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;
47 import org.forester.evoinference.distance.NeighborJoining;
48 import org.forester.evoinference.matrix.character.CharacterStateMatrix.Format;
49 import org.forester.evoinference.matrix.distance.DistanceMatrix;
50 import org.forester.go.GoId;
51 import org.forester.go.GoNameSpace;
52 import org.forester.go.GoTerm;
53 import org.forester.go.GoUtils;
54 import org.forester.go.OBOparser;
55 import org.forester.go.PfamToGoMapping;
56 import org.forester.go.PfamToGoParser;
57 import org.forester.io.parsers.HmmscanPerDomainTableParser;
58 import org.forester.io.parsers.HmmscanPerDomainTableParser.INDIVIDUAL_SCORE_CUTOFF;
59 import org.forester.io.parsers.util.ParserUtils;
60 import org.forester.io.writers.PhylogenyWriter;
61 import org.forester.phylogeny.Phylogeny;
62 import org.forester.phylogeny.PhylogenyMethods;
63 import org.forester.phylogeny.PhylogenyNode;
64 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
65 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
66 import org.forester.protein.BinaryDomainCombination;
67 import org.forester.protein.Domain;
68 import org.forester.protein.DomainId;
69 import org.forester.protein.Protein;
70 import org.forester.species.BasicSpecies;
71 import org.forester.species.Species;
72 import org.forester.surfacing.BasicDomainSimilarityCalculator;
73 import org.forester.surfacing.BasicGenomeWideCombinableDomains;
74 import org.forester.surfacing.CombinationsBasedPairwiseDomainSimilarityCalculator;
75 import org.forester.surfacing.DomainCountsBasedPairwiseSimilarityCalculator;
76 import org.forester.surfacing.DomainCountsDifferenceUtil;
77 import org.forester.surfacing.DomainLengthsTable;
78 import org.forester.surfacing.DomainParsimonyCalculator;
79 import org.forester.surfacing.DomainSimilarity;
80 import org.forester.surfacing.DomainSimilarity.DomainSimilarityScoring;
81 import org.forester.surfacing.DomainSimilarity.DomainSimilaritySortField;
82 import org.forester.surfacing.DomainSimilarityCalculator;
83 import org.forester.surfacing.DomainSimilarityCalculator.Detailedness;
84 import org.forester.surfacing.GenomeWideCombinableDomains;
85 import org.forester.surfacing.GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder;
86 import org.forester.surfacing.MappingResults;
87 import org.forester.surfacing.PairwiseDomainSimilarityCalculator;
88 import org.forester.surfacing.PairwiseGenomeComparator;
89 import org.forester.surfacing.PrintableDomainSimilarity;
90 import org.forester.surfacing.PrintableDomainSimilarity.PRINT_OPTION;
91 import org.forester.surfacing.ProteinCountsBasedPairwiseDomainSimilarityCalculator;
92 import org.forester.surfacing.SurfacingUtil;
93 import org.forester.util.BasicDescriptiveStatistics;
94 import org.forester.util.BasicTable;
95 import org.forester.util.BasicTableParser;
96 import org.forester.util.CommandLineArguments;
97 import org.forester.util.DescriptiveStatistics;
98 import org.forester.util.ForesterConstants;
99 import org.forester.util.ForesterUtil;
101 public class surfacing {
103 private static final int MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING = 1000;
104 public final static String DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS = "graph_analysis_out";
105 public final static String DOMAIN_COMBINITONS_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_dc.dot";
106 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_fitch_present_dc.dot";
107 public final static String DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX = ".dcc";
109 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS = "_dollo_gl_d";
110 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_gl_dc";
111 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_DOMAINS = "_fitch_gl_d";
112 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_gl_dc";
114 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS = "_dollo_glc_d";
115 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_glc_dc";
116 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_DOMAINS = "_fitch_glc_d";
117 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_glc_dc";
119 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_BC = "_fitch_gains_dc";
120 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_HTML_BC = "_fitch_gains_dc.html";
121 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_BC = "_fitch_losses_dc";
122 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_HTML_BC = "_fitch_losses_dc.html";
123 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC = "_fitch_present_dc";
124 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_HTML_BC = "_fitch_present_dc.html";
125 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_D = "_dollo_gains_d";
126 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_HTML_D = "_dollo_gains_d.html";
127 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_D = "_dollo_losses_d";
128 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_HTML_D = "_dollo_losses_d.html";
129 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_D = "_dollo_present_d";
130 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_HTML_D = "_dollo_present_d.html";
131 public final static String DOMAINS_PRESENT_NEXUS = "_dom.nex";
132 public final static String BDC_PRESENT_NEXUS = "_dc.nex";
134 public final static String PRG_NAME = "surfacing";
135 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_d_dollo"
136 + ForesterConstants.PHYLO_XML_SUFFIX;
137 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_d_fitch"
138 + ForesterConstants.PHYLO_XML_SUFFIX;
139 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_dc_dollo"
140 + ForesterConstants.PHYLO_XML_SUFFIX;
141 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_dc_fitch"
142 + ForesterConstants.PHYLO_XML_SUFFIX;
143 public static final String NEXUS_EXTERNAL_DOMAINS = "_dom.nex";
144 public static final String NEXUS_EXTERNAL_DOMAIN_COMBINATIONS = "_dc.nex";
145 public static final String NEXUS_SECONDARY_FEATURES = "_secondary_features.nex";
146 public static final String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_gl_secondary_features";
147 public static final String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_glc_secondary_features";
148 public static final String PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES = "_dollo_gains_secondary_features";
149 public static final String PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES = "_dollo_losses_secondary_features";
150 public static final String PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES = "_dollo_present_secondary_features";
151 public static final String SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_secondary_features_dollo"
152 + ForesterConstants.PHYLO_XML_SUFFIX;
153 public static final String PARSIMONY_OUTPUT_DOLLO_ALL_GOID_D_ALL_NAMESPACES = "_dollo_goid_d";
154 public static final String PARSIMONY_OUTPUT_FITCH_ALL_GOID_BC_ALL_NAMESPACES = "_fitch_goid_dc";
155 final static private String HELP_OPTION_1 = "help";
156 final static private String HELP_OPTION_2 = "h";
157 final static private String OUTPUT_DIR_OPTION = "out_dir";
158 final static private String SCORING_OPTION = "scoring";
159 private static final DomainSimilarityScoring SCORING_DEFAULT = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
160 final static private String SCORING_DOMAIN_COUNT_BASED = "domains";
161 final static private String SCORING_PROTEIN_COUNT_BASED = "proteins";
162 final static private String SCORING_COMBINATION_BASED = "combinations";
163 final static private String DETAILEDNESS_OPTION = "detail";
164 private final static Detailedness DETAILEDNESS_DEFAULT = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
165 final static private String SPECIES_MATRIX_OPTION = "smatrix";
166 final static private String DETAILEDNESS_BASIC = "basic";
167 final static private String DETAILEDNESS_LIST_IDS = "list_ids";
168 final static private String DETAILEDNESS_PUNCTILIOUS = "punctilious";
169 final static private String DOMAIN_SIMILARITY_SORT_OPTION = "sort";
170 private static final DomainSimilaritySortField DOMAIN_SORT_FILD_DEFAULT = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
171 final static private String DOMAIN_SIMILARITY_SORT_MIN = "min";
172 final static private String DOMAIN_SIMILARITY_SORT_MAX = "max";
173 final static private String DOMAIN_SIMILARITY_SORT_SD = "sd";
174 final static private String DOMAIN_SIMILARITY_SORT_MEAN = "mean";
175 final static private String DOMAIN_SIMILARITY_SORT_DIFF = "diff";
176 final static private String DOMAIN_SIMILARITY_SORT_COUNTS_DIFF = "count_diff";
177 final static private String DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF = "abs_count_diff";
178 final static private String DOMAIN_SIMILARITY_SORT_SPECIES_COUNT = "species";
179 final static private String DOMAIN_SIMILARITY_SORT_ALPHA = "alpha";
180 final static private String DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION = "species_first";
181 final static private String DOMAIN_COUNT_SORT_OPTION = "dc_sort";
182 private static final GenomeWideCombinableDomainsSortOrder DOMAINS_SORT_ORDER_DEFAULT = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
183 final static private String DOMAIN_COUNT_SORT_ALPHA = "alpha";
184 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT = "dom";
185 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT = "prot";
186 final static private String DOMAIN_COUNT_SORT_COMBINATIONS_COUNT = "comb";
187 final static private String CUTOFF_SCORE_FILE_OPTION = "cos";
188 final static private String NOT_IGNORE_DUFS_OPTION = "dufs";
189 final static private String MAX_E_VALUE_OPTION = "e";
190 final static private String MAX_ALLOWED_OVERLAP_OPTION = "mo";
191 final static private String NO_ENGULFING_OVERLAP_OPTION = "no_eo";
192 final static private String IGNORE_COMBINATION_WITH_SAME_OPTION = "ignore_self_comb";
193 final static private String PAIRWISE_DOMAIN_COMPARISONS_PREFIX = "pwc_";
194 final static private String PAIRWISE_DOMAIN_COMPARISONS_OPTION = "pwc";
195 final static private String OUTPUT_FILE_OPTION = "o";
196 final static private String PFAM_TO_GO_FILE_USE_OPTION = "p2g";
197 final static private String GO_OBO_FILE_USE_OPTION = "obo";
198 final static private String GO_NAMESPACE_LIMIT_OPTION = "go_namespace";
199 final static private String GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION = "molecular_function";
200 final static private String GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS = "biological_process";
201 final static private String GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT = "cellular_component";
202 final static private String SECONDARY_FEATURES_PARSIMONY_MAP_FILE = "secondary";
203 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED = "simple_tab";
204 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML = "simple_html";
205 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML = "detailed_html";
206 final static private String DOMAIN_SIMILARITY_PRINT_OPTION = "ds_output";
207 private static final PRINT_OPTION DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT = PrintableDomainSimilarity.PRINT_OPTION.HTML;
208 final static private String IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION = "ignore_singlet_domains";
209 final static private String IGNORE_VIRAL_IDS = "ignore_viral_ids";
210 final static private boolean IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT = false;
211 final static private String IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION = "ignore_species_specific_domains";
212 final static private boolean IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT = false;
213 final static private String MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score.pwd";
214 final static private String MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains.pwd";
215 final static private String MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations.pwd";
216 final static private String NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score_NJ"
217 + ForesterConstants.PHYLO_XML_SUFFIX;
218 final static private String NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains_NJ"
219 + ForesterConstants.PHYLO_XML_SUFFIX;
220 final static private String NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations_NJ"
221 + ForesterConstants.PHYLO_XML_SUFFIX;
222 final static private String JACKNIFE_OPTION = "jack";
223 final static private String JACKNIFE_RANDOM_SEED_OPTION = "seed";
224 final static private String JACKNIFE_RATIO_OPTION = "jack_ratio";
225 private static final int JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT = 100;
226 final static private long JACKNIFE_RANDOM_SEED_DEFAULT = 19;
227 final static private double JACKNIFE_RATIO_DEFAULT = 0.5;
228 //final static private String INFER_SPECIES_TREES_OPTION = "species_tree_inference";
229 final static private String INFERRED_SD_BASED_NJ_SPECIES_TREE_SUFFIX = "_sd_nj.nh";
230 final static private String INFERRED_SBC_BASED_NJ_SPECIES_TREE_SUFFIX = "_sbc_nj.nh";
231 final static private String FILTER_POSITIVE_OPTION = "pos_filter";
232 final static private String FILTER_NEGATIVE_OPTION = "neg_filter";
233 final static private String FILTER_NEGATIVE_DOMAINS_OPTION = "neg_dom_filter";
234 final static private String INPUT_FILES_FROM_FILE_OPTION = "input";
235 final static private String INPUT_SPECIES_TREE_OPTION = "species_tree";
236 final static private String SEQ_EXTRACT_OPTION = "prot_extract";
237 final static private char SEPARATOR_FOR_INPUT_VALUES = '#';
238 final static private String PRG_VERSION = "2.250";
239 final static private String PRG_DATE = "2012.05.07";
240 final static private String E_MAIL = "czmasek@burnham.org";
241 final static private String WWW = "www.phylosoft.org/forester/applications/surfacing";
242 final static private boolean IGNORE_DUFS_DEFAULT = true;
243 final static private boolean IGNORE_COMBINATION_WITH_SAME_DEFAULLT = false;
244 final static private double MAX_E_VALUE_DEFAULT = -1;
245 final static private int MAX_ALLOWED_OVERLAP_DEFAULT = -1;
246 private static final String RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION = "random_seed";
247 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS = "consider_bdc_direction";
248 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY = "consider_bdc_adj";
249 private static final String SEQ_EXTRACT_SUFFIX = ".prot";
250 private static final String PLUS_MINUS_ANALYSIS_OPTION = "plus_minus";
251 private static final String PLUS_MINUS_DOM_SUFFIX = "_plus_minus_dom.txt";
252 private static final String PLUS_MINUS_DOM_SUFFIX_HTML = "_plus_minus_dom.html";
253 private static final String PLUS_MINUS_DC_SUFFIX_HTML = "_plus_minus_dc.html";
254 private static final int PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT = 0;
255 private static final double PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT = 1.0;
256 private static final String PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_all.txt";
257 private static final String PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_passing.txt";
258 private static final String OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS = "all_prot";
259 private static final boolean VERBOSE = false;
260 private static final String OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_gains_counts";
261 private static final String OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_losses_counts";
262 private static final String DOMAIN_LENGTHS_ANALYSIS_SUFFIX = "_domain_lengths_analysis";
263 private static final boolean PERFORM_DOMAIN_LENGTH_ANALYSIS = true;
264 public static final String ALL_PFAMS_ENCOUNTERED_SUFFIX = "_all_encountered_pfams";
265 public static final String ALL_PFAMS_ENCOUNTERED_WITH_GO_ANNOTATION_SUFFIX = "_all_encountered_pfams_with_go_annotation";
266 public static final String ENCOUNTERED_PFAMS_SUMMARY_SUFFIX = "_encountered_pfams_summary";
267 public static final String ALL_PFAMS_GAINED_AS_DOMAINS_SUFFIX = "_all_pfams_gained_as_domains";
268 public static final String ALL_PFAMS_LOST_AS_DOMAINS_SUFFIX = "_all_pfams_lost_as_domains";
269 public static final String ALL_PFAMS_GAINED_AS_DC_SUFFIX = "_all_pfams_gained_as_dc";
270 public static final String ALL_PFAMS_LOST_AS_DC_SUFFIX = "_all_pfams_lost_as_dc";
271 public static final String BASE_DIRECTORY_PER_NODE_DOMAIN_GAIN_LOSS_FILES = "PER_NODE_EVENTS";
272 public static final String BASE_DIRECTORY_PER_SUBTREE_DOMAIN_GAIN_LOSS_FILES = "PER_SUBTREE_EVENTS";
273 public static final String D_PROMISCUITY_FILE_SUFFIX = "_domain_promiscuities";
274 private static final String LOG_FILE_SUFFIX = "_log.txt";
275 private static final String DATA_FILE_SUFFIX = "_domain_combination_data.txt";
276 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";
277 private static final INDIVIDUAL_SCORE_CUTOFF INDIVIDUAL_SCORE_CUTOFF_DEFAULT = INDIVIDUAL_SCORE_CUTOFF.FULL_SEQUENCE;
278 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts.txt";
279 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists.txt";
280 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping.txt";
281 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";
282 public static final String LIMIT_SPEC_FOR_PROT_EX = null; // e.g. "HUMAN"; set to null for not using this feature (default).
283 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH_MAPPED = "_dc_MAPPED_secondary_features_fitch"
284 + ForesterConstants.PHYLO_XML_SUFFIX;
285 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts_MAPPED.txt";
286 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_MAPPED.txt";
287 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";
288 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";
289 private static final boolean PERFORM_DC_REGAIN_PROTEINS_STATS = true;
291 private static void checkWriteabilityForPairwiseComparisons( final PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option,
292 final String[][] input_file_properties,
293 final String automated_pairwise_comparison_suffix,
294 final File outdir ) {
295 for( int i = 0; i < input_file_properties.length; ++i ) {
296 for( int j = 0; j < i; ++j ) {
297 final String species_i = input_file_properties[ i ][ 1 ];
298 final String species_j = input_file_properties[ j ][ 1 ];
299 String pairwise_similarities_output_file_str = PAIRWISE_DOMAIN_COMPARISONS_PREFIX + species_i + "_"
300 + species_j + automated_pairwise_comparison_suffix;
301 switch ( domain_similarity_print_option ) {
303 if ( !pairwise_similarities_output_file_str.endsWith( ".html" ) ) {
304 pairwise_similarities_output_file_str += ".html";
308 final String error = ForesterUtil
309 .isWritableFile( new File( outdir == null ? pairwise_similarities_output_file_str : outdir
310 + ForesterUtil.FILE_SEPARATOR + pairwise_similarities_output_file_str ) );
311 if ( !ForesterUtil.isEmpty( error ) ) {
312 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
318 private static StringBuilder createParametersAsString( final boolean ignore_dufs,
319 final double e_value_max,
320 final int max_allowed_overlap,
321 final boolean no_engulfing_overlaps,
322 final File cutoff_scores_file,
323 final BinaryDomainCombination.DomainCombinationType dc_type ) {
324 final StringBuilder parameters_sb = new StringBuilder();
325 parameters_sb.append( "E-value: " + e_value_max );
326 if ( cutoff_scores_file != null ) {
327 parameters_sb.append( ", Cutoff-scores-file: " + cutoff_scores_file );
330 parameters_sb.append( ", Cutoff-scores-file: not-set" );
332 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
333 parameters_sb.append( ", Max-overlap: " + max_allowed_overlap );
336 parameters_sb.append( ", Max-overlap: not-set" );
338 if ( no_engulfing_overlaps ) {
339 parameters_sb.append( ", Engulfing-overlaps: not-allowed" );
342 parameters_sb.append( ", Engulfing-overlaps: allowed" );
345 parameters_sb.append( ", Ignore-dufs: true" );
348 parameters_sb.append( ", Ignore-dufs: false" );
350 parameters_sb.append( ", DC type (if applicable): " + dc_type );
351 return parameters_sb;
355 * Warning: This side-effects 'all_bin_domain_combinations_encountered'!
359 * @param all_bin_domain_combinations_changed
360 * @param sum_of_all_domains_encountered
361 * @param all_bin_domain_combinations_encountered
362 * @param is_gains_analysis
363 * @param protein_length_stats_by_dc
364 * @throws IOException
366 private static void executeFitchGainsAnalysis( final File output_file,
367 final List<BinaryDomainCombination> all_bin_domain_combinations_changed,
368 final int sum_of_all_domains_encountered,
369 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered,
370 final boolean is_gains_analysis ) throws IOException {
371 SurfacingUtil.checkForOutputFileWriteability( output_file );
372 final Writer out = ForesterUtil.createBufferedWriter( output_file );
373 final SortedMap<Object, Integer> bdc_to_counts = ForesterUtil
374 .listToSortedCountsMap( all_bin_domain_combinations_changed );
375 final SortedSet<DomainId> all_domains_in_combination_changed_more_than_once = new TreeSet<DomainId>();
376 final SortedSet<DomainId> all_domains_in_combination_changed_only_once = new TreeSet<DomainId>();
379 for( final Object bdc_object : bdc_to_counts.keySet() ) {
380 final BinaryDomainCombination bdc = ( BinaryDomainCombination ) bdc_object;
381 final int count = bdc_to_counts.get( bdc_object );
383 ForesterUtil.unexpectedFatalError( PRG_NAME, "count < 1 " );
385 out.write( bdc + "\t" + count + ForesterUtil.LINE_SEPARATOR );
387 all_domains_in_combination_changed_more_than_once.add( bdc.getId0() );
388 all_domains_in_combination_changed_more_than_once.add( bdc.getId1() );
391 else if ( count == 1 ) {
392 all_domains_in_combination_changed_only_once.add( bdc.getId0() );
393 all_domains_in_combination_changed_only_once.add( bdc.getId1() );
397 final int all = all_bin_domain_combinations_encountered.size();
399 if ( !is_gains_analysis ) {
400 all_bin_domain_combinations_encountered.removeAll( all_bin_domain_combinations_changed );
401 never_lost = all_bin_domain_combinations_encountered.size();
402 for( final BinaryDomainCombination bdc : all_bin_domain_combinations_encountered ) {
403 out.write( bdc + "\t" + "0" + ForesterUtil.LINE_SEPARATOR );
406 if ( is_gains_analysis ) {
407 out.write( "Sum of all distinct domain combinations appearing once : " + one
408 + ForesterUtil.LINE_SEPARATOR );
409 out.write( "Sum of all distinct domain combinations appearing more than once : " + above_one
410 + ForesterUtil.LINE_SEPARATOR );
411 out.write( "Sum of all distinct domains in combinations apppearing only once : "
412 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
413 out.write( "Sum of all distinct domains in combinations apppearing more than once: "
414 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
417 out.write( "Sum of all distinct domain combinations never lost : " + never_lost
418 + ForesterUtil.LINE_SEPARATOR );
419 out.write( "Sum of all distinct domain combinations lost once : " + one
420 + ForesterUtil.LINE_SEPARATOR );
421 out.write( "Sum of all distinct domain combinations lost more than once : " + above_one
422 + ForesterUtil.LINE_SEPARATOR );
423 out.write( "Sum of all distinct domains in combinations lost only once : "
424 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
425 out.write( "Sum of all distinct domains in combinations lost more than once: "
426 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
428 out.write( "All binary combinations : " + all
429 + ForesterUtil.LINE_SEPARATOR );
430 out.write( "All domains : "
431 + sum_of_all_domains_encountered );
433 ForesterUtil.programMessage( surfacing.PRG_NAME,
434 "Wrote fitch domain combination dynamics counts analysis to \"" + output_file
438 private static void executePlusMinusAnalysis( final File output_file,
439 final List<String> plus_minus_analysis_high_copy_base,
440 final List<String> plus_minus_analysis_high_copy_target,
441 final List<String> plus_minus_analysis_low_copy,
442 final List<GenomeWideCombinableDomains> gwcd_list,
443 final SortedMap<Species, List<Protein>> protein_lists_per_species,
444 final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
445 final Map<GoId, GoTerm> go_id_to_term_map,
446 final List<Object> plus_minus_analysis_numbers ) {
447 final Set<String> all_spec = new HashSet<String>();
448 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
449 all_spec.add( gwcd.getSpecies().getSpeciesId() );
451 final File html_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX_HTML );
452 final File plain_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX );
453 final File html_out_dc = new File( output_file + PLUS_MINUS_DC_SUFFIX_HTML );
454 final File all_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX );
455 final File passing_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX );
456 final File proteins_file_base = new File( output_file + "" );
457 final int min_diff = ( ( Integer ) plus_minus_analysis_numbers.get( 0 ) ).intValue();
458 final double factor = ( ( Double ) plus_minus_analysis_numbers.get( 1 ) ).doubleValue();
460 DomainCountsDifferenceUtil.calculateCopyNumberDifferences( gwcd_list,
461 protein_lists_per_species,
462 plus_minus_analysis_high_copy_base,
463 plus_minus_analysis_high_copy_target,
464 plus_minus_analysis_low_copy,
470 domain_id_to_go_ids_map,
472 all_domains_go_ids_out_dom,
473 passing_domains_go_ids_out_dom,
474 proteins_file_base );
476 catch ( final IOException e ) {
477 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
479 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
480 + html_out_dom + "\"" );
481 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
482 + plain_out_dom + "\"" );
483 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \"" + html_out_dc
485 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based passing GO ids to \""
486 + passing_domains_go_ids_out_dom + "\"" );
487 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based all GO ids to \""
488 + all_domains_go_ids_out_dom + "\"" );
491 private static Phylogeny[] getIntrees( final File[] intree_files,
492 final int number_of_genomes,
493 final String[][] input_file_properties ) {
494 final Phylogeny[] intrees = new Phylogeny[ intree_files.length ];
496 for( final File intree_file : intree_files ) {
497 Phylogeny intree = null;
498 final String error = ForesterUtil.isReadableFile( intree_file );
499 if ( !ForesterUtil.isEmpty( error ) ) {
500 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read input tree file [" + intree_file + "]: "
504 final Phylogeny[] p_array = ParserBasedPhylogenyFactory.getInstance()
505 .create( intree_file, ParserUtils.createParserDependingOnFileType( intree_file, true ) );
506 if ( p_array.length < 1 ) {
507 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
508 + "] does not contain any phylogeny in phyloXML format" );
510 else if ( p_array.length > 1 ) {
511 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
512 + "] contains more than one phylogeny in phyloXML format" );
514 intree = p_array[ 0 ];
516 catch ( final Exception e ) {
517 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read input tree from file [" + intree_file
520 if ( ( intree == null ) || intree.isEmpty() ) {
521 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" );
523 if ( !intree.isRooted() ) {
524 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is not rooted" );
526 if ( intree.getNumberOfExternalNodes() < number_of_genomes ) {
527 ForesterUtil.fatalError( surfacing.PRG_NAME,
528 "number of external nodes [" + intree.getNumberOfExternalNodes()
529 + "] of input tree [" + intree_file
530 + "] is smaller than the number of genomes the be analyzed ["
531 + number_of_genomes + "]" );
533 final StringBuilder parent_names = new StringBuilder();
534 final int nodes_lacking_name = SurfacingUtil.getNumberOfNodesLackingName( intree, parent_names );
535 if ( nodes_lacking_name > 0 ) {
536 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] has "
537 + nodes_lacking_name + " node(s) lacking a name [parent names:" + parent_names + "]" );
539 preparePhylogenyForParsimonyAnalyses( intree, input_file_properties );
540 if ( !intree.isCompletelyBinary() ) {
541 ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "input tree [" + intree_file
542 + "] is not completely binary" );
544 intrees[ i++ ] = intree;
549 private static List<Phylogeny> inferSpeciesTrees( final File outfile, final List<DistanceMatrix> distances_list ) {
550 final NeighborJoining nj = NeighborJoining.createInstance();
551 final List<Phylogeny> phylogenies = nj.execute( distances_list );
552 final PhylogenyWriter w = new PhylogenyWriter();
554 w.toNewHampshire( phylogenies, true, true, outfile, ";" );
556 catch ( final IOException e ) {
557 ForesterUtil.fatalError( PRG_NAME, "failed to write to outfile [" + outfile + "]: " + e.getMessage() );
562 private static void log( final String msg, final Writer w ) {
565 w.write( ForesterUtil.LINE_SEPARATOR );
567 catch ( final IOException e ) {
568 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
572 public static void main( final String args[] ) {
573 final long start_time = new Date().getTime();
574 // final StringBuffer log = new StringBuffer();
575 final StringBuilder html_desc = new StringBuilder();
576 ForesterUtil.printProgramInformation( surfacing.PRG_NAME,
577 surfacing.PRG_VERSION,
581 final String nl = ForesterUtil.LINE_SEPARATOR;
582 html_desc.append( "<table>" + nl );
583 html_desc.append( "<tr><td>Produced by:</td><td>" + surfacing.PRG_NAME + "</td></tr>" + nl );
584 html_desc.append( "<tr><td>Version:</td><td>" + surfacing.PRG_VERSION + "</td></tr>" + nl );
585 html_desc.append( "<tr><td>Release Date:</td><td>" + surfacing.PRG_DATE + "</td></tr>" + nl );
586 html_desc.append( "<tr><td>Contact:</td><td>" + surfacing.E_MAIL + "</td></tr>" + nl );
587 html_desc.append( "<tr><td>WWW:</td><td>" + surfacing.WWW + "</td></tr>" + nl );
588 CommandLineArguments cla = null;
590 cla = new CommandLineArguments( args );
592 catch ( final Exception e ) {
593 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
595 if ( cla.isOptionSet( surfacing.HELP_OPTION_1 ) || cla.isOptionSet( surfacing.HELP_OPTION_2 ) ) {
596 surfacing.printHelp();
599 if ( ( args.length < 1 ) ) {
600 surfacing.printHelp();
603 final List<String> allowed_options = new ArrayList<String>();
604 allowed_options.add( surfacing.NOT_IGNORE_DUFS_OPTION );
605 allowed_options.add( surfacing.MAX_E_VALUE_OPTION );
606 allowed_options.add( surfacing.DETAILEDNESS_OPTION );
607 allowed_options.add( surfacing.OUTPUT_FILE_OPTION );
608 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_OPTION );
609 allowed_options.add( surfacing.SPECIES_MATRIX_OPTION );
610 allowed_options.add( surfacing.SCORING_OPTION );
611 allowed_options.add( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
612 allowed_options.add( surfacing.NO_ENGULFING_OVERLAP_OPTION );
613 allowed_options.add( surfacing.DOMAIN_COUNT_SORT_OPTION );
614 allowed_options.add( surfacing.CUTOFF_SCORE_FILE_OPTION );
615 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION );
616 allowed_options.add( surfacing.OUTPUT_DIR_OPTION );
617 allowed_options.add( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION );
618 allowed_options.add( surfacing.PFAM_TO_GO_FILE_USE_OPTION );
619 allowed_options.add( surfacing.GO_OBO_FILE_USE_OPTION );
620 allowed_options.add( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION );
621 allowed_options.add( surfacing.GO_NAMESPACE_LIMIT_OPTION );
622 allowed_options.add( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
623 allowed_options.add( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION );
624 allowed_options.add( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS );
625 allowed_options.add( JACKNIFE_OPTION );
626 allowed_options.add( JACKNIFE_RANDOM_SEED_OPTION );
627 allowed_options.add( JACKNIFE_RATIO_OPTION );
628 allowed_options.add( INPUT_SPECIES_TREE_OPTION );
629 //allowed_options.add( INFER_SPECIES_TREES_OPTION );
630 allowed_options.add( FILTER_POSITIVE_OPTION );
631 allowed_options.add( FILTER_NEGATIVE_OPTION );
632 allowed_options.add( INPUT_FILES_FROM_FILE_OPTION );
633 allowed_options.add( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
634 allowed_options.add( FILTER_NEGATIVE_DOMAINS_OPTION );
635 allowed_options.add( IGNORE_VIRAL_IDS );
636 allowed_options.add( SEQ_EXTRACT_OPTION );
637 allowed_options.add( SECONDARY_FEATURES_PARSIMONY_MAP_FILE );
638 allowed_options.add( PLUS_MINUS_ANALYSIS_OPTION );
639 allowed_options.add( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS );
640 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS );
641 allowed_options.add( CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY );
642 boolean ignore_dufs = surfacing.IGNORE_DUFS_DEFAULT;
643 boolean ignore_combination_with_same = surfacing.IGNORE_COMBINATION_WITH_SAME_DEFAULLT;
644 double e_value_max = surfacing.MAX_E_VALUE_DEFAULT;
645 int max_allowed_overlap = surfacing.MAX_ALLOWED_OVERLAP_DEFAULT;
646 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
647 if ( dissallowed_options.length() > 0 ) {
648 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown option(s): " + dissallowed_options );
650 boolean output_binary_domain_combinationsfor_graph_analysis = false;
651 if ( cla.isOptionSet( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS ) ) {
652 output_binary_domain_combinationsfor_graph_analysis = true;
654 if ( cla.isOptionSet( surfacing.MAX_E_VALUE_OPTION ) ) {
656 e_value_max = cla.getOptionValueAsDouble( surfacing.MAX_E_VALUE_OPTION );
658 catch ( final Exception e ) {
659 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for E-value maximum" );
662 if ( cla.isOptionSet( surfacing.MAX_ALLOWED_OVERLAP_OPTION ) ) {
664 max_allowed_overlap = cla.getOptionValueAsInt( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
666 catch ( final Exception e ) {
667 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for maximal allowed domain overlap" );
670 boolean no_engulfing_overlaps = false;
671 if ( cla.isOptionSet( surfacing.NO_ENGULFING_OVERLAP_OPTION ) ) {
672 no_engulfing_overlaps = true;
674 boolean ignore_virus_like_ids = false;
675 if ( cla.isOptionSet( surfacing.IGNORE_VIRAL_IDS ) ) {
676 ignore_virus_like_ids = true;
678 if ( cla.isOptionSet( surfacing.NOT_IGNORE_DUFS_OPTION ) ) {
681 if ( cla.isOptionSet( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION ) ) {
682 ignore_combination_with_same = true;
684 boolean ignore_domains_without_combs_in_all_spec = IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT;
685 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION ) ) {
686 ignore_domains_without_combs_in_all_spec = true;
688 boolean ignore_species_specific_domains = IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT;
689 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION ) ) {
690 ignore_species_specific_domains = true;
692 File output_file = null;
693 if ( cla.isOptionSet( surfacing.OUTPUT_FILE_OPTION ) ) {
694 if ( !cla.isOptionValueSet( surfacing.OUTPUT_FILE_OPTION ) ) {
695 ForesterUtil.fatalError( surfacing.PRG_NAME,
696 "no value for domain combinations similarities output file: -"
697 + surfacing.OUTPUT_FILE_OPTION + "=<file>" );
699 output_file = new File( cla.getOptionValue( surfacing.OUTPUT_FILE_OPTION ) );
700 SurfacingUtil.checkForOutputFileWriteability( output_file );
702 File cutoff_scores_file = null;
703 Map<String, Double> individual_score_cutoffs = null;
704 if ( cla.isOptionSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
705 if ( !cla.isOptionValueSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
706 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for individual domain score cutoffs file: -"
707 + surfacing.CUTOFF_SCORE_FILE_OPTION + "=<file>" );
709 cutoff_scores_file = new File( cla.getOptionValue( surfacing.CUTOFF_SCORE_FILE_OPTION ) );
710 final String error = ForesterUtil.isReadableFile( cutoff_scores_file );
711 if ( !ForesterUtil.isEmpty( error ) ) {
712 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read individual domain score cutoffs file: "
716 final BasicTable<String> scores_table = BasicTableParser.parse( cutoff_scores_file, " " );
717 individual_score_cutoffs = scores_table.getColumnsAsMapDouble( 0, 1 );
719 catch ( final IOException e ) {
720 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from individual score cutoffs file: " + e );
723 BinaryDomainCombination.DomainCombinationType dc_type = BinaryDomainCombination.DomainCombinationType.BASIC;
724 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS ) ) {
725 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED;
727 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY ) ) {
728 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT;
731 if ( cla.isOptionSet( surfacing.OUTPUT_DIR_OPTION ) ) {
732 if ( !cla.isOptionValueSet( surfacing.OUTPUT_DIR_OPTION ) ) {
733 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for output directory: -"
734 + surfacing.OUTPUT_DIR_OPTION + "=<dir>" );
736 out_dir = new File( cla.getOptionValue( surfacing.OUTPUT_DIR_OPTION ) );
737 if ( out_dir.exists() && ( out_dir.listFiles().length > 0 ) ) {
738 ForesterUtil.fatalError( surfacing.PRG_NAME, "\"" + out_dir + "\" aready exists and is not empty" );
740 if ( !out_dir.exists() ) {
741 final boolean success = out_dir.mkdir();
742 if ( !success || !out_dir.exists() ) {
743 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to create \"" + out_dir + "\"" );
746 if ( !out_dir.canWrite() ) {
747 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot write to \"" + out_dir + "\"" );
750 File positive_filter_file = null;
751 File negative_filter_file = null;
752 File negative_domains_filter_file = null;
753 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) && cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
754 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use both negative and positive protein filter" );
756 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION )
757 && ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) || cla
758 .isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) ) {
760 .fatalError( surfacing.PRG_NAME,
761 "attempt to use both negative or positive protein filter together wirh a negative domains filter" );
763 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
764 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
765 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative filter: -"
766 + surfacing.FILTER_NEGATIVE_OPTION + "=<file>" );
768 negative_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_OPTION ) );
769 final String msg = ForesterUtil.isReadableFile( negative_filter_file );
770 if ( !ForesterUtil.isEmpty( msg ) ) {
771 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_filter_file + "\": "
775 else if ( cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
776 if ( !cla.isOptionValueSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
777 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for positive filter: -"
778 + surfacing.FILTER_POSITIVE_OPTION + "=<file>" );
780 positive_filter_file = new File( cla.getOptionValue( surfacing.FILTER_POSITIVE_OPTION ) );
781 final String msg = ForesterUtil.isReadableFile( positive_filter_file );
782 if ( !ForesterUtil.isEmpty( msg ) ) {
783 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + positive_filter_file + "\": "
787 else if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
788 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
789 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative domains filter: -"
790 + surfacing.FILTER_NEGATIVE_DOMAINS_OPTION + "=<file>" );
792 negative_domains_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) );
793 final String msg = ForesterUtil.isReadableFile( negative_domains_filter_file );
794 if ( !ForesterUtil.isEmpty( msg ) ) {
795 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_domains_filter_file
799 final List<String> plus_minus_analysis_high_copy_base_species = new ArrayList<String>();
800 final List<String> plus_minus_analysis_high_copy_target_species = new ArrayList<String>();
801 final List<String> plus_minus_analysis_high_low_copy_species = new ArrayList<String>();
802 final List<Object> plus_minus_analysis_numbers = new ArrayList<Object>();
803 processPlusMinusAnalysisOption( cla,
804 plus_minus_analysis_high_copy_base_species,
805 plus_minus_analysis_high_copy_target_species,
806 plus_minus_analysis_high_low_copy_species,
807 plus_minus_analysis_numbers );
808 File input_files_file = null;
809 String[] input_file_names_from_file = null;
810 if ( cla.isOptionSet( surfacing.INPUT_FILES_FROM_FILE_OPTION ) ) {
811 if ( !cla.isOptionValueSet( surfacing.INPUT_FILES_FROM_FILE_OPTION ) ) {
812 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input files file: -"
813 + surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>" );
815 input_files_file = new File( cla.getOptionValue( surfacing.INPUT_FILES_FROM_FILE_OPTION ) );
816 final String msg = ForesterUtil.isReadableFile( input_files_file );
817 if ( !ForesterUtil.isEmpty( msg ) ) {
818 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + input_files_file + "\": " + msg );
821 input_file_names_from_file = ForesterUtil.file2array( input_files_file );
823 catch ( final IOException e ) {
824 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read from \"" + input_files_file + "\": " + e );
827 if ( ( cla.getNumberOfNames() < 1 )
828 && ( ( input_file_names_from_file == null ) || ( input_file_names_from_file.length < 1 ) ) ) {
829 ForesterUtil.fatalError( surfacing.PRG_NAME,
830 "No hmmpfam output file indicated is input: use comand line directly or "
831 + surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>" );
833 DomainSimilarity.DomainSimilarityScoring scoring = SCORING_DEFAULT;
834 if ( cla.isOptionSet( surfacing.SCORING_OPTION ) ) {
835 if ( !cla.isOptionValueSet( surfacing.SCORING_OPTION ) ) {
836 ForesterUtil.fatalError( surfacing.PRG_NAME,
837 "no value for scoring method for domain combinations similarity calculation: -"
838 + surfacing.SCORING_OPTION + "=<"
839 + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
840 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|"
841 + surfacing.SCORING_COMBINATION_BASED + ">\"" );
843 final String scoring_str = cla.getOptionValue( surfacing.SCORING_OPTION );
844 if ( scoring_str.equals( surfacing.SCORING_DOMAIN_COUNT_BASED ) ) {
845 scoring = DomainSimilarity.DomainSimilarityScoring.DOMAINS;
847 else if ( scoring_str.equals( surfacing.SCORING_COMBINATION_BASED ) ) {
848 scoring = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
850 else if ( scoring_str.equals( surfacing.SCORING_PROTEIN_COUNT_BASED ) ) {
851 scoring = DomainSimilarity.DomainSimilarityScoring.PROTEINS;
854 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + scoring_str
855 + "\" for scoring method for domain combinations similarity calculation: \"-"
856 + surfacing.SCORING_OPTION + "=<" + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
857 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|" + surfacing.SCORING_COMBINATION_BASED + ">\"" );
860 boolean sort_by_species_count_first = false;
861 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION ) ) {
862 sort_by_species_count_first = true;
864 boolean species_matrix = false;
865 if ( cla.isOptionSet( surfacing.SPECIES_MATRIX_OPTION ) ) {
866 species_matrix = true;
868 boolean output_protein_lists_for_all_domains = false;
869 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS ) ) {
870 output_protein_lists_for_all_domains = true;
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 );
920 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field = DOMAIN_SORT_FILD_DEFAULT;
921 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field_for_automated_pwc = DOMAIN_SORT_FILD_DEFAULT;
922 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
923 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
924 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for domain combinations similarities sorting: -"
925 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
926 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
927 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
928 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
929 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|"
930 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
933 final String sort_str = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ).toLowerCase();
934 if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ALPHA ) ) {
935 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
936 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
938 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MAX ) ) {
939 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX;
940 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
942 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MIN ) ) {
943 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MIN;
944 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
946 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MEAN ) ) {
947 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MEAN;
948 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MEAN;
950 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT ) ) {
951 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SPECIES_COUNT;
952 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
954 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SD ) ) {
955 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SD;
956 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
958 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_DIFF ) ) {
959 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
960 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
962 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF ) ) {
963 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
964 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
966 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF ) ) {
967 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
968 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
971 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort_str
972 + "\" for domain combinations similarities sorting: \"-"
973 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
974 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
975 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
976 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
977 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|" + "|"
978 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
982 PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option = DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT;
983 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
984 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
985 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for print option: -"
986 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
987 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
988 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
990 final String sort = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ).toLowerCase();
991 if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML ) ) {
992 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.HTML;
994 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML ) ) {
995 // domain_similarity_print_option =
996 // DomainSimilarity.PRINT_OPTION.SIMPLE_HTML;
997 ForesterUtil.fatalError( surfacing.PRG_NAME, "simple HTML output not implemented yet :(" );
999 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED ) ) {
1000 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.SIMPLE_TAB_DELIMITED;
1003 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort + "\" for print option: -"
1004 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
1005 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
1006 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
1009 GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order = DOMAINS_SORT_ORDER_DEFAULT;
1010 if ( cla.isOptionSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
1011 if ( !cla.isOptionValueSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
1012 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for sorting of domain counts: -"
1013 + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<" + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|"
1014 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1015 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1016 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1018 final String sort = cla.getOptionValue( surfacing.DOMAIN_COUNT_SORT_OPTION ).toLowerCase();
1019 if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_ALPHA ) ) {
1020 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
1022 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT ) ) {
1023 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_COUNT;
1025 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT ) ) {
1026 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_PROTEINS_COUNT;
1028 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT ) ) {
1029 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.COMBINATIONS_COUNT;
1032 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort
1033 + "\" for sorting of domain counts: \"-" + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<"
1034 + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|" + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1035 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1036 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1039 String[][] input_file_properties = null;
1040 if ( input_file_names_from_file != null ) {
1041 input_file_properties = surfacing.processInputFileNames( input_file_names_from_file );
1044 input_file_properties = surfacing.processInputFileNames( cla.getNames() );
1046 final int number_of_genomes = input_file_properties.length;
1047 if ( number_of_genomes < 2 ) {
1048 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot analyze less than two files" );
1050 if ( ( number_of_genomes < 3 ) && perform_pwc ) {
1051 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use : -"
1052 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1053 + "=<suffix> to turn on pairwise analyses with less than three input files" );
1055 checkWriteabilityForPairwiseComparisons( domain_similarity_print_option,
1056 input_file_properties,
1057 automated_pairwise_comparison_suffix,
1059 for( int i = 0; i < number_of_genomes; i++ ) {
1060 File dcc_outfile = new File( input_file_properties[ i ][ 0 ]
1061 + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
1062 if ( out_dir != null ) {
1063 dcc_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + dcc_outfile );
1065 SurfacingUtil.checkForOutputFileWriteability( dcc_outfile );
1067 File pfam_to_go_file = null;
1068 Map<DomainId, List<GoId>> domain_id_to_go_ids_map = null;
1069 int domain_id_to_go_ids_count = 0;
1070 if ( cla.isOptionSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1071 if ( !cla.isOptionValueSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1072 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for Pfam to GO mapping file: -"
1073 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>" );
1075 pfam_to_go_file = new File( cla.getOptionValue( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) );
1076 final String error = ForesterUtil.isReadableFile( pfam_to_go_file );
1077 if ( !ForesterUtil.isEmpty( error ) ) {
1078 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read Pfam to GO mapping file: " + error );
1081 final PfamToGoParser parser = new PfamToGoParser( pfam_to_go_file );
1082 final List<PfamToGoMapping> pfam_to_go_mappings = parser.parse();
1083 domain_id_to_go_ids_map = SurfacingUtil.createDomainIdToGoIdMap( pfam_to_go_mappings );
1084 if ( parser.getMappingCount() < domain_id_to_go_ids_map.size() ) {
1085 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME,
1086 "parser.getMappingCount() < domain_id_to_go_ids_map.size()" );
1088 domain_id_to_go_ids_count = parser.getMappingCount();
1090 catch ( final IOException e ) {
1091 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from Pfam to GO mapping file: " + e );
1094 File go_obo_file = null;
1095 List<GoTerm> go_terms = null;
1096 if ( cla.isOptionSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1097 if ( !cla.isOptionValueSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1098 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO OBO file: -"
1099 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>" );
1101 if ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) {
1102 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO OBO file (-"
1103 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>) without Pfam to GO mapping file ("
1104 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1106 go_obo_file = new File( cla.getOptionValue( surfacing.GO_OBO_FILE_USE_OPTION ) );
1107 final String error = ForesterUtil.isReadableFile( go_obo_file );
1108 if ( !ForesterUtil.isEmpty( error ) ) {
1109 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read GO OBO file: " + error );
1112 final OBOparser parser = new OBOparser( go_obo_file, OBOparser.ReturnType.BASIC_GO_TERM );
1113 go_terms = parser.parse();
1114 if ( parser.getGoTermCount() != go_terms.size() ) {
1116 .unexpectedFatalError( surfacing.PRG_NAME, "parser.getGoTermCount() != go_terms.size()" );
1119 catch ( final IOException e ) {
1120 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from GO OBO file: " + e );
1123 Map<GoId, GoTerm> go_id_to_term_map = null;
1124 if ( ( ( domain_id_to_go_ids_map != null ) && ( domain_id_to_go_ids_map.size() > 0 ) )
1125 && ( ( go_terms != null ) && ( go_terms.size() > 0 ) ) ) {
1126 go_id_to_term_map = GoUtils.createGoIdToGoTermMap( go_terms );
1128 GoNameSpace go_namespace_limit = null;
1129 if ( cla.isOptionSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1130 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1131 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO namespace limit (-"
1132 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<namespace>) without Pfam to GO mapping file ("
1133 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>) and GO OBO file (-"
1134 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1136 if ( !cla.isOptionValueSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1137 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO namespace limit: \"-"
1138 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1139 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1140 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1141 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1143 final String go_namespace_limit_str = cla.getOptionValue( surfacing.GO_NAMESPACE_LIMIT_OPTION )
1145 if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION ) ) {
1146 go_namespace_limit = GoNameSpace.createMolecularFunction();
1148 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS ) ) {
1149 go_namespace_limit = GoNameSpace.createBiologicalProcess();
1151 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT ) ) {
1152 go_namespace_limit = GoNameSpace.createCellularComponent();
1155 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + go_namespace_limit_str
1156 + "\" for GO namespace limit: \"-" + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1157 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1158 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1159 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1162 if ( ( domain_similarity_sort_field == DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE )
1163 && ( number_of_genomes > 2 ) ) {
1164 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
1166 boolean jacknifed_distances = false;
1167 int jacknife_resamplings = JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT;
1168 double jacknife_ratio = JACKNIFE_RATIO_DEFAULT;
1169 long random_seed = JACKNIFE_RANDOM_SEED_DEFAULT;
1170 if ( cla.isOptionSet( surfacing.JACKNIFE_OPTION ) ) {
1171 if ( ( number_of_genomes < 3 ) || !perform_pwc ) {
1172 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use jacknife resampling analysis (-"
1173 + surfacing.JACKNIFE_OPTION + "[=<number of resamplings>]) without pairwise analyses ("
1174 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1175 + "=<suffix for pairwise comparison output files>)" );
1177 jacknifed_distances = true;
1178 if ( cla.isOptionHasAValue( surfacing.JACKNIFE_OPTION ) ) {
1180 jacknife_resamplings = cla.getOptionValueAsInt( surfacing.JACKNIFE_OPTION );
1182 catch ( final IOException e ) {
1183 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for number of resamplings" );
1185 if ( jacknife_resamplings < 2 ) {
1186 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use less than 2 resamplings" );
1189 if ( cla.isOptionSet( surfacing.JACKNIFE_RATIO_OPTION )
1190 && cla.isOptionHasAValue( surfacing.JACKNIFE_RATIO_OPTION ) ) {
1192 jacknife_ratio = cla.getOptionValueAsDouble( surfacing.JACKNIFE_RATIO_OPTION );
1194 catch ( final IOException e ) {
1195 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for jacknife ratio" );
1197 if ( ( jacknife_ratio <= 0.0 ) || ( jacknife_ratio >= 1.0 ) ) {
1198 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use illegal value for jacknife ratio: "
1202 if ( cla.isOptionSet( surfacing.JACKNIFE_RANDOM_SEED_OPTION )
1203 && cla.isOptionHasAValue( surfacing.JACKNIFE_RANDOM_SEED_OPTION ) ) {
1205 random_seed = cla.getOptionValueAsLong( surfacing.JACKNIFE_RANDOM_SEED_OPTION );
1207 catch ( final IOException e ) {
1208 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for random generator seed" );
1212 // boolean infer_species_trees = false;
1213 // if ( cla.isOptionSet( surfacing.INFER_SPECIES_TREES_OPTION ) ) {
1214 // if ( ( output_file == null ) || ( number_of_genomes < 3 )
1215 // || ForesterUtil.isEmpty( automated_pairwise_comparison_suffix ) ) {
1216 // ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer species trees (-"
1217 // + surfacing.INFER_SPECIES_TREES_OPTION + " without pairwise analyses ("
1218 // + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1219 // + "=<suffix for pairwise comparison output files>)" );
1221 // infer_species_trees = true;
1223 File[] intree_files = null;
1224 Phylogeny[] intrees = null;
1225 if ( cla.isOptionSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1226 // TODO FIXME if jacknife.... maybe not
1227 if ( number_of_genomes < 3 ) {
1228 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer gains and losses on input species trees (-"
1229 + surfacing.INPUT_SPECIES_TREE_OPTION + " without pairwise analyses ("
1230 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1231 + "=<suffix for pairwise comparison output files>)" );
1233 if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1234 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input tree: -"
1235 + surfacing.INPUT_SPECIES_TREE_OPTION + "=<tree file in phyloXML format>" );
1237 final String intrees_str = cla.getOptionValue( surfacing.INPUT_SPECIES_TREE_OPTION );
1238 if ( intrees_str.indexOf( "#" ) > 0 ) {
1239 final String[] intrees_strs = intrees_str.split( "#" );
1240 intree_files = new File[ intrees_strs.length ];
1242 for( final String s : intrees_strs ) {
1243 intree_files[ i++ ] = new File( s.trim() );
1247 intree_files = new File[ 1 ];
1248 intree_files[ 0 ] = new File( intrees_str );
1250 intrees = getIntrees( intree_files, number_of_genomes, input_file_properties );
1252 long random_number_seed_for_fitch_parsimony = 0l;
1253 boolean radomize_fitch_parsimony = false;
1254 if ( cla.isOptionSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1255 if ( !cla.isOptionValueSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1256 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for random number seed: -"
1257 + surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION + "=<seed>" );
1260 random_number_seed_for_fitch_parsimony = cla
1261 .getOptionValueAsLong( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
1263 catch ( final IOException e ) {
1264 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1266 radomize_fitch_parsimony = true;
1268 SortedSet<DomainId> filter = null;
1269 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1270 || ( negative_domains_filter_file != null ) ) {
1271 filter = new TreeSet<DomainId>();
1272 if ( positive_filter_file != null ) {
1273 processFilter( positive_filter_file, filter );
1275 else if ( negative_filter_file != null ) {
1276 processFilter( negative_filter_file, filter );
1278 else if ( negative_domains_filter_file != null ) {
1279 processFilter( negative_domains_filter_file, filter );
1282 Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps = null;
1283 File[] secondary_features_map_files = null;
1284 final File domain_lengths_analysis_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1285 + DOMAIN_LENGTHS_ANALYSIS_SUFFIX );
1286 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
1287 SurfacingUtil.checkForOutputFileWriteability( domain_lengths_analysis_outfile );
1289 if ( cla.isOptionSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1290 if ( !cla.isOptionValueSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1291 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for secondary features map file: -"
1292 + surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE + "=<file>" );
1294 final String[] secondary_features_map_files_strs = cla
1295 .getOptionValue( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ).split( "#" );
1296 secondary_features_map_files = new File[ secondary_features_map_files_strs.length ];
1297 domain_id_to_secondary_features_maps = new Map[ secondary_features_map_files_strs.length ];
1299 for( final String secondary_features_map_files_str : secondary_features_map_files_strs ) {
1300 secondary_features_map_files[ i ] = new File( secondary_features_map_files_str );
1301 final String error = ForesterUtil.isReadableFile( secondary_features_map_files[ i ] );
1302 if ( !ForesterUtil.isEmpty( error ) ) {
1303 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read secondary features map file: " + error );
1306 domain_id_to_secondary_features_maps[ i ] = SurfacingUtil
1307 .createDomainIdToSecondaryFeaturesMap( secondary_features_map_files[ i ] );
1309 catch ( final IOException e ) {
1310 ForesterUtil.fatalError( surfacing.PRG_NAME,
1311 "cannot read secondary features map file: " + e.getMessage() );
1313 catch ( final Exception e ) {
1314 ForesterUtil.fatalError( surfacing.PRG_NAME, "problem with contents of features map file ["
1315 + secondary_features_map_files[ i ] + "]: " + e.getMessage() );
1320 if ( out_dir == null ) {
1321 ForesterUtil.fatalError( surfacing.PRG_NAME, "no output directory indicated (-"
1322 + surfacing.OUTPUT_DIR_OPTION + "=<dir>)" );
1324 if ( output_file == null ) {
1325 ForesterUtil.fatalError( surfacing.PRG_NAME, "no name for (main) output file indicated (-"
1326 + surfacing.OUTPUT_FILE_OPTION + "=<file>)" );
1328 if ( ( domain_id_to_go_ids_map == null ) || domain_id_to_go_ids_map.isEmpty() ) {
1329 ForesterUtil.fatalError( surfacing.PRG_NAME,
1330 "no (acceptable) Pfam to GO id mapping file provided ('pfam2go file') (-"
1331 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1333 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1334 ForesterUtil.fatalError( surfacing.PRG_NAME,
1335 "no (acceptable) go id to term mapping file provided ('GO OBO file') (-"
1336 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1338 System.out.println( "Output directory : " + out_dir );
1339 if ( input_file_names_from_file != null ) {
1340 System.out.println( "Input files names from : " + input_files_file + " ["
1341 + input_file_names_from_file.length + " input files]" );
1342 html_desc.append( "<tr><td>Input files names from:</td><td>" + input_files_file + " ["
1343 + input_file_names_from_file.length + " input files]</td></tr>" + nl );
1345 if ( positive_filter_file != null ) {
1346 final int filter_size = filter.size();
1347 System.out.println( "Positive protein filter : " + positive_filter_file + " [" + filter_size
1349 html_desc.append( "<tr><td>Positive protein filter:</td><td>" + positive_filter_file + " [" + filter_size
1350 + " domain ids]</td></tr>" + nl );
1352 if ( negative_filter_file != null ) {
1353 final int filter_size = filter.size();
1354 System.out.println( "Negative protein filter : " + negative_filter_file + " [" + filter_size
1356 html_desc.append( "<tr><td>Negative protein filter:</td><td>" + negative_filter_file + " [" + filter_size
1357 + " domain ids]</td></tr>" + nl );
1359 if ( negative_domains_filter_file != null ) {
1360 final int filter_size = filter.size();
1361 System.out.println( "Negative domain filter : " + negative_domains_filter_file + " [" + filter_size
1363 html_desc.append( "<tr><td>Negative domain filter:</td><td>" + negative_domains_filter_file + " ["
1364 + filter_size + " domain ids]</td></tr>" + nl );
1366 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
1368 for( final String s : plus_minus_analysis_high_copy_base_species ) {
1369 plus0 += "+" + s + " ";
1372 for( final String s : plus_minus_analysis_high_copy_target_species ) {
1373 plus1 += "*" + s + " ";
1376 for( final String s : plus_minus_analysis_high_low_copy_species ) {
1377 minus += "-" + s + " ";
1379 System.out.println( "Plus-minus analysis : " + plus1 + "&& " + plus0 + "&& " + minus );
1380 html_desc.append( "<tr><td>Plus-minus analysis:</td><td>" + plus1 + "&& " + plus0 + "&& " + minus
1381 + "</td></tr>" + nl );
1383 if ( cutoff_scores_file != null ) {
1384 System.out.println( "Cutoff scores file : " + cutoff_scores_file );
1385 html_desc.append( "<tr><td>Cutoff scores file:</td><td>" + cutoff_scores_file + "</td></tr>" + nl );
1387 if ( e_value_max >= 0.0 ) {
1388 System.out.println( "E-value maximum (inclusive) : " + e_value_max );
1389 html_desc.append( "<tr><td>E-value maximum (inclusive):</td><td>" + e_value_max + "</td></tr>" + nl );
1391 System.out.println( "Ignore DUFs : " + ignore_dufs );
1392 if ( ignore_virus_like_ids ) {
1393 System.out.println( "Ignore virus like ids : " + ignore_virus_like_ids );
1394 html_desc.append( "<tr><td>Ignore virus, phage, transposition related ids:</td><td>"
1395 + ignore_virus_like_ids + "</td></tr>" + nl );
1397 html_desc.append( "<tr><td>Ignore DUFs:</td><td>" + ignore_dufs + "</td></tr>" + nl );
1398 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1399 System.out.println( "Max allowed domain overlap : " + max_allowed_overlap );
1400 html_desc.append( "<tr><td>Max allowed domain overlap:</td><td>" + max_allowed_overlap + "</td></tr>" + nl );
1402 if ( no_engulfing_overlaps ) {
1403 System.out.println( "Ignore engulfed domains : " + no_engulfing_overlaps );
1404 html_desc.append( "<tr><td>Ignore (lower confidence) engulfed domains:</td><td>" + no_engulfing_overlaps
1405 + "</td></tr>" + nl );
1407 System.out.println( "Ignore singlet domains : " + ignore_domains_without_combs_in_all_spec );
1409 .append( "<tr><td>Ignore singlet domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1410 + ignore_domains_without_combs_in_all_spec + "</td></tr>" + nl );
1411 System.out.println( "Ignore species specific doms: " + ignore_species_specific_domains );
1413 .append( "<tr><td>Ignore species specific domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1414 + ignore_species_specific_domains + "</td></tr>" + nl );
1415 System.out.println( "Ignore combination with self: " + ignore_combination_with_same );
1416 html_desc.append( "<tr><td>Ignore combination with self for domain combination similarity analyses:</td><td>"
1417 + ignore_combination_with_same + "</td></tr>" + nl );
1418 System.out.println( "Consider directedness : "
1419 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) );
1420 html_desc.append( "<tr><td>Consider directedness of binary domain combinations:</td><td>"
1421 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) + "</td></tr>" + nl );
1422 if ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) {
1423 System.out.println( "Consider adjacency : "
1424 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) );
1425 html_desc.append( "<tr><td>Consider djacency of binary domain combinations:</td><td>"
1426 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) + "</td></tr>"
1429 System.out.print( "Domain counts sort order : " );
1430 switch ( dc_sort_order ) {
1431 case ALPHABETICAL_KEY_ID:
1432 System.out.println( "alphabetical" );
1434 case KEY_DOMAIN_COUNT:
1435 System.out.println( "domain count" );
1437 case KEY_DOMAIN_PROTEINS_COUNT:
1438 System.out.println( "domain proteins count" );
1440 case COMBINATIONS_COUNT:
1441 System.out.println( "domain combinations count" );
1444 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for dc sort order" );
1446 if ( domain_id_to_go_ids_map != null ) {
1447 System.out.println( "Pfam to GO mappings from : " + pfam_to_go_file + " [" + domain_id_to_go_ids_count
1449 html_desc.append( "<tr><td>Pfam to GO mappings from:</td><td>" + pfam_to_go_file + " ["
1450 + domain_id_to_go_ids_count + " mappings]" + "</td></tr>" + nl );
1452 if ( go_terms != null ) {
1453 System.out.println( "GO terms from : " + go_obo_file + " [" + go_terms.size() + " terms]" );
1454 html_desc.append( "<tr><td>GO terms from:</td><td>" + go_obo_file + " [" + go_terms.size() + " terms]"
1455 + "</td></tr>" + nl );
1457 if ( go_namespace_limit != null ) {
1458 System.out.println( "Limit GO terms to : " + go_namespace_limit.toString() );
1459 html_desc.append( "<tr><td>Limit GO terms to</td><td>" + go_namespace_limit + "</td></tr>" + nl );
1461 if ( perform_pwc ) {
1462 System.out.println( "Suffix for PWC files : " + automated_pairwise_comparison_suffix );
1463 html_desc.append( "<tr><td>Suffix for PWC files</td><td>" + automated_pairwise_comparison_suffix
1464 + "</td></tr>" + nl );
1466 if ( out_dir != null ) {
1467 System.out.println( "Output directory : " + out_dir );
1469 if ( query_domain_ids != null ) {
1470 System.out.println( "Query domains (ordered) : " + query_domain_ids );
1471 html_desc.append( "<tr><td></td><td>" + query_domain_ids + "</td></tr>" + nl );
1473 System.out.println( "Write similarities to : " + output_file );
1474 System.out.print( " Scoring method : " );
1475 html_desc.append( "<tr><td>Scoring method:</td><td>" );
1476 switch ( scoring ) {
1478 System.out.println( "domain combinations based" );
1479 html_desc.append( "domain combinations based" + "</td></tr>" + nl );
1482 System.out.println( "domain counts based" );
1483 html_desc.append( "domain counts based" + "</td></tr>" + nl );
1486 System.out.println( "domain proteins counts based" );
1487 html_desc.append( "domain proteins counts based" + "</td></tr>" + nl );
1490 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
1492 System.out.print( " Sort by : " );
1493 html_desc.append( "<tr><td>Sort by:</td><td>" );
1494 switch ( domain_similarity_sort_field ) {
1496 System.out.print( "score minimum" );
1497 html_desc.append( "score minimum" );
1500 System.out.print( "score maximum" );
1501 html_desc.append( "score maximum" );
1504 System.out.print( "score mean" );
1505 html_desc.append( "score mean" );
1508 System.out.print( "score standard deviation" );
1509 html_desc.append( "score standard deviation" );
1512 System.out.print( "species number" );
1513 html_desc.append( "species number" );
1516 System.out.print( "alphabetical domain identifier" );
1517 html_desc.append( "alphabetical domain identifier" );
1519 case MAX_DIFFERENCE:
1520 System.out.print( "(maximal) difference" );
1521 html_desc.append( "(maximal) difference" );
1523 case ABS_MAX_COUNTS_DIFFERENCE:
1524 System.out.print( "absolute (maximal) counts difference" );
1525 html_desc.append( "absolute (maximal) counts difference" );
1527 case MAX_COUNTS_DIFFERENCE:
1528 System.out.print( "(maximal) counts difference" );
1529 html_desc.append( "(maximal) counts difference" );
1532 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1534 if ( sort_by_species_count_first ) {
1535 System.out.println( " (sort by species count first)" );
1536 html_desc.append( " (sort by species count first)" );
1539 System.out.println();
1541 html_desc.append( "</td></tr>" + nl );
1542 System.out.print( " Detailedness : " );
1543 switch ( detailedness ) {
1545 System.out.println( "basic" );
1547 case LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES:
1548 System.out.println( "list combining domains for each species" );
1551 System.out.println( "punctilious" );
1554 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for detailedness" );
1556 System.out.print( " Print option : " );
1557 switch ( domain_similarity_print_option ) {
1559 System.out.println( "HTML" );
1561 case SIMPLE_TAB_DELIMITED:
1562 System.out.println( "simple tab delimited" );
1565 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for print option" );
1567 System.out.print( " Species matrix : " + species_matrix );
1568 System.out.println();
1569 final File dc_data_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + DATA_FILE_SUFFIX );
1570 System.out.println( "Domain comb data output : " + dc_data_file );
1571 html_desc.append( "<tr><td>Domain combination data output:</td><td> " + dc_data_file + " </td></tr>" );
1572 System.out.println();
1573 if ( perform_pwc ) {
1574 System.out.println( "Pairwise comparisons: " );
1575 html_desc.append( "<tr><td>Pairwise comparisons:</td><td></td></tr>" );
1576 System.out.print( " Sort by : " );
1577 html_desc.append( "<tr><td>Sort by:</td><td>" );
1578 switch ( domain_similarity_sort_field_for_automated_pwc ) {
1580 System.out.print( "score mean" );
1581 html_desc.append( "score mean" );
1584 System.out.print( "alphabetical domain identifier" );
1585 html_desc.append( "alphabetical domain identifier" );
1587 case MAX_DIFFERENCE:
1588 System.out.print( "difference" );
1589 html_desc.append( "difference" );
1591 case ABS_MAX_COUNTS_DIFFERENCE:
1592 System.out.print( "absolute counts difference" );
1593 html_desc.append( "absolute counts difference" );
1595 case MAX_COUNTS_DIFFERENCE:
1596 System.out.print( "counts difference" );
1597 html_desc.append( "counts difference" );
1601 .unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1603 System.out.println();
1604 html_desc.append( "</td></tr>" + nl );
1605 if ( jacknifed_distances ) {
1606 html_desc.append( "<tr><td>Jacknife:</td><td>" + jacknife_resamplings + " resamplings</td></tr>" + nl );
1607 html_desc.append( "<tr><td>Jacknife ratio:</td><td>" + ForesterUtil.round( jacknife_ratio, 2 )
1608 + "</td></tr>" + nl );
1609 html_desc.append( "<tr><td>Jacknife random number seed:</td><td>" + random_seed + "</td></tr>" + nl );
1610 System.out.println( " Jacknife : " + jacknife_resamplings + " resamplings" );
1611 System.out.println( " Ratio : " + ForesterUtil.round( jacknife_ratio, 2 ) );
1612 System.out.println( " Random number seed : " + random_seed );
1614 // if ( infer_species_trees ) {
1615 // html_desc.append( "<tr><td>Infer species trees:</td><td>true</td></tr>" + nl );
1616 // System.out.println( " Infer species trees : true" );
1618 if ( ( intrees != null ) && ( intrees.length > 0 ) ) {
1619 for( final File intree_file : intree_files ) {
1620 html_desc.append( "<tr><td>Intree for gain/loss parsimony analysis:</td><td>" + intree_file
1621 + "</td></tr>" + nl );
1622 System.out.println( " Intree for gain/loss pars.: " + intree_file );
1625 if ( radomize_fitch_parsimony ) {
1626 html_desc.append( "<tr><td> Random number seed for Fitch parsimony analysis:</td><td>"
1627 + random_number_seed_for_fitch_parsimony + "</td></tr>" + nl );
1628 System.out.println( " Random number seed : " + random_number_seed_for_fitch_parsimony );
1630 if ( ( domain_id_to_secondary_features_maps != null ) && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
1631 for( int i = 0; i < secondary_features_map_files.length; i++ ) {
1632 html_desc.append( "<tr><td>Secondary features map file:</td><td>"
1633 + secondary_features_map_files[ i ] + "</td></tr>" + nl );
1634 System.out.println( "Secondary features map file : " + secondary_features_map_files[ i ]
1635 + " [mappings for " + domain_id_to_secondary_features_maps[ i ].size() + " domain ids]" );
1637 System.out.println();
1638 System.out.println( "Domain ids to secondary features map:" );
1639 for( final DomainId domain_id : domain_id_to_secondary_features_maps[ i ].keySet() ) {
1640 System.out.print( domain_id.getId() );
1641 System.out.print( " => " );
1642 for( final String sec : domain_id_to_secondary_features_maps[ i ].get( domain_id ) ) {
1643 System.out.print( sec );
1644 System.out.print( " " );
1646 System.out.println();
1651 } // if ( perform_pwc ) {
1652 System.out.println();
1653 html_desc.append( "<tr><td>Command line:</td><td>\n" + cla.getCommandLineArgsAsString() + "\n</td></tr>" + nl );
1654 System.out.println( "Command line : " + cla.getCommandLineArgsAsString() );
1655 BufferedWriter[] query_domains_writer_ary = null;
1656 List<DomainId>[] query_domain_ids_array = null;
1657 if ( query_domain_ids != null ) {
1658 final String[] query_domain_ids_str_array = query_domain_ids.split( "#" );
1659 query_domain_ids_array = new ArrayList[ query_domain_ids_str_array.length ];
1660 query_domains_writer_ary = new BufferedWriter[ query_domain_ids_str_array.length ];
1661 for( int i = 0; i < query_domain_ids_str_array.length; i++ ) {
1662 String query_domain_ids_str = query_domain_ids_str_array[ i ];
1663 final String[] query_domain_ids_str_ary = query_domain_ids_str.split( "~" );
1664 final List<DomainId> query = new ArrayList<DomainId>();
1665 for( final String element : query_domain_ids_str_ary ) {
1666 query.add( new DomainId( element ) );
1668 query_domain_ids_array[ i ] = query;
1669 query_domain_ids_str = query_domain_ids_str.replace( '~', '_' );
1670 String protein_names_writer_str = query_domain_ids_str + surfacing.SEQ_EXTRACT_SUFFIX;
1671 if ( out_dir != null ) {
1672 protein_names_writer_str = out_dir + ForesterUtil.FILE_SEPARATOR + protein_names_writer_str;
1675 query_domains_writer_ary[ i ] = new BufferedWriter( new FileWriter( protein_names_writer_str ) );
1677 catch ( final IOException e ) {
1678 ForesterUtil.fatalError( surfacing.PRG_NAME, "Could not open [" + protein_names_writer_str + "]: "
1679 + e.getLocalizedMessage() );
1683 SortedMap<Species, List<Protein>> protein_lists_per_species = null; //This will only be created if neede.
1684 boolean need_protein_lists_per_species = false;
1685 if ( ( plus_minus_analysis_high_copy_base_species.size() > 0 ) || output_protein_lists_for_all_domains ) {
1686 need_protein_lists_per_species = true;
1688 if ( need_protein_lists_per_species ) {
1689 protein_lists_per_species = new TreeMap<Species, List<Protein>>();
1691 final List<GenomeWideCombinableDomains> gwcd_list = new ArrayList<GenomeWideCombinableDomains>( number_of_genomes );
1692 final SortedSet<DomainId> all_domains_encountered = new TreeSet<DomainId>();
1693 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered = new TreeSet<BinaryDomainCombination>();
1694 List<BinaryDomainCombination> all_bin_domain_combinations_gained_fitch = null;
1695 List<BinaryDomainCombination> all_bin_domain_combinations_lost_fitch = null;
1696 if ( ( intrees != null ) && ( intrees.length == 1 ) ) {
1697 all_bin_domain_combinations_gained_fitch = new ArrayList<BinaryDomainCombination>();
1698 all_bin_domain_combinations_lost_fitch = new ArrayList<BinaryDomainCombination>();
1700 final DomainLengthsTable domain_lengths_table = new DomainLengthsTable();
1701 final File per_genome_domain_promiscuity_statistics_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR
1702 + output_file + D_PROMISCUITY_FILE_SUFFIX );
1703 BufferedWriter per_genome_domain_promiscuity_statistics_writer = null;
1705 per_genome_domain_promiscuity_statistics_writer = new BufferedWriter( new FileWriter( per_genome_domain_promiscuity_statistics_file ) );
1706 per_genome_domain_promiscuity_statistics_writer.write( "Species:\t" );
1707 per_genome_domain_promiscuity_statistics_writer.write( "Mean:\t" );
1708 per_genome_domain_promiscuity_statistics_writer.write( "SD:\t" );
1709 per_genome_domain_promiscuity_statistics_writer.write( "Median:\t" );
1710 per_genome_domain_promiscuity_statistics_writer.write( "Min:\t" );
1711 per_genome_domain_promiscuity_statistics_writer.write( "Max:\t" );
1712 per_genome_domain_promiscuity_statistics_writer.write( "N:\t" );
1713 per_genome_domain_promiscuity_statistics_writer.write( "Max Promiscuous Domains:"
1714 + ForesterUtil.LINE_SEPARATOR );
1716 catch ( final IOException e2 ) {
1717 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1719 final File log_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + LOG_FILE_SUFFIX );
1720 BufferedWriter log_writer = null;
1722 log_writer = new BufferedWriter( new FileWriter( log_file ) );
1724 catch ( final IOException e2 ) {
1725 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1727 BufferedWriter dc_data_writer = null;
1729 dc_data_writer = new BufferedWriter( new FileWriter( dc_data_file ) );
1730 dc_data_writer.write( DATA_FILE_DESC );
1731 dc_data_writer.write( ForesterUtil.LINE_SEPARATOR );
1733 catch ( final IOException e2 ) {
1734 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1736 final DescriptiveStatistics protein_coverage_stats = new BasicDescriptiveStatistics();
1737 final DescriptiveStatistics all_genomes_domains_per_potein_stats = new BasicDescriptiveStatistics();
1738 final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo = new TreeMap<Integer, Integer>();
1739 final SortedSet<String> domains_which_are_always_single = new TreeSet<String>();
1740 final SortedSet<String> domains_which_are_sometimes_single_sometimes_not = new TreeSet<String>();
1741 final SortedSet<String> domains_which_never_single = new TreeSet<String>();
1742 BufferedWriter domains_per_potein_stats_writer = null;
1744 domains_per_potein_stats_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
1745 + output_file + "__domains_per_potein_stats.txt" ) );
1746 domains_per_potein_stats_writer.write( "Genome" );
1747 domains_per_potein_stats_writer.write( "\t" );
1748 domains_per_potein_stats_writer.write( "Mean" );
1749 domains_per_potein_stats_writer.write( "\t" );
1750 domains_per_potein_stats_writer.write( "SD" );
1751 domains_per_potein_stats_writer.write( "\t" );
1752 domains_per_potein_stats_writer.write( "Median" );
1753 domains_per_potein_stats_writer.write( "\t" );
1754 domains_per_potein_stats_writer.write( "N" );
1755 domains_per_potein_stats_writer.write( "\t" );
1756 domains_per_potein_stats_writer.write( "Min" );
1757 domains_per_potein_stats_writer.write( "\t" );
1758 domains_per_potein_stats_writer.write( "Max" );
1759 domains_per_potein_stats_writer.write( "\n" );
1761 catch ( final IOException e3 ) {
1762 e3.printStackTrace();
1764 Map<String, DescriptiveStatistics> protein_length_stats_by_dc = null;
1765 Map<String, DescriptiveStatistics> domain_number_stats_by_dc = null;
1766 final Map<String, DescriptiveStatistics> domain_length_stats_by_domain = new HashMap<String, DescriptiveStatistics>();
1767 if ( PERFORM_DC_REGAIN_PROTEINS_STATS ) {
1768 protein_length_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1769 domain_number_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1772 for( int i = 0; i < number_of_genomes; ++i ) {
1773 System.out.println();
1774 System.out.println( ( i + 1 ) + "/" + number_of_genomes );
1775 log( ( i + 1 ) + "/" + number_of_genomes, log_writer );
1776 System.out.println( "Processing : " + input_file_properties[ i ][ 0 ] );
1777 log( "Genome : " + input_file_properties[ i ][ 0 ], log_writer );
1778 HmmscanPerDomainTableParser parser = null;
1779 INDIVIDUAL_SCORE_CUTOFF ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF.NONE;
1780 if ( individual_score_cutoffs != null ) {
1781 ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF_DEFAULT;
1783 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1784 || ( negative_domains_filter_file != null ) ) {
1785 HmmscanPerDomainTableParser.FilterType filter_type = HmmscanPerDomainTableParser.FilterType.NONE;
1786 if ( positive_filter_file != null ) {
1787 filter_type = HmmscanPerDomainTableParser.FilterType.POSITIVE_PROTEIN;
1789 else if ( negative_filter_file != null ) {
1790 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_PROTEIN;
1792 else if ( negative_domains_filter_file != null ) {
1793 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_DOMAIN;
1795 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1796 input_file_properties[ i ][ 1 ],
1803 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1804 input_file_properties[ i ][ 1 ],
1808 if ( e_value_max >= 0.0 ) {
1809 parser.setEValueMaximum( e_value_max );
1811 parser.setIgnoreDufs( ignore_dufs );
1812 parser.setIgnoreVirusLikeIds( ignore_virus_like_ids );
1813 parser.setIgnoreEngulfedDomains( no_engulfing_overlaps );
1814 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1815 parser.setMaxAllowedOverlap( max_allowed_overlap );
1817 parser.setReturnType( HmmscanPerDomainTableParser.ReturnType.UNORDERED_PROTEIN_DOMAIN_COLLECTION_PER_PROTEIN );
1818 if ( individual_score_cutoffs != null ) {
1819 parser.setIndividualScoreCutoffs( individual_score_cutoffs );
1821 List<Protein> protein_list = null;
1823 protein_list = parser.parse();
1825 catch ( final IOException e ) {
1826 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1828 catch ( final Exception e ) {
1829 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, e.getMessage(), e );
1832 System.out.println( "Domains ignored due to negative domain filter: " );
1833 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToNegativeDomainFilterCountsMap() );
1834 System.out.println( "Domains ignored due to virus like id: " );
1835 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToVirusLikeIdCountsMap() );
1837 final double coverage = ( double ) protein_list.size() / parser.getProteinsEncountered();
1838 protein_coverage_stats.addValue( coverage );
1839 System.out.println( "Number of proteins encountered : " + parser.getProteinsEncountered() );
1840 log( "Number of proteins encountered : " + parser.getProteinsEncountered(), log_writer );
1841 System.out.println( "Number of proteins stored : " + protein_list.size() );
1842 log( "Number of proteins stored : " + protein_list.size(), log_writer );
1843 System.out.println( "Coverage : "
1844 + ForesterUtil.roundToInt( 100.0 * coverage ) + "%" );
1845 log( "Coverage : " + ForesterUtil.roundToInt( 100.0 * coverage )
1846 + "%", log_writer );
1847 System.out.println( "Domains encountered : " + parser.getDomainsEncountered() );
1848 log( "Domains encountered : " + parser.getDomainsEncountered(), log_writer );
1849 System.out.println( "Domains stored : " + parser.getDomainsStored() );
1850 log( "Domains stored : " + parser.getDomainsStored(), log_writer );
1851 System.out.println( "Distinct domains stored : "
1852 + parser.getDomainsStoredSet().size() );
1853 log( "Distinct domains stored : " + parser.getDomainsStoredSet().size(), log_writer );
1854 System.out.println( "Domains ignored due to individual score cutoffs: "
1855 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() );
1856 log( "Domains ignored due to individual score cutoffs: "
1857 + parser.getDomainsIgnoredDueToIndividualScoreCutoff(),
1859 System.out.println( "Domains ignored due to E-value : "
1860 + parser.getDomainsIgnoredDueToEval() );
1861 log( "Domains ignored due to E-value : " + parser.getDomainsIgnoredDueToEval(), log_writer );
1862 System.out.println( "Domains ignored due to DUF designation : "
1863 + parser.getDomainsIgnoredDueToDuf() );
1864 log( "Domains ignored due to DUF designation : " + parser.getDomainsIgnoredDueToDuf(), log_writer );
1865 if ( ignore_virus_like_ids ) {
1866 System.out.println( "Domains ignored due virus like ids : "
1867 + parser.getDomainsIgnoredDueToVirusLikeIds() );
1868 log( "Domains ignored due virus like ids : " + parser.getDomainsIgnoredDueToVirusLikeIds(),
1871 System.out.println( "Domains ignored due negative domain filter : "
1872 + parser.getDomainsIgnoredDueToNegativeDomainFilter() );
1873 log( "Domains ignored due negative domain filter : "
1874 + parser.getDomainsIgnoredDueToNegativeDomainFilter(),
1876 System.out.println( "Domains ignored due to overlap : "
1877 + parser.getDomainsIgnoredDueToOverlap() );
1878 log( "Domains ignored due to overlap : " + parser.getDomainsIgnoredDueToOverlap(),
1880 if ( negative_filter_file != null ) {
1881 System.out.println( "Proteins ignored due to negative filter : "
1882 + parser.getProteinsIgnoredDueToFilter() );
1883 log( "Proteins ignored due to negative filter : " + parser.getProteinsIgnoredDueToFilter(),
1886 if ( positive_filter_file != null ) {
1887 System.out.println( "Proteins ignored due to positive filter : "
1888 + parser.getProteinsIgnoredDueToFilter() );
1889 log( "Proteins ignored due to positive filter : " + parser.getProteinsIgnoredDueToFilter(),
1892 System.out.println( "Time for processing : " + parser.getTime() + "ms" );
1893 log( "", log_writer );
1894 html_desc.append( "<tr><td>" + input_file_properties[ i ][ 0 ] + " [species: "
1895 + input_file_properties[ i ][ 1 ] + "]" + ":</td><td>domains analyzed: "
1896 + parser.getDomainsStored() + "; domains ignored: [ind score cutoffs: "
1897 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() + "] [E-value cutoff: "
1898 + parser.getDomainsIgnoredDueToEval() + "] [DUF: " + parser.getDomainsIgnoredDueToDuf()
1899 + "] [virus like ids: " + parser.getDomainsIgnoredDueToVirusLikeIds()
1900 + "] [negative domain filter: " + parser.getDomainsIgnoredDueToNegativeDomainFilter()
1901 + "] [overlap: " + parser.getDomainsIgnoredDueToOverlap() + "]" );
1902 if ( negative_filter_file != null ) {
1903 html_desc.append( "; proteins ignored due to negative filter: "
1904 + parser.getProteinsIgnoredDueToFilter() );
1906 if ( positive_filter_file != null ) {
1907 html_desc.append( "; proteins ignored due to positive filter: "
1908 + parser.getProteinsIgnoredDueToFilter() );
1910 html_desc.append( "</td></tr>" + nl );
1911 // domain_partner_counts_array[ i ] =
1912 // Methods.getDomainPartnerCounts( protein_domain_collections_array[
1914 // false, input_file_properties[ i ][ 1 ] );
1917 for( final Protein protein : protein_list ) {
1918 dc_data_writer.write( SurfacingUtil.proteinToDomainCombinations( protein, count + "", "\t" )
1921 for( final Domain d : protein.getProteinDomains() ) {
1922 final String d_str = d.getDomainId().toString();
1923 if ( !domain_length_stats_by_domain.containsKey( d_str ) ) {
1924 domain_length_stats_by_domain.put( d_str, new BasicDescriptiveStatistics() );
1926 domain_length_stats_by_domain.get( d_str ).addValue( d.getLength() );
1930 catch ( final IOException e ) {
1931 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1933 SurfacingUtil.domainsPerProteinsStatistics( input_file_properties[ i ][ 1 ],
1935 all_genomes_domains_per_potein_stats,
1936 all_genomes_domains_per_potein_histo,
1937 domains_which_are_always_single,
1938 domains_which_are_sometimes_single_sometimes_not,
1939 domains_which_never_single,
1940 domains_per_potein_stats_writer );
1941 gwcd_list.add( BasicGenomeWideCombinableDomains
1942 .createInstance( protein_list,
1943 ignore_combination_with_same,
1944 new BasicSpecies( input_file_properties[ i ][ 1 ] ),
1945 domain_id_to_go_ids_map,
1947 protein_length_stats_by_dc,
1948 domain_number_stats_by_dc ) );
1949 domain_lengths_table.addLengths( protein_list );
1950 if ( gwcd_list.get( i ).getSize() > 0 ) {
1951 SurfacingUtil.writeDomainCombinationsCountsFile( input_file_properties,
1953 per_genome_domain_promiscuity_statistics_writer,
1957 if ( output_binary_domain_combinationsfor_graph_analysis ) {
1958 SurfacingUtil.writeBinaryDomainCombinationsFileForGraphAnalysis( input_file_properties,
1964 SurfacingUtil.addAllDomainIdsToSet( gwcd_list.get( i ), all_domains_encountered );
1965 SurfacingUtil.addAllBinaryDomainCombinationToSet( gwcd_list.get( i ),
1966 all_bin_domain_combinations_encountered );
1968 if ( query_domains_writer_ary != null ) {
1969 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1971 SurfacingUtil.extractProteinNames( protein_list,
1972 query_domain_ids_array[ j ],
1973 query_domains_writer_ary[ j ],
1975 LIMIT_SPEC_FOR_PROT_EX );
1976 query_domains_writer_ary[ j ].flush();
1978 catch ( final IOException e ) {
1979 e.printStackTrace();
1983 if ( need_protein_lists_per_species ) {
1984 protein_lists_per_species.put( new BasicSpecies( input_file_properties[ i ][ 1 ] ), protein_list );
1989 catch ( final IOException e2 ) {
1990 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1993 } // for( int i = 0; i < number_of_genomes; ++i ) {
1994 ForesterUtil.programMessage( PRG_NAME, "Wrote domain promiscuities to: "
1995 + per_genome_domain_promiscuity_statistics_file );
1998 domains_per_potein_stats_writer.write( "ALL" );
1999 domains_per_potein_stats_writer.write( "\t" );
2000 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.arithmeticMean() + "" );
2001 domains_per_potein_stats_writer.write( "\t" );
2002 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.sampleStandardDeviation() + "" );
2003 domains_per_potein_stats_writer.write( "\t" );
2004 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.median() + "" );
2005 domains_per_potein_stats_writer.write( "\t" );
2006 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getN() + "" );
2007 domains_per_potein_stats_writer.write( "\t" );
2008 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMin() + "" );
2009 domains_per_potein_stats_writer.write( "\t" );
2010 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMax() + "" );
2011 domains_per_potein_stats_writer.write( "\n" );
2012 domains_per_potein_stats_writer.close();
2013 printOutPercentageOfMultidomainProteins( all_genomes_domains_per_potein_histo, log_writer );
2014 ForesterUtil.map2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2015 + "__all_genomes_domains_per_potein_histo.txt" ), all_genomes_domains_per_potein_histo, "\t", "\n" );
2016 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2017 + "__domains_always_single_.txt" ), domains_which_are_always_single, "\n" );
2018 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2019 + "__domains_single_or_combined.txt" ), domains_which_are_sometimes_single_sometimes_not, "\n" );
2020 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2021 + "__domains_always_combined.txt" ), domains_which_never_single, "\n" );
2022 ForesterUtil.programMessage( PRG_NAME,
2023 "Average of proteins with a least one domain assigned: "
2024 + ( 100 * protein_coverage_stats.arithmeticMean() ) + "% (+/-"
2025 + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)" );
2026 ForesterUtil.programMessage( PRG_NAME, "Range of proteins with a least one domain assigned: " + 100
2027 * protein_coverage_stats.getMin() + "%-" + 100 * protein_coverage_stats.getMax() + "%" );
2028 log( "Average of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.arithmeticMean() )
2029 + "% (+/-" + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)", log_writer );
2030 log( "Range of prot with a least one dom assigned : " + 100 * protein_coverage_stats.getMin() + "%-"
2031 + 100 * protein_coverage_stats.getMax() + "%", log_writer );
2033 catch ( final IOException e2 ) {
2034 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
2036 if ( query_domains_writer_ary != null ) {
2037 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
2039 query_domains_writer_ary[ j ].close();
2041 catch ( final IOException e ) {
2042 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
2047 per_genome_domain_promiscuity_statistics_writer.close();
2048 dc_data_writer.close();
2051 catch ( final IOException e2 ) {
2052 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
2054 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
2056 SurfacingUtil.executeDomainLengthAnalysis( input_file_properties,
2058 domain_lengths_table,
2059 domain_lengths_analysis_outfile );
2061 catch ( final IOException e1 ) {
2062 ForesterUtil.fatalError( surfacing.PRG_NAME, e1.toString() );
2064 System.out.println();
2065 ForesterUtil.programMessage( PRG_NAME, "Wrote domain length data to: " + domain_lengths_analysis_outfile );
2066 System.out.println();
2068 final long analysis_start_time = new Date().getTime();
2069 PairwiseDomainSimilarityCalculator pw_calc = null;
2070 // double[] values_for_all_scores_histogram = null;
2071 final DomainSimilarityCalculator calc = new BasicDomainSimilarityCalculator( domain_similarity_sort_field,
2072 sort_by_species_count_first,
2073 number_of_genomes == 2 );
2074 switch ( scoring ) {
2076 pw_calc = new CombinationsBasedPairwiseDomainSimilarityCalculator();
2079 pw_calc = new DomainCountsBasedPairwiseSimilarityCalculator();
2082 pw_calc = new ProteinCountsBasedPairwiseDomainSimilarityCalculator();
2085 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
2087 DomainSimilarityCalculator.GoAnnotationOutput go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.NONE;
2088 if ( domain_id_to_go_ids_map != null ) {
2089 go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.ALL;
2091 final SortedSet<DomainSimilarity> similarities = calc
2092 .calculateSimilarities( pw_calc,
2094 ignore_domains_without_combs_in_all_spec,
2095 ignore_species_specific_domains );
2096 SurfacingUtil.decoratePrintableDomainSimilarities( similarities,
2098 go_annotation_output,
2100 go_namespace_limit );
2101 DescriptiveStatistics pw_stats = null;
2103 String my_outfile = output_file.toString();
2104 Map<Character, Writer> split_writers = null;
2105 Writer writer = null;
2106 if ( similarities.size() > MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING ) {
2107 if ( my_outfile.endsWith( ".html" ) ) {
2108 my_outfile = my_outfile.substring( 0, my_outfile.length() - 5 );
2110 split_writers = new HashMap<Character, Writer>();
2111 createSplitWriters( out_dir, my_outfile, split_writers );
2113 else if ( !my_outfile.endsWith( ".html" ) ) {
2114 my_outfile += ".html";
2115 writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) );
2117 List<Species> species_order = null;
2118 if ( species_matrix ) {
2119 species_order = new ArrayList<Species>();
2120 for( int i = 0; i < number_of_genomes; i++ ) {
2121 species_order.add( new BasicSpecies( input_file_properties[ i ][ 1 ] ) );
2124 html_desc.append( "<tr><td>Sum of all distinct binary combinations:</td><td>"
2125 + all_bin_domain_combinations_encountered.size() + "</td></tr>" + nl );
2126 html_desc.append( "<tr><td>Sum of all distinct domains:</td><td>" + all_domains_encountered.size()
2127 + "</td></tr>" + nl );
2128 html_desc.append( "<tr><td>Analysis date/time:</td><td>"
2129 + new java.text.SimpleDateFormat( "yyyy.MM.dd HH:mm:ss" ).format( new java.util.Date() )
2130 + "</td></tr>" + nl );
2131 html_desc.append( "</table>" + nl );
2132 pw_stats = SurfacingUtil
2133 .writeDomainSimilaritiesToFile( html_desc,
2134 new StringBuilder( number_of_genomes + " genomes" ),
2138 number_of_genomes == 2,
2140 domain_similarity_print_option,
2141 domain_similarity_sort_field,
2144 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote main output (includes domain similarities) to: \""
2145 + ( out_dir == null ? my_outfile : out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) + "\"" );
2147 catch ( final IOException e ) {
2148 ForesterUtil.fatalError( surfacing.PRG_NAME, "Failed to write similarites to: \"" + output_file + "\" ["
2149 + e.getMessage() + "]" );
2151 System.out.println();
2152 // values_for_all_scores_histogram = pw_stats.getDataAsDoubleArray();
2153 final Species[] species = new Species[ number_of_genomes ];
2154 for( int i = 0; i < number_of_genomes; ++i ) {
2155 species[ i ] = new BasicSpecies( input_file_properties[ i ][ 1 ] );
2157 List<Phylogeny> inferred_trees = null;
2158 if ( ( number_of_genomes > 2 ) && perform_pwc ) {
2159 final PairwiseGenomeComparator pwgc = new PairwiseGenomeComparator();
2160 pwgc.performPairwiseComparisons( html_desc,
2161 sort_by_species_count_first,
2163 ignore_domains_without_combs_in_all_spec,
2164 ignore_species_specific_domains,
2165 domain_similarity_sort_field_for_automated_pwc,
2166 domain_similarity_print_option,
2168 domain_id_to_go_ids_map,
2175 automated_pairwise_comparison_suffix,
2177 surfacing.PAIRWISE_DOMAIN_COMPARISONS_PREFIX,
2181 String matrix_output_file = new String( output_file.toString() );
2182 if ( matrix_output_file.indexOf( '.' ) > 1 ) {
2183 matrix_output_file = matrix_output_file.substring( 0, matrix_output_file.indexOf( '.' ) );
2185 if ( out_dir != null ) {
2186 matrix_output_file = out_dir + ForesterUtil.FILE_SEPARATOR + matrix_output_file;
2187 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2189 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2190 + surfacing.MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans() );
2192 .writeMatrixToFile( new File( matrix_output_file
2193 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2194 pwgc.getSharedBinaryCombinationsBasedDistances() );
2195 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2196 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2197 pwgc.getSharedDomainsBasedDistances() );
2198 final Phylogeny nj_gd = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2199 + surfacing.NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans()
2201 final Phylogeny nj_bc = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2202 + surfacing.NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2203 .getSharedBinaryCombinationsBasedDistances().get( 0 ) );
2204 final Phylogeny nj_d = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2205 + surfacing.NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2206 .getSharedDomainsBasedDistances().get( 0 ) );
2207 inferred_trees = new ArrayList<Phylogeny>();
2208 inferred_trees.add( nj_gd );
2209 inferred_trees.add( nj_bc );
2210 inferred_trees.add( nj_d );
2211 if ( jacknifed_distances ) {
2212 pwgc.performPairwiseComparisonsJacknifed( species,
2216 jacknife_resamplings,
2220 .writeMatrixToFile( new File( matrix_output_file
2222 + ForesterUtil.round( jacknife_ratio, 2 )
2224 + jacknife_resamplings
2225 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2226 pwgc.getSharedBinaryCombinationsBasedDistances() );
2228 .writeMatrixToFile( new File( matrix_output_file + "_" + ForesterUtil.round( jacknife_ratio, 2 )
2229 + "_" + jacknife_resamplings
2230 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2231 pwgc.getSharedDomainsBasedDistances() );
2232 // if ( infer_species_trees ) {
2233 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2234 // + INFERRED_SBC_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc
2235 // .getSharedBinaryCombinationsBasedDistances() );
2236 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2237 // + INFERRED_SD_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc.getSharedDomainsBasedDistances() );
2240 } // if ( ( output_file != null ) && ( number_of_genomes > 2 ) && !isEmpty( automated_pairwise_comparison_suffix ) )
2241 if ( ( out_dir != null ) && ( !perform_pwc ) ) {
2242 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2244 writePresentToNexus( output_file, positive_filter_file, filter, gwcd_list );
2245 if ( ( ( intrees != null ) && ( intrees.length > 0 ) ) && ( number_of_genomes > 2 ) ) {
2246 final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
2248 max_allowed_overlap,
2249 no_engulfing_overlaps,
2253 if ( radomize_fitch_parsimony ) {
2254 s += random_number_seed_for_fitch_parsimony + "_";
2257 for( final Phylogeny intree : intrees ) {
2258 final String outfile_name = ForesterUtil.removeSuffix( output_file.toString() ) + s
2259 + ForesterUtil.removeSuffix( intree_files[ i ].toString() );
2260 final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator.createInstance( intree,
2262 SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
2263 radomize_fitch_parsimony,
2267 domain_id_to_go_ids_map,
2270 parameters_sb.toString(),
2271 domain_id_to_secondary_features_maps,
2272 positive_filter_file == null ? null : filter,
2273 output_binary_domain_combinationsfor_graph_analysis,
2274 all_bin_domain_combinations_gained_fitch,
2275 all_bin_domain_combinations_lost_fitch,
2277 protein_length_stats_by_dc,
2278 domain_number_stats_by_dc,
2279 domain_length_stats_by_domain );
2280 // Listing of all domain combinations gained is only done if only one input tree is used.
2281 if ( ( domain_id_to_secondary_features_maps != null )
2282 && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
2284 for( final Map<DomainId, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
2285 final Map<Species, MappingResults> mapping_results_map = new TreeMap<Species, MappingResults>();
2286 final DomainParsimonyCalculator secondary_features_parsimony = DomainParsimonyCalculator
2287 .createInstance( intree, gwcd_list, domain_id_to_secondary_features_map );
2289 .executeParsimonyAnalysisForSecondaryFeatures( outfile_name
2291 + secondary_features_map_files[ j++ ],
2292 secondary_features_parsimony,
2294 parameters_sb.toString(),
2295 mapping_results_map );
2297 System.out.println();
2298 System.out.println( "Mapping to secondary features:" );
2299 for( final Species spec : mapping_results_map.keySet() ) {
2300 final MappingResults mapping_results = mapping_results_map.get( spec );
2301 final int total_domains = mapping_results.getSumOfFailures()
2302 + mapping_results.getSumOfSuccesses();
2303 System.out.print( spec + ":" );
2304 System.out.print( " mapped domains = " + mapping_results.getSumOfSuccesses() );
2305 System.out.print( ", not mapped domains = " + mapping_results.getSumOfFailures() );
2306 if ( total_domains > 0 ) {
2307 System.out.println( ", mapped ratio = "
2308 + ( 100 * mapping_results.getSumOfSuccesses() / total_domains ) + "%" );
2311 System.out.println( ", mapped ratio = n/a (total domains = 0 )" );
2318 } // for( final Phylogeny intree : intrees ) {
2320 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
2321 executePlusMinusAnalysis( output_file,
2322 plus_minus_analysis_high_copy_base_species,
2323 plus_minus_analysis_high_copy_target_species,
2324 plus_minus_analysis_high_low_copy_species,
2326 protein_lists_per_species,
2327 domain_id_to_go_ids_map,
2329 plus_minus_analysis_numbers );
2331 if ( output_protein_lists_for_all_domains ) {
2332 writeProteinListsForAllSpecies( out_dir, protein_lists_per_species, gwcd_list );
2334 // if ( ( intrees != null ) && ( intrees.length > 0 ) && ( inferred_trees != null ) && ( inferred_trees.size() > 0 ) ) {
2335 // final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
2337 // max_allowed_overlap,
2338 // no_engulfing_overlaps,
2339 // cutoff_scores_file );
2341 // if ( radomize_fitch_parsimony ) {
2342 // s += random_number_seed_for_fitch_parsimony + "_";
2345 // for( final Phylogeny inferred_tree : inferred_trees ) {
2346 // if ( !inferred_tree.isRooted() ) {
2347 // intrees[ 0 ].getRoot().getName();
2350 // final String outfile_name = ForesterUtil.removeSuffix( inferred_tree.getName() ) + s;
2351 // final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator
2352 // .createInstance( inferred_tree, gwcd_list );
2353 // SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
2354 // radomize_fitch_parsimony,
2356 // domain_parsimony,
2358 // domain_id_to_go_ids_map,
2359 // go_id_to_term_map,
2360 // go_namespace_limit,
2361 // parameters_sb.toString() );
2365 if ( all_bin_domain_combinations_gained_fitch != null ) {
2367 executeFitchGainsAnalysis( new File( output_file
2368 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2369 all_bin_domain_combinations_gained_fitch,
2370 all_domains_encountered.size(),
2371 all_bin_domain_combinations_encountered,
2374 catch ( final IOException e ) {
2375 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2378 if ( all_bin_domain_combinations_lost_fitch != null ) {
2380 executeFitchGainsAnalysis( new File( output_file
2381 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2382 all_bin_domain_combinations_lost_fitch,
2383 all_domains_encountered.size(),
2384 all_bin_domain_combinations_encountered,
2387 catch ( final IOException e ) {
2388 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2391 final Runtime rt = java.lang.Runtime.getRuntime();
2392 final long free_memory = rt.freeMemory() / 1000000;
2393 final long total_memory = rt.totalMemory() / 1000000;
2394 ForesterUtil.programMessage( PRG_NAME, "Time for analysis : " + ( new Date().getTime() - analysis_start_time )
2396 ForesterUtil.programMessage( PRG_NAME, "Total running time: " + ( new Date().getTime() - start_time ) + "ms " );
2397 ForesterUtil.programMessage( PRG_NAME, "Free memory : " + free_memory + "MB, total memory: "
2398 + total_memory + "MB" );
2399 ForesterUtil.programMessage( PRG_NAME, "If this application is useful to you, please cite:" );
2400 ForesterUtil.programMessage( PRG_NAME, surfacing.WWW );
2401 ForesterUtil.programMessage( PRG_NAME, "OK" );
2402 System.out.println();
2405 private static void createSplitWriters( final File out_dir,
2406 final String my_outfile,
2407 final Map<Character, Writer> split_writers ) throws IOException {
2408 split_writers.put( 'a', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2409 + "_domains_A.html" ) ) );
2410 split_writers.put( 'b', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2411 + "_domains_B.html" ) ) );
2412 split_writers.put( 'c', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2413 + "_domains_C.html" ) ) );
2414 split_writers.put( 'd', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2415 + "_domains_D.html" ) ) );
2416 split_writers.put( 'e', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2417 + "_domains_E.html" ) ) );
2418 split_writers.put( 'f', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2419 + "_domains_F.html" ) ) );
2420 split_writers.put( 'g', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2421 + "_domains_G.html" ) ) );
2422 split_writers.put( 'h', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2423 + "_domains_H.html" ) ) );
2424 split_writers.put( 'i', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2425 + "_domains_I.html" ) ) );
2426 split_writers.put( 'j', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2427 + "_domains_J.html" ) ) );
2428 split_writers.put( 'k', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2429 + "_domains_K.html" ) ) );
2430 split_writers.put( 'l', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2431 + "_domains_L.html" ) ) );
2432 split_writers.put( 'm', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2433 + "_domains_M.html" ) ) );
2434 split_writers.put( 'n', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2435 + "_domains_N.html" ) ) );
2436 split_writers.put( 'o', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2437 + "_domains_O.html" ) ) );
2438 split_writers.put( 'p', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2439 + "_domains_P.html" ) ) );
2440 split_writers.put( 'q', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2441 + "_domains_Q.html" ) ) );
2442 split_writers.put( 'r', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2443 + "_domains_R.html" ) ) );
2444 split_writers.put( 's', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2445 + "_domains_S.html" ) ) );
2446 split_writers.put( 't', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2447 + "_domains_T.html" ) ) );
2448 split_writers.put( 'u', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2449 + "_domains_U.html" ) ) );
2450 split_writers.put( 'v', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2451 + "_domains_V.html" ) ) );
2452 split_writers.put( 'w', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2453 + "_domains_W.html" ) ) );
2454 split_writers.put( 'x', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2455 + "_domains_X.html" ) ) );
2456 split_writers.put( 'y', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2457 + "_domains_Y.html" ) ) );
2458 split_writers.put( 'z', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2459 + "_domains_Z.html" ) ) );
2460 split_writers.put( '0', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2461 + "_domains_0.html" ) ) );
2464 private static void printOutPercentageOfMultidomainProteins( final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo,
2465 final Writer log_writer ) {
2467 for( final Entry<Integer, Integer> entry : all_genomes_domains_per_potein_histo.entrySet() ) {
2468 sum += entry.getValue();
2470 final double percentage = 100.0 * ( sum - all_genomes_domains_per_potein_histo.get( 1 ) ) / sum;
2471 ForesterUtil.programMessage( PRG_NAME, "Percentage of multidomain proteins: " + percentage + "%" );
2472 log( "Percentage of multidomain proteins: : " + percentage + "%", log_writer );
2475 private static void preparePhylogenyForParsimonyAnalyses( final Phylogeny intree,
2476 final String[][] input_file_properties ) {
2477 final String[] genomes = new String[ input_file_properties.length ];
2478 for( int i = 0; i < input_file_properties.length; ++i ) {
2479 if ( intree.getNodes( input_file_properties[ i ][ 1 ] ).size() > 1 ) {
2480 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
2481 + "] is not unique in input tree " + intree.getName() );
2483 genomes[ i ] = input_file_properties[ i ][ 1 ];
2486 final PhylogenyNodeIterator it = intree.iteratorPostorder();
2487 while ( it.hasNext() ) {
2488 final PhylogenyNode n = it.next();
2489 if ( ForesterUtil.isEmpty( n.getName() ) ) {
2490 if ( n.getNodeData().isHasTaxonomy()
2491 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getTaxonomyCode() ) ) {
2492 n.setName( n.getNodeData().getTaxonomy().getTaxonomyCode() );
2494 else if ( n.getNodeData().isHasTaxonomy()
2495 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
2496 n.setName( n.getNodeData().getTaxonomy().getScientificName() );
2498 else if ( n.getNodeData().isHasTaxonomy()
2499 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getCommonName() ) ) {
2500 n.setName( n.getNodeData().getTaxonomy().getCommonName() );
2504 .fatalError( surfacing.PRG_NAME,
2505 "node with no name, scientific name, common name, or taxonomy code present" );
2510 final List<String> igns = PhylogenyMethods.deleteExternalNodesPositiveSelection( genomes, intree );
2511 if ( igns.size() > 0 ) {
2512 System.out.println( "Not using the following " + igns.size() + " nodes:" );
2513 for( int i = 0; i < igns.size(); ++i ) {
2514 System.out.println( " " + i + ": " + igns.get( i ) );
2516 System.out.println( "--" );
2518 for( int i = 0; i < input_file_properties.length; ++i ) {
2520 intree.getNode( input_file_properties[ i ][ 1 ] );
2522 catch ( final IllegalArgumentException e ) {
2523 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
2524 + "] not present/not unique in input tree" );
2529 // public static StringBuffer stringCombinableDomainsMapToStringBuffer(
2530 // final SortedMap<String, CombinableDomains> map ) {
2531 // final StringBuffer sb = new StringBuffer();
2532 // for( final Iterator<String> iter = map.keySet().iterator();
2533 // iter.hasNext(); ) {
2534 // final Object key = iter.next();
2535 // sb.append( ForesterUtil.pad( new StringBuffer( key.toString() ), 18, ' ',
2537 // final CombinableDomains domain_combination = map.get( key );
2538 // sb.append( ForesterUtil.pad( new StringBuffer( "" +
2539 // domain_combination.getNumberOfCombiningDomains() ), 8,
2541 // sb.append( domain_combination.toStringBuffer() );
2542 // sb.append( ForesterUtil.getLineSeparator() );
2546 private static void printHelp() {
2547 System.out.println();
2548 System.out.println( "Usage:" );
2549 System.out.println();
2550 System.out.println( "% java -Xms256m -Xmx512m -cp forester.jar org.forester.applications." + surfacing.PRG_NAME
2551 + " [options] <phylogen(y|ies) infile> [external node name 1] [name 2] ... [name n]" );
2552 System.out.println();
2553 System.out.println( " Note: This software might need a significant amount of memory (heap space);" );
2555 .println( " hence use \"-Xms128m -Xmx512m\" (or more) to prevent a \"java.lang.OutOfMemoryError\"." );
2556 System.out.println();
2557 System.out.println( " Options: " );
2558 System.out.println( surfacing.DETAILEDNESS_OPTION + ": level of detail for similarities output file (default:"
2559 + DETAILEDNESS_DEFAULT + ")" );
2560 System.out.println( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION
2561 + ": to ignore combinations with self (default: not to ignore)" );
2563 .println( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION
2564 + ": to ignore domains without combinations in any species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2566 .println( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION
2567 + ": to ignore domains specific to one species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2568 System.out.println( surfacing.NOT_IGNORE_DUFS_OPTION
2569 + ": to _not_ ignore DUFs (domains with unknown function) (default: ignore DUFs)" );
2571 .println( surfacing.IGNORE_VIRAL_IDS
2572 + ": to ignore domains with ids containing 'vir', 'retro', 'transpos', 'phage', or starting with 'rv' or 'gag_'" );
2573 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_OPTION + ": sorting for similarities (default: "
2574 + DOMAIN_SORT_FILD_DEFAULT + ")" );
2575 System.out.println( surfacing.OUTPUT_FILE_OPTION + ": name for (main) output file (mandatory)" );
2576 System.out.println( surfacing.MAX_E_VALUE_OPTION + ": max (inclusive) E-value" );
2577 System.out.println( surfacing.MAX_ALLOWED_OVERLAP_OPTION + ": maximal allowed domain overlap" );
2578 System.out.println( surfacing.NO_ENGULFING_OVERLAP_OPTION + ": to ignore engulfed lower confidence domains" );
2579 System.out.println( surfacing.SPECIES_MATRIX_OPTION + ": species matrix" );
2580 System.out.println( surfacing.SCORING_OPTION + ": scoring (default:" + SCORING_DEFAULT + ")" );
2581 System.out.println( surfacing.DOMAIN_COUNT_SORT_OPTION + ": sorting for domain counts (default:"
2582 + DOMAINS_SORT_ORDER_DEFAULT + ")" );
2583 System.out.println( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION + ": domain similarity print option (default:"
2584 + DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT + ")" );
2585 System.out.println( surfacing.CUTOFF_SCORE_FILE_OPTION + ": cutoff score file" );
2586 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION
2587 + ": sort by species count first" );
2588 System.out.println( surfacing.OUTPUT_DIR_OPTION + ": output directory" );
2589 System.out.println( surfacing.PFAM_TO_GO_FILE_USE_OPTION + ": Pfam to GO mapping file" );
2590 System.out.println( surfacing.GO_OBO_FILE_USE_OPTION + ": GO terms file (OBO format)" );
2591 System.out.println( surfacing.GO_NAMESPACE_LIMIT_OPTION + ": limit GO term to one GO namespace" );
2592 System.out.println( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
2593 + "[=<suffix for pairwise comparison output files>]: to perform pairwise comparison based analyses" );
2594 System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION
2595 + ": species tree, to perform (Dollo, Fitch) parismony analyses" );
2597 .println( JACKNIFE_OPTION
2598 + ": perform jacknife resampling for domain and binary domain combination based distance matrices [default resamplings: "
2599 + JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT + "]" );
2600 System.out.println( JACKNIFE_RATIO_OPTION + ": ratio for jacknife resampling [default: "
2601 + JACKNIFE_RATIO_DEFAULT + "]" );
2602 System.out.println( JACKNIFE_RANDOM_SEED_OPTION
2603 + ": seed for random number generator for jacknife resampling [default: "
2604 + JACKNIFE_RANDOM_SEED_DEFAULT + "]" );
2605 // System.out.println( surfacing.INFER_SPECIES_TREES_OPTION
2606 // + ": to infer NJ species trees based on shared domains/binary domain combinations" );
2608 .println( surfacing.INPUT_SPECIES_TREE_OPTION
2609 + "=<treefiles in phyloXML format, separated by #>: to infer domain/binary domain combination gains/losses on given species trees" );
2610 System.out.println( surfacing.FILTER_POSITIVE_OPTION
2611 + "=<file>: to filter out proteins not containing at least one domain listed in <file>" );
2612 System.out.println( surfacing.FILTER_NEGATIVE_OPTION
2613 + "=<file>: to filter out proteins containing at least one domain listed in <file>" );
2614 System.out.println( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION
2615 + "=<file>: to filter out (ignore) domains listed in <file>" );
2616 System.out.println( surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>: to read input files from <file>" );
2618 .println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION
2619 + "=<seed>: seed for random number generator for Fitch Parsimony analysis (type: long, default: no randomization - given a choice, prefer absence" );
2620 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS
2621 + ": to consider directedness in binary combinations: e.g. A-B != B-A" );
2622 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY
2623 + ": to consider directedness and adjacency in binary combinations" );
2625 .println( surfacing.SEQ_EXTRACT_OPTION
2626 + "=<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')" );
2627 System.out.println( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE
2628 + "=<file>: to perfom parsimony analysis on secondary features" );
2629 System.out.println( surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>: to presence/absence genome analysis" );
2630 System.out.println( surfacing.DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS
2631 + ": to output binary domain combinations for (downstream) graph analysis" );
2632 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS + ": to output all proteins per domain" );
2633 System.out.println();
2634 System.out.println();
2635 System.out.println( "Example: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2636 + " org.forester.application.surfacing -detail=punctilious -o=TEST.html -pwc=TEST"
2637 + " -cos=Pfam_ls_22_TC2 -p2g=pfam2go -obo=gene_ontology_edit.obo "
2638 + "-dc_sort=dom -ignore_with_self -no_singles -e=0.001 -mo=1 -no_eo "
2639 + "-ds_output=detailed_html -scoring=domains -sort=alpha -" + JACKNIFE_OPTION
2640 + "=50 human mouse brafl strpu" );
2641 System.out.println();
2644 private static void processFilter( final File filter_file, final SortedSet<DomainId> filter ) {
2645 SortedSet<String> filter_str = null;
2647 filter_str = ForesterUtil.file2set( filter_file );
2649 catch ( final IOException e ) {
2650 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2652 if ( filter_str != null ) {
2653 for( final String string : filter_str ) {
2654 filter.add( new DomainId( string ) );
2658 System.out.println( "Filter:" );
2659 for( final DomainId domainId : filter ) {
2660 System.out.println( domainId.getId() );
2665 private static String[][] processInputFileNames( final String[] names ) {
2666 final String[][] input_file_properties = new String[ names.length ][];
2667 for( int i = 0; i < names.length; ++i ) {
2668 if ( names[ i ].indexOf( SEPARATOR_FOR_INPUT_VALUES ) < 0 ) {
2669 input_file_properties[ i ] = new String[ 2 ];
2670 input_file_properties[ i ][ 0 ] = names[ i ];
2671 input_file_properties[ i ][ 1 ] = names[ i ];
2674 input_file_properties[ i ] = names[ i ].split( surfacing.SEPARATOR_FOR_INPUT_VALUES + "" );
2675 if ( input_file_properties[ i ].length != 3 ) {
2677 .fatalError( surfacing.PRG_NAME,
2678 "properties for the input files (hmmpfam output) are expected "
2679 + "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 \""
2680 + names[ i ] + "\"" );
2683 final String error = ForesterUtil.isReadableFile( new File( input_file_properties[ i ][ 0 ] ) );
2684 if ( !ForesterUtil.isEmpty( error ) ) {
2685 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
2688 return input_file_properties;
2691 private static void processPlusMinusAnalysisOption( final CommandLineArguments cla,
2692 final List<String> high_copy_base,
2693 final List<String> high_copy_target,
2694 final List<String> low_copy,
2695 final List<Object> numbers ) {
2696 if ( cla.isOptionSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2697 if ( !cla.isOptionValueSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2698 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for 'plus-minus' file: -"
2699 + surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>" );
2701 final File plus_minus_file = new File( cla.getOptionValue( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) );
2702 final String msg = ForesterUtil.isReadableFile( plus_minus_file );
2703 if ( !ForesterUtil.isEmpty( msg ) ) {
2704 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + plus_minus_file + "\": " + msg );
2706 processPlusMinusFile( plus_minus_file, high_copy_base, high_copy_target, low_copy, numbers );
2710 // First numbers is minimal difference, second is factor.
2711 private static void processPlusMinusFile( final File plus_minus_file,
2712 final List<String> high_copy_base,
2713 final List<String> high_copy_target,
2714 final List<String> low_copy,
2715 final List<Object> numbers ) {
2716 Set<String> species_set = null;
2717 int min_diff = PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT;
2718 double factor = PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT;
2720 species_set = ForesterUtil.file2set( plus_minus_file );
2722 catch ( final IOException e ) {
2723 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2725 if ( species_set != null ) {
2726 for( final String species : species_set ) {
2727 final String species_trimmed = species.substring( 1 );
2728 if ( species.startsWith( "+" ) ) {
2729 if ( low_copy.contains( species_trimmed ) ) {
2730 ForesterUtil.fatalError( surfacing.PRG_NAME,
2731 "species/genome names can not appear with both '+' and '-' suffix, as appears the case for: \""
2732 + species_trimmed + "\"" );
2734 high_copy_base.add( species_trimmed );
2736 else if ( species.startsWith( "*" ) ) {
2737 if ( low_copy.contains( species_trimmed ) ) {
2738 ForesterUtil.fatalError( surfacing.PRG_NAME,
2739 "species/genome names can not appear with both '*' and '-' suffix, as appears the case for: \""
2740 + species_trimmed + "\"" );
2742 high_copy_target.add( species_trimmed );
2744 else if ( species.startsWith( "-" ) ) {
2745 if ( high_copy_base.contains( species_trimmed ) || high_copy_target.contains( species_trimmed ) ) {
2746 ForesterUtil.fatalError( surfacing.PRG_NAME,
2747 "species/genome names can not appear with both '+' or '*' and '-' suffix, as appears the case for: \""
2748 + species_trimmed + "\"" );
2750 low_copy.add( species_trimmed );
2752 else if ( species.startsWith( "$D" ) ) {
2754 min_diff = Integer.parseInt( species.substring( 3 ) );
2756 catch ( final NumberFormatException e ) {
2757 ForesterUtil.fatalError( surfacing.PRG_NAME,
2758 "could not parse integer value for minimal difference from: \""
2759 + species.substring( 3 ) + "\"" );
2762 else if ( species.startsWith( "$F" ) ) {
2764 factor = Double.parseDouble( species.substring( 3 ) );
2766 catch ( final NumberFormatException e ) {
2767 ForesterUtil.fatalError( surfacing.PRG_NAME, "could not parse double value for factor from: \""
2768 + species.substring( 3 ) + "\"" );
2771 else if ( species.startsWith( "#" ) ) {
2776 .fatalError( surfacing.PRG_NAME,
2777 "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: \""
2780 numbers.add( new Integer( min_diff + "" ) );
2781 numbers.add( new Double( factor + "" ) );
2785 ForesterUtil.fatalError( surfacing.PRG_NAME, "'plus minus' file [" + plus_minus_file + "] appears empty" );
2789 private static void writePresentToNexus( final File output_file,
2790 final File positive_filter_file,
2791 final SortedSet<DomainId> filter,
2792 final List<GenomeWideCombinableDomains> gwcd_list ) {
2795 .writeMatrixToFile( DomainParsimonyCalculator
2796 .createMatrixOfDomainPresenceOrAbsence( gwcd_list, positive_filter_file == null ? null
2797 : filter ), output_file + DOMAINS_PRESENT_NEXUS, Format.NEXUS_BINARY );
2798 SurfacingUtil.writeMatrixToFile( DomainParsimonyCalculator
2799 .createMatrixOfBinaryDomainCombinationPresenceOrAbsence( gwcd_list ), output_file
2800 + BDC_PRESENT_NEXUS, Format.NEXUS_BINARY );
2802 catch ( final Exception e ) {
2803 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2807 private static void writeProteinListsForAllSpecies( final File output_dir,
2808 final SortedMap<Species, List<Protein>> protein_lists_per_species,
2809 final List<GenomeWideCombinableDomains> gwcd_list ) {
2810 final SortedSet<DomainId> all_domains = new TreeSet<DomainId>();
2811 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
2812 all_domains.addAll( gwcd.getAllDomainIds() );
2814 for( final DomainId domain : all_domains ) {
2815 final File out = new File( output_dir + ForesterUtil.FILE_SEPARATOR + domain + SEQ_EXTRACT_SUFFIX );
2816 SurfacingUtil.checkForOutputFileWriteability( out );
2818 final Writer proteins_file_writer = new BufferedWriter( new FileWriter( out ) );
2819 SurfacingUtil.extractProteinNames( protein_lists_per_species,
2821 proteins_file_writer,
2823 LIMIT_SPEC_FOR_PROT_EX );
2824 proteins_file_writer.close();
2826 catch ( final IOException e ) {
2827 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2829 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote proteins list to \"" + out + "\"" );