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";
290 private static void checkWriteabilityForPairwiseComparisons( final PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option,
291 final String[][] input_file_properties,
292 final String automated_pairwise_comparison_suffix,
293 final File outdir ) {
294 for( int i = 0; i < input_file_properties.length; ++i ) {
295 for( int j = 0; j < i; ++j ) {
296 final String species_i = input_file_properties[ i ][ 1 ];
297 final String species_j = input_file_properties[ j ][ 1 ];
298 String pairwise_similarities_output_file_str = PAIRWISE_DOMAIN_COMPARISONS_PREFIX + species_i + "_"
299 + species_j + automated_pairwise_comparison_suffix;
300 switch ( domain_similarity_print_option ) {
302 if ( !pairwise_similarities_output_file_str.endsWith( ".html" ) ) {
303 pairwise_similarities_output_file_str += ".html";
307 final String error = ForesterUtil
308 .isWritableFile( new File( outdir == null ? pairwise_similarities_output_file_str : outdir
309 + ForesterUtil.FILE_SEPARATOR + pairwise_similarities_output_file_str ) );
310 if ( !ForesterUtil.isEmpty( error ) ) {
311 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
317 private static StringBuilder createParametersAsString( final boolean ignore_dufs,
318 final double e_value_max,
319 final int max_allowed_overlap,
320 final boolean no_engulfing_overlaps,
321 final File cutoff_scores_file,
322 final BinaryDomainCombination.DomainCombinationType dc_type ) {
323 final StringBuilder parameters_sb = new StringBuilder();
324 parameters_sb.append( "E-value: " + e_value_max );
325 if ( cutoff_scores_file != null ) {
326 parameters_sb.append( ", Cutoff-scores-file: " + cutoff_scores_file );
329 parameters_sb.append( ", Cutoff-scores-file: not-set" );
331 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
332 parameters_sb.append( ", Max-overlap: " + max_allowed_overlap );
335 parameters_sb.append( ", Max-overlap: not-set" );
337 if ( no_engulfing_overlaps ) {
338 parameters_sb.append( ", Engulfing-overlaps: not-allowed" );
341 parameters_sb.append( ", Engulfing-overlaps: allowed" );
344 parameters_sb.append( ", Ignore-dufs: true" );
347 parameters_sb.append( ", Ignore-dufs: false" );
349 parameters_sb.append( ", DC type (if applicable): " + dc_type );
350 return parameters_sb;
354 * Warning: This side-effects 'all_bin_domain_combinations_encountered'!
358 * @param all_bin_domain_combinations_changed
359 * @param sum_of_all_domains_encountered
360 * @param all_bin_domain_combinations_encountered
361 * @param is_gains_analysis
362 * @param protein_length_stats_by_dc
363 * @throws IOException
365 private static void executeFitchGainsAnalysis( final File output_file,
366 final List<BinaryDomainCombination> all_bin_domain_combinations_changed,
367 final int sum_of_all_domains_encountered,
368 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered,
369 final boolean is_gains_analysis ) throws IOException {
370 SurfacingUtil.checkForOutputFileWriteability( output_file );
371 final Writer out = ForesterUtil.createBufferedWriter( output_file );
372 final SortedMap<Object, Integer> bdc_to_counts = ForesterUtil
373 .listToSortedCountsMap( all_bin_domain_combinations_changed );
374 final SortedSet<DomainId> all_domains_in_combination_changed_more_than_once = new TreeSet<DomainId>();
375 final SortedSet<DomainId> all_domains_in_combination_changed_only_once = new TreeSet<DomainId>();
378 for( final Object bdc_object : bdc_to_counts.keySet() ) {
379 final BinaryDomainCombination bdc = ( BinaryDomainCombination ) bdc_object;
380 final int count = bdc_to_counts.get( bdc_object );
382 ForesterUtil.unexpectedFatalError( PRG_NAME, "count < 1 " );
384 out.write( bdc + "\t" + count + ForesterUtil.LINE_SEPARATOR );
386 all_domains_in_combination_changed_more_than_once.add( bdc.getId0() );
387 all_domains_in_combination_changed_more_than_once.add( bdc.getId1() );
390 else if ( count == 1 ) {
391 all_domains_in_combination_changed_only_once.add( bdc.getId0() );
392 all_domains_in_combination_changed_only_once.add( bdc.getId1() );
396 final int all = all_bin_domain_combinations_encountered.size();
398 if ( !is_gains_analysis ) {
399 all_bin_domain_combinations_encountered.removeAll( all_bin_domain_combinations_changed );
400 never_lost = all_bin_domain_combinations_encountered.size();
401 for( final BinaryDomainCombination bdc : all_bin_domain_combinations_encountered ) {
402 out.write( bdc + "\t" + "0" + ForesterUtil.LINE_SEPARATOR );
405 if ( is_gains_analysis ) {
406 out.write( "Sum of all distinct domain combinations appearing once : " + one
407 + ForesterUtil.LINE_SEPARATOR );
408 out.write( "Sum of all distinct domain combinations appearing more than once : " + above_one
409 + ForesterUtil.LINE_SEPARATOR );
410 out.write( "Sum of all distinct domains in combinations apppearing only once : "
411 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
412 out.write( "Sum of all distinct domains in combinations apppearing more than once: "
413 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
416 out.write( "Sum of all distinct domain combinations never lost : " + never_lost
417 + ForesterUtil.LINE_SEPARATOR );
418 out.write( "Sum of all distinct domain combinations lost once : " + one
419 + ForesterUtil.LINE_SEPARATOR );
420 out.write( "Sum of all distinct domain combinations lost more than once : " + above_one
421 + ForesterUtil.LINE_SEPARATOR );
422 out.write( "Sum of all distinct domains in combinations lost only once : "
423 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
424 out.write( "Sum of all distinct domains in combinations lost more than once: "
425 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
427 out.write( "All binary combinations : " + all
428 + ForesterUtil.LINE_SEPARATOR );
429 out.write( "All domains : "
430 + sum_of_all_domains_encountered );
432 ForesterUtil.programMessage( surfacing.PRG_NAME,
433 "Wrote fitch domain combination dynamics counts analysis to \"" + output_file
437 private static void executePlusMinusAnalysis( final File output_file,
438 final List<String> plus_minus_analysis_high_copy_base,
439 final List<String> plus_minus_analysis_high_copy_target,
440 final List<String> plus_minus_analysis_low_copy,
441 final List<GenomeWideCombinableDomains> gwcd_list,
442 final SortedMap<Species, List<Protein>> protein_lists_per_species,
443 final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
444 final Map<GoId, GoTerm> go_id_to_term_map,
445 final List<Object> plus_minus_analysis_numbers ) {
446 final Set<String> all_spec = new HashSet<String>();
447 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
448 all_spec.add( gwcd.getSpecies().getSpeciesId() );
450 final File html_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX_HTML );
451 final File plain_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX );
452 final File html_out_dc = new File( output_file + PLUS_MINUS_DC_SUFFIX_HTML );
453 final File all_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX );
454 final File passing_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX );
455 final File proteins_file_base = new File( output_file + "" );
456 final int min_diff = ( ( Integer ) plus_minus_analysis_numbers.get( 0 ) ).intValue();
457 final double factor = ( ( Double ) plus_minus_analysis_numbers.get( 1 ) ).doubleValue();
459 DomainCountsDifferenceUtil.calculateCopyNumberDifferences( gwcd_list,
460 protein_lists_per_species,
461 plus_minus_analysis_high_copy_base,
462 plus_minus_analysis_high_copy_target,
463 plus_minus_analysis_low_copy,
469 domain_id_to_go_ids_map,
471 all_domains_go_ids_out_dom,
472 passing_domains_go_ids_out_dom,
473 proteins_file_base );
475 catch ( final IOException e ) {
476 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
478 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
479 + html_out_dom + "\"" );
480 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
481 + plain_out_dom + "\"" );
482 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \"" + html_out_dc
484 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based passing GO ids to \""
485 + passing_domains_go_ids_out_dom + "\"" );
486 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based all GO ids to \""
487 + all_domains_go_ids_out_dom + "\"" );
490 private static Phylogeny[] getIntrees( final File[] intree_files,
491 final int number_of_genomes,
492 final String[][] input_file_properties ) {
493 final Phylogeny[] intrees = new Phylogeny[ intree_files.length ];
495 for( final File intree_file : intree_files ) {
496 Phylogeny intree = null;
497 final String error = ForesterUtil.isReadableFile( intree_file );
498 if ( !ForesterUtil.isEmpty( error ) ) {
499 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read input tree file [" + intree_file + "]: "
503 final Phylogeny[] p_array = ParserBasedPhylogenyFactory.getInstance()
504 .create( intree_file, ParserUtils.createParserDependingOnFileType( intree_file, true ) );
505 if ( p_array.length < 1 ) {
506 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
507 + "] does not contain any phylogeny in phyloXML format" );
509 else if ( p_array.length > 1 ) {
510 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
511 + "] contains more than one phylogeny in phyloXML format" );
513 intree = p_array[ 0 ];
515 catch ( final Exception e ) {
516 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read input tree from file [" + intree_file
519 if ( ( intree == null ) || intree.isEmpty() ) {
520 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" );
522 if ( !intree.isRooted() ) {
523 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is not rooted" );
525 if ( intree.getNumberOfExternalNodes() < number_of_genomes ) {
526 ForesterUtil.fatalError( surfacing.PRG_NAME,
527 "number of external nodes [" + intree.getNumberOfExternalNodes()
528 + "] of input tree [" + intree_file
529 + "] is smaller than the number of genomes the be analyzed ["
530 + number_of_genomes + "]" );
532 final StringBuilder parent_names = new StringBuilder();
533 final int nodes_lacking_name = SurfacingUtil.getNumberOfNodesLackingName( intree, parent_names );
534 if ( nodes_lacking_name > 0 ) {
535 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] has "
536 + nodes_lacking_name + " node(s) lacking a name [parent names:" + parent_names + "]" );
538 preparePhylogenyForParsimonyAnalyses( intree, input_file_properties );
539 if ( !intree.isCompletelyBinary() ) {
540 ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "input tree [" + intree_file
541 + "] is not completely binary" );
543 intrees[ i++ ] = intree;
548 private static List<Phylogeny> inferSpeciesTrees( final File outfile, final List<DistanceMatrix> distances_list ) {
549 final NeighborJoining nj = NeighborJoining.createInstance();
550 final List<Phylogeny> phylogenies = nj.execute( distances_list );
551 final PhylogenyWriter w = new PhylogenyWriter();
553 w.toNewHampshire( phylogenies, true, true, outfile, ";" );
555 catch ( final IOException e ) {
556 ForesterUtil.fatalError( PRG_NAME, "failed to write to outfile [" + outfile + "]: " + e.getMessage() );
561 private static void log( final String msg, final Writer w ) {
564 w.write( ForesterUtil.LINE_SEPARATOR );
566 catch ( final IOException e ) {
567 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
571 public static void main( final String args[] ) {
572 final long start_time = new Date().getTime();
573 // final StringBuffer log = new StringBuffer();
574 final StringBuilder html_desc = new StringBuilder();
575 ForesterUtil.printProgramInformation( surfacing.PRG_NAME,
576 surfacing.PRG_VERSION,
580 final String nl = ForesterUtil.LINE_SEPARATOR;
581 html_desc.append( "<table>" + nl );
582 html_desc.append( "<tr><td>Produced by:</td><td>" + surfacing.PRG_NAME + "</td></tr>" + nl );
583 html_desc.append( "<tr><td>Version:</td><td>" + surfacing.PRG_VERSION + "</td></tr>" + nl );
584 html_desc.append( "<tr><td>Release Date:</td><td>" + surfacing.PRG_DATE + "</td></tr>" + nl );
585 html_desc.append( "<tr><td>Contact:</td><td>" + surfacing.E_MAIL + "</td></tr>" + nl );
586 html_desc.append( "<tr><td>WWW:</td><td>" + surfacing.WWW + "</td></tr>" + nl );
587 CommandLineArguments cla = null;
589 cla = new CommandLineArguments( args );
591 catch ( final Exception e ) {
592 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
594 if ( cla.isOptionSet( surfacing.HELP_OPTION_1 ) || cla.isOptionSet( surfacing.HELP_OPTION_2 ) ) {
595 surfacing.printHelp();
598 if ( ( args.length < 1 ) ) {
599 surfacing.printHelp();
602 final List<String> allowed_options = new ArrayList<String>();
603 allowed_options.add( surfacing.NOT_IGNORE_DUFS_OPTION );
604 allowed_options.add( surfacing.MAX_E_VALUE_OPTION );
605 allowed_options.add( surfacing.DETAILEDNESS_OPTION );
606 allowed_options.add( surfacing.OUTPUT_FILE_OPTION );
607 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_OPTION );
608 allowed_options.add( surfacing.SPECIES_MATRIX_OPTION );
609 allowed_options.add( surfacing.SCORING_OPTION );
610 allowed_options.add( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
611 allowed_options.add( surfacing.NO_ENGULFING_OVERLAP_OPTION );
612 allowed_options.add( surfacing.DOMAIN_COUNT_SORT_OPTION );
613 allowed_options.add( surfacing.CUTOFF_SCORE_FILE_OPTION );
614 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION );
615 allowed_options.add( surfacing.OUTPUT_DIR_OPTION );
616 allowed_options.add( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION );
617 allowed_options.add( surfacing.PFAM_TO_GO_FILE_USE_OPTION );
618 allowed_options.add( surfacing.GO_OBO_FILE_USE_OPTION );
619 allowed_options.add( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION );
620 allowed_options.add( surfacing.GO_NAMESPACE_LIMIT_OPTION );
621 allowed_options.add( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
622 allowed_options.add( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION );
623 allowed_options.add( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS );
624 allowed_options.add( JACKNIFE_OPTION );
625 allowed_options.add( JACKNIFE_RANDOM_SEED_OPTION );
626 allowed_options.add( JACKNIFE_RATIO_OPTION );
627 allowed_options.add( INPUT_SPECIES_TREE_OPTION );
628 //allowed_options.add( INFER_SPECIES_TREES_OPTION );
629 allowed_options.add( FILTER_POSITIVE_OPTION );
630 allowed_options.add( FILTER_NEGATIVE_OPTION );
631 allowed_options.add( INPUT_FILES_FROM_FILE_OPTION );
632 allowed_options.add( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
633 allowed_options.add( FILTER_NEGATIVE_DOMAINS_OPTION );
634 allowed_options.add( IGNORE_VIRAL_IDS );
635 allowed_options.add( SEQ_EXTRACT_OPTION );
636 allowed_options.add( SECONDARY_FEATURES_PARSIMONY_MAP_FILE );
637 allowed_options.add( PLUS_MINUS_ANALYSIS_OPTION );
638 allowed_options.add( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS );
639 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS );
640 allowed_options.add( CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY );
641 boolean ignore_dufs = surfacing.IGNORE_DUFS_DEFAULT;
642 boolean ignore_combination_with_same = surfacing.IGNORE_COMBINATION_WITH_SAME_DEFAULLT;
643 double e_value_max = surfacing.MAX_E_VALUE_DEFAULT;
644 int max_allowed_overlap = surfacing.MAX_ALLOWED_OVERLAP_DEFAULT;
645 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
646 if ( dissallowed_options.length() > 0 ) {
647 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown option(s): " + dissallowed_options );
649 boolean output_binary_domain_combinationsfor_graph_analysis = false;
650 if ( cla.isOptionSet( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS ) ) {
651 output_binary_domain_combinationsfor_graph_analysis = true;
653 if ( cla.isOptionSet( surfacing.MAX_E_VALUE_OPTION ) ) {
655 e_value_max = cla.getOptionValueAsDouble( surfacing.MAX_E_VALUE_OPTION );
657 catch ( final Exception e ) {
658 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for E-value maximum" );
661 if ( cla.isOptionSet( surfacing.MAX_ALLOWED_OVERLAP_OPTION ) ) {
663 max_allowed_overlap = cla.getOptionValueAsInt( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
665 catch ( final Exception e ) {
666 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for maximal allowed domain overlap" );
669 boolean no_engulfing_overlaps = false;
670 if ( cla.isOptionSet( surfacing.NO_ENGULFING_OVERLAP_OPTION ) ) {
671 no_engulfing_overlaps = true;
673 boolean ignore_virus_like_ids = false;
674 if ( cla.isOptionSet( surfacing.IGNORE_VIRAL_IDS ) ) {
675 ignore_virus_like_ids = true;
677 if ( cla.isOptionSet( surfacing.NOT_IGNORE_DUFS_OPTION ) ) {
680 if ( cla.isOptionSet( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION ) ) {
681 ignore_combination_with_same = true;
683 boolean ignore_domains_without_combs_in_all_spec = IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT;
684 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION ) ) {
685 ignore_domains_without_combs_in_all_spec = true;
687 boolean ignore_species_specific_domains = IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT;
688 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION ) ) {
689 ignore_species_specific_domains = true;
691 File output_file = null;
692 if ( cla.isOptionSet( surfacing.OUTPUT_FILE_OPTION ) ) {
693 if ( !cla.isOptionValueSet( surfacing.OUTPUT_FILE_OPTION ) ) {
694 ForesterUtil.fatalError( surfacing.PRG_NAME,
695 "no value for domain combinations similarities output file: -"
696 + surfacing.OUTPUT_FILE_OPTION + "=<file>" );
698 output_file = new File( cla.getOptionValue( surfacing.OUTPUT_FILE_OPTION ) );
699 SurfacingUtil.checkForOutputFileWriteability( output_file );
701 File cutoff_scores_file = null;
702 Map<String, Double> individual_score_cutoffs = null;
703 if ( cla.isOptionSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
704 if ( !cla.isOptionValueSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
705 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for individual domain score cutoffs file: -"
706 + surfacing.CUTOFF_SCORE_FILE_OPTION + "=<file>" );
708 cutoff_scores_file = new File( cla.getOptionValue( surfacing.CUTOFF_SCORE_FILE_OPTION ) );
709 final String error = ForesterUtil.isReadableFile( cutoff_scores_file );
710 if ( !ForesterUtil.isEmpty( error ) ) {
711 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read individual domain score cutoffs file: "
715 final BasicTable<String> scores_table = BasicTableParser.parse( cutoff_scores_file, " " );
716 individual_score_cutoffs = scores_table.getColumnsAsMapDouble( 0, 1 );
718 catch ( final IOException e ) {
719 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from individual score cutoffs file: " + e );
722 BinaryDomainCombination.DomainCombinationType dc_type = BinaryDomainCombination.DomainCombinationType.BASIC;
723 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS ) ) {
724 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED;
726 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY ) ) {
727 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT;
730 if ( cla.isOptionSet( surfacing.OUTPUT_DIR_OPTION ) ) {
731 if ( !cla.isOptionValueSet( surfacing.OUTPUT_DIR_OPTION ) ) {
732 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for output directory: -"
733 + surfacing.OUTPUT_DIR_OPTION + "=<dir>" );
735 out_dir = new File( cla.getOptionValue( surfacing.OUTPUT_DIR_OPTION ) );
736 if ( out_dir.exists() && ( out_dir.listFiles().length > 0 ) ) {
737 ForesterUtil.fatalError( surfacing.PRG_NAME, "\"" + out_dir + "\" aready exists and is not empty" );
739 if ( !out_dir.exists() ) {
740 final boolean success = out_dir.mkdir();
741 if ( !success || !out_dir.exists() ) {
742 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to create \"" + out_dir + "\"" );
745 if ( !out_dir.canWrite() ) {
746 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot write to \"" + out_dir + "\"" );
749 File positive_filter_file = null;
750 File negative_filter_file = null;
751 File negative_domains_filter_file = null;
752 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) && cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
753 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use both negative and positive protein filter" );
755 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION )
756 && ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) || cla
757 .isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) ) {
759 .fatalError( surfacing.PRG_NAME,
760 "attempt to use both negative or positive protein filter together wirh a negative domains filter" );
762 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
763 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
764 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative filter: -"
765 + surfacing.FILTER_NEGATIVE_OPTION + "=<file>" );
767 negative_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_OPTION ) );
768 final String msg = ForesterUtil.isReadableFile( negative_filter_file );
769 if ( !ForesterUtil.isEmpty( msg ) ) {
770 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_filter_file + "\": "
774 else if ( cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
775 if ( !cla.isOptionValueSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
776 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for positive filter: -"
777 + surfacing.FILTER_POSITIVE_OPTION + "=<file>" );
779 positive_filter_file = new File( cla.getOptionValue( surfacing.FILTER_POSITIVE_OPTION ) );
780 final String msg = ForesterUtil.isReadableFile( positive_filter_file );
781 if ( !ForesterUtil.isEmpty( msg ) ) {
782 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + positive_filter_file + "\": "
786 else if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
787 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
788 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative domains filter: -"
789 + surfacing.FILTER_NEGATIVE_DOMAINS_OPTION + "=<file>" );
791 negative_domains_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) );
792 final String msg = ForesterUtil.isReadableFile( negative_domains_filter_file );
793 if ( !ForesterUtil.isEmpty( msg ) ) {
794 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_domains_filter_file
798 final List<String> plus_minus_analysis_high_copy_base_species = new ArrayList<String>();
799 final List<String> plus_minus_analysis_high_copy_target_species = new ArrayList<String>();
800 final List<String> plus_minus_analysis_high_low_copy_species = new ArrayList<String>();
801 final List<Object> plus_minus_analysis_numbers = new ArrayList<Object>();
802 processPlusMinusAnalysisOption( cla,
803 plus_minus_analysis_high_copy_base_species,
804 plus_minus_analysis_high_copy_target_species,
805 plus_minus_analysis_high_low_copy_species,
806 plus_minus_analysis_numbers );
807 File input_files_file = null;
808 String[] input_file_names_from_file = null;
809 if ( cla.isOptionSet( surfacing.INPUT_FILES_FROM_FILE_OPTION ) ) {
810 if ( !cla.isOptionValueSet( surfacing.INPUT_FILES_FROM_FILE_OPTION ) ) {
811 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input files file: -"
812 + surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>" );
814 input_files_file = new File( cla.getOptionValue( surfacing.INPUT_FILES_FROM_FILE_OPTION ) );
815 final String msg = ForesterUtil.isReadableFile( input_files_file );
816 if ( !ForesterUtil.isEmpty( msg ) ) {
817 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + input_files_file + "\": " + msg );
820 input_file_names_from_file = ForesterUtil.file2array( input_files_file );
822 catch ( final IOException e ) {
823 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read from \"" + input_files_file + "\": " + e );
826 if ( ( cla.getNumberOfNames() < 1 )
827 && ( ( input_file_names_from_file == null ) || ( input_file_names_from_file.length < 1 ) ) ) {
828 ForesterUtil.fatalError( surfacing.PRG_NAME,
829 "No hmmpfam output file indicated is input: use comand line directly or "
830 + surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>" );
832 DomainSimilarity.DomainSimilarityScoring scoring = SCORING_DEFAULT;
833 if ( cla.isOptionSet( surfacing.SCORING_OPTION ) ) {
834 if ( !cla.isOptionValueSet( surfacing.SCORING_OPTION ) ) {
835 ForesterUtil.fatalError( surfacing.PRG_NAME,
836 "no value for scoring method for domain combinations similarity calculation: -"
837 + surfacing.SCORING_OPTION + "=<"
838 + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
839 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|"
840 + surfacing.SCORING_COMBINATION_BASED + ">\"" );
842 final String scoring_str = cla.getOptionValue( surfacing.SCORING_OPTION );
843 if ( scoring_str.equals( surfacing.SCORING_DOMAIN_COUNT_BASED ) ) {
844 scoring = DomainSimilarity.DomainSimilarityScoring.DOMAINS;
846 else if ( scoring_str.equals( surfacing.SCORING_COMBINATION_BASED ) ) {
847 scoring = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
849 else if ( scoring_str.equals( surfacing.SCORING_PROTEIN_COUNT_BASED ) ) {
850 scoring = DomainSimilarity.DomainSimilarityScoring.PROTEINS;
853 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + scoring_str
854 + "\" for scoring method for domain combinations similarity calculation: \"-"
855 + surfacing.SCORING_OPTION + "=<" + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
856 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|" + surfacing.SCORING_COMBINATION_BASED + ">\"" );
859 boolean sort_by_species_count_first = false;
860 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION ) ) {
861 sort_by_species_count_first = true;
863 boolean species_matrix = false;
864 if ( cla.isOptionSet( surfacing.SPECIES_MATRIX_OPTION ) ) {
865 species_matrix = true;
867 boolean output_protein_lists_for_all_domains = false;
868 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS ) ) {
869 output_protein_lists_for_all_domains = true;
871 Detailedness detailedness = DETAILEDNESS_DEFAULT;
872 if ( cla.isOptionSet( surfacing.DETAILEDNESS_OPTION ) ) {
873 if ( !cla.isOptionValueSet( surfacing.DETAILEDNESS_OPTION ) ) {
874 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for -" + surfacing.DETAILEDNESS_OPTION + "=<"
875 + surfacing.DETAILEDNESS_BASIC + "|" + surfacing.DETAILEDNESS_LIST_IDS + "|"
876 + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
878 final String detness = cla.getOptionValue( surfacing.DETAILEDNESS_OPTION ).toLowerCase();
879 if ( detness.equals( surfacing.DETAILEDNESS_BASIC ) ) {
880 detailedness = DomainSimilarityCalculator.Detailedness.BASIC;
882 else if ( detness.equals( surfacing.DETAILEDNESS_LIST_IDS ) ) {
883 detailedness = DomainSimilarityCalculator.Detailedness.LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES;
885 else if ( detness.equals( surfacing.DETAILEDNESS_PUNCTILIOUS ) ) {
886 detailedness = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
889 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + detness + "\" for detailedness: \"-"
890 + surfacing.DETAILEDNESS_OPTION + "=<" + surfacing.DETAILEDNESS_BASIC + "|"
891 + surfacing.DETAILEDNESS_LIST_IDS + "|" + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
894 String automated_pairwise_comparison_suffix = null;
895 boolean perform_pwc = false;
896 boolean write_pwc_files = false;
897 if ( cla.isOptionSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
899 if ( !cla.isOptionValueSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
900 write_pwc_files = false;
903 write_pwc_files = true;
904 automated_pairwise_comparison_suffix = "_"
905 + cla.getOptionValue( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
908 String query_domain_ids = null;
909 if ( cla.isOptionSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
910 if ( !cla.isOptionValueSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
912 .fatalError( surfacing.PRG_NAME,
913 "no domain ids given for sequences with given domains to be extracted : -"
914 + surfacing.SEQ_EXTRACT_OPTION
915 + "=<ordered domain sequences, domain ids separated by '~', sequences separated by '#'>" );
917 query_domain_ids = cla.getOptionValue( surfacing.SEQ_EXTRACT_OPTION );
919 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field = DOMAIN_SORT_FILD_DEFAULT;
920 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field_for_automated_pwc = DOMAIN_SORT_FILD_DEFAULT;
921 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
922 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
923 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for domain combinations similarities sorting: -"
924 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
925 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
926 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
927 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
928 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|"
929 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
932 final String sort_str = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ).toLowerCase();
933 if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ALPHA ) ) {
934 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
935 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
937 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MAX ) ) {
938 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX;
939 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
941 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MIN ) ) {
942 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MIN;
943 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
945 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MEAN ) ) {
946 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MEAN;
947 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MEAN;
949 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT ) ) {
950 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SPECIES_COUNT;
951 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
953 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SD ) ) {
954 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SD;
955 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
957 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_DIFF ) ) {
958 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
959 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
961 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF ) ) {
962 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
963 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
965 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF ) ) {
966 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
967 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
970 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort_str
971 + "\" for domain combinations similarities sorting: \"-"
972 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
973 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
974 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
975 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
976 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|" + "|"
977 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
981 PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option = DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT;
982 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
983 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
984 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for print option: -"
985 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
986 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
987 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
989 final String sort = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ).toLowerCase();
990 if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML ) ) {
991 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.HTML;
993 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML ) ) {
994 // domain_similarity_print_option =
995 // DomainSimilarity.PRINT_OPTION.SIMPLE_HTML;
996 ForesterUtil.fatalError( surfacing.PRG_NAME, "simple HTML output not implemented yet :(" );
998 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED ) ) {
999 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.SIMPLE_TAB_DELIMITED;
1002 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort + "\" for print option: -"
1003 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
1004 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
1005 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
1008 GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order = DOMAINS_SORT_ORDER_DEFAULT;
1009 if ( cla.isOptionSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
1010 if ( !cla.isOptionValueSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
1011 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for sorting of domain counts: -"
1012 + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<" + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|"
1013 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1014 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1015 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1017 final String sort = cla.getOptionValue( surfacing.DOMAIN_COUNT_SORT_OPTION ).toLowerCase();
1018 if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_ALPHA ) ) {
1019 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
1021 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT ) ) {
1022 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_COUNT;
1024 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT ) ) {
1025 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_PROTEINS_COUNT;
1027 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT ) ) {
1028 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.COMBINATIONS_COUNT;
1031 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort
1032 + "\" for sorting of domain counts: \"-" + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<"
1033 + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|" + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1034 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1035 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1038 String[][] input_file_properties = null;
1039 if ( input_file_names_from_file != null ) {
1040 input_file_properties = surfacing.processInputFileNames( input_file_names_from_file );
1043 input_file_properties = surfacing.processInputFileNames( cla.getNames() );
1045 final int number_of_genomes = input_file_properties.length;
1046 if ( number_of_genomes < 2 ) {
1047 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot analyze less than two files" );
1049 if ( ( number_of_genomes < 3 ) && perform_pwc ) {
1050 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use : -"
1051 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1052 + "=<suffix> to turn on pairwise analyses with less than three input files" );
1054 checkWriteabilityForPairwiseComparisons( domain_similarity_print_option,
1055 input_file_properties,
1056 automated_pairwise_comparison_suffix,
1058 for( int i = 0; i < number_of_genomes; i++ ) {
1059 File dcc_outfile = new File( input_file_properties[ i ][ 0 ]
1060 + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
1061 if ( out_dir != null ) {
1062 dcc_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + dcc_outfile );
1064 SurfacingUtil.checkForOutputFileWriteability( dcc_outfile );
1066 File pfam_to_go_file = null;
1067 Map<DomainId, List<GoId>> domain_id_to_go_ids_map = null;
1068 int domain_id_to_go_ids_count = 0;
1069 if ( cla.isOptionSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1070 if ( !cla.isOptionValueSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1071 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for Pfam to GO mapping file: -"
1072 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>" );
1074 pfam_to_go_file = new File( cla.getOptionValue( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) );
1075 final String error = ForesterUtil.isReadableFile( pfam_to_go_file );
1076 if ( !ForesterUtil.isEmpty( error ) ) {
1077 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read Pfam to GO mapping file: " + error );
1080 final PfamToGoParser parser = new PfamToGoParser( pfam_to_go_file );
1081 final List<PfamToGoMapping> pfam_to_go_mappings = parser.parse();
1082 domain_id_to_go_ids_map = SurfacingUtil.createDomainIdToGoIdMap( pfam_to_go_mappings );
1083 if ( parser.getMappingCount() < domain_id_to_go_ids_map.size() ) {
1084 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME,
1085 "parser.getMappingCount() < domain_id_to_go_ids_map.size()" );
1087 domain_id_to_go_ids_count = parser.getMappingCount();
1089 catch ( final IOException e ) {
1090 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from Pfam to GO mapping file: " + e );
1093 File go_obo_file = null;
1094 List<GoTerm> go_terms = null;
1095 if ( cla.isOptionSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1096 if ( !cla.isOptionValueSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1097 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO OBO file: -"
1098 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>" );
1100 if ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) {
1101 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO OBO file (-"
1102 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>) without Pfam to GO mapping file ("
1103 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1105 go_obo_file = new File( cla.getOptionValue( surfacing.GO_OBO_FILE_USE_OPTION ) );
1106 final String error = ForesterUtil.isReadableFile( go_obo_file );
1107 if ( !ForesterUtil.isEmpty( error ) ) {
1108 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read GO OBO file: " + error );
1111 final OBOparser parser = new OBOparser( go_obo_file, OBOparser.ReturnType.BASIC_GO_TERM );
1112 go_terms = parser.parse();
1113 if ( parser.getGoTermCount() != go_terms.size() ) {
1115 .unexpectedFatalError( surfacing.PRG_NAME, "parser.getGoTermCount() != go_terms.size()" );
1118 catch ( final IOException e ) {
1119 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from GO OBO file: " + e );
1122 Map<GoId, GoTerm> go_id_to_term_map = null;
1123 if ( ( ( domain_id_to_go_ids_map != null ) && ( domain_id_to_go_ids_map.size() > 0 ) )
1124 && ( ( go_terms != null ) && ( go_terms.size() > 0 ) ) ) {
1125 go_id_to_term_map = GoUtils.createGoIdToGoTermMap( go_terms );
1127 GoNameSpace go_namespace_limit = null;
1128 if ( cla.isOptionSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1129 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1130 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO namespace limit (-"
1131 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<namespace>) without Pfam to GO mapping file ("
1132 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>) and GO OBO file (-"
1133 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1135 if ( !cla.isOptionValueSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1136 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO namespace limit: \"-"
1137 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1138 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1139 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1140 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1142 final String go_namespace_limit_str = cla.getOptionValue( surfacing.GO_NAMESPACE_LIMIT_OPTION )
1144 if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION ) ) {
1145 go_namespace_limit = GoNameSpace.createMolecularFunction();
1147 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS ) ) {
1148 go_namespace_limit = GoNameSpace.createBiologicalProcess();
1150 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT ) ) {
1151 go_namespace_limit = GoNameSpace.createCellularComponent();
1154 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + go_namespace_limit_str
1155 + "\" for GO namespace limit: \"-" + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1156 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1157 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1158 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1161 if ( ( domain_similarity_sort_field == DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE )
1162 && ( number_of_genomes > 2 ) ) {
1163 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
1165 boolean jacknifed_distances = false;
1166 int jacknife_resamplings = JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT;
1167 double jacknife_ratio = JACKNIFE_RATIO_DEFAULT;
1168 long random_seed = JACKNIFE_RANDOM_SEED_DEFAULT;
1169 if ( cla.isOptionSet( surfacing.JACKNIFE_OPTION ) ) {
1170 if ( ( number_of_genomes < 3 ) || !perform_pwc ) {
1171 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use jacknife resampling analysis (-"
1172 + surfacing.JACKNIFE_OPTION + "[=<number of resamplings>]) without pairwise analyses ("
1173 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1174 + "=<suffix for pairwise comparison output files>)" );
1176 jacknifed_distances = true;
1177 if ( cla.isOptionHasAValue( surfacing.JACKNIFE_OPTION ) ) {
1179 jacknife_resamplings = cla.getOptionValueAsInt( surfacing.JACKNIFE_OPTION );
1181 catch ( final IOException e ) {
1182 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for number of resamplings" );
1184 if ( jacknife_resamplings < 2 ) {
1185 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use less than 2 resamplings" );
1188 if ( cla.isOptionSet( surfacing.JACKNIFE_RATIO_OPTION )
1189 && cla.isOptionHasAValue( surfacing.JACKNIFE_RATIO_OPTION ) ) {
1191 jacknife_ratio = cla.getOptionValueAsDouble( surfacing.JACKNIFE_RATIO_OPTION );
1193 catch ( final IOException e ) {
1194 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for jacknife ratio" );
1196 if ( ( jacknife_ratio <= 0.0 ) || ( jacknife_ratio >= 1.0 ) ) {
1197 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use illegal value for jacknife ratio: "
1201 if ( cla.isOptionSet( surfacing.JACKNIFE_RANDOM_SEED_OPTION )
1202 && cla.isOptionHasAValue( surfacing.JACKNIFE_RANDOM_SEED_OPTION ) ) {
1204 random_seed = cla.getOptionValueAsLong( surfacing.JACKNIFE_RANDOM_SEED_OPTION );
1206 catch ( final IOException e ) {
1207 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for random generator seed" );
1211 // boolean infer_species_trees = false;
1212 // if ( cla.isOptionSet( surfacing.INFER_SPECIES_TREES_OPTION ) ) {
1213 // if ( ( output_file == null ) || ( number_of_genomes < 3 )
1214 // || ForesterUtil.isEmpty( automated_pairwise_comparison_suffix ) ) {
1215 // ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer species trees (-"
1216 // + surfacing.INFER_SPECIES_TREES_OPTION + " without pairwise analyses ("
1217 // + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1218 // + "=<suffix for pairwise comparison output files>)" );
1220 // infer_species_trees = true;
1222 File[] intree_files = null;
1223 Phylogeny[] intrees = null;
1224 if ( cla.isOptionSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1225 // TODO FIXME if jacknife.... maybe not
1226 if ( number_of_genomes < 3 ) {
1227 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer gains and losses on input species trees (-"
1228 + surfacing.INPUT_SPECIES_TREE_OPTION + " without pairwise analyses ("
1229 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1230 + "=<suffix for pairwise comparison output files>)" );
1232 if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1233 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input tree: -"
1234 + surfacing.INPUT_SPECIES_TREE_OPTION + "=<tree file in phyloXML format>" );
1236 final String intrees_str = cla.getOptionValue( surfacing.INPUT_SPECIES_TREE_OPTION );
1237 if ( intrees_str.indexOf( "#" ) > 0 ) {
1238 final String[] intrees_strs = intrees_str.split( "#" );
1239 intree_files = new File[ intrees_strs.length ];
1241 for( final String s : intrees_strs ) {
1242 intree_files[ i++ ] = new File( s.trim() );
1246 intree_files = new File[ 1 ];
1247 intree_files[ 0 ] = new File( intrees_str );
1249 intrees = getIntrees( intree_files, number_of_genomes, input_file_properties );
1251 long random_number_seed_for_fitch_parsimony = 0l;
1252 boolean radomize_fitch_parsimony = false;
1253 if ( cla.isOptionSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1254 if ( !cla.isOptionValueSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1255 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for random number seed: -"
1256 + surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION + "=<seed>" );
1259 random_number_seed_for_fitch_parsimony = cla
1260 .getOptionValueAsLong( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
1262 catch ( final IOException e ) {
1263 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1265 radomize_fitch_parsimony = true;
1267 SortedSet<DomainId> filter = null;
1268 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1269 || ( negative_domains_filter_file != null ) ) {
1270 filter = new TreeSet<DomainId>();
1271 if ( positive_filter_file != null ) {
1272 processFilter( positive_filter_file, filter );
1274 else if ( negative_filter_file != null ) {
1275 processFilter( negative_filter_file, filter );
1277 else if ( negative_domains_filter_file != null ) {
1278 processFilter( negative_domains_filter_file, filter );
1281 Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps = null;
1282 File[] secondary_features_map_files = null;
1283 final File domain_lengths_analysis_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1284 + DOMAIN_LENGTHS_ANALYSIS_SUFFIX );
1285 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
1286 SurfacingUtil.checkForOutputFileWriteability( domain_lengths_analysis_outfile );
1288 if ( cla.isOptionSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1289 if ( !cla.isOptionValueSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1290 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for secondary features map file: -"
1291 + surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE + "=<file>" );
1293 final String[] secondary_features_map_files_strs = cla
1294 .getOptionValue( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ).split( "#" );
1295 secondary_features_map_files = new File[ secondary_features_map_files_strs.length ];
1296 domain_id_to_secondary_features_maps = new Map[ secondary_features_map_files_strs.length ];
1298 for( final String secondary_features_map_files_str : secondary_features_map_files_strs ) {
1299 secondary_features_map_files[ i ] = new File( secondary_features_map_files_str );
1300 final String error = ForesterUtil.isReadableFile( secondary_features_map_files[ i ] );
1301 if ( !ForesterUtil.isEmpty( error ) ) {
1302 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read secondary features map file: " + error );
1305 domain_id_to_secondary_features_maps[ i ] = SurfacingUtil
1306 .createDomainIdToSecondaryFeaturesMap( secondary_features_map_files[ i ] );
1308 catch ( final IOException e ) {
1309 ForesterUtil.fatalError( surfacing.PRG_NAME,
1310 "cannot read secondary features map file: " + e.getMessage() );
1312 catch ( final Exception e ) {
1313 ForesterUtil.fatalError( surfacing.PRG_NAME, "problem with contents of features map file ["
1314 + secondary_features_map_files[ i ] + "]: " + e.getMessage() );
1319 if ( out_dir == null ) {
1320 ForesterUtil.fatalError( surfacing.PRG_NAME, "no output directory indicated (-"
1321 + surfacing.OUTPUT_DIR_OPTION + "=<dir>)" );
1323 if ( output_file == null ) {
1324 ForesterUtil.fatalError( surfacing.PRG_NAME, "no name for (main) output file indicated (-"
1325 + surfacing.OUTPUT_FILE_OPTION + "=<file>)" );
1327 if ( ( domain_id_to_go_ids_map == null ) || domain_id_to_go_ids_map.isEmpty() ) {
1328 ForesterUtil.fatalError( surfacing.PRG_NAME,
1329 "no (acceptable) Pfam to GO id mapping file provided ('pfam2go file') (-"
1330 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1332 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1333 ForesterUtil.fatalError( surfacing.PRG_NAME,
1334 "no (acceptable) go id to term mapping file provided ('GO OBO file') (-"
1335 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1337 System.out.println( "Output directory : " + out_dir );
1338 if ( input_file_names_from_file != null ) {
1339 System.out.println( "Input files names from : " + input_files_file + " ["
1340 + input_file_names_from_file.length + " input files]" );
1341 html_desc.append( "<tr><td>Input files names from:</td><td>" + input_files_file + " ["
1342 + input_file_names_from_file.length + " input files]</td></tr>" + nl );
1344 if ( positive_filter_file != null ) {
1345 final int filter_size = filter.size();
1346 System.out.println( "Positive protein filter : " + positive_filter_file + " [" + filter_size
1348 html_desc.append( "<tr><td>Positive protein filter:</td><td>" + positive_filter_file + " [" + filter_size
1349 + " domain ids]</td></tr>" + nl );
1351 if ( negative_filter_file != null ) {
1352 final int filter_size = filter.size();
1353 System.out.println( "Negative protein filter : " + negative_filter_file + " [" + filter_size
1355 html_desc.append( "<tr><td>Negative protein filter:</td><td>" + negative_filter_file + " [" + filter_size
1356 + " domain ids]</td></tr>" + nl );
1358 if ( negative_domains_filter_file != null ) {
1359 final int filter_size = filter.size();
1360 System.out.println( "Negative domain filter : " + negative_domains_filter_file + " [" + filter_size
1362 html_desc.append( "<tr><td>Negative domain filter:</td><td>" + negative_domains_filter_file + " ["
1363 + filter_size + " domain ids]</td></tr>" + nl );
1365 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
1367 for( final String s : plus_minus_analysis_high_copy_base_species ) {
1368 plus0 += "+" + s + " ";
1371 for( final String s : plus_minus_analysis_high_copy_target_species ) {
1372 plus1 += "*" + s + " ";
1375 for( final String s : plus_minus_analysis_high_low_copy_species ) {
1376 minus += "-" + s + " ";
1378 System.out.println( "Plus-minus analysis : " + plus1 + "&& " + plus0 + "&& " + minus );
1379 html_desc.append( "<tr><td>Plus-minus analysis:</td><td>" + plus1 + "&& " + plus0 + "&& " + minus
1380 + "</td></tr>" + nl );
1382 if ( cutoff_scores_file != null ) {
1383 System.out.println( "Cutoff scores file : " + cutoff_scores_file );
1384 html_desc.append( "<tr><td>Cutoff scores file:</td><td>" + cutoff_scores_file + "</td></tr>" + nl );
1386 if ( e_value_max >= 0.0 ) {
1387 System.out.println( "E-value maximum (inclusive) : " + e_value_max );
1388 html_desc.append( "<tr><td>E-value maximum (inclusive):</td><td>" + e_value_max + "</td></tr>" + nl );
1390 System.out.println( "Ignore DUFs : " + ignore_dufs );
1391 if ( ignore_virus_like_ids ) {
1392 System.out.println( "Ignore virus like ids : " + ignore_virus_like_ids );
1393 html_desc.append( "<tr><td>Ignore virus, phage, transposition related ids:</td><td>"
1394 + ignore_virus_like_ids + "</td></tr>" + nl );
1396 html_desc.append( "<tr><td>Ignore DUFs:</td><td>" + ignore_dufs + "</td></tr>" + nl );
1397 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1398 System.out.println( "Max allowed domain overlap : " + max_allowed_overlap );
1399 html_desc.append( "<tr><td>Max allowed domain overlap:</td><td>" + max_allowed_overlap + "</td></tr>" + nl );
1401 if ( no_engulfing_overlaps ) {
1402 System.out.println( "Ignore engulfed domains : " + no_engulfing_overlaps );
1403 html_desc.append( "<tr><td>Ignore (lower confidence) engulfed domains:</td><td>" + no_engulfing_overlaps
1404 + "</td></tr>" + nl );
1406 System.out.println( "Ignore singlet domains : " + ignore_domains_without_combs_in_all_spec );
1408 .append( "<tr><td>Ignore singlet domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1409 + ignore_domains_without_combs_in_all_spec + "</td></tr>" + nl );
1410 System.out.println( "Ignore species specific doms: " + ignore_species_specific_domains );
1412 .append( "<tr><td>Ignore species specific domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1413 + ignore_species_specific_domains + "</td></tr>" + nl );
1414 System.out.println( "Ignore combination with self: " + ignore_combination_with_same );
1415 html_desc.append( "<tr><td>Ignore combination with self for domain combination similarity analyses:</td><td>"
1416 + ignore_combination_with_same + "</td></tr>" + nl );
1417 System.out.println( "Consider directedness : "
1418 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) );
1419 html_desc.append( "<tr><td>Consider directedness of binary domain combinations:</td><td>"
1420 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) + "</td></tr>" + nl );
1421 if ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) {
1422 System.out.println( "Consider adjacency : "
1423 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) );
1424 html_desc.append( "<tr><td>Consider djacency of binary domain combinations:</td><td>"
1425 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) + "</td></tr>"
1428 System.out.print( "Domain counts sort order : " );
1429 switch ( dc_sort_order ) {
1430 case ALPHABETICAL_KEY_ID:
1431 System.out.println( "alphabetical" );
1433 case KEY_DOMAIN_COUNT:
1434 System.out.println( "domain count" );
1436 case KEY_DOMAIN_PROTEINS_COUNT:
1437 System.out.println( "domain proteins count" );
1439 case COMBINATIONS_COUNT:
1440 System.out.println( "domain combinations count" );
1443 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for dc sort order" );
1445 if ( domain_id_to_go_ids_map != null ) {
1446 System.out.println( "Pfam to GO mappings from : " + pfam_to_go_file + " [" + domain_id_to_go_ids_count
1448 html_desc.append( "<tr><td>Pfam to GO mappings from:</td><td>" + pfam_to_go_file + " ["
1449 + domain_id_to_go_ids_count + " mappings]" + "</td></tr>" + nl );
1451 if ( go_terms != null ) {
1452 System.out.println( "GO terms from : " + go_obo_file + " [" + go_terms.size() + " terms]" );
1453 html_desc.append( "<tr><td>GO terms from:</td><td>" + go_obo_file + " [" + go_terms.size() + " terms]"
1454 + "</td></tr>" + nl );
1456 if ( go_namespace_limit != null ) {
1457 System.out.println( "Limit GO terms to : " + go_namespace_limit.toString() );
1458 html_desc.append( "<tr><td>Limit GO terms to</td><td>" + go_namespace_limit + "</td></tr>" + nl );
1460 if ( perform_pwc ) {
1461 System.out.println( "Suffix for PWC files : " + automated_pairwise_comparison_suffix );
1462 html_desc.append( "<tr><td>Suffix for PWC files</td><td>" + automated_pairwise_comparison_suffix
1463 + "</td></tr>" + nl );
1465 if ( out_dir != null ) {
1466 System.out.println( "Output directory : " + out_dir );
1468 if ( query_domain_ids != null ) {
1469 System.out.println( "Query domains (ordered) : " + query_domain_ids );
1470 html_desc.append( "<tr><td></td><td>" + query_domain_ids + "</td></tr>" + nl );
1472 System.out.println( "Write similarities to : " + output_file );
1473 System.out.print( " Scoring method : " );
1474 html_desc.append( "<tr><td>Scoring method:</td><td>" );
1475 switch ( scoring ) {
1477 System.out.println( "domain combinations based" );
1478 html_desc.append( "domain combinations based" + "</td></tr>" + nl );
1481 System.out.println( "domain counts based" );
1482 html_desc.append( "domain counts based" + "</td></tr>" + nl );
1485 System.out.println( "domain proteins counts based" );
1486 html_desc.append( "domain proteins counts based" + "</td></tr>" + nl );
1489 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
1491 System.out.print( " Sort by : " );
1492 html_desc.append( "<tr><td>Sort by:</td><td>" );
1493 switch ( domain_similarity_sort_field ) {
1495 System.out.print( "score minimum" );
1496 html_desc.append( "score minimum" );
1499 System.out.print( "score maximum" );
1500 html_desc.append( "score maximum" );
1503 System.out.print( "score mean" );
1504 html_desc.append( "score mean" );
1507 System.out.print( "score standard deviation" );
1508 html_desc.append( "score standard deviation" );
1511 System.out.print( "species number" );
1512 html_desc.append( "species number" );
1515 System.out.print( "alphabetical domain identifier" );
1516 html_desc.append( "alphabetical domain identifier" );
1518 case MAX_DIFFERENCE:
1519 System.out.print( "(maximal) difference" );
1520 html_desc.append( "(maximal) difference" );
1522 case ABS_MAX_COUNTS_DIFFERENCE:
1523 System.out.print( "absolute (maximal) counts difference" );
1524 html_desc.append( "absolute (maximal) counts difference" );
1526 case MAX_COUNTS_DIFFERENCE:
1527 System.out.print( "(maximal) counts difference" );
1528 html_desc.append( "(maximal) counts difference" );
1531 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1533 if ( sort_by_species_count_first ) {
1534 System.out.println( " (sort by species count first)" );
1535 html_desc.append( " (sort by species count first)" );
1538 System.out.println();
1540 html_desc.append( "</td></tr>" + nl );
1541 System.out.print( " Detailedness : " );
1542 switch ( detailedness ) {
1544 System.out.println( "basic" );
1546 case LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES:
1547 System.out.println( "list combining domains for each species" );
1550 System.out.println( "punctilious" );
1553 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for detailedness" );
1555 System.out.print( " Print option : " );
1556 switch ( domain_similarity_print_option ) {
1558 System.out.println( "HTML" );
1560 case SIMPLE_TAB_DELIMITED:
1561 System.out.println( "simple tab delimited" );
1564 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for print option" );
1566 System.out.print( " Species matrix : " + species_matrix );
1567 System.out.println();
1568 final File dc_data_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + DATA_FILE_SUFFIX );
1569 System.out.println( "Domain comb data output : " + dc_data_file );
1570 html_desc.append( "<tr><td>Domain combination data output:</td><td> " + dc_data_file + " </td></tr>" );
1571 System.out.println();
1572 if ( perform_pwc ) {
1573 System.out.println( "Pairwise comparisons: " );
1574 html_desc.append( "<tr><td>Pairwise comparisons:</td><td></td></tr>" );
1575 System.out.print( " Sort by : " );
1576 html_desc.append( "<tr><td>Sort by:</td><td>" );
1577 switch ( domain_similarity_sort_field_for_automated_pwc ) {
1579 System.out.print( "score mean" );
1580 html_desc.append( "score mean" );
1583 System.out.print( "alphabetical domain identifier" );
1584 html_desc.append( "alphabetical domain identifier" );
1586 case MAX_DIFFERENCE:
1587 System.out.print( "difference" );
1588 html_desc.append( "difference" );
1590 case ABS_MAX_COUNTS_DIFFERENCE:
1591 System.out.print( "absolute counts difference" );
1592 html_desc.append( "absolute counts difference" );
1594 case MAX_COUNTS_DIFFERENCE:
1595 System.out.print( "counts difference" );
1596 html_desc.append( "counts difference" );
1600 .unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1602 System.out.println();
1603 html_desc.append( "</td></tr>" + nl );
1604 if ( jacknifed_distances ) {
1605 html_desc.append( "<tr><td>Jacknife:</td><td>" + jacknife_resamplings + " resamplings</td></tr>" + nl );
1606 html_desc.append( "<tr><td>Jacknife ratio:</td><td>" + ForesterUtil.round( jacknife_ratio, 2 )
1607 + "</td></tr>" + nl );
1608 html_desc.append( "<tr><td>Jacknife random number seed:</td><td>" + random_seed + "</td></tr>" + nl );
1609 System.out.println( " Jacknife : " + jacknife_resamplings + " resamplings" );
1610 System.out.println( " Ratio : " + ForesterUtil.round( jacknife_ratio, 2 ) );
1611 System.out.println( " Random number seed : " + random_seed );
1613 // if ( infer_species_trees ) {
1614 // html_desc.append( "<tr><td>Infer species trees:</td><td>true</td></tr>" + nl );
1615 // System.out.println( " Infer species trees : true" );
1617 if ( ( intrees != null ) && ( intrees.length > 0 ) ) {
1618 for( final File intree_file : intree_files ) {
1619 html_desc.append( "<tr><td>Intree for gain/loss parsimony analysis:</td><td>" + intree_file
1620 + "</td></tr>" + nl );
1621 System.out.println( " Intree for gain/loss pars.: " + intree_file );
1624 if ( radomize_fitch_parsimony ) {
1625 html_desc.append( "<tr><td> Random number seed for Fitch parsimony analysis:</td><td>"
1626 + random_number_seed_for_fitch_parsimony + "</td></tr>" + nl );
1627 System.out.println( " Random number seed : " + random_number_seed_for_fitch_parsimony );
1629 if ( ( domain_id_to_secondary_features_maps != null ) && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
1630 for( int i = 0; i < secondary_features_map_files.length; i++ ) {
1631 html_desc.append( "<tr><td>Secondary features map file:</td><td>"
1632 + secondary_features_map_files[ i ] + "</td></tr>" + nl );
1633 System.out.println( "Secondary features map file : " + secondary_features_map_files[ i ]
1634 + " [mappings for " + domain_id_to_secondary_features_maps[ i ].size() + " domain ids]" );
1636 System.out.println();
1637 System.out.println( "Domain ids to secondary features map:" );
1638 for( final DomainId domain_id : domain_id_to_secondary_features_maps[ i ].keySet() ) {
1639 System.out.print( domain_id.getId() );
1640 System.out.print( " => " );
1641 for( final String sec : domain_id_to_secondary_features_maps[ i ].get( domain_id ) ) {
1642 System.out.print( sec );
1643 System.out.print( " " );
1645 System.out.println();
1650 } // if ( perform_pwc ) {
1651 System.out.println();
1652 html_desc.append( "<tr><td>Command line:</td><td>\n" + cla.getCommandLineArgsAsString() + "\n</td></tr>" + nl );
1653 System.out.println( "Command line : " + cla.getCommandLineArgsAsString() );
1654 BufferedWriter[] query_domains_writer_ary = null;
1655 List<DomainId>[] query_domain_ids_array = null;
1656 if ( query_domain_ids != null ) {
1657 final String[] query_domain_ids_str_array = query_domain_ids.split( "#" );
1658 query_domain_ids_array = new ArrayList[ query_domain_ids_str_array.length ];
1659 query_domains_writer_ary = new BufferedWriter[ query_domain_ids_str_array.length ];
1660 for( int i = 0; i < query_domain_ids_str_array.length; i++ ) {
1661 String query_domain_ids_str = query_domain_ids_str_array[ i ];
1662 final String[] query_domain_ids_str_ary = query_domain_ids_str.split( "~" );
1663 final List<DomainId> query = new ArrayList<DomainId>();
1664 for( final String element : query_domain_ids_str_ary ) {
1665 query.add( new DomainId( element ) );
1667 query_domain_ids_array[ i ] = query;
1668 query_domain_ids_str = query_domain_ids_str.replace( '~', '_' );
1669 String protein_names_writer_str = query_domain_ids_str + surfacing.SEQ_EXTRACT_SUFFIX;
1670 if ( out_dir != null ) {
1671 protein_names_writer_str = out_dir + ForesterUtil.FILE_SEPARATOR + protein_names_writer_str;
1674 query_domains_writer_ary[ i ] = new BufferedWriter( new FileWriter( protein_names_writer_str ) );
1676 catch ( final IOException e ) {
1677 ForesterUtil.fatalError( surfacing.PRG_NAME, "Could not open [" + protein_names_writer_str + "]: "
1678 + e.getLocalizedMessage() );
1682 SortedMap<Species, List<Protein>> protein_lists_per_species = null; //This will only be created if neede.
1683 boolean need_protein_lists_per_species = false;
1684 if ( ( plus_minus_analysis_high_copy_base_species.size() > 0 ) || output_protein_lists_for_all_domains ) {
1685 need_protein_lists_per_species = true;
1687 if ( need_protein_lists_per_species ) {
1688 protein_lists_per_species = new TreeMap<Species, List<Protein>>();
1690 final List<GenomeWideCombinableDomains> gwcd_list = new ArrayList<GenomeWideCombinableDomains>( number_of_genomes );
1691 final SortedSet<DomainId> all_domains_encountered = new TreeSet<DomainId>();
1692 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered = new TreeSet<BinaryDomainCombination>();
1693 List<BinaryDomainCombination> all_bin_domain_combinations_gained_fitch = null;
1694 List<BinaryDomainCombination> all_bin_domain_combinations_lost_fitch = null;
1695 if ( ( intrees != null ) && ( intrees.length == 1 ) ) {
1696 all_bin_domain_combinations_gained_fitch = new ArrayList<BinaryDomainCombination>();
1697 all_bin_domain_combinations_lost_fitch = new ArrayList<BinaryDomainCombination>();
1699 final DomainLengthsTable domain_lengths_table = new DomainLengthsTable();
1700 final File per_genome_domain_promiscuity_statistics_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR
1701 + output_file + D_PROMISCUITY_FILE_SUFFIX );
1702 BufferedWriter per_genome_domain_promiscuity_statistics_writer = null;
1704 per_genome_domain_promiscuity_statistics_writer = new BufferedWriter( new FileWriter( per_genome_domain_promiscuity_statistics_file ) );
1705 per_genome_domain_promiscuity_statistics_writer.write( "Species:\t" );
1706 per_genome_domain_promiscuity_statistics_writer.write( "Mean:\t" );
1707 per_genome_domain_promiscuity_statistics_writer.write( "SD:\t" );
1708 per_genome_domain_promiscuity_statistics_writer.write( "Median:\t" );
1709 per_genome_domain_promiscuity_statistics_writer.write( "Min:\t" );
1710 per_genome_domain_promiscuity_statistics_writer.write( "Max:\t" );
1711 per_genome_domain_promiscuity_statistics_writer.write( "N:\t" );
1712 per_genome_domain_promiscuity_statistics_writer.write( "Max Promiscuous Domains:"
1713 + ForesterUtil.LINE_SEPARATOR );
1715 catch ( final IOException e2 ) {
1716 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1718 final File log_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + LOG_FILE_SUFFIX );
1719 BufferedWriter log_writer = null;
1721 log_writer = new BufferedWriter( new FileWriter( log_file ) );
1723 catch ( final IOException e2 ) {
1724 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1726 BufferedWriter dc_data_writer = null;
1728 dc_data_writer = new BufferedWriter( new FileWriter( dc_data_file ) );
1729 dc_data_writer.write( DATA_FILE_DESC );
1730 dc_data_writer.write( ForesterUtil.LINE_SEPARATOR );
1732 catch ( final IOException e2 ) {
1733 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1735 final DescriptiveStatistics protein_coverage_stats = new BasicDescriptiveStatistics();
1736 final DescriptiveStatistics all_genomes_domains_per_potein_stats = new BasicDescriptiveStatistics();
1737 final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo = new TreeMap<Integer, Integer>();
1738 final SortedSet<String> domains_which_are_always_single = new TreeSet<String>();
1739 final SortedSet<String> domains_which_are_sometimes_single_sometimes_not = new TreeSet<String>();
1740 final SortedSet<String> domains_which_never_single = new TreeSet<String>();
1741 BufferedWriter domains_per_potein_stats_writer = null;
1743 domains_per_potein_stats_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
1744 + output_file + "__domains_per_potein_stats.txt" ) );
1745 domains_per_potein_stats_writer.write( "Genome" );
1746 domains_per_potein_stats_writer.write( "\t" );
1747 domains_per_potein_stats_writer.write( "Mean" );
1748 domains_per_potein_stats_writer.write( "\t" );
1749 domains_per_potein_stats_writer.write( "SD" );
1750 domains_per_potein_stats_writer.write( "\t" );
1751 domains_per_potein_stats_writer.write( "Median" );
1752 domains_per_potein_stats_writer.write( "\t" );
1753 domains_per_potein_stats_writer.write( "N" );
1754 domains_per_potein_stats_writer.write( "\t" );
1755 domains_per_potein_stats_writer.write( "Min" );
1756 domains_per_potein_stats_writer.write( "\t" );
1757 domains_per_potein_stats_writer.write( "Max" );
1758 domains_per_potein_stats_writer.write( "\n" );
1760 catch ( final IOException e3 ) {
1761 e3.printStackTrace();
1763 final Map<String, DescriptiveStatistics> protein_length_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1764 final Map<String, DescriptiveStatistics> domain_number_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1765 final Map<String, DescriptiveStatistics> domain_length_stats_by_domain = new HashMap<String, DescriptiveStatistics>();
1767 for( int i = 0; i < number_of_genomes; ++i ) {
1768 System.out.println();
1769 System.out.println( ( i + 1 ) + "/" + number_of_genomes );
1770 log( ( i + 1 ) + "/" + number_of_genomes, log_writer );
1771 System.out.println( "Processing : " + input_file_properties[ i ][ 0 ] );
1772 log( "Genome : " + input_file_properties[ i ][ 0 ], log_writer );
1773 HmmscanPerDomainTableParser parser = null;
1774 INDIVIDUAL_SCORE_CUTOFF ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF.NONE;
1775 if ( individual_score_cutoffs != null ) {
1776 ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF_DEFAULT;
1778 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1779 || ( negative_domains_filter_file != null ) ) {
1780 HmmscanPerDomainTableParser.FilterType filter_type = HmmscanPerDomainTableParser.FilterType.NONE;
1781 if ( positive_filter_file != null ) {
1782 filter_type = HmmscanPerDomainTableParser.FilterType.POSITIVE_PROTEIN;
1784 else if ( negative_filter_file != null ) {
1785 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_PROTEIN;
1787 else if ( negative_domains_filter_file != null ) {
1788 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_DOMAIN;
1790 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1791 input_file_properties[ i ][ 1 ],
1798 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1799 input_file_properties[ i ][ 1 ],
1803 if ( e_value_max >= 0.0 ) {
1804 parser.setEValueMaximum( e_value_max );
1806 parser.setIgnoreDufs( ignore_dufs );
1807 parser.setIgnoreVirusLikeIds( ignore_virus_like_ids );
1808 parser.setIgnoreEngulfedDomains( no_engulfing_overlaps );
1809 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1810 parser.setMaxAllowedOverlap( max_allowed_overlap );
1812 parser.setReturnType( HmmscanPerDomainTableParser.ReturnType.UNORDERED_PROTEIN_DOMAIN_COLLECTION_PER_PROTEIN );
1813 if ( individual_score_cutoffs != null ) {
1814 parser.setIndividualScoreCutoffs( individual_score_cutoffs );
1816 List<Protein> protein_list = null;
1818 protein_list = parser.parse();
1820 catch ( final IOException e ) {
1821 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1823 catch ( final Exception e ) {
1824 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, e.getMessage(), e );
1827 System.out.println( "Domains ignored due to negative domain filter: " );
1828 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToNegativeDomainFilterCountsMap() );
1829 System.out.println( "Domains ignored due to virus like id: " );
1830 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToVirusLikeIdCountsMap() );
1832 final double coverage = ( double ) protein_list.size() / parser.getProteinsEncountered();
1833 protein_coverage_stats.addValue( coverage );
1834 System.out.println( "Number of proteins encountered : " + parser.getProteinsEncountered() );
1835 log( "Number of proteins encountered : " + parser.getProteinsEncountered(), log_writer );
1836 System.out.println( "Number of proteins stored : " + protein_list.size() );
1837 log( "Number of proteins stored : " + protein_list.size(), log_writer );
1838 System.out.println( "Coverage : "
1839 + ForesterUtil.roundToInt( 100.0 * coverage ) + "%" );
1840 log( "Coverage : " + ForesterUtil.roundToInt( 100.0 * coverage )
1841 + "%", log_writer );
1842 System.out.println( "Domains encountered : " + parser.getDomainsEncountered() );
1843 log( "Domains encountered : " + parser.getDomainsEncountered(), log_writer );
1844 System.out.println( "Domains stored : " + parser.getDomainsStored() );
1845 log( "Domains stored : " + parser.getDomainsStored(), log_writer );
1846 System.out.println( "Distinct domains stored : "
1847 + parser.getDomainsStoredSet().size() );
1848 log( "Distinct domains stored : " + parser.getDomainsStoredSet().size(), log_writer );
1849 System.out.println( "Domains ignored due to individual score cutoffs: "
1850 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() );
1851 log( "Domains ignored due to individual score cutoffs: "
1852 + parser.getDomainsIgnoredDueToIndividualScoreCutoff(),
1854 System.out.println( "Domains ignored due to E-value : "
1855 + parser.getDomainsIgnoredDueToEval() );
1856 log( "Domains ignored due to E-value : " + parser.getDomainsIgnoredDueToEval(), log_writer );
1857 System.out.println( "Domains ignored due to DUF designation : "
1858 + parser.getDomainsIgnoredDueToDuf() );
1859 log( "Domains ignored due to DUF designation : " + parser.getDomainsIgnoredDueToDuf(), log_writer );
1860 if ( ignore_virus_like_ids ) {
1861 System.out.println( "Domains ignored due virus like ids : "
1862 + parser.getDomainsIgnoredDueToVirusLikeIds() );
1863 log( "Domains ignored due virus like ids : " + parser.getDomainsIgnoredDueToVirusLikeIds(),
1866 System.out.println( "Domains ignored due negative domain filter : "
1867 + parser.getDomainsIgnoredDueToNegativeDomainFilter() );
1868 log( "Domains ignored due negative domain filter : "
1869 + parser.getDomainsIgnoredDueToNegativeDomainFilter(),
1871 System.out.println( "Domains ignored due to overlap : "
1872 + parser.getDomainsIgnoredDueToOverlap() );
1873 log( "Domains ignored due to overlap : " + parser.getDomainsIgnoredDueToOverlap(),
1875 if ( negative_filter_file != null ) {
1876 System.out.println( "Proteins ignored due to negative filter : "
1877 + parser.getProteinsIgnoredDueToFilter() );
1878 log( "Proteins ignored due to negative filter : " + parser.getProteinsIgnoredDueToFilter(),
1881 if ( positive_filter_file != null ) {
1882 System.out.println( "Proteins ignored due to positive filter : "
1883 + parser.getProteinsIgnoredDueToFilter() );
1884 log( "Proteins ignored due to positive filter : " + parser.getProteinsIgnoredDueToFilter(),
1887 System.out.println( "Time for processing : " + parser.getTime() + "ms" );
1888 log( "", log_writer );
1889 html_desc.append( "<tr><td>" + input_file_properties[ i ][ 0 ] + " [species: "
1890 + input_file_properties[ i ][ 1 ] + "]" + ":</td><td>domains analyzed: "
1891 + parser.getDomainsStored() + "; domains ignored: [ind score cutoffs: "
1892 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() + "] [E-value cutoff: "
1893 + parser.getDomainsIgnoredDueToEval() + "] [DUF: " + parser.getDomainsIgnoredDueToDuf()
1894 + "] [virus like ids: " + parser.getDomainsIgnoredDueToVirusLikeIds()
1895 + "] [negative domain filter: " + parser.getDomainsIgnoredDueToNegativeDomainFilter()
1896 + "] [overlap: " + parser.getDomainsIgnoredDueToOverlap() + "]" );
1897 if ( negative_filter_file != null ) {
1898 html_desc.append( "; proteins ignored due to negative filter: "
1899 + parser.getProteinsIgnoredDueToFilter() );
1901 if ( positive_filter_file != null ) {
1902 html_desc.append( "; proteins ignored due to positive filter: "
1903 + parser.getProteinsIgnoredDueToFilter() );
1905 html_desc.append( "</td></tr>" + nl );
1906 // domain_partner_counts_array[ i ] =
1907 // Methods.getDomainPartnerCounts( protein_domain_collections_array[
1909 // false, input_file_properties[ i ][ 1 ] );
1912 for( final Protein protein : protein_list ) {
1913 dc_data_writer.write( SurfacingUtil.proteinToDomainCombinations( protein, count + "", "\t" )
1916 for( final Domain d : protein.getProteinDomains() ) {
1917 final String d_str = d.getDomainId().toString();
1918 if ( !domain_length_stats_by_domain.containsKey( d_str ) ) {
1919 domain_length_stats_by_domain.put( d_str, new BasicDescriptiveStatistics() );
1921 domain_length_stats_by_domain.get( d_str ).addValue( d.getLength() );
1925 catch ( final IOException e ) {
1926 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1928 SurfacingUtil.domainsPerProteinsStatistics( input_file_properties[ i ][ 1 ],
1930 all_genomes_domains_per_potein_stats,
1931 all_genomes_domains_per_potein_histo,
1932 domains_which_are_always_single,
1933 domains_which_are_sometimes_single_sometimes_not,
1934 domains_which_never_single,
1935 domains_per_potein_stats_writer );
1936 gwcd_list.add( BasicGenomeWideCombinableDomains
1937 .createInstance( protein_list,
1938 ignore_combination_with_same,
1939 new BasicSpecies( input_file_properties[ i ][ 1 ] ),
1940 domain_id_to_go_ids_map,
1942 protein_length_stats_by_dc,
1943 domain_number_stats_by_dc ) );
1944 domain_lengths_table.addLengths( protein_list );
1945 if ( gwcd_list.get( i ).getSize() > 0 ) {
1946 SurfacingUtil.writeDomainCombinationsCountsFile( input_file_properties,
1948 per_genome_domain_promiscuity_statistics_writer,
1952 if ( output_binary_domain_combinationsfor_graph_analysis ) {
1953 SurfacingUtil.writeBinaryDomainCombinationsFileForGraphAnalysis( input_file_properties,
1959 SurfacingUtil.addAllDomainIdsToSet( gwcd_list.get( i ), all_domains_encountered );
1960 SurfacingUtil.addAllBinaryDomainCombinationToSet( gwcd_list.get( i ),
1961 all_bin_domain_combinations_encountered );
1963 if ( query_domains_writer_ary != null ) {
1964 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1966 SurfacingUtil.extractProteinNames( protein_list,
1967 query_domain_ids_array[ j ],
1968 query_domains_writer_ary[ j ],
1970 LIMIT_SPEC_FOR_PROT_EX );
1971 query_domains_writer_ary[ j ].flush();
1973 catch ( final IOException e ) {
1974 e.printStackTrace();
1978 if ( need_protein_lists_per_species ) {
1979 protein_lists_per_species.put( new BasicSpecies( input_file_properties[ i ][ 1 ] ), protein_list );
1984 catch ( final IOException e2 ) {
1985 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1988 } // for( int i = 0; i < number_of_genomes; ++i ) {
1989 ForesterUtil.programMessage( PRG_NAME, "Wrote domain promiscuities to: "
1990 + per_genome_domain_promiscuity_statistics_file );
1993 domains_per_potein_stats_writer.write( "ALL" );
1994 domains_per_potein_stats_writer.write( "\t" );
1995 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.arithmeticMean() + "" );
1996 domains_per_potein_stats_writer.write( "\t" );
1997 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.sampleStandardDeviation() + "" );
1998 domains_per_potein_stats_writer.write( "\t" );
1999 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.median() + "" );
2000 domains_per_potein_stats_writer.write( "\t" );
2001 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getN() + "" );
2002 domains_per_potein_stats_writer.write( "\t" );
2003 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMin() + "" );
2004 domains_per_potein_stats_writer.write( "\t" );
2005 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMax() + "" );
2006 domains_per_potein_stats_writer.write( "\n" );
2007 domains_per_potein_stats_writer.close();
2008 printOutPercentageOfMultidomainProteins( all_genomes_domains_per_potein_histo, log_writer );
2009 ForesterUtil.map2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2010 + "__all_genomes_domains_per_potein_histo.txt" ), all_genomes_domains_per_potein_histo, "\t", "\n" );
2011 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2012 + "__domains_always_single_.txt" ), domains_which_are_always_single, "\n" );
2013 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2014 + "__domains_single_or_combined.txt" ), domains_which_are_sometimes_single_sometimes_not, "\n" );
2015 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
2016 + "__domains_always_combined.txt" ), domains_which_never_single, "\n" );
2017 ForesterUtil.programMessage( PRG_NAME,
2018 "Average of proteins with a least one domain assigned: "
2019 + ( 100 * protein_coverage_stats.arithmeticMean() ) + "% (+/-"
2020 + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)" );
2021 ForesterUtil.programMessage( PRG_NAME, "Range of proteins with a least one domain assigned: " + 100
2022 * protein_coverage_stats.getMin() + "%-" + 100 * protein_coverage_stats.getMax() + "%" );
2023 log( "Average of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.arithmeticMean() )
2024 + "% (+/-" + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)", log_writer );
2025 log( "Range of prot with a least one dom assigned : " + 100 * protein_coverage_stats.getMin() + "%-"
2026 + 100 * protein_coverage_stats.getMax() + "%", log_writer );
2028 catch ( final IOException e2 ) {
2029 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
2031 if ( query_domains_writer_ary != null ) {
2032 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
2034 query_domains_writer_ary[ j ].close();
2036 catch ( final IOException e ) {
2037 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
2042 per_genome_domain_promiscuity_statistics_writer.close();
2043 dc_data_writer.close();
2046 catch ( final IOException e2 ) {
2047 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
2049 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
2051 SurfacingUtil.executeDomainLengthAnalysis( input_file_properties,
2053 domain_lengths_table,
2054 domain_lengths_analysis_outfile );
2056 catch ( final IOException e1 ) {
2057 ForesterUtil.fatalError( surfacing.PRG_NAME, e1.toString() );
2059 System.out.println();
2060 ForesterUtil.programMessage( PRG_NAME, "Wrote domain length data to: " + domain_lengths_analysis_outfile );
2061 System.out.println();
2063 final long analysis_start_time = new Date().getTime();
2064 PairwiseDomainSimilarityCalculator pw_calc = null;
2065 // double[] values_for_all_scores_histogram = null;
2066 final DomainSimilarityCalculator calc = new BasicDomainSimilarityCalculator( domain_similarity_sort_field,
2067 sort_by_species_count_first,
2068 number_of_genomes == 2 );
2069 switch ( scoring ) {
2071 pw_calc = new CombinationsBasedPairwiseDomainSimilarityCalculator();
2074 pw_calc = new DomainCountsBasedPairwiseSimilarityCalculator();
2077 pw_calc = new ProteinCountsBasedPairwiseDomainSimilarityCalculator();
2080 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
2082 DomainSimilarityCalculator.GoAnnotationOutput go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.NONE;
2083 if ( domain_id_to_go_ids_map != null ) {
2084 go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.ALL;
2086 final SortedSet<DomainSimilarity> similarities = calc
2087 .calculateSimilarities( pw_calc,
2089 ignore_domains_without_combs_in_all_spec,
2090 ignore_species_specific_domains );
2091 SurfacingUtil.decoratePrintableDomainSimilarities( similarities,
2093 go_annotation_output,
2095 go_namespace_limit );
2096 DescriptiveStatistics pw_stats = null;
2098 String my_outfile = output_file.toString();
2099 Map<Character, Writer> split_writers = null;
2100 Writer writer = null;
2101 if ( similarities.size() > MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING ) {
2102 if ( my_outfile.endsWith( ".html" ) ) {
2103 my_outfile = my_outfile.substring( 0, my_outfile.length() - 5 );
2105 split_writers = new HashMap<Character, Writer>();
2106 createSplitWriters( out_dir, my_outfile, split_writers );
2108 else if ( !my_outfile.endsWith( ".html" ) ) {
2109 my_outfile += ".html";
2110 writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) );
2112 List<Species> species_order = null;
2113 if ( species_matrix ) {
2114 species_order = new ArrayList<Species>();
2115 for( int i = 0; i < number_of_genomes; i++ ) {
2116 species_order.add( new BasicSpecies( input_file_properties[ i ][ 1 ] ) );
2119 html_desc.append( "<tr><td>Sum of all distinct binary combinations:</td><td>"
2120 + all_bin_domain_combinations_encountered.size() + "</td></tr>" + nl );
2121 html_desc.append( "<tr><td>Sum of all distinct domains:</td><td>" + all_domains_encountered.size()
2122 + "</td></tr>" + nl );
2123 html_desc.append( "<tr><td>Analysis date/time:</td><td>"
2124 + new java.text.SimpleDateFormat( "yyyy.MM.dd HH:mm:ss" ).format( new java.util.Date() )
2125 + "</td></tr>" + nl );
2126 html_desc.append( "</table>" + nl );
2127 pw_stats = SurfacingUtil
2128 .writeDomainSimilaritiesToFile( html_desc,
2129 new StringBuilder( number_of_genomes + " genomes" ),
2133 number_of_genomes == 2,
2135 domain_similarity_print_option,
2136 domain_similarity_sort_field,
2139 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote main output (includes domain similarities) to: \""
2140 + ( out_dir == null ? my_outfile : out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) + "\"" );
2142 catch ( final IOException e ) {
2143 ForesterUtil.fatalError( surfacing.PRG_NAME, "Failed to write similarites to: \"" + output_file + "\" ["
2144 + e.getMessage() + "]" );
2146 System.out.println();
2147 // values_for_all_scores_histogram = pw_stats.getDataAsDoubleArray();
2148 final Species[] species = new Species[ number_of_genomes ];
2149 for( int i = 0; i < number_of_genomes; ++i ) {
2150 species[ i ] = new BasicSpecies( input_file_properties[ i ][ 1 ] );
2152 List<Phylogeny> inferred_trees = null;
2153 if ( ( number_of_genomes > 2 ) && perform_pwc ) {
2154 final PairwiseGenomeComparator pwgc = new PairwiseGenomeComparator();
2155 pwgc.performPairwiseComparisons( html_desc,
2156 sort_by_species_count_first,
2158 ignore_domains_without_combs_in_all_spec,
2159 ignore_species_specific_domains,
2160 domain_similarity_sort_field_for_automated_pwc,
2161 domain_similarity_print_option,
2163 domain_id_to_go_ids_map,
2170 automated_pairwise_comparison_suffix,
2172 surfacing.PAIRWISE_DOMAIN_COMPARISONS_PREFIX,
2176 String matrix_output_file = new String( output_file.toString() );
2177 if ( matrix_output_file.indexOf( '.' ) > 1 ) {
2178 matrix_output_file = matrix_output_file.substring( 0, matrix_output_file.indexOf( '.' ) );
2180 if ( out_dir != null ) {
2181 matrix_output_file = out_dir + ForesterUtil.FILE_SEPARATOR + matrix_output_file;
2182 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2184 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2185 + surfacing.MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans() );
2187 .writeMatrixToFile( new File( matrix_output_file
2188 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2189 pwgc.getSharedBinaryCombinationsBasedDistances() );
2190 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2191 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2192 pwgc.getSharedDomainsBasedDistances() );
2193 final Phylogeny nj_gd = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2194 + surfacing.NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans()
2196 final Phylogeny nj_bc = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2197 + surfacing.NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2198 .getSharedBinaryCombinationsBasedDistances().get( 0 ) );
2199 final Phylogeny nj_d = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2200 + surfacing.NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2201 .getSharedDomainsBasedDistances().get( 0 ) );
2202 inferred_trees = new ArrayList<Phylogeny>();
2203 inferred_trees.add( nj_gd );
2204 inferred_trees.add( nj_bc );
2205 inferred_trees.add( nj_d );
2206 if ( jacknifed_distances ) {
2207 pwgc.performPairwiseComparisonsJacknifed( species,
2211 jacknife_resamplings,
2215 .writeMatrixToFile( new File( matrix_output_file
2217 + ForesterUtil.round( jacknife_ratio, 2 )
2219 + jacknife_resamplings
2220 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2221 pwgc.getSharedBinaryCombinationsBasedDistances() );
2223 .writeMatrixToFile( new File( matrix_output_file + "_" + ForesterUtil.round( jacknife_ratio, 2 )
2224 + "_" + jacknife_resamplings
2225 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2226 pwgc.getSharedDomainsBasedDistances() );
2227 // if ( infer_species_trees ) {
2228 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2229 // + INFERRED_SBC_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc
2230 // .getSharedBinaryCombinationsBasedDistances() );
2231 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2232 // + INFERRED_SD_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc.getSharedDomainsBasedDistances() );
2235 } // if ( ( output_file != null ) && ( number_of_genomes > 2 ) && !isEmpty( automated_pairwise_comparison_suffix ) )
2236 if ( ( out_dir != null ) && ( !perform_pwc ) ) {
2237 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2239 writePresentToNexus( output_file, positive_filter_file, filter, gwcd_list );
2240 if ( ( ( intrees != null ) && ( intrees.length > 0 ) ) && ( number_of_genomes > 2 ) ) {
2241 final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
2243 max_allowed_overlap,
2244 no_engulfing_overlaps,
2248 if ( radomize_fitch_parsimony ) {
2249 s += random_number_seed_for_fitch_parsimony + "_";
2252 for( final Phylogeny intree : intrees ) {
2253 final String outfile_name = ForesterUtil.removeSuffix( output_file.toString() ) + s
2254 + ForesterUtil.removeSuffix( intree_files[ i ].toString() );
2255 final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator.createInstance( intree,
2257 SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
2258 radomize_fitch_parsimony,
2262 domain_id_to_go_ids_map,
2265 parameters_sb.toString(),
2266 domain_id_to_secondary_features_maps,
2267 positive_filter_file == null ? null : filter,
2268 output_binary_domain_combinationsfor_graph_analysis,
2269 all_bin_domain_combinations_gained_fitch,
2270 all_bin_domain_combinations_lost_fitch,
2272 protein_length_stats_by_dc,
2273 domain_number_stats_by_dc,
2274 domain_length_stats_by_domain );
2275 // Listing of all domain combinations gained is only done if only one input tree is used.
2276 if ( ( domain_id_to_secondary_features_maps != null )
2277 && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
2279 for( final Map<DomainId, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
2280 final Map<Species, MappingResults> mapping_results_map = new TreeMap<Species, MappingResults>();
2281 final DomainParsimonyCalculator secondary_features_parsimony = DomainParsimonyCalculator
2282 .createInstance( intree, gwcd_list, domain_id_to_secondary_features_map );
2284 .executeParsimonyAnalysisForSecondaryFeatures( outfile_name
2286 + secondary_features_map_files[ j++ ],
2287 secondary_features_parsimony,
2289 parameters_sb.toString(),
2290 mapping_results_map );
2292 System.out.println();
2293 System.out.println( "Mapping to secondary features:" );
2294 for( final Species spec : mapping_results_map.keySet() ) {
2295 final MappingResults mapping_results = mapping_results_map.get( spec );
2296 final int total_domains = mapping_results.getSumOfFailures()
2297 + mapping_results.getSumOfSuccesses();
2298 System.out.print( spec + ":" );
2299 System.out.print( " mapped domains = " + mapping_results.getSumOfSuccesses() );
2300 System.out.print( ", not mapped domains = " + mapping_results.getSumOfFailures() );
2301 if ( total_domains > 0 ) {
2302 System.out.println( ", mapped ratio = "
2303 + ( 100 * mapping_results.getSumOfSuccesses() / total_domains ) + "%" );
2306 System.out.println( ", mapped ratio = n/a (total domains = 0 )" );
2313 } // for( final Phylogeny intree : intrees ) {
2315 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
2316 executePlusMinusAnalysis( output_file,
2317 plus_minus_analysis_high_copy_base_species,
2318 plus_minus_analysis_high_copy_target_species,
2319 plus_minus_analysis_high_low_copy_species,
2321 protein_lists_per_species,
2322 domain_id_to_go_ids_map,
2324 plus_minus_analysis_numbers );
2326 if ( output_protein_lists_for_all_domains ) {
2327 writeProteinListsForAllSpecies( out_dir, protein_lists_per_species, gwcd_list );
2329 // if ( ( intrees != null ) && ( intrees.length > 0 ) && ( inferred_trees != null ) && ( inferred_trees.size() > 0 ) ) {
2330 // final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
2332 // max_allowed_overlap,
2333 // no_engulfing_overlaps,
2334 // cutoff_scores_file );
2336 // if ( radomize_fitch_parsimony ) {
2337 // s += random_number_seed_for_fitch_parsimony + "_";
2340 // for( final Phylogeny inferred_tree : inferred_trees ) {
2341 // if ( !inferred_tree.isRooted() ) {
2342 // intrees[ 0 ].getRoot().getName();
2345 // final String outfile_name = ForesterUtil.removeSuffix( inferred_tree.getName() ) + s;
2346 // final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator
2347 // .createInstance( inferred_tree, gwcd_list );
2348 // SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
2349 // radomize_fitch_parsimony,
2351 // domain_parsimony,
2353 // domain_id_to_go_ids_map,
2354 // go_id_to_term_map,
2355 // go_namespace_limit,
2356 // parameters_sb.toString() );
2360 if ( all_bin_domain_combinations_gained_fitch != null ) {
2362 executeFitchGainsAnalysis( new File( output_file
2363 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2364 all_bin_domain_combinations_gained_fitch,
2365 all_domains_encountered.size(),
2366 all_bin_domain_combinations_encountered,
2369 catch ( final IOException e ) {
2370 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2373 if ( all_bin_domain_combinations_lost_fitch != null ) {
2375 executeFitchGainsAnalysis( new File( output_file
2376 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2377 all_bin_domain_combinations_lost_fitch,
2378 all_domains_encountered.size(),
2379 all_bin_domain_combinations_encountered,
2382 catch ( final IOException e ) {
2383 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2386 final Runtime rt = java.lang.Runtime.getRuntime();
2387 final long free_memory = rt.freeMemory() / 1000000;
2388 final long total_memory = rt.totalMemory() / 1000000;
2389 ForesterUtil.programMessage( PRG_NAME, "Time for analysis : " + ( new Date().getTime() - analysis_start_time )
2391 ForesterUtil.programMessage( PRG_NAME, "Total running time: " + ( new Date().getTime() - start_time ) + "ms " );
2392 ForesterUtil.programMessage( PRG_NAME, "Free memory : " + free_memory + "MB, total memory: "
2393 + total_memory + "MB" );
2394 ForesterUtil.programMessage( PRG_NAME, "If this application is useful to you, please cite:" );
2395 ForesterUtil.programMessage( PRG_NAME, surfacing.WWW );
2396 ForesterUtil.programMessage( PRG_NAME, "OK" );
2397 System.out.println();
2400 private static void createSplitWriters( final File out_dir,
2401 final String my_outfile,
2402 final Map<Character, Writer> split_writers ) throws IOException {
2403 split_writers.put( 'a', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2404 + "_domains_A.html" ) ) );
2405 split_writers.put( 'b', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2406 + "_domains_B.html" ) ) );
2407 split_writers.put( 'c', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2408 + "_domains_C.html" ) ) );
2409 split_writers.put( 'd', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2410 + "_domains_D.html" ) ) );
2411 split_writers.put( 'e', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2412 + "_domains_E.html" ) ) );
2413 split_writers.put( 'f', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2414 + "_domains_F.html" ) ) );
2415 split_writers.put( 'g', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2416 + "_domains_G.html" ) ) );
2417 split_writers.put( 'h', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2418 + "_domains_H.html" ) ) );
2419 split_writers.put( 'i', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2420 + "_domains_I.html" ) ) );
2421 split_writers.put( 'j', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2422 + "_domains_J.html" ) ) );
2423 split_writers.put( 'k', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2424 + "_domains_K.html" ) ) );
2425 split_writers.put( 'l', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2426 + "_domains_L.html" ) ) );
2427 split_writers.put( 'm', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2428 + "_domains_M.html" ) ) );
2429 split_writers.put( 'n', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2430 + "_domains_N.html" ) ) );
2431 split_writers.put( 'o', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2432 + "_domains_O.html" ) ) );
2433 split_writers.put( 'p', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2434 + "_domains_P.html" ) ) );
2435 split_writers.put( 'q', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2436 + "_domains_Q.html" ) ) );
2437 split_writers.put( 'r', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2438 + "_domains_R.html" ) ) );
2439 split_writers.put( 's', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2440 + "_domains_S.html" ) ) );
2441 split_writers.put( 't', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2442 + "_domains_T.html" ) ) );
2443 split_writers.put( 'u', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2444 + "_domains_U.html" ) ) );
2445 split_writers.put( 'v', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2446 + "_domains_V.html" ) ) );
2447 split_writers.put( 'w', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2448 + "_domains_W.html" ) ) );
2449 split_writers.put( 'x', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2450 + "_domains_X.html" ) ) );
2451 split_writers.put( 'y', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2452 + "_domains_Y.html" ) ) );
2453 split_writers.put( 'z', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2454 + "_domains_Z.html" ) ) );
2455 split_writers.put( '0', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2456 + "_domains_0.html" ) ) );
2459 private static void printOutPercentageOfMultidomainProteins( final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo,
2460 final Writer log_writer ) {
2462 for( final Entry<Integer, Integer> entry : all_genomes_domains_per_potein_histo.entrySet() ) {
2463 sum += entry.getValue();
2465 final double percentage = 100.0 * ( sum - all_genomes_domains_per_potein_histo.get( 1 ) ) / sum;
2466 ForesterUtil.programMessage( PRG_NAME, "Percentage of multidomain proteins: " + percentage + "%" );
2467 log( "Percentage of multidomain proteins: : " + percentage + "%", log_writer );
2470 private static void preparePhylogenyForParsimonyAnalyses( final Phylogeny intree,
2471 final String[][] input_file_properties ) {
2472 final String[] genomes = new String[ input_file_properties.length ];
2473 for( int i = 0; i < input_file_properties.length; ++i ) {
2474 if ( intree.getNodes( input_file_properties[ i ][ 1 ] ).size() > 1 ) {
2475 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
2476 + "] is not unique in input tree " + intree.getName() );
2478 genomes[ i ] = input_file_properties[ i ][ 1 ];
2481 final PhylogenyNodeIterator it = intree.iteratorPostorder();
2482 while ( it.hasNext() ) {
2483 final PhylogenyNode n = it.next();
2484 if ( ForesterUtil.isEmpty( n.getName() ) ) {
2485 if ( n.getNodeData().isHasTaxonomy()
2486 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getTaxonomyCode() ) ) {
2487 n.setName( n.getNodeData().getTaxonomy().getTaxonomyCode() );
2489 else if ( n.getNodeData().isHasTaxonomy()
2490 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
2491 n.setName( n.getNodeData().getTaxonomy().getScientificName() );
2493 else if ( n.getNodeData().isHasTaxonomy()
2494 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getCommonName() ) ) {
2495 n.setName( n.getNodeData().getTaxonomy().getCommonName() );
2499 .fatalError( surfacing.PRG_NAME,
2500 "node with no name, scientific name, common name, or taxonomy code present" );
2505 final List<String> igns = PhylogenyMethods.deleteExternalNodesPositiveSelection( genomes, intree );
2506 if ( igns.size() > 0 ) {
2507 System.out.println( "Not using the following " + igns.size() + " nodes:" );
2508 for( int i = 0; i < igns.size(); ++i ) {
2509 System.out.println( " " + i + ": " + igns.get( i ) );
2511 System.out.println( "--" );
2513 for( int i = 0; i < input_file_properties.length; ++i ) {
2515 intree.getNode( input_file_properties[ i ][ 1 ] );
2517 catch ( final IllegalArgumentException e ) {
2518 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
2519 + "] not present/not unique in input tree" );
2524 // public static StringBuffer stringCombinableDomainsMapToStringBuffer(
2525 // final SortedMap<String, CombinableDomains> map ) {
2526 // final StringBuffer sb = new StringBuffer();
2527 // for( final Iterator<String> iter = map.keySet().iterator();
2528 // iter.hasNext(); ) {
2529 // final Object key = iter.next();
2530 // sb.append( ForesterUtil.pad( new StringBuffer( key.toString() ), 18, ' ',
2532 // final CombinableDomains domain_combination = map.get( key );
2533 // sb.append( ForesterUtil.pad( new StringBuffer( "" +
2534 // domain_combination.getNumberOfCombiningDomains() ), 8,
2536 // sb.append( domain_combination.toStringBuffer() );
2537 // sb.append( ForesterUtil.getLineSeparator() );
2541 private static void printHelp() {
2542 System.out.println();
2543 System.out.println( "Usage:" );
2544 System.out.println();
2545 System.out.println( "% java -Xms256m -Xmx512m -cp forester.jar org.forester.applications." + surfacing.PRG_NAME
2546 + " [options] <phylogen(y|ies) infile> [external node name 1] [name 2] ... [name n]" );
2547 System.out.println();
2548 System.out.println( " Note: This software might need a significant amount of memory (heap space);" );
2550 .println( " hence use \"-Xms128m -Xmx512m\" (or more) to prevent a \"java.lang.OutOfMemoryError\"." );
2551 System.out.println();
2552 System.out.println( " Options: " );
2553 System.out.println( surfacing.DETAILEDNESS_OPTION + ": level of detail for similarities output file (default:"
2554 + DETAILEDNESS_DEFAULT + ")" );
2555 System.out.println( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION
2556 + ": to ignore combinations with self (default: not to ignore)" );
2558 .println( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION
2559 + ": to ignore domains without combinations in any species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2561 .println( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION
2562 + ": to ignore domains specific to one species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2563 System.out.println( surfacing.NOT_IGNORE_DUFS_OPTION
2564 + ": to _not_ ignore DUFs (domains with unknown function) (default: ignore DUFs)" );
2566 .println( surfacing.IGNORE_VIRAL_IDS
2567 + ": to ignore domains with ids containing 'vir', 'retro', 'transpos', 'phage', or starting with 'rv' or 'gag_'" );
2568 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_OPTION + ": sorting for similarities (default: "
2569 + DOMAIN_SORT_FILD_DEFAULT + ")" );
2570 System.out.println( surfacing.OUTPUT_FILE_OPTION + ": name for (main) output file (mandatory)" );
2571 System.out.println( surfacing.MAX_E_VALUE_OPTION + ": max (inclusive) E-value" );
2572 System.out.println( surfacing.MAX_ALLOWED_OVERLAP_OPTION + ": maximal allowed domain overlap" );
2573 System.out.println( surfacing.NO_ENGULFING_OVERLAP_OPTION + ": to ignore engulfed lower confidence domains" );
2574 System.out.println( surfacing.SPECIES_MATRIX_OPTION + ": species matrix" );
2575 System.out.println( surfacing.SCORING_OPTION + ": scoring (default:" + SCORING_DEFAULT + ")" );
2576 System.out.println( surfacing.DOMAIN_COUNT_SORT_OPTION + ": sorting for domain counts (default:"
2577 + DOMAINS_SORT_ORDER_DEFAULT + ")" );
2578 System.out.println( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION + ": domain similarity print option (default:"
2579 + DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT + ")" );
2580 System.out.println( surfacing.CUTOFF_SCORE_FILE_OPTION + ": cutoff score file" );
2581 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION
2582 + ": sort by species count first" );
2583 System.out.println( surfacing.OUTPUT_DIR_OPTION + ": output directory" );
2584 System.out.println( surfacing.PFAM_TO_GO_FILE_USE_OPTION + ": Pfam to GO mapping file" );
2585 System.out.println( surfacing.GO_OBO_FILE_USE_OPTION + ": GO terms file (OBO format)" );
2586 System.out.println( surfacing.GO_NAMESPACE_LIMIT_OPTION + ": limit GO term to one GO namespace" );
2587 System.out.println( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
2588 + "[=<suffix for pairwise comparison output files>]: to perform pairwise comparison based analyses" );
2589 System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION
2590 + ": species tree, to perform (Dollo, Fitch) parismony analyses" );
2592 .println( JACKNIFE_OPTION
2593 + ": perform jacknife resampling for domain and binary domain combination based distance matrices [default resamplings: "
2594 + JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT + "]" );
2595 System.out.println( JACKNIFE_RATIO_OPTION + ": ratio for jacknife resampling [default: "
2596 + JACKNIFE_RATIO_DEFAULT + "]" );
2597 System.out.println( JACKNIFE_RANDOM_SEED_OPTION
2598 + ": seed for random number generator for jacknife resampling [default: "
2599 + JACKNIFE_RANDOM_SEED_DEFAULT + "]" );
2600 // System.out.println( surfacing.INFER_SPECIES_TREES_OPTION
2601 // + ": to infer NJ species trees based on shared domains/binary domain combinations" );
2603 .println( surfacing.INPUT_SPECIES_TREE_OPTION
2604 + "=<treefiles in phyloXML format, separated by #>: to infer domain/binary domain combination gains/losses on given species trees" );
2605 System.out.println( surfacing.FILTER_POSITIVE_OPTION
2606 + "=<file>: to filter out proteins not containing at least one domain listed in <file>" );
2607 System.out.println( surfacing.FILTER_NEGATIVE_OPTION
2608 + "=<file>: to filter out proteins containing at least one domain listed in <file>" );
2609 System.out.println( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION
2610 + "=<file>: to filter out (ignore) domains listed in <file>" );
2611 System.out.println( surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>: to read input files from <file>" );
2613 .println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION
2614 + "=<seed>: seed for random number generator for Fitch Parsimony analysis (type: long, default: no randomization - given a choice, prefer absence" );
2615 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS
2616 + ": to consider directedness in binary combinations: e.g. A-B != B-A" );
2617 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY
2618 + ": to consider directedness and adjacency in binary combinations" );
2620 .println( surfacing.SEQ_EXTRACT_OPTION
2621 + "=<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')" );
2622 System.out.println( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE
2623 + "=<file>: to perfom parsimony analysis on secondary features" );
2624 System.out.println( surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>: to presence/absence genome analysis" );
2625 System.out.println( surfacing.DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS
2626 + ": to output binary domain combinations for (downstream) graph analysis" );
2627 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS + ": to output all proteins per domain" );
2628 System.out.println();
2629 System.out.println();
2630 System.out.println( "Example: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2631 + " org.forester.application.surfacing -detail=punctilious -o=TEST.html -pwc=TEST"
2632 + " -cos=Pfam_ls_22_TC2 -p2g=pfam2go -obo=gene_ontology_edit.obo "
2633 + "-dc_sort=dom -ignore_with_self -no_singles -e=0.001 -mo=1 -no_eo "
2634 + "-ds_output=detailed_html -scoring=domains -sort=alpha -" + JACKNIFE_OPTION
2635 + "=50 human mouse brafl strpu" );
2636 System.out.println();
2639 private static void processFilter( final File filter_file, final SortedSet<DomainId> filter ) {
2640 SortedSet<String> filter_str = null;
2642 filter_str = ForesterUtil.file2set( filter_file );
2644 catch ( final IOException e ) {
2645 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2647 if ( filter_str != null ) {
2648 for( final String string : filter_str ) {
2649 filter.add( new DomainId( string ) );
2653 System.out.println( "Filter:" );
2654 for( final DomainId domainId : filter ) {
2655 System.out.println( domainId.getId() );
2660 private static String[][] processInputFileNames( final String[] names ) {
2661 final String[][] input_file_properties = new String[ names.length ][];
2662 for( int i = 0; i < names.length; ++i ) {
2663 if ( names[ i ].indexOf( SEPARATOR_FOR_INPUT_VALUES ) < 0 ) {
2664 input_file_properties[ i ] = new String[ 2 ];
2665 input_file_properties[ i ][ 0 ] = names[ i ];
2666 input_file_properties[ i ][ 1 ] = names[ i ];
2669 input_file_properties[ i ] = names[ i ].split( surfacing.SEPARATOR_FOR_INPUT_VALUES + "" );
2670 if ( input_file_properties[ i ].length != 3 ) {
2672 .fatalError( surfacing.PRG_NAME,
2673 "properties for the input files (hmmpfam output) are expected "
2674 + "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 \""
2675 + names[ i ] + "\"" );
2678 final String error = ForesterUtil.isReadableFile( new File( input_file_properties[ i ][ 0 ] ) );
2679 if ( !ForesterUtil.isEmpty( error ) ) {
2680 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
2683 return input_file_properties;
2686 private static void processPlusMinusAnalysisOption( final CommandLineArguments cla,
2687 final List<String> high_copy_base,
2688 final List<String> high_copy_target,
2689 final List<String> low_copy,
2690 final List<Object> numbers ) {
2691 if ( cla.isOptionSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2692 if ( !cla.isOptionValueSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2693 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for 'plus-minus' file: -"
2694 + surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>" );
2696 final File plus_minus_file = new File( cla.getOptionValue( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) );
2697 final String msg = ForesterUtil.isReadableFile( plus_minus_file );
2698 if ( !ForesterUtil.isEmpty( msg ) ) {
2699 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + plus_minus_file + "\": " + msg );
2701 processPlusMinusFile( plus_minus_file, high_copy_base, high_copy_target, low_copy, numbers );
2705 // First numbers is minimal difference, second is factor.
2706 private static void processPlusMinusFile( final File plus_minus_file,
2707 final List<String> high_copy_base,
2708 final List<String> high_copy_target,
2709 final List<String> low_copy,
2710 final List<Object> numbers ) {
2711 Set<String> species_set = null;
2712 int min_diff = PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT;
2713 double factor = PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT;
2715 species_set = ForesterUtil.file2set( plus_minus_file );
2717 catch ( final IOException e ) {
2718 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2720 if ( species_set != null ) {
2721 for( final String species : species_set ) {
2722 final String species_trimmed = species.substring( 1 );
2723 if ( species.startsWith( "+" ) ) {
2724 if ( low_copy.contains( species_trimmed ) ) {
2725 ForesterUtil.fatalError( surfacing.PRG_NAME,
2726 "species/genome names can not appear with both '+' and '-' suffix, as appears the case for: \""
2727 + species_trimmed + "\"" );
2729 high_copy_base.add( species_trimmed );
2731 else if ( species.startsWith( "*" ) ) {
2732 if ( low_copy.contains( species_trimmed ) ) {
2733 ForesterUtil.fatalError( surfacing.PRG_NAME,
2734 "species/genome names can not appear with both '*' and '-' suffix, as appears the case for: \""
2735 + species_trimmed + "\"" );
2737 high_copy_target.add( species_trimmed );
2739 else if ( species.startsWith( "-" ) ) {
2740 if ( high_copy_base.contains( species_trimmed ) || high_copy_target.contains( species_trimmed ) ) {
2741 ForesterUtil.fatalError( surfacing.PRG_NAME,
2742 "species/genome names can not appear with both '+' or '*' and '-' suffix, as appears the case for: \""
2743 + species_trimmed + "\"" );
2745 low_copy.add( species_trimmed );
2747 else if ( species.startsWith( "$D" ) ) {
2749 min_diff = Integer.parseInt( species.substring( 3 ) );
2751 catch ( final NumberFormatException e ) {
2752 ForesterUtil.fatalError( surfacing.PRG_NAME,
2753 "could not parse integer value for minimal difference from: \""
2754 + species.substring( 3 ) + "\"" );
2757 else if ( species.startsWith( "$F" ) ) {
2759 factor = Double.parseDouble( species.substring( 3 ) );
2761 catch ( final NumberFormatException e ) {
2762 ForesterUtil.fatalError( surfacing.PRG_NAME, "could not parse double value for factor from: \""
2763 + species.substring( 3 ) + "\"" );
2766 else if ( species.startsWith( "#" ) ) {
2771 .fatalError( surfacing.PRG_NAME,
2772 "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: \""
2775 numbers.add( new Integer( min_diff + "" ) );
2776 numbers.add( new Double( factor + "" ) );
2780 ForesterUtil.fatalError( surfacing.PRG_NAME, "'plus minus' file [" + plus_minus_file + "] appears empty" );
2784 private static void writePresentToNexus( final File output_file,
2785 final File positive_filter_file,
2786 final SortedSet<DomainId> filter,
2787 final List<GenomeWideCombinableDomains> gwcd_list ) {
2790 .writeMatrixToFile( DomainParsimonyCalculator
2791 .createMatrixOfDomainPresenceOrAbsence( gwcd_list, positive_filter_file == null ? null
2792 : filter ), output_file + DOMAINS_PRESENT_NEXUS, Format.NEXUS_BINARY );
2793 SurfacingUtil.writeMatrixToFile( DomainParsimonyCalculator
2794 .createMatrixOfBinaryDomainCombinationPresenceOrAbsence( gwcd_list ), output_file
2795 + BDC_PRESENT_NEXUS, Format.NEXUS_BINARY );
2797 catch ( final Exception e ) {
2798 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2802 private static void writeProteinListsForAllSpecies( final File output_dir,
2803 final SortedMap<Species, List<Protein>> protein_lists_per_species,
2804 final List<GenomeWideCombinableDomains> gwcd_list ) {
2805 final SortedSet<DomainId> all_domains = new TreeSet<DomainId>();
2806 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
2807 all_domains.addAll( gwcd.getAllDomainIds() );
2809 for( final DomainId domain : all_domains ) {
2810 final File out = new File( output_dir + ForesterUtil.FILE_SEPARATOR + domain + SEQ_EXTRACT_SUFFIX );
2811 SurfacingUtil.checkForOutputFileWriteability( out );
2813 final Writer proteins_file_writer = new BufferedWriter( new FileWriter( out ) );
2814 SurfacingUtil.extractProteinNames( protein_lists_per_species,
2816 proteins_file_writer,
2818 LIMIT_SPEC_FOR_PROT_EX );
2819 proteins_file_writer.close();
2821 catch ( final IOException e ) {
2822 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2824 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote proteins list to \"" + out + "\"" );