3 // FORESTER -- software libraries and applications
4 // for evolutionary biology research and applications.
6 // Copyright (C) 2008-2009 Christian M. Zmasek
7 // Copyright (C) 2008-2009 Burnham Institute for Medical Research
10 // This library is free software; you can redistribute it and/or
11 // modify it under the terms of the GNU Lesser General Public
12 // License as published by the Free Software Foundation; either
13 // version 2.1 of the License, or (at your option) any later version.
15 // This library is distributed in the hope that it will be useful,
16 // but WITHOUT ANY WARRANTY; without even the implied warranty of
17 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
18 // Lesser General Public License for more details.
20 // You should have received a copy of the GNU Lesser General Public
21 // License along with this library; if not, write to the Free Software
22 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
24 // Contact: phylosoft @ gmail . com
25 // WWW: www.phylosoft.org/forester
27 package org.forester.application;
29 import java.io.BufferedWriter;
31 import java.io.FileWriter;
32 import java.io.IOException;
33 import java.io.Writer;
34 import java.util.ArrayList;
35 import java.util.Date;
36 import java.util.HashSet;
37 import java.util.List;
39 import java.util.Map.Entry;
41 import java.util.SortedMap;
42 import java.util.SortedSet;
43 import java.util.TreeMap;
44 import java.util.TreeSet;
46 import org.forester.evoinference.distance.NeighborJoining;
47 import org.forester.evoinference.matrix.character.CharacterStateMatrix.Format;
48 import org.forester.evoinference.matrix.distance.DistanceMatrix;
49 import org.forester.go.GoId;
50 import org.forester.go.GoNameSpace;
51 import org.forester.go.GoTerm;
52 import org.forester.go.GoUtils;
53 import org.forester.go.OBOparser;
54 import org.forester.go.PfamToGoMapping;
55 import org.forester.go.PfamToGoParser;
56 import org.forester.io.parsers.HmmscanPerDomainTableParser;
57 import org.forester.io.parsers.HmmscanPerDomainTableParser.INDIVIDUAL_SCORE_CUTOFF;
58 import org.forester.io.parsers.util.ParserUtils;
59 import org.forester.io.writers.PhylogenyWriter;
60 import org.forester.phylogeny.Phylogeny;
61 import org.forester.phylogeny.PhylogenyMethods;
62 import org.forester.phylogeny.PhylogenyNode;
63 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
64 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
65 import org.forester.surfacing.BasicDomainSimilarityCalculator;
66 import org.forester.surfacing.BasicGenomeWideCombinableDomains;
67 import org.forester.surfacing.BasicSpecies;
68 import org.forester.surfacing.BinaryDomainCombination;
69 import org.forester.surfacing.CombinationsBasedPairwiseDomainSimilarityCalculator;
70 import org.forester.surfacing.DomainCountsBasedPairwiseSimilarityCalculator;
71 import org.forester.surfacing.DomainCountsDifferenceUtil;
72 import org.forester.surfacing.DomainId;
73 import org.forester.surfacing.DomainLengthsTable;
74 import org.forester.surfacing.DomainParsimonyCalculator;
75 import org.forester.surfacing.DomainSimilarity;
76 import org.forester.surfacing.DomainSimilarity.DomainSimilarityScoring;
77 import org.forester.surfacing.DomainSimilarity.DomainSimilaritySortField;
78 import org.forester.surfacing.DomainSimilarityCalculator;
79 import org.forester.surfacing.DomainSimilarityCalculator.Detailedness;
80 import org.forester.surfacing.GenomeWideCombinableDomains;
81 import org.forester.surfacing.GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder;
82 import org.forester.surfacing.MappingResults;
83 import org.forester.surfacing.PairwiseDomainSimilarityCalculator;
84 import org.forester.surfacing.PairwiseGenomeComparator;
85 import org.forester.surfacing.PrintableDomainSimilarity;
86 import org.forester.surfacing.PrintableDomainSimilarity.PRINT_OPTION;
87 import org.forester.surfacing.Protein;
88 import org.forester.surfacing.ProteinCountsBasedPairwiseDomainSimilarityCalculator;
89 import org.forester.surfacing.Species;
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 public final static String DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS = "graph_analysis_out";
102 public final static String DOMAIN_COMBINITONS_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_dc.dot";
103 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_fitch_present_dc.dot";
104 public final static String DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX = ".dcc";
106 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS = "_dollo_gl_d";
107 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_gl_dc";
108 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_DOMAINS = "_fitch_gl_d";
109 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_gl_dc";
111 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS = "_dollo_glc_d";
112 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_glc_dc";
113 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_DOMAINS = "_fitch_glc_d";
114 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_glc_dc";
116 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_BC = "_fitch_gains_dc";
117 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_HTML_BC = "_fitch_gains_dc.html";
118 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_BC = "_fitch_losses_dc";
119 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_HTML_BC = "_fitch_losses_dc.html";
120 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC = "_fitch_present_dc";
121 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_HTML_BC = "_fitch_present_dc.html";
122 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_D = "_dollo_gains_d";
123 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_HTML_D = "_dollo_gains_d.html";
124 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_D = "_dollo_losses_d";
125 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_HTML_D = "_dollo_losses_d.html";
126 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_D = "_dollo_present_d";
127 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_HTML_D = "_dollo_present_d.html";
128 public final static String DOMAINS_PRESENT_NEXUS = "_dom.nex";
129 public final static String BDC_PRESENT_NEXUS = "_dc.nex";
131 public final static String PRG_NAME = "surfacing";
132 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_d_dollo"
133 + ForesterConstants.PHYLO_XML_SUFFIX;
134 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_d_fitch"
135 + ForesterConstants.PHYLO_XML_SUFFIX;
136 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_dc_dollo"
137 + ForesterConstants.PHYLO_XML_SUFFIX;
138 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_dc_fitch"
139 + ForesterConstants.PHYLO_XML_SUFFIX;
140 public static final String NEXUS_EXTERNAL_DOMAINS = "_dom.nex";
141 public static final String NEXUS_EXTERNAL_DOMAIN_COMBINATIONS = "_dc.nex";
142 public static final String NEXUS_SECONDARY_FEATURES = "_secondary_features.nex";
143 public static final String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_gl_secondary_features";
144 public static final String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_glc_secondary_features";
145 public static final String PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES = "_dollo_gains_secondary_features";
146 public static final String PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES = "_dollo_losses_secondary_features";
147 public static final String PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES = "_dollo_present_secondary_features";
148 public static final String SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_secondary_features_dollo"
149 + ForesterConstants.PHYLO_XML_SUFFIX;
150 public static final String PARSIMONY_OUTPUT_DOLLO_ALL_GOID_D_ALL_NAMESPACES = "_dollo_goid_d";
151 public static final String PARSIMONY_OUTPUT_FITCH_ALL_GOID_BC_ALL_NAMESPACES = "_fitch_goid_dc";
152 final static private String HELP_OPTION_1 = "help";
153 final static private String HELP_OPTION_2 = "h";
154 final static private String OUTPUT_DIR_OPTION = "out_dir";
155 final static private String SCORING_OPTION = "scoring";
156 private static final DomainSimilarityScoring SCORING_DEFAULT = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
157 final static private String SCORING_DOMAIN_COUNT_BASED = "domains";
158 final static private String SCORING_PROTEIN_COUNT_BASED = "proteins";
159 final static private String SCORING_COMBINATION_BASED = "combinations";
160 final static private String DETAILEDNESS_OPTION = "detail";
161 private final static Detailedness DETAILEDNESS_DEFAULT = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
162 final static private String SPECIES_MATRIX_OPTION = "smatrix";
163 final static private String DETAILEDNESS_BASIC = "basic";
164 final static private String DETAILEDNESS_LIST_IDS = "list_ids";
165 final static private String DETAILEDNESS_PUNCTILIOUS = "punctilious";
166 final static private String DOMAIN_SIMILARITY_SORT_OPTION = "sort";
167 private static final DomainSimilaritySortField DOMAIN_SORT_FILD_DEFAULT = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
168 final static private String DOMAIN_SIMILARITY_SORT_MIN = "min";
169 final static private String DOMAIN_SIMILARITY_SORT_MAX = "max";
170 final static private String DOMAIN_SIMILARITY_SORT_SD = "sd";
171 final static private String DOMAIN_SIMILARITY_SORT_MEAN = "mean";
172 final static private String DOMAIN_SIMILARITY_SORT_DIFF = "diff";
173 final static private String DOMAIN_SIMILARITY_SORT_COUNTS_DIFF = "count_diff";
174 final static private String DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF = "abs_count_diff";
175 final static private String DOMAIN_SIMILARITY_SORT_SPECIES_COUNT = "species";
176 final static private String DOMAIN_SIMILARITY_SORT_ALPHA = "alpha";
177 final static private String DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION = "species_first";
178 final static private String DOMAIN_COUNT_SORT_OPTION = "dc_sort";
179 private static final GenomeWideCombinableDomainsSortOrder DOMAINS_SORT_ORDER_DEFAULT = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
180 final static private String DOMAIN_COUNT_SORT_ALPHA = "alpha";
181 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT = "dom";
182 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT = "prot";
183 final static private String DOMAIN_COUNT_SORT_COMBINATIONS_COUNT = "comb";
184 final static private String CUTOFF_SCORE_FILE_OPTION = "cos";
185 final static private String NOT_IGNORE_DUFS_OPTION = "dufs";
186 final static private String MAX_E_VALUE_OPTION = "e";
187 final static private String MAX_ALLOWED_OVERLAP_OPTION = "mo";
188 final static private String NO_ENGULFING_OVERLAP_OPTION = "no_eo";
189 final static private String IGNORE_COMBINATION_WITH_SAME_OPTION = "ignore_self_comb";
190 final static private String PAIRWISE_DOMAIN_COMPARISONS_PREFIX = "pwc_";
191 final static private String PAIRWISE_DOMAIN_COMPARISONS_OPTION = "pwc";
192 final static private String OUTPUT_FILE_OPTION = "o";
193 final static private String PFAM_TO_GO_FILE_USE_OPTION = "p2g";
194 final static private String GO_OBO_FILE_USE_OPTION = "obo";
195 final static private String GO_NAMESPACE_LIMIT_OPTION = "go_namespace";
196 final static private String GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION = "molecular_function";
197 final static private String GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS = "biological_process";
198 final static private String GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT = "cellular_component";
199 final static private String SECONDARY_FEATURES_PARSIMONY_MAP_FILE = "secondary";
200 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED = "simple_tab";
201 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML = "simple_html";
202 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML = "detailed_html";
203 final static private String DOMAIN_SIMILARITY_PRINT_OPTION = "ds_output";
204 private static final PRINT_OPTION DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT = PrintableDomainSimilarity.PRINT_OPTION.HTML;
205 final static private String IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION = "ignore_singlet_domains";
206 final static private String IGNORE_VIRAL_IDS = "ignore_viral_ids";
207 final static private boolean IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT = false;
208 final static private String IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION = "ignore_species_specific_domains";
209 final static private boolean IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT = false;
210 final static private String MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score.pwd";
211 final static private String MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains.pwd";
212 final static private String MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations.pwd";
213 final static private String NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score_NJ"
214 + ForesterConstants.PHYLO_XML_SUFFIX;
215 final static private String NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains_NJ"
216 + ForesterConstants.PHYLO_XML_SUFFIX;
217 final static private String NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations_NJ"
218 + ForesterConstants.PHYLO_XML_SUFFIX;
219 final static private String JACKNIFE_OPTION = "jack";
220 final static private String JACKNIFE_RANDOM_SEED_OPTION = "seed";
221 final static private String JACKNIFE_RATIO_OPTION = "jack_ratio";
222 private static final int JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT = 100;
223 final static private long JACKNIFE_RANDOM_SEED_DEFAULT = 19;
224 final static private double JACKNIFE_RATIO_DEFAULT = 0.5;
225 //final static private String INFER_SPECIES_TREES_OPTION = "species_tree_inference";
226 final static private String INFERRED_SD_BASED_NJ_SPECIES_TREE_SUFFIX = "_sd_nj.nh";
227 final static private String INFERRED_SBC_BASED_NJ_SPECIES_TREE_SUFFIX = "_sbc_nj.nh";
228 final static private String FILTER_POSITIVE_OPTION = "pos_filter";
229 final static private String FILTER_NEGATIVE_OPTION = "neg_filter";
230 final static private String FILTER_NEGATIVE_DOMAINS_OPTION = "neg_dom_filter";
231 final static private String INPUT_FILES_FROM_FILE_OPTION = "input";
232 final static private String INPUT_SPECIES_TREE_OPTION = "species_tree";
233 final static private String SEQ_EXTRACT_OPTION = "prot_extract";
234 final static private char SEPARATOR_FOR_INPUT_VALUES = '#';
235 final static private String PRG_VERSION = "2.200";
236 final static private String PRG_DATE = "2011.10.18";
237 final static private String E_MAIL = "czmasek@burnham.org";
238 final static private String WWW = "www.phylosoft.org/forester/applications/surfacing";
239 final static private boolean IGNORE_DUFS_DEFAULT = true;
240 final static private boolean IGNORE_COMBINATION_WITH_SAME_DEFAULLT = false;
241 final static private double MAX_E_VALUE_DEFAULT = -1;
242 final static private int MAX_ALLOWED_OVERLAP_DEFAULT = -1;
243 private static final String RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION = "random_seed";
244 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS = "consider_bdc_direction";
245 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY = "consider_bdc_adj";
246 private static final String SEQ_EXTRACT_SUFFIX = ".prot";
247 private static final String PLUS_MINUS_ANALYSIS_OPTION = "plus_minus";
248 private static final String PLUS_MINUS_DOM_SUFFIX = "_plus_minus_dom.txt";
249 private static final String PLUS_MINUS_DOM_SUFFIX_HTML = "_plus_minus_dom.html";
250 private static final String PLUS_MINUS_DC_SUFFIX_HTML = "_plus_minus_dc.html";
251 private static final int PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT = 0;
252 private static final double PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT = 1.0;
253 private static final String PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_all.txt";
254 private static final String PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_passing.txt";
255 private static final String OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS = "all_prot";
256 private static final boolean VERBOSE = false;
257 private static final String OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_gains_counts";
258 private static final String OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_losses_counts";
259 private static final String DOMAIN_LENGTHS_ANALYSIS_SUFFIX = "_domain_lengths_analysis";
260 private static final boolean PERFORM_DOMAIN_LENGTH_ANALYSIS = true;
261 public static final String ALL_PFAMS_ENCOUNTERED_SUFFIX = "_all_encountered_pfams";
262 public static final String ALL_PFAMS_ENCOUNTERED_WITH_GO_ANNOTATION_SUFFIX = "_all_encountered_pfams_with_go_annotation";
263 public static final String ENCOUNTERED_PFAMS_SUMMARY_SUFFIX = "_encountered_pfams_summary";
264 public static final String ALL_PFAMS_GAINED_AS_DOMAINS_SUFFIX = "_all_pfams_gained_as_domains";
265 public static final String ALL_PFAMS_LOST_AS_DOMAINS_SUFFIX = "_all_pfams_lost_as_domains";
266 public static final String ALL_PFAMS_GAINED_AS_DC_SUFFIX = "_all_pfams_gained_as_dc";
267 public static final String ALL_PFAMS_LOST_AS_DC_SUFFIX = "_all_pfams_lost_as_dc";
268 public static final String BASE_DIRECTORY_PER_NODE_DOMAIN_GAIN_LOSS_FILES = "PER_NODE_EVENTS";
269 public static final String BASE_DIRECTORY_PER_SUBTREE_DOMAIN_GAIN_LOSS_FILES = "PER_SUBTREE_EVENTS";
270 public static final String D_PROMISCUITY_FILE_SUFFIX = "_domain_promiscuities";
271 private static final String LOG_FILE_SUFFIX = "_log.txt";
272 private static final String DATA_FILE_SUFFIX = "_domain_combination_data.txt";
273 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";
274 private static final INDIVIDUAL_SCORE_CUTOFF INDIVIDUAL_SCORE_CUTOFF_DEFAULT = INDIVIDUAL_SCORE_CUTOFF.FULL_SEQUENCE;
275 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts.txt";
276 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists.txt";
277 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping.txt";
278 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";
280 private static void checkWriteabilityForPairwiseComparisons( final PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option,
281 final String[][] input_file_properties,
282 final String automated_pairwise_comparison_suffix,
283 final File outdir ) {
284 for( int i = 0; i < input_file_properties.length; ++i ) {
285 for( int j = 0; j < i; ++j ) {
286 final String species_i = input_file_properties[ i ][ 1 ];
287 final String species_j = input_file_properties[ j ][ 1 ];
288 String pairwise_similarities_output_file_str = PAIRWISE_DOMAIN_COMPARISONS_PREFIX + species_i + "_"
289 + species_j + automated_pairwise_comparison_suffix;
290 switch ( domain_similarity_print_option ) {
292 if ( !pairwise_similarities_output_file_str.endsWith( ".html" ) ) {
293 pairwise_similarities_output_file_str += ".html";
297 final String error = ForesterUtil
298 .isWritableFile( new File( outdir == null ? pairwise_similarities_output_file_str : outdir
299 + ForesterUtil.FILE_SEPARATOR + pairwise_similarities_output_file_str ) );
300 if ( !ForesterUtil.isEmpty( error ) ) {
301 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
307 private static StringBuilder createParametersAsString( final boolean ignore_dufs,
308 final double e_value_max,
309 final int max_allowed_overlap,
310 final boolean no_engulfing_overlaps,
311 final File cutoff_scores_file,
312 final BinaryDomainCombination.DomainCombinationType dc_type ) {
313 final StringBuilder parameters_sb = new StringBuilder();
314 parameters_sb.append( "E-value: " + e_value_max );
315 if ( cutoff_scores_file != null ) {
316 parameters_sb.append( ", Cutoff-scores-file: " + cutoff_scores_file );
319 parameters_sb.append( ", Cutoff-scores-file: not-set" );
321 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
322 parameters_sb.append( ", Max-overlap: " + max_allowed_overlap );
325 parameters_sb.append( ", Max-overlap: not-set" );
327 if ( no_engulfing_overlaps ) {
328 parameters_sb.append( ", Engulfing-overlaps: not-allowed" );
331 parameters_sb.append( ", Engulfing-overlaps: allowed" );
334 parameters_sb.append( ", Ignore-dufs: true" );
337 parameters_sb.append( ", Ignore-dufs: false" );
339 parameters_sb.append( ", DC type (if applicable): " + dc_type );
340 return parameters_sb;
344 * Warning: This side-effects 'all_bin_domain_combinations_encountered'!
348 * @param all_bin_domain_combinations_changed
349 * @param sum_of_all_domains_encountered
350 * @param all_bin_domain_combinations_encountered
351 * @param is_gains_analysis
352 * @throws IOException
354 private static void executeFitchGainsAnalysis( final File output_file,
355 final List<BinaryDomainCombination> all_bin_domain_combinations_changed,
356 final int sum_of_all_domains_encountered,
357 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered,
358 final boolean is_gains_analysis ) throws IOException {
359 SurfacingUtil.checkForOutputFileWriteability( output_file );
360 final Writer out = ForesterUtil.createBufferedWriter( output_file );
361 final SortedMap<Object, Integer> bdc_to_counts = ForesterUtil
362 .listToSortedCountsMap( all_bin_domain_combinations_changed );
363 final SortedSet<DomainId> all_domains_in_combination_changed_more_than_once = new TreeSet<DomainId>();
364 final SortedSet<DomainId> all_domains_in_combination_changed_only_once = new TreeSet<DomainId>();
367 for( final Object bdc_object : bdc_to_counts.keySet() ) {
368 final BinaryDomainCombination bdc = ( BinaryDomainCombination ) bdc_object;
369 final int count = bdc_to_counts.get( bdc_object );
371 ForesterUtil.unexpectedFatalError( PRG_NAME, "count < 1 " );
373 out.write( bdc + "\t" + count + ForesterUtil.LINE_SEPARATOR );
375 all_domains_in_combination_changed_more_than_once.add( bdc.getId0() );
376 all_domains_in_combination_changed_more_than_once.add( bdc.getId1() );
379 else if ( count == 1 ) {
380 all_domains_in_combination_changed_only_once.add( bdc.getId0() );
381 all_domains_in_combination_changed_only_once.add( bdc.getId1() );
385 final int all = all_bin_domain_combinations_encountered.size();
387 if ( !is_gains_analysis ) {
388 all_bin_domain_combinations_encountered.removeAll( all_bin_domain_combinations_changed );
389 never_lost = all_bin_domain_combinations_encountered.size();
390 for( final BinaryDomainCombination bdc : all_bin_domain_combinations_encountered ) {
391 out.write( bdc + "\t" + "0" + ForesterUtil.LINE_SEPARATOR );
394 if ( is_gains_analysis ) {
395 out.write( "Sum of all distinct domain combinations appearing once : " + one
396 + ForesterUtil.LINE_SEPARATOR );
397 out.write( "Sum of all distinct domain combinations appearing more than once : " + above_one
398 + ForesterUtil.LINE_SEPARATOR );
399 out.write( "Sum of all distinct domains in combinations apppearing only once : "
400 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
401 out.write( "Sum of all distinct domains in combinations apppearing more than once: "
402 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
405 out.write( "Sum of all distinct domain combinations never lost : " + never_lost
406 + ForesterUtil.LINE_SEPARATOR );
407 out.write( "Sum of all distinct domain combinations lost once : " + one
408 + ForesterUtil.LINE_SEPARATOR );
409 out.write( "Sum of all distinct domain combinations lost more than once : " + above_one
410 + ForesterUtil.LINE_SEPARATOR );
411 out.write( "Sum of all distinct domains in combinations lost only once : "
412 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
413 out.write( "Sum of all distinct domains in combinations lost more than once: "
414 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
416 out.write( "All binary combinations : " + all
417 + ForesterUtil.LINE_SEPARATOR );
418 out.write( "All domains : "
419 + sum_of_all_domains_encountered );
421 ForesterUtil.programMessage( surfacing.PRG_NAME,
422 "Wrote fitch domain combination dynamics counts analysis to \"" + output_file
426 private static void executePlusMinusAnalysis( final File output_file,
427 final List<String> plus_minus_analysis_high_copy_base,
428 final List<String> plus_minus_analysis_high_copy_target,
429 final List<String> plus_minus_analysis_low_copy,
430 final List<GenomeWideCombinableDomains> gwcd_list,
431 final SortedMap<Species, List<Protein>> protein_lists_per_species,
432 final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
433 final Map<GoId, GoTerm> go_id_to_term_map,
434 final List<Object> plus_minus_analysis_numbers ) {
435 final Set<String> all_spec = new HashSet<String>();
436 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
437 all_spec.add( gwcd.getSpecies().getSpeciesId() );
439 final File html_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX_HTML );
440 final File plain_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX );
441 final File html_out_dc = new File( output_file + PLUS_MINUS_DC_SUFFIX_HTML );
442 final File all_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX );
443 final File passing_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX );
444 final File proteins_file_base = new File( output_file + "" );
445 final int min_diff = ( ( Integer ) plus_minus_analysis_numbers.get( 0 ) ).intValue();
446 final double factor = ( ( Double ) plus_minus_analysis_numbers.get( 1 ) ).doubleValue();
448 DomainCountsDifferenceUtil.calculateCopyNumberDifferences( gwcd_list,
449 protein_lists_per_species,
450 plus_minus_analysis_high_copy_base,
451 plus_minus_analysis_high_copy_target,
452 plus_minus_analysis_low_copy,
458 domain_id_to_go_ids_map,
460 all_domains_go_ids_out_dom,
461 passing_domains_go_ids_out_dom,
462 proteins_file_base );
464 catch ( final IOException e ) {
465 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
467 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
468 + html_out_dom + "\"" );
469 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
470 + plain_out_dom + "\"" );
471 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \"" + html_out_dc
473 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based passing GO ids to \""
474 + passing_domains_go_ids_out_dom + "\"" );
475 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based all GO ids to \""
476 + all_domains_go_ids_out_dom + "\"" );
479 private static Phylogeny[] getIntrees( final File[] intree_files,
480 final int number_of_genomes,
481 final String[][] input_file_properties ) {
482 final Phylogeny[] intrees = new Phylogeny[ intree_files.length ];
484 for( final File intree_file : intree_files ) {
485 Phylogeny intree = null;
486 final String error = ForesterUtil.isReadableFile( intree_file );
487 if ( !ForesterUtil.isEmpty( error ) ) {
488 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read input tree file [" + intree_file + "]: "
492 final Phylogeny[] p_array = ParserBasedPhylogenyFactory.getInstance()
493 .create( intree_file, ParserUtils.createParserDependingOnFileType( intree_file, true ) );
494 if ( p_array.length < 1 ) {
495 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
496 + "] does not contain any phylogeny in phyloXML format" );
498 else if ( p_array.length > 1 ) {
499 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
500 + "] contains more than one phylogeny in phyloXML format" );
502 intree = p_array[ 0 ];
504 catch ( final Exception e ) {
505 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read input tree from file [" + intree_file
508 if ( ( intree == null ) || intree.isEmpty() ) {
509 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" );
511 if ( !intree.isRooted() ) {
512 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is not rooted" );
514 if ( intree.getNumberOfExternalNodes() < number_of_genomes ) {
515 ForesterUtil.fatalError( surfacing.PRG_NAME,
516 "number of external nodes [" + intree.getNumberOfExternalNodes()
517 + "] of input tree [" + intree_file
518 + "] is smaller than the number of genomes the be analyzed ["
519 + number_of_genomes + "]" );
521 final StringBuilder parent_names = new StringBuilder();
522 final int nodes_lacking_name = SurfacingUtil.getNumberOfNodesLackingName( intree, parent_names );
523 if ( nodes_lacking_name > 0 ) {
524 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] has "
525 + nodes_lacking_name + " node(s) lacking a name [parent names:" + parent_names + "]" );
527 preparePhylogenyForParsimonyAnalyses( intree, input_file_properties );
528 if ( !intree.isCompletelyBinary() ) {
529 ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "input tree [" + intree_file
530 + "] is not completely binary" );
532 intrees[ i++ ] = intree;
537 private static List<Phylogeny> inferSpeciesTrees( final File outfile, final List<DistanceMatrix> distances_list ) {
538 final NeighborJoining nj = NeighborJoining.createInstance();
539 final List<Phylogeny> phylogenies = nj.execute( distances_list );
540 final PhylogenyWriter w = new PhylogenyWriter();
542 w.toNewHampshire( phylogenies, true, true, outfile, ";" );
544 catch ( final IOException e ) {
545 ForesterUtil.fatalError( PRG_NAME, "failed to write to outfile [" + outfile + "]: " + e.getMessage() );
550 private static void log( final String msg, final Writer w ) {
553 w.write( ForesterUtil.LINE_SEPARATOR );
555 catch ( final IOException e ) {
556 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
560 public static void main( final String args[] ) {
561 final long start_time = new Date().getTime();
562 // final StringBuffer log = new StringBuffer();
563 final StringBuilder html_desc = new StringBuilder();
564 ForesterUtil.printProgramInformation( surfacing.PRG_NAME,
565 surfacing.PRG_VERSION,
569 final String nl = ForesterUtil.LINE_SEPARATOR;
570 html_desc.append( "<table>" + nl );
571 html_desc.append( "<tr><td>Produced by:</td><td>" + surfacing.PRG_NAME + "</td></tr>" + nl );
572 html_desc.append( "<tr><td>Version:</td><td>" + surfacing.PRG_VERSION + "</td></tr>" + nl );
573 html_desc.append( "<tr><td>Release Date:</td><td>" + surfacing.PRG_DATE + "</td></tr>" + nl );
574 html_desc.append( "<tr><td>Contact:</td><td>" + surfacing.E_MAIL + "</td></tr>" + nl );
575 html_desc.append( "<tr><td>WWW:</td><td>" + surfacing.WWW + "</td></tr>" + nl );
576 CommandLineArguments cla = null;
578 cla = new CommandLineArguments( args );
580 catch ( final Exception e ) {
581 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
583 if ( cla.isOptionSet( surfacing.HELP_OPTION_1 ) || cla.isOptionSet( surfacing.HELP_OPTION_2 ) ) {
584 surfacing.printHelp();
587 if ( ( args.length < 1 ) ) {
588 surfacing.printHelp();
591 final List<String> allowed_options = new ArrayList<String>();
592 allowed_options.add( surfacing.NOT_IGNORE_DUFS_OPTION );
593 allowed_options.add( surfacing.MAX_E_VALUE_OPTION );
594 allowed_options.add( surfacing.DETAILEDNESS_OPTION );
595 allowed_options.add( surfacing.OUTPUT_FILE_OPTION );
596 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_OPTION );
597 allowed_options.add( surfacing.SPECIES_MATRIX_OPTION );
598 allowed_options.add( surfacing.SCORING_OPTION );
599 allowed_options.add( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
600 allowed_options.add( surfacing.NO_ENGULFING_OVERLAP_OPTION );
601 allowed_options.add( surfacing.DOMAIN_COUNT_SORT_OPTION );
602 allowed_options.add( surfacing.CUTOFF_SCORE_FILE_OPTION );
603 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION );
604 allowed_options.add( surfacing.OUTPUT_DIR_OPTION );
605 allowed_options.add( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION );
606 allowed_options.add( surfacing.PFAM_TO_GO_FILE_USE_OPTION );
607 allowed_options.add( surfacing.GO_OBO_FILE_USE_OPTION );
608 allowed_options.add( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION );
609 allowed_options.add( surfacing.GO_NAMESPACE_LIMIT_OPTION );
610 allowed_options.add( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
611 allowed_options.add( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION );
612 allowed_options.add( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS );
613 allowed_options.add( JACKNIFE_OPTION );
614 allowed_options.add( JACKNIFE_RANDOM_SEED_OPTION );
615 allowed_options.add( JACKNIFE_RATIO_OPTION );
616 allowed_options.add( INPUT_SPECIES_TREE_OPTION );
617 //allowed_options.add( INFER_SPECIES_TREES_OPTION );
618 allowed_options.add( FILTER_POSITIVE_OPTION );
619 allowed_options.add( FILTER_NEGATIVE_OPTION );
620 allowed_options.add( INPUT_FILES_FROM_FILE_OPTION );
621 allowed_options.add( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
622 allowed_options.add( FILTER_NEGATIVE_DOMAINS_OPTION );
623 allowed_options.add( IGNORE_VIRAL_IDS );
624 allowed_options.add( SEQ_EXTRACT_OPTION );
625 allowed_options.add( SECONDARY_FEATURES_PARSIMONY_MAP_FILE );
626 allowed_options.add( PLUS_MINUS_ANALYSIS_OPTION );
627 allowed_options.add( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS );
628 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS );
629 allowed_options.add( CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY );
630 boolean ignore_dufs = surfacing.IGNORE_DUFS_DEFAULT;
631 boolean ignore_combination_with_same = surfacing.IGNORE_COMBINATION_WITH_SAME_DEFAULLT;
632 double e_value_max = surfacing.MAX_E_VALUE_DEFAULT;
633 int max_allowed_overlap = surfacing.MAX_ALLOWED_OVERLAP_DEFAULT;
634 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
635 if ( dissallowed_options.length() > 0 ) {
636 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown option(s): " + dissallowed_options );
638 boolean output_binary_domain_combinationsfor_graph_analysis = false;
639 if ( cla.isOptionSet( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS ) ) {
640 output_binary_domain_combinationsfor_graph_analysis = true;
642 if ( cla.isOptionSet( surfacing.MAX_E_VALUE_OPTION ) ) {
644 e_value_max = cla.getOptionValueAsDouble( surfacing.MAX_E_VALUE_OPTION );
646 catch ( final Exception e ) {
647 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for E-value maximum" );
650 if ( cla.isOptionSet( surfacing.MAX_ALLOWED_OVERLAP_OPTION ) ) {
652 max_allowed_overlap = cla.getOptionValueAsInt( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
654 catch ( final Exception e ) {
655 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for maximal allowed domain overlap" );
658 boolean no_engulfing_overlaps = false;
659 if ( cla.isOptionSet( surfacing.NO_ENGULFING_OVERLAP_OPTION ) ) {
660 no_engulfing_overlaps = true;
662 boolean ignore_virus_like_ids = false;
663 if ( cla.isOptionSet( surfacing.IGNORE_VIRAL_IDS ) ) {
664 ignore_virus_like_ids = true;
666 if ( cla.isOptionSet( surfacing.NOT_IGNORE_DUFS_OPTION ) ) {
669 if ( cla.isOptionSet( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION ) ) {
670 ignore_combination_with_same = true;
672 boolean ignore_domains_without_combs_in_all_spec = IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT;
673 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION ) ) {
674 ignore_domains_without_combs_in_all_spec = true;
676 boolean ignore_species_specific_domains = IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT;
677 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION ) ) {
678 ignore_species_specific_domains = true;
680 File output_file = null;
681 if ( cla.isOptionSet( surfacing.OUTPUT_FILE_OPTION ) ) {
682 if ( !cla.isOptionValueSet( surfacing.OUTPUT_FILE_OPTION ) ) {
683 ForesterUtil.fatalError( surfacing.PRG_NAME,
684 "no value for domain combinations similarities output file: -"
685 + surfacing.OUTPUT_FILE_OPTION + "=<file>" );
687 output_file = new File( cla.getOptionValue( surfacing.OUTPUT_FILE_OPTION ) );
688 SurfacingUtil.checkForOutputFileWriteability( output_file );
690 File cutoff_scores_file = null;
691 Map<String, Double> individual_score_cutoffs = null;
692 if ( cla.isOptionSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
693 if ( !cla.isOptionValueSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
694 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for individual domain score cutoffs file: -"
695 + surfacing.CUTOFF_SCORE_FILE_OPTION + "=<file>" );
697 cutoff_scores_file = new File( cla.getOptionValue( surfacing.CUTOFF_SCORE_FILE_OPTION ) );
698 final String error = ForesterUtil.isReadableFile( cutoff_scores_file );
699 if ( !ForesterUtil.isEmpty( error ) ) {
700 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read individual domain score cutoffs file: "
704 final BasicTable<String> scores_table = BasicTableParser.parse( cutoff_scores_file, " " );
705 individual_score_cutoffs = scores_table.getColumnsAsMapDouble( 0, 1 );
707 catch ( final IOException e ) {
708 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from individual score cutoffs file: " + e );
711 BinaryDomainCombination.DomainCombinationType dc_type = BinaryDomainCombination.DomainCombinationType.BASIC;
712 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS ) ) {
713 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED;
715 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY ) ) {
716 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT;
719 if ( cla.isOptionSet( surfacing.OUTPUT_DIR_OPTION ) ) {
720 if ( !cla.isOptionValueSet( surfacing.OUTPUT_DIR_OPTION ) ) {
721 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for output directory: -"
722 + surfacing.OUTPUT_DIR_OPTION + "=<dir>" );
724 out_dir = new File( cla.getOptionValue( surfacing.OUTPUT_DIR_OPTION ) );
725 if ( out_dir.exists() && ( out_dir.listFiles().length > 0 ) ) {
726 ForesterUtil.fatalError( surfacing.PRG_NAME, "\"" + out_dir + "\" aready exists and is not empty" );
728 if ( !out_dir.exists() ) {
729 final boolean success = out_dir.mkdir();
730 if ( !success || !out_dir.exists() ) {
731 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to create \"" + out_dir + "\"" );
734 if ( !out_dir.canWrite() ) {
735 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot write to \"" + out_dir + "\"" );
738 File positive_filter_file = null;
739 File negative_filter_file = null;
740 File negative_domains_filter_file = null;
741 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) && cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
742 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use both negative and positive protein filter" );
744 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION )
745 && ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) || cla
746 .isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) ) {
748 .fatalError( surfacing.PRG_NAME,
749 "attempt to use both negative or positive protein filter together wirh a negative domains filter" );
751 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
752 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
753 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative filter: -"
754 + surfacing.FILTER_NEGATIVE_OPTION + "=<file>" );
756 negative_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_OPTION ) );
757 final String msg = ForesterUtil.isReadableFile( negative_filter_file );
758 if ( !ForesterUtil.isEmpty( msg ) ) {
759 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_filter_file + "\": "
763 else if ( cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
764 if ( !cla.isOptionValueSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
765 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for positive filter: -"
766 + surfacing.FILTER_POSITIVE_OPTION + "=<file>" );
768 positive_filter_file = new File( cla.getOptionValue( surfacing.FILTER_POSITIVE_OPTION ) );
769 final String msg = ForesterUtil.isReadableFile( positive_filter_file );
770 if ( !ForesterUtil.isEmpty( msg ) ) {
771 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + positive_filter_file + "\": "
775 else if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
776 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
777 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative domains filter: -"
778 + surfacing.FILTER_NEGATIVE_DOMAINS_OPTION + "=<file>" );
780 negative_domains_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) );
781 final String msg = ForesterUtil.isReadableFile( negative_domains_filter_file );
782 if ( !ForesterUtil.isEmpty( msg ) ) {
783 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_domains_filter_file
787 final List<String> plus_minus_analysis_high_copy_base_species = new ArrayList<String>();
788 final List<String> plus_minus_analysis_high_copy_target_species = new ArrayList<String>();
789 final List<String> plus_minus_analysis_high_low_copy_species = new ArrayList<String>();
790 final List<Object> plus_minus_analysis_numbers = new ArrayList<Object>();
791 processPlusMinusAnalysisOption( cla,
792 plus_minus_analysis_high_copy_base_species,
793 plus_minus_analysis_high_copy_target_species,
794 plus_minus_analysis_high_low_copy_species,
795 plus_minus_analysis_numbers );
796 File input_files_file = null;
797 String[] input_file_names_from_file = null;
798 if ( cla.isOptionSet( surfacing.INPUT_FILES_FROM_FILE_OPTION ) ) {
799 if ( !cla.isOptionValueSet( surfacing.INPUT_FILES_FROM_FILE_OPTION ) ) {
800 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input files file: -"
801 + surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>" );
803 input_files_file = new File( cla.getOptionValue( surfacing.INPUT_FILES_FROM_FILE_OPTION ) );
804 final String msg = ForesterUtil.isReadableFile( input_files_file );
805 if ( !ForesterUtil.isEmpty( msg ) ) {
806 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + input_files_file + "\": " + msg );
809 input_file_names_from_file = ForesterUtil.file2array( input_files_file );
811 catch ( final IOException e ) {
812 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read from \"" + input_files_file + "\": " + e );
815 if ( ( cla.getNumberOfNames() < 1 )
816 && ( ( input_file_names_from_file == null ) || ( input_file_names_from_file.length < 1 ) ) ) {
817 ForesterUtil.fatalError( surfacing.PRG_NAME,
818 "No hmmpfam output file indicated is input: use comand line directly or "
819 + surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>" );
821 DomainSimilarity.DomainSimilarityScoring scoring = SCORING_DEFAULT;
822 if ( cla.isOptionSet( surfacing.SCORING_OPTION ) ) {
823 if ( !cla.isOptionValueSet( surfacing.SCORING_OPTION ) ) {
824 ForesterUtil.fatalError( surfacing.PRG_NAME,
825 "no value for scoring method for domain combinations similarity calculation: -"
826 + surfacing.SCORING_OPTION + "=<"
827 + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
828 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|"
829 + surfacing.SCORING_COMBINATION_BASED + ">\"" );
831 final String scoring_str = cla.getOptionValue( surfacing.SCORING_OPTION );
832 if ( scoring_str.equals( surfacing.SCORING_DOMAIN_COUNT_BASED ) ) {
833 scoring = DomainSimilarity.DomainSimilarityScoring.DOMAINS;
835 else if ( scoring_str.equals( surfacing.SCORING_COMBINATION_BASED ) ) {
836 scoring = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
838 else if ( scoring_str.equals( surfacing.SCORING_PROTEIN_COUNT_BASED ) ) {
839 scoring = DomainSimilarity.DomainSimilarityScoring.PROTEINS;
842 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + scoring_str
843 + "\" for scoring method for domain combinations similarity calculation: \"-"
844 + surfacing.SCORING_OPTION + "=<" + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
845 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|" + surfacing.SCORING_COMBINATION_BASED + ">\"" );
848 boolean sort_by_species_count_first = false;
849 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION ) ) {
850 sort_by_species_count_first = true;
852 boolean species_matrix = false;
853 if ( cla.isOptionSet( surfacing.SPECIES_MATRIX_OPTION ) ) {
854 species_matrix = true;
856 boolean output_protein_lists_for_all_domains = false;
857 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS ) ) {
858 output_protein_lists_for_all_domains = true;
860 Detailedness detailedness = DETAILEDNESS_DEFAULT;
861 if ( cla.isOptionSet( surfacing.DETAILEDNESS_OPTION ) ) {
862 if ( !cla.isOptionValueSet( surfacing.DETAILEDNESS_OPTION ) ) {
863 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for -" + surfacing.DETAILEDNESS_OPTION + "=<"
864 + surfacing.DETAILEDNESS_BASIC + "|" + surfacing.DETAILEDNESS_LIST_IDS + "|"
865 + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
867 final String detness = cla.getOptionValue( surfacing.DETAILEDNESS_OPTION ).toLowerCase();
868 if ( detness.equals( surfacing.DETAILEDNESS_BASIC ) ) {
869 detailedness = DomainSimilarityCalculator.Detailedness.BASIC;
871 else if ( detness.equals( surfacing.DETAILEDNESS_LIST_IDS ) ) {
872 detailedness = DomainSimilarityCalculator.Detailedness.LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES;
874 else if ( detness.equals( surfacing.DETAILEDNESS_PUNCTILIOUS ) ) {
875 detailedness = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
878 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + detness + "\" for detailedness: \"-"
879 + surfacing.DETAILEDNESS_OPTION + "=<" + surfacing.DETAILEDNESS_BASIC + "|"
880 + surfacing.DETAILEDNESS_LIST_IDS + "|" + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
883 String automated_pairwise_comparison_suffix = null;
884 boolean perform_pwc = false;
885 boolean write_pwc_files = false;
886 if ( cla.isOptionSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
888 if ( !cla.isOptionValueSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
889 write_pwc_files = false;
892 write_pwc_files = true;
893 automated_pairwise_comparison_suffix = "_"
894 + cla.getOptionValue( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
897 String query_domain_ids = null;
898 if ( cla.isOptionSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
899 if ( !cla.isOptionValueSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
901 .fatalError( surfacing.PRG_NAME,
902 "no domain ids given for sequences with given domains to be extracted : -"
903 + surfacing.SEQ_EXTRACT_OPTION
904 + "=<ordered domain sequences, domain ids separated by '~', sequences separated by '#'>" );
906 query_domain_ids = cla.getOptionValue( surfacing.SEQ_EXTRACT_OPTION );
908 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field = DOMAIN_SORT_FILD_DEFAULT;
909 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field_for_automated_pwc = DOMAIN_SORT_FILD_DEFAULT;
910 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
911 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
912 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for domain combinations similarities sorting: -"
913 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
914 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
915 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
916 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
917 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|"
918 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
921 final String sort_str = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ).toLowerCase();
922 if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ALPHA ) ) {
923 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
924 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
926 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MAX ) ) {
927 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX;
928 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
930 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MIN ) ) {
931 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MIN;
932 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
934 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MEAN ) ) {
935 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MEAN;
936 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MEAN;
938 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT ) ) {
939 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SPECIES_COUNT;
940 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
942 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SD ) ) {
943 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SD;
944 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
946 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_DIFF ) ) {
947 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
948 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
950 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF ) ) {
951 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
952 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
954 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF ) ) {
955 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
956 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
959 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort_str
960 + "\" for domain combinations similarities sorting: \"-"
961 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
962 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
963 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
964 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
965 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|" + "|"
966 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
970 PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option = DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT;
971 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
972 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
973 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for print option: -"
974 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
975 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
976 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
978 final String sort = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ).toLowerCase();
979 if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML ) ) {
980 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.HTML;
982 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML ) ) {
983 // domain_similarity_print_option =
984 // DomainSimilarity.PRINT_OPTION.SIMPLE_HTML;
985 ForesterUtil.fatalError( surfacing.PRG_NAME, "simple HTML output not implemented yet :(" );
987 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED ) ) {
988 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.SIMPLE_TAB_DELIMITED;
991 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort + "\" for print option: -"
992 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
993 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
994 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
997 GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order = DOMAINS_SORT_ORDER_DEFAULT;
998 if ( cla.isOptionSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
999 if ( !cla.isOptionValueSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
1000 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for sorting of domain counts: -"
1001 + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<" + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|"
1002 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1003 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1004 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1006 final String sort = cla.getOptionValue( surfacing.DOMAIN_COUNT_SORT_OPTION ).toLowerCase();
1007 if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_ALPHA ) ) {
1008 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
1010 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT ) ) {
1011 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_COUNT;
1013 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT ) ) {
1014 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_PROTEINS_COUNT;
1016 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT ) ) {
1017 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.COMBINATIONS_COUNT;
1020 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort
1021 + "\" for sorting of domain counts: \"-" + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<"
1022 + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|" + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1023 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1024 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1027 String[][] input_file_properties = null;
1028 if ( input_file_names_from_file != null ) {
1029 input_file_properties = surfacing.processInputFileNames( input_file_names_from_file );
1032 input_file_properties = surfacing.processInputFileNames( cla.getNames() );
1034 final int number_of_genomes = input_file_properties.length;
1035 if ( number_of_genomes < 2 ) {
1036 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot analyze less than two files" );
1038 if ( ( number_of_genomes < 3 ) && perform_pwc ) {
1039 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use : -"
1040 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1041 + "=<suffix> to turn on pairwise analyses with less than three input files" );
1043 checkWriteabilityForPairwiseComparisons( domain_similarity_print_option,
1044 input_file_properties,
1045 automated_pairwise_comparison_suffix,
1047 for( int i = 0; i < number_of_genomes; i++ ) {
1048 File dcc_outfile = new File( input_file_properties[ i ][ 0 ]
1049 + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
1050 if ( out_dir != null ) {
1051 dcc_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + dcc_outfile );
1053 SurfacingUtil.checkForOutputFileWriteability( dcc_outfile );
1055 File pfam_to_go_file = null;
1056 Map<DomainId, List<GoId>> domain_id_to_go_ids_map = null;
1057 int domain_id_to_go_ids_count = 0;
1058 if ( cla.isOptionSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1059 if ( !cla.isOptionValueSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1060 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for Pfam to GO mapping file: -"
1061 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>" );
1063 pfam_to_go_file = new File( cla.getOptionValue( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) );
1064 final String error = ForesterUtil.isReadableFile( pfam_to_go_file );
1065 if ( !ForesterUtil.isEmpty( error ) ) {
1066 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read Pfam to GO mapping file: " + error );
1069 final PfamToGoParser parser = new PfamToGoParser( pfam_to_go_file );
1070 final List<PfamToGoMapping> pfam_to_go_mappings = parser.parse();
1071 domain_id_to_go_ids_map = SurfacingUtil.createDomainIdToGoIdMap( pfam_to_go_mappings );
1072 if ( parser.getMappingCount() < domain_id_to_go_ids_map.size() ) {
1073 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME,
1074 "parser.getMappingCount() < domain_id_to_go_ids_map.size()" );
1076 domain_id_to_go_ids_count = parser.getMappingCount();
1078 catch ( final IOException e ) {
1079 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from Pfam to GO mapping file: " + e );
1082 File go_obo_file = null;
1083 List<GoTerm> go_terms = null;
1084 if ( cla.isOptionSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1085 if ( !cla.isOptionValueSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1086 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO OBO file: -"
1087 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>" );
1089 if ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) {
1090 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO OBO file (-"
1091 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>) without Pfam to GO mapping file ("
1092 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1094 go_obo_file = new File( cla.getOptionValue( surfacing.GO_OBO_FILE_USE_OPTION ) );
1095 final String error = ForesterUtil.isReadableFile( go_obo_file );
1096 if ( !ForesterUtil.isEmpty( error ) ) {
1097 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read GO OBO file: " + error );
1100 final OBOparser parser = new OBOparser( go_obo_file, OBOparser.ReturnType.BASIC_GO_TERM );
1101 go_terms = parser.parse();
1102 if ( parser.getGoTermCount() != go_terms.size() ) {
1104 .unexpectedFatalError( surfacing.PRG_NAME, "parser.getGoTermCount() != go_terms.size()" );
1107 catch ( final IOException e ) {
1108 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from GO OBO file: " + e );
1111 Map<GoId, GoTerm> go_id_to_term_map = null;
1112 if ( ( ( domain_id_to_go_ids_map != null ) && ( domain_id_to_go_ids_map.size() > 0 ) )
1113 && ( ( go_terms != null ) && ( go_terms.size() > 0 ) ) ) {
1114 go_id_to_term_map = GoUtils.createGoIdToGoTermMap( go_terms );
1116 GoNameSpace go_namespace_limit = null;
1117 if ( cla.isOptionSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1118 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1119 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO namespace limit (-"
1120 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<namespace>) without Pfam to GO mapping file ("
1121 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>) and GO OBO file (-"
1122 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1124 if ( !cla.isOptionValueSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1125 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO namespace limit: \"-"
1126 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1127 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1128 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1129 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1131 final String go_namespace_limit_str = cla.getOptionValue( surfacing.GO_NAMESPACE_LIMIT_OPTION )
1133 if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION ) ) {
1134 go_namespace_limit = GoNameSpace.createMolecularFunction();
1136 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS ) ) {
1137 go_namespace_limit = GoNameSpace.createBiologicalProcess();
1139 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT ) ) {
1140 go_namespace_limit = GoNameSpace.createCellularComponent();
1143 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + go_namespace_limit_str
1144 + "\" for GO namespace limit: \"-" + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1145 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1146 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1147 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1150 if ( ( domain_similarity_sort_field == DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE )
1151 && ( number_of_genomes > 2 ) ) {
1152 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
1154 boolean jacknifed_distances = false;
1155 int jacknife_resamplings = JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT;
1156 double jacknife_ratio = JACKNIFE_RATIO_DEFAULT;
1157 long random_seed = JACKNIFE_RANDOM_SEED_DEFAULT;
1158 if ( cla.isOptionSet( surfacing.JACKNIFE_OPTION ) ) {
1159 if ( ( number_of_genomes < 3 ) || !perform_pwc ) {
1160 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use jacknife resampling analysis (-"
1161 + surfacing.JACKNIFE_OPTION + "[=<number of resamplings>]) without pairwise analyses ("
1162 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1163 + "=<suffix for pairwise comparison output files>)" );
1165 jacknifed_distances = true;
1166 if ( cla.isOptionHasAValue( surfacing.JACKNIFE_OPTION ) ) {
1168 jacknife_resamplings = cla.getOptionValueAsInt( surfacing.JACKNIFE_OPTION );
1170 catch ( final IOException e ) {
1171 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for number of resamplings" );
1173 if ( jacknife_resamplings < 2 ) {
1174 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use less than 2 resamplings" );
1177 if ( cla.isOptionSet( surfacing.JACKNIFE_RATIO_OPTION )
1178 && cla.isOptionHasAValue( surfacing.JACKNIFE_RATIO_OPTION ) ) {
1180 jacknife_ratio = cla.getOptionValueAsDouble( surfacing.JACKNIFE_RATIO_OPTION );
1182 catch ( final IOException e ) {
1183 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for jacknife ratio" );
1185 if ( ( jacknife_ratio <= 0.0 ) || ( jacknife_ratio >= 1.0 ) ) {
1186 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use illegal value for jacknife ratio: "
1190 if ( cla.isOptionSet( surfacing.JACKNIFE_RANDOM_SEED_OPTION )
1191 && cla.isOptionHasAValue( surfacing.JACKNIFE_RANDOM_SEED_OPTION ) ) {
1193 random_seed = cla.getOptionValueAsLong( surfacing.JACKNIFE_RANDOM_SEED_OPTION );
1195 catch ( final IOException e ) {
1196 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for random generator seed" );
1200 // boolean infer_species_trees = false;
1201 // if ( cla.isOptionSet( surfacing.INFER_SPECIES_TREES_OPTION ) ) {
1202 // if ( ( output_file == null ) || ( number_of_genomes < 3 )
1203 // || ForesterUtil.isEmpty( automated_pairwise_comparison_suffix ) ) {
1204 // ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer species trees (-"
1205 // + surfacing.INFER_SPECIES_TREES_OPTION + " without pairwise analyses ("
1206 // + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1207 // + "=<suffix for pairwise comparison output files>)" );
1209 // infer_species_trees = true;
1211 File[] intree_files = null;
1212 Phylogeny[] intrees = null;
1213 if ( cla.isOptionSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1214 // TODO FIXME if jacknife.... maybe not
1215 if ( number_of_genomes < 3 ) {
1216 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer gains and losses on input species trees (-"
1217 + surfacing.INPUT_SPECIES_TREE_OPTION + " without pairwise analyses ("
1218 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1219 + "=<suffix for pairwise comparison output files>)" );
1221 if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1222 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input tree: -"
1223 + surfacing.INPUT_SPECIES_TREE_OPTION + "=<tree file in phyloXML format>" );
1225 final String intrees_str = cla.getOptionValue( surfacing.INPUT_SPECIES_TREE_OPTION );
1226 if ( intrees_str.indexOf( "#" ) > 0 ) {
1227 final String[] intrees_strs = intrees_str.split( "#" );
1228 intree_files = new File[ intrees_strs.length ];
1230 for( final String s : intrees_strs ) {
1231 intree_files[ i++ ] = new File( s.trim() );
1235 intree_files = new File[ 1 ];
1236 intree_files[ 0 ] = new File( intrees_str );
1238 intrees = getIntrees( intree_files, number_of_genomes, input_file_properties );
1240 long random_number_seed_for_fitch_parsimony = 0l;
1241 boolean radomize_fitch_parsimony = false;
1242 if ( cla.isOptionSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1243 if ( !cla.isOptionValueSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1244 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for random number seed: -"
1245 + surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION + "=<seed>" );
1248 random_number_seed_for_fitch_parsimony = cla
1249 .getOptionValueAsLong( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
1251 catch ( final IOException e ) {
1252 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1254 radomize_fitch_parsimony = true;
1256 SortedSet<DomainId> filter = null;
1257 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1258 || ( negative_domains_filter_file != null ) ) {
1259 filter = new TreeSet<DomainId>();
1260 if ( positive_filter_file != null ) {
1261 processFilter( positive_filter_file, filter );
1263 else if ( negative_filter_file != null ) {
1264 processFilter( negative_filter_file, filter );
1266 else if ( negative_domains_filter_file != null ) {
1267 processFilter( negative_domains_filter_file, filter );
1270 Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps = null;
1271 File[] secondary_features_map_files = null;
1272 final File domain_lengths_analysis_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1273 + DOMAIN_LENGTHS_ANALYSIS_SUFFIX );
1274 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
1275 SurfacingUtil.checkForOutputFileWriteability( domain_lengths_analysis_outfile );
1277 if ( cla.isOptionSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1278 if ( !cla.isOptionValueSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1279 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for secondary features map file: -"
1280 + surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE + "=<file>" );
1282 final String[] secondary_features_map_files_strs = cla
1283 .getOptionValue( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ).split( "#" );
1284 secondary_features_map_files = new File[ secondary_features_map_files_strs.length ];
1285 domain_id_to_secondary_features_maps = new Map[ secondary_features_map_files_strs.length ];
1287 for( final String secondary_features_map_files_str : secondary_features_map_files_strs ) {
1288 secondary_features_map_files[ i ] = new File( secondary_features_map_files_str );
1289 final String error = ForesterUtil.isReadableFile( secondary_features_map_files[ i ] );
1290 if ( !ForesterUtil.isEmpty( error ) ) {
1291 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read secondary features map file: " + error );
1294 domain_id_to_secondary_features_maps[ i ] = SurfacingUtil
1295 .createDomainIdToSecondaryFeaturesMap( secondary_features_map_files[ i ] );
1297 catch ( final IOException e ) {
1298 ForesterUtil.fatalError( surfacing.PRG_NAME,
1299 "cannot read secondary features map file: " + e.getMessage() );
1301 catch ( final Exception e ) {
1302 ForesterUtil.fatalError( surfacing.PRG_NAME, "problem with contents of features map file ["
1303 + secondary_features_map_files[ i ] + "]: " + e.getMessage() );
1308 if ( out_dir == null ) {
1309 ForesterUtil.fatalError( surfacing.PRG_NAME, "no output directory indicated (-"
1310 + surfacing.OUTPUT_DIR_OPTION + "=<dir>)" );
1312 if ( output_file == null ) {
1313 ForesterUtil.fatalError( surfacing.PRG_NAME, "no name for (main) output file indicated (-"
1314 + surfacing.OUTPUT_FILE_OPTION + "=<file>)" );
1316 if ( ( domain_id_to_go_ids_map == null ) || domain_id_to_go_ids_map.isEmpty() ) {
1317 ForesterUtil.fatalError( surfacing.PRG_NAME,
1318 "no (acceptable) Pfam to GO id mapping file provided ('pfam2go file') (-"
1319 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1321 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1322 ForesterUtil.fatalError( surfacing.PRG_NAME,
1323 "no (acceptable) go id to term mapping file provided ('GO OBO file') (-"
1324 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1326 System.out.println( "Output directory : " + out_dir );
1327 if ( input_file_names_from_file != null ) {
1328 System.out.println( "Input files names from : " + input_files_file + " ["
1329 + input_file_names_from_file.length + " input files]" );
1330 html_desc.append( "<tr><td>Input files names from:</td><td>" + input_files_file + " ["
1331 + input_file_names_from_file.length + " input files]</td></tr>" + nl );
1333 if ( positive_filter_file != null ) {
1334 final int filter_size = filter.size();
1335 System.out.println( "Positive protein filter : " + positive_filter_file + " [" + filter_size
1337 html_desc.append( "<tr><td>Positive protein filter:</td><td>" + positive_filter_file + " [" + filter_size
1338 + " domain ids]</td></tr>" + nl );
1340 if ( negative_filter_file != null ) {
1341 final int filter_size = filter.size();
1342 System.out.println( "Negative protein filter : " + negative_filter_file + " [" + filter_size
1344 html_desc.append( "<tr><td>Negative protein filter:</td><td>" + negative_filter_file + " [" + filter_size
1345 + " domain ids]</td></tr>" + nl );
1347 if ( negative_domains_filter_file != null ) {
1348 final int filter_size = filter.size();
1349 System.out.println( "Negative domain filter : " + negative_domains_filter_file + " [" + filter_size
1351 html_desc.append( "<tr><td>Negative domain filter:</td><td>" + negative_domains_filter_file + " ["
1352 + filter_size + " domain ids]</td></tr>" + nl );
1354 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
1356 for( final String s : plus_minus_analysis_high_copy_base_species ) {
1357 plus0 += "+" + s + " ";
1360 for( final String s : plus_minus_analysis_high_copy_target_species ) {
1361 plus1 += "*" + s + " ";
1364 for( final String s : plus_minus_analysis_high_low_copy_species ) {
1365 minus += "-" + s + " ";
1367 System.out.println( "Plus-minus analysis : " + plus1 + "&& " + plus0 + "&& " + minus );
1368 html_desc.append( "<tr><td>Plus-minus analysis:</td><td>" + plus1 + "&& " + plus0 + "&& " + minus
1369 + "</td></tr>" + nl );
1371 if ( cutoff_scores_file != null ) {
1372 System.out.println( "Cutoff scores file : " + cutoff_scores_file );
1373 html_desc.append( "<tr><td>Cutoff scores file:</td><td>" + cutoff_scores_file + "</td></tr>" + nl );
1375 if ( e_value_max >= 0.0 ) {
1376 System.out.println( "E-value maximum (inclusive) : " + e_value_max );
1377 html_desc.append( "<tr><td>E-value maximum (inclusive):</td><td>" + e_value_max + "</td></tr>" + nl );
1379 System.out.println( "Ignore DUFs : " + ignore_dufs );
1380 if ( ignore_virus_like_ids ) {
1381 System.out.println( "Ignore virus like ids : " + ignore_virus_like_ids );
1382 html_desc.append( "<tr><td>Ignore virus, phage, transposition related ids:</td><td>"
1383 + ignore_virus_like_ids + "</td></tr>" + nl );
1385 html_desc.append( "<tr><td>Ignore DUFs:</td><td>" + ignore_dufs + "</td></tr>" + nl );
1386 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1387 System.out.println( "Max allowed domain overlap : " + max_allowed_overlap );
1388 html_desc.append( "<tr><td>Max allowed domain overlap:</td><td>" + max_allowed_overlap + "</td></tr>" + nl );
1390 if ( no_engulfing_overlaps ) {
1391 System.out.println( "Ignore engulfed domains : " + no_engulfing_overlaps );
1392 html_desc.append( "<tr><td>Ignore (lower confidence) engulfed domains:</td><td>" + no_engulfing_overlaps
1393 + "</td></tr>" + nl );
1395 System.out.println( "Ignore singlet domains : " + ignore_domains_without_combs_in_all_spec );
1397 .append( "<tr><td>Ignore singlet domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1398 + ignore_domains_without_combs_in_all_spec + "</td></tr>" + nl );
1399 System.out.println( "Ignore species specific doms: " + ignore_species_specific_domains );
1401 .append( "<tr><td>Ignore species specific domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1402 + ignore_species_specific_domains + "</td></tr>" + nl );
1403 System.out.println( "Ignore combination with self: " + ignore_combination_with_same );
1404 html_desc.append( "<tr><td>Ignore combination with self for domain combination similarity analyses:</td><td>"
1405 + ignore_combination_with_same + "</td></tr>" + nl );
1407 System.out.println( "Consider directedness : "
1408 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) );
1409 html_desc.append( "<tr><td>Consider directedness of binary domain combinations:</td><td>"
1410 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) + "</td></tr>" + nl );
1411 if ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) {
1412 System.out.println( "Consider adjacency : "
1413 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) );
1414 html_desc.append( "<tr><td>Consider djacency of binary domain combinations:</td><td>"
1415 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) + "</td></tr>"
1418 System.out.print( "Domain counts sort order : " );
1419 switch ( dc_sort_order ) {
1420 case ALPHABETICAL_KEY_ID:
1421 System.out.println( "alphabetical" );
1423 case KEY_DOMAIN_COUNT:
1424 System.out.println( "domain count" );
1426 case KEY_DOMAIN_PROTEINS_COUNT:
1427 System.out.println( "domain proteins count" );
1429 case COMBINATIONS_COUNT:
1430 System.out.println( "domain combinations count" );
1433 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for dc sort order" );
1435 if ( domain_id_to_go_ids_map != null ) {
1436 System.out.println( "Pfam to GO mappings from : " + pfam_to_go_file + " [" + domain_id_to_go_ids_count
1438 html_desc.append( "<tr><td>Pfam to GO mappings from:</td><td>" + pfam_to_go_file + " ["
1439 + domain_id_to_go_ids_count + " mappings]" + "</td></tr>" + nl );
1441 if ( go_terms != null ) {
1442 System.out.println( "GO terms from : " + go_obo_file + " [" + go_terms.size() + " terms]" );
1443 html_desc.append( "<tr><td>GO terms from:</td><td>" + go_obo_file + " [" + go_terms.size() + " terms]"
1444 + "</td></tr>" + nl );
1446 if ( go_namespace_limit != null ) {
1447 System.out.println( "Limit GO terms to : " + go_namespace_limit.toString() );
1448 html_desc.append( "<tr><td>Limit GO terms to</td><td>" + go_namespace_limit + "</td></tr>" + nl );
1450 if ( perform_pwc ) {
1451 System.out.println( "Suffix for PWC files : " + automated_pairwise_comparison_suffix );
1452 html_desc.append( "<tr><td>Suffix for PWC files</td><td>" + automated_pairwise_comparison_suffix
1453 + "</td></tr>" + nl );
1455 if ( out_dir != null ) {
1456 System.out.println( "Output directory : " + out_dir );
1458 if ( query_domain_ids != null ) {
1459 System.out.println( "Query domains (ordered) : " + query_domain_ids );
1460 html_desc.append( "<tr><td></td><td>" + query_domain_ids + "</td></tr>" + nl );
1462 System.out.println( "Write similarities to : " + output_file );
1463 System.out.print( " Scoring method : " );
1464 html_desc.append( "<tr><td>Scoring method:</td><td>" );
1465 switch ( scoring ) {
1467 System.out.println( "domain combinations based" );
1468 html_desc.append( "domain combinations based" + "</td></tr>" + nl );
1471 System.out.println( "domain counts based" );
1472 html_desc.append( "domain counts based" + "</td></tr>" + nl );
1475 System.out.println( "domain proteins counts based" );
1476 html_desc.append( "domain proteins counts based" + "</td></tr>" + nl );
1479 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
1481 System.out.print( " Sort by : " );
1482 html_desc.append( "<tr><td>Sort by:</td><td>" );
1483 switch ( domain_similarity_sort_field ) {
1485 System.out.print( "score minimum" );
1486 html_desc.append( "score minimum" );
1489 System.out.print( "score maximum" );
1490 html_desc.append( "score maximum" );
1493 System.out.print( "score mean" );
1494 html_desc.append( "score mean" );
1497 System.out.print( "score standard deviation" );
1498 html_desc.append( "score standard deviation" );
1501 System.out.print( "species number" );
1502 html_desc.append( "species number" );
1505 System.out.print( "alphabetical domain identifier" );
1506 html_desc.append( "alphabetical domain identifier" );
1508 case MAX_DIFFERENCE:
1509 System.out.print( "(maximal) difference" );
1510 html_desc.append( "(maximal) difference" );
1512 case ABS_MAX_COUNTS_DIFFERENCE:
1513 System.out.print( "absolute (maximal) counts difference" );
1514 html_desc.append( "absolute (maximal) counts difference" );
1516 case MAX_COUNTS_DIFFERENCE:
1517 System.out.print( "(maximal) counts difference" );
1518 html_desc.append( "(maximal) counts difference" );
1521 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1523 if ( sort_by_species_count_first ) {
1524 System.out.println( " (sort by species count first)" );
1525 html_desc.append( " (sort by species count first)" );
1528 System.out.println();
1530 html_desc.append( "</td></tr>" + nl );
1531 System.out.print( " Detailedness : " );
1532 switch ( detailedness ) {
1534 System.out.println( "basic" );
1536 case LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES:
1537 System.out.println( "list combining domains for each species" );
1540 System.out.println( "punctilious" );
1543 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for detailedness" );
1545 System.out.print( " Print option : " );
1546 switch ( domain_similarity_print_option ) {
1548 System.out.println( "HTML" );
1550 case SIMPLE_TAB_DELIMITED:
1551 System.out.println( "simple tab delimited" );
1554 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for print option" );
1556 System.out.print( " Species matrix : " + species_matrix );
1557 System.out.println();
1558 final File dc_data_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + DATA_FILE_SUFFIX );
1559 System.out.println( "Domain comb data output : " + dc_data_file );
1560 html_desc.append( "<tr><td>Domain combination data output:</td><td> " + dc_data_file + " </td></tr>" );
1561 System.out.println();
1562 if ( perform_pwc ) {
1563 System.out.println( "Pairwise comparisons: " );
1564 html_desc.append( "<tr><td>Pairwise comparisons:</td><td></td></tr>" );
1565 System.out.print( " Sort by : " );
1566 html_desc.append( "<tr><td>Sort by:</td><td>" );
1567 switch ( domain_similarity_sort_field_for_automated_pwc ) {
1569 System.out.print( "score mean" );
1570 html_desc.append( "score mean" );
1573 System.out.print( "alphabetical domain identifier" );
1574 html_desc.append( "alphabetical domain identifier" );
1576 case MAX_DIFFERENCE:
1577 System.out.print( "difference" );
1578 html_desc.append( "difference" );
1580 case ABS_MAX_COUNTS_DIFFERENCE:
1581 System.out.print( "absolute counts difference" );
1582 html_desc.append( "absolute counts difference" );
1584 case MAX_COUNTS_DIFFERENCE:
1585 System.out.print( "counts difference" );
1586 html_desc.append( "counts difference" );
1590 .unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1592 System.out.println();
1593 html_desc.append( "</td></tr>" + nl );
1594 if ( jacknifed_distances ) {
1595 html_desc.append( "<tr><td>Jacknife:</td><td>" + jacknife_resamplings + " resamplings</td></tr>" + nl );
1596 html_desc.append( "<tr><td>Jacknife ratio:</td><td>" + ForesterUtil.round( jacknife_ratio, 2 )
1597 + "</td></tr>" + nl );
1598 html_desc.append( "<tr><td>Jacknife random number seed:</td><td>" + random_seed + "</td></tr>" + nl );
1599 System.out.println( " Jacknife : " + jacknife_resamplings + " resamplings" );
1600 System.out.println( " Ratio : " + ForesterUtil.round( jacknife_ratio, 2 ) );
1601 System.out.println( " Random number seed : " + random_seed );
1603 // if ( infer_species_trees ) {
1604 // html_desc.append( "<tr><td>Infer species trees:</td><td>true</td></tr>" + nl );
1605 // System.out.println( " Infer species trees : true" );
1607 if ( ( intrees != null ) && ( intrees.length > 0 ) ) {
1608 for( final File intree_file : intree_files ) {
1609 html_desc.append( "<tr><td>Intree for gain/loss parsimony analysis:</td><td>" + intree_file
1610 + "</td></tr>" + nl );
1611 System.out.println( " Intree for gain/loss pars.: " + intree_file );
1614 if ( radomize_fitch_parsimony ) {
1615 html_desc.append( "<tr><td> Random number seed for Fitch parsimony analysis:</td><td>"
1616 + random_number_seed_for_fitch_parsimony + "</td></tr>" + nl );
1617 System.out.println( " Random number seed : " + random_number_seed_for_fitch_parsimony );
1619 if ( ( domain_id_to_secondary_features_maps != null ) && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
1620 for( int i = 0; i < secondary_features_map_files.length; i++ ) {
1621 html_desc.append( "<tr><td>Secondary features map file:</td><td>"
1622 + secondary_features_map_files[ i ] + "</td></tr>" + nl );
1623 System.out.println( "Secondary features map file : " + secondary_features_map_files[ i ]
1624 + " [mappings for " + domain_id_to_secondary_features_maps[ i ].size() + " domain ids]" );
1626 System.out.println();
1627 System.out.println( "Domain ids to secondary features map:" );
1628 for( final DomainId domain_id : domain_id_to_secondary_features_maps[ i ].keySet() ) {
1629 System.out.print( domain_id.getId() );
1630 System.out.print( " => " );
1631 for( final String sec : domain_id_to_secondary_features_maps[ i ].get( domain_id ) ) {
1632 System.out.print( sec );
1633 System.out.print( " " );
1635 System.out.println();
1640 } // if ( perform_pwc ) {
1641 System.out.println();
1642 html_desc.append( "<tr><td>Command line:</td><td>\n" + cla.getCommandLineArgsAsString() + "\n</td></tr>" + nl );
1643 System.out.println( "Command line : " + cla.getCommandLineArgsAsString() );
1644 BufferedWriter[] query_domains_writer_ary = null;
1645 List<DomainId>[] query_domain_ids_array = null;
1646 if ( query_domain_ids != null ) {
1647 final String[] query_domain_ids_str_array = query_domain_ids.split( "#" );
1648 query_domain_ids_array = new ArrayList[ query_domain_ids_str_array.length ];
1649 query_domains_writer_ary = new BufferedWriter[ query_domain_ids_str_array.length ];
1650 for( int i = 0; i < query_domain_ids_str_array.length; i++ ) {
1651 String query_domain_ids_str = query_domain_ids_str_array[ i ];
1652 final String[] query_domain_ids_str_ary = query_domain_ids_str.split( "~" );
1653 final List<DomainId> query = new ArrayList<DomainId>();
1654 for( final String element : query_domain_ids_str_ary ) {
1655 query.add( new DomainId( element ) );
1657 query_domain_ids_array[ i ] = query;
1658 query_domain_ids_str = query_domain_ids_str.replace( '~', '_' );
1659 String protein_names_writer_str = query_domain_ids_str + surfacing.SEQ_EXTRACT_SUFFIX;
1660 if ( out_dir != null ) {
1661 protein_names_writer_str = out_dir + ForesterUtil.FILE_SEPARATOR + protein_names_writer_str;
1664 query_domains_writer_ary[ i ] = new BufferedWriter( new FileWriter( protein_names_writer_str ) );
1666 catch ( final IOException e ) {
1667 ForesterUtil.fatalError( surfacing.PRG_NAME, "Could not open [" + protein_names_writer_str + "]: "
1668 + e.getLocalizedMessage() );
1672 SortedMap<Species, List<Protein>> protein_lists_per_species = null; //This will only be created if neede.
1673 boolean need_protein_lists_per_species = false;
1674 if ( ( plus_minus_analysis_high_copy_base_species.size() > 0 ) || output_protein_lists_for_all_domains ) {
1675 need_protein_lists_per_species = true;
1677 if ( need_protein_lists_per_species ) {
1678 protein_lists_per_species = new TreeMap<Species, List<Protein>>();
1680 final List<GenomeWideCombinableDomains> gwcd_list = new ArrayList<GenomeWideCombinableDomains>( number_of_genomes );
1681 final SortedSet<DomainId> all_domains_encountered = new TreeSet<DomainId>();
1682 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered = new TreeSet<BinaryDomainCombination>();
1683 List<BinaryDomainCombination> all_bin_domain_combinations_gained_fitch = null;
1684 List<BinaryDomainCombination> all_bin_domain_combinations_lost_fitch = null;
1685 if ( ( intrees != null ) && ( intrees.length == 1 ) ) {
1686 all_bin_domain_combinations_gained_fitch = new ArrayList<BinaryDomainCombination>();
1687 all_bin_domain_combinations_lost_fitch = new ArrayList<BinaryDomainCombination>();
1689 final DomainLengthsTable domain_lengths_table = new DomainLengthsTable();
1690 final File per_genome_domain_promiscuity_statistics_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR
1691 + output_file + D_PROMISCUITY_FILE_SUFFIX );
1692 BufferedWriter per_genome_domain_promiscuity_statistics_writer = null;
1694 per_genome_domain_promiscuity_statistics_writer = new BufferedWriter( new FileWriter( per_genome_domain_promiscuity_statistics_file ) );
1695 per_genome_domain_promiscuity_statistics_writer.write( "Species:\t" );
1696 per_genome_domain_promiscuity_statistics_writer.write( "Mean:\t" );
1697 per_genome_domain_promiscuity_statistics_writer.write( "SD:\t" );
1698 per_genome_domain_promiscuity_statistics_writer.write( "Median:\t" );
1699 per_genome_domain_promiscuity_statistics_writer.write( "Min:\t" );
1700 per_genome_domain_promiscuity_statistics_writer.write( "Max:\t" );
1701 per_genome_domain_promiscuity_statistics_writer.write( "N:\t" );
1702 per_genome_domain_promiscuity_statistics_writer.write( "Max Promiscuous Domains:"
1703 + ForesterUtil.LINE_SEPARATOR );
1705 catch ( final IOException e2 ) {
1706 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1708 final File log_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + LOG_FILE_SUFFIX );
1709 BufferedWriter log_writer = null;
1711 log_writer = new BufferedWriter( new FileWriter( log_file ) );
1713 catch ( final IOException e2 ) {
1714 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1716 BufferedWriter dc_data_writer = null;
1718 dc_data_writer = new BufferedWriter( new FileWriter( dc_data_file ) );
1719 dc_data_writer.write( DATA_FILE_DESC );
1720 dc_data_writer.write( ForesterUtil.LINE_SEPARATOR );
1722 catch ( final IOException e2 ) {
1723 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1725 final DescriptiveStatistics protein_coverage_stats = new BasicDescriptiveStatistics();
1726 final DescriptiveStatistics all_genomes_domains_per_potein_stats = new BasicDescriptiveStatistics();
1727 final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo = new TreeMap<Integer, Integer>();
1728 final SortedSet<String> domains_which_are_always_single = new TreeSet<String>();
1729 final SortedSet<String> domains_which_are_sometimes_single_sometimes_not = new TreeSet<String>();
1730 final SortedSet<String> domains_which_never_single = new TreeSet<String>();
1731 BufferedWriter domains_per_potein_stats_writer = null;
1733 domains_per_potein_stats_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
1734 + output_file + "__domains_per_potein_stats.txt" ) );
1735 domains_per_potein_stats_writer.write( "Genome" );
1736 domains_per_potein_stats_writer.write( "\t" );
1737 domains_per_potein_stats_writer.write( "Mean" );
1738 domains_per_potein_stats_writer.write( "\t" );
1739 domains_per_potein_stats_writer.write( "SD" );
1740 domains_per_potein_stats_writer.write( "\t" );
1741 domains_per_potein_stats_writer.write( "Median" );
1742 domains_per_potein_stats_writer.write( "\t" );
1743 domains_per_potein_stats_writer.write( "N" );
1744 domains_per_potein_stats_writer.write( "\t" );
1745 domains_per_potein_stats_writer.write( "Min" );
1746 domains_per_potein_stats_writer.write( "\t" );
1747 domains_per_potein_stats_writer.write( "Max" );
1748 domains_per_potein_stats_writer.write( "\n" );
1750 catch ( final IOException e3 ) {
1751 e3.printStackTrace();
1754 for( int i = 0; i < number_of_genomes; ++i ) {
1755 System.out.println();
1756 System.out.println( ( i + 1 ) + "/" + number_of_genomes );
1757 log( ( i + 1 ) + "/" + number_of_genomes, log_writer );
1758 System.out.println( "Processing : " + input_file_properties[ i ][ 0 ] );
1759 log( "Genome : " + input_file_properties[ i ][ 0 ], log_writer );
1760 HmmscanPerDomainTableParser parser = null;
1761 INDIVIDUAL_SCORE_CUTOFF ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF.NONE;
1762 if ( individual_score_cutoffs != null ) {
1763 ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF_DEFAULT;
1765 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1766 || ( negative_domains_filter_file != null ) ) {
1767 HmmscanPerDomainTableParser.FilterType filter_type = HmmscanPerDomainTableParser.FilterType.NONE;
1768 if ( positive_filter_file != null ) {
1769 filter_type = HmmscanPerDomainTableParser.FilterType.POSITIVE_PROTEIN;
1771 else if ( negative_filter_file != null ) {
1772 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_PROTEIN;
1774 else if ( negative_domains_filter_file != null ) {
1775 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_DOMAIN;
1777 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1778 input_file_properties[ i ][ 1 ],
1785 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1786 input_file_properties[ i ][ 1 ],
1790 if ( e_value_max >= 0.0 ) {
1791 parser.setEValueMaximum( e_value_max );
1793 parser.setIgnoreDufs( ignore_dufs );
1794 parser.setIgnoreVirusLikeIds( ignore_virus_like_ids );
1795 parser.setIgnoreEngulfedDomains( no_engulfing_overlaps );
1796 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1797 parser.setMaxAllowedOverlap( max_allowed_overlap );
1799 parser.setReturnType( HmmscanPerDomainTableParser.ReturnType.UNORDERED_PROTEIN_DOMAIN_COLLECTION_PER_PROTEIN );
1800 if ( individual_score_cutoffs != null ) {
1801 parser.setIndividualScoreCutoffs( individual_score_cutoffs );
1803 List<Protein> protein_list = null;
1805 protein_list = parser.parse();
1807 catch ( final IOException e ) {
1808 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1810 catch ( final Exception e ) {
1811 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, e.getMessage(), e );
1814 System.out.println( "Domains ignored due to negative domain filter: " );
1815 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToNegativeDomainFilterCountsMap() );
1816 System.out.println( "Domains ignored due to virus like id: " );
1817 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToVirusLikeIdCountsMap() );
1819 final double coverage = ( double ) protein_list.size() / parser.getProteinsEncountered();
1820 protein_coverage_stats.addValue( coverage );
1821 System.out.println( "Number of proteins encountered : " + parser.getProteinsEncountered() );
1822 log( "Number of proteins encountered : " + parser.getProteinsEncountered(), log_writer );
1823 System.out.println( "Number of proteins stored : " + protein_list.size() );
1824 log( "Number of proteins stored : " + protein_list.size(), log_writer );
1825 System.out.println( "Coverage : "
1826 + ForesterUtil.roundToInt( 100.0 * coverage ) + "%" );
1827 log( "Coverage : " + ForesterUtil.roundToInt( 100.0 * coverage )
1828 + "%", log_writer );
1829 System.out.println( "Domains encountered : " + parser.getDomainsEncountered() );
1830 log( "Domains encountered : " + parser.getDomainsEncountered(), log_writer );
1831 System.out.println( "Domains stored : " + parser.getDomainsStored() );
1832 log( "Domains stored : " + parser.getDomainsStored(), log_writer );
1833 System.out.println( "Distinct domains stored : "
1834 + parser.getDomainsStoredSet().size() );
1835 log( "Distinct domains stored : " + parser.getDomainsStoredSet().size(), log_writer );
1836 System.out.println( "Domains ignored due to individual score cutoffs: "
1837 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() );
1838 log( "Domains ignored due to individual score cutoffs: "
1839 + parser.getDomainsIgnoredDueToIndividualScoreCutoff(),
1841 System.out.println( "Domains ignored due to E-value : "
1842 + parser.getDomainsIgnoredDueToEval() );
1843 log( "Domains ignored due to E-value : " + parser.getDomainsIgnoredDueToEval(), log_writer );
1844 System.out.println( "Domains ignored due to DUF designation : "
1845 + parser.getDomainsIgnoredDueToDuf() );
1846 log( "Domains ignored due to DUF designation : " + parser.getDomainsIgnoredDueToDuf(), log_writer );
1847 if ( ignore_virus_like_ids ) {
1848 System.out.println( "Domains ignored due virus like ids : "
1849 + parser.getDomainsIgnoredDueToVirusLikeIds() );
1850 log( "Domains ignored due virus like ids : " + parser.getDomainsIgnoredDueToVirusLikeIds(),
1853 System.out.println( "Domains ignored due negative domain filter : "
1854 + parser.getDomainsIgnoredDueToNegativeDomainFilter() );
1855 log( "Domains ignored due negative domain filter : "
1856 + parser.getDomainsIgnoredDueToNegativeDomainFilter(),
1858 System.out.println( "Domains ignored due to overlap : "
1859 + parser.getDomainsIgnoredDueToOverlap() );
1860 log( "Domains ignored due to overlap : " + parser.getDomainsIgnoredDueToOverlap(),
1862 if ( negative_filter_file != null ) {
1863 System.out.println( "Proteins ignored due to negative filter : "
1864 + parser.getProteinsIgnoredDueToFilter() );
1865 log( "Proteins ignored due to negative filter : " + parser.getProteinsIgnoredDueToFilter(),
1868 if ( positive_filter_file != null ) {
1869 System.out.println( "Proteins ignored due to positive filter : "
1870 + parser.getProteinsIgnoredDueToFilter() );
1871 log( "Proteins ignored due to positive filter : " + parser.getProteinsIgnoredDueToFilter(),
1874 System.out.println( "Time for processing : " + parser.getTime() + "ms" );
1875 log( "", log_writer );
1876 html_desc.append( "<tr><td>" + input_file_properties[ i ][ 0 ] + " [species: "
1877 + input_file_properties[ i ][ 1 ] + "]" + ":</td><td>domains analyzed: "
1878 + parser.getDomainsStored() + "; domains ignored: [ind score cutoffs: "
1879 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() + "] [E-value cutoff: "
1880 + parser.getDomainsIgnoredDueToEval() + "] [DUF: " + parser.getDomainsIgnoredDueToDuf()
1881 + "] [virus like ids: " + parser.getDomainsIgnoredDueToVirusLikeIds()
1882 + "] [negative domain filter: " + parser.getDomainsIgnoredDueToNegativeDomainFilter()
1883 + "] [overlap: " + parser.getDomainsIgnoredDueToOverlap() + "]" );
1884 if ( negative_filter_file != null ) {
1885 html_desc.append( "; proteins ignored due to negative filter: "
1886 + parser.getProteinsIgnoredDueToFilter() );
1888 if ( positive_filter_file != null ) {
1889 html_desc.append( "; proteins ignored due to positive filter: "
1890 + parser.getProteinsIgnoredDueToFilter() );
1892 html_desc.append( "</td></tr>" + nl );
1893 // domain_partner_counts_array[ i ] =
1894 // Methods.getDomainPartnerCounts( protein_domain_collections_array[
1896 // false, input_file_properties[ i ][ 1 ] );
1899 for( final Protein protein : protein_list ) {
1900 dc_data_writer.write( SurfacingUtil.proteinToDomainCombinations( protein, count + "", "\t" )
1905 catch ( final IOException e ) {
1906 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1908 SurfacingUtil.domainsPerProteinsStatistics( input_file_properties[ i ][ 1 ],
1910 all_genomes_domains_per_potein_stats,
1911 all_genomes_domains_per_potein_histo,
1912 domains_which_are_always_single,
1913 domains_which_are_sometimes_single_sometimes_not,
1914 domains_which_never_single,
1915 domains_per_potein_stats_writer );
1916 gwcd_list.add( BasicGenomeWideCombinableDomains
1917 .createInstance( protein_list,
1918 ignore_combination_with_same,
1919 new BasicSpecies( input_file_properties[ i ][ 1 ] ),
1920 domain_id_to_go_ids_map,
1922 domain_lengths_table.addLengths( protein_list );
1923 if ( gwcd_list.get( i ).getSize() > 0 ) {
1924 SurfacingUtil.writeDomainCombinationsCountsFile( input_file_properties,
1926 per_genome_domain_promiscuity_statistics_writer,
1930 if ( output_binary_domain_combinationsfor_graph_analysis ) {
1931 SurfacingUtil.writeBinaryDomainCombinationsFileForGraphAnalysis( input_file_properties,
1937 SurfacingUtil.addAllDomainIdsToSet( gwcd_list.get( i ), all_domains_encountered );
1938 SurfacingUtil.addAllBinaryDomainCombinationToSet( gwcd_list.get( i ),
1939 all_bin_domain_combinations_encountered );
1941 if ( query_domains_writer_ary != null ) {
1942 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1944 SurfacingUtil.extractProteinNames( protein_list,
1945 query_domain_ids_array[ j ],
1946 query_domains_writer_ary[ j ],
1948 query_domains_writer_ary[ j ].flush();
1950 catch ( final IOException e ) {
1951 e.printStackTrace();
1955 if ( need_protein_lists_per_species ) {
1956 protein_lists_per_species.put( new BasicSpecies( input_file_properties[ i ][ 1 ] ), protein_list );
1961 catch ( final IOException e2 ) {
1962 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1965 } // for( int i = 0; i < number_of_genomes; ++i ) {
1966 ForesterUtil.programMessage( PRG_NAME, "Wrote domain promiscuities to: "
1967 + per_genome_domain_promiscuity_statistics_file );
1970 domains_per_potein_stats_writer.write( "ALL" );
1971 domains_per_potein_stats_writer.write( "\t" );
1972 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.arithmeticMean() + "" );
1973 domains_per_potein_stats_writer.write( "\t" );
1974 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.sampleStandardDeviation() + "" );
1975 domains_per_potein_stats_writer.write( "\t" );
1976 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.median() + "" );
1977 domains_per_potein_stats_writer.write( "\t" );
1978 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getN() + "" );
1979 domains_per_potein_stats_writer.write( "\t" );
1980 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMin() + "" );
1981 domains_per_potein_stats_writer.write( "\t" );
1982 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMax() + "" );
1983 domains_per_potein_stats_writer.write( "\n" );
1984 domains_per_potein_stats_writer.close();
1985 printOutPercentageOfMultidomainProteins( all_genomes_domains_per_potein_histo, log_writer );
1986 ForesterUtil.map2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1987 + "__all_genomes_domains_per_potein_histo.txt" ), all_genomes_domains_per_potein_histo, "\t", "\n" );
1988 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1989 + "__domains_always_single_.txt" ), domains_which_are_always_single, "\n" );
1990 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1991 + "__domains_single_or_combined.txt" ), domains_which_are_sometimes_single_sometimes_not, "\n" );
1992 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1993 + "__domains_always_combined.txt" ), domains_which_never_single, "\n" );
1994 ForesterUtil.programMessage( PRG_NAME,
1995 "Average of proteins with a least one domain assigned: "
1996 + ( 100 * protein_coverage_stats.arithmeticMean() ) + "% (+/-"
1997 + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)" );
1998 ForesterUtil.programMessage( PRG_NAME, "Range of proteins with a least one domain assigned: " + 100
1999 * protein_coverage_stats.getMin() + "%-" + 100 * protein_coverage_stats.getMax() + "%" );
2000 log( "Average of prot with a least one dom assigned : " + ( 100 * protein_coverage_stats.arithmeticMean() )
2001 + "% (+/-" + ( 100 * protein_coverage_stats.sampleStandardDeviation() ) + "%)", log_writer );
2002 log( "Range of prot with a least one dom assigned : " + 100 * protein_coverage_stats.getMin() + "%-"
2003 + 100 * protein_coverage_stats.getMax() + "%", log_writer );
2005 catch ( final IOException e2 ) {
2006 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
2008 if ( query_domains_writer_ary != null ) {
2009 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
2011 query_domains_writer_ary[ j ].close();
2013 catch ( final IOException e ) {
2014 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
2019 per_genome_domain_promiscuity_statistics_writer.close();
2020 dc_data_writer.close();
2023 catch ( final IOException e2 ) {
2024 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
2026 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
2028 SurfacingUtil.executeDomainLengthAnalysis( input_file_properties,
2030 domain_lengths_table,
2031 domain_lengths_analysis_outfile );
2033 catch ( final IOException e1 ) {
2034 ForesterUtil.fatalError( surfacing.PRG_NAME, e1.toString() );
2036 System.out.println();
2037 ForesterUtil.programMessage( PRG_NAME, "Wrote domain length data to: " + domain_lengths_analysis_outfile );
2038 System.out.println();
2040 final long analysis_start_time = new Date().getTime();
2041 PairwiseDomainSimilarityCalculator pw_calc = null;
2042 // double[] values_for_all_scores_histogram = null;
2043 final DomainSimilarityCalculator calc = new BasicDomainSimilarityCalculator( domain_similarity_sort_field,
2044 sort_by_species_count_first,
2045 number_of_genomes == 2 );
2046 switch ( scoring ) {
2048 pw_calc = new CombinationsBasedPairwiseDomainSimilarityCalculator();
2051 pw_calc = new DomainCountsBasedPairwiseSimilarityCalculator();
2054 pw_calc = new ProteinCountsBasedPairwiseDomainSimilarityCalculator();
2057 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
2059 DomainSimilarityCalculator.GoAnnotationOutput go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.NONE;
2060 if ( domain_id_to_go_ids_map != null ) {
2061 go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.ALL;
2063 final SortedSet<DomainSimilarity> similarities = calc
2064 .calculateSimilarities( pw_calc,
2066 ignore_domains_without_combs_in_all_spec,
2067 ignore_species_specific_domains );
2068 SurfacingUtil.decoratePrintableDomainSimilarities( similarities,
2070 go_annotation_output,
2072 go_namespace_limit );
2073 DescriptiveStatistics pw_stats = null;
2075 String my_outfile = output_file.toString();
2076 if ( !my_outfile.endsWith( ".html" ) ) {
2077 my_outfile += ".html";
2079 final Writer writer = new BufferedWriter( new FileWriter( out_dir == null ? my_outfile : out_dir
2080 + ForesterUtil.FILE_SEPARATOR + my_outfile ) );
2081 List<Species> species_order = null;
2082 if ( species_matrix ) {
2083 species_order = new ArrayList<Species>();
2084 for( int i = 0; i < number_of_genomes; i++ ) {
2085 species_order.add( new BasicSpecies( input_file_properties[ i ][ 1 ] ) );
2088 html_desc.append( "<tr><td>Sum of all distinct binary combinations:</td><td>"
2089 + all_bin_domain_combinations_encountered.size() + "</td></tr>" + nl );
2090 html_desc.append( "<tr><td>Sum of all distinct domains:</td><td>" + all_domains_encountered.size()
2091 + "</td></tr>" + nl );
2092 html_desc.append( "<tr><td>Analysis date/time:</td><td>"
2093 + new java.text.SimpleDateFormat( "yyyy.MM.dd HH:mm:ss" ).format( new java.util.Date() )
2094 + "</td></tr>" + nl );
2095 html_desc.append( "</table>" + nl );
2096 pw_stats = SurfacingUtil
2097 .writeDomainSimilaritiesToFile( html_desc,
2098 new StringBuilder( number_of_genomes + " genomes" ),
2101 number_of_genomes == 2,
2103 domain_similarity_print_option,
2104 domain_similarity_sort_field,
2107 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote main output (includes domain similarities) to: \""
2108 + ( out_dir == null ? my_outfile : out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) + "\"" );
2110 catch ( final IOException e ) {
2111 ForesterUtil.fatalError( surfacing.PRG_NAME, "Failed to write similarites to: \"" + output_file + "\" ["
2112 + e.getMessage() + "]" );
2114 System.out.println();
2115 // values_for_all_scores_histogram = pw_stats.getDataAsDoubleArray();
2116 final Species[] species = new Species[ number_of_genomes ];
2117 for( int i = 0; i < number_of_genomes; ++i ) {
2118 species[ i ] = new BasicSpecies( input_file_properties[ i ][ 1 ] );
2120 List<Phylogeny> inferred_trees = null;
2121 if ( ( number_of_genomes > 2 ) && perform_pwc ) {
2122 final PairwiseGenomeComparator pwgc = new PairwiseGenomeComparator();
2123 pwgc.performPairwiseComparisons( html_desc,
2124 sort_by_species_count_first,
2126 ignore_domains_without_combs_in_all_spec,
2127 ignore_species_specific_domains,
2128 domain_similarity_sort_field_for_automated_pwc,
2129 domain_similarity_print_option,
2131 domain_id_to_go_ids_map,
2138 automated_pairwise_comparison_suffix,
2140 surfacing.PAIRWISE_DOMAIN_COMPARISONS_PREFIX,
2144 String matrix_output_file = new String( output_file.toString() );
2145 if ( matrix_output_file.indexOf( '.' ) > 1 ) {
2146 matrix_output_file = matrix_output_file.substring( 0, matrix_output_file.indexOf( '.' ) );
2148 if ( out_dir != null ) {
2149 matrix_output_file = out_dir + ForesterUtil.FILE_SEPARATOR + matrix_output_file;
2150 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2152 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2153 + surfacing.MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans() );
2155 .writeMatrixToFile( new File( matrix_output_file
2156 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2157 pwgc.getSharedBinaryCombinationsBasedDistances() );
2158 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2159 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2160 pwgc.getSharedDomainsBasedDistances() );
2161 final Phylogeny nj_gd = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2162 + surfacing.NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans()
2164 final Phylogeny nj_bc = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2165 + surfacing.NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2166 .getSharedBinaryCombinationsBasedDistances().get( 0 ) );
2167 final Phylogeny nj_d = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2168 + surfacing.NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2169 .getSharedDomainsBasedDistances().get( 0 ) );
2170 inferred_trees = new ArrayList<Phylogeny>();
2171 inferred_trees.add( nj_gd );
2172 inferred_trees.add( nj_bc );
2173 inferred_trees.add( nj_d );
2174 if ( jacknifed_distances ) {
2175 pwgc.performPairwiseComparisonsJacknifed( species,
2179 jacknife_resamplings,
2183 .writeMatrixToFile( new File( matrix_output_file
2185 + ForesterUtil.round( jacknife_ratio, 2 )
2187 + jacknife_resamplings
2188 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2189 pwgc.getSharedBinaryCombinationsBasedDistances() );
2191 .writeMatrixToFile( new File( matrix_output_file + "_" + ForesterUtil.round( jacknife_ratio, 2 )
2192 + "_" + jacknife_resamplings
2193 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2194 pwgc.getSharedDomainsBasedDistances() );
2195 // if ( infer_species_trees ) {
2196 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2197 // + INFERRED_SBC_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc
2198 // .getSharedBinaryCombinationsBasedDistances() );
2199 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2200 // + INFERRED_SD_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc.getSharedDomainsBasedDistances() );
2203 } // if ( ( output_file != null ) && ( number_of_genomes > 2 ) && !isEmpty( automated_pairwise_comparison_suffix ) )
2204 if ( ( out_dir != null ) && ( !perform_pwc ) ) {
2205 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2207 writePresentToNexus( output_file, positive_filter_file, filter, gwcd_list );
2208 if ( ( ( intrees != null ) && ( intrees.length > 0 ) ) && ( number_of_genomes > 2 ) ) {
2209 final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
2211 max_allowed_overlap,
2212 no_engulfing_overlaps,
2216 if ( radomize_fitch_parsimony ) {
2217 s += random_number_seed_for_fitch_parsimony + "_";
2220 for( final Phylogeny intree : intrees ) {
2221 final String outfile_name = ForesterUtil.removeSuffix( output_file.toString() ) + s
2222 + ForesterUtil.removeSuffix( intree_files[ i ].toString() );
2223 final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator.createInstance( intree,
2225 SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
2226 radomize_fitch_parsimony,
2230 domain_id_to_go_ids_map,
2233 parameters_sb.toString(),
2234 domain_id_to_secondary_features_maps,
2235 positive_filter_file == null ? null : filter,
2236 output_binary_domain_combinationsfor_graph_analysis,
2237 all_bin_domain_combinations_gained_fitch,
2238 all_bin_domain_combinations_lost_fitch,
2240 // Listing of all domain combinations gained is only done if only one input tree is used.
2241 if ( ( domain_id_to_secondary_features_maps != null )
2242 && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
2244 for( final Map<DomainId, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
2245 final Map<Species, MappingResults> mapping_results_map = new TreeMap<Species, MappingResults>();
2246 final DomainParsimonyCalculator secondary_features_parsimony = DomainParsimonyCalculator
2247 .createInstance( intree, gwcd_list, domain_id_to_secondary_features_map );
2249 .executeParsimonyAnalysisForSecondaryFeatures( outfile_name
2251 + secondary_features_map_files[ j++ ],
2252 secondary_features_parsimony,
2254 parameters_sb.toString(),
2255 mapping_results_map );
2257 System.out.println();
2258 System.out.println( "Mapping to secondary features:" );
2259 for( final Species spec : mapping_results_map.keySet() ) {
2260 final MappingResults mapping_results = mapping_results_map.get( spec );
2261 final int total_domains = mapping_results.getSumOfFailures()
2262 + mapping_results.getSumOfSuccesses();
2263 System.out.print( spec + ":" );
2264 System.out.print( " mapped domains = " + mapping_results.getSumOfSuccesses() );
2265 System.out.print( ", not mapped domains = " + mapping_results.getSumOfFailures() );
2266 if ( total_domains > 0 ) {
2267 System.out.println( ", mapped ratio = "
2268 + ( 100 * mapping_results.getSumOfSuccesses() / total_domains ) + "%" );
2271 System.out.println( ", mapped ratio = n/a (total domains = 0 )" );
2278 } // for( final Phylogeny intree : intrees ) {
2280 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
2281 executePlusMinusAnalysis( output_file,
2282 plus_minus_analysis_high_copy_base_species,
2283 plus_minus_analysis_high_copy_target_species,
2284 plus_minus_analysis_high_low_copy_species,
2286 protein_lists_per_species,
2287 domain_id_to_go_ids_map,
2289 plus_minus_analysis_numbers );
2291 if ( output_protein_lists_for_all_domains ) {
2292 writeProteinListsForAllSpecies( out_dir, protein_lists_per_species, gwcd_list );
2294 // if ( ( intrees != null ) && ( intrees.length > 0 ) && ( inferred_trees != null ) && ( inferred_trees.size() > 0 ) ) {
2295 // final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
2297 // max_allowed_overlap,
2298 // no_engulfing_overlaps,
2299 // cutoff_scores_file );
2301 // if ( radomize_fitch_parsimony ) {
2302 // s += random_number_seed_for_fitch_parsimony + "_";
2305 // for( final Phylogeny inferred_tree : inferred_trees ) {
2306 // if ( !inferred_tree.isRooted() ) {
2307 // intrees[ 0 ].getRoot().getName();
2310 // final String outfile_name = ForesterUtil.removeSuffix( inferred_tree.getName() ) + s;
2311 // final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator
2312 // .createInstance( inferred_tree, gwcd_list );
2313 // SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
2314 // radomize_fitch_parsimony,
2316 // domain_parsimony,
2318 // domain_id_to_go_ids_map,
2319 // go_id_to_term_map,
2320 // go_namespace_limit,
2321 // parameters_sb.toString() );
2325 if ( all_bin_domain_combinations_gained_fitch != null ) {
2327 executeFitchGainsAnalysis( new File( output_file
2328 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2329 all_bin_domain_combinations_gained_fitch,
2330 all_domains_encountered.size(),
2331 all_bin_domain_combinations_encountered,
2334 catch ( final IOException e ) {
2335 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2338 if ( all_bin_domain_combinations_lost_fitch != null ) {
2340 executeFitchGainsAnalysis( new File( output_file
2341 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2342 all_bin_domain_combinations_lost_fitch,
2343 all_domains_encountered.size(),
2344 all_bin_domain_combinations_encountered,
2347 catch ( final IOException e ) {
2348 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2351 final Runtime rt = java.lang.Runtime.getRuntime();
2352 final long free_memory = rt.freeMemory() / 1000000;
2353 final long total_memory = rt.totalMemory() / 1000000;
2354 System.out.println();
2355 System.out.println( "Time for analysis : " + ( new Date().getTime() - analysis_start_time ) + "ms" );
2356 System.out.println( "Total running time: " + ( new Date().getTime() - start_time ) + "ms " );
2357 System.out.println( "Free memory : " + free_memory + "MB, total memory: " + total_memory + "MB" );
2358 System.out.println();
2359 System.out.println( "If this application is useful to you, please cite:" );
2360 System.out.println( surfacing.WWW );
2361 System.out.println();
2362 ForesterUtil.programMessage( PRG_NAME, "OK" );
2363 System.out.println();
2366 private static void printOutPercentageOfMultidomainProteins( final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo,
2367 final Writer log_writer ) {
2369 for( final Entry<Integer, Integer> entry : all_genomes_domains_per_potein_histo.entrySet() ) {
2370 sum += entry.getValue();
2372 final double percentage = 100.0 * ( sum - all_genomes_domains_per_potein_histo.get( 1 ) ) / sum;
2373 ForesterUtil.programMessage( PRG_NAME, "Percentage of multidomain proteins: " + percentage + "%" );
2374 log( "Percentage of multidomain proteins: : " + percentage + "%", log_writer );
2377 private static void preparePhylogenyForParsimonyAnalyses( final Phylogeny intree,
2378 final String[][] input_file_properties ) {
2379 final String[] genomes = new String[ input_file_properties.length ];
2380 for( int i = 0; i < input_file_properties.length; ++i ) {
2381 if ( intree.getNodes( input_file_properties[ i ][ 1 ] ).size() > 1 ) {
2382 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
2383 + "] is not unique in input tree " + intree.getName() );
2385 genomes[ i ] = input_file_properties[ i ][ 1 ];
2388 final PhylogenyNodeIterator it = intree.iteratorPostorder();
2389 while ( it.hasNext() ) {
2390 final PhylogenyNode n = it.next();
2391 if ( ForesterUtil.isEmpty( n.getName() ) ) {
2392 if ( n.getNodeData().isHasTaxonomy()
2393 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getTaxonomyCode() ) ) {
2394 n.setName( n.getNodeData().getTaxonomy().getTaxonomyCode() );
2396 else if ( n.getNodeData().isHasTaxonomy()
2397 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
2398 n.setName( n.getNodeData().getTaxonomy().getScientificName() );
2400 else if ( n.getNodeData().isHasTaxonomy()
2401 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getCommonName() ) ) {
2402 n.setName( n.getNodeData().getTaxonomy().getCommonName() );
2406 .fatalError( surfacing.PRG_NAME,
2407 "node with no name, scientific name, common name, or taxonomy code present" );
2412 final List<String> igns = PhylogenyMethods.deleteExternalNodesPositiveSelection( genomes, intree );
2413 if ( igns.size() > 0 ) {
2414 System.out.println( "Not using the following " + igns.size() + " nodes:" );
2415 for( int i = 0; i < igns.size(); ++i ) {
2416 System.out.println( " " + i + ": " + igns.get( i ) );
2418 System.out.println( "--" );
2420 for( int i = 0; i < input_file_properties.length; ++i ) {
2422 intree.getNode( input_file_properties[ i ][ 1 ] );
2424 catch ( final IllegalArgumentException e ) {
2425 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
2426 + "] not present/not unique in input tree" );
2431 // public static StringBuffer stringCombinableDomainsMapToStringBuffer(
2432 // final SortedMap<String, CombinableDomains> map ) {
2433 // final StringBuffer sb = new StringBuffer();
2434 // for( final Iterator<String> iter = map.keySet().iterator();
2435 // iter.hasNext(); ) {
2436 // final Object key = iter.next();
2437 // sb.append( ForesterUtil.pad( new StringBuffer( key.toString() ), 18, ' ',
2439 // final CombinableDomains domain_combination = map.get( key );
2440 // sb.append( ForesterUtil.pad( new StringBuffer( "" +
2441 // domain_combination.getNumberOfCombiningDomains() ), 8,
2443 // sb.append( domain_combination.toStringBuffer() );
2444 // sb.append( ForesterUtil.getLineSeparator() );
2448 private static void printHelp() {
2449 System.out.println();
2450 System.out.println( "Usage:" );
2451 System.out.println();
2452 System.out.println( "% java -Xms256m -Xmx512m -cp forester.jar org.forester.applications." + surfacing.PRG_NAME
2453 + " [options] <phylogen(y|ies) infile> [external node name 1] [name 2] ... [name n]" );
2454 System.out.println();
2455 System.out.println( " Note: This software might need a significant amount of memory (heap space);" );
2457 .println( " hence use \"-Xms128m -Xmx512m\" (or more) to prevent a \"java.lang.OutOfMemoryError\"." );
2458 System.out.println();
2459 System.out.println( " Options: " );
2460 System.out.println( surfacing.DETAILEDNESS_OPTION + ": level of detail for similarities output file (default:"
2461 + DETAILEDNESS_DEFAULT + ")" );
2462 System.out.println( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION
2463 + ": to ignore combinations with self (default: not to ignore)" );
2465 .println( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION
2466 + ": to ignore domains without combinations in any species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2468 .println( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION
2469 + ": to ignore domains specific to one species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2470 System.out.println( surfacing.NOT_IGNORE_DUFS_OPTION
2471 + ": to _not_ ignore DUFs (domains with unknown function) (default: ignore DUFs)" );
2473 .println( surfacing.IGNORE_VIRAL_IDS
2474 + ": to ignore domains with ids containing 'vir', 'retro', 'transpos', 'phage', or starting with 'rv' or 'gag_'" );
2475 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_OPTION + ": sorting for similarities (default: "
2476 + DOMAIN_SORT_FILD_DEFAULT + ")" );
2477 System.out.println( surfacing.OUTPUT_FILE_OPTION + ": name for (main) output file (mandatory)" );
2478 System.out.println( surfacing.MAX_E_VALUE_OPTION + ": max (inclusive) E-value" );
2479 System.out.println( surfacing.MAX_ALLOWED_OVERLAP_OPTION + ": maximal allowed domain overlap" );
2480 System.out.println( surfacing.NO_ENGULFING_OVERLAP_OPTION + ": to ignore engulfed lower confidence domains" );
2481 System.out.println( surfacing.SPECIES_MATRIX_OPTION + ": species matrix" );
2482 System.out.println( surfacing.SCORING_OPTION + ": scoring (default:" + SCORING_DEFAULT + ")" );
2483 System.out.println( surfacing.DOMAIN_COUNT_SORT_OPTION + ": sorting for domain counts (default:"
2484 + DOMAINS_SORT_ORDER_DEFAULT + ")" );
2485 System.out.println( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION + ": domain similarity print option (default:"
2486 + DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT + ")" );
2487 System.out.println( surfacing.CUTOFF_SCORE_FILE_OPTION + ": cutoff score file" );
2488 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION
2489 + ": sort by species count first" );
2490 System.out.println( surfacing.OUTPUT_DIR_OPTION + ": output directory" );
2491 System.out.println( surfacing.PFAM_TO_GO_FILE_USE_OPTION + ": Pfam to GO mapping file" );
2492 System.out.println( surfacing.GO_OBO_FILE_USE_OPTION + ": GO terms file (OBO format)" );
2493 System.out.println( surfacing.GO_NAMESPACE_LIMIT_OPTION + ": limit GO term to one GO namespace" );
2494 System.out.println( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
2495 + "[=<suffix for pairwise comparison output files>]: to perform pairwise comparison based analyses" );
2496 System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION
2497 + ": species tree, to perform (Dollo, Fitch) parismony analyses" );
2499 .println( JACKNIFE_OPTION
2500 + ": perform jacknife resampling for domain and binary domain combination based distance matrices [default resamplings: "
2501 + JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT + "]" );
2502 System.out.println( JACKNIFE_RATIO_OPTION + ": ratio for jacknife resampling [default: "
2503 + JACKNIFE_RATIO_DEFAULT + "]" );
2504 System.out.println( JACKNIFE_RANDOM_SEED_OPTION
2505 + ": seed for random number generator for jacknife resampling [default: "
2506 + JACKNIFE_RANDOM_SEED_DEFAULT + "]" );
2507 // System.out.println( surfacing.INFER_SPECIES_TREES_OPTION
2508 // + ": to infer NJ species trees based on shared domains/binary domain combinations" );
2510 .println( surfacing.INPUT_SPECIES_TREE_OPTION
2511 + "=<treefiles in phyloXML format, separated by #>: to infer domain/binary domain combination gains/losses on given species trees" );
2512 System.out.println( surfacing.FILTER_POSITIVE_OPTION
2513 + "=<file>: to filter out proteins not containing at least one domain listed in <file>" );
2514 System.out.println( surfacing.FILTER_NEGATIVE_OPTION
2515 + "=<file>: to filter out proteins containing at least one domain listed in <file>" );
2516 System.out.println( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION
2517 + "=<file>: to filter out (ignore) domains listed in <file>" );
2518 System.out.println( surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>: to read input files from <file>" );
2520 .println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION
2521 + "=<seed>: seed for random number generator for Fitch Parsimony analysis (type: long, default: no randomization - given a choice, prefer absence" );
2522 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS
2523 + ": to consider directedness in binary combinations: e.g. A-B != B-A" );
2524 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY
2525 + ": to consider directedness and adjacency in binary combinations" );
2527 .println( surfacing.SEQ_EXTRACT_OPTION
2528 + "=<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')" );
2529 System.out.println( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE
2530 + "=<file>: to perfom parsimony analysis on secondary features" );
2531 System.out.println( surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>: to presence/absence genome analysis" );
2532 System.out.println( surfacing.DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS
2533 + ": to output binary domain combinations for (downstream) graph analysis" );
2534 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS + ": to output all proteins per domain" );
2535 System.out.println();
2536 System.out.println();
2537 System.out.println( "Example: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2538 + " org.forester.application.surfacing -detail=punctilious -o=TEST.html -pwc=TEST"
2539 + " -cos=Pfam_ls_22_TC2 -p2g=pfam2go -obo=gene_ontology_edit.obo "
2540 + "-dc_sort=dom -ignore_with_self -no_singles -e=0.001 -mo=1 -no_eo "
2541 + "-ds_output=detailed_html -scoring=domains -sort=alpha -" + JACKNIFE_OPTION
2542 + "=50 human mouse brafl strpu" );
2543 System.out.println();
2546 private static void processFilter( final File filter_file, final SortedSet<DomainId> filter ) {
2547 SortedSet<String> filter_str = null;
2549 filter_str = ForesterUtil.file2set( filter_file );
2551 catch ( final IOException e ) {
2552 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2554 if ( filter_str != null ) {
2555 for( final String string : filter_str ) {
2556 filter.add( new DomainId( string ) );
2560 System.out.println( "Filter:" );
2561 for( final DomainId domainId : filter ) {
2562 System.out.println( domainId.getId() );
2567 private static String[][] processInputFileNames( final String[] names ) {
2568 final String[][] input_file_properties = new String[ names.length ][];
2569 for( int i = 0; i < names.length; ++i ) {
2570 if ( names[ i ].indexOf( SEPARATOR_FOR_INPUT_VALUES ) < 0 ) {
2571 input_file_properties[ i ] = new String[ 2 ];
2572 input_file_properties[ i ][ 0 ] = names[ i ];
2573 input_file_properties[ i ][ 1 ] = names[ i ];
2576 input_file_properties[ i ] = names[ i ].split( surfacing.SEPARATOR_FOR_INPUT_VALUES + "" );
2577 if ( input_file_properties[ i ].length != 3 ) {
2579 .fatalError( surfacing.PRG_NAME,
2580 "properties for the input files (hmmpfam output) are expected "
2581 + "to be in the following format \"<hmmpfam output file>#<species>\" (or just one word, which is both the filename and the species id), instead received \""
2582 + names[ i ] + "\"" );
2585 final String error = ForesterUtil.isReadableFile( new File( input_file_properties[ i ][ 0 ] ) );
2586 if ( !ForesterUtil.isEmpty( error ) ) {
2587 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
2590 return input_file_properties;
2593 private static void processPlusMinusAnalysisOption( final CommandLineArguments cla,
2594 final List<String> high_copy_base,
2595 final List<String> high_copy_target,
2596 final List<String> low_copy,
2597 final List<Object> numbers ) {
2598 if ( cla.isOptionSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2599 if ( !cla.isOptionValueSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2600 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for 'plus-minus' file: -"
2601 + surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>" );
2603 final File plus_minus_file = new File( cla.getOptionValue( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) );
2604 final String msg = ForesterUtil.isReadableFile( plus_minus_file );
2605 if ( !ForesterUtil.isEmpty( msg ) ) {
2606 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + plus_minus_file + "\": " + msg );
2608 processPlusMinusFile( plus_minus_file, high_copy_base, high_copy_target, low_copy, numbers );
2612 // First numbers is minimal difference, second is factor.
2613 private static void processPlusMinusFile( final File plus_minus_file,
2614 final List<String> high_copy_base,
2615 final List<String> high_copy_target,
2616 final List<String> low_copy,
2617 final List<Object> numbers ) {
2618 Set<String> species_set = null;
2619 int min_diff = PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT;
2620 double factor = PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT;
2622 species_set = ForesterUtil.file2set( plus_minus_file );
2624 catch ( final IOException e ) {
2625 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2627 if ( species_set != null ) {
2628 for( final String species : species_set ) {
2629 final String species_trimmed = species.substring( 1 );
2630 if ( species.startsWith( "+" ) ) {
2631 if ( low_copy.contains( species_trimmed ) ) {
2632 ForesterUtil.fatalError( surfacing.PRG_NAME,
2633 "species/genome names can not appear with both '+' and '-' suffix, as appears the case for: \""
2634 + species_trimmed + "\"" );
2636 high_copy_base.add( species_trimmed );
2638 else if ( species.startsWith( "*" ) ) {
2639 if ( low_copy.contains( species_trimmed ) ) {
2640 ForesterUtil.fatalError( surfacing.PRG_NAME,
2641 "species/genome names can not appear with both '*' and '-' suffix, as appears the case for: \""
2642 + species_trimmed + "\"" );
2644 high_copy_target.add( species_trimmed );
2646 else if ( species.startsWith( "-" ) ) {
2647 if ( high_copy_base.contains( species_trimmed ) || high_copy_target.contains( species_trimmed ) ) {
2648 ForesterUtil.fatalError( surfacing.PRG_NAME,
2649 "species/genome names can not appear with both '+' or '*' and '-' suffix, as appears the case for: \""
2650 + species_trimmed + "\"" );
2652 low_copy.add( species_trimmed );
2654 else if ( species.startsWith( "$D" ) ) {
2656 min_diff = Integer.parseInt( species.substring( 3 ) );
2658 catch ( final NumberFormatException e ) {
2659 ForesterUtil.fatalError( surfacing.PRG_NAME,
2660 "could not parse integer value for minimal difference from: \""
2661 + species.substring( 3 ) + "\"" );
2664 else if ( species.startsWith( "$F" ) ) {
2666 factor = Double.parseDouble( species.substring( 3 ) );
2668 catch ( final NumberFormatException e ) {
2669 ForesterUtil.fatalError( surfacing.PRG_NAME, "could not parse double value for factor from: \""
2670 + species.substring( 3 ) + "\"" );
2673 else if ( species.startsWith( "#" ) ) {
2678 .fatalError( surfacing.PRG_NAME,
2679 "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: \""
2682 numbers.add( new Integer( min_diff + "" ) );
2683 numbers.add( new Double( factor + "" ) );
2687 ForesterUtil.fatalError( surfacing.PRG_NAME, "'plus minus' file [" + plus_minus_file + "] appears empty" );
2691 private static void writePresentToNexus( final File output_file,
2692 final File positive_filter_file,
2693 final SortedSet<DomainId> filter,
2694 final List<GenomeWideCombinableDomains> gwcd_list ) {
2697 .writeMatrixToFile( DomainParsimonyCalculator
2698 .createMatrixOfDomainPresenceOrAbsence( gwcd_list, positive_filter_file == null ? null
2699 : filter ), output_file + DOMAINS_PRESENT_NEXUS, Format.NEXUS_BINARY );
2700 SurfacingUtil.writeMatrixToFile( DomainParsimonyCalculator
2701 .createMatrixOfBinaryDomainCombinationPresenceOrAbsence( gwcd_list ), output_file
2702 + BDC_PRESENT_NEXUS, Format.NEXUS_BINARY );
2704 catch ( final Exception e ) {
2705 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2709 private static void writeProteinListsForAllSpecies( final File output_dir,
2710 final SortedMap<Species, List<Protein>> protein_lists_per_species,
2711 final List<GenomeWideCombinableDomains> gwcd_list ) {
2712 final SortedSet<DomainId> all_domains = new TreeSet<DomainId>();
2713 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
2714 all_domains.addAll( gwcd.getAllDomainIds() );
2716 for( final DomainId domain : all_domains ) {
2717 final File out = new File( output_dir + ForesterUtil.FILE_SEPARATOR + domain + SEQ_EXTRACT_SUFFIX );
2718 SurfacingUtil.checkForOutputFileWriteability( out );
2720 final Writer proteins_file_writer = new BufferedWriter( new FileWriter( out ) );
2721 SurfacingUtil.extractProteinNames( protein_lists_per_species, domain, proteins_file_writer, "\t" );
2722 proteins_file_writer.close();
2724 catch ( final IOException e ) {
2725 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2727 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote proteins list to \"" + out + "\"" );