( detness.equals( surfacing.DETAILEDNESS_BASIC ) ) {
881 detailedness = DomainSimilarityCalculator.Detailedness.BASIC;
883 else if ( detness.equals( surfacing.DETAILEDNESS_LIST_IDS ) ) {
884 detailedness = DomainSimilarityCalculator.Detailedness.LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES;
886 else if ( detness.equals( surfacing.DETAILEDNESS_PUNCTILIOUS ) ) {
887 detailedness = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
890 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + detness + "\" for detailedness: \"-"
891 + surfacing.DETAILEDNESS_OPTION + "=<" + surfacing.DETAILEDNESS_BASIC + "|"
892 + surfacing.DETAILEDNESS_LIST_IDS + "|" + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
895 String automated_pairwise_comparison_suffix = null;
896 boolean perform_pwc = false;
897 boolean write_pwc_files = false;
898 if ( cla.isOptionSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
900 if ( !cla.isOptionValueSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
901 write_pwc_files = false;
904 write_pwc_files = true;
905 automated_pairwise_comparison_suffix = "_"
906 + cla.getOptionValue( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
909 String query_domain_ids = null;
910 if ( cla.isOptionSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
911 if ( !cla.isOptionValueSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
913 .fatalError( surfacing.PRG_NAME,
914 "no domain ids given for sequences with given domains to be extracted : -"
915 + surfacing.SEQ_EXTRACT_OPTION
916 + "=<ordered domain sequences, domain ids separated by '~', sequences separated by '#'>" );
918 query_domain_ids = cla.getOptionValue( surfacing.SEQ_EXTRACT_OPTION );
921 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field = DOMAIN_SORT_FILD_DEFAULT;
922 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field_for_automated_pwc = DOMAIN_SORT_FILD_DEFAULT;
923 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
924 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
925 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for domain combinations similarities sorting: -"
926 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
927 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
928 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
929 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
930 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|"
931 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
934 final String sort_str = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ).toLowerCase();
935 if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ALPHA ) ) {
936 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
937 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
939 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MAX ) ) {
940 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX;
941 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
943 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MIN ) ) {
944 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MIN;
945 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
947 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MEAN ) ) {
948 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MEAN;
949 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MEAN;
951 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT ) ) {
952 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SPECIES_COUNT;
953 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
955 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SD ) ) {
956 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SD;
957 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
959 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_DIFF ) ) {
960 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
961 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
963 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF ) ) {
964 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
965 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
967 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF ) ) {
968 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
969 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
972 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort_str
973 + "\" for domain combinations similarities sorting: \"-"
974 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
975 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
976 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
977 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
978 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|" + "|"
979 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
983 PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option = DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT;
984 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
985 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
986 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for print option: -"
987 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
988 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
989 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
991 final String sort = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ).toLowerCase();
992 if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML ) ) {
993 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.HTML;
995 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML ) ) {
996 // domain_similarity_print_option =
997 // DomainSimilarity.PRINT_OPTION.SIMPLE_HTML;
998 ForesterUtil.fatalError( surfacing.PRG_NAME, "simple HTML output not implemented yet :(" );
1000 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED ) ) {
1001 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.SIMPLE_TAB_DELIMITED;
1004 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort + "\" for print option: -"
1005 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
1006 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
1007 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
1010 GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order = DOMAINS_SORT_ORDER_DEFAULT;
1011 if ( cla.isOptionSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
1012 if ( !cla.isOptionValueSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
1013 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for sorting of domain counts: -"
1014 + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<" + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|"
1015 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1016 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1017 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1019 final String sort = cla.getOptionValue( surfacing.DOMAIN_COUNT_SORT_OPTION ).toLowerCase();
1020 if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_ALPHA ) ) {
1021 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
1023 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT ) ) {
1024 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_COUNT;
1026 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT ) ) {
1027 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_PROTEINS_COUNT;
1029 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT ) ) {
1030 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.COMBINATIONS_COUNT;
1033 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort
1034 + "\" for sorting of domain counts: \"-" + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<"
1035 + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|" + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1036 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1037 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1040 String[][] input_file_properties = null;
1041 if ( input_file_names_from_file != null ) {
1042 input_file_properties = surfacing.processInputFileNames( input_file_names_from_file );
1045 input_file_properties = surfacing.processInputFileNames( cla.getNames() );
1047 final int number_of_genomes = input_file_properties.length;
1048 if ( number_of_genomes < 2 ) {
1049 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot analyze less than two files" );
1051 if ( ( number_of_genomes < 3 ) && perform_pwc ) {
1052 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use : -"
1053 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1054 + "=<suffix> to turn on pairwise analyses with less than three input files" );
1056 checkWriteabilityForPairwiseComparisons( domain_similarity_print_option,
1057 input_file_properties,
1058 automated_pairwise_comparison_suffix,
1060 for( int i = 0; i < number_of_genomes; i++ ) {
1061 File dcc_outfile = new File( input_file_properties[ i ][ 0 ]
1062 + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
1063 if ( out_dir != null ) {
1064 dcc_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + dcc_outfile );
1066 SurfacingUtil.checkForOutputFileWriteability( dcc_outfile );
1068 File pfam_to_go_file = null;
1069 Map<DomainId, List<GoId>> domain_id_to_go_ids_map = null;
1070 int domain_id_to_go_ids_count = 0;
1071 if ( cla.isOptionSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1072 if ( !cla.isOptionValueSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1073 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for Pfam to GO mapping file: -"
1074 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>" );
1076 pfam_to_go_file = new File( cla.getOptionValue( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) );
1077 final String error = ForesterUtil.isReadableFile( pfam_to_go_file );
1078 if ( !ForesterUtil.isEmpty( error ) ) {
1079 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read Pfam to GO mapping file: " + error );
1082 final PfamToGoParser parser = new PfamToGoParser( pfam_to_go_file );
1083 final List<PfamToGoMapping> pfam_to_go_mappings = parser.parse();
1084 domain_id_to_go_ids_map = SurfacingUtil.createDomainIdToGoIdMap( pfam_to_go_mappings );
1085 if ( parser.getMappingCount() < domain_id_to_go_ids_map.size() ) {
1086 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME,
1087 "parser.getMappingCount() < domain_id_to_go_ids_map.size()" );
1089 domain_id_to_go_ids_count = parser.getMappingCount();
1091 catch ( final IOException e ) {
1092 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from Pfam to GO mapping file: " + e );
1095 File go_obo_file = null;
1096 List<GoTerm> go_terms = null;
1097 if ( cla.isOptionSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1098 if ( !cla.isOptionValueSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1099 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO OBO file: -"
1100 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>" );
1102 if ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) {
1103 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO OBO file (-"
1104 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>) without Pfam to GO mapping file ("
1105 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1107 go_obo_file = new File( cla.getOptionValue( surfacing.GO_OBO_FILE_USE_OPTION ) );
1108 final String error = ForesterUtil.isReadableFile( go_obo_file );
1109 if ( !ForesterUtil.isEmpty( error ) ) {
1110 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read GO OBO file: " + error );
1113 final OBOparser parser = new OBOparser( go_obo_file, OBOparser.ReturnType.BASIC_GO_TERM );
1114 go_terms = parser.parse();
1115 if ( parser.getGoTermCount() != go_terms.size() ) {
1117 .unexpectedFatalError( surfacing.PRG_NAME, "parser.getGoTermCount() != go_terms.size()" );
1120 catch ( final IOException e ) {
1121 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from GO OBO file: " + e );
1124 Map<GoId, GoTerm> go_id_to_term_map = null;
1125 if ( ( ( domain_id_to_go_ids_map != null ) && ( domain_id_to_go_ids_map.size() > 0 ) )
1126 && ( ( go_terms != null ) && ( go_terms.size() > 0 ) ) ) {
1127 go_id_to_term_map = GoUtils.createGoIdToGoTermMap( go_terms );
1129 GoNameSpace go_namespace_limit = null;
1130 if ( cla.isOptionSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1131 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1132 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO namespace limit (-"
1133 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<namespace>) without Pfam to GO mapping file ("
1134 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>) and GO OBO file (-"
1135 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1137 if ( !cla.isOptionValueSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1138 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO namespace limit: \"-"
1139 + 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 + ">\"" );
1144 final String go_namespace_limit_str = cla.getOptionValue( surfacing.GO_NAMESPACE_LIMIT_OPTION )
1146 if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION ) ) {
1147 go_namespace_limit = GoNameSpace.createMolecularFunction();
1149 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS ) ) {
1150 go_namespace_limit = GoNameSpace.createBiologicalProcess();
1152 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT ) ) {
1153 go_namespace_limit = GoNameSpace.createCellularComponent();
1156 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + go_namespace_limit_str
1157 + "\" for GO namespace limit: \"-" + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1158 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1159 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1160 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1163 if ( ( domain_similarity_sort_field == DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE )
1164 && ( number_of_genomes > 2 ) ) {
1165 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
1167 boolean jacknifed_distances = false;
1168 int jacknife_resamplings = JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT;
1169 double jacknife_ratio = JACKNIFE_RATIO_DEFAULT;
1170 long random_seed = JACKNIFE_RANDOM_SEED_DEFAULT;
1171 if ( cla.isOptionSet( surfacing.JACKNIFE_OPTION ) ) {
1172 if ( ( number_of_genomes < 3 ) || !perform_pwc ) {
1173 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use jacknife resampling analysis (-"
1174 + surfacing.JACKNIFE_OPTION + "[=<number of resamplings>]) without pairwise analyses ("
1175 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1176 + "=<suffix for pairwise comparison output files>)" );
1178 jacknifed_distances = true;
1179 if ( cla.isOptionHasAValue( surfacing.JACKNIFE_OPTION ) ) {
1181 jacknife_resamplings = cla.getOptionValueAsInt( surfacing.JACKNIFE_OPTION );
1183 catch ( final IOException e ) {
1184 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for number of resamplings" );
1186 if ( jacknife_resamplings < 2 ) {
1187 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use less than 2 resamplings" );
1190 if ( cla.isOptionSet( surfacing.JACKNIFE_RATIO_OPTION )
1191 && cla.isOptionHasAValue( surfacing.JACKNIFE_RATIO_OPTION ) ) {
1193 jacknife_ratio = cla.getOptionValueAsDouble( surfacing.JACKNIFE_RATIO_OPTION );
1195 catch ( final IOException e ) {
1196 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for jacknife ratio" );
1198 if ( ( jacknife_ratio <= 0.0 ) || ( jacknife_ratio >= 1.0 ) ) {
1199 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use illegal value for jacknife ratio: "
1203 if ( cla.isOptionSet( surfacing.JACKNIFE_RANDOM_SEED_OPTION )
1204 && cla.isOptionHasAValue( surfacing.JACKNIFE_RANDOM_SEED_OPTION ) ) {
1206 random_seed = cla.getOptionValueAsLong( surfacing.JACKNIFE_RANDOM_SEED_OPTION );
1208 catch ( final IOException e ) {
1209 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for random generator seed" );
1213 // boolean infer_species_trees = false;
1214 // if ( cla.isOptionSet( surfacing.INFER_SPECIES_TREES_OPTION ) ) {
1215 // if ( ( output_file == null ) || ( number_of_genomes < 3 )
1216 // || ForesterUtil.isEmpty( automated_pairwise_comparison_suffix ) ) {
1217 // ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer species trees (-"
1218 // + surfacing.INFER_SPECIES_TREES_OPTION + " without pairwise analyses ("
1219 // + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1220 // + "=<suffix for pairwise comparison output files>)" );
1222 // infer_species_trees = true;
1224 File[] intree_files = null;
1225 Phylogeny[] intrees = null;
1226 if ( cla.isOptionSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1227 // TODO FIXME if jacknife.... maybe not
1228 if ( number_of_genomes < 3 ) {
1229 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer gains and losses on input species trees (-"
1230 + surfacing.INPUT_SPECIES_TREE_OPTION + " without pairwise analyses ("
1231 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1232 + "=<suffix for pairwise comparison output files>)" );
1234 if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1235 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input tree: -"
1236 + surfacing.INPUT_SPECIES_TREE_OPTION + "=<tree file in phyloXML format>" );
1238 final String intrees_str = cla.getOptionValue( surfacing.INPUT_SPECIES_TREE_OPTION );
1239 if ( intrees_str.indexOf( "#" ) > 0 ) {
1240 final String[] intrees_strs = intrees_str.split( "#" );
1241 intree_files = new File[ intrees_strs.length ];
1243 for( final String s : intrees_strs ) {
1244 intree_files[ i++ ] = new File( s.trim() );
1248 intree_files = new File[ 1 ];
1249 intree_files[ 0 ] = new File( intrees_str );
1251 intrees = getIntrees( intree_files, number_of_genomes, input_file_properties );
1253 long random_number_seed_for_fitch_parsimony = 0l;
1254 boolean radomize_fitch_parsimony = false;
1255 if ( cla.isOptionSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1256 if ( !cla.isOptionValueSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1257 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for random number seed: -"
1258 + surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION + "=<seed>" );
1261 random_number_seed_for_fitch_parsimony = cla
1262 .getOptionValueAsLong( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
1264 catch ( final IOException e ) {
1265 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1267 radomize_fitch_parsimony = true;
1269 SortedSet<DomainId> filter = null;
1270 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1271 || ( negative_domains_filter_file != null ) ) {
1272 filter = new TreeSet<DomainId>();
1273 if ( positive_filter_file != null ) {
1274 processFilter( positive_filter_file, filter );
1276 else if ( negative_filter_file != null ) {
1277 processFilter( negative_filter_file, filter );
1279 else if ( negative_domains_filter_file != null ) {
1280 processFilter( negative_domains_filter_file, filter );
1283 Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps = null;
1284 File[] secondary_features_map_files = null;
1285 final File domain_lengths_analysis_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1286 + DOMAIN_LENGTHS_ANALYSIS_SUFFIX );
1287 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
1288 SurfacingUtil.checkForOutputFileWriteability( domain_lengths_analysis_outfile );
1290 if ( cla.isOptionSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1291 if ( !cla.isOptionValueSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1292 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for secondary features map file: -"
1293 + surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE + "=<file>" );
1295 final String[] secondary_features_map_files_strs = cla
1296 .getOptionValue( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ).split( "#" );
1297 secondary_features_map_files = new File[ secondary_features_map_files_strs.length ];
1298 domain_id_to_secondary_features_maps = new Map[ secondary_features_map_files_strs.length ];
1300 for( final String secondary_features_map_files_str : secondary_features_map_files_strs ) {
1301 secondary_features_map_files[ i ] = new File( secondary_features_map_files_str );
1302 final String error = ForesterUtil.isReadableFile( secondary_features_map_files[ i ] );
1303 if ( !ForesterUtil.isEmpty( error ) ) {
1304 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read secondary features map file: " + error );
1307 domain_id_to_secondary_features_maps[ i ] = SurfacingUtil
1308 .createDomainIdToSecondaryFeaturesMap( secondary_features_map_files[ i ] );
1310 catch ( final IOException e ) {
1311 ForesterUtil.fatalError( surfacing.PRG_NAME,
1312 "cannot read secondary features map file: " + e.getMessage() );
1314 catch ( final Exception e ) {
1315 ForesterUtil.fatalError( surfacing.PRG_NAME, "problem with contents of features map file ["
1316 + secondary_features_map_files[ i ] + "]: " + e.getMessage() );
1321 if ( out_dir == null ) {
1322 ForesterUtil.fatalError( surfacing.PRG_NAME, "no output directory indicated (-"
1323 + surfacing.OUTPUT_DIR_OPTION + "=<dir>)" );
1325 if ( output_file == null ) {
1326 ForesterUtil.fatalError( surfacing.PRG_NAME, "no name for (main) output file indicated (-"
1327 + surfacing.OUTPUT_FILE_OPTION + "=<file>)" );
1329 if ( ( domain_id_to_go_ids_map == null ) || domain_id_to_go_ids_map.isEmpty() ) {
1330 ForesterUtil.fatalError( surfacing.PRG_NAME,
1331 "no (acceptable) Pfam to GO id mapping file provided ('pfam2go file') (-"
1332 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1334 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1335 ForesterUtil.fatalError( surfacing.PRG_NAME,
1336 "no (acceptable) go id to term mapping file provided ('GO OBO file') (-"
1337 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1339 System.out.println( "Output directory : " + out_dir );
1340 if ( input_file_names_from_file != null ) {
1341 System.out.println( "Input files names from : " + input_files_file + " ["
1342 + input_file_names_from_file.length + " input files]" );
1343 html_desc.append( "<tr><td>Input files names from:</td><td>" + input_files_file + " ["
1344 + input_file_names_from_file.length + " input files]</td></tr>" + nl );
1346 if ( positive_filter_file != null ) {
1347 final int filter_size = filter.size();
1348 System.out.println( "Positive protein filter : " + positive_filter_file + " [" + filter_size
1350 html_desc.append( "<tr><td>Positive protein filter:</td><td>" + positive_filter_file + " [" + filter_size
1351 + " domain ids]</td></tr>" + nl );
1353 if ( negative_filter_file != null ) {
1354 final int filter_size = filter.size();
1355 System.out.println( "Negative protein filter : " + negative_filter_file + " [" + filter_size
1357 html_desc.append( "<tr><td>Negative protein filter:</td><td>" + negative_filter_file + " [" + filter_size
1358 + " domain ids]</td></tr>" + nl );
1360 if ( negative_domains_filter_file != null ) {
1361 final int filter_size = filter.size();
1362 System.out.println( "Negative domain filter : " + negative_domains_filter_file + " [" + filter_size
1364 html_desc.append( "<tr><td>Negative domain filter:</td><td>" + negative_domains_filter_file + " ["
1365 + filter_size + " domain ids]</td></tr>" + nl );
1367 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
1369 for( final String s : plus_minus_analysis_high_copy_base_species ) {
1370 plus0 += "+" + s + " ";
1373 for( final String s : plus_minus_analysis_high_copy_target_species ) {
1374 plus1 += "*" + s + " ";
1377 for( final String s : plus_minus_analysis_high_low_copy_species ) {
1378 minus += "-" + s + " ";
1380 System.out.println( "Plus-minus analysis : " + plus1 + "&& " + plus0 + "&& " + minus );
1381 html_desc.append( "<tr><td>Plus-minus analysis:</td><td>" + plus1 + "&& " + plus0 + "&& " + minus
1382 + "</td></tr>" + nl );
1384 if ( cutoff_scores_file != null ) {
1385 System.out.println( "Cutoff scores file : " + cutoff_scores_file );
1386 html_desc.append( "<tr><td>Cutoff scores file:</td><td>" + cutoff_scores_file + "</td></tr>" + nl );
1388 if ( e_value_max >= 0.0 ) {
1389 System.out.println( "E-value maximum (inclusive) : " + e_value_max );
1390 html_desc.append( "<tr><td>E-value maximum (inclusive):</td><td>" + e_value_max + "</td></tr>" + nl );
1392 if ( output_protein_lists_for_all_domains ) {
1393 System.out.println( "Domain E-value max : " + output_list_of_all_proteins_per_domain_e_value_max );
1394 html_desc.append( "<tr><td>Protein lists: E-value maximum per domain (inclusive):</td><td>" + output_list_of_all_proteins_per_domain_e_value_max + "</td></tr>" + nl );
1396 System.out.println( "Ignore DUFs : " + ignore_dufs );
1397 if ( ignore_virus_like_ids ) {
1398 System.out.println( "Ignore virus like ids : " + ignore_virus_like_ids );
1399 html_desc.append( "<tr><td>Ignore virus, phage, transposition related ids:</td><td>"
1400 + ignore_virus_like_ids + "</td></tr>" + nl );
1402 html_desc.append( "<tr><td>Ignore DUFs:</td><td>" + ignore_dufs + "</td></tr>" + nl );
1403 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1404 System.out.println( "Max allowed domain overlap : " + max_allowed_overlap );
1405 html_desc.append( "<tr><td>Max allowed domain overlap:</td><td>" + max_allowed_overlap + "</td></tr>" + nl );
1407 if ( no_engulfing_overlaps ) {
1408 System.out.println( "Ignore engulfed domains : " + no_engulfing_overlaps );
1409 html_desc.append( "<tr><td>Ignore (lower confidence) engulfed domains:</td><td>" + no_engulfing_overlaps
1410 + "</td></tr>" + nl );
1412 System.out.println( "Ignore singlet domains : " + ignore_domains_without_combs_in_all_spec );
1414 .append( "<tr><td>Ignore singlet domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1415 + ignore_domains_without_combs_in_all_spec + "</td></tr>" + nl );
1416 System.out.println( "Ignore species specific doms: " + ignore_species_specific_domains );
1418 .append( "<tr><td>Ignore species specific domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1419 + ignore_species_specific_domains + "</td></tr>" + nl );
1420 System.out.println( "Ignore combination with self: " + ignore_combination_with_same );
1421 html_desc.append( "<tr><td>Ignore combination with self for domain combination similarity analyses:</td><td>"
1422 + ignore_combination_with_same + "</td></tr>" + nl );
1423 System.out.println( "Consider directedness : "
1424 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) );
1425 html_desc.append( "<tr><td>Consider directedness of binary domain combinations:</td><td>"
1426 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) + "</td></tr>" + nl );
1427 if ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) {
1428 System.out.println( "Consider adjacency : "
1429 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) );
1430 html_desc.append( "<tr><td>Consider djacency of binary domain combinations:</td><td>"
1431 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) + "</td></tr>"
1434 System.out.print( "Domain counts sort order : " );
1435 switch ( dc_sort_order ) {
1436 case ALPHABETICAL_KEY_ID:
1437 System.out.println( "alphabetical" );
1439 case KEY_DOMAIN_COUNT:
1440 System.out.println( "domain count" );
1442 case KEY_DOMAIN_PROTEINS_COUNT:
1443 System.out.println( "domain proteins count" );
1445 case COMBINATIONS_COUNT:
1446 System.out.println( "domain combinations count" );
1449 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for dc sort order" );
1451 if ( domain_id_to_go_ids_map != null ) {
1452 System.out.println( "Pfam to GO mappings from : " + pfam_to_go_file + " [" + domain_id_to_go_ids_count
1454 html_desc.append( "<tr><td>Pfam to GO mappings from:</td><td>" + pfam_to_go_file + " ["
1455 + domain_id_to_go_ids_count + " mappings]" + "</td></tr>" + nl );
1457 if ( go_terms != null ) {
1458 System.out.println( "GO terms from : " + go_obo_file + " [" + go_terms.size() + " terms]" );
1459 html_desc.append( "<tr><td>GO terms from:</td><td>" + go_obo_file + " [" + go_terms.size() + " terms]"
1460 + "</td></tr>" + nl );
1462 if ( go_namespace_limit != null ) {
1463 System.out.println( "Limit GO terms to : " + go_namespace_limit.toString() );
1464 html_desc.append( "<tr><td>Limit GO terms to</td><td>" + go_namespace_limit + "</td></tr>" + nl );
1466 if ( perform_pwc ) {
1467 System.out.println( "Suffix for PWC files : " + automated_pairwise_comparison_suffix );
1468 html_desc.append( "<tr><td>Suffix for PWC files</td><td>" + automated_pairwise_comparison_suffix
1469 + "</td></tr>" + nl );
1471 if ( out_dir != null ) {
1472 System.out.println( "Output directory : " + out_dir );
1474 if ( query_domain_ids != null ) {
1475 System.out.println( "Query domains (ordered) : " + query_domain_ids );
1476 html_desc.append( "<tr><td></td><td>" + query_domain_ids + "</td></tr>" + nl );
1478 System.out.println( "Write similarities to : " + output_file );
1479 System.out.print( " Scoring method : " );
1480 html_desc.append( "<tr><td>Scoring method:</td><td>" );
1481 switch ( scoring ) {
1483 System.out.println( "domain combinations based" );
1484 html_desc.append( "domain combinations based" + "</td></tr>" + nl );
1487 System.out.println( "domain counts based" );
1488 html_desc.append( "domain counts based" + "</td></tr>" + nl );
1491 System.out.println( "domain proteins counts based" );
1492 html_desc.append( "domain proteins counts based" + "</td></tr>" + nl );
1495 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
1497 System.out.print( " Sort by : " );
1498 html_desc.append( "<tr><td>Sort by:</td><td>" );
1499 switch ( domain_similarity_sort_field ) {
1501 System.out.print( "score minimum" );
1502 html_desc.append( "score minimum" );
1505 System.out.print( "score maximum" );
1506 html_desc.append( "score maximum" );
1509 System.out.print( "score mean" );
1510 html_desc.append( "score mean" );
1513 System.out.print( "score standard deviation" );
1514 html_desc.append( "score standard deviation" );
1517 System.out.print( "species number" );
1518 html_desc.append( "species number" );
1521 System.out.print( "alphabetical domain identifier" );
1522 html_desc.append( "alphabetical domain identifier" );
1524 case MAX_DIFFERENCE:
1525 System.out.print( "(maximal) difference" );
1526 html_desc.append( "(maximal) difference" );
1528 case ABS_MAX_COUNTS_DIFFERENCE:
1529 System.out.print( "absolute (maximal) counts difference" );
1530 html_desc.append( "absolute (maximal) counts difference" );
1532 case MAX_COUNTS_DIFFERENCE:
1533 System.out.print( "(maximal) counts difference" );
1534 html_desc.append( "(maximal) counts difference" );
1537 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1539 if ( sort_by_species_count_first ) {
1540 System.out.println( " (sort by species count first)" );
1541 html_desc.append( " (sort by species count first)" );
1544 System.out.println();
1546 html_desc.append( "</td></tr>" + nl );
1547 System.out.print( " Detailedness : " );
1548 switch ( detailedness ) {
1550 System.out.println( "basic" );
1552 case LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES:
1553 System.out.println( "list combining domains for each species" );
1556 System.out.println( "punctilious" );
1559 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for detailedness" );
1561 System.out.print( " Print option : " );
1562 switch ( domain_similarity_print_option ) {
1564 System.out.println( "HTML" );
1566 case SIMPLE_TAB_DELIMITED:
1567 System.out.println( "simple tab delimited" );
1570 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for print option" );
1572 System.out.print( " Species matrix : " + species_matrix );
1573 System.out.println();
1574 final File dc_data_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + DATA_FILE_SUFFIX );
1575 System.out.println( "Domain comb data output : " + dc_data_file );
1576 html_desc.append( "<tr><td>Domain combination data output:</td><td> " + dc_data_file + " </td></tr>" );
1577 System.out.println();
1578 if ( perform_pwc ) {
1579 System.out.println( "Pairwise comparisons: " );
1580 html_desc.append( "<tr><td>Pairwise comparisons:</td><td></td></tr>" );
1581 System.out.print( " Sort by : " );
1582 html_desc.append( "<tr><td>Sort by:</td><td>" );
1583 switch ( domain_similarity_sort_field_for_automated_pwc ) {
1585 System.out.print( "score mean" );
1586 html_desc.append( "score mean" );
1589 System.out.print( "alphabetical domain identifier" );
1590 html_desc.append( "alphabetical domain identifier" );
1592 case MAX_DIFFERENCE:
1593 System.out.print( "difference" );
1594 html_desc.append( "difference" );
1596 case ABS_MAX_COUNTS_DIFFERENCE:
1597 System.out.print( "absolute counts difference" );
1598 html_desc.append( "absolute counts difference" );
1600 case MAX_COUNTS_DIFFERENCE:
1601 System.out.print( "counts difference" );
1602 html_desc.append( "counts difference" );
1606 .unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1608 System.out.println();
1609 html_desc.append( "</td></tr>" + nl );
1610 if ( jacknifed_distances ) {
1611 html_desc.append( "<tr><td>Jacknife:</td><td>" + jacknife_resamplings + " resamplings</td></tr>" + nl );
1612 html_desc.append( "<tr><td>Jacknife ratio:</td><td>" + ForesterUtil.round( jacknife_ratio, 2 )
1613 + "</td></tr>" + nl );
1614 html_desc.append( "<tr><td>Jacknife random number seed:</td><td>" + random_seed + "</td></tr>" + nl );
1615 System.out.println( " Jacknife : " + jacknife_resamplings + " resamplings" );
1616 System.out.println( " Ratio : " + ForesterUtil.round( jacknife_ratio, 2 ) );
1617 System.out.println( " Random number seed : " + random_seed );
1619 // if ( infer_species_trees ) {
1620 // html_desc.append( "<tr><td>Infer species trees:</td><td>true</td></tr>" + nl );
1621 // System.out.println( " Infer species trees : true" );
1623 if ( ( intrees != null ) && ( intrees.length > 0 ) ) {
1624 for( final File intree_file : intree_files ) {
1625 html_desc.append( "<tr><td>Intree for gain/loss parsimony analysis:</td><td>" + intree_file
1626 + "</td></tr>" + nl );
1627 System.out.println( " Intree for gain/loss pars.: " + intree_file );
1630 if ( radomize_fitch_parsimony ) {
1631 html_desc.append( "<tr><td> Random number seed for Fitch parsimony analysis:</td><td>"
1632 + random_number_seed_for_fitch_parsimony + "</td></tr>" + nl );
1633 System.out.println( " Random number seed : " + random_number_seed_for_fitch_parsimony );
1635 if ( ( domain_id_to_secondary_features_maps != null ) && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
1636 for( int i = 0; i < secondary_features_map_files.length; i++ ) {
1637 html_desc.append( "<tr><td>Secondary features map file:</td><td>"
1638 + secondary_features_map_files[ i ] + "</td></tr>" + nl );
1639 System.out.println( "Secondary features map file : " + secondary_features_map_files[ i ]
1640 + " [mappings for " + domain_id_to_secondary_features_maps[ i ].size() + " domain ids]" );
1642 System.out.println();
1643 System.out.println( "Domain ids to secondary features map:" );
1644 for( final DomainId domain_id : domain_id_to_secondary_features_maps[ i ].keySet() ) {
1645 System.out.print( domain_id.getId() );
1646 System.out.print( " => " );
1647 for( final String sec : domain_id_to_secondary_features_maps[ i ].get( domain_id ) ) {
1648 System.out.print( sec );
1649 System.out.print( " " );
1651 System.out.println();
1656 } // if ( perform_pwc ) {
1657 System.out.println();
1658 html_desc.append( "<tr><td>Command line:</td><td>\n" + cla.getCommandLineArgsAsString() + "\n</td></tr>" + nl );
1659 System.out.println( "Command line : " + cla.getCommandLineArgsAsString() );
1660 BufferedWriter[] query_domains_writer_ary = null;
1661 List<DomainId>[] query_domain_ids_array = null;
1662 if ( query_domain_ids != null ) {
1663 final String[] query_domain_ids_str_array = query_domain_ids.split( "#" );
1664 query_domain_ids_array = new ArrayList[ query_domain_ids_str_array.length ];
1665 query_domains_writer_ary = new BufferedWriter[ query_domain_ids_str_array.length ];
1666 for( int i = 0; i < query_domain_ids_str_array.length; i++ ) {
1667 String query_domain_ids_str = query_domain_ids_str_array[ i ];
1668 final String[] query_domain_ids_str_ary = query_domain_ids_str.split( "~" );
1669 final List<DomainId> query = new ArrayList<DomainId>();
1670 for( final String element : query_domain_ids_str_ary ) {
1671 query.add( new DomainId( element ) );
1673 query_domain_ids_array[ i ] = query;
1674 query_domain_ids_str = query_domain_ids_str.replace( '~', '_' );
1675 String protein_names_writer_str = query_domain_ids_str + surfacing.SEQ_EXTRACT_SUFFIX;
1676 if ( out_dir != null ) {
1677 protein_names_writer_str = out_dir + ForesterUtil.FILE_SEPARATOR + protein_names_writer_str;
1680 query_domains_writer_ary[ i ] = new BufferedWriter( new FileWriter( protein_names_writer_str ) );
1682 catch ( final IOException e ) {
1683 ForesterUtil.fatalError( surfacing.PRG_NAME, "Could not open [" + protein_names_writer_str + "]: "
1684 + e.getLocalizedMessage() );
1688 SortedMap<Species, List<Protein>> protein_lists_per_species = null; //This will only be created if neede.
1689 boolean need_protein_lists_per_species = false;
1690 if ( ( plus_minus_analysis_high_copy_base_species.size() > 0 ) || output_protein_lists_for_all_domains ) {
1691 need_protein_lists_per_species = true;
1693 if ( need_protein_lists_per_species ) {
1694 protein_lists_per_species = new TreeMap<Species, List<Protein>>();
1696 final List<GenomeWideCombinableDomains> gwcd_list = new ArrayList<GenomeWideCombinableDomains>( number_of_genomes );
1697 final SortedSet<DomainId> all_domains_encountered = new TreeSet<DomainId>();
1698 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered = new TreeSet<BinaryDomainCombination>();
1699 List<BinaryDomainCombination> all_bin_domain_combinations_gained_fitch = null;
1700 List<BinaryDomainCombination> all_bin_domain_combinations_lost_fitch = null;
1701 if ( ( intrees != null ) && ( intrees.length == 1 ) ) {
1702 all_bin_domain_combinations_gained_fitch = new ArrayList<BinaryDomainCombination>();
1703 all_bin_domain_combinations_lost_fitch = new ArrayList<BinaryDomainCombination>();
1705 final DomainLengthsTable domain_lengths_table = new DomainLengthsTable();
1706 final File per_genome_domain_promiscuity_statistics_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR
1707 + output_file + D_PROMISCUITY_FILE_SUFFIX );
1708 BufferedWriter per_genome_domain_promiscuity_statistics_writer = null;
1710 per_genome_domain_promiscuity_statistics_writer = new BufferedWriter( new FileWriter( per_genome_domain_promiscuity_statistics_file ) );
1711 per_genome_domain_promiscuity_statistics_writer.write( "Species:\t" );
1712 per_genome_domain_promiscuity_statistics_writer.write( "Mean:\t" );
1713 per_genome_domain_promiscuity_statistics_writer.write( "SD:\t" );
1714 per_genome_domain_promiscuity_statistics_writer.write( "Median:\t" );
1715 per_genome_domain_promiscuity_statistics_writer.write( "Min:\t" );
1716 per_genome_domain_promiscuity_statistics_writer.write( "Max:\t" );
1717 per_genome_domain_promiscuity_statistics_writer.write( "N:\t" );
1718 per_genome_domain_promiscuity_statistics_writer.write( "Max Promiscuous Domains:"
1719 + ForesterUtil.LINE_SEPARATOR );
1721 catch ( final IOException e2 ) {
1722 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1724 final File log_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + LOG_FILE_SUFFIX );
1725 BufferedWriter log_writer = null;
1727 log_writer = new BufferedWriter( new FileWriter( log_file ) );
1729 catch ( final IOException e2 ) {
1730 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1732 BufferedWriter dc_data_writer = null;
1734 dc_data_writer = new BufferedWriter( new FileWriter( dc_data_file ) );
1735 dc_data_writer.write( DATA_FILE_DESC );
1736 dc_data_writer.write( ForesterUtil.LINE_SEPARATOR );
1738 catch ( final IOException e2 ) {
1739 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1741 final DescriptiveStatistics protein_coverage_stats = new BasicDescriptiveStatistics();
1742 final DescriptiveStatistics all_genomes_domains_per_potein_stats = new BasicDescriptiveStatistics();
1743 final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo = new TreeMap<Integer, Integer>();
1744 final SortedSet<String> domains_which_are_always_single = new TreeSet<String>();
1745 final SortedSet<String> domains_which_are_sometimes_single_sometimes_not = new TreeSet<String>();
1746 final SortedSet<String> domains_which_never_single = new TreeSet<String>();
1747 BufferedWriter domains_per_potein_stats_writer = null;
1749 domains_per_potein_stats_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
1750 + output_file + "__domains_per_potein_stats.txt" ) );
1751 domains_per_potein_stats_writer.write( "Genome" );
1752 domains_per_potein_stats_writer.write( "\t" );
1753 domains_per_potein_stats_writer.write( "Mean" );
1754 domains_per_potein_stats_writer.write( "\t" );
1755 domains_per_potein_stats_writer.write( "SD" );
1756 domains_per_potein_stats_writer.write( "\t" );
1757 domains_per_potein_stats_writer.write( "Median" );
1758 domains_per_potein_stats_writer.write( "\t" );
1759 domains_per_potein_stats_writer.write( "N" );
1760 domains_per_potein_stats_writer.write( "\t" );
1761 domains_per_potein_stats_writer.write( "Min" );
1762 domains_per_potein_stats_writer.write( "\t" );
1763 domains_per_potein_stats_writer.write( "Max" );
1764 domains_per_potein_stats_writer.write( "\n" );
1766 catch ( final IOException e3 ) {
1767 e3.printStackTrace();
1769 Map<String, DescriptiveStatistics> protein_length_stats_by_dc = null;
1770 Map<String, DescriptiveStatistics> domain_number_stats_by_dc = null;
1771 final Map<String, DescriptiveStatistics> domain_length_stats_by_domain = new HashMap<String, DescriptiveStatistics>();
1772 if ( PERFORM_DC_REGAIN_PROTEINS_STATS ) {
1773 protein_length_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1774 domain_number_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1777 for( int i = 0; i < number_of_genomes; ++i ) {
1778 System.out.println();
1779 System.out.println( ( i + 1 ) + "/" + number_of_genomes );
1780 log( ( i + 1 ) + "/" + number_of_genomes, log_writer );
1781 System.out.println( "Processing : " + input_file_properties[ i ][ 0 ] );
1782 log( "Genome : " + input_file_properties[ i ][ 0 ], log_writer );
1783 HmmscanPerDomainTableParser parser = null;
1784 INDIVIDUAL_SCORE_CUTOFF ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF.NONE;
1785 if ( individual_score_cutoffs != null ) {
1786 ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF_DEFAULT;
1788 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1789 || ( negative_domains_filter_file != null ) ) {
1790 HmmscanPerDomainTableParser.FilterType filter_type = HmmscanPerDomainTableParser.FilterType.NONE;
1791 if ( positive_filter_file != null ) {
1792 filter_type = HmmscanPerDomainTableParser.FilterType.POSITIVE_PROTEIN;
1794 else if ( negative_filter_file != null ) {
1795 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_PROTEIN;
1797 else if ( negative_domains_filter_file != null ) {
1798 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_DOMAIN;
1800 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1801 input_file_properties[ i ][ 1 ],
1808 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1809 input_file_properties[ i ][ 1 ],
1813 if ( e_value_max >= 0.0 ) {
1814 parser.setEValueMaximum( e_value_max );
1816 parser.setIgnoreDufs( ignore_dufs );
1817 parser.setIgnoreVirusLikeIds( ignore_virus_like_ids );
1818 parser.setIgnoreEngulfedDomains( no_engulfing_overlaps );
1819 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1820 parser.setMaxAllowedOverlap( max_allowed_overlap );
1822 parser.setReturnType( HmmscanPerDomainTableParser.ReturnType.UNORDERED_PROTEIN_DOMAIN_COLLECTION_PER_PROTEIN );
1823 if ( individual_score_cutoffs != null ) {
1824 parser.setIndividualScoreCutoffs( individual_score_cutoffs );
1826 List<Protein> protein_list = null;
1828 protein_list = parser.parse();
1830 catch ( final IOException e ) {
1831 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1833 catch ( final Exception e ) {
1834 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, e.getMessage(), e );
1837 System.out.println( "Domains ignored due to negative domain filter: " );
1838 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToNegativeDomainFilterCountsMap() );
1839 System.out.println( "Domains ignored due to virus like id: " );
1840 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToVirusLikeIdCountsMap() );
1842 final double coverage = ( double ) protein_list.size() / parser.getProteinsEncountered();
1843 protein_coverage_stats.addValue( coverage );
1844 System.out.println( "Number of proteins encountered : " + parser.getProteinsEncountered() );
1845 log( "Number of proteins encountered : " + parser.getProteinsEncountered(), log_writer );
1846 System.out.println( "Number of proteins stored : " + protein_list.size() );
1847 log( "Number of proteins stored : " + protein_list.size(), log_writer );
1848 System.out.println( "Coverage : "
1849 + ForesterUtil.roundToInt( 100.0 * coverage ) + "%" );
1850 log( "Coverage : " + ForesterUtil.roundToInt( 100.0 * coverage )
1851 + "%", log_writer );
1852 System.out.println( "Domains encountered : " + parser.getDomainsEncountered() );
1853 log( "Domains encountered : " + parser.getDomainsEncountered(), log_writer );
1854 System.out.println( "Domains stored : " + parser.getDomainsStored() );
1855 log( "Domains stored : " + parser.getDomainsStored(), log_writer );
1856 System.out.println( "Distinct domains stored : "
1857 + parser.getDomainsStoredSet().size() );
1858 log( "Distinct domains stored : " + parser.getDomainsStoredSet().size(), log_writer );
1859 System.out.println( "Domains ignored due to individual score cutoffs: "
1860 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() );
1861 log( "Domains ignored due to individual score cutoffs: "
1862 + parser.getDomainsIgnoredDueToIndividualScoreCutoff(),
1864 System.out.println( "Domains ignored due to E-value : "
1865 + parser.getDomainsIgnoredDueToEval() );
1866 log( "Domains ignored due to E-value : " + parser.getDomainsIgnoredDueToEval(), log_writer );
1867 System.out.println( "Domains ignored due to DUF designation : "
1868 + parser.getDomainsIgnoredDueToDuf() );
1869 log( "Domains ignored due to DUF designation : " + parser.getDomainsIgnoredDueToDuf(), log_writer );
1870 if ( ignore_virus_like_ids ) {
1871 System.out.println( "Domains ignored due virus like ids : "
1872 + parser.getDomainsIgnoredDueToVirusLikeIds() );
1873 log( "Domains ignored due virus like ids : " + parser.getDomainsIgnoredDueToVirusLikeIds(),
1876 System.out.println( "Domains ignored due negative domain filter : "
1877 + parser.getDomainsIgnoredDueToNegativeDomainFilter() );
1878 log( "Domains ignored due negative domain filter : "
1879 + parser.getDomainsIgnoredDueToNegativeDomainFilter(),
1881 System.out.println( "Domains ignored due to overlap : "
1882 + parser.getDomainsIgnoredDueToOverlap() );
1883 log( "Domains ignored due to overlap : " + parser.getDomainsIgnoredDueToOverlap(),
1885 if ( negative_filter_file != null ) {
1886 System.out.println( "Proteins ignored due to negative filter : "
1887 + parser.getProteinsIgnoredDueToFilter() );
1888 log( "Proteins ignored due to negative filter : " + parser.getProteinsIgnoredDueToFilter(),
1891 if ( positive_filter_file != null ) {
1892 System.out.println( "Proteins ignored due to positive filter : "
1893 + parser.getProteinsIgnoredDueToFilter() );
1894 log( "Proteins ignored due to positive filter : " + parser.getProteinsIgnoredDueToFilter(),
1897 System.out.println( "Time for processing : " + parser.getTime() + "ms" );
1898 log( "", log_writer );
1899 html_desc.append( "<tr><td>" + input_file_properties[ i ][ 0 ] + " [species: "
1900 + input_file_properties[ i ][ 1 ] + "]" + ":</td><td>domains analyzed: "
1901 + parser.getDomainsStored() + "; domains ignored: [ind score cutoffs: "
1902 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() + "] [E-value cutoff: "
1903 + parser.getDomainsIgnoredDueToEval() + "] [DUF: " + parser.getDomainsIgnoredDueToDuf()
1904 + "] [virus like ids: " + parser.getDomainsIgnoredDueToVirusLikeIds()
1905 + "] [negative domain filter: " + parser.getDomainsIgnoredDueToNegativeDomainFilter()
1906 + "] [overlap: " + parser.getDomainsIgnoredDueToOverlap() + "]" );
1907 if ( negative_filter_file != null ) {
1908 html_desc.append( "; proteins ignored due to negative filter: "
1909 + parser.getProteinsIgnoredDueToFilter() );
1911 if ( positive_filter_file != null ) {
1912 html_desc.append( "; proteins ignored due to positive filter: "
1913 + parser.getProteinsIgnoredDueToFilter() );
1915 html_desc.append( "</td></tr>" + nl );
1916 // domain_partner_counts_array[ i ] =
1917 // Methods.getDomainPartnerCounts( protein_domain_collections_array[
1919 // false, input_file_properties[ i ][ 1 ] );
1922 for( final Protein protein : protein_list ) {
1923 dc_data_writer.write( SurfacingUtil.proteinToDomainCombinations( protein, count + "", "\t" )
1926 for( final Domain d : protein.getProteinDomains() ) {
1927 final String d_str = d.getDomainId().toString();
1928 if ( !domain_length_stats_by_domain.containsKey( d_str ) ) {
1929 domain_length_stats_by_domain.put( d_str, new BasicDescriptiveStatistics() );
1931 domain_length_stats_by_domain.get( d_str ).addValue( d.getLength() );
1935 catch ( final IOException e ) {
1936 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1938 SurfacingUtil.domainsPerProteinsStatistics( input_file_properties[ i ][ 1 ],
1940 all_genomes_domains_per_potein_stats,
1941 all_genomes_domains_per_potein_histo,
1942 domains_which_are_always_single,
1943 domains_which_are_sometimes_single_sometimes_not,
1944 domains_which_never_single,
1945 domains_per_potein_stats_writer );
1946 gwcd_list.add( BasicGenomeWideCombinableDomains
1947 .createInstance( protein_list,
1948 ignore_combination_with_same,
1949 new BasicSpecies( input_file_properties[ i ][ 1 ] ),
1950 domain_id_to_go_ids_map,
1952 protein_length_stats_by_dc,
1953 domain_number_stats_by_dc ) );
1954 domain_lengths_table.addLengths( protein_list );
1955 if ( gwcd_list.get( i ).getSize() > 0 ) {
1956 SurfacingUtil.writeDomainCombinationsCountsFile( input_file_properties,
1958 per_genome_domain_promiscuity_statistics_writer,
1962 if ( output_binary_domain_combinationsfor_graph_analysis ) {
1963 SurfacingUtil.writeBinaryDomainCombinationsFileForGraphAnalysis( input_file_properties,
1969 SurfacingUtil.addAllDomainIdsToSet( gwcd_list.get( i ), all_domains_encountered );
1970 SurfacingUtil.addAllBinaryDomainCombinationToSet( gwcd_list.get( i ),
1971 all_bin_domain_combinations_encountered );
1973 if ( query_domains_writer_ary != null ) {
1974 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1976 SurfacingUtil.extractProteinNames( protein_list,
1977 query_domain_ids_array[ j ],
1978 query_domains_writer_ary[ j ],
1980 LIMIT_SPEC_FOR_PROT_EX );
1981 query_domains_writer_ary[ j ].flush();
1983 catch ( final IOException e ) {
1984 e.printStackTrace();
1988 if ( need_protein_lists_per_species ) {
1989 protein_lists_per_species.put( new BasicSpecies( input_file_properties[ i ][ 1 ] ), protein_list );
1994 catch ( final IOException e2 ) {
1995 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1998 } // for( int i = 0; i < number_of_genomes; ++i ) {
1999 ForesterUtil.programMessage( PRG_NAME, "Wrote domain promiscuities to: "
2000 + per_genome_domain_promiscuity_statistics_file );
2003 domains_per_potein_stats_writer.write( "ALL" );
2004 domains_per_potein_stats_writer.write( "\t" );
2005 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.arithmeticMean() + "" );
2006 domains_per_potein_stats_writer.write( "\t" );
2007 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.sampleStandardDeviation() + "" );
2008 domains_per_potein_stats_writer.write( "\t" );
2009 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.median() + "" );
2010 domains_per_potein_stats_writer.write( "\t" );
2011 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getN() + "" );
2012 domains_per_potein_stats_writer.write( "\t" );
2013 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMin() + "" );
2014 domains_per_potein_stats_writer.write( "\t" );
2015 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMax() + "" );
2016 domains_per_potein_stats_writer.write( "\n" );
2017 domains_per_potein_stats_writer.close();
2018 printOutPercentageOfMultidomainProteins( all_genomes_domains_per_potein_histo, log_writer );
2019 ForesterUtil.map2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2020 + "__all_genomes_domains_per_potein_histo.txt" ), all_genomes_domains_per_potein_histo, "\t", "\n" );
2021 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2022 + "__domains_always_single_.txt" ), domains_which_are_always_single, "\n" );
2023 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2024 + "__domains_single_or_combined.txt" ), domains_which_are_sometimes_single_sometimes_not, "\n" );
2025 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2026 + "__domains_always_combined.txt" ), domains_which_never_single, "\n" );
2027 ForesterUtil.programMessage( PRG_NAME,
2028 "Average of proteins with a least one domain assigned: "
2029 + ( 100 * protein_coverage_stats.arithmeticMean() ) + "% (+/-"
2030 + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)" );
2031 ForesterUtil.programMessage( PRG_NAME, "Range of proteins with a least one domain assigned: " + 100
2032 * protein_coverage_stats.getMin() + "%-" + 100 * protein_coverage_stats.getMax() + "%" );
2033 log( "Average of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.arithmeticMean() )
2034 + "% (+/-" + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)", log_writer );
2035 log( "Range of prot with a least one dom assigned : " + 100 * protein_coverage_stats.getMin() + "%-"
2036 + 100 * protein_coverage_stats.getMax() + "%", log_writer );
2038 catch ( final IOException e2 ) {
2039 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
2041 if ( query_domains_writer_ary != null ) {
2042 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
2044 query_domains_writer_ary[ j ].close();
2046 catch ( final IOException e ) {
2047 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
2052 per_genome_domain_promiscuity_statistics_writer.close();
2053 dc_data_writer.close();
2056 catch ( final IOException e2 ) {
2057 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
2059 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
2061 SurfacingUtil.executeDomainLengthAnalysis( input_file_properties,
2063 domain_lengths_table,
2064 domain_lengths_analysis_outfile );
2066 catch ( final IOException e1 ) {
2067 ForesterUtil.fatalError( surfacing.PRG_NAME, e1.toString() );
2069 System.out.println();
2070 ForesterUtil.programMessage( PRG_NAME, "Wrote domain length data to: " + domain_lengths_analysis_outfile );
2071 System.out.println();
2073 final long analysis_start_time = new Date().getTime();
2074 PairwiseDomainSimilarityCalculator pw_calc = null;
2075 // double[] values_for_all_scores_histogram = null;
2076 final DomainSimilarityCalculator calc = new BasicDomainSimilarityCalculator( domain_similarity_sort_field,
2077 sort_by_species_count_first,
2078 number_of_genomes == 2 );
2079 switch ( scoring ) {
2081 pw_calc = new CombinationsBasedPairwiseDomainSimilarityCalculator();
2084 pw_calc = new DomainCountsBasedPairwiseSimilarityCalculator();
2087 pw_calc = new ProteinCountsBasedPairwiseDomainSimilarityCalculator();
2090 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
2092 DomainSimilarityCalculator.GoAnnotationOutput go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.NONE;
2093 if ( domain_id_to_go_ids_map != null ) {
2094 go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.ALL;
2096 final SortedSet<DomainSimilarity> similarities = calc
2097 .calculateSimilarities( pw_calc,
2099 ignore_domains_without_combs_in_all_spec,
2100 ignore_species_specific_domains );
2101 SurfacingUtil.decoratePrintableDomainSimilarities( similarities,
2103 go_annotation_output,
2105 go_namespace_limit );
2106 DescriptiveStatistics pw_stats = null;
2108 String my_outfile = output_file.toString();
2109 Map<Character, Writer> split_writers = null;
2110 Writer writer = null;
2111 if ( similarities.size() > MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING ) {
2112 if ( my_outfile.endsWith( ".html" ) ) {
2113 my_outfile = my_outfile.substring( 0, my_outfile.length() - 5 );
2115 split_writers = new HashMap<Character, Writer>();
2116 createSplitWriters( out_dir, my_outfile, split_writers );
2118 else if ( !my_outfile.endsWith( ".html" ) ) {
2119 my_outfile += ".html";
2120 writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) );
2122 List<Species> species_order = null;
2123 if ( species_matrix ) {
2124 species_order = new ArrayList<Species>();
2125 for( int i = 0; i < number_of_genomes; i++ ) {
2126 species_order.add( new BasicSpecies( input_file_properties[ i ][ 1 ] ) );
2129 html_desc.append( "<tr><td>Sum of all distinct binary combinations:</td><td>"
2130 + all_bin_domain_combinations_encountered.size() + "</td></tr>" + nl );
2131 html_desc.append( "<tr><td>Sum of all distinct domains:</td><td>" + all_domains_encountered.size()
2132 + "</td></tr>" + nl );
2133 html_desc.append( "<tr><td>Analysis date/time:</td><td>"
2134 + new java.text.SimpleDateFormat( "yyyy.MM.dd HH:mm:ss" ).format( new java.util.Date() )
2135 + "</td></tr>" + nl );
2136 html_desc.append( "</table>" + nl );
2137 pw_stats = SurfacingUtil
2138 .writeDomainSimilaritiesToFile( html_desc,
2139 new StringBuilder( number_of_genomes + " genomes" ),
2143 number_of_genomes == 2,
2145 domain_similarity_print_option,
2146 domain_similarity_sort_field,
2149 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote main output (includes domain similarities) to: \""
2150 + ( out_dir == null ? my_outfile : out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) + "\"" );
2152 catch ( final IOException e ) {
2153 ForesterUtil.fatalError( surfacing.PRG_NAME, "Failed to write similarites to: \"" + output_file + "\" ["
2154 + e.getMessage() + "]" );
2156 System.out.println();
2157 // values_for_all_scores_histogram = pw_stats.getDataAsDoubleArray();
2158 final Species[] species = new Species[ number_of_genomes ];
2159 for( int i = 0; i < number_of_genomes; ++i ) {
2160 species[ i ] = new BasicSpecies( input_file_properties[ i ][ 1 ] );
2162 List<Phylogeny> inferred_trees = null;
2163 if ( ( number_of_genomes > 2 ) && perform_pwc ) {
2164 final PairwiseGenomeComparator pwgc = new PairwiseGenomeComparator();
2165 pwgc.performPairwiseComparisons( html_desc,
2166 sort_by_species_count_first,
2168 ignore_domains_without_combs_in_all_spec,
2169 ignore_species_specific_domains,
2170 domain_similarity_sort_field_for_automated_pwc,
2171 domain_similarity_print_option,
2173 domain_id_to_go_ids_map,
2180 automated_pairwise_comparison_suffix,
2182 surfacing.PAIRWISE_DOMAIN_COMPARISONS_PREFIX,
2186 String matrix_output_file = new String( output_file.toString() );
2187 if ( matrix_output_file.indexOf( '.' ) > 1 ) {
2188 matrix_output_file = matrix_output_file.substring( 0, matrix_output_file.indexOf( '.' ) );
2190 if ( out_dir != null ) {
2191 matrix_output_file = out_dir + ForesterUtil.FILE_SEPARATOR + matrix_output_file;
2192 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2194 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2195 + surfacing.MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans() );
2197 .writeMatrixToFile( new File( matrix_output_file
2198 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2199 pwgc.getSharedBinaryCombinationsBasedDistances() );
2200 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2201 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2202 pwgc.getSharedDomainsBasedDistances() );
2203 final Phylogeny nj_gd = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2204 + surfacing.NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans()
2206 final Phylogeny nj_bc = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2207 + surfacing.NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2208 .getSharedBinaryCombinationsBasedDistances().get( 0 ) );
2209 final Phylogeny nj_d = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2210 + surfacing.NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2211 .getSharedDomainsBasedDistances().get( 0 ) );
2212 inferred_trees = new ArrayList<Phylogeny>();
2213 inferred_trees.add( nj_gd );
2214 inferred_trees.add( nj_bc );
2215 inferred_trees.add( nj_d );
2216 if ( jacknifed_distances ) {
2217 pwgc.performPairwiseComparisonsJacknifed( species,
2221 jacknife_resamplings,
2225 .writeMatrixToFile( new File( matrix_output_file
2227 + ForesterUtil.round( jacknife_ratio, 2 )
2229 + jacknife_resamplings
2230 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2231 pwgc.getSharedBinaryCombinationsBasedDistances() );
2233 .writeMatrixToFile( new File( matrix_output_file + "_" + ForesterUtil.round( jacknife_ratio, 2 )
2234 + "_" + jacknife_resamplings
2235 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2236 pwgc.getSharedDomainsBasedDistances() );
2237 // if ( infer_species_trees ) {
2238 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2239 // + INFERRED_SBC_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc
2240 // .getSharedBinaryCombinationsBasedDistances() );
2241 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2242 // + INFERRED_SD_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc.getSharedDomainsBasedDistances() );
2245 } // if ( ( output_file != null ) && ( number_of_genomes > 2 ) && !isEmpty( automated_pairwise_comparison_suffix ) )
2246 if ( ( out_dir != null ) && ( !perform_pwc ) ) {
2247 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2249 writePresentToNexus( output_file, positive_filter_file, filter, gwcd_list );
2250 if ( ( ( intrees != null ) && ( intrees.length > 0 ) ) && ( number_of_genomes > 2 ) ) {
2251 final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
2253 max_allowed_overlap,
2254 no_engulfing_overlaps,
2258 if ( radomize_fitch_parsimony ) {
2259 s += random_number_seed_for_fitch_parsimony + "_";
2262 for( final Phylogeny intree : intrees ) {
2263 final String outfile_name = ForesterUtil.removeSuffix( output_file.toString() ) + s
2264 + ForesterUtil.removeSuffix( intree_files[ i ].toString() );
2265 final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator.createInstance( intree,
2267 SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
2268 radomize_fitch_parsimony,
2272 domain_id_to_go_ids_map,
2275 parameters_sb.toString(),
2276 domain_id_to_secondary_features_maps,
2277 positive_filter_file == null ? null : filter,
2278 output_binary_domain_combinationsfor_graph_analysis,
2279 all_bin_domain_combinations_gained_fitch,
2280 all_bin_domain_combinations_lost_fitch,
2282 protein_length_stats_by_dc,
2283 domain_number_stats_by_dc,
2284 domain_length_stats_by_domain );
2285 // Listing of all domain combinations gained is only done if only one input tree is used.
2286 if ( ( domain_id_to_secondary_features_maps != null )
2287 && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
2289 for( final Map<DomainId, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
2290 final Map<Species, MappingResults> mapping_results_map = new TreeMap<Species, MappingResults>();
2291 final DomainParsimonyCalculator secondary_features_parsimony = DomainParsimonyCalculator
2292 .createInstance( intree, gwcd_list, domain_id_to_secondary_features_map );
2294 .executeParsimonyAnalysisForSecondaryFeatures( outfile_name
2296 + secondary_features_map_files[ j++ ],
2297 secondary_features_parsimony,
2299 parameters_sb.toString(),
2300 mapping_results_map );
2302 System.out.println();
2303 System.out.println( "Mapping to secondary features:" );
2304 for( final Species spec : mapping_results_map.keySet() ) {
2305 final MappingResults mapping_results = mapping_results_map.get( spec );
2306 final int total_domains = mapping_results.getSumOfFailures()
2307 + mapping_results.getSumOfSuccesses();
2308 System.out.print( spec + ":" );
2309 System.out.print( " mapped domains = " + mapping_results.getSumOfSuccesses() );
2310 System.out.print( ", not mapped domains = " + mapping_results.getSumOfFailures() );
2311 if ( total_domains > 0 ) {
2312 System.out.println( ", mapped ratio = "
2313 + ( 100 * mapping_results.getSumOfSuccesses() / total_domains ) + "%" );
2316 System.out.println( ", mapped ratio = n/a (total domains = 0 )" );
2323 } // for( final Phylogeny intree : intrees ) {
2325 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
2326 executePlusMinusAnalysis( output_file,
2327 plus_minus_analysis_high_copy_base_species,
2328 plus_minus_analysis_high_copy_target_species,
2329 plus_minus_analysis_high_low_copy_species,
2331 protein_lists_per_species,
2332 domain_id_to_go_ids_map,
2334 plus_minus_analysis_numbers
2337 if ( output_protein_lists_for_all_domains ) {
2338 writeProteinListsForAllSpecies( out_dir, protein_lists_per_species, gwcd_list, output_list_of_all_proteins_per_domain_e_value_max );
2341 if ( all_bin_domain_combinations_gained_fitch != null ) {
2343 executeFitchGainsAnalysis( new File( output_file
2344 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2345 all_bin_domain_combinations_gained_fitch,
2346 all_domains_encountered.size(),
2347 all_bin_domain_combinations_encountered,
2350 catch ( final IOException e ) {
2351 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2354 if ( all_bin_domain_combinations_lost_fitch != null ) {
2356 executeFitchGainsAnalysis( new File( output_file
2357 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2358 all_bin_domain_combinations_lost_fitch,
2359 all_domains_encountered.size(),
2360 all_bin_domain_combinations_encountered,
2363 catch ( final IOException e ) {
2364 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2367 final Runtime rt = java.lang.Runtime.getRuntime();
2368 final long free_memory = rt.freeMemory() / 1000000;
2369 final long total_memory = rt.totalMemory() / 1000000;
2370 ForesterUtil.programMessage( PRG_NAME, "Time for analysis : " + ( new Date().getTime() - analysis_start_time )
2372 ForesterUtil.programMessage( PRG_NAME, "Total running time: " + ( new Date().getTime() - start_time ) + "ms " );
2373 ForesterUtil.programMessage( PRG_NAME, "Free memory : " + free_memory + "MB, total memory: "
2374 + total_memory + "MB" );
2375 ForesterUtil.programMessage( PRG_NAME, "If this application is useful to you, please cite:" );
2376 ForesterUtil.programMessage( PRG_NAME, surfacing.WWW );
2377 ForesterUtil.programMessage( PRG_NAME, "OK" );
2378 System.out.println();
2381 private static void createSplitWriters( final File out_dir,
2382 final String my_outfile,
2383 final Map<Character, Writer> split_writers ) throws IOException {
2384 split_writers.put( 'a', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2385 + "_domains_A.html" ) ) );
2386 split_writers.put( 'b', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2387 + "_domains_B.html" ) ) );
2388 split_writers.put( 'c', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2389 + "_domains_C.html" ) ) );
2390 split_writers.put( 'd', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2391 + "_domains_D.html" ) ) );
2392 split_writers.put( 'e', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2393 + "_domains_E.html" ) ) );
2394 split_writers.put( 'f', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2395 + "_domains_F.html" ) ) );
2396 split_writers.put( 'g', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2397 + "_domains_G.html" ) ) );
2398 split_writers.put( 'h', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2399 + "_domains_H.html" ) ) );
2400 split_writers.put( 'i', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2401 + "_domains_I.html" ) ) );
2402 split_writers.put( 'j', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2403 + "_domains_J.html" ) ) );
2404 split_writers.put( 'k', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2405 + "_domains_K.html" ) ) );
2406 split_writers.put( 'l', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2407 + "_domains_L.html" ) ) );
2408 split_writers.put( 'm', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2409 + "_domains_M.html" ) ) );
2410 split_writers.put( 'n', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2411 + "_domains_N.html" ) ) );
2412 split_writers.put( 'o', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2413 + "_domains_O.html" ) ) );
2414 split_writers.put( 'p', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2415 + "_domains_P.html" ) ) );
2416 split_writers.put( 'q', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2417 + "_domains_Q.html" ) ) );
2418 split_writers.put( 'r', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2419 + "_domains_R.html" ) ) );
2420 split_writers.put( 's', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2421 + "_domains_S.html" ) ) );
2422 split_writers.put( 't', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2423 + "_domains_T.html" ) ) );
2424 split_writers.put( 'u', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2425 + "_domains_U.html" ) ) );
2426 split_writers.put( 'v', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2427 + "_domains_V.html" ) ) );
2428 split_writers.put( 'w', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2429 + "_domains_W.html" ) ) );
2430 split_writers.put( 'x', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2431 + "_domains_X.html" ) ) );
2432 split_writers.put( 'y', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2433 + "_domains_Y.html" ) ) );
2434 split_writers.put( 'z', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2435 + "_domains_Z.html" ) ) );
2436 split_writers.put( '0', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2437 + "_domains_0.html" ) ) );
2440 private static void printOutPercentageOfMultidomainProteins( final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo,
2441 final Writer log_writer ) {
2443 for( final Entry<Integer, Integer> entry : all_genomes_domains_per_potein_histo.entrySet() ) {
2444 sum += entry.getValue();
2446 final double percentage = 100.0 * ( sum - all_genomes_domains_per_potein_histo.get( 1 ) ) / sum;
2447 ForesterUtil.programMessage( PRG_NAME, "Percentage of multidomain proteins: " + percentage + "%" );
2448 log( "Percentage of multidomain proteins: : " + percentage + "%", log_writer );
2451 private static void preparePhylogenyForParsimonyAnalyses( final Phylogeny intree,
2452 final String[][] input_file_properties ) {
2453 final String[] genomes = new String[ input_file_properties.length ];
2454 for( int i = 0; i < input_file_properties.length; ++i ) {
2455 if ( intree.getNodes( input_file_properties[ i ][ 1 ] ).size() > 1 ) {
2456 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
2457 + "] is not unique in input tree " + intree.getName() );
2459 genomes[ i ] = input_file_properties[ i ][ 1 ];
2462 final PhylogenyNodeIterator it = intree.iteratorPostorder();
2463 while ( it.hasNext() ) {
2464 final PhylogenyNode n = it.next();
2465 if ( ForesterUtil.isEmpty( n.getName() ) ) {
2466 if ( n.getNodeData().isHasTaxonomy()
2467 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getTaxonomyCode() ) ) {
2468 n.setName( n.getNodeData().getTaxonomy().getTaxonomyCode() );
2470 else if ( n.getNodeData().isHasTaxonomy()
2471 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
2472 n.setName( n.getNodeData().getTaxonomy().getScientificName() );
2474 else if ( n.getNodeData().isHasTaxonomy()
2475 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getCommonName() ) ) {
2476 n.setName( n.getNodeData().getTaxonomy().getCommonName() );
2480 .fatalError( surfacing.PRG_NAME,
2481 "node with no name, scientific name, common name, or taxonomy code present" );
2486 final List<String> igns = PhylogenyMethods.deleteExternalNodesPositiveSelection( genomes, intree );
2487 if ( igns.size() > 0 ) {
2488 System.out.println( "Not using the following " + igns.size() + " nodes:" );
2489 for( int i = 0; i < igns.size(); ++i ) {
2490 System.out.println( " " + i + ": " + igns.get( i ) );
2492 System.out.println( "--" );
2494 for( int i = 0; i < input_file_properties.length; ++i ) {
2496 intree.getNode( input_file_properties[ i ][ 1 ] );
2498 catch ( final IllegalArgumentException e ) {
2499 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
2500 + "] not present/not unique in input tree" );
2506 private static void printHelp() {
2507 System.out.println();
2508 System.out.println( "Usage:" );
2509 System.out.println();
2510 System.out.println( "% java -Xms256m -Xmx512m -cp forester.jar org.forester.applications." + surfacing.PRG_NAME
2511 + " [options] <phylogen(y|ies) infile> [external node name 1] [name 2] ... [name n]" );
2512 System.out.println();
2513 System.out.println( " Note: This software might need a significant amount of memory (heap space);" );
2515 .println( " hence use \"-Xms128m -Xmx512m\" (or more) to prevent a \"java.lang.OutOfMemoryError\"." );
2516 System.out.println();
2517 System.out.println( " Options: " );
2518 System.out.println( surfacing.DETAILEDNESS_OPTION + ": level of detail for similarities output file (default:"
2519 + DETAILEDNESS_DEFAULT + ")" );
2520 System.out.println( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION
2521 + ": to ignore combinations with self (default: not to ignore)" );
2523 .println( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION
2524 + ": to ignore domains without combinations in any species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2526 .println( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION
2527 + ": to ignore domains specific to one species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2528 System.out.println( surfacing.NOT_IGNORE_DUFS_OPTION
2529 + ": to _not_ ignore DUFs (domains with unknown function) (default: ignore DUFs)" );
2531 .println( surfacing.IGNORE_VIRAL_IDS
2532 + ": to ignore domains with ids containing 'vir', 'retro', 'transpos', 'phage', or starting with 'rv' or 'gag_'" );
2533 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_OPTION + ": sorting for similarities (default: "
2534 + DOMAIN_SORT_FILD_DEFAULT + ")" );
2535 System.out.println( surfacing.OUTPUT_FILE_OPTION + ": name for (main) output file (mandatory)" );
2536 System.out.println( surfacing.MAX_E_VALUE_OPTION + ": max (inclusive) E-value" );
2537 System.out.println( surfacing.MAX_ALLOWED_OVERLAP_OPTION + ": maximal allowed domain overlap" );
2538 System.out.println( surfacing.NO_ENGULFING_OVERLAP_OPTION + ": to ignore engulfed lower confidence domains" );
2539 System.out.println( surfacing.SPECIES_MATRIX_OPTION + ": species matrix" );
2540 System.out.println( surfacing.SCORING_OPTION + ": scoring (default:" + SCORING_DEFAULT + ")" );
2541 System.out.println( surfacing.DOMAIN_COUNT_SORT_OPTION + ": sorting for domain counts (default:"
2542 + DOMAINS_SORT_ORDER_DEFAULT + ")" );
2543 System.out.println( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION + ": domain similarity print option (default:"
2544 + DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT + ")" );
2545 System.out.println( surfacing.CUTOFF_SCORE_FILE_OPTION + ": cutoff score file" );
2546 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION
2547 + ": sort by species count first" );
2548 System.out.println( surfacing.OUTPUT_DIR_OPTION + ": output directory" );
2549 System.out.println( surfacing.PFAM_TO_GO_FILE_USE_OPTION + ": Pfam to GO mapping file" );
2550 System.out.println( surfacing.GO_OBO_FILE_USE_OPTION + ": GO terms file (OBO format)" );
2551 System.out.println( surfacing.GO_NAMESPACE_LIMIT_OPTION + ": limit GO term to one GO namespace" );
2552 System.out.println( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
2553 + "[=<suffix for pairwise comparison output files>]: to perform pairwise comparison based analyses" );
2554 System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION
2555 + ": species tree, to perform (Dollo, Fitch) parismony analyses" );
2557 .println( JACKNIFE_OPTION
2558 + ": perform jacknife resampling for domain and binary domain combination based distance matrices [default resamplings: "
2559 + JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT + "]" );
2560 System.out.println( JACKNIFE_RATIO_OPTION + ": ratio for jacknife resampling [default: "
2561 + JACKNIFE_RATIO_DEFAULT + "]" );
2562 System.out.println( JACKNIFE_RANDOM_SEED_OPTION
2563 + ": seed for random number generator for jacknife resampling [default: "
2564 + JACKNIFE_RANDOM_SEED_DEFAULT + "]" );
2565 // System.out.println( surfacing.INFER_SPECIES_TREES_OPTION
2566 // + ": to infer NJ species trees based on shared domains/binary domain combinations" );
2568 .println( surfacing.INPUT_SPECIES_TREE_OPTION
2569 + "=<treefiles in phyloXML format, separated by #>: to infer domain/binary domain combination gains/losses on given species trees" );
2570 System.out.println( surfacing.FILTER_POSITIVE_OPTION
2571 + "=<file>: to filter out proteins not containing at least one domain listed in <file>" );
2572 System.out.println( surfacing.FILTER_NEGATIVE_OPTION
2573 + "=<file>: to filter out proteins containing at least one domain listed in <file>" );
2574 System.out.println( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION
2575 + "=<file>: to filter out (ignore) domains listed in <file>" );
2576 System.out.println( surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>: to read input files from <file>" );
2578 .println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION
2579 + "=<seed>: seed for random number generator for Fitch Parsimony analysis (type: long, default: no randomization - given a choice, prefer absence" );
2580 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS
2581 + ": to consider directedness in binary combinations: e.g. A-B != B-A" );
2582 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY
2583 + ": to consider directedness and adjacency in binary combinations" );
2585 .println( surfacing.SEQ_EXTRACT_OPTION
2586 + "=<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')" );
2587 System.out.println( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE
2588 + "=<file>: to perfom parsimony analysis on secondary features" );
2589 System.out.println( surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>: to presence/absence genome analysis" );
2590 System.out.println( surfacing.DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS
2591 + ": to output binary domain combinations for (downstream) graph analysis" );
2592 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS + ": to output all proteins per domain" );
2593 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION + ": e value max per domain for output of all proteins per domain" );
2595 System.out.println();
2596 System.out.println( "Example 1: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2597 + " org.forester.application.surfacing p2g=pfam2go_2012_02_07.txt -dufs -cos=Pfam_260_NC1"
2598 + " -no_eo -mo=0 -input=genomes_limited.txt -out_dir=out -o=o "
2599 + " -species_tree=tol.xml -obo=gene_ontology_2012_02_07.obo -pos_filter=f.txt -all_prot" );
2600 System.out.println();
2601 System.out.println( "Example 2: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2602 + " org.forester.application.surfacing -detail=punctilious -o=TEST.html -pwc=TEST"
2603 + " -cos=Pfam_ls_22_TC2 -p2g=pfam2go -obo=gene_ontology_edit.obo "
2604 + "-dc_sort=dom -ignore_with_self -no_singles -e=0.001 -mo=1 -no_eo "
2605 + "-ds_output=detailed_html -scoring=domains -sort=alpha human mouse brafl strpu" );
2606 System.out.println();
2609 private static void processFilter( final File filter_file, final SortedSet<DomainId> filter ) {
2610 SortedSet<String> filter_str = null;
2612 filter_str = ForesterUtil.file2set( filter_file );
2614 catch ( final IOException e ) {
2615 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2617 if ( filter_str != null ) {
2618 for( final String string : filter_str ) {
2619 filter.add( new DomainId( string ) );
2623 System.out.println( "Filter:" );
2624 for( final DomainId domainId : filter ) {
2625 System.out.println( domainId.getId() );
2630 private static String[][] processInputFileNames( final String[] names ) {
2631 final String[][] input_file_properties = new String[ names.length ][];
2632 for( int i = 0; i < names.length; ++i ) {
2633 if ( names[ i ].indexOf( SEPARATOR_FOR_INPUT_VALUES ) < 0 ) {
2634 input_file_properties[ i ] = new String[ 2 ];
2635 input_file_properties[ i ][ 0 ] = names[ i ];
2636 input_file_properties[ i ][ 1 ] = names[ i ];
2639 input_file_properties[ i ] = names[ i ].split( surfacing.SEPARATOR_FOR_INPUT_VALUES + "" );
2640 if ( input_file_properties[ i ].length != 3 ) {
2642 .fatalError( surfacing.PRG_NAME,
2643 "properties for the input files (hmmpfam output) are expected "
2644 + "to be in the following format \"<hmmpfam output file>#<species>\" (or just one word, which is both the filename and the species id), instead received \""
2645 + names[ i ] + "\"" );
2648 final String error = ForesterUtil.isReadableFile( new File( input_file_properties[ i ][ 0 ] ) );
2649 if ( !ForesterUtil.isEmpty( error ) ) {
2650 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
2653 return input_file_properties;
2656 private static void processPlusMinusAnalysisOption( final CommandLineArguments cla,
2657 final List<String> high_copy_base,
2658 final List<String> high_copy_target,
2659 final List<String> low_copy,
2660 final List<Object> numbers ) {
2661 if ( cla.isOptionSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2662 if ( !cla.isOptionValueSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2663 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for 'plus-minus' file: -"
2664 + surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>" );
2666 final File plus_minus_file = new File( cla.getOptionValue( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) );
2667 final String msg = ForesterUtil.isReadableFile( plus_minus_file );
2668 if ( !ForesterUtil.isEmpty( msg ) ) {
2669 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + plus_minus_file + "\": " + msg );
2671 processPlusMinusFile( plus_minus_file, high_copy_base, high_copy_target, low_copy, numbers );
2675 // First numbers is minimal difference, second is factor.
2676 private static void processPlusMinusFile( final File plus_minus_file,
2677 final List<String> high_copy_base,
2678 final List<String> high_copy_target,
2679 final List<String> low_copy,
2680 final List<Object> numbers ) {
2681 Set<String> species_set = null;
2682 int min_diff = PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT;
2683 double factor = PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT;
2685 species_set = ForesterUtil.file2set( plus_minus_file );
2687 catch ( final IOException e ) {
2688 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2690 if ( species_set != null ) {
2691 for( final String species : species_set ) {
2692 final String species_trimmed = species.substring( 1 );
2693 if ( species.startsWith( "+" ) ) {
2694 if ( low_copy.contains( species_trimmed ) ) {
2695 ForesterUtil.fatalError( surfacing.PRG_NAME,
2696 "species/genome names can not appear with both '+' and '-' suffix, as appears the case for: \""
2697 + species_trimmed + "\"" );
2699 high_copy_base.add( species_trimmed );
2701 else if ( species.startsWith( "*" ) ) {
2702 if ( low_copy.contains( species_trimmed ) ) {
2703 ForesterUtil.fatalError( surfacing.PRG_NAME,
2704 "species/genome names can not appear with both '*' and '-' suffix, as appears the case for: \""
2705 + species_trimmed + "\"" );
2707 high_copy_target.add( species_trimmed );
2709 else if ( species.startsWith( "-" ) ) {
2710 if ( high_copy_base.contains( species_trimmed ) || high_copy_target.contains( species_trimmed ) ) {
2711 ForesterUtil.fatalError( surfacing.PRG_NAME,
2712 "species/genome names can not appear with both '+' or '*' and '-' suffix, as appears the case for: \""
2713 + species_trimmed + "\"" );
2715 low_copy.add( species_trimmed );
2717 else if ( species.startsWith( "$D" ) ) {
2719 min_diff = Integer.parseInt( species.substring( 3 ) );
2721 catch ( final NumberFormatException e ) {
2722 ForesterUtil.fatalError( surfacing.PRG_NAME,
2723 "could not parse integer value for minimal difference from: \""
2724 + species.substring( 3 ) + "\"" );
2727 else if ( species.startsWith( "$F" ) ) {
2729 factor = Double.parseDouble( species.substring( 3 ) );
2731 catch ( final NumberFormatException e ) {
2732 ForesterUtil.fatalError( surfacing.PRG_NAME, "could not parse double value for factor from: \""
2733 + species.substring( 3 ) + "\"" );
2736 else if ( species.startsWith( "#" ) ) {
2741 .fatalError( surfacing.PRG_NAME,
2742 "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: \""
2745 numbers.add( new Integer( min_diff + "" ) );
2746 numbers.add( new Double( factor + "" ) );
2750 ForesterUtil.fatalError( surfacing.PRG_NAME, "'plus minus' file [" + plus_minus_file + "] appears empty" );
2754 private static void writePresentToNexus( final File output_file,
2755 final File positive_filter_file,
2756 final SortedSet<DomainId> filter,
2757 final List<GenomeWideCombinableDomains> gwcd_list ) {
2760 .writeMatrixToFile( DomainParsimonyCalculator
2761 .createMatrixOfDomainPresenceOrAbsence( gwcd_list, positive_filter_file == null ? null
2762 : filter ), output_file + DOMAINS_PRESENT_NEXUS, Format.NEXUS_BINARY );
2763 SurfacingUtil.writeMatrixToFile( DomainParsimonyCalculator
2764 .createMatrixOfBinaryDomainCombinationPresenceOrAbsence( gwcd_list ), output_file
2765 + BDC_PRESENT_NEXUS, Format.NEXUS_BINARY );
2767 catch ( final Exception e ) {
2768 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2772 private static void writeProteinListsForAllSpecies( final File output_dir,
2773 final SortedMap<Species, List<Protein>> protein_lists_per_species,
2774 final List<GenomeWideCombinableDomains> gwcd_list,
2775 final double domain_e_cutoff ) {
2776 final SortedSet<DomainId> all_domains = new TreeSet<DomainId>();
2777 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
2778 all_domains.addAll( gwcd.getAllDomainIds() );
2780 for( final DomainId domain : all_domains ) {
2781 final File out = new File( output_dir + ForesterUtil.FILE_SEPARATOR + domain + SEQ_EXTRACT_SUFFIX );
2782 SurfacingUtil.checkForOutputFileWriteability( out );
2784 final Writer proteins_file_writer = new BufferedWriter( new FileWriter( out ) );
2785 SurfacingUtil.extractProteinNames( protein_lists_per_species,
2787 proteins_file_writer,
2789 LIMIT_SPEC_FOR_PROT_EX,
2791 proteins_file_writer.close();
2793 catch ( final IOException e ) {
2794 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2796 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote proteins list to \"" + out + "\"" );