3 // FORESTER -- software libraries and applications
4 // for evolutionary biology research and applications.
6 // Copyright (C) 2008-2009 Christian M. Zmasek
7 // Copyright (C) 2008-2009 Burnham Institute for Medical Research
10 // This library is free software; you can redistribute it and/or
11 // modify it under the terms of the GNU Lesser General Public
12 // License as published by the Free Software Foundation; either
13 // version 2.1 of the License, or (at your option) any later version.
15 // This library is distributed in the hope that it will be useful,
16 // but WITHOUT ANY WARRANTY; without even the implied warranty of
17 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
18 // Lesser General Public License for more details.
20 // You should have received a copy of the GNU Lesser General Public
21 // License along with this library; if not, write to the Free Software
22 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
24 // Contact: phylosoft @ gmail . com
25 // WWW: https://sites.google.com/site/cmzmasek/home/software/forester
27 package org.forester.application;
29 import java.io.BufferedWriter;
31 import java.io.FileWriter;
32 import java.io.IOException;
33 import java.io.Writer;
34 import java.util.ArrayList;
35 import java.util.Date;
36 import java.util.HashMap;
37 import java.util.HashSet;
38 import java.util.List;
40 import java.util.Map.Entry;
42 import java.util.SortedMap;
43 import java.util.SortedSet;
44 import java.util.TreeMap;
45 import java.util.TreeSet;
47 import org.forester.evoinference.matrix.character.CharacterStateMatrix.Format;
48 import org.forester.go.GoId;
49 import org.forester.go.GoNameSpace;
50 import org.forester.go.GoTerm;
51 import org.forester.go.GoUtils;
52 import org.forester.go.OBOparser;
53 import org.forester.go.PfamToGoMapping;
54 import org.forester.go.PfamToGoParser;
55 import org.forester.io.parsers.HmmscanPerDomainTableParser;
56 import org.forester.io.parsers.HmmscanPerDomainTableParser.INDIVIDUAL_SCORE_CUTOFF;
57 import org.forester.io.parsers.phyloxml.PhyloXmlUtil;
58 import org.forester.io.parsers.util.ParserUtils;
59 import org.forester.phylogeny.Phylogeny;
60 import org.forester.phylogeny.PhylogenyMethods;
61 import org.forester.phylogeny.PhylogenyNode;
62 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
63 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
64 import org.forester.protein.BinaryDomainCombination;
65 import org.forester.protein.Domain;
66 import org.forester.protein.DomainId;
67 import org.forester.protein.Protein;
68 import org.forester.species.BasicSpecies;
69 import org.forester.species.Species;
70 import org.forester.surfacing.BasicDomainSimilarityCalculator;
71 import org.forester.surfacing.BasicGenomeWideCombinableDomains;
72 import org.forester.surfacing.CombinationsBasedPairwiseDomainSimilarityCalculator;
73 import org.forester.surfacing.DomainCountsBasedPairwiseSimilarityCalculator;
74 import org.forester.surfacing.DomainCountsDifferenceUtil;
75 import org.forester.surfacing.DomainLengthsTable;
76 import org.forester.surfacing.DomainParsimonyCalculator;
77 import org.forester.surfacing.DomainSimilarity;
78 import org.forester.surfacing.DomainSimilarity.DomainSimilarityScoring;
79 import org.forester.surfacing.DomainSimilarity.DomainSimilaritySortField;
80 import org.forester.surfacing.DomainSimilarityCalculator;
81 import org.forester.surfacing.DomainSimilarityCalculator.Detailedness;
82 import org.forester.surfacing.GenomeWideCombinableDomains;
83 import org.forester.surfacing.GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder;
84 import org.forester.surfacing.MappingResults;
85 import org.forester.surfacing.PairwiseDomainSimilarityCalculator;
86 import org.forester.surfacing.PairwiseGenomeComparator;
87 import org.forester.surfacing.PrintableDomainSimilarity;
88 import org.forester.surfacing.PrintableDomainSimilarity.PRINT_OPTION;
89 import org.forester.surfacing.ProteinCountsBasedPairwiseDomainSimilarityCalculator;
90 import org.forester.surfacing.SurfacingUtil;
91 import org.forester.util.BasicDescriptiveStatistics;
92 import org.forester.util.BasicTable;
93 import org.forester.util.BasicTableParser;
94 import org.forester.util.CommandLineArguments;
95 import org.forester.util.DescriptiveStatistics;
96 import org.forester.util.ForesterConstants;
97 import org.forester.util.ForesterUtil;
99 public class surfacing {
101 private static final int MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING = 1000;
102 public final static String DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS = "graph_analysis_out";
103 public final static String DOMAIN_COMBINITONS_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_dc.dot";
104 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_fitch_present_dc.dot";
105 public final static String DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX = ".dcc";
107 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS = "_dollo_gl_d";
108 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_gl_dc";
109 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_DOMAINS = "_fitch_gl_d";
110 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_gl_dc";
112 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS = "_dollo_glc_d";
113 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_glc_dc";
114 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_DOMAINS = "_fitch_glc_d";
115 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_glc_dc";
117 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_BC = "_fitch_gains_dc";
118 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_HTML_BC = "_fitch_gains_dc.html";
119 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_BC = "_fitch_losses_dc";
120 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_HTML_BC = "_fitch_losses_dc.html";
121 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC = "_fitch_present_dc";
122 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_HTML_BC = "_fitch_present_dc.html";
123 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_D = "_dollo_gains_d";
124 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_HTML_D = "_dollo_gains_d.html";
125 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_D = "_dollo_losses_d";
126 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_HTML_D = "_dollo_losses_d.html";
127 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_D = "_dollo_present_d";
128 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_HTML_D = "_dollo_present_d.html";
129 public final static String DOMAINS_PRESENT_NEXUS = "_dom.nex";
130 public final static String BDC_PRESENT_NEXUS = "_dc.nex";
132 public final static String PRG_NAME = "surfacing";
133 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_d_dollo"
134 + ForesterConstants.PHYLO_XML_SUFFIX;
135 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_d_fitch"
136 + ForesterConstants.PHYLO_XML_SUFFIX;
137 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_dc_dollo"
138 + ForesterConstants.PHYLO_XML_SUFFIX;
139 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_dc_fitch"
140 + ForesterConstants.PHYLO_XML_SUFFIX;
141 public static final String NEXUS_EXTERNAL_DOMAINS = "_dom.nex";
142 public static final String NEXUS_EXTERNAL_DOMAIN_COMBINATIONS = "_dc.nex";
143 public static final String NEXUS_SECONDARY_FEATURES = "_secondary_features.nex";
144 public static final String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_gl_secondary_features";
145 public static final String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_glc_secondary_features";
146 public static final String PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES = "_dollo_gains_secondary_features";
147 public static final String PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES = "_dollo_losses_secondary_features";
148 public static final String PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES = "_dollo_present_secondary_features";
149 public static final String SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_secondary_features_dollo"
150 + ForesterConstants.PHYLO_XML_SUFFIX;
151 public static final String PARSIMONY_OUTPUT_DOLLO_ALL_GOID_D_ALL_NAMESPACES = "_dollo_goid_d";
152 public static final String PARSIMONY_OUTPUT_FITCH_ALL_GOID_BC_ALL_NAMESPACES = "_fitch_goid_dc";
153 final static private String HELP_OPTION_1 = "help";
154 final static private String HELP_OPTION_2 = "h";
155 final static private String OUTPUT_DIR_OPTION = "out_dir";
156 final static private String SCORING_OPTION = "scoring";
157 private static final DomainSimilarityScoring SCORING_DEFAULT = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
158 final static private String SCORING_DOMAIN_COUNT_BASED = "domains";
159 final static private String SCORING_PROTEIN_COUNT_BASED = "proteins";
160 final static private String SCORING_COMBINATION_BASED = "combinations";
161 final static private String DETAILEDNESS_OPTION = "detail";
162 private final static Detailedness DETAILEDNESS_DEFAULT = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
163 final static private String SPECIES_MATRIX_OPTION = "smatrix";
164 final static private String DETAILEDNESS_BASIC = "basic";
165 final static private String DETAILEDNESS_LIST_IDS = "list_ids";
166 final static private String DETAILEDNESS_PUNCTILIOUS = "punctilious";
167 final static private String DOMAIN_SIMILARITY_SORT_OPTION = "sort";
168 private static final DomainSimilaritySortField DOMAIN_SORT_FILD_DEFAULT = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
169 final static private String DOMAIN_SIMILARITY_SORT_MIN = "min";
170 final static private String DOMAIN_SIMILARITY_SORT_MAX = "max";
171 final static private String DOMAIN_SIMILARITY_SORT_SD = "sd";
172 final static private String DOMAIN_SIMILARITY_SORT_MEAN = "mean";
173 final static private String DOMAIN_SIMILARITY_SORT_DIFF = "diff";
174 final static private String DOMAIN_SIMILARITY_SORT_COUNTS_DIFF = "count_diff";
175 final static private String DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF = "abs_count_diff";
176 final static private String DOMAIN_SIMILARITY_SORT_SPECIES_COUNT = "species";
177 final static private String DOMAIN_SIMILARITY_SORT_ALPHA = "alpha";
178 final static private String DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION = "species_first";
179 final static private String DOMAIN_COUNT_SORT_OPTION = "dc_sort";
180 private static final GenomeWideCombinableDomainsSortOrder DOMAINS_SORT_ORDER_DEFAULT = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
181 final static private String DOMAIN_COUNT_SORT_ALPHA = "alpha";
182 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT = "dom";
183 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT = "prot";
184 final static private String DOMAIN_COUNT_SORT_COMBINATIONS_COUNT = "comb";
185 final static private String CUTOFF_SCORE_FILE_OPTION = "cos";
186 final static private String NOT_IGNORE_DUFS_OPTION = "dufs";
187 final static private String MAX_E_VALUE_OPTION = "e";
188 final static private String MAX_ALLOWED_OVERLAP_OPTION = "mo";
189 final static private String NO_ENGULFING_OVERLAP_OPTION = "no_eo";
190 final static private String IGNORE_COMBINATION_WITH_SAME_OPTION = "ignore_self_comb";
191 final static private String PAIRWISE_DOMAIN_COMPARISONS_PREFIX = "pwc_";
192 final static private String PAIRWISE_DOMAIN_COMPARISONS_OPTION = "pwc";
193 final static private String OUTPUT_FILE_OPTION = "o";
194 final static private String PFAM_TO_GO_FILE_USE_OPTION = "p2g";
195 final static private String GO_OBO_FILE_USE_OPTION = "obo";
196 final static private String GO_NAMESPACE_LIMIT_OPTION = "go_namespace";
197 final static private String GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION = "molecular_function";
198 final static private String GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS = "biological_process";
199 final static private String GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT = "cellular_component";
200 final static private String SECONDARY_FEATURES_PARSIMONY_MAP_FILE = "secondary";
201 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED = "simple_tab";
202 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML = "simple_html";
203 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML = "detailed_html";
204 final static private String DOMAIN_SIMILARITY_PRINT_OPTION = "ds_output";
205 private static final PRINT_OPTION DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT = PrintableDomainSimilarity.PRINT_OPTION.HTML;
206 final static private String IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION = "ignore_singlet_domains";
207 final static private String IGNORE_VIRAL_IDS = "ignore_viral_ids";
208 final static private boolean IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT = false;
209 final static private String IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION = "ignore_species_specific_domains";
210 final static private boolean IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT = false;
211 final static private String MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score.pwd";
212 final static private String MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains.pwd";
213 final static private String MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations.pwd";
214 final static private String NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score_NJ"
215 + ForesterConstants.PHYLO_XML_SUFFIX;
216 final static private String NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains_NJ"
217 + ForesterConstants.PHYLO_XML_SUFFIX;
218 final static private String NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations_NJ"
219 + ForesterConstants.PHYLO_XML_SUFFIX;
220 final static private String JACKNIFE_OPTION = "jack";
221 final static private String JACKNIFE_RANDOM_SEED_OPTION = "seed";
222 final static private String JACKNIFE_RATIO_OPTION = "jack_ratio";
223 private static final int JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT = 100;
224 final static private long JACKNIFE_RANDOM_SEED_DEFAULT = 19;
225 final static private double JACKNIFE_RATIO_DEFAULT = 0.5;
226 final static private String FILTER_POSITIVE_OPTION = "pos_filter";
227 final static private String FILTER_NEGATIVE_OPTION = "neg_filter";
228 final static private String FILTER_NEGATIVE_DOMAINS_OPTION = "neg_dom_filter";
229 final static private String INPUT_GENOMES_FILE_OPTION = "genomes";
230 final static private String INPUT_SPECIES_TREE_OPTION = "species_tree";
231 final static private String SEQ_EXTRACT_OPTION = "prot_extract";
232 final static private String PRG_VERSION = "2.260";
233 final static private String PRG_DATE = "130721";
234 final static private String E_MAIL = "czmasek@burnham.org";
235 final static private String WWW = "www.phylosoft.org/forester/applications/surfacing";
236 final static private boolean IGNORE_DUFS_DEFAULT = true;
237 final static private boolean IGNORE_COMBINATION_WITH_SAME_DEFAULLT = false;
238 final static private double MAX_E_VALUE_DEFAULT = -1;
239 final static private int MAX_ALLOWED_OVERLAP_DEFAULT = -1;
240 private static final String RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION = "random_seed";
241 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS = "consider_bdc_direction";
242 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY = "consider_bdc_adj";
243 private static final String SEQ_EXTRACT_SUFFIX = ".prot";
244 private static final String PLUS_MINUS_ANALYSIS_OPTION = "plus_minus";
245 private static final String PLUS_MINUS_DOM_SUFFIX = "_plus_minus_dom.txt";
246 private static final String PLUS_MINUS_DOM_SUFFIX_HTML = "_plus_minus_dom.html";
247 private static final String PLUS_MINUS_DC_SUFFIX_HTML = "_plus_minus_dc.html";
248 private static final int PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT = 0;
249 private static final double PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT = 1.0;
250 private static final String PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_all.txt";
251 private static final String PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_passing.txt";
252 private static final String OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS = "all_prot";
253 final static private String OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION = "all_prot_e";
254 private static final boolean VERBOSE = false;
255 private static final String OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_gains_counts";
256 private static final String OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_losses_counts";
257 private static final String DOMAIN_LENGTHS_ANALYSIS_SUFFIX = "_domain_lengths_analysis";
258 private static final boolean PERFORM_DOMAIN_LENGTH_ANALYSIS = true;
259 public static final String ALL_PFAMS_ENCOUNTERED_SUFFIX = "_all_encountered_pfams";
260 public static final String ALL_PFAMS_ENCOUNTERED_WITH_GO_ANNOTATION_SUFFIX = "_all_encountered_pfams_with_go_annotation";
261 public static final String ENCOUNTERED_PFAMS_SUMMARY_SUFFIX = "_encountered_pfams_summary";
262 public static final String ALL_PFAMS_GAINED_AS_DOMAINS_SUFFIX = "_all_pfams_gained_as_domains";
263 public static final String ALL_PFAMS_LOST_AS_DOMAINS_SUFFIX = "_all_pfams_lost_as_domains";
264 public static final String ALL_PFAMS_GAINED_AS_DC_SUFFIX = "_all_pfams_gained_as_dc";
265 public static final String ALL_PFAMS_LOST_AS_DC_SUFFIX = "_all_pfams_lost_as_dc";
266 public static final String BASE_DIRECTORY_PER_NODE_DOMAIN_GAIN_LOSS_FILES = "PER_NODE_EVENTS";
267 public static final String BASE_DIRECTORY_PER_SUBTREE_DOMAIN_GAIN_LOSS_FILES = "PER_SUBTREE_EVENTS";
268 public static final String D_PROMISCUITY_FILE_SUFFIX = "_domain_promiscuities";
269 private static final String LOG_FILE_SUFFIX = "_log.txt";
270 private static final String DATA_FILE_SUFFIX = "_domain_combination_data.txt";
271 private static final String DATA_FILE_DESC = "#SPECIES\tPRTEIN_ID\tN_TERM_DOMAIN\tC_TERM_DOMAIN\tN_TERM_DOMAIN_PER_DOMAIN_E_VALUE\tC_TERM_DOMAIN_PER_DOMAIN_E_VALUE\tN_TERM_DOMAIN_COUNTS_PER_PROTEIN\tC_TERM_DOMAIN_COUNTS_PER_PROTEIN";
272 private static final INDIVIDUAL_SCORE_CUTOFF INDIVIDUAL_SCORE_CUTOFF_DEFAULT = INDIVIDUAL_SCORE_CUTOFF.FULL_SEQUENCE; //TODO look at me! change?
273 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts.txt";
274 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists.txt";
275 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping.txt";
276 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";
277 public static final String LIMIT_SPEC_FOR_PROT_EX = null; // e.g. "HUMAN"; set to null for not using this feature (default).
278 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH_MAPPED = "_dc_MAPPED_secondary_features_fitch"
279 + ForesterConstants.PHYLO_XML_SUFFIX;
280 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts_MAPPED.txt";
281 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_MAPPED_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_MAPPED.txt";
282 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";
283 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";
284 private static final boolean PERFORM_DC_REGAIN_PROTEINS_STATS = true;
285 private static final boolean DA_ANALYSIS = false;
287 private static void checkWriteabilityForPairwiseComparisons( final PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option,
288 final String[][] input_file_properties,
289 final String automated_pairwise_comparison_suffix,
290 final File outdir ) {
291 for( int i = 0; i < input_file_properties.length; ++i ) {
292 for( int j = 0; j < i; ++j ) {
293 final String species_i = input_file_properties[ i ][ 1 ];
294 final String species_j = input_file_properties[ j ][ 1 ];
295 String pairwise_similarities_output_file_str = PAIRWISE_DOMAIN_COMPARISONS_PREFIX + species_i + "_"
296 + species_j + automated_pairwise_comparison_suffix;
297 switch ( domain_similarity_print_option ) {
299 if ( !pairwise_similarities_output_file_str.endsWith( ".html" ) ) {
300 pairwise_similarities_output_file_str += ".html";
304 final String error = ForesterUtil
305 .isWritableFile( new File( outdir == null ? pairwise_similarities_output_file_str : outdir
306 + ForesterUtil.FILE_SEPARATOR + pairwise_similarities_output_file_str ) );
307 if ( !ForesterUtil.isEmpty( error ) ) {
308 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
314 private static StringBuilder createParametersAsString( final boolean ignore_dufs,
315 final double e_value_max,
316 final int max_allowed_overlap,
317 final boolean no_engulfing_overlaps,
318 final File cutoff_scores_file,
319 final BinaryDomainCombination.DomainCombinationType dc_type ) {
320 final StringBuilder parameters_sb = new StringBuilder();
321 parameters_sb.append( "E-value: " + e_value_max );
322 if ( cutoff_scores_file != null ) {
323 parameters_sb.append( ", Cutoff-scores-file: " + cutoff_scores_file );
326 parameters_sb.append( ", Cutoff-scores-file: not-set" );
328 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
329 parameters_sb.append( ", Max-overlap: " + max_allowed_overlap );
332 parameters_sb.append( ", Max-overlap: not-set" );
334 if ( no_engulfing_overlaps ) {
335 parameters_sb.append( ", Engulfing-overlaps: not-allowed" );
338 parameters_sb.append( ", Engulfing-overlaps: allowed" );
341 parameters_sb.append( ", Ignore-dufs: true" );
344 parameters_sb.append( ", Ignore-dufs: false" );
346 parameters_sb.append( ", DC type (if applicable): " + dc_type );
347 return parameters_sb;
351 * Warning: This side-effects 'all_bin_domain_combinations_encountered'!
355 * @param all_bin_domain_combinations_changed
356 * @param sum_of_all_domains_encountered
357 * @param all_bin_domain_combinations_encountered
358 * @param is_gains_analysis
359 * @param protein_length_stats_by_dc
360 * @throws IOException
362 private static void executeFitchGainsAnalysis( final File output_file,
363 final List<BinaryDomainCombination> all_bin_domain_combinations_changed,
364 final int sum_of_all_domains_encountered,
365 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered,
366 final boolean is_gains_analysis ) throws IOException {
367 SurfacingUtil.checkForOutputFileWriteability( output_file );
368 final Writer out = ForesterUtil.createBufferedWriter( output_file );
369 final SortedMap<Object, Integer> bdc_to_counts = ForesterUtil
370 .listToSortedCountsMap( all_bin_domain_combinations_changed );
371 final SortedSet<DomainId> all_domains_in_combination_changed_more_than_once = new TreeSet<DomainId>();
372 final SortedSet<DomainId> all_domains_in_combination_changed_only_once = new TreeSet<DomainId>();
375 for( final Object bdc_object : bdc_to_counts.keySet() ) {
376 final BinaryDomainCombination bdc = ( BinaryDomainCombination ) bdc_object;
377 final int count = bdc_to_counts.get( bdc_object );
379 ForesterUtil.unexpectedFatalError( PRG_NAME, "count < 1 " );
381 out.write( bdc + "\t" + count + ForesterUtil.LINE_SEPARATOR );
383 all_domains_in_combination_changed_more_than_once.add( bdc.getId0() );
384 all_domains_in_combination_changed_more_than_once.add( bdc.getId1() );
387 else if ( count == 1 ) {
388 all_domains_in_combination_changed_only_once.add( bdc.getId0() );
389 all_domains_in_combination_changed_only_once.add( bdc.getId1() );
393 final int all = all_bin_domain_combinations_encountered.size();
395 if ( !is_gains_analysis ) {
396 all_bin_domain_combinations_encountered.removeAll( all_bin_domain_combinations_changed );
397 never_lost = all_bin_domain_combinations_encountered.size();
398 for( final BinaryDomainCombination bdc : all_bin_domain_combinations_encountered ) {
399 out.write( bdc + "\t" + "0" + ForesterUtil.LINE_SEPARATOR );
402 if ( is_gains_analysis ) {
403 out.write( "Sum of all distinct domain combinations appearing once : " + one
404 + ForesterUtil.LINE_SEPARATOR );
405 out.write( "Sum of all distinct domain combinations appearing more than once : " + above_one
406 + ForesterUtil.LINE_SEPARATOR );
407 out.write( "Sum of all distinct domains in combinations apppearing only once : "
408 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
409 out.write( "Sum of all distinct domains in combinations apppearing more than once: "
410 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
413 out.write( "Sum of all distinct domain combinations never lost : " + never_lost
414 + ForesterUtil.LINE_SEPARATOR );
415 out.write( "Sum of all distinct domain combinations lost once : " + one
416 + ForesterUtil.LINE_SEPARATOR );
417 out.write( "Sum of all distinct domain combinations lost more than once : " + above_one
418 + ForesterUtil.LINE_SEPARATOR );
419 out.write( "Sum of all distinct domains in combinations lost only once : "
420 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
421 out.write( "Sum of all distinct domains in combinations lost more than once: "
422 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
424 out.write( "All binary combinations : " + all
425 + ForesterUtil.LINE_SEPARATOR );
426 out.write( "All domains : "
427 + sum_of_all_domains_encountered );
429 ForesterUtil.programMessage( surfacing.PRG_NAME,
430 "Wrote fitch domain combination dynamics counts analysis to \"" + output_file
434 private static void executePlusMinusAnalysis( final File output_file,
435 final List<String> plus_minus_analysis_high_copy_base,
436 final List<String> plus_minus_analysis_high_copy_target,
437 final List<String> plus_minus_analysis_low_copy,
438 final List<GenomeWideCombinableDomains> gwcd_list,
439 final SortedMap<Species, List<Protein>> protein_lists_per_species,
440 final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
441 final Map<GoId, GoTerm> go_id_to_term_map,
442 final List<Object> plus_minus_analysis_numbers ) {
443 final Set<String> all_spec = new HashSet<String>();
444 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
445 all_spec.add( gwcd.getSpecies().getSpeciesId() );
447 final File html_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX_HTML );
448 final File plain_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX );
449 final File html_out_dc = new File( output_file + PLUS_MINUS_DC_SUFFIX_HTML );
450 final File all_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX );
451 final File passing_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX );
452 final File proteins_file_base = new File( output_file + "" );
453 final int min_diff = ( ( Integer ) plus_minus_analysis_numbers.get( 0 ) ).intValue();
454 final double factor = ( ( Double ) plus_minus_analysis_numbers.get( 1 ) ).doubleValue();
456 DomainCountsDifferenceUtil.calculateCopyNumberDifferences( gwcd_list,
457 protein_lists_per_species,
458 plus_minus_analysis_high_copy_base,
459 plus_minus_analysis_high_copy_target,
460 plus_minus_analysis_low_copy,
466 domain_id_to_go_ids_map,
468 all_domains_go_ids_out_dom,
469 passing_domains_go_ids_out_dom,
470 proteins_file_base );
472 catch ( final IOException e ) {
473 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
475 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
476 + html_out_dom + "\"" );
477 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
478 + plain_out_dom + "\"" );
479 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \"" + html_out_dc
481 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based passing GO ids to \""
482 + passing_domains_go_ids_out_dom + "\"" );
483 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based all GO ids to \""
484 + all_domains_go_ids_out_dom + "\"" );
487 private static Phylogeny[] getIntrees( final File[] intree_files,
488 final int number_of_genomes,
489 final String[][] input_file_properties ) {
490 final Phylogeny[] intrees = new Phylogeny[ intree_files.length ];
492 for( final File intree_file : intree_files ) {
493 Phylogeny intree = null;
494 final String error = ForesterUtil.isReadableFile( intree_file );
495 if ( !ForesterUtil.isEmpty( error ) ) {
496 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read input tree file [" + intree_file + "]: "
500 final Phylogeny[] p_array = ParserBasedPhylogenyFactory.getInstance()
501 .create( intree_file, ParserUtils.createParserDependingOnFileType( intree_file, true ) );
502 if ( p_array.length < 1 ) {
503 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
504 + "] does not contain any phylogeny in phyloXML format" );
506 else if ( p_array.length > 1 ) {
507 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
508 + "] contains more than one phylogeny in phyloXML format" );
510 intree = p_array[ 0 ];
512 catch ( final Exception e ) {
513 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read input tree from file [" + intree_file
516 if ( ( intree == null ) || intree.isEmpty() ) {
517 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" );
519 if ( !intree.isRooted() ) {
520 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is not rooted" );
522 if ( intree.getNumberOfExternalNodes() < number_of_genomes ) {
523 ForesterUtil.fatalError( surfacing.PRG_NAME,
524 "number of external nodes [" + intree.getNumberOfExternalNodes()
525 + "] of input tree [" + intree_file
526 + "] is smaller than the number of genomes the be analyzed ["
527 + number_of_genomes + "]" );
529 final StringBuilder parent_names = new StringBuilder();
530 final int nodes_lacking_name = SurfacingUtil.getNumberOfNodesLackingName( intree, parent_names );
531 if ( nodes_lacking_name > 0 ) {
532 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] has "
533 + nodes_lacking_name + " node(s) lacking a name [parent names:" + parent_names + "]" );
535 preparePhylogenyForParsimonyAnalyses( intree, input_file_properties );
536 if ( !intree.isCompletelyBinary() ) {
537 ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "input tree [" + intree_file
538 + "] is not completely binary" );
540 intrees[ i++ ] = intree;
545 private static void log( final String msg, final Writer w ) {
548 w.write( ForesterUtil.LINE_SEPARATOR );
550 catch ( final IOException e ) {
551 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
555 public static void main( final String args[] ) {
556 final long start_time = new Date().getTime();
557 // final StringBuffer log = new StringBuffer();
558 final StringBuilder html_desc = new StringBuilder();
559 ForesterUtil.printProgramInformation( surfacing.PRG_NAME,
560 surfacing.PRG_VERSION,
564 final String nl = ForesterUtil.LINE_SEPARATOR;
565 html_desc.append( "<table>" + nl );
566 html_desc.append( "<tr><td>Produced by:</td><td>" + surfacing.PRG_NAME + "</td></tr>" + nl );
567 html_desc.append( "<tr><td>Version:</td><td>" + surfacing.PRG_VERSION + "</td></tr>" + nl );
568 html_desc.append( "<tr><td>Release Date:</td><td>" + surfacing.PRG_DATE + "</td></tr>" + nl );
569 html_desc.append( "<tr><td>Contact:</td><td>" + surfacing.E_MAIL + "</td></tr>" + nl );
570 html_desc.append( "<tr><td>WWW:</td><td>" + surfacing.WWW + "</td></tr>" + nl );
571 CommandLineArguments cla = null;
573 cla = new CommandLineArguments( args );
575 catch ( final Exception e ) {
576 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
578 if ( cla.isOptionSet( surfacing.HELP_OPTION_1 ) || cla.isOptionSet( surfacing.HELP_OPTION_2 ) ) {
579 surfacing.printHelp();
582 if ( ( args.length < 1 ) ) {
583 surfacing.printHelp();
586 final List<String> allowed_options = new ArrayList<String>();
587 allowed_options.add( surfacing.NOT_IGNORE_DUFS_OPTION );
588 allowed_options.add( surfacing.MAX_E_VALUE_OPTION );
589 allowed_options.add( surfacing.DETAILEDNESS_OPTION );
590 allowed_options.add( surfacing.OUTPUT_FILE_OPTION );
591 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_OPTION );
592 allowed_options.add( surfacing.SPECIES_MATRIX_OPTION );
593 allowed_options.add( surfacing.SCORING_OPTION );
594 allowed_options.add( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
595 allowed_options.add( surfacing.NO_ENGULFING_OVERLAP_OPTION );
596 allowed_options.add( surfacing.DOMAIN_COUNT_SORT_OPTION );
597 allowed_options.add( surfacing.CUTOFF_SCORE_FILE_OPTION );
598 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION );
599 allowed_options.add( surfacing.OUTPUT_DIR_OPTION );
600 allowed_options.add( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION );
601 allowed_options.add( surfacing.PFAM_TO_GO_FILE_USE_OPTION );
602 allowed_options.add( surfacing.GO_OBO_FILE_USE_OPTION );
603 allowed_options.add( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION );
604 allowed_options.add( surfacing.GO_NAMESPACE_LIMIT_OPTION );
605 allowed_options.add( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
606 allowed_options.add( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION );
607 allowed_options.add( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS );
608 allowed_options.add( JACKNIFE_OPTION );
609 allowed_options.add( JACKNIFE_RANDOM_SEED_OPTION );
610 allowed_options.add( JACKNIFE_RATIO_OPTION );
611 allowed_options.add( INPUT_SPECIES_TREE_OPTION );
612 allowed_options.add( FILTER_POSITIVE_OPTION );
613 allowed_options.add( FILTER_NEGATIVE_OPTION );
614 allowed_options.add( INPUT_GENOMES_FILE_OPTION );
615 allowed_options.add( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
616 allowed_options.add( FILTER_NEGATIVE_DOMAINS_OPTION );
617 allowed_options.add( IGNORE_VIRAL_IDS );
618 allowed_options.add( SEQ_EXTRACT_OPTION );
619 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
620 allowed_options.add( SECONDARY_FEATURES_PARSIMONY_MAP_FILE );
621 allowed_options.add( PLUS_MINUS_ANALYSIS_OPTION );
622 allowed_options.add( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS );
623 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS );
624 allowed_options.add( CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY );
625 boolean ignore_dufs = surfacing.IGNORE_DUFS_DEFAULT;
626 boolean ignore_combination_with_same = surfacing.IGNORE_COMBINATION_WITH_SAME_DEFAULLT;
627 double e_value_max = surfacing.MAX_E_VALUE_DEFAULT;
628 int max_allowed_overlap = surfacing.MAX_ALLOWED_OVERLAP_DEFAULT;
629 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
630 if ( dissallowed_options.length() > 0 ) {
631 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown option(s): " + dissallowed_options );
633 boolean output_binary_domain_combinationsfor_graph_analysis = false;
634 if ( cla.isOptionSet( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS ) ) {
635 output_binary_domain_combinationsfor_graph_analysis = true;
637 if ( cla.isOptionSet( surfacing.MAX_E_VALUE_OPTION ) ) {
639 e_value_max = cla.getOptionValueAsDouble( surfacing.MAX_E_VALUE_OPTION );
641 catch ( final Exception e ) {
642 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for E-value maximum" );
645 if ( cla.isOptionSet( surfacing.MAX_ALLOWED_OVERLAP_OPTION ) ) {
647 max_allowed_overlap = cla.getOptionValueAsInt( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
649 catch ( final Exception e ) {
650 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for maximal allowed domain overlap" );
653 boolean no_engulfing_overlaps = false;
654 if ( cla.isOptionSet( surfacing.NO_ENGULFING_OVERLAP_OPTION ) ) {
655 no_engulfing_overlaps = true;
657 boolean ignore_virus_like_ids = false;
658 if ( cla.isOptionSet( surfacing.IGNORE_VIRAL_IDS ) ) {
659 ignore_virus_like_ids = true;
661 if ( cla.isOptionSet( surfacing.NOT_IGNORE_DUFS_OPTION ) ) {
664 if ( cla.isOptionSet( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION ) ) {
665 ignore_combination_with_same = true;
667 boolean ignore_domains_without_combs_in_all_spec = IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT;
668 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION ) ) {
669 ignore_domains_without_combs_in_all_spec = true;
671 boolean ignore_species_specific_domains = IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT;
672 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION ) ) {
673 ignore_species_specific_domains = true;
675 File output_file = null;
676 if ( cla.isOptionSet( surfacing.OUTPUT_FILE_OPTION ) ) {
677 if ( !cla.isOptionValueSet( surfacing.OUTPUT_FILE_OPTION ) ) {
678 ForesterUtil.fatalError( surfacing.PRG_NAME,
679 "no value for domain combinations similarities output file: -"
680 + surfacing.OUTPUT_FILE_OPTION + "=<file>" );
682 output_file = new File( cla.getOptionValue( surfacing.OUTPUT_FILE_OPTION ) );
683 SurfacingUtil.checkForOutputFileWriteability( output_file );
685 File cutoff_scores_file = null;
686 Map<String, Double> individual_score_cutoffs = null;
687 if ( cla.isOptionSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
688 if ( !cla.isOptionValueSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
689 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for individual domain score cutoffs file: -"
690 + surfacing.CUTOFF_SCORE_FILE_OPTION + "=<file>" );
692 cutoff_scores_file = new File( cla.getOptionValue( surfacing.CUTOFF_SCORE_FILE_OPTION ) );
693 final String error = ForesterUtil.isReadableFile( cutoff_scores_file );
694 if ( !ForesterUtil.isEmpty( error ) ) {
695 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read individual domain score cutoffs file: "
699 final BasicTable<String> scores_table = BasicTableParser.parse( cutoff_scores_file, ' ' );
700 individual_score_cutoffs = scores_table.getColumnsAsMapDouble( 0, 1 );
702 catch ( final IOException e ) {
703 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from individual score cutoffs file: " + e );
706 BinaryDomainCombination.DomainCombinationType dc_type = BinaryDomainCombination.DomainCombinationType.BASIC;
707 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS ) ) {
708 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED;
710 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY ) ) {
711 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT;
714 if ( cla.isOptionSet( surfacing.OUTPUT_DIR_OPTION ) ) {
715 if ( !cla.isOptionValueSet( surfacing.OUTPUT_DIR_OPTION ) ) {
716 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for output directory: -"
717 + surfacing.OUTPUT_DIR_OPTION + "=<dir>" );
719 out_dir = new File( cla.getOptionValue( surfacing.OUTPUT_DIR_OPTION ) );
720 if ( out_dir.exists() && ( out_dir.listFiles().length > 0 ) ) {
721 ForesterUtil.fatalError( surfacing.PRG_NAME, "\"" + out_dir + "\" aready exists and is not empty" );
723 if ( !out_dir.exists() ) {
724 final boolean success = out_dir.mkdir();
725 if ( !success || !out_dir.exists() ) {
726 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to create \"" + out_dir + "\"" );
729 if ( !out_dir.canWrite() ) {
730 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot write to \"" + out_dir + "\"" );
733 File positive_filter_file = null;
734 File negative_filter_file = null;
735 File negative_domains_filter_file = null;
736 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) && cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
737 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use both negative and positive protein filter" );
739 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION )
740 && ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) || cla
741 .isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) ) {
743 .fatalError( surfacing.PRG_NAME,
744 "attempt to use both negative or positive protein filter together wirh a negative domains filter" );
746 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
747 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
748 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative filter: -"
749 + surfacing.FILTER_NEGATIVE_OPTION + "=<file>" );
751 negative_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_OPTION ) );
752 final String msg = ForesterUtil.isReadableFile( negative_filter_file );
753 if ( !ForesterUtil.isEmpty( msg ) ) {
754 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_filter_file + "\": "
758 else if ( cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
759 if ( !cla.isOptionValueSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
760 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for positive filter: -"
761 + surfacing.FILTER_POSITIVE_OPTION + "=<file>" );
763 positive_filter_file = new File( cla.getOptionValue( surfacing.FILTER_POSITIVE_OPTION ) );
764 final String msg = ForesterUtil.isReadableFile( positive_filter_file );
765 if ( !ForesterUtil.isEmpty( msg ) ) {
766 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + positive_filter_file + "\": "
770 else if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
771 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
772 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative domains filter: -"
773 + surfacing.FILTER_NEGATIVE_DOMAINS_OPTION + "=<file>" );
775 negative_domains_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) );
776 final String msg = ForesterUtil.isReadableFile( negative_domains_filter_file );
777 if ( !ForesterUtil.isEmpty( msg ) ) {
778 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_domains_filter_file
782 final List<String> plus_minus_analysis_high_copy_base_species = new ArrayList<String>();
783 final List<String> plus_minus_analysis_high_copy_target_species = new ArrayList<String>();
784 final List<String> plus_minus_analysis_high_low_copy_species = new ArrayList<String>();
785 final List<Object> plus_minus_analysis_numbers = new ArrayList<Object>();
786 processPlusMinusAnalysisOption( cla,
787 plus_minus_analysis_high_copy_base_species,
788 plus_minus_analysis_high_copy_target_species,
789 plus_minus_analysis_high_low_copy_species,
790 plus_minus_analysis_numbers );
791 File input_genomes_file = null;
792 if ( cla.isOptionSet( surfacing.INPUT_GENOMES_FILE_OPTION ) ) {
793 if ( !cla.isOptionValueSet( surfacing.INPUT_GENOMES_FILE_OPTION ) ) {
794 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input genomes file: -"
795 + surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>" );
797 input_genomes_file = new File( cla.getOptionValue( surfacing.INPUT_GENOMES_FILE_OPTION ) );
798 final String msg = ForesterUtil.isReadableFile( input_genomes_file );
799 if ( !ForesterUtil.isEmpty( msg ) ) {
801 .fatalError( surfacing.PRG_NAME, "can not read from \"" + input_genomes_file + "\": " + msg );
805 ForesterUtil.fatalError( surfacing.PRG_NAME, "no input genomes file given: "
806 + surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>" );
808 DomainSimilarity.DomainSimilarityScoring scoring = SCORING_DEFAULT;
809 if ( cla.isOptionSet( surfacing.SCORING_OPTION ) ) {
810 if ( !cla.isOptionValueSet( surfacing.SCORING_OPTION ) ) {
811 ForesterUtil.fatalError( surfacing.PRG_NAME,
812 "no value for scoring method for domain combinations similarity calculation: -"
813 + surfacing.SCORING_OPTION + "=<"
814 + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
815 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|"
816 + surfacing.SCORING_COMBINATION_BASED + ">\"" );
818 final String scoring_str = cla.getOptionValue( surfacing.SCORING_OPTION );
819 if ( scoring_str.equals( surfacing.SCORING_DOMAIN_COUNT_BASED ) ) {
820 scoring = DomainSimilarity.DomainSimilarityScoring.DOMAINS;
822 else if ( scoring_str.equals( surfacing.SCORING_COMBINATION_BASED ) ) {
823 scoring = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
825 else if ( scoring_str.equals( surfacing.SCORING_PROTEIN_COUNT_BASED ) ) {
826 scoring = DomainSimilarity.DomainSimilarityScoring.PROTEINS;
829 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + scoring_str
830 + "\" for scoring method for domain combinations similarity calculation: \"-"
831 + surfacing.SCORING_OPTION + "=<" + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
832 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|" + surfacing.SCORING_COMBINATION_BASED + ">\"" );
835 boolean sort_by_species_count_first = false;
836 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION ) ) {
837 sort_by_species_count_first = true;
839 boolean species_matrix = false;
840 if ( cla.isOptionSet( surfacing.SPECIES_MATRIX_OPTION ) ) {
841 species_matrix = true;
843 boolean output_protein_lists_for_all_domains = false;
844 double output_list_of_all_proteins_per_domain_e_value_max = -1;
845 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS ) ) {
846 output_protein_lists_for_all_domains = true;
847 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION ) ) {
849 output_list_of_all_proteins_per_domain_e_value_max = cla
850 .getOptionValueAsDouble( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION );
852 catch ( final Exception e ) {
853 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for per domain E-value maximum" );
857 Detailedness detailedness = DETAILEDNESS_DEFAULT;
858 if ( cla.isOptionSet( surfacing.DETAILEDNESS_OPTION ) ) {
859 if ( !cla.isOptionValueSet( surfacing.DETAILEDNESS_OPTION ) ) {
860 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for -" + surfacing.DETAILEDNESS_OPTION + "=<"
861 + surfacing.DETAILEDNESS_BASIC + "|" + surfacing.DETAILEDNESS_LIST_IDS + "|"
862 + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
864 final String detness = cla.getOptionValue( surfacing.DETAILEDNESS_OPTION ).toLowerCase();
865 if ( detness.equals( surfacing.DETAILEDNESS_BASIC ) ) {
866 detailedness = DomainSimilarityCalculator.Detailedness.BASIC;
868 else if ( detness.equals( surfacing.DETAILEDNESS_LIST_IDS ) ) {
869 detailedness = DomainSimilarityCalculator.Detailedness.LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES;
871 else if ( detness.equals( surfacing.DETAILEDNESS_PUNCTILIOUS ) ) {
872 detailedness = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
875 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + detness + "\" for detailedness: \"-"
876 + surfacing.DETAILEDNESS_OPTION + "=<" + surfacing.DETAILEDNESS_BASIC + "|"
877 + surfacing.DETAILEDNESS_LIST_IDS + "|" + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
880 String automated_pairwise_comparison_suffix = null;
881 boolean perform_pwc = false;
882 boolean write_pwc_files = false;
883 if ( cla.isOptionSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
885 if ( !cla.isOptionValueSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
886 write_pwc_files = false;
889 write_pwc_files = true;
890 automated_pairwise_comparison_suffix = "_"
891 + cla.getOptionValue( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
894 String query_domain_ids = null;
895 if ( cla.isOptionSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
896 if ( !cla.isOptionValueSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
898 .fatalError( surfacing.PRG_NAME,
899 "no domain ids given for sequences with given domains to be extracted : -"
900 + surfacing.SEQ_EXTRACT_OPTION
901 + "=<ordered domain sequences, domain ids separated by '~', sequences separated by '#'>" );
903 query_domain_ids = cla.getOptionValue( surfacing.SEQ_EXTRACT_OPTION );
905 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field = DOMAIN_SORT_FILD_DEFAULT;
906 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field_for_automated_pwc = DOMAIN_SORT_FILD_DEFAULT;
907 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
908 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
909 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for domain combinations similarities sorting: -"
910 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
911 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
912 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
913 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
914 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|"
915 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
918 final String sort_str = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ).toLowerCase();
919 if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ALPHA ) ) {
920 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
921 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
923 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MAX ) ) {
924 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX;
925 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
927 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MIN ) ) {
928 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MIN;
929 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
931 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MEAN ) ) {
932 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MEAN;
933 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MEAN;
935 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT ) ) {
936 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SPECIES_COUNT;
937 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
939 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SD ) ) {
940 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SD;
941 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
943 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_DIFF ) ) {
944 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
945 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
947 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF ) ) {
948 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
949 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
951 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF ) ) {
952 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
953 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
956 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort_str
957 + "\" for domain combinations similarities sorting: \"-"
958 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
959 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
960 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
961 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
962 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|" + "|"
963 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
967 PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option = DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT;
968 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
969 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
970 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for print option: -"
971 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
972 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
973 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
975 final String sort = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ).toLowerCase();
976 if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML ) ) {
977 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.HTML;
979 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML ) ) {
980 ForesterUtil.fatalError( surfacing.PRG_NAME, "simple HTML output not implemented yet :(" );
982 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED ) ) {
983 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.SIMPLE_TAB_DELIMITED;
986 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort + "\" for print option: -"
987 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
988 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
989 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
992 GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order = DOMAINS_SORT_ORDER_DEFAULT;
993 if ( cla.isOptionSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
994 if ( !cla.isOptionValueSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
995 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for sorting of domain counts: -"
996 + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<" + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|"
997 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
998 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
999 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1001 final String sort = cla.getOptionValue( surfacing.DOMAIN_COUNT_SORT_OPTION ).toLowerCase();
1002 if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_ALPHA ) ) {
1003 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
1005 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT ) ) {
1006 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_COUNT;
1008 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT ) ) {
1009 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_PROTEINS_COUNT;
1011 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT ) ) {
1012 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.COMBINATIONS_COUNT;
1015 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort
1016 + "\" for sorting of domain counts: \"-" + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<"
1017 + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|" + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1018 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1019 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1022 final String[][] input_file_properties = processInputGenomesFile( input_genomes_file );
1023 // for( final String[] input_file_propertie : input_file_properties ) {
1024 // for( final String element : input_file_propertie ) {
1025 // System.out.print( element + " " );
1027 // System.out.println();
1029 final int number_of_genomes = input_file_properties.length;
1030 if ( number_of_genomes < 2 ) {
1031 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot analyze less than two files" );
1033 if ( ( number_of_genomes < 3 ) && perform_pwc ) {
1034 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use : -"
1035 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1036 + "=<suffix> to turn on pairwise analyses with less than three input files" );
1038 checkWriteabilityForPairwiseComparisons( domain_similarity_print_option,
1039 input_file_properties,
1040 automated_pairwise_comparison_suffix,
1042 for( int i = 0; i < number_of_genomes; i++ ) {
1043 File dcc_outfile = new File( input_file_properties[ i ][ 1 ]
1044 + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
1045 if ( out_dir != null ) {
1046 dcc_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + dcc_outfile );
1048 SurfacingUtil.checkForOutputFileWriteability( dcc_outfile );
1050 File pfam_to_go_file = null;
1051 Map<DomainId, List<GoId>> domain_id_to_go_ids_map = null;
1052 int domain_id_to_go_ids_count = 0;
1053 if ( cla.isOptionSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1054 if ( !cla.isOptionValueSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1055 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for Pfam to GO mapping file: -"
1056 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>" );
1058 pfam_to_go_file = new File( cla.getOptionValue( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) );
1059 final String error = ForesterUtil.isReadableFile( pfam_to_go_file );
1060 if ( !ForesterUtil.isEmpty( error ) ) {
1061 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read Pfam to GO mapping file: " + error );
1064 final PfamToGoParser parser = new PfamToGoParser( pfam_to_go_file );
1065 final List<PfamToGoMapping> pfam_to_go_mappings = parser.parse();
1066 domain_id_to_go_ids_map = SurfacingUtil.createDomainIdToGoIdMap( pfam_to_go_mappings );
1067 if ( parser.getMappingCount() < domain_id_to_go_ids_map.size() ) {
1068 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME,
1069 "parser.getMappingCount() < domain_id_to_go_ids_map.size()" );
1071 domain_id_to_go_ids_count = parser.getMappingCount();
1073 catch ( final IOException e ) {
1074 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from Pfam to GO mapping file: " + e );
1077 File go_obo_file = null;
1078 List<GoTerm> go_terms = null;
1079 if ( cla.isOptionSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1080 if ( !cla.isOptionValueSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1081 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO OBO file: -"
1082 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>" );
1084 if ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) {
1085 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO OBO file (-"
1086 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>) without Pfam to GO mapping file ("
1087 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1089 go_obo_file = new File( cla.getOptionValue( surfacing.GO_OBO_FILE_USE_OPTION ) );
1090 final String error = ForesterUtil.isReadableFile( go_obo_file );
1091 if ( !ForesterUtil.isEmpty( error ) ) {
1092 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read GO OBO file: " + error );
1095 final OBOparser parser = new OBOparser( go_obo_file, OBOparser.ReturnType.BASIC_GO_TERM );
1096 go_terms = parser.parse();
1097 if ( parser.getGoTermCount() != go_terms.size() ) {
1099 .unexpectedFatalError( surfacing.PRG_NAME, "parser.getGoTermCount() != go_terms.size()" );
1102 catch ( final IOException e ) {
1103 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from GO OBO file: " + e );
1106 Map<GoId, GoTerm> go_id_to_term_map = null;
1107 if ( ( ( domain_id_to_go_ids_map != null ) && ( domain_id_to_go_ids_map.size() > 0 ) )
1108 && ( ( go_terms != null ) && ( go_terms.size() > 0 ) ) ) {
1109 go_id_to_term_map = GoUtils.createGoIdToGoTermMap( go_terms );
1111 GoNameSpace go_namespace_limit = null;
1112 if ( cla.isOptionSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1113 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1114 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO namespace limit (-"
1115 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<namespace>) without Pfam to GO mapping file ("
1116 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>) and GO OBO file (-"
1117 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1119 if ( !cla.isOptionValueSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1120 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO namespace limit: \"-"
1121 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1122 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1123 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1124 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1126 final String go_namespace_limit_str = cla.getOptionValue( surfacing.GO_NAMESPACE_LIMIT_OPTION )
1128 if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION ) ) {
1129 go_namespace_limit = GoNameSpace.createMolecularFunction();
1131 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS ) ) {
1132 go_namespace_limit = GoNameSpace.createBiologicalProcess();
1134 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT ) ) {
1135 go_namespace_limit = GoNameSpace.createCellularComponent();
1138 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + go_namespace_limit_str
1139 + "\" for GO namespace limit: \"-" + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1140 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1141 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1142 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1145 if ( ( domain_similarity_sort_field == DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE )
1146 && ( number_of_genomes > 2 ) ) {
1147 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
1149 boolean jacknifed_distances = false;
1150 int jacknife_resamplings = JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT;
1151 double jacknife_ratio = JACKNIFE_RATIO_DEFAULT;
1152 long random_seed = JACKNIFE_RANDOM_SEED_DEFAULT;
1153 if ( cla.isOptionSet( surfacing.JACKNIFE_OPTION ) ) {
1154 if ( ( number_of_genomes < 3 ) || !perform_pwc ) {
1155 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use jacknife resampling analysis (-"
1156 + surfacing.JACKNIFE_OPTION + "[=<number of resamplings>]) without pairwise analyses ("
1157 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1158 + "=<suffix for pairwise comparison output files>)" );
1160 jacknifed_distances = true;
1161 if ( cla.isOptionHasAValue( surfacing.JACKNIFE_OPTION ) ) {
1163 jacknife_resamplings = cla.getOptionValueAsInt( surfacing.JACKNIFE_OPTION );
1165 catch ( final IOException e ) {
1166 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for number of resamplings" );
1168 if ( jacknife_resamplings < 2 ) {
1169 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use less than 2 resamplings" );
1172 if ( cla.isOptionSet( surfacing.JACKNIFE_RATIO_OPTION )
1173 && cla.isOptionHasAValue( surfacing.JACKNIFE_RATIO_OPTION ) ) {
1175 jacknife_ratio = cla.getOptionValueAsDouble( surfacing.JACKNIFE_RATIO_OPTION );
1177 catch ( final IOException e ) {
1178 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for jacknife ratio" );
1180 if ( ( jacknife_ratio <= 0.0 ) || ( jacknife_ratio >= 1.0 ) ) {
1181 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use illegal value for jacknife ratio: "
1185 if ( cla.isOptionSet( surfacing.JACKNIFE_RANDOM_SEED_OPTION )
1186 && cla.isOptionHasAValue( surfacing.JACKNIFE_RANDOM_SEED_OPTION ) ) {
1188 random_seed = cla.getOptionValueAsLong( surfacing.JACKNIFE_RANDOM_SEED_OPTION );
1190 catch ( final IOException e ) {
1191 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for random generator seed" );
1195 File[] intree_files = null;
1196 Phylogeny[] intrees = null;
1197 if ( cla.isOptionSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1198 // TODO FIXME if jacknife.... maybe not
1199 if ( number_of_genomes < 3 ) {
1200 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer gains and losses on input species trees (-"
1201 + surfacing.INPUT_SPECIES_TREE_OPTION + " without pairwise analyses ("
1202 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1203 + "=<suffix for pairwise comparison output files>)" );
1205 if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1206 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input tree: -"
1207 + surfacing.INPUT_SPECIES_TREE_OPTION + "=<tree file in phyloXML format>" );
1209 final String intrees_str = cla.getOptionValue( surfacing.INPUT_SPECIES_TREE_OPTION );
1210 if ( intrees_str.indexOf( "#" ) > 0 ) {
1211 final String[] intrees_strs = intrees_str.split( "#" );
1212 intree_files = new File[ intrees_strs.length ];
1214 for( final String s : intrees_strs ) {
1215 intree_files[ i++ ] = new File( s.trim() );
1219 intree_files = new File[ 1 ];
1220 intree_files[ 0 ] = new File( intrees_str );
1222 intrees = getIntrees( intree_files, number_of_genomes, input_file_properties );
1224 long random_number_seed_for_fitch_parsimony = 0l;
1225 boolean radomize_fitch_parsimony = false;
1226 if ( cla.isOptionSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1227 if ( !cla.isOptionValueSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1228 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for random number seed: -"
1229 + surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION + "=<seed>" );
1232 random_number_seed_for_fitch_parsimony = cla
1233 .getOptionValueAsLong( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
1235 catch ( final IOException e ) {
1236 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1238 radomize_fitch_parsimony = true;
1240 SortedSet<DomainId> filter = null;
1241 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1242 || ( negative_domains_filter_file != null ) ) {
1243 filter = new TreeSet<DomainId>();
1244 if ( positive_filter_file != null ) {
1245 processFilter( positive_filter_file, filter );
1247 else if ( negative_filter_file != null ) {
1248 processFilter( negative_filter_file, filter );
1250 else if ( negative_domains_filter_file != null ) {
1251 processFilter( negative_domains_filter_file, filter );
1254 Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps = null;
1255 File[] secondary_features_map_files = null;
1256 final File domain_lengths_analysis_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1257 + DOMAIN_LENGTHS_ANALYSIS_SUFFIX );
1258 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
1259 SurfacingUtil.checkForOutputFileWriteability( domain_lengths_analysis_outfile );
1261 if ( cla.isOptionSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1262 if ( !cla.isOptionValueSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1263 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for secondary features map file: -"
1264 + surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE + "=<file>" );
1266 final String[] secondary_features_map_files_strs = cla
1267 .getOptionValue( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ).split( "#" );
1268 secondary_features_map_files = new File[ secondary_features_map_files_strs.length ];
1269 domain_id_to_secondary_features_maps = new Map[ secondary_features_map_files_strs.length ];
1271 for( final String secondary_features_map_files_str : secondary_features_map_files_strs ) {
1272 secondary_features_map_files[ i ] = new File( secondary_features_map_files_str );
1273 final String error = ForesterUtil.isReadableFile( secondary_features_map_files[ i ] );
1274 if ( !ForesterUtil.isEmpty( error ) ) {
1275 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read secondary features map file: " + error );
1278 domain_id_to_secondary_features_maps[ i ] = SurfacingUtil
1279 .createDomainIdToSecondaryFeaturesMap( secondary_features_map_files[ i ] );
1281 catch ( final IOException e ) {
1282 ForesterUtil.fatalError( surfacing.PRG_NAME,
1283 "cannot read secondary features map file: " + e.getMessage() );
1285 catch ( final Exception e ) {
1286 ForesterUtil.fatalError( surfacing.PRG_NAME, "problem with contents of features map file ["
1287 + secondary_features_map_files[ i ] + "]: " + e.getMessage() );
1292 if ( out_dir == null ) {
1293 ForesterUtil.fatalError( surfacing.PRG_NAME, "no output directory indicated (-"
1294 + surfacing.OUTPUT_DIR_OPTION + "=<dir>)" );
1296 if ( output_file == null ) {
1297 ForesterUtil.fatalError( surfacing.PRG_NAME, "no name for (main) output file indicated (-"
1298 + surfacing.OUTPUT_FILE_OPTION + "=<file>)" );
1300 if ( ( domain_id_to_go_ids_map == null ) || domain_id_to_go_ids_map.isEmpty() ) {
1301 ForesterUtil.fatalError( surfacing.PRG_NAME,
1302 "no (acceptable) Pfam to GO id mapping file provided ('pfam2go file') (-"
1303 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1305 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1306 ForesterUtil.fatalError( surfacing.PRG_NAME,
1307 "no (acceptable) go id to term mapping file provided ('GO OBO file') (-"
1308 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1310 System.out.println( "Output directory : " + out_dir );
1311 System.out.println( "Input genomes from : " + input_genomes_file );
1312 html_desc.append( "<tr><td>Input genomes from:</td><td>" + input_genomes_file + "</td></tr>" + nl );
1313 if ( positive_filter_file != null ) {
1314 final int filter_size = filter.size();
1315 System.out.println( "Positive protein filter : " + positive_filter_file + " [" + filter_size
1317 html_desc.append( "<tr><td>Positive protein filter:</td><td>" + positive_filter_file + " [" + filter_size
1318 + " domain ids]</td></tr>" + nl );
1320 if ( negative_filter_file != null ) {
1321 final int filter_size = filter.size();
1322 System.out.println( "Negative protein filter : " + negative_filter_file + " [" + filter_size
1324 html_desc.append( "<tr><td>Negative protein filter:</td><td>" + negative_filter_file + " [" + filter_size
1325 + " domain ids]</td></tr>" + nl );
1327 if ( negative_domains_filter_file != null ) {
1328 final int filter_size = filter.size();
1329 System.out.println( "Negative domain filter : " + negative_domains_filter_file + " [" + filter_size
1331 html_desc.append( "<tr><td>Negative domain filter:</td><td>" + negative_domains_filter_file + " ["
1332 + filter_size + " domain ids]</td></tr>" + nl );
1334 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
1336 for( final String s : plus_minus_analysis_high_copy_base_species ) {
1337 plus0 += "+" + s + " ";
1340 for( final String s : plus_minus_analysis_high_copy_target_species ) {
1341 plus1 += "*" + s + " ";
1344 for( final String s : plus_minus_analysis_high_low_copy_species ) {
1345 minus += "-" + s + " ";
1347 System.out.println( "Plus-minus analysis : " + plus1 + "&& " + plus0 + "&& " + minus );
1348 html_desc.append( "<tr><td>Plus-minus analysis:</td><td>" + plus1 + "&& " + plus0 + "&& " + minus
1349 + "</td></tr>" + nl );
1351 if ( cutoff_scores_file != null ) {
1352 System.out.println( "Cutoff scores file : " + cutoff_scores_file );
1353 html_desc.append( "<tr><td>Cutoff scores file:</td><td>" + cutoff_scores_file + "</td></tr>" + nl );
1355 if ( e_value_max >= 0.0 ) {
1356 System.out.println( "E-value maximum (inclusive) : " + e_value_max );
1357 html_desc.append( "<tr><td>E-value maximum (inclusive):</td><td>" + e_value_max + "</td></tr>" + nl );
1359 if ( output_protein_lists_for_all_domains ) {
1360 System.out.println( "Domain E-value max : " + output_list_of_all_proteins_per_domain_e_value_max );
1361 html_desc.append( "<tr><td>Protein lists: E-value maximum per domain (inclusive):</td><td>"
1362 + output_list_of_all_proteins_per_domain_e_value_max + "</td></tr>" + nl );
1364 System.out.println( "Ignore DUFs : " + ignore_dufs );
1365 if ( ignore_virus_like_ids ) {
1366 System.out.println( "Ignore virus like ids : " + ignore_virus_like_ids );
1367 html_desc.append( "<tr><td>Ignore virus, phage, transposition related ids:</td><td>"
1368 + ignore_virus_like_ids + "</td></tr>" + nl );
1370 html_desc.append( "<tr><td>Ignore DUFs:</td><td>" + ignore_dufs + "</td></tr>" + nl );
1371 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1372 System.out.println( "Max allowed domain overlap : " + max_allowed_overlap );
1373 html_desc.append( "<tr><td>Max allowed domain overlap:</td><td>" + max_allowed_overlap + "</td></tr>" + nl );
1375 if ( no_engulfing_overlaps ) {
1376 System.out.println( "Ignore engulfed domains : " + no_engulfing_overlaps );
1377 html_desc.append( "<tr><td>Ignore (lower confidence) engulfed domains:</td><td>" + no_engulfing_overlaps
1378 + "</td></tr>" + nl );
1380 System.out.println( "Ignore singlet domains : " + ignore_domains_without_combs_in_all_spec );
1382 .append( "<tr><td>Ignore singlet domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1383 + ignore_domains_without_combs_in_all_spec + "</td></tr>" + nl );
1384 System.out.println( "Ignore species specific doms: " + ignore_species_specific_domains );
1386 .append( "<tr><td>Ignore species specific domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1387 + ignore_species_specific_domains + "</td></tr>" + nl );
1388 System.out.println( "Ignore combination with self: " + ignore_combination_with_same );
1389 html_desc.append( "<tr><td>Ignore combination with self for domain combination similarity analyses:</td><td>"
1390 + ignore_combination_with_same + "</td></tr>" + nl );
1391 System.out.println( "Consider directedness : "
1392 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) );
1393 html_desc.append( "<tr><td>Consider directedness of binary domain combinations:</td><td>"
1394 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) + "</td></tr>" + nl );
1395 if ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) {
1396 System.out.println( "Consider adjacency : "
1397 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) );
1398 html_desc.append( "<tr><td>Consider djacency of binary domain combinations:</td><td>"
1399 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) + "</td></tr>"
1402 System.out.print( "Domain counts sort order : " );
1403 switch ( dc_sort_order ) {
1404 case ALPHABETICAL_KEY_ID:
1405 System.out.println( "alphabetical" );
1407 case KEY_DOMAIN_COUNT:
1408 System.out.println( "domain count" );
1410 case KEY_DOMAIN_PROTEINS_COUNT:
1411 System.out.println( "domain proteins count" );
1413 case COMBINATIONS_COUNT:
1414 System.out.println( "domain combinations count" );
1417 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for dc sort order" );
1419 if ( domain_id_to_go_ids_map != null ) {
1420 System.out.println( "Pfam to GO mappings from : " + pfam_to_go_file + " [" + domain_id_to_go_ids_count
1422 html_desc.append( "<tr><td>Pfam to GO mappings from:</td><td>" + pfam_to_go_file + " ["
1423 + domain_id_to_go_ids_count + " mappings]" + "</td></tr>" + nl );
1425 if ( go_terms != null ) {
1426 System.out.println( "GO terms from : " + go_obo_file + " [" + go_terms.size() + " terms]" );
1427 html_desc.append( "<tr><td>GO terms from:</td><td>" + go_obo_file + " [" + go_terms.size() + " terms]"
1428 + "</td></tr>" + nl );
1430 if ( go_namespace_limit != null ) {
1431 System.out.println( "Limit GO terms to : " + go_namespace_limit.toString() );
1432 html_desc.append( "<tr><td>Limit GO terms to</td><td>" + go_namespace_limit + "</td></tr>" + nl );
1434 if ( perform_pwc ) {
1435 System.out.println( "Suffix for PWC files : " + automated_pairwise_comparison_suffix );
1436 html_desc.append( "<tr><td>Suffix for PWC files</td><td>" + automated_pairwise_comparison_suffix
1437 + "</td></tr>" + nl );
1439 if ( out_dir != null ) {
1440 System.out.println( "Output directory : " + out_dir );
1442 if ( query_domain_ids != null ) {
1443 System.out.println( "Query domains (ordered) : " + query_domain_ids );
1444 html_desc.append( "<tr><td></td><td>" + query_domain_ids + "</td></tr>" + nl );
1446 System.out.println( "Write similarities to : " + output_file );
1447 System.out.print( " Scoring method : " );
1448 html_desc.append( "<tr><td>Scoring method:</td><td>" );
1449 switch ( scoring ) {
1451 System.out.println( "domain combinations based" );
1452 html_desc.append( "domain combinations based" + "</td></tr>" + nl );
1455 System.out.println( "domain counts based" );
1456 html_desc.append( "domain counts based" + "</td></tr>" + nl );
1459 System.out.println( "domain proteins counts based" );
1460 html_desc.append( "domain proteins counts based" + "</td></tr>" + nl );
1463 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
1465 System.out.print( " Sort by : " );
1466 html_desc.append( "<tr><td>Sort by:</td><td>" );
1467 switch ( domain_similarity_sort_field ) {
1469 System.out.print( "score minimum" );
1470 html_desc.append( "score minimum" );
1473 System.out.print( "score maximum" );
1474 html_desc.append( "score maximum" );
1477 System.out.print( "score mean" );
1478 html_desc.append( "score mean" );
1481 System.out.print( "score standard deviation" );
1482 html_desc.append( "score standard deviation" );
1485 System.out.print( "species number" );
1486 html_desc.append( "species number" );
1489 System.out.print( "alphabetical domain identifier" );
1490 html_desc.append( "alphabetical domain identifier" );
1492 case MAX_DIFFERENCE:
1493 System.out.print( "(maximal) difference" );
1494 html_desc.append( "(maximal) difference" );
1496 case ABS_MAX_COUNTS_DIFFERENCE:
1497 System.out.print( "absolute (maximal) counts difference" );
1498 html_desc.append( "absolute (maximal) counts difference" );
1500 case MAX_COUNTS_DIFFERENCE:
1501 System.out.print( "(maximal) counts difference" );
1502 html_desc.append( "(maximal) counts difference" );
1505 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1507 if ( sort_by_species_count_first ) {
1508 System.out.println( " (sort by species count first)" );
1509 html_desc.append( " (sort by species count first)" );
1512 System.out.println();
1514 html_desc.append( "</td></tr>" + nl );
1515 System.out.print( " Detailedness : " );
1516 switch ( detailedness ) {
1518 System.out.println( "basic" );
1520 case LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES:
1521 System.out.println( "list combining domains for each species" );
1524 System.out.println( "punctilious" );
1527 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for detailedness" );
1529 System.out.print( " Print option : " );
1530 switch ( domain_similarity_print_option ) {
1532 System.out.println( "HTML" );
1534 case SIMPLE_TAB_DELIMITED:
1535 System.out.println( "simple tab delimited" );
1538 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for print option" );
1540 System.out.print( " Species matrix : " + species_matrix );
1541 System.out.println();
1542 final File dc_data_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + DATA_FILE_SUFFIX );
1543 System.out.println( "Domain comb data output : " + dc_data_file );
1544 html_desc.append( "<tr><td>Domain combination data output:</td><td> " + dc_data_file + " </td></tr>" );
1545 System.out.println();
1546 if ( perform_pwc ) {
1547 System.out.println( "Pairwise comparisons: " );
1548 html_desc.append( "<tr><td>Pairwise comparisons:</td><td></td></tr>" );
1549 System.out.print( " Sort by : " );
1550 html_desc.append( "<tr><td>Sort by:</td><td>" );
1551 switch ( domain_similarity_sort_field_for_automated_pwc ) {
1553 System.out.print( "score mean" );
1554 html_desc.append( "score mean" );
1557 System.out.print( "alphabetical domain identifier" );
1558 html_desc.append( "alphabetical domain identifier" );
1560 case MAX_DIFFERENCE:
1561 System.out.print( "difference" );
1562 html_desc.append( "difference" );
1564 case ABS_MAX_COUNTS_DIFFERENCE:
1565 System.out.print( "absolute counts difference" );
1566 html_desc.append( "absolute counts difference" );
1568 case MAX_COUNTS_DIFFERENCE:
1569 System.out.print( "counts difference" );
1570 html_desc.append( "counts difference" );
1574 .unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1576 System.out.println();
1577 html_desc.append( "</td></tr>" + nl );
1578 if ( jacknifed_distances ) {
1579 html_desc.append( "<tr><td>Jacknife:</td><td>" + jacknife_resamplings + " resamplings</td></tr>" + nl );
1580 html_desc.append( "<tr><td>Jacknife ratio:</td><td>" + ForesterUtil.round( jacknife_ratio, 2 )
1581 + "</td></tr>" + nl );
1582 html_desc.append( "<tr><td>Jacknife random number seed:</td><td>" + random_seed + "</td></tr>" + nl );
1583 System.out.println( " Jacknife : " + jacknife_resamplings + " resamplings" );
1584 System.out.println( " Ratio : " + ForesterUtil.round( jacknife_ratio, 2 ) );
1585 System.out.println( " Random number seed : " + random_seed );
1587 if ( ( intrees != null ) && ( intrees.length > 0 ) ) {
1588 for( final File intree_file : intree_files ) {
1589 html_desc.append( "<tr><td>Intree for gain/loss parsimony analysis:</td><td>" + intree_file
1590 + "</td></tr>" + nl );
1591 System.out.println( " Intree for gain/loss pars.: " + intree_file );
1594 if ( radomize_fitch_parsimony ) {
1595 html_desc.append( "<tr><td> Random number seed for Fitch parsimony analysis:</td><td>"
1596 + random_number_seed_for_fitch_parsimony + "</td></tr>" + nl );
1597 System.out.println( " Random number seed : " + random_number_seed_for_fitch_parsimony );
1599 if ( ( domain_id_to_secondary_features_maps != null ) && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
1600 for( int i = 0; i < secondary_features_map_files.length; i++ ) {
1601 html_desc.append( "<tr><td>Secondary features map file:</td><td>"
1602 + secondary_features_map_files[ i ] + "</td></tr>" + nl );
1603 System.out.println( "Secondary features map file : " + secondary_features_map_files[ i ]
1604 + " [mappings for " + domain_id_to_secondary_features_maps[ i ].size() + " domain ids]" );
1606 System.out.println();
1607 System.out.println( "Domain ids to secondary features map:" );
1608 for( final DomainId domain_id : domain_id_to_secondary_features_maps[ i ].keySet() ) {
1609 System.out.print( domain_id.getId() );
1610 System.out.print( " => " );
1611 for( final String sec : domain_id_to_secondary_features_maps[ i ].get( domain_id ) ) {
1612 System.out.print( sec );
1613 System.out.print( " " );
1615 System.out.println();
1620 } // if ( perform_pwc ) {
1621 System.out.println();
1622 html_desc.append( "<tr><td>Command line:</td><td>\n" + cla.getCommandLineArgsAsString() + "\n</td></tr>" + nl );
1623 System.out.println( "Command line : " + cla.getCommandLineArgsAsString() );
1624 BufferedWriter[] query_domains_writer_ary = null;
1625 List<DomainId>[] query_domain_ids_array = null;
1626 if ( query_domain_ids != null ) {
1627 final String[] query_domain_ids_str_array = query_domain_ids.split( "#" );
1628 query_domain_ids_array = new ArrayList[ query_domain_ids_str_array.length ];
1629 query_domains_writer_ary = new BufferedWriter[ query_domain_ids_str_array.length ];
1630 for( int i = 0; i < query_domain_ids_str_array.length; i++ ) {
1631 String query_domain_ids_str = query_domain_ids_str_array[ i ];
1632 final String[] query_domain_ids_str_ary = query_domain_ids_str.split( "~" );
1633 final List<DomainId> query = new ArrayList<DomainId>();
1634 for( final String element : query_domain_ids_str_ary ) {
1635 query.add( new DomainId( element ) );
1637 query_domain_ids_array[ i ] = query;
1638 query_domain_ids_str = query_domain_ids_str.replace( '~', '_' );
1639 String protein_names_writer_str = query_domain_ids_str + surfacing.SEQ_EXTRACT_SUFFIX;
1640 if ( out_dir != null ) {
1641 protein_names_writer_str = out_dir + ForesterUtil.FILE_SEPARATOR + protein_names_writer_str;
1644 query_domains_writer_ary[ i ] = new BufferedWriter( new FileWriter( protein_names_writer_str ) );
1646 catch ( final IOException e ) {
1647 ForesterUtil.fatalError( surfacing.PRG_NAME, "Could not open [" + protein_names_writer_str + "]: "
1648 + e.getLocalizedMessage() );
1652 SortedMap<Species, List<Protein>> protein_lists_per_species = null; //This will only be created if neede.
1653 boolean need_protein_lists_per_species = false;
1654 if ( ( plus_minus_analysis_high_copy_base_species.size() > 0 ) || output_protein_lists_for_all_domains ) {
1655 need_protein_lists_per_species = true;
1657 if ( need_protein_lists_per_species ) {
1658 protein_lists_per_species = new TreeMap<Species, List<Protein>>();
1660 final List<GenomeWideCombinableDomains> gwcd_list = new ArrayList<GenomeWideCombinableDomains>( number_of_genomes );
1661 final SortedSet<DomainId> all_domains_encountered = new TreeSet<DomainId>();
1662 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered = new TreeSet<BinaryDomainCombination>();
1663 List<BinaryDomainCombination> all_bin_domain_combinations_gained_fitch = null;
1664 List<BinaryDomainCombination> all_bin_domain_combinations_lost_fitch = null;
1665 if ( ( intrees != null ) && ( intrees.length == 1 ) ) {
1666 all_bin_domain_combinations_gained_fitch = new ArrayList<BinaryDomainCombination>();
1667 all_bin_domain_combinations_lost_fitch = new ArrayList<BinaryDomainCombination>();
1669 final DomainLengthsTable domain_lengths_table = new DomainLengthsTable();
1670 final File per_genome_domain_promiscuity_statistics_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR
1671 + output_file + D_PROMISCUITY_FILE_SUFFIX );
1672 BufferedWriter per_genome_domain_promiscuity_statistics_writer = null;
1674 per_genome_domain_promiscuity_statistics_writer = new BufferedWriter( new FileWriter( per_genome_domain_promiscuity_statistics_file ) );
1675 per_genome_domain_promiscuity_statistics_writer.write( "Species:\t" );
1676 per_genome_domain_promiscuity_statistics_writer.write( "Mean:\t" );
1677 per_genome_domain_promiscuity_statistics_writer.write( "SD:\t" );
1678 per_genome_domain_promiscuity_statistics_writer.write( "Median:\t" );
1679 per_genome_domain_promiscuity_statistics_writer.write( "Min:\t" );
1680 per_genome_domain_promiscuity_statistics_writer.write( "Max:\t" );
1681 per_genome_domain_promiscuity_statistics_writer.write( "N:\t" );
1682 per_genome_domain_promiscuity_statistics_writer.write( "Max Promiscuous Domains:"
1683 + ForesterUtil.LINE_SEPARATOR );
1685 catch ( final IOException e2 ) {
1686 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1688 final File log_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + LOG_FILE_SUFFIX );
1689 BufferedWriter log_writer = null;
1691 log_writer = new BufferedWriter( new FileWriter( log_file ) );
1693 catch ( final IOException e2 ) {
1694 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1696 BufferedWriter dc_data_writer = null;
1698 dc_data_writer = new BufferedWriter( new FileWriter( dc_data_file ) );
1699 dc_data_writer.write( DATA_FILE_DESC );
1700 dc_data_writer.write( ForesterUtil.LINE_SEPARATOR );
1702 catch ( final IOException e2 ) {
1703 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1705 final DescriptiveStatistics protein_coverage_stats = new BasicDescriptiveStatistics();
1706 final DescriptiveStatistics all_genomes_domains_per_potein_stats = new BasicDescriptiveStatistics();
1707 final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo = new TreeMap<Integer, Integer>();
1708 final SortedSet<String> domains_which_are_always_single = new TreeSet<String>();
1709 final SortedSet<String> domains_which_are_sometimes_single_sometimes_not = new TreeSet<String>();
1710 final SortedSet<String> domains_which_never_single = new TreeSet<String>();
1711 BufferedWriter domains_per_potein_stats_writer = null;
1713 domains_per_potein_stats_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
1714 + output_file + "_domains_per_potein_stats.txt" ) );
1715 domains_per_potein_stats_writer.write( "Genome" );
1716 domains_per_potein_stats_writer.write( "\t" );
1717 domains_per_potein_stats_writer.write( "Mean" );
1718 domains_per_potein_stats_writer.write( "\t" );
1719 domains_per_potein_stats_writer.write( "SD" );
1720 domains_per_potein_stats_writer.write( "\t" );
1721 domains_per_potein_stats_writer.write( "Median" );
1722 domains_per_potein_stats_writer.write( "\t" );
1723 domains_per_potein_stats_writer.write( "N" );
1724 domains_per_potein_stats_writer.write( "\t" );
1725 domains_per_potein_stats_writer.write( "Min" );
1726 domains_per_potein_stats_writer.write( "\t" );
1727 domains_per_potein_stats_writer.write( "Max" );
1728 domains_per_potein_stats_writer.write( "\n" );
1730 catch ( final IOException e3 ) {
1731 e3.printStackTrace();
1733 Map<String, DescriptiveStatistics> protein_length_stats_by_dc = null;
1734 Map<String, DescriptiveStatistics> domain_number_stats_by_dc = null;
1735 final Map<String, DescriptiveStatistics> domain_length_stats_by_domain = new HashMap<String, DescriptiveStatistics>();
1736 if ( PERFORM_DC_REGAIN_PROTEINS_STATS ) {
1737 protein_length_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1738 domain_number_stats_by_dc = new HashMap<String, DescriptiveStatistics>();
1741 final SortedMap<String, Set<String>> distinct_domain_architecutures_per_genome = new TreeMap<String, Set<String>>();
1742 final SortedMap<String, Integer> distinct_domain_architecuture_counts = new TreeMap<String, Integer>();
1743 for( int i = 0; i < number_of_genomes; ++i ) {
1744 System.out.println();
1745 System.out.println( ( i + 1 ) + "/" + number_of_genomes );
1746 log( ( i + 1 ) + "/" + number_of_genomes, log_writer );
1747 System.out.println( "Processing : " + input_file_properties[ i ][ 1 ]
1748 + " [" + input_file_properties[ i ][ 0 ] + "]" );
1749 log( "Genome : " + input_file_properties[ i ][ 1 ] + " ["
1750 + input_file_properties[ i ][ 0 ] + "]", log_writer );
1751 HmmscanPerDomainTableParser parser = null;
1752 INDIVIDUAL_SCORE_CUTOFF ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF.NONE;
1753 if ( individual_score_cutoffs != null ) {
1754 ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF_DEFAULT;
1756 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1757 || ( negative_domains_filter_file != null ) ) {
1758 HmmscanPerDomainTableParser.FilterType filter_type = HmmscanPerDomainTableParser.FilterType.NONE;
1759 if ( positive_filter_file != null ) {
1760 filter_type = HmmscanPerDomainTableParser.FilterType.POSITIVE_PROTEIN;
1762 else if ( negative_filter_file != null ) {
1763 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_PROTEIN;
1765 else if ( negative_domains_filter_file != null ) {
1766 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_DOMAIN;
1768 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1769 input_file_properties[ i ][ 1 ],
1776 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1777 input_file_properties[ i ][ 1 ],
1781 if ( e_value_max >= 0.0 ) {
1782 parser.setEValueMaximum( e_value_max );
1784 parser.setIgnoreDufs( ignore_dufs );
1785 parser.setIgnoreVirusLikeIds( ignore_virus_like_ids );
1786 parser.setIgnoreEngulfedDomains( no_engulfing_overlaps );
1787 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1788 parser.setMaxAllowedOverlap( max_allowed_overlap );
1790 parser.setReturnType( HmmscanPerDomainTableParser.ReturnType.UNORDERED_PROTEIN_DOMAIN_COLLECTION_PER_PROTEIN );
1791 if ( individual_score_cutoffs != null ) {
1792 parser.setIndividualScoreCutoffs( individual_score_cutoffs );
1794 List<Protein> protein_list = null;
1796 protein_list = parser.parse();
1798 catch ( final IOException e ) {
1799 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1801 catch ( final Exception e ) {
1802 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, e.getMessage(), e );
1805 System.out.println( "Domains ignored due to negative domain filter: " );
1806 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToNegativeDomainFilterCountsMap() );
1807 System.out.println( "Domains ignored due to virus like id: " );
1808 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToVirusLikeIdCountsMap() );
1810 final double coverage = ( double ) protein_list.size() / parser.getProteinsEncountered();
1811 protein_coverage_stats.addValue( coverage );
1812 int distinct_das = -1;
1813 if ( DA_ANALYSIS ) {
1814 final String genome = input_file_properties[ i ][ 0 ];
1815 distinct_das = SurfacingUtil.storeDomainArchitectures( genome,
1816 distinct_domain_architecutures_per_genome,
1818 distinct_domain_architecuture_counts );
1820 System.out.println( "Number of proteins encountered : " + parser.getProteinsEncountered() );
1821 log( "Number of proteins encountered : " + parser.getProteinsEncountered(), log_writer );
1822 System.out.println( "Number of proteins stored : " + protein_list.size() );
1823 log( "Number of proteins stored : " + protein_list.size(), log_writer );
1824 System.out.println( "Coverage : "
1825 + ForesterUtil.roundToInt( 100.0 * coverage ) + "%" );
1826 log( "Coverage : " + ForesterUtil.roundToInt( 100.0 * coverage )
1827 + "%", log_writer );
1828 System.out.println( "Domains encountered : " + parser.getDomainsEncountered() );
1829 log( "Domains encountered : " + parser.getDomainsEncountered(), log_writer );
1830 System.out.println( "Domains stored : " + parser.getDomainsStored() );
1831 log( "Domains stored : " + parser.getDomainsStored(), log_writer );
1832 System.out.println( "Distinct domains stored : "
1833 + parser.getDomainsStoredSet().size() );
1834 log( "Distinct domains stored : " + parser.getDomainsStoredSet().size(), log_writer );
1835 System.out.println( "Domains ignored due to individual score cutoffs: "
1836 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() );
1837 log( "Domains ignored due to individual score cutoffs: "
1838 + parser.getDomainsIgnoredDueToIndividualScoreCutoff(),
1840 System.out.println( "Domains ignored due to E-value : "
1841 + parser.getDomainsIgnoredDueToEval() );
1842 log( "Domains ignored due to E-value : " + parser.getDomainsIgnoredDueToEval(), log_writer );
1843 System.out.println( "Domains ignored due to DUF designation : "
1844 + parser.getDomainsIgnoredDueToDuf() );
1845 log( "Domains ignored due to DUF designation : " + parser.getDomainsIgnoredDueToDuf(), log_writer );
1846 if ( ignore_virus_like_ids ) {
1847 System.out.println( "Domains ignored due virus like ids : "
1848 + parser.getDomainsIgnoredDueToVirusLikeIds() );
1849 log( "Domains ignored due virus like ids : " + parser.getDomainsIgnoredDueToVirusLikeIds(),
1852 System.out.println( "Domains ignored due negative domain filter : "
1853 + parser.getDomainsIgnoredDueToNegativeDomainFilter() );
1854 log( "Domains ignored due negative domain filter : "
1855 + parser.getDomainsIgnoredDueToNegativeDomainFilter(),
1857 System.out.println( "Domains ignored due to overlap : "
1858 + parser.getDomainsIgnoredDueToOverlap() );
1859 log( "Domains ignored due to overlap : " + parser.getDomainsIgnoredDueToOverlap(),
1861 if ( negative_filter_file != null ) {
1862 System.out.println( "Proteins ignored due to negative filter : "
1863 + parser.getProteinsIgnoredDueToFilter() );
1864 log( "Proteins ignored due to negative filter : " + parser.getProteinsIgnoredDueToFilter(),
1867 if ( positive_filter_file != null ) {
1868 System.out.println( "Proteins ignored due to positive filter : "
1869 + parser.getProteinsIgnoredDueToFilter() );
1870 log( "Proteins ignored due to positive filter : " + parser.getProteinsIgnoredDueToFilter(),
1873 if ( DA_ANALYSIS ) {
1874 System.out.println( "Distinct domain architectures stored : " + distinct_das );
1875 log( "Distinct domain architectures stored : " + distinct_das, log_writer );
1877 System.out.println( "Time for processing : " + parser.getTime() + "ms" );
1878 log( "", log_writer );
1879 html_desc.append( "<tr><td>" + input_file_properties[ i ][ 0 ] + " [species: "
1880 + input_file_properties[ i ][ 1 ] + "]" + ":</td><td>domains analyzed: "
1881 + parser.getDomainsStored() + "; domains ignored: [ind score cutoffs: "
1882 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() + "] [E-value cutoff: "
1883 + parser.getDomainsIgnoredDueToEval() + "] [DUF: " + parser.getDomainsIgnoredDueToDuf()
1884 + "] [virus like ids: " + parser.getDomainsIgnoredDueToVirusLikeIds()
1885 + "] [negative domain filter: " + parser.getDomainsIgnoredDueToNegativeDomainFilter()
1886 + "] [overlap: " + parser.getDomainsIgnoredDueToOverlap() + "]" );
1887 if ( negative_filter_file != null ) {
1888 html_desc.append( "; proteins ignored due to negative filter: "
1889 + parser.getProteinsIgnoredDueToFilter() );
1891 if ( positive_filter_file != null ) {
1892 html_desc.append( "; proteins ignored due to positive filter: "
1893 + parser.getProteinsIgnoredDueToFilter() );
1895 html_desc.append( "</td></tr>" + nl );
1898 for( final Protein protein : protein_list ) {
1899 dc_data_writer.write( SurfacingUtil.proteinToDomainCombinations( protein, count + "", "\t" )
1902 for( final Domain d : protein.getProteinDomains() ) {
1903 final String d_str = d.getDomainId().toString();
1904 if ( !domain_length_stats_by_domain.containsKey( d_str ) ) {
1905 domain_length_stats_by_domain.put( d_str, new BasicDescriptiveStatistics() );
1907 domain_length_stats_by_domain.get( d_str ).addValue( d.getLength() );
1911 catch ( final IOException e ) {
1912 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1914 SurfacingUtil.domainsPerProteinsStatistics( input_file_properties[ i ][ 1 ],
1916 all_genomes_domains_per_potein_stats,
1917 all_genomes_domains_per_potein_histo,
1918 domains_which_are_always_single,
1919 domains_which_are_sometimes_single_sometimes_not,
1920 domains_which_never_single,
1921 domains_per_potein_stats_writer );
1922 domain_lengths_table.addLengths( protein_list );
1923 if ( !DA_ANALYSIS ) {
1924 gwcd_list.add( BasicGenomeWideCombinableDomains
1925 .createInstance( protein_list,
1926 ignore_combination_with_same,
1927 new BasicSpecies( input_file_properties[ i ][ 1 ] ),
1928 domain_id_to_go_ids_map,
1930 protein_length_stats_by_dc,
1931 domain_number_stats_by_dc ) );
1932 if ( gwcd_list.get( i ).getSize() > 0 ) {
1933 SurfacingUtil.writeDomainCombinationsCountsFile( input_file_properties,
1935 per_genome_domain_promiscuity_statistics_writer,
1939 if ( output_binary_domain_combinationsfor_graph_analysis ) {
1940 SurfacingUtil.writeBinaryDomainCombinationsFileForGraphAnalysis( input_file_properties,
1946 SurfacingUtil.addAllDomainIdsToSet( gwcd_list.get( i ), all_domains_encountered );
1947 SurfacingUtil.addAllBinaryDomainCombinationToSet( gwcd_list.get( i ),
1948 all_bin_domain_combinations_encountered );
1951 if ( query_domains_writer_ary != null ) {
1952 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1954 SurfacingUtil.extractProteinNames( protein_list,
1955 query_domain_ids_array[ j ],
1956 query_domains_writer_ary[ j ],
1958 LIMIT_SPEC_FOR_PROT_EX );
1959 query_domains_writer_ary[ j ].flush();
1961 catch ( final IOException e ) {
1962 e.printStackTrace();
1966 if ( need_protein_lists_per_species ) {
1967 protein_lists_per_species.put( new BasicSpecies( input_file_properties[ i ][ 1 ] ), protein_list );
1972 catch ( final IOException e2 ) {
1973 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1976 } // for( int i = 0; i < number_of_genomes; ++i ) {
1977 ForesterUtil.programMessage( PRG_NAME, "Wrote domain promiscuities to: "
1978 + per_genome_domain_promiscuity_statistics_file );
1980 if ( DA_ANALYSIS ) {
1981 SurfacingUtil.performDomainArchitectureAnalysis( distinct_domain_architecutures_per_genome,
1982 distinct_domain_architecuture_counts,
1984 new File( out_dir.toString() + "/" + output_file
1985 + "_DA_counts.txt" ),
1986 new File( out_dir.toString() + "/" + output_file
1987 + "_unique_DAs.txt" ) );
1988 distinct_domain_architecutures_per_genome.clear();
1989 distinct_domain_architecuture_counts.clear();
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: "
2022 + ( 100 * protein_coverage_stats.getMin() ) + "%-" + ( 100 * protein_coverage_stats.getMax() )
2024 log( "Average of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.arithmeticMean() )
2025 + "% (+/-" + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)", log_writer );
2026 log( "Range of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.getMin() ) + "%-"
2027 + ( 100 * protein_coverage_stats.getMax() ) + "%", log_writer );
2029 catch ( final IOException e2 ) {
2030 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
2032 if ( query_domains_writer_ary != null ) {
2033 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
2035 query_domains_writer_ary[ j ].close();
2037 catch ( final IOException e ) {
2038 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
2043 per_genome_domain_promiscuity_statistics_writer.close();
2044 dc_data_writer.close();
2047 catch ( final IOException e2 ) {
2048 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
2050 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
2052 SurfacingUtil.executeDomainLengthAnalysis( input_file_properties,
2054 domain_lengths_table,
2055 domain_lengths_analysis_outfile );
2057 catch ( final IOException e1 ) {
2058 ForesterUtil.fatalError( surfacing.PRG_NAME, e1.toString() );
2060 System.out.println();
2061 ForesterUtil.programMessage( PRG_NAME, "Wrote domain length data to: " + domain_lengths_analysis_outfile );
2062 System.out.println();
2064 final long analysis_start_time = new Date().getTime();
2065 PairwiseDomainSimilarityCalculator pw_calc = null;
2066 // double[] values_for_all_scores_histogram = null;
2067 final DomainSimilarityCalculator calc = new BasicDomainSimilarityCalculator( domain_similarity_sort_field,
2068 sort_by_species_count_first,
2069 number_of_genomes == 2 );
2070 switch ( scoring ) {
2072 pw_calc = new CombinationsBasedPairwiseDomainSimilarityCalculator();
2075 pw_calc = new DomainCountsBasedPairwiseSimilarityCalculator();
2078 pw_calc = new ProteinCountsBasedPairwiseDomainSimilarityCalculator();
2081 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
2083 DomainSimilarityCalculator.GoAnnotationOutput go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.NONE;
2084 if ( domain_id_to_go_ids_map != null ) {
2085 go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.ALL;
2087 final SortedSet<DomainSimilarity> similarities = calc
2088 .calculateSimilarities( pw_calc,
2090 ignore_domains_without_combs_in_all_spec,
2091 ignore_species_specific_domains );
2092 SurfacingUtil.decoratePrintableDomainSimilarities( similarities,
2094 go_annotation_output,
2096 go_namespace_limit );
2097 DescriptiveStatistics pw_stats = null;
2099 String my_outfile = output_file.toString();
2100 Map<Character, Writer> split_writers = null;
2101 Writer writer = null;
2102 if ( similarities.size() > MINIMAL_NUMBER_OF_SIMILARITIES_FOR_SPLITTING ) {
2103 if ( my_outfile.endsWith( ".html" ) ) {
2104 my_outfile = my_outfile.substring( 0, my_outfile.length() - 5 );
2106 split_writers = new HashMap<Character, Writer>();
2107 createSplitWriters( out_dir, my_outfile, split_writers );
2109 else if ( !my_outfile.endsWith( ".html" ) ) {
2110 my_outfile += ".html";
2111 writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) );
2113 List<Species> species_order = null;
2114 if ( species_matrix ) {
2115 species_order = new ArrayList<Species>();
2116 for( int i = 0; i < number_of_genomes; i++ ) {
2117 species_order.add( new BasicSpecies( input_file_properties[ i ][ 1 ] ) );
2120 html_desc.append( "<tr><td>Sum of all distinct binary combinations:</td><td>"
2121 + all_bin_domain_combinations_encountered.size() + "</td></tr>" + nl );
2122 html_desc.append( "<tr><td>Sum of all distinct domains:</td><td>" + all_domains_encountered.size()
2123 + "</td></tr>" + nl );
2124 html_desc.append( "<tr><td>Analysis date/time:</td><td>"
2125 + new java.text.SimpleDateFormat( "yyyy.MM.dd HH:mm:ss" ).format( new java.util.Date() )
2126 + "</td></tr>" + nl );
2127 html_desc.append( "</table>" + nl );
2128 pw_stats = SurfacingUtil
2129 .writeDomainSimilaritiesToFile( html_desc,
2130 new StringBuilder( number_of_genomes + " genomes" ),
2134 number_of_genomes == 2,
2136 domain_similarity_print_option,
2137 domain_similarity_sort_field,
2140 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote main output (includes domain similarities) to: \""
2141 + ( out_dir == null ? my_outfile : out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) + "\"" );
2143 catch ( final IOException e ) {
2144 ForesterUtil.fatalError( surfacing.PRG_NAME, "Failed to write similarites to: \"" + output_file + "\" ["
2145 + e.getMessage() + "]" );
2147 System.out.println();
2148 // values_for_all_scores_histogram = pw_stats.getDataAsDoubleArray();
2149 final Species[] species = new Species[ number_of_genomes ];
2150 for( int i = 0; i < number_of_genomes; ++i ) {
2151 species[ i ] = new BasicSpecies( input_file_properties[ i ][ 1 ] );
2153 List<Phylogeny> inferred_trees = null;
2154 if ( ( number_of_genomes > 2 ) && perform_pwc ) {
2155 final PairwiseGenomeComparator pwgc = new PairwiseGenomeComparator();
2156 pwgc.performPairwiseComparisons( html_desc,
2157 sort_by_species_count_first,
2159 ignore_domains_without_combs_in_all_spec,
2160 ignore_species_specific_domains,
2161 domain_similarity_sort_field_for_automated_pwc,
2162 domain_similarity_print_option,
2164 domain_id_to_go_ids_map,
2171 automated_pairwise_comparison_suffix,
2173 surfacing.PAIRWISE_DOMAIN_COMPARISONS_PREFIX,
2177 String matrix_output_file = new String( output_file.toString() );
2178 if ( matrix_output_file.indexOf( '.' ) > 1 ) {
2179 matrix_output_file = matrix_output_file.substring( 0, matrix_output_file.indexOf( '.' ) );
2181 if ( out_dir != null ) {
2182 matrix_output_file = out_dir + ForesterUtil.FILE_SEPARATOR + matrix_output_file;
2183 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2185 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2186 + surfacing.MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans() );
2188 .writeMatrixToFile( new File( matrix_output_file
2189 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2190 pwgc.getSharedBinaryCombinationsBasedDistances() );
2191 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2192 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2193 pwgc.getSharedDomainsBasedDistances() );
2194 final Phylogeny nj_gd = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2195 + surfacing.NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans()
2197 final Phylogeny nj_bc = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2198 + surfacing.NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2199 .getSharedBinaryCombinationsBasedDistances().get( 0 ) );
2200 final Phylogeny nj_d = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2201 + surfacing.NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2202 .getSharedDomainsBasedDistances().get( 0 ) );
2203 inferred_trees = new ArrayList<Phylogeny>();
2204 inferred_trees.add( nj_gd );
2205 inferred_trees.add( nj_bc );
2206 inferred_trees.add( nj_d );
2207 if ( jacknifed_distances ) {
2208 pwgc.performPairwiseComparisonsJacknifed( species,
2212 jacknife_resamplings,
2216 .writeMatrixToFile( new File( matrix_output_file
2218 + ForesterUtil.round( jacknife_ratio, 2 )
2220 + jacknife_resamplings
2221 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2222 pwgc.getSharedBinaryCombinationsBasedDistances() );
2224 .writeMatrixToFile( new File( matrix_output_file + "_" + ForesterUtil.round( jacknife_ratio, 2 )
2225 + "_" + jacknife_resamplings
2226 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2227 pwgc.getSharedDomainsBasedDistances() );
2228 // if ( infer_species_trees ) {
2229 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2230 // + INFERRED_SBC_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc
2231 // .getSharedBinaryCombinationsBasedDistances() );
2232 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2233 // + INFERRED_SD_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc.getSharedDomainsBasedDistances() );
2236 } // if ( ( output_file != null ) && ( number_of_genomes > 2 ) && !isEmpty( automated_pairwise_comparison_suffix ) )
2237 if ( ( out_dir != null ) && ( !perform_pwc ) ) {
2238 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2240 writePresentToNexus( output_file, positive_filter_file, filter, gwcd_list );
2241 if ( ( ( intrees != null ) && ( intrees.length > 0 ) ) && ( number_of_genomes > 2 ) ) {
2242 final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
2244 max_allowed_overlap,
2245 no_engulfing_overlaps,
2249 if ( radomize_fitch_parsimony ) {
2250 s += random_number_seed_for_fitch_parsimony + "_";
2253 for( final Phylogeny intree : intrees ) {
2254 final String outfile_name = ForesterUtil.removeSuffix( output_file.toString() ) + s
2255 + ForesterUtil.removeSuffix( intree_files[ i ].toString() );
2256 final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator.createInstance( intree,
2258 SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
2259 radomize_fitch_parsimony,
2263 domain_id_to_go_ids_map,
2266 parameters_sb.toString(),
2267 domain_id_to_secondary_features_maps,
2268 positive_filter_file == null ? null : filter,
2269 output_binary_domain_combinationsfor_graph_analysis,
2270 all_bin_domain_combinations_gained_fitch,
2271 all_bin_domain_combinations_lost_fitch,
2273 protein_length_stats_by_dc,
2274 domain_number_stats_by_dc,
2275 domain_length_stats_by_domain );
2276 // Listing of all domain combinations gained is only done if only one input tree is used.
2277 if ( ( domain_id_to_secondary_features_maps != null )
2278 && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
2280 for( final Map<DomainId, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
2281 final Map<Species, MappingResults> mapping_results_map = new TreeMap<Species, MappingResults>();
2282 final DomainParsimonyCalculator secondary_features_parsimony = DomainParsimonyCalculator
2283 .createInstance( intree, gwcd_list, domain_id_to_secondary_features_map );
2285 .executeParsimonyAnalysisForSecondaryFeatures( outfile_name
2287 + secondary_features_map_files[ j++ ],
2288 secondary_features_parsimony,
2290 parameters_sb.toString(),
2291 mapping_results_map );
2293 System.out.println();
2294 System.out.println( "Mapping to secondary features:" );
2295 for( final Species spec : mapping_results_map.keySet() ) {
2296 final MappingResults mapping_results = mapping_results_map.get( spec );
2297 final int total_domains = mapping_results.getSumOfFailures()
2298 + mapping_results.getSumOfSuccesses();
2299 System.out.print( spec + ":" );
2300 System.out.print( " mapped domains = " + mapping_results.getSumOfSuccesses() );
2301 System.out.print( ", not mapped domains = " + mapping_results.getSumOfFailures() );
2302 if ( total_domains > 0 ) {
2303 System.out.println( ", mapped ratio = "
2304 + ( ( 100 * mapping_results.getSumOfSuccesses() ) / total_domains ) + "%" );
2307 System.out.println( ", mapped ratio = n/a (total domains = 0 )" );
2314 } // for( final Phylogeny intree : intrees ) {
2316 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
2317 executePlusMinusAnalysis( output_file,
2318 plus_minus_analysis_high_copy_base_species,
2319 plus_minus_analysis_high_copy_target_species,
2320 plus_minus_analysis_high_low_copy_species,
2322 protein_lists_per_species,
2323 domain_id_to_go_ids_map,
2325 plus_minus_analysis_numbers );
2327 if ( output_protein_lists_for_all_domains ) {
2328 writeProteinListsForAllSpecies( out_dir,
2329 protein_lists_per_species,
2331 output_list_of_all_proteins_per_domain_e_value_max );
2333 if ( all_bin_domain_combinations_gained_fitch != null ) {
2335 executeFitchGainsAnalysis( new File( output_file
2336 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2337 all_bin_domain_combinations_gained_fitch,
2338 all_domains_encountered.size(),
2339 all_bin_domain_combinations_encountered,
2342 catch ( final IOException e ) {
2343 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2346 if ( all_bin_domain_combinations_lost_fitch != null ) {
2348 executeFitchGainsAnalysis( new File( output_file
2349 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2350 all_bin_domain_combinations_lost_fitch,
2351 all_domains_encountered.size(),
2352 all_bin_domain_combinations_encountered,
2355 catch ( final IOException e ) {
2356 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2359 final Runtime rt = java.lang.Runtime.getRuntime();
2360 final long free_memory = rt.freeMemory() / 1000000;
2361 final long total_memory = rt.totalMemory() / 1000000;
2362 ForesterUtil.programMessage( PRG_NAME, "Time for analysis : " + ( new Date().getTime() - analysis_start_time )
2364 ForesterUtil.programMessage( PRG_NAME, "Total running time: " + ( new Date().getTime() - start_time ) + "ms " );
2365 ForesterUtil.programMessage( PRG_NAME, "Free memory : " + free_memory + "MB, total memory: "
2366 + total_memory + "MB" );
2367 ForesterUtil.programMessage( PRG_NAME, "If this application is useful to you, please cite:" );
2368 ForesterUtil.programMessage( PRG_NAME, surfacing.WWW );
2369 ForesterUtil.programMessage( PRG_NAME, "OK" );
2370 System.out.println();
2373 private static void createSplitWriters( final File out_dir,
2374 final String my_outfile,
2375 final Map<Character, Writer> split_writers ) throws IOException {
2376 split_writers.put( 'a', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2377 + "_domains_A.html" ) ) );
2378 split_writers.put( 'b', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2379 + "_domains_B.html" ) ) );
2380 split_writers.put( 'c', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2381 + "_domains_C.html" ) ) );
2382 split_writers.put( 'd', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2383 + "_domains_D.html" ) ) );
2384 split_writers.put( 'e', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2385 + "_domains_E.html" ) ) );
2386 split_writers.put( 'f', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2387 + "_domains_F.html" ) ) );
2388 split_writers.put( 'g', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2389 + "_domains_G.html" ) ) );
2390 split_writers.put( 'h', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2391 + "_domains_H.html" ) ) );
2392 split_writers.put( 'i', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2393 + "_domains_I.html" ) ) );
2394 split_writers.put( 'j', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2395 + "_domains_J.html" ) ) );
2396 split_writers.put( 'k', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2397 + "_domains_K.html" ) ) );
2398 split_writers.put( 'l', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2399 + "_domains_L.html" ) ) );
2400 split_writers.put( 'm', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2401 + "_domains_M.html" ) ) );
2402 split_writers.put( 'n', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2403 + "_domains_N.html" ) ) );
2404 split_writers.put( 'o', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2405 + "_domains_O.html" ) ) );
2406 split_writers.put( 'p', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2407 + "_domains_P.html" ) ) );
2408 split_writers.put( 'q', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2409 + "_domains_Q.html" ) ) );
2410 split_writers.put( 'r', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2411 + "_domains_R.html" ) ) );
2412 split_writers.put( 's', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2413 + "_domains_S.html" ) ) );
2414 split_writers.put( 't', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2415 + "_domains_T.html" ) ) );
2416 split_writers.put( 'u', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2417 + "_domains_U.html" ) ) );
2418 split_writers.put( 'v', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2419 + "_domains_V.html" ) ) );
2420 split_writers.put( 'w', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2421 + "_domains_W.html" ) ) );
2422 split_writers.put( 'x', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2423 + "_domains_X.html" ) ) );
2424 split_writers.put( 'y', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2425 + "_domains_Y.html" ) ) );
2426 split_writers.put( 'z', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2427 + "_domains_Z.html" ) ) );
2428 split_writers.put( '0', new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile
2429 + "_domains_0.html" ) ) );
2432 private static void printOutPercentageOfMultidomainProteins( final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo,
2433 final Writer log_writer ) {
2435 for( final Entry<Integer, Integer> entry : all_genomes_domains_per_potein_histo.entrySet() ) {
2436 sum += entry.getValue();
2438 final double percentage = ( 100.0 * ( sum - all_genomes_domains_per_potein_histo.get( 1 ) ) ) / sum;
2439 ForesterUtil.programMessage( PRG_NAME, "Percentage of multidomain proteins: " + percentage + "%" );
2440 log( "Percentage of multidomain proteins: : " + percentage + "%", log_writer );
2443 private static void preparePhylogenyForParsimonyAnalyses( final Phylogeny intree,
2444 final String[][] input_file_properties ) {
2445 final String[] genomes = new String[ input_file_properties.length ];
2446 for( int i = 0; i < input_file_properties.length; ++i ) {
2447 if ( intree.getNodes( input_file_properties[ i ][ 1 ] ).size() > 1 ) {
2448 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
2449 + "] is not unique in input tree " + intree.getName() );
2451 genomes[ i ] = input_file_properties[ i ][ 1 ];
2454 final PhylogenyNodeIterator it = intree.iteratorPostorder();
2455 while ( it.hasNext() ) {
2456 final PhylogenyNode n = it.next();
2457 if ( ForesterUtil.isEmpty( n.getName() ) ) {
2458 if ( n.getNodeData().isHasTaxonomy()
2459 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getTaxonomyCode() ) ) {
2460 n.setName( n.getNodeData().getTaxonomy().getTaxonomyCode() );
2462 else if ( n.getNodeData().isHasTaxonomy()
2463 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
2464 n.setName( n.getNodeData().getTaxonomy().getScientificName() );
2466 else if ( n.getNodeData().isHasTaxonomy()
2467 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getCommonName() ) ) {
2468 n.setName( n.getNodeData().getTaxonomy().getCommonName() );
2472 .fatalError( surfacing.PRG_NAME,
2473 "node with no name, scientific name, common name, or taxonomy code present" );
2478 final List<String> igns = PhylogenyMethods.deleteExternalNodesPositiveSelection( genomes, intree );
2479 if ( igns.size() > 0 ) {
2480 System.out.println( "Not using the following " + igns.size() + " nodes:" );
2481 for( int i = 0; i < igns.size(); ++i ) {
2482 System.out.println( " " + i + ": " + igns.get( i ) );
2484 System.out.println( "--" );
2486 for( final String[] input_file_propertie : input_file_properties ) {
2488 intree.getNode( input_file_propertie[ 1 ] );
2490 catch ( final IllegalArgumentException e ) {
2491 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_propertie[ 1 ]
2492 + "] not present/not unique in input tree" );
2497 private static void printHelp() {
2498 System.out.println();
2499 System.out.println( "Usage:" );
2500 System.out.println();
2501 System.out.println( "% java -Xms256m -Xmx512m -cp forester.jar org.forester.applications." + surfacing.PRG_NAME
2502 + " [options] <phylogen(y|ies) infile> [external node name 1] [name 2] ... [name n]" );
2503 System.out.println();
2504 System.out.println( " Note: This software might need a significant amount of memory (heap space);" );
2506 .println( " hence use \"-Xms128m -Xmx512m\" (or more) to prevent a \"java.lang.OutOfMemoryError\"." );
2507 System.out.println();
2508 System.out.println( " Options: " );
2509 System.out.println( surfacing.DETAILEDNESS_OPTION + ": level of detail for similarities output file (default:"
2510 + DETAILEDNESS_DEFAULT + ")" );
2511 System.out.println( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION
2512 + ": to ignore combinations with self (default: not to ignore)" );
2514 .println( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION
2515 + ": to ignore domains without combinations in any species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2517 .println( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION
2518 + ": to ignore domains specific to one species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2519 System.out.println( surfacing.NOT_IGNORE_DUFS_OPTION
2520 + ": to _not_ ignore DUFs (domains with unknown function) (default: ignore DUFs)" );
2522 .println( surfacing.IGNORE_VIRAL_IDS
2523 + ": to ignore domains with ids containing 'vir', 'retro', 'transpos', 'phage', or starting with 'rv' or 'gag_'" );
2524 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_OPTION + ": sorting for similarities (default: "
2525 + DOMAIN_SORT_FILD_DEFAULT + ")" );
2526 System.out.println( surfacing.OUTPUT_FILE_OPTION + ": name for (main) output file (mandatory)" );
2527 System.out.println( surfacing.MAX_E_VALUE_OPTION + ": max (inclusive) E-value" );
2528 System.out.println( surfacing.MAX_ALLOWED_OVERLAP_OPTION + ": maximal allowed domain overlap" );
2529 System.out.println( surfacing.NO_ENGULFING_OVERLAP_OPTION + ": to ignore engulfed lower confidence domains" );
2530 System.out.println( surfacing.SPECIES_MATRIX_OPTION + ": species matrix" );
2531 System.out.println( surfacing.SCORING_OPTION + ": scoring (default:" + SCORING_DEFAULT + ")" );
2532 System.out.println( surfacing.DOMAIN_COUNT_SORT_OPTION + ": sorting for domain counts (default:"
2533 + DOMAINS_SORT_ORDER_DEFAULT + ")" );
2534 System.out.println( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION + ": domain similarity print option (default:"
2535 + DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT + ")" );
2536 System.out.println( surfacing.CUTOFF_SCORE_FILE_OPTION + ": cutoff score file" );
2537 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION
2538 + ": sort by species count first" );
2539 System.out.println( surfacing.OUTPUT_DIR_OPTION + ": output directory" );
2540 System.out.println( surfacing.PFAM_TO_GO_FILE_USE_OPTION + ": Pfam to GO mapping file" );
2541 System.out.println( surfacing.GO_OBO_FILE_USE_OPTION + ": GO terms file (OBO format)" );
2542 System.out.println( surfacing.GO_NAMESPACE_LIMIT_OPTION + ": limit GO term to one GO namespace" );
2543 System.out.println( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
2544 + "[=<suffix for pairwise comparison output files>]: to perform pairwise comparison based analyses" );
2545 System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION
2546 + ": species tree, to perform (Dollo, Fitch) parismony analyses" );
2548 .println( JACKNIFE_OPTION
2549 + ": perform jacknife resampling for domain and binary domain combination based distance matrices [default resamplings: "
2550 + JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT + "]" );
2551 System.out.println( JACKNIFE_RATIO_OPTION + ": ratio for jacknife resampling [default: "
2552 + JACKNIFE_RATIO_DEFAULT + "]" );
2553 System.out.println( JACKNIFE_RANDOM_SEED_OPTION
2554 + ": seed for random number generator for jacknife resampling [default: "
2555 + JACKNIFE_RANDOM_SEED_DEFAULT + "]" );
2556 // System.out.println( surfacing.INFER_SPECIES_TREES_OPTION
2557 // + ": to infer NJ species trees based on shared domains/binary domain combinations" );
2559 .println( surfacing.INPUT_SPECIES_TREE_OPTION
2560 + "=<treefiles in phyloXML format, separated by #>: to infer domain/binary domain combination gains/losses on given species trees" );
2561 System.out.println( surfacing.FILTER_POSITIVE_OPTION
2562 + "=<file>: to filter out proteins not containing at least one domain listed in <file>" );
2563 System.out.println( surfacing.FILTER_NEGATIVE_OPTION
2564 + "=<file>: to filter out proteins containing at least one domain listed in <file>" );
2565 System.out.println( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION
2566 + "=<file>: to filter out (ignore) domains listed in <file>" );
2567 System.out.println( surfacing.INPUT_GENOMES_FILE_OPTION + "=<file>: to read input files from <file>" );
2569 .println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION
2570 + "=<seed>: seed for random number generator for Fitch Parsimony analysis (type: long, default: no randomization - given a choice, prefer absence" );
2571 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS
2572 + ": to consider directedness in binary combinations: e.g. A-B != B-A" );
2573 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY
2574 + ": to consider directedness and adjacency in binary combinations" );
2576 .println( surfacing.SEQ_EXTRACT_OPTION
2577 + "=<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')" );
2578 System.out.println( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE
2579 + "=<file>: to perfom parsimony analysis on secondary features" );
2580 System.out.println( surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>: to presence/absence genome analysis" );
2581 System.out.println( surfacing.DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS
2582 + ": to output binary domain combinations for (downstream) graph analysis" );
2583 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS + ": to output all proteins per domain" );
2584 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_PER_DOMAIN_E_VALUE_OPTION
2585 + ": e value max per domain for output of all proteins per domain" );
2586 System.out.println();
2587 System.out.println( "Example 1: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2588 + " org.forester.application.surfacing p2g=pfam2go_2012_02_07.txt -dufs -cos=Pfam_260_NC1"
2589 + " -no_eo -mo=0 -genomes=eukaryotes.txt -out_dir=out -o=o "
2590 + " -species_tree=tol.xml -obo=gene_ontology_2012_02_07.obo -pos_filter=f.txt -all_prot" );
2591 System.out.println();
2592 System.out.println( "Example 2: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2593 + " org.forester.application.surfacing -detail=punctilious -o=TEST.html -pwc=TEST"
2594 + " -cos=Pfam_ls_22_TC2 -p2g=pfam2go -obo=gene_ontology_edit.obo "
2595 + "-dc_sort=dom -ignore_with_self -no_singles -e=0.001 -mo=1 -no_eo -genomes=eukaryotes.txt "
2596 + "-ds_output=detailed_html -scoring=domains -sort=alpha " );
2597 System.out.println();
2600 private static void processFilter( final File filter_file, final SortedSet<DomainId> filter ) {
2601 SortedSet<String> filter_str = null;
2603 filter_str = ForesterUtil.file2set( filter_file );
2605 catch ( final IOException e ) {
2606 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2608 if ( filter_str != null ) {
2609 for( final String string : filter_str ) {
2610 filter.add( new DomainId( string ) );
2614 System.out.println( "Filter:" );
2615 for( final DomainId domainId : filter ) {
2616 System.out.println( domainId.getId() );
2621 private static String[][] processInputGenomesFile( final File input_genomes ) {
2622 String[][] input_file_properties = null;
2624 input_file_properties = ForesterUtil.file22dArray( input_genomes );
2626 catch ( final IOException e ) {
2627 ForesterUtil.fatalError( surfacing.PRG_NAME,
2628 "genomes files is to be in the following format \"<hmmpfam output file> <species>\": "
2629 + e.getLocalizedMessage() );
2631 final Set<String> specs = new HashSet<String>();
2632 final Set<String> paths = new HashSet<String>();
2633 for( int i = 0; i < input_file_properties.length; ++i ) {
2634 if ( !PhyloXmlUtil.TAXOMONY_CODE_PATTERN.matcher( input_file_properties[ i ][ 1 ] ).matches() ) {
2635 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for species code: "
2636 + input_file_properties[ i ][ 1 ] );
2638 if ( specs.contains( input_file_properties[ i ][ 1 ] ) ) {
2639 ForesterUtil.fatalError( surfacing.PRG_NAME, "species code " + input_file_properties[ i ][ 1 ]
2640 + " is not unique" );
2642 specs.add( input_file_properties[ i ][ 1 ] );
2643 if ( paths.contains( input_file_properties[ i ][ 0 ] ) ) {
2644 ForesterUtil.fatalError( surfacing.PRG_NAME, "path " + input_file_properties[ i ][ 0 ]
2645 + " is not unique" );
2647 paths.add( input_file_properties[ i ][ 0 ] );
2648 final String error = ForesterUtil.isReadableFile( new File( input_file_properties[ i ][ 0 ] ) );
2649 if ( !ForesterUtil.isEmpty( error ) ) {
2650 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
2653 return input_file_properties;
2656 private static void processPlusMinusAnalysisOption( final CommandLineArguments cla,
2657 final List<String> high_copy_base,
2658 final List<String> high_copy_target,
2659 final List<String> low_copy,
2660 final List<Object> numbers ) {
2661 if ( cla.isOptionSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2662 if ( !cla.isOptionValueSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2663 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for 'plus-minus' file: -"
2664 + surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>" );
2666 final File plus_minus_file = new File( cla.getOptionValue( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) );
2667 final String msg = ForesterUtil.isReadableFile( plus_minus_file );
2668 if ( !ForesterUtil.isEmpty( msg ) ) {
2669 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + plus_minus_file + "\": " + msg );
2671 processPlusMinusFile( plus_minus_file, high_copy_base, high_copy_target, low_copy, numbers );
2675 // First numbers is minimal difference, second is factor.
2676 private static void processPlusMinusFile( final File plus_minus_file,
2677 final List<String> high_copy_base,
2678 final List<String> high_copy_target,
2679 final List<String> low_copy,
2680 final List<Object> numbers ) {
2681 Set<String> species_set = null;
2682 int min_diff = PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT;
2683 double factor = PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT;
2685 species_set = ForesterUtil.file2set( plus_minus_file );
2687 catch ( final IOException e ) {
2688 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2690 if ( species_set != null ) {
2691 for( final String species : species_set ) {
2692 final String species_trimmed = species.substring( 1 );
2693 if ( species.startsWith( "+" ) ) {
2694 if ( low_copy.contains( species_trimmed ) ) {
2695 ForesterUtil.fatalError( surfacing.PRG_NAME,
2696 "species/genome names can not appear with both '+' and '-' suffix, as appears the case for: \""
2697 + species_trimmed + "\"" );
2699 high_copy_base.add( species_trimmed );
2701 else if ( species.startsWith( "*" ) ) {
2702 if ( low_copy.contains( species_trimmed ) ) {
2703 ForesterUtil.fatalError( surfacing.PRG_NAME,
2704 "species/genome names can not appear with both '*' and '-' suffix, as appears the case for: \""
2705 + species_trimmed + "\"" );
2707 high_copy_target.add( species_trimmed );
2709 else if ( species.startsWith( "-" ) ) {
2710 if ( high_copy_base.contains( species_trimmed ) || high_copy_target.contains( species_trimmed ) ) {
2711 ForesterUtil.fatalError( surfacing.PRG_NAME,
2712 "species/genome names can not appear with both '+' or '*' and '-' suffix, as appears the case for: \""
2713 + species_trimmed + "\"" );
2715 low_copy.add( species_trimmed );
2717 else if ( species.startsWith( "$D" ) ) {
2719 min_diff = Integer.parseInt( species.substring( 3 ) );
2721 catch ( final NumberFormatException e ) {
2722 ForesterUtil.fatalError( surfacing.PRG_NAME,
2723 "could not parse integer value for minimal difference from: \""
2724 + species.substring( 3 ) + "\"" );
2727 else if ( species.startsWith( "$F" ) ) {
2729 factor = Double.parseDouble( species.substring( 3 ) );
2731 catch ( final NumberFormatException e ) {
2732 ForesterUtil.fatalError( surfacing.PRG_NAME, "could not parse double value for factor from: \""
2733 + species.substring( 3 ) + "\"" );
2736 else if ( species.startsWith( "#" ) ) {
2741 .fatalError( surfacing.PRG_NAME,
2742 "species/genome names in 'plus minus' file must begin with '*' (high copy target genome), '+' (high copy base genomes), '-' (low copy genomes), '$D=<integer>' minimal Difference (default is 1), '$F=<double>' factor (default is 1.0), double), or '#' (ignore) suffix, encountered: \""
2745 numbers.add( new Integer( min_diff + "" ) );
2746 numbers.add( new Double( factor + "" ) );
2750 ForesterUtil.fatalError( surfacing.PRG_NAME, "'plus minus' file [" + plus_minus_file + "] appears empty" );
2754 private static void writePresentToNexus( final File output_file,
2755 final File positive_filter_file,
2756 final SortedSet<DomainId> filter,
2757 final List<GenomeWideCombinableDomains> gwcd_list ) {
2760 .writeMatrixToFile( DomainParsimonyCalculator
2761 .createMatrixOfDomainPresenceOrAbsence( gwcd_list, positive_filter_file == null ? null
2762 : filter ), output_file + DOMAINS_PRESENT_NEXUS, Format.NEXUS_BINARY );
2763 SurfacingUtil.writeMatrixToFile( DomainParsimonyCalculator
2764 .createMatrixOfBinaryDomainCombinationPresenceOrAbsence( gwcd_list ), output_file
2765 + BDC_PRESENT_NEXUS, Format.NEXUS_BINARY );
2767 catch ( final Exception e ) {
2768 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2772 private static void writeProteinListsForAllSpecies( final File output_dir,
2773 final SortedMap<Species, List<Protein>> protein_lists_per_species,
2774 final List<GenomeWideCombinableDomains> gwcd_list,
2775 final double domain_e_cutoff ) {
2776 final SortedSet<DomainId> all_domains = new TreeSet<DomainId>();
2777 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
2778 all_domains.addAll( gwcd.getAllDomainIds() );
2780 for( final DomainId domain : all_domains ) {
2781 final File out = new File( output_dir + ForesterUtil.FILE_SEPARATOR + domain + SEQ_EXTRACT_SUFFIX );
2782 SurfacingUtil.checkForOutputFileWriteability( out );
2784 final Writer proteins_file_writer = new BufferedWriter( new FileWriter( out ) );
2785 SurfacingUtil.extractProteinNames( protein_lists_per_species,
2787 proteins_file_writer,
2789 LIMIT_SPEC_FOR_PROT_EX,
2791 proteins_file_writer.close();
2793 catch ( final IOException e ) {
2794 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2796 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote proteins list to \"" + out + "\"" );