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;
40 import java.util.SortedMap;
41 import java.util.SortedSet;
42 import java.util.TreeMap;
43 import java.util.TreeSet;
45 import org.forester.evoinference.distance.NeighborJoining;
46 import org.forester.evoinference.matrix.character.CharacterStateMatrix.Format;
47 import org.forester.evoinference.matrix.distance.DistanceMatrix;
48 import org.forester.go.GoId;
49 import org.forester.go.GoNameSpace;
50 import org.forester.go.GoTerm;
51 import org.forester.go.GoUtils;
52 import org.forester.go.OBOparser;
53 import org.forester.go.PfamToGoMapping;
54 import org.forester.go.PfamToGoParser;
55 import org.forester.io.parsers.HmmscanPerDomainTableParser;
56 import org.forester.io.parsers.HmmscanPerDomainTableParser.INDIVIDUAL_SCORE_CUTOFF;
57 import org.forester.io.writers.PhylogenyWriter;
58 import org.forester.phylogeny.Phylogeny;
59 import org.forester.phylogeny.PhylogenyMethods;
60 import org.forester.phylogeny.PhylogenyNode;
61 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
62 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
63 import org.forester.surfacing.BasicDomainSimilarityCalculator;
64 import org.forester.surfacing.BasicGenomeWideCombinableDomains;
65 import org.forester.surfacing.BasicSpecies;
66 import org.forester.surfacing.BinaryDomainCombination;
67 import org.forester.surfacing.CombinationsBasedPairwiseDomainSimilarityCalculator;
68 import org.forester.surfacing.DomainCountsBasedPairwiseSimilarityCalculator;
69 import org.forester.surfacing.DomainCountsDifferenceUtil;
70 import org.forester.surfacing.DomainId;
71 import org.forester.surfacing.DomainLengthsTable;
72 import org.forester.surfacing.DomainParsimonyCalculator;
73 import org.forester.surfacing.DomainSimilarity;
74 import org.forester.surfacing.DomainSimilarity.DomainSimilarityScoring;
75 import org.forester.surfacing.DomainSimilarity.DomainSimilaritySortField;
76 import org.forester.surfacing.DomainSimilarityCalculator;
77 import org.forester.surfacing.DomainSimilarityCalculator.Detailedness;
78 import org.forester.surfacing.GenomeWideCombinableDomains;
79 import org.forester.surfacing.GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder;
80 import org.forester.surfacing.MappingResults;
81 import org.forester.surfacing.PairwiseDomainSimilarityCalculator;
82 import org.forester.surfacing.PairwiseGenomeComparator;
83 import org.forester.surfacing.PrintableDomainSimilarity;
84 import org.forester.surfacing.PrintableDomainSimilarity.PRINT_OPTION;
85 import org.forester.surfacing.Protein;
86 import org.forester.surfacing.ProteinCountsBasedPairwiseDomainSimilarityCalculator;
87 import org.forester.surfacing.Species;
88 import org.forester.surfacing.SurfacingUtil;
89 import org.forester.util.BasicTable;
90 import org.forester.util.BasicTableParser;
91 import org.forester.util.CommandLineArguments;
92 import org.forester.util.DescriptiveStatistics;
93 import org.forester.util.ForesterConstants;
94 import org.forester.util.ForesterUtil;
96 public class surfacing {
98 public final static String DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS = "graph_analysis_out";
99 public final static String DOMAIN_COMBINITONS_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_dc.dot";
100 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_fitch_present_dc.dot";
101 public final static String DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX = ".dcc";
103 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS = "_dollo_gl_d";
104 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_gl_dc";
105 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_DOMAINS = "_fitch_gl_d";
106 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_gl_dc";
108 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS = "_dollo_glc_d";
109 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_glc_dc";
110 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_DOMAINS = "_fitch_glc_d";
111 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_glc_dc";
113 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_BC = "_fitch_gains_dc";
114 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_HTML_BC = "_fitch_gains_dc.html";
115 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_BC = "_fitch_losses_dc";
116 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_HTML_BC = "_fitch_losses_dc.html";
117 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC = "_fitch_present_dc";
118 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_HTML_BC = "_fitch_present_dc.html";
119 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_D = "_dollo_gains_d";
120 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_HTML_D = "_dollo_gains_d.html";
121 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_D = "_dollo_losses_d";
122 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_HTML_D = "_dollo_losses_d.html";
123 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_D = "_dollo_present_d";
124 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_HTML_D = "_dollo_present_d.html";
125 public final static String DOMAINS_PRESENT_NEXUS = "_dom.nex";
126 public final static String BDC_PRESENT_NEXUS = "_dc.nex";
128 public final static String PRG_NAME = "surfacing";
129 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_d_dollo"
130 + ForesterConstants.PHYLO_XML_SUFFIX;
131 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_d_fitch"
132 + ForesterConstants.PHYLO_XML_SUFFIX;
133 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_dc_dollo"
134 + ForesterConstants.PHYLO_XML_SUFFIX;
135 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_dc_fitch"
136 + ForesterConstants.PHYLO_XML_SUFFIX;
137 public static final String NEXUS_EXTERNAL_DOMAINS = "_dom.nex";
138 public static final String NEXUS_EXTERNAL_DOMAIN_COMBINATIONS = "_dc.nex";
139 public static final String NEXUS_SECONDARY_FEATURES = "_secondary_features.nex";
140 public static final String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_gl_secondary_features";
141 public static final String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_glc_secondary_features";
142 public static final String PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES = "_dollo_gains_secondary_features";
143 public static final String PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES = "_dollo_losses_secondary_features";
144 public static final String PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES = "_dollo_present_secondary_features";
145 public static final String SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_secondary_features_dollo"
146 + ForesterConstants.PHYLO_XML_SUFFIX;
147 public static final String PARSIMONY_OUTPUT_DOLLO_ALL_GOID_D_ALL_NAMESPACES = "_dollo_goid_d";
148 public static final String PARSIMONY_OUTPUT_FITCH_ALL_GOID_BC_ALL_NAMESPACES = "_fitch_goid_dc";
149 final static private String HELP_OPTION_1 = "help";
150 final static private String HELP_OPTION_2 = "h";
151 final static private String OUTPUT_DIR_OPTION = "out_dir";
152 final static private String SCORING_OPTION = "scoring";
153 private static final DomainSimilarityScoring SCORING_DEFAULT = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
154 final static private String SCORING_DOMAIN_COUNT_BASED = "domains";
155 final static private String SCORING_PROTEIN_COUNT_BASED = "proteins";
156 final static private String SCORING_COMBINATION_BASED = "combinations";
157 final static private String DETAILEDNESS_OPTION = "detail";
158 private final static Detailedness DETAILEDNESS_DEFAULT = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
159 final static private String SPECIES_MATRIX_OPTION = "smatrix";
160 final static private String DETAILEDNESS_BASIC = "basic";
161 final static private String DETAILEDNESS_LIST_IDS = "list_ids";
162 final static private String DETAILEDNESS_PUNCTILIOUS = "punctilious";
163 final static private String DOMAIN_SIMILARITY_SORT_OPTION = "sort";
164 private static final DomainSimilaritySortField DOMAIN_SORT_FILD_DEFAULT = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
165 final static private String DOMAIN_SIMILARITY_SORT_MIN = "min";
166 final static private String DOMAIN_SIMILARITY_SORT_MAX = "max";
167 final static private String DOMAIN_SIMILARITY_SORT_SD = "sd";
168 final static private String DOMAIN_SIMILARITY_SORT_MEAN = "mean";
169 final static private String DOMAIN_SIMILARITY_SORT_DIFF = "diff";
170 final static private String DOMAIN_SIMILARITY_SORT_COUNTS_DIFF = "count_diff";
171 final static private String DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF = "abs_count_diff";
172 final static private String DOMAIN_SIMILARITY_SORT_SPECIES_COUNT = "species";
173 final static private String DOMAIN_SIMILARITY_SORT_ALPHA = "alpha";
174 final static private String DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION = "species_first";
175 final static private String DOMAIN_COUNT_SORT_OPTION = "dc_sort";
176 private static final GenomeWideCombinableDomainsSortOrder DOMAINS_SORT_ORDER_DEFAULT = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
177 final static private String DOMAIN_COUNT_SORT_ALPHA = "alpha";
178 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT = "dom";
179 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT = "prot";
180 final static private String DOMAIN_COUNT_SORT_COMBINATIONS_COUNT = "comb";
181 final static private String CUTOFF_SCORE_FILE_OPTION = "cos";
182 final static private String NOT_IGNORE_DUFS_OPTION = "dufs";
183 final static private String MAX_E_VALUE_OPTION = "e";
184 final static private String MAX_ALLOWED_OVERLAP_OPTION = "mo";
185 final static private String NO_ENGULFING_OVERLAP_OPTION = "no_eo";
186 final static private String IGNORE_COMBINATION_WITH_SAME_OPTION = "ignore_self_comb";
187 final static private String PAIRWISE_DOMAIN_COMPARISONS_PREFIX = "pwc_";
188 final static private String PAIRWISE_DOMAIN_COMPARISONS_OPTION = "pwc";
189 final static private String OUTPUT_FILE_OPTION = "o";
190 final static private String PFAM_TO_GO_FILE_USE_OPTION = "p2g";
191 final static private String GO_OBO_FILE_USE_OPTION = "obo";
192 final static private String GO_NAMESPACE_LIMIT_OPTION = "go_namespace";
193 final static private String GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION = "molecular_function";
194 final static private String GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS = "biological_process";
195 final static private String GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT = "cellular_component";
196 final static private String SECONDARY_FEATURES_PARSIMONY_MAP_FILE = "secondary";
197 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED = "simple_tab";
198 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML = "simple_html";
199 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML = "detailed_html";
200 final static private String DOMAIN_SIMILARITY_PRINT_OPTION = "ds_output";
201 private static final PRINT_OPTION DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT = PrintableDomainSimilarity.PRINT_OPTION.HTML;
202 final static private String IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION = "ignore_singlet_domains";
203 final static private String IGNORE_VIRAL_IDS = "ignore_viral_ids";
204 final static private boolean IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT = false;
205 final static private String IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION = "ignore_species_specific_domains";
206 final static private boolean IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT = false;
207 final static private String MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score.pwd";
208 final static private String MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains.pwd";
209 final static private String MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations.pwd";
210 final static private String NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score_NJ"
211 + ForesterConstants.PHYLO_XML_SUFFIX;
212 final static private String NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains_NJ"
213 + ForesterConstants.PHYLO_XML_SUFFIX;
214 final static private String NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations_NJ"
215 + ForesterConstants.PHYLO_XML_SUFFIX;
216 final static private String JACKNIFE_OPTION = "jack";
217 final static private String JACKNIFE_RANDOM_SEED_OPTION = "seed";
218 final static private String JACKNIFE_RATIO_OPTION = "jack_ratio";
219 private static final int JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT = 100;
220 final static private long JACKNIFE_RANDOM_SEED_DEFAULT = 19;
221 final static private double JACKNIFE_RATIO_DEFAULT = 0.5;
222 //final static private String INFER_SPECIES_TREES_OPTION = "species_tree_inference";
223 final static private String INFERRED_SD_BASED_NJ_SPECIES_TREE_SUFFIX = "_sd_nj.nh";
224 final static private String INFERRED_SBC_BASED_NJ_SPECIES_TREE_SUFFIX = "_sbc_nj.nh";
225 final static private String FILTER_POSITIVE_OPTION = "pos_filter";
226 final static private String FILTER_NEGATIVE_OPTION = "neg_filter";
227 final static private String FILTER_NEGATIVE_DOMAINS_OPTION = "neg_dom_filter";
228 final static private String INPUT_FILES_FROM_FILE_OPTION = "input";
229 final static private String INPUT_SPECIES_TREE_OPTION = "species_tree";
230 final static private String SEQ_EXTRACT_OPTION = "prot_extract";
231 final static private char SEPARATOR_FOR_INPUT_VALUES = '#';
232 final static private String PRG_VERSION = "2.100";
233 final static private String PRG_DATE = "2011.06.17";
234 final static private String E_MAIL = "czmasek@burnham.org";
235 final static private String WWW = "www.phylosoft.org/forester/applications/surfacing";
236 final static private boolean IGNORE_DUFS_DEFAULT = true;
237 final static private boolean IGNORE_COMBINATION_WITH_SAME_DEFAULLT = false;
238 final static private double MAX_E_VALUE_DEFAULT = -1;
239 final static private int MAX_ALLOWED_OVERLAP_DEFAULT = -1;
240 private static final String RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION = "random_seed";
241 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS = "consider_bdc_direction";
242 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY = "consider_bdc_adj";
243 private static final String SEQ_EXTRACT_SUFFIX = ".prot";
244 private static final String PLUS_MINUS_ANALYSIS_OPTION = "plus_minus";
245 private static final String PLUS_MINUS_DOM_SUFFIX = "_plus_minus_dom.txt";
246 private static final String PLUS_MINUS_DOM_SUFFIX_HTML = "_plus_minus_dom.html";
247 private static final String PLUS_MINUS_DC_SUFFIX_HTML = "_plus_minus_dc.html";
248 private static final int PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT = 0;
249 private static final double PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT = 1.0;
250 private static final String PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_all.txt";
251 private static final String PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_passing.txt";
252 private static final String OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS = "all_prot";
253 private static final boolean VERBOSE = false;
254 private static final String OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_gains_counts";
255 private static final String OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_losses_counts";
256 private static final String DOMAIN_LENGTHS_ANALYSIS_SUFFIX = "_domain_lengths_analysis";
257 private static final boolean PERFORM_DOMAIN_LENGTH_ANALYSIS = true;
258 public static final String ALL_PFAMS_ENCOUNTERED_SUFFIX = "_all_encountered_pfams";
259 public static final String ALL_PFAMS_ENCOUNTERED_WITH_GO_ANNOTATION_SUFFIX = "_all_encountered_pfams_with_go_annotation";
260 public static final String ENCOUNTERED_PFAMS_SUMMARY_SUFFIX = "_encountered_pfams_summary";
261 public static final String ALL_PFAMS_GAINED_AS_DOMAINS_SUFFIX = "_all_pfams_gained_as_domains";
262 public static final String ALL_PFAMS_LOST_AS_DOMAINS_SUFFIX = "_all_pfams_lost_as_domains";
263 public static final String ALL_PFAMS_GAINED_AS_DC_SUFFIX = "_all_pfams_gained_as_dc";
264 public static final String ALL_PFAMS_LOST_AS_DC_SUFFIX = "_all_pfams_lost_as_dc";
265 public static final String BASE_DIRECTORY_PER_NODE_DOMAIN_GAIN_LOSS_FILES = "PER_NODE_EVENTS";
266 public static final String BASE_DIRECTORY_PER_SUBTREE_DOMAIN_GAIN_LOSS_FILES = "PER_SUBTREE_EVENTS";
267 public static final String D_PROMISCUITY_FILE_SUFFIX = "_domain_promiscuities";
268 private static final String LOG_FILE_SUFFIX = "_log.txt";
269 private static final String DATA_FILE_SUFFIX = "_domain_combination_data.txt";
270 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";
271 private static final INDIVIDUAL_SCORE_CUTOFF INDIVIDUAL_SCORE_CUTOFF_DEFAULT = INDIVIDUAL_SCORE_CUTOFF.FULL_SEQUENCE;
272 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts.txt";
273 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists.txt";
274 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping.txt";
275 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_UNIQUE_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping_unique.txt";
277 private static void checkWriteabilityForPairwiseComparisons( final PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option,
278 final String[][] input_file_properties,
279 final String automated_pairwise_comparison_suffix,
280 final File outdir ) {
281 for( int i = 0; i < input_file_properties.length; ++i ) {
282 for( int j = 0; j < i; ++j ) {
283 final String species_i = input_file_properties[ i ][ 1 ];
284 final String species_j = input_file_properties[ j ][ 1 ];
285 String pairwise_similarities_output_file_str = PAIRWISE_DOMAIN_COMPARISONS_PREFIX + species_i + "_"
286 + species_j + automated_pairwise_comparison_suffix;
287 switch ( domain_similarity_print_option ) {
289 if ( !pairwise_similarities_output_file_str.endsWith( ".html" ) ) {
290 pairwise_similarities_output_file_str += ".html";
294 final String error = ForesterUtil
295 .isWritableFile( new File( outdir == null ? pairwise_similarities_output_file_str : outdir
296 + ForesterUtil.FILE_SEPARATOR + pairwise_similarities_output_file_str ) );
297 if ( !ForesterUtil.isEmpty( error ) ) {
298 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
304 private static StringBuilder createParametersAsString( final boolean ignore_dufs,
305 final double e_value_max,
306 final int max_allowed_overlap,
307 final boolean no_engulfing_overlaps,
308 final File cutoff_scores_file,
309 final BinaryDomainCombination.DomainCombinationType dc_type ) {
310 final StringBuilder parameters_sb = new StringBuilder();
311 parameters_sb.append( "E-value: " + e_value_max );
312 if ( cutoff_scores_file != null ) {
313 parameters_sb.append( ", Cutoff-scores-file: " + cutoff_scores_file );
316 parameters_sb.append( ", Cutoff-scores-file: not-set" );
318 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
319 parameters_sb.append( ", Max-overlap: " + max_allowed_overlap );
322 parameters_sb.append( ", Max-overlap: not-set" );
324 if ( no_engulfing_overlaps ) {
325 parameters_sb.append( ", Engulfing-overlaps: not-allowed" );
328 parameters_sb.append( ", Engulfing-overlaps: allowed" );
331 parameters_sb.append( ", Ignore-dufs: true" );
334 parameters_sb.append( ", Ignore-dufs: false" );
336 parameters_sb.append( ", DC type (if applicable): " + dc_type );
337 return parameters_sb;
341 * Warning: This side-effects 'all_bin_domain_combinations_encountered'!
345 * @param all_bin_domain_combinations_changed
346 * @param sum_of_all_domains_encountered
347 * @param all_bin_domain_combinations_encountered
348 * @param is_gains_analysis
349 * @throws IOException
351 private static void executeFitchGainsAnalysis( final File output_file,
352 final List<BinaryDomainCombination> all_bin_domain_combinations_changed,
353 final int sum_of_all_domains_encountered,
354 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered,
355 final boolean is_gains_analysis ) throws IOException {
356 SurfacingUtil.checkForOutputFileWriteability( output_file );
357 final Writer out = ForesterUtil.createBufferedWriter( output_file );
358 final SortedMap<Object, Integer> bdc_to_counts = ForesterUtil
359 .listToSortedCountsMap( all_bin_domain_combinations_changed );
360 final SortedSet<DomainId> all_domains_in_combination_changed_more_than_once = new TreeSet<DomainId>();
361 final SortedSet<DomainId> all_domains_in_combination_changed_only_once = new TreeSet<DomainId>();
364 for( final Object bdc_object : bdc_to_counts.keySet() ) {
365 final BinaryDomainCombination bdc = ( BinaryDomainCombination ) bdc_object;
366 final int count = bdc_to_counts.get( bdc_object );
368 ForesterUtil.unexpectedFatalError( PRG_NAME, "count < 1 " );
370 out.write( bdc + "\t" + count + ForesterUtil.LINE_SEPARATOR );
372 all_domains_in_combination_changed_more_than_once.add( bdc.getId0() );
373 all_domains_in_combination_changed_more_than_once.add( bdc.getId1() );
376 else if ( count == 1 ) {
377 all_domains_in_combination_changed_only_once.add( bdc.getId0() );
378 all_domains_in_combination_changed_only_once.add( bdc.getId1() );
382 final int all = all_bin_domain_combinations_encountered.size();
384 if ( !is_gains_analysis ) {
385 all_bin_domain_combinations_encountered.removeAll( all_bin_domain_combinations_changed );
386 never_lost = all_bin_domain_combinations_encountered.size();
387 for( final BinaryDomainCombination bdc : all_bin_domain_combinations_encountered ) {
388 out.write( bdc + "\t" + "0" + ForesterUtil.LINE_SEPARATOR );
391 if ( is_gains_analysis ) {
392 out.write( "Sum of all distinct domain combinations appearing once : " + one
393 + ForesterUtil.LINE_SEPARATOR );
394 out.write( "Sum of all distinct domain combinations appearing more than once : " + above_one
395 + ForesterUtil.LINE_SEPARATOR );
396 out.write( "Sum of all distinct domains in combinations apppearing only once : "
397 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
398 out.write( "Sum of all distinct domains in combinations apppearing more than once: "
399 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
402 out.write( "Sum of all distinct domain combinations never lost : " + never_lost
403 + ForesterUtil.LINE_SEPARATOR );
404 out.write( "Sum of all distinct domain combinations lost once : " + one
405 + ForesterUtil.LINE_SEPARATOR );
406 out.write( "Sum of all distinct domain combinations lost more than once : " + above_one
407 + ForesterUtil.LINE_SEPARATOR );
408 out.write( "Sum of all distinct domains in combinations lost only once : "
409 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
410 out.write( "Sum of all distinct domains in combinations lost more than once: "
411 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
413 out.write( "All binary combinations : " + all
414 + ForesterUtil.LINE_SEPARATOR );
415 out.write( "All domains : "
416 + sum_of_all_domains_encountered );
418 ForesterUtil.programMessage( surfacing.PRG_NAME,
419 "Wrote fitch domain combination dynamics counts analysis to \"" + output_file
423 private static void executePlusMinusAnalysis( final File output_file,
424 final List<String> plus_minus_analysis_high_copy_base,
425 final List<String> plus_minus_analysis_high_copy_target,
426 final List<String> plus_minus_analysis_low_copy,
427 final List<GenomeWideCombinableDomains> gwcd_list,
428 final SortedMap<Species, List<Protein>> protein_lists_per_species,
429 final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
430 final Map<GoId, GoTerm> go_id_to_term_map,
431 final List<Object> plus_minus_analysis_numbers ) {
432 final Set<String> all_spec = new HashSet<String>();
433 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
434 all_spec.add( gwcd.getSpecies().getSpeciesId() );
436 final File html_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX_HTML );
437 final File plain_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX );
438 final File html_out_dc = new File( output_file + PLUS_MINUS_DC_SUFFIX_HTML );
439 final File all_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX );
440 final File passing_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX );
441 final File proteins_file_base = new File( output_file + "" );
442 final int min_diff = ( ( Integer ) plus_minus_analysis_numbers.get( 0 ) ).intValue();
443 final double factor = ( ( Double ) plus_minus_analysis_numbers.get( 1 ) ).doubleValue();
445 DomainCountsDifferenceUtil.calculateCopyNumberDifferences( gwcd_list,
446 protein_lists_per_species,
447 plus_minus_analysis_high_copy_base,
448 plus_minus_analysis_high_copy_target,
449 plus_minus_analysis_low_copy,
455 domain_id_to_go_ids_map,
457 all_domains_go_ids_out_dom,
458 passing_domains_go_ids_out_dom,
459 proteins_file_base );
461 catch ( final IOException e ) {
462 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
464 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
465 + html_out_dom + "\"" );
466 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
467 + plain_out_dom + "\"" );
468 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \"" + html_out_dc
470 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based passing GO ids to \""
471 + passing_domains_go_ids_out_dom + "\"" );
472 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based all GO ids to \""
473 + all_domains_go_ids_out_dom + "\"" );
476 private static Phylogeny[] getIntrees( final File[] intree_files,
477 final int number_of_genomes,
478 final String[][] input_file_properties ) {
479 final Phylogeny[] intrees = new Phylogeny[ intree_files.length ];
481 for( final File intree_file : intree_files ) {
482 Phylogeny intree = null;
483 final String error = ForesterUtil.isReadableFile( intree_file );
484 if ( !ForesterUtil.isEmpty( error ) ) {
485 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read input tree file [" + intree_file + "]: "
489 final Phylogeny[] p_array = ParserBasedPhylogenyFactory.getInstance()
490 .create( intree_file, ForesterUtil.createParserDependingOnFileType( intree_file, true ) );
491 if ( p_array.length < 1 ) {
492 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
493 + "] does not contain any phylogeny in phyloXML format" );
495 else if ( p_array.length > 1 ) {
496 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
497 + "] contains more than one phylogeny in phyloXML format" );
499 intree = p_array[ 0 ];
501 catch ( final Exception e ) {
502 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read input tree from file [" + intree_file
505 if ( ( intree == null ) || intree.isEmpty() ) {
506 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" );
508 if ( !intree.isRooted() ) {
509 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is not rooted" );
511 if ( intree.getNumberOfExternalNodes() < number_of_genomes ) {
512 ForesterUtil.fatalError( surfacing.PRG_NAME,
513 "number of external nodes [" + intree.getNumberOfExternalNodes()
514 + "] of input tree [" + intree_file
515 + "] is smaller than the number of genomes the be analyzed ["
516 + number_of_genomes + "]" );
518 final StringBuilder parent_names = new StringBuilder();
519 final int nodes_lacking_name = SurfacingUtil.getNumberOfNodesLackingName( intree, parent_names );
520 if ( nodes_lacking_name > 0 ) {
521 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] has "
522 + nodes_lacking_name + " node(s) lacking a name [parent names:" + parent_names + "]" );
524 preparePhylogenyForParsimonyAnalyses( intree, input_file_properties );
525 if ( !intree.isCompletelyBinary() ) {
526 ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "input tree [" + intree_file
527 + "] is not completely binary" );
529 intrees[ i++ ] = intree;
534 private static List<Phylogeny> inferSpeciesTrees( final File outfile, final List<DistanceMatrix> distances_list ) {
535 final NeighborJoining nj = NeighborJoining.createInstance();
536 final List<Phylogeny> phylogenies = nj.execute( distances_list );
537 final PhylogenyWriter w = new PhylogenyWriter();
539 w.toNewHampshire( phylogenies, true, true, outfile, ";" );
541 catch ( final IOException e ) {
542 ForesterUtil.fatalError( PRG_NAME, "failed to write to outfile [" + outfile + "]: " + e.getMessage() );
547 private static void log( final String msg, final Writer w ) {
550 w.write( ForesterUtil.LINE_SEPARATOR );
552 catch ( final IOException e ) {
553 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
557 public static void main( final String args[] ) {
558 final long start_time = new Date().getTime();
559 // final StringBuffer log = new StringBuffer();
560 final StringBuilder html_desc = new StringBuilder();
561 ForesterUtil.printProgramInformation( surfacing.PRG_NAME,
562 surfacing.PRG_VERSION,
566 final String nl = ForesterUtil.LINE_SEPARATOR;
567 html_desc.append( "<table>" + nl );
568 html_desc.append( "<tr><td>Produced by:</td><td>" + surfacing.PRG_NAME + "</td></tr>" + nl );
569 html_desc.append( "<tr><td>Version:</td><td>" + surfacing.PRG_VERSION + "</td></tr>" + nl );
570 html_desc.append( "<tr><td>Release Date:</td><td>" + surfacing.PRG_DATE + "</td></tr>" + nl );
571 html_desc.append( "<tr><td>Contact:</td><td>" + surfacing.E_MAIL + "</td></tr>" + nl );
572 html_desc.append( "<tr><td>WWW:</td><td>" + surfacing.WWW + "</td></tr>" + nl );
573 CommandLineArguments cla = null;
575 cla = new CommandLineArguments( args );
577 catch ( final Exception e ) {
578 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
580 if ( cla.isOptionSet( surfacing.HELP_OPTION_1 ) || cla.isOptionSet( surfacing.HELP_OPTION_2 ) ) {
581 surfacing.printHelp();
584 if ( ( args.length < 1 ) ) {
585 surfacing.printHelp();
588 final List<String> allowed_options = new ArrayList<String>();
589 allowed_options.add( surfacing.NOT_IGNORE_DUFS_OPTION );
590 allowed_options.add( surfacing.MAX_E_VALUE_OPTION );
591 allowed_options.add( surfacing.DETAILEDNESS_OPTION );
592 allowed_options.add( surfacing.OUTPUT_FILE_OPTION );
593 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_OPTION );
594 allowed_options.add( surfacing.SPECIES_MATRIX_OPTION );
595 allowed_options.add( surfacing.SCORING_OPTION );
596 allowed_options.add( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
597 allowed_options.add( surfacing.NO_ENGULFING_OVERLAP_OPTION );
598 allowed_options.add( surfacing.DOMAIN_COUNT_SORT_OPTION );
599 allowed_options.add( surfacing.CUTOFF_SCORE_FILE_OPTION );
600 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION );
601 allowed_options.add( surfacing.OUTPUT_DIR_OPTION );
602 allowed_options.add( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION );
603 allowed_options.add( surfacing.PFAM_TO_GO_FILE_USE_OPTION );
604 allowed_options.add( surfacing.GO_OBO_FILE_USE_OPTION );
605 allowed_options.add( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION );
606 allowed_options.add( surfacing.GO_NAMESPACE_LIMIT_OPTION );
607 allowed_options.add( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
608 allowed_options.add( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION );
609 allowed_options.add( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS );
610 allowed_options.add( JACKNIFE_OPTION );
611 allowed_options.add( JACKNIFE_RANDOM_SEED_OPTION );
612 allowed_options.add( JACKNIFE_RATIO_OPTION );
613 allowed_options.add( INPUT_SPECIES_TREE_OPTION );
614 //allowed_options.add( INFER_SPECIES_TREES_OPTION );
615 allowed_options.add( FILTER_POSITIVE_OPTION );
616 allowed_options.add( FILTER_NEGATIVE_OPTION );
617 allowed_options.add( INPUT_FILES_FROM_FILE_OPTION );
618 allowed_options.add( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
619 allowed_options.add( FILTER_NEGATIVE_DOMAINS_OPTION );
620 allowed_options.add( IGNORE_VIRAL_IDS );
621 allowed_options.add( SEQ_EXTRACT_OPTION );
622 allowed_options.add( SECONDARY_FEATURES_PARSIMONY_MAP_FILE );
623 allowed_options.add( PLUS_MINUS_ANALYSIS_OPTION );
624 allowed_options.add( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS );
625 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS );
626 allowed_options.add( CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY );
627 boolean ignore_dufs = surfacing.IGNORE_DUFS_DEFAULT;
628 boolean ignore_combination_with_same = surfacing.IGNORE_COMBINATION_WITH_SAME_DEFAULLT;
629 double e_value_max = surfacing.MAX_E_VALUE_DEFAULT;
630 int max_allowed_overlap = surfacing.MAX_ALLOWED_OVERLAP_DEFAULT;
631 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
632 if ( dissallowed_options.length() > 0 ) {
633 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown option(s): " + dissallowed_options );
635 boolean output_binary_domain_combinationsfor_graph_analysis = false;
636 if ( cla.isOptionSet( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS ) ) {
637 output_binary_domain_combinationsfor_graph_analysis = true;
639 if ( cla.isOptionSet( surfacing.MAX_E_VALUE_OPTION ) ) {
641 e_value_max = cla.getOptionValueAsDouble( surfacing.MAX_E_VALUE_OPTION );
643 catch ( final Exception e ) {
644 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for E-value maximum" );
647 if ( cla.isOptionSet( surfacing.MAX_ALLOWED_OVERLAP_OPTION ) ) {
649 max_allowed_overlap = cla.getOptionValueAsInt( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
651 catch ( final Exception e ) {
652 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for maximal allowed domain overlap" );
655 boolean no_engulfing_overlaps = false;
656 if ( cla.isOptionSet( surfacing.NO_ENGULFING_OVERLAP_OPTION ) ) {
657 no_engulfing_overlaps = true;
659 boolean ignore_virus_like_ids = false;
660 if ( cla.isOptionSet( surfacing.IGNORE_VIRAL_IDS ) ) {
661 ignore_virus_like_ids = true;
663 if ( cla.isOptionSet( surfacing.NOT_IGNORE_DUFS_OPTION ) ) {
666 if ( cla.isOptionSet( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION ) ) {
667 ignore_combination_with_same = true;
669 boolean ignore_domains_without_combs_in_all_spec = IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT;
670 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION ) ) {
671 ignore_domains_without_combs_in_all_spec = true;
673 boolean ignore_species_specific_domains = IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT;
674 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION ) ) {
675 ignore_species_specific_domains = true;
677 File output_file = null;
678 if ( cla.isOptionSet( surfacing.OUTPUT_FILE_OPTION ) ) {
679 if ( !cla.isOptionValueSet( surfacing.OUTPUT_FILE_OPTION ) ) {
680 ForesterUtil.fatalError( surfacing.PRG_NAME,
681 "no value for domain combinations similarities output file: -"
682 + surfacing.OUTPUT_FILE_OPTION + "=<file>" );
684 output_file = new File( cla.getOptionValue( surfacing.OUTPUT_FILE_OPTION ) );
685 SurfacingUtil.checkForOutputFileWriteability( output_file );
687 File cutoff_scores_file = null;
688 Map<String, Double> individual_score_cutoffs = null;
689 if ( cla.isOptionSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
690 if ( !cla.isOptionValueSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
691 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for individual domain score cutoffs file: -"
692 + surfacing.CUTOFF_SCORE_FILE_OPTION + "=<file>" );
694 cutoff_scores_file = new File( cla.getOptionValue( surfacing.CUTOFF_SCORE_FILE_OPTION ) );
695 final String error = ForesterUtil.isReadableFile( cutoff_scores_file );
696 if ( !ForesterUtil.isEmpty( error ) ) {
697 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read individual domain score cutoffs file: "
701 final BasicTable<String> scores_table = BasicTableParser.parse( cutoff_scores_file, " " );
702 individual_score_cutoffs = scores_table.getColumnsAsMapDouble( 0, 1 );
704 catch ( final IOException e ) {
705 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from individual score cutoffs file: " + e );
708 BinaryDomainCombination.DomainCombinationType dc_type = BinaryDomainCombination.DomainCombinationType.BASIC;
709 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS ) ) {
710 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED;
712 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY ) ) {
713 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT;
716 if ( cla.isOptionSet( surfacing.OUTPUT_DIR_OPTION ) ) {
717 if ( !cla.isOptionValueSet( surfacing.OUTPUT_DIR_OPTION ) ) {
718 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for output directory: -"
719 + surfacing.OUTPUT_DIR_OPTION + "=<dir>" );
721 out_dir = new File( cla.getOptionValue( surfacing.OUTPUT_DIR_OPTION ) );
722 if ( out_dir.exists() && ( out_dir.listFiles().length > 0 ) ) {
723 ForesterUtil.fatalError( surfacing.PRG_NAME, "\"" + out_dir + "\" aready exists and is not empty" );
725 if ( !out_dir.exists() ) {
726 final boolean success = out_dir.mkdir();
727 if ( !success || !out_dir.exists() ) {
728 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to create \"" + out_dir + "\"" );
731 if ( !out_dir.canWrite() ) {
732 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot write to \"" + out_dir + "\"" );
735 File positive_filter_file = null;
736 File negative_filter_file = null;
737 File negative_domains_filter_file = null;
738 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) && cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
739 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use both negative and positive protein filter" );
741 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION )
742 && ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) || cla
743 .isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) ) {
745 .fatalError( surfacing.PRG_NAME,
746 "attempt to use both negative or positive protein filter together wirh a negative domains filter" );
748 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
749 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
750 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative filter: -"
751 + surfacing.FILTER_NEGATIVE_OPTION + "=<file>" );
753 negative_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_OPTION ) );
754 final String msg = ForesterUtil.isReadableFile( negative_filter_file );
755 if ( !ForesterUtil.isEmpty( msg ) ) {
756 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_filter_file + "\": "
760 else if ( cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
761 if ( !cla.isOptionValueSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
762 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for positive filter: -"
763 + surfacing.FILTER_POSITIVE_OPTION + "=<file>" );
765 positive_filter_file = new File( cla.getOptionValue( surfacing.FILTER_POSITIVE_OPTION ) );
766 final String msg = ForesterUtil.isReadableFile( positive_filter_file );
767 if ( !ForesterUtil.isEmpty( msg ) ) {
768 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + positive_filter_file + "\": "
772 else if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
773 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
774 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative domains filter: -"
775 + surfacing.FILTER_NEGATIVE_DOMAINS_OPTION + "=<file>" );
777 negative_domains_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) );
778 final String msg = ForesterUtil.isReadableFile( negative_domains_filter_file );
779 if ( !ForesterUtil.isEmpty( msg ) ) {
780 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_domains_filter_file
784 final List<String> plus_minus_analysis_high_copy_base_species = new ArrayList<String>();
785 final List<String> plus_minus_analysis_high_copy_target_species = new ArrayList<String>();
786 final List<String> plus_minus_analysis_high_low_copy_species = new ArrayList<String>();
787 final List<Object> plus_minus_analysis_numbers = new ArrayList<Object>();
788 processPlusMinusAnalysisOption( cla,
789 plus_minus_analysis_high_copy_base_species,
790 plus_minus_analysis_high_copy_target_species,
791 plus_minus_analysis_high_low_copy_species,
792 plus_minus_analysis_numbers );
793 File input_files_file = null;
794 String[] input_file_names_from_file = null;
795 if ( cla.isOptionSet( surfacing.INPUT_FILES_FROM_FILE_OPTION ) ) {
796 if ( !cla.isOptionValueSet( surfacing.INPUT_FILES_FROM_FILE_OPTION ) ) {
797 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input files file: -"
798 + surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>" );
800 input_files_file = new File( cla.getOptionValue( surfacing.INPUT_FILES_FROM_FILE_OPTION ) );
801 final String msg = ForesterUtil.isReadableFile( input_files_file );
802 if ( !ForesterUtil.isEmpty( msg ) ) {
803 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + input_files_file + "\": " + msg );
806 input_file_names_from_file = ForesterUtil.file2array( input_files_file );
808 catch ( final IOException e ) {
809 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read from \"" + input_files_file + "\": " + e );
812 if ( ( cla.getNumberOfNames() < 1 )
813 && ( ( input_file_names_from_file == null ) || ( input_file_names_from_file.length < 1 ) ) ) {
814 ForesterUtil.fatalError( surfacing.PRG_NAME,
815 "No hmmpfam output file indicated is input: use comand line directly or "
816 + surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>" );
818 DomainSimilarity.DomainSimilarityScoring scoring = SCORING_DEFAULT;
819 if ( cla.isOptionSet( surfacing.SCORING_OPTION ) ) {
820 if ( !cla.isOptionValueSet( surfacing.SCORING_OPTION ) ) {
821 ForesterUtil.fatalError( surfacing.PRG_NAME,
822 "no value for scoring method for domain combinations similarity calculation: -"
823 + surfacing.SCORING_OPTION + "=<"
824 + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
825 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|"
826 + surfacing.SCORING_COMBINATION_BASED + ">\"" );
828 final String scoring_str = cla.getOptionValue( surfacing.SCORING_OPTION );
829 if ( scoring_str.equals( surfacing.SCORING_DOMAIN_COUNT_BASED ) ) {
830 scoring = DomainSimilarity.DomainSimilarityScoring.DOMAINS;
832 else if ( scoring_str.equals( surfacing.SCORING_COMBINATION_BASED ) ) {
833 scoring = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
835 else if ( scoring_str.equals( surfacing.SCORING_PROTEIN_COUNT_BASED ) ) {
836 scoring = DomainSimilarity.DomainSimilarityScoring.PROTEINS;
839 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + scoring_str
840 + "\" for scoring method for domain combinations similarity calculation: \"-"
841 + surfacing.SCORING_OPTION + "=<" + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
842 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|" + surfacing.SCORING_COMBINATION_BASED + ">\"" );
845 boolean sort_by_species_count_first = false;
846 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION ) ) {
847 sort_by_species_count_first = true;
849 boolean species_matrix = false;
850 if ( cla.isOptionSet( surfacing.SPECIES_MATRIX_OPTION ) ) {
851 species_matrix = true;
853 boolean output_protein_lists_for_all_domains = false;
854 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS ) ) {
855 output_protein_lists_for_all_domains = true;
857 Detailedness detailedness = DETAILEDNESS_DEFAULT;
858 if ( cla.isOptionSet( surfacing.DETAILEDNESS_OPTION ) ) {
859 if ( !cla.isOptionValueSet( surfacing.DETAILEDNESS_OPTION ) ) {
860 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for -" + surfacing.DETAILEDNESS_OPTION + "=<"
861 + surfacing.DETAILEDNESS_BASIC + "|" + surfacing.DETAILEDNESS_LIST_IDS + "|"
862 + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
864 final String detness = cla.getOptionValue( surfacing.DETAILEDNESS_OPTION ).toLowerCase();
865 if ( detness.equals( surfacing.DETAILEDNESS_BASIC ) ) {
866 detailedness = DomainSimilarityCalculator.Detailedness.BASIC;
868 else if ( detness.equals( surfacing.DETAILEDNESS_LIST_IDS ) ) {
869 detailedness = DomainSimilarityCalculator.Detailedness.LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES;
871 else if ( detness.equals( surfacing.DETAILEDNESS_PUNCTILIOUS ) ) {
872 detailedness = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
875 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + detness + "\" for detailedness: \"-"
876 + surfacing.DETAILEDNESS_OPTION + "=<" + surfacing.DETAILEDNESS_BASIC + "|"
877 + surfacing.DETAILEDNESS_LIST_IDS + "|" + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
880 String automated_pairwise_comparison_suffix = null;
881 boolean perform_pwc = false;
882 boolean write_pwc_files = false;
883 if ( cla.isOptionSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
885 if ( !cla.isOptionValueSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
886 write_pwc_files = false;
889 write_pwc_files = true;
890 automated_pairwise_comparison_suffix = "_"
891 + cla.getOptionValue( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
894 String query_domain_ids = null;
895 if ( cla.isOptionSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
896 if ( !cla.isOptionValueSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
898 .fatalError( surfacing.PRG_NAME,
899 "no domain ids given for sequences with given domains to be extracted : -"
900 + surfacing.SEQ_EXTRACT_OPTION
901 + "=<ordered domain sequences, domain ids separated by '~', sequences separated by '#'>" );
903 query_domain_ids = cla.getOptionValue( surfacing.SEQ_EXTRACT_OPTION );
905 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field = DOMAIN_SORT_FILD_DEFAULT;
906 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field_for_automated_pwc = DOMAIN_SORT_FILD_DEFAULT;
907 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
908 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
909 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for domain combinations similarities sorting: -"
910 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
911 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
912 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
913 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
914 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|"
915 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
918 final String sort_str = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ).toLowerCase();
919 if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ALPHA ) ) {
920 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
921 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
923 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MAX ) ) {
924 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX;
925 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
927 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MIN ) ) {
928 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MIN;
929 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
931 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MEAN ) ) {
932 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MEAN;
933 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MEAN;
935 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT ) ) {
936 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SPECIES_COUNT;
937 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
939 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SD ) ) {
940 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SD;
941 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
943 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_DIFF ) ) {
944 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
945 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
947 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF ) ) {
948 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
949 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
951 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF ) ) {
952 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
953 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
956 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort_str
957 + "\" for domain combinations similarities sorting: \"-"
958 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
959 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
960 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
961 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
962 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|" + "|"
963 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
967 PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option = DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT;
968 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
969 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
970 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for print option: -"
971 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
972 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
973 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
975 final String sort = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ).toLowerCase();
976 if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML ) ) {
977 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.HTML;
979 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML ) ) {
980 // domain_similarity_print_option =
981 // DomainSimilarity.PRINT_OPTION.SIMPLE_HTML;
982 ForesterUtil.fatalError( surfacing.PRG_NAME, "simple HTML output not implemented yet :(" );
984 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED ) ) {
985 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.SIMPLE_TAB_DELIMITED;
988 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort + "\" for print option: -"
989 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
990 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
991 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
994 GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order = DOMAINS_SORT_ORDER_DEFAULT;
995 if ( cla.isOptionSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
996 if ( !cla.isOptionValueSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
997 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for sorting of domain counts: -"
998 + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<" + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|"
999 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1000 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1001 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1003 final String sort = cla.getOptionValue( surfacing.DOMAIN_COUNT_SORT_OPTION ).toLowerCase();
1004 if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_ALPHA ) ) {
1005 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
1007 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT ) ) {
1008 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_COUNT;
1010 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT ) ) {
1011 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_PROTEINS_COUNT;
1013 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT ) ) {
1014 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.COMBINATIONS_COUNT;
1017 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort
1018 + "\" for sorting of domain counts: \"-" + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<"
1019 + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|" + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1020 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1021 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1024 String[][] input_file_properties = null;
1025 if ( input_file_names_from_file != null ) {
1026 input_file_properties = surfacing.processInputFileNames( input_file_names_from_file );
1029 input_file_properties = surfacing.processInputFileNames( cla.getNames() );
1031 final int number_of_genomes = input_file_properties.length;
1032 if ( number_of_genomes < 2 ) {
1033 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot analyze less than two files" );
1035 if ( ( number_of_genomes < 3 ) && perform_pwc ) {
1036 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use : -"
1037 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1038 + "=<suffix> to turn on pairwise analyses with less than three input files" );
1040 checkWriteabilityForPairwiseComparisons( domain_similarity_print_option,
1041 input_file_properties,
1042 automated_pairwise_comparison_suffix,
1044 for( int i = 0; i < number_of_genomes; i++ ) {
1045 File dcc_outfile = new File( input_file_properties[ i ][ 0 ]
1046 + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
1047 if ( out_dir != null ) {
1048 dcc_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + dcc_outfile );
1050 SurfacingUtil.checkForOutputFileWriteability( dcc_outfile );
1052 File pfam_to_go_file = null;
1053 Map<DomainId, List<GoId>> domain_id_to_go_ids_map = null;
1054 int domain_id_to_go_ids_count = 0;
1055 if ( cla.isOptionSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1056 if ( !cla.isOptionValueSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1057 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for Pfam to GO mapping file: -"
1058 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>" );
1060 pfam_to_go_file = new File( cla.getOptionValue( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) );
1061 final String error = ForesterUtil.isReadableFile( pfam_to_go_file );
1062 if ( !ForesterUtil.isEmpty( error ) ) {
1063 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read Pfam to GO mapping file: " + error );
1066 final PfamToGoParser parser = new PfamToGoParser( pfam_to_go_file );
1067 final List<PfamToGoMapping> pfam_to_go_mappings = parser.parse();
1068 domain_id_to_go_ids_map = SurfacingUtil.createDomainIdToGoIdMap( pfam_to_go_mappings );
1069 if ( parser.getMappingCount() < domain_id_to_go_ids_map.size() ) {
1070 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME,
1071 "parser.getMappingCount() < domain_id_to_go_ids_map.size()" );
1073 domain_id_to_go_ids_count = parser.getMappingCount();
1075 catch ( final IOException e ) {
1076 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from Pfam to GO mapping file: " + e );
1079 File go_obo_file = null;
1080 List<GoTerm> go_terms = null;
1081 if ( cla.isOptionSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1082 if ( !cla.isOptionValueSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1083 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO OBO file: -"
1084 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>" );
1086 if ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) {
1087 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO OBO file (-"
1088 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>) without Pfam to GO mapping file ("
1089 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1091 go_obo_file = new File( cla.getOptionValue( surfacing.GO_OBO_FILE_USE_OPTION ) );
1092 final String error = ForesterUtil.isReadableFile( go_obo_file );
1093 if ( !ForesterUtil.isEmpty( error ) ) {
1094 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read GO OBO file: " + error );
1097 final OBOparser parser = new OBOparser( go_obo_file, OBOparser.ReturnType.BASIC_GO_TERM );
1098 go_terms = parser.parse();
1099 if ( parser.getGoTermCount() != go_terms.size() ) {
1101 .unexpectedFatalError( surfacing.PRG_NAME, "parser.getGoTermCount() != go_terms.size()" );
1104 catch ( final IOException e ) {
1105 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from GO OBO file: " + e );
1108 Map<GoId, GoTerm> go_id_to_term_map = null;
1109 if ( ( ( domain_id_to_go_ids_map != null ) && ( domain_id_to_go_ids_map.size() > 0 ) )
1110 && ( ( go_terms != null ) && ( go_terms.size() > 0 ) ) ) {
1111 go_id_to_term_map = GoUtils.createGoIdToGoTermMap( go_terms );
1113 GoNameSpace go_namespace_limit = null;
1114 if ( cla.isOptionSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1115 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1116 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO namespace limit (-"
1117 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<namespace>) without Pfam to GO mapping file ("
1118 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>) and GO OBO file (-"
1119 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1121 if ( !cla.isOptionValueSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1122 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO namespace limit: \"-"
1123 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1124 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1125 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1126 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1128 final String go_namespace_limit_str = cla.getOptionValue( surfacing.GO_NAMESPACE_LIMIT_OPTION )
1130 if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION ) ) {
1131 go_namespace_limit = GoNameSpace.createMolecularFunction();
1133 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS ) ) {
1134 go_namespace_limit = GoNameSpace.createBiologicalProcess();
1136 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT ) ) {
1137 go_namespace_limit = GoNameSpace.createCellularComponent();
1140 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + go_namespace_limit_str
1141 + "\" for GO namespace limit: \"-" + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1142 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1143 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1144 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1147 if ( ( domain_similarity_sort_field == DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE )
1148 && ( number_of_genomes > 2 ) ) {
1149 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
1151 boolean jacknifed_distances = false;
1152 int jacknife_resamplings = JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT;
1153 double jacknife_ratio = JACKNIFE_RATIO_DEFAULT;
1154 long random_seed = JACKNIFE_RANDOM_SEED_DEFAULT;
1155 if ( cla.isOptionSet( surfacing.JACKNIFE_OPTION ) ) {
1156 if ( ( number_of_genomes < 3 ) || !perform_pwc ) {
1157 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use jacknife resampling analysis (-"
1158 + surfacing.JACKNIFE_OPTION + "[=<number of resamplings>]) without pairwise analyses ("
1159 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1160 + "=<suffix for pairwise comparison output files>)" );
1162 jacknifed_distances = true;
1163 if ( cla.isOptionHasAValue( surfacing.JACKNIFE_OPTION ) ) {
1165 jacknife_resamplings = cla.getOptionValueAsInt( surfacing.JACKNIFE_OPTION );
1167 catch ( final IOException e ) {
1168 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for number of resamplings" );
1170 if ( jacknife_resamplings < 2 ) {
1171 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use less than 2 resamplings" );
1174 if ( cla.isOptionSet( surfacing.JACKNIFE_RATIO_OPTION )
1175 && cla.isOptionHasAValue( surfacing.JACKNIFE_RATIO_OPTION ) ) {
1177 jacknife_ratio = cla.getOptionValueAsDouble( surfacing.JACKNIFE_RATIO_OPTION );
1179 catch ( final IOException e ) {
1180 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for jacknife ratio" );
1182 if ( ( jacknife_ratio <= 0.0 ) || ( jacknife_ratio >= 1.0 ) ) {
1183 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use illegal value for jacknife ratio: "
1187 if ( cla.isOptionSet( surfacing.JACKNIFE_RANDOM_SEED_OPTION )
1188 && cla.isOptionHasAValue( surfacing.JACKNIFE_RANDOM_SEED_OPTION ) ) {
1190 random_seed = cla.getOptionValueAsLong( surfacing.JACKNIFE_RANDOM_SEED_OPTION );
1192 catch ( final IOException e ) {
1193 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for random generator seed" );
1197 // boolean infer_species_trees = false;
1198 // if ( cla.isOptionSet( surfacing.INFER_SPECIES_TREES_OPTION ) ) {
1199 // if ( ( output_file == null ) || ( number_of_genomes < 3 )
1200 // || ForesterUtil.isEmpty( automated_pairwise_comparison_suffix ) ) {
1201 // ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer species trees (-"
1202 // + surfacing.INFER_SPECIES_TREES_OPTION + " without pairwise analyses ("
1203 // + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1204 // + "=<suffix for pairwise comparison output files>)" );
1206 // infer_species_trees = true;
1208 File[] intree_files = null;
1209 Phylogeny[] intrees = null;
1210 if ( cla.isOptionSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1211 // TODO FIXME if jacknife.... maybe not
1212 if ( number_of_genomes < 3 ) {
1213 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer gains and losses on input species trees (-"
1214 + surfacing.INPUT_SPECIES_TREE_OPTION + " without pairwise analyses ("
1215 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1216 + "=<suffix for pairwise comparison output files>)" );
1218 if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1219 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input tree: -"
1220 + surfacing.INPUT_SPECIES_TREE_OPTION + "=<tree file in phyloXML format>" );
1222 final String intrees_str = cla.getOptionValue( surfacing.INPUT_SPECIES_TREE_OPTION );
1223 if ( intrees_str.indexOf( "#" ) > 0 ) {
1224 final String[] intrees_strs = intrees_str.split( "#" );
1225 intree_files = new File[ intrees_strs.length ];
1227 for( final String s : intrees_strs ) {
1228 intree_files[ i++ ] = new File( s.trim() );
1232 intree_files = new File[ 1 ];
1233 intree_files[ 0 ] = new File( intrees_str );
1235 intrees = getIntrees( intree_files, number_of_genomes, input_file_properties );
1237 long random_number_seed_for_fitch_parsimony = 0l;
1238 boolean radomize_fitch_parsimony = false;
1239 if ( cla.isOptionSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1240 if ( !cla.isOptionValueSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1241 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for random number seed: -"
1242 + surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION + "=<seed>" );
1245 random_number_seed_for_fitch_parsimony = cla
1246 .getOptionValueAsLong( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
1248 catch ( final IOException e ) {
1249 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1251 radomize_fitch_parsimony = true;
1253 SortedSet<DomainId> filter = null;
1254 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1255 || ( negative_domains_filter_file != null ) ) {
1256 filter = new TreeSet<DomainId>();
1257 if ( positive_filter_file != null ) {
1258 processFilter( positive_filter_file, filter );
1260 else if ( negative_filter_file != null ) {
1261 processFilter( negative_filter_file, filter );
1263 else if ( negative_domains_filter_file != null ) {
1264 processFilter( negative_domains_filter_file, filter );
1267 Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps = null;
1268 File[] secondary_features_map_files = null;
1269 final File domain_lengths_analysis_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1270 + DOMAIN_LENGTHS_ANALYSIS_SUFFIX );
1271 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
1272 SurfacingUtil.checkForOutputFileWriteability( domain_lengths_analysis_outfile );
1274 if ( cla.isOptionSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1275 if ( !cla.isOptionValueSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1276 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for secondary features map file: -"
1277 + surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE + "=<file>" );
1279 final String[] secondary_features_map_files_strs = cla
1280 .getOptionValue( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ).split( "#" );
1281 secondary_features_map_files = new File[ secondary_features_map_files_strs.length ];
1282 domain_id_to_secondary_features_maps = new Map[ secondary_features_map_files_strs.length ];
1284 for( final String secondary_features_map_files_str : secondary_features_map_files_strs ) {
1285 secondary_features_map_files[ i ] = new File( secondary_features_map_files_str );
1286 final String error = ForesterUtil.isReadableFile( secondary_features_map_files[ i ] );
1287 if ( !ForesterUtil.isEmpty( error ) ) {
1288 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read secondary features map file: " + error );
1291 domain_id_to_secondary_features_maps[ i ] = SurfacingUtil
1292 .createDomainIdToSecondaryFeaturesMap( secondary_features_map_files[ i ] );
1294 catch ( final IOException e ) {
1295 ForesterUtil.fatalError( surfacing.PRG_NAME,
1296 "cannot read secondary features map file: " + e.getMessage() );
1298 catch ( final Exception e ) {
1299 ForesterUtil.fatalError( surfacing.PRG_NAME, "problem with contents of features map file ["
1300 + secondary_features_map_files[ i ] + "]: " + e.getMessage() );
1305 if ( out_dir == null ) {
1306 ForesterUtil.fatalError( surfacing.PRG_NAME, "no output directory indicated (-"
1307 + surfacing.OUTPUT_DIR_OPTION + "=<dir>)" );
1309 if ( output_file == null ) {
1310 ForesterUtil.fatalError( surfacing.PRG_NAME, "no name for (main) output file indicated (-"
1311 + surfacing.OUTPUT_FILE_OPTION + "=<file>)" );
1313 if ( ( domain_id_to_go_ids_map == null ) || domain_id_to_go_ids_map.isEmpty() ) {
1314 ForesterUtil.fatalError( surfacing.PRG_NAME,
1315 "no (acceptable) Pfam to GO id mapping file provided ('pfam2go file') (-"
1316 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1318 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1319 ForesterUtil.fatalError( surfacing.PRG_NAME,
1320 "no (acceptable) go id to term mapping file provided ('GO OBO file') (-"
1321 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1323 System.out.println( "Output directory : " + out_dir );
1324 if ( input_file_names_from_file != null ) {
1325 System.out.println( "Input files names from : " + input_files_file + " ["
1326 + input_file_names_from_file.length + " input files]" );
1327 html_desc.append( "<tr><td>Input files names from:</td><td>" + input_files_file + " ["
1328 + input_file_names_from_file.length + " input files]</td></tr>" + nl );
1330 if ( positive_filter_file != null ) {
1331 final int filter_size = filter.size();
1332 System.out.println( "Positive protein filter : " + positive_filter_file + " [" + filter_size
1334 html_desc.append( "<tr><td>Positive protein filter:</td><td>" + positive_filter_file + " [" + filter_size
1335 + " domain ids]</td></tr>" + nl );
1337 if ( negative_filter_file != null ) {
1338 final int filter_size = filter.size();
1339 System.out.println( "Negative protein filter : " + negative_filter_file + " [" + filter_size
1341 html_desc.append( "<tr><td>Negative protein filter:</td><td>" + negative_filter_file + " [" + filter_size
1342 + " domain ids]</td></tr>" + nl );
1344 if ( negative_domains_filter_file != null ) {
1345 final int filter_size = filter.size();
1346 System.out.println( "Negative domain filter : " + negative_domains_filter_file + " [" + filter_size
1348 html_desc.append( "<tr><td>Negative domain filter:</td><td>" + negative_domains_filter_file + " ["
1349 + filter_size + " domain ids]</td></tr>" + nl );
1351 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
1353 for( final String s : plus_minus_analysis_high_copy_base_species ) {
1354 plus0 += "+" + s + " ";
1357 for( final String s : plus_minus_analysis_high_copy_target_species ) {
1358 plus1 += "*" + s + " ";
1361 for( final String s : plus_minus_analysis_high_low_copy_species ) {
1362 minus += "-" + s + " ";
1364 System.out.println( "Plus-minus analysis : " + plus1 + "&& " + plus0 + "&& " + minus );
1365 html_desc.append( "<tr><td>Plus-minus analysis:</td><td>" + plus1 + "&& " + plus0 + "&& " + minus
1366 + "</td></tr>" + nl );
1368 if ( cutoff_scores_file != null ) {
1369 System.out.println( "Cutoff scores file : " + cutoff_scores_file );
1370 html_desc.append( "<tr><td>Cutoff scores file:</td><td>" + cutoff_scores_file + "</td></tr>" + nl );
1372 if ( e_value_max >= 0.0 ) {
1373 System.out.println( "E-value maximum (inclusive) : " + e_value_max );
1374 html_desc.append( "<tr><td>E-value maximum (inclusive):</td><td>" + e_value_max + "</td></tr>" + nl );
1376 System.out.println( "Ignore DUFs : " + ignore_dufs );
1377 if ( ignore_virus_like_ids ) {
1378 System.out.println( "Ignore virus like ids : " + ignore_virus_like_ids );
1379 html_desc.append( "<tr><td>Ignore virus, phage, transposition related ids:</td><td>"
1380 + ignore_virus_like_ids + "</td></tr>" + nl );
1382 html_desc.append( "<tr><td>Ignore DUFs:</td><td>" + ignore_dufs + "</td></tr>" + nl );
1383 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1384 System.out.println( "Max allowed domain overlap : " + max_allowed_overlap );
1385 html_desc.append( "<tr><td>Max allowed domain overlap:</td><td>" + max_allowed_overlap + "</td></tr>" + nl );
1387 if ( no_engulfing_overlaps ) {
1388 System.out.println( "Ignore engulfed domains : " + no_engulfing_overlaps );
1389 html_desc.append( "<tr><td>Ignore (lower confidence) engulfed domains:</td><td>" + no_engulfing_overlaps
1390 + "</td></tr>" + nl );
1392 System.out.println( "Ignore singlet domains : " + ignore_domains_without_combs_in_all_spec );
1394 .append( "<tr><td>Ignore singlet domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1395 + ignore_domains_without_combs_in_all_spec + "</td></tr>" + nl );
1396 System.out.println( "Ignore species specific doms: " + ignore_species_specific_domains );
1398 .append( "<tr><td>Ignore species specific domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1399 + ignore_species_specific_domains + "</td></tr>" + nl );
1400 System.out.println( "Ignore combination with self: " + ignore_combination_with_same );
1401 html_desc.append( "<tr><td>Ignore combination with self for domain combination similarity analyses:</td><td>"
1402 + ignore_combination_with_same + "</td></tr>" + nl );
1404 System.out.println( "Consider directedness : "
1405 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) );
1406 html_desc.append( "<tr><td>Consider directedness of binary domain combinations:</td><td>"
1407 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) + "</td></tr>" + nl );
1408 if ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) {
1409 System.out.println( "Consider adjacency : "
1410 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) );
1411 html_desc.append( "<tr><td>Consider djacency of binary domain combinations:</td><td>"
1412 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) + "</td></tr>"
1415 System.out.print( "Domain counts sort order : " );
1416 switch ( dc_sort_order ) {
1417 case ALPHABETICAL_KEY_ID:
1418 System.out.println( "alphabetical" );
1420 case KEY_DOMAIN_COUNT:
1421 System.out.println( "domain count" );
1423 case KEY_DOMAIN_PROTEINS_COUNT:
1424 System.out.println( "domain proteins count" );
1426 case COMBINATIONS_COUNT:
1427 System.out.println( "domain combinations count" );
1430 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for dc sort order" );
1432 if ( domain_id_to_go_ids_map != null ) {
1433 System.out.println( "Pfam to GO mappings from : " + pfam_to_go_file + " [" + domain_id_to_go_ids_count
1435 html_desc.append( "<tr><td>Pfam to GO mappings from:</td><td>" + pfam_to_go_file + " ["
1436 + domain_id_to_go_ids_count + " mappings]" + "</td></tr>" + nl );
1438 if ( go_terms != null ) {
1439 System.out.println( "GO terms from : " + go_obo_file + " [" + go_terms.size() + " terms]" );
1440 html_desc.append( "<tr><td>GO terms from:</td><td>" + go_obo_file + " [" + go_terms.size() + " terms]"
1441 + "</td></tr>" + nl );
1443 if ( go_namespace_limit != null ) {
1444 System.out.println( "Limit GO terms to : " + go_namespace_limit.toString() );
1445 html_desc.append( "<tr><td>Limit GO terms to</td><td>" + go_namespace_limit + "</td></tr>" + nl );
1447 if ( perform_pwc ) {
1448 System.out.println( "Suffix for PWC files : " + automated_pairwise_comparison_suffix );
1449 html_desc.append( "<tr><td>Suffix for PWC files</td><td>" + automated_pairwise_comparison_suffix
1450 + "</td></tr>" + nl );
1452 if ( out_dir != null ) {
1453 System.out.println( "Output directory : " + out_dir );
1455 if ( query_domain_ids != null ) {
1456 System.out.println( "Query domains (ordered) : " + query_domain_ids );
1457 html_desc.append( "<tr><td></td><td>" + query_domain_ids + "</td></tr>" + nl );
1459 System.out.println( "Write similarities to : " + output_file );
1460 System.out.print( " Scoring method : " );
1461 html_desc.append( "<tr><td>Scoring method:</td><td>" );
1462 switch ( scoring ) {
1464 System.out.println( "domain combinations based" );
1465 html_desc.append( "domain combinations based" + "</td></tr>" + nl );
1468 System.out.println( "domain counts based" );
1469 html_desc.append( "domain counts based" + "</td></tr>" + nl );
1472 System.out.println( "domain proteins counts based" );
1473 html_desc.append( "domain proteins counts based" + "</td></tr>" + nl );
1476 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
1478 System.out.print( " Sort by : " );
1479 html_desc.append( "<tr><td>Sort by:</td><td>" );
1480 switch ( domain_similarity_sort_field ) {
1482 System.out.print( "score minimum" );
1483 html_desc.append( "score minimum" );
1486 System.out.print( "score maximum" );
1487 html_desc.append( "score maximum" );
1490 System.out.print( "score mean" );
1491 html_desc.append( "score mean" );
1494 System.out.print( "score standard deviation" );
1495 html_desc.append( "score standard deviation" );
1498 System.out.print( "species number" );
1499 html_desc.append( "species number" );
1502 System.out.print( "alphabetical domain identifier" );
1503 html_desc.append( "alphabetical domain identifier" );
1505 case MAX_DIFFERENCE:
1506 System.out.print( "(maximal) difference" );
1507 html_desc.append( "(maximal) difference" );
1509 case ABS_MAX_COUNTS_DIFFERENCE:
1510 System.out.print( "absolute (maximal) counts difference" );
1511 html_desc.append( "absolute (maximal) counts difference" );
1513 case MAX_COUNTS_DIFFERENCE:
1514 System.out.print( "(maximal) counts difference" );
1515 html_desc.append( "(maximal) counts difference" );
1518 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1520 if ( sort_by_species_count_first ) {
1521 System.out.println( " (sort by species count first)" );
1522 html_desc.append( " (sort by species count first)" );
1525 System.out.println();
1527 html_desc.append( "</td></tr>" + nl );
1528 System.out.print( " Detailedness : " );
1529 switch ( detailedness ) {
1531 System.out.println( "basic" );
1533 case LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES:
1534 System.out.println( "list combining domains for each species" );
1537 System.out.println( "punctilious" );
1540 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for detailedness" );
1542 System.out.print( " Print option : " );
1543 switch ( domain_similarity_print_option ) {
1545 System.out.println( "HTML" );
1547 case SIMPLE_TAB_DELIMITED:
1548 System.out.println( "simple tab delimited" );
1551 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for print option" );
1553 System.out.print( " Species matrix : " + species_matrix );
1554 System.out.println();
1555 final File dc_data_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + DATA_FILE_SUFFIX );
1556 System.out.println( "Domain comb data output : " + dc_data_file );
1557 html_desc.append( "<tr><td>Domain combination data output:</td><td> " + dc_data_file + " </td></tr>" );
1558 System.out.println();
1559 if ( perform_pwc ) {
1560 System.out.println( "Pairwise comparisons: " );
1561 html_desc.append( "<tr><td>Pairwise comparisons:</td><td></td></tr>" );
1562 System.out.print( " Sort by : " );
1563 html_desc.append( "<tr><td>Sort by:</td><td>" );
1564 switch ( domain_similarity_sort_field_for_automated_pwc ) {
1566 System.out.print( "score mean" );
1567 html_desc.append( "score mean" );
1570 System.out.print( "alphabetical domain identifier" );
1571 html_desc.append( "alphabetical domain identifier" );
1573 case MAX_DIFFERENCE:
1574 System.out.print( "difference" );
1575 html_desc.append( "difference" );
1577 case ABS_MAX_COUNTS_DIFFERENCE:
1578 System.out.print( "absolute counts difference" );
1579 html_desc.append( "absolute counts difference" );
1581 case MAX_COUNTS_DIFFERENCE:
1582 System.out.print( "counts difference" );
1583 html_desc.append( "counts difference" );
1587 .unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1589 System.out.println();
1590 html_desc.append( "</td></tr>" + nl );
1591 if ( jacknifed_distances ) {
1592 html_desc.append( "<tr><td>Jacknife:</td><td>" + jacknife_resamplings + " resamplings</td></tr>" + nl );
1593 html_desc.append( "<tr><td>Jacknife ratio:</td><td>" + ForesterUtil.round( jacknife_ratio, 2 )
1594 + "</td></tr>" + nl );
1595 html_desc.append( "<tr><td>Jacknife random number seed:</td><td>" + random_seed + "</td></tr>" + nl );
1596 System.out.println( " Jacknife : " + jacknife_resamplings + " resamplings" );
1597 System.out.println( " Ratio : " + ForesterUtil.round( jacknife_ratio, 2 ) );
1598 System.out.println( " Random number seed : " + random_seed );
1600 // if ( infer_species_trees ) {
1601 // html_desc.append( "<tr><td>Infer species trees:</td><td>true</td></tr>" + nl );
1602 // System.out.println( " Infer species trees : true" );
1604 if ( ( intrees != null ) && ( intrees.length > 0 ) ) {
1605 for( final File intree_file : intree_files ) {
1606 html_desc.append( "<tr><td>Intree for gain/loss parsimony analysis:</td><td>" + intree_file
1607 + "</td></tr>" + nl );
1608 System.out.println( " Intree for gain/loss pars.: " + intree_file );
1611 if ( radomize_fitch_parsimony ) {
1612 html_desc.append( "<tr><td> Random number seed for Fitch parsimony analysis:</td><td>"
1613 + random_number_seed_for_fitch_parsimony + "</td></tr>" + nl );
1614 System.out.println( " Random number seed : " + random_number_seed_for_fitch_parsimony );
1616 if ( ( domain_id_to_secondary_features_maps != null ) && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
1617 for( int i = 0; i < secondary_features_map_files.length; i++ ) {
1618 html_desc.append( "<tr><td>Secondary features map file:</td><td>"
1619 + secondary_features_map_files[ i ] + "</td></tr>" + nl );
1620 System.out.println( "Secondary features map file : " + secondary_features_map_files[ i ]
1621 + " [mappings for " + domain_id_to_secondary_features_maps[ i ].size() + " domain ids]" );
1623 System.out.println();
1624 System.out.println( "Domain ids to secondary features map:" );
1625 for( final DomainId domain_id : domain_id_to_secondary_features_maps[ i ].keySet() ) {
1626 System.out.print( domain_id.getId() );
1627 System.out.print( " => " );
1628 for( final String sec : domain_id_to_secondary_features_maps[ i ].get( domain_id ) ) {
1629 System.out.print( sec );
1630 System.out.print( " " );
1632 System.out.println();
1637 } // if ( perform_pwc ) {
1638 System.out.println();
1639 html_desc.append( "<tr><td>Command line:</td><td>" + cla.getCommandLineArgsAsString() + "</td></tr>" + nl );
1640 System.out.println( "Command line : " + cla.getCommandLineArgsAsString() );
1641 BufferedWriter[] query_domains_writer_ary = null;
1642 List<DomainId>[] query_domain_ids_array = null;
1643 if ( query_domain_ids != null ) {
1644 final String[] query_domain_ids_str_array = query_domain_ids.split( "#" );
1645 query_domain_ids_array = new ArrayList[ query_domain_ids_str_array.length ];
1646 query_domains_writer_ary = new BufferedWriter[ query_domain_ids_str_array.length ];
1647 for( int i = 0; i < query_domain_ids_str_array.length; i++ ) {
1648 String query_domain_ids_str = query_domain_ids_str_array[ i ];
1649 final String[] query_domain_ids_str_ary = query_domain_ids_str.split( "~" );
1650 final List<DomainId> query = new ArrayList<DomainId>();
1651 for( final String element : query_domain_ids_str_ary ) {
1652 query.add( new DomainId( element ) );
1654 query_domain_ids_array[ i ] = query;
1655 query_domain_ids_str = query_domain_ids_str.replace( '~', '_' );
1656 String protein_names_writer_str = query_domain_ids_str + surfacing.SEQ_EXTRACT_SUFFIX;
1657 if ( out_dir != null ) {
1658 protein_names_writer_str = out_dir + ForesterUtil.FILE_SEPARATOR + protein_names_writer_str;
1661 query_domains_writer_ary[ i ] = new BufferedWriter( new FileWriter( protein_names_writer_str ) );
1663 catch ( final IOException e ) {
1664 ForesterUtil.fatalError( surfacing.PRG_NAME, "Could not open [" + protein_names_writer_str + "]: "
1665 + e.getLocalizedMessage() );
1669 SortedMap<Species, List<Protein>> protein_lists_per_species = null; //This will only be created if neede.
1670 boolean need_protein_lists_per_species = false;
1671 if ( ( plus_minus_analysis_high_copy_base_species.size() > 0 ) || output_protein_lists_for_all_domains ) {
1672 need_protein_lists_per_species = true;
1674 if ( need_protein_lists_per_species ) {
1675 protein_lists_per_species = new TreeMap<Species, List<Protein>>();
1677 final List<GenomeWideCombinableDomains> gwcd_list = new ArrayList<GenomeWideCombinableDomains>( number_of_genomes );
1678 final SortedSet<DomainId> all_domains_encountered = new TreeSet<DomainId>();
1679 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered = new TreeSet<BinaryDomainCombination>();
1680 List<BinaryDomainCombination> all_bin_domain_combinations_gained_fitch = null;
1681 List<BinaryDomainCombination> all_bin_domain_combinations_lost_fitch = null;
1682 if ( ( intrees != null ) && ( intrees.length == 1 ) ) {
1683 all_bin_domain_combinations_gained_fitch = new ArrayList<BinaryDomainCombination>();
1684 all_bin_domain_combinations_lost_fitch = new ArrayList<BinaryDomainCombination>();
1686 final DomainLengthsTable domain_lengths_table = new DomainLengthsTable();
1687 final File per_genome_domain_promiscuity_statistics_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR
1688 + output_file + D_PROMISCUITY_FILE_SUFFIX );
1689 BufferedWriter per_genome_domain_promiscuity_statistics_writer = null;
1691 per_genome_domain_promiscuity_statistics_writer = new BufferedWriter( new FileWriter( per_genome_domain_promiscuity_statistics_file ) );
1692 per_genome_domain_promiscuity_statistics_writer.write( "Species:\t" );
1693 per_genome_domain_promiscuity_statistics_writer.write( "Mean:\t" );
1694 per_genome_domain_promiscuity_statistics_writer.write( "SD:\t" );
1695 per_genome_domain_promiscuity_statistics_writer.write( "Median:\t" );
1696 per_genome_domain_promiscuity_statistics_writer.write( "Min:\t" );
1697 per_genome_domain_promiscuity_statistics_writer.write( "Max:\t" );
1698 per_genome_domain_promiscuity_statistics_writer.write( "N:\t" );
1699 per_genome_domain_promiscuity_statistics_writer.write( "Max Promiscuous Domains:"
1700 + ForesterUtil.LINE_SEPARATOR );
1702 catch ( final IOException e2 ) {
1703 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1705 final File log_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + LOG_FILE_SUFFIX );
1706 BufferedWriter log_writer = null;
1708 log_writer = new BufferedWriter( new FileWriter( log_file ) );
1710 catch ( final IOException e2 ) {
1711 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1713 BufferedWriter dc_data_writer = null;
1715 dc_data_writer = new BufferedWriter( new FileWriter( dc_data_file ) );
1716 dc_data_writer.write( DATA_FILE_DESC );
1717 dc_data_writer.write( ForesterUtil.LINE_SEPARATOR );
1719 catch ( final IOException e2 ) {
1720 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1722 for( int i = 0; i < number_of_genomes; ++i ) {
1723 System.out.println();
1724 System.out.println( ( i + 1 ) + "/" + number_of_genomes );
1725 log( ( i + 1 ) + "/" + number_of_genomes, log_writer );
1726 System.out.println( "Processing : " + input_file_properties[ i ][ 0 ] );
1727 log( "Genome : " + input_file_properties[ i ][ 0 ], log_writer );
1728 HmmscanPerDomainTableParser parser = null;
1729 INDIVIDUAL_SCORE_CUTOFF ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF.NONE;
1730 if ( individual_score_cutoffs != null ) {
1731 ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF_DEFAULT;
1733 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1734 || ( negative_domains_filter_file != null ) ) {
1735 HmmscanPerDomainTableParser.FilterType filter_type = HmmscanPerDomainTableParser.FilterType.NONE;
1736 if ( positive_filter_file != null ) {
1737 filter_type = HmmscanPerDomainTableParser.FilterType.POSITIVE_PROTEIN;
1739 else if ( negative_filter_file != null ) {
1740 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_PROTEIN;
1742 else if ( negative_domains_filter_file != null ) {
1743 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_DOMAIN;
1745 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1746 input_file_properties[ i ][ 1 ],
1752 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1753 input_file_properties[ i ][ 1 ],
1756 if ( e_value_max >= 0.0 ) {
1757 parser.setEValueMaximum( e_value_max );
1759 parser.setIgnoreDufs( ignore_dufs );
1760 parser.setIgnoreVirusLikeIds( ignore_virus_like_ids );
1761 parser.setIgnoreEngulfedDomains( no_engulfing_overlaps );
1762 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1763 parser.setMaxAllowedOverlap( max_allowed_overlap );
1765 parser.setReturnType( HmmscanPerDomainTableParser.ReturnType.UNORDERED_PROTEIN_DOMAIN_COLLECTION_PER_PROTEIN );
1766 if ( individual_score_cutoffs != null ) {
1767 parser.setIndividualScoreCutoffs( individual_score_cutoffs );
1769 List<Protein> protein_list = null;
1771 protein_list = parser.parse();
1773 catch ( final IOException e ) {
1774 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1776 catch ( final Exception e ) {
1777 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, e.getMessage(), e );
1780 System.out.println( "Domains ignored due to negative domain filter: " );
1781 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToNegativeDomainFilterCountsMap() );
1782 System.out.println( "Domains ignored due to virus like id: " );
1783 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToVirusLikeIdCountsMap() );
1785 System.out.println( "Number of proteins encountered : " + parser.getProteinsEncountered() );
1786 log( "Number of proteins encountered : " + parser.getProteinsEncountered(), log_writer );
1787 System.out.println( "Number of proteins stored : " + protein_list.size() );
1788 log( "Number of proteins stored : " + protein_list.size(), log_writer );
1789 System.out.println( "Domains encountered : " + parser.getDomainsEncountered() );
1790 log( "Domains encountered : " + parser.getDomainsEncountered(), log_writer );
1791 System.out.println( "Domains stored : " + parser.getDomainsStored() );
1792 log( "Domains stored : " + parser.getDomainsStored(), log_writer );
1793 System.out.println( "Distinct domains stored : "
1794 + parser.getDomainsStoredSet().size() );
1795 log( "Distinct domains stored : " + parser.getDomainsStoredSet().size(), log_writer );
1796 System.out.println( "Domains ignored due to individual score cutoffs: "
1797 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() );
1798 log( "Domains ignored due to individual score cutoffs: "
1799 + parser.getDomainsIgnoredDueToIndividualScoreCutoff(),
1801 System.out.println( "Domains ignored due to E-value : "
1802 + parser.getDomainsIgnoredDueToEval() );
1803 log( "Domains ignored due to E-value : " + parser.getDomainsIgnoredDueToEval(), log_writer );
1804 System.out.println( "Domains ignored due to DUF designation : "
1805 + parser.getDomainsIgnoredDueToDuf() );
1806 log( "Domains ignored due to DUF designation : " + parser.getDomainsIgnoredDueToDuf(), log_writer );
1807 if ( ignore_virus_like_ids ) {
1808 System.out.println( "Domains ignored due virus like ids : "
1809 + parser.getDomainsIgnoredDueToVirusLikeIds() );
1810 log( "Domains ignored due virus like ids : " + parser.getDomainsIgnoredDueToVirusLikeIds(),
1813 System.out.println( "Domains ignored due negative domain filter : "
1814 + parser.getDomainsIgnoredDueToNegativeDomainFilter() );
1815 log( "Domains ignored due negative domain filter : "
1816 + parser.getDomainsIgnoredDueToNegativeDomainFilter(),
1818 System.out.println( "Domains ignored due to overlap : "
1819 + parser.getDomainsIgnoredDueToOverlap() );
1820 log( "Domains ignored due to overlap : " + parser.getDomainsIgnoredDueToOverlap(),
1822 if ( negative_filter_file != null ) {
1823 System.out.println( "Proteins ignored due to negative filter : "
1824 + parser.getProteinsIgnoredDueToFilter() );
1825 log( "Proteins ignored due to negative filter : " + parser.getProteinsIgnoredDueToFilter(),
1828 if ( positive_filter_file != null ) {
1829 System.out.println( "Proteins ignored due to positive filter : "
1830 + parser.getProteinsIgnoredDueToFilter() );
1831 log( "Proteins ignored due to positive filter : " + parser.getProteinsIgnoredDueToFilter(),
1834 System.out.println( "Time for processing : " + parser.getTime() + "ms" );
1835 log( "", log_writer );
1836 html_desc.append( "<tr><td>" + input_file_properties[ i ][ 0 ] + " [species: "
1837 + input_file_properties[ i ][ 1 ] + "]" + ":</td><td>domains analyzed: "
1838 + parser.getDomainsStored() + "; domains ignored: [ind score cutoffs: "
1839 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() + "] [E-value cutoff: "
1840 + parser.getDomainsIgnoredDueToEval() + "] [DUF: " + parser.getDomainsIgnoredDueToDuf()
1841 + "] [virus like ids: " + parser.getDomainsIgnoredDueToVirusLikeIds()
1842 + "] [negative domain filter: " + parser.getDomainsIgnoredDueToNegativeDomainFilter()
1843 + "] [overlap: " + parser.getDomainsIgnoredDueToOverlap() + "]" );
1844 if ( negative_filter_file != null ) {
1845 html_desc.append( "; proteins ignored due to negative filter: "
1846 + parser.getProteinsIgnoredDueToFilter() );
1848 if ( positive_filter_file != null ) {
1849 html_desc.append( "; proteins ignored due to positive filter: "
1850 + parser.getProteinsIgnoredDueToFilter() );
1852 html_desc.append( "</td></tr>" + nl );
1853 // domain_partner_counts_array[ i ] =
1854 // Methods.getDomainPartnerCounts( protein_domain_collections_array[
1856 // false, input_file_properties[ i ][ 1 ] );
1859 for( final Protein protein : protein_list ) {
1860 dc_data_writer.write( SurfacingUtil.proteinToDomainCombinations( protein, count + "", "\t" )
1865 catch ( final IOException e ) {
1866 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1868 gwcd_list.add( BasicGenomeWideCombinableDomains
1869 .createInstance( protein_list,
1870 ignore_combination_with_same,
1871 new BasicSpecies( input_file_properties[ i ][ 1 ] ),
1872 domain_id_to_go_ids_map,
1874 domain_lengths_table.addLengths( protein_list );
1875 if ( gwcd_list.get( i ).getSize() > 0 ) {
1876 SurfacingUtil.writeDomainCombinationsCountsFile( input_file_properties,
1878 per_genome_domain_promiscuity_statistics_writer,
1882 if ( output_binary_domain_combinationsfor_graph_analysis ) {
1883 SurfacingUtil.writeBinaryDomainCombinationsFileForGraphAnalysis( input_file_properties,
1889 SurfacingUtil.addAllDomainIdsToSet( gwcd_list.get( i ), all_domains_encountered );
1890 SurfacingUtil.addAllBinaryDomainCombinationToSet( gwcd_list.get( i ),
1891 all_bin_domain_combinations_encountered );
1893 if ( query_domains_writer_ary != null ) {
1894 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1896 SurfacingUtil.extractProteinNames( protein_list,
1897 query_domain_ids_array[ j ],
1898 query_domains_writer_ary[ j ],
1900 query_domains_writer_ary[ j ].flush();
1902 catch ( final IOException e ) {
1903 e.printStackTrace();
1907 if ( need_protein_lists_per_species ) {
1908 protein_lists_per_species.put( new BasicSpecies( input_file_properties[ i ][ 1 ] ), protein_list );
1913 catch ( final IOException e2 ) {
1914 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1917 } // for( int i = 0; i < number_of_genomes; ++i ) {
1919 per_genome_domain_promiscuity_statistics_writer.flush();
1920 per_genome_domain_promiscuity_statistics_writer.close();
1921 dc_data_writer.flush();
1922 dc_data_writer.close();
1926 catch ( final IOException e2 ) {
1927 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1929 ForesterUtil.programMessage( PRG_NAME, "Wrote domain promiscuities to: "
1930 + per_genome_domain_promiscuity_statistics_file );
1931 if ( query_domains_writer_ary != null ) {
1932 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1934 query_domains_writer_ary[ j ].close();
1936 catch ( final IOException e ) {
1937 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1941 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
1943 SurfacingUtil.executeDomainLengthAnalysis( input_file_properties,
1945 domain_lengths_table,
1946 domain_lengths_analysis_outfile );
1948 catch ( final IOException e1 ) {
1949 ForesterUtil.fatalError( surfacing.PRG_NAME, e1.toString() );
1951 System.out.println();
1952 ForesterUtil.programMessage( PRG_NAME, "Wrote domain length data to: " + domain_lengths_analysis_outfile );
1953 System.out.println();
1955 final long analysis_start_time = new Date().getTime();
1956 PairwiseDomainSimilarityCalculator pw_calc = null;
1957 // double[] values_for_all_scores_histogram = null;
1958 final DomainSimilarityCalculator calc = new BasicDomainSimilarityCalculator( domain_similarity_sort_field,
1959 sort_by_species_count_first,
1960 number_of_genomes == 2 );
1961 switch ( scoring ) {
1963 pw_calc = new CombinationsBasedPairwiseDomainSimilarityCalculator();
1966 pw_calc = new DomainCountsBasedPairwiseSimilarityCalculator();
1969 pw_calc = new ProteinCountsBasedPairwiseDomainSimilarityCalculator();
1972 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
1974 DomainSimilarityCalculator.GoAnnotationOutput go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.NONE;
1975 if ( domain_id_to_go_ids_map != null ) {
1976 go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.ALL;
1978 final SortedSet<DomainSimilarity> similarities = calc
1979 .calculateSimilarities( pw_calc,
1981 ignore_domains_without_combs_in_all_spec,
1982 ignore_species_specific_domains );
1983 SurfacingUtil.decoratePrintableDomainSimilarities( similarities,
1985 go_annotation_output,
1987 go_namespace_limit );
1988 DescriptiveStatistics pw_stats = null;
1990 String my_outfile = output_file.toString();
1991 if ( !my_outfile.endsWith( ".html" ) ) {
1992 my_outfile += ".html";
1994 final Writer writer = new BufferedWriter( new FileWriter( out_dir == null ? my_outfile : out_dir
1995 + ForesterUtil.FILE_SEPARATOR + my_outfile ) );
1996 List<Species> species_order = null;
1997 if ( species_matrix ) {
1998 species_order = new ArrayList<Species>();
1999 for( int i = 0; i < number_of_genomes; i++ ) {
2000 species_order.add( new BasicSpecies( input_file_properties[ i ][ 1 ] ) );
2003 html_desc.append( "<tr><td>Sum of all distinct binary combinations:</td><td>"
2004 + all_bin_domain_combinations_encountered.size() + "</td></tr>" + nl );
2005 html_desc.append( "<tr><td>Sum of all distinct domains:</td><td>" + all_domains_encountered.size()
2006 + "</td></tr>" + nl );
2007 html_desc.append( "<tr><td>Analysis date/time:</td><td>"
2008 + new java.text.SimpleDateFormat( "yyyy.MM.dd HH:mm:ss" ).format( new java.util.Date() )
2009 + "</td></tr>" + nl );
2010 html_desc.append( "</table>" + nl );
2011 pw_stats = SurfacingUtil
2012 .writeDomainSimilaritiesToFile( html_desc,
2013 new StringBuilder( number_of_genomes + " genomes" ),
2016 number_of_genomes == 2,
2018 domain_similarity_print_option,
2019 domain_similarity_sort_field,
2022 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote main output (includes domain similarities) to: \""
2023 + ( out_dir == null ? my_outfile : out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) + "\"" );
2025 catch ( final IOException e ) {
2026 ForesterUtil.fatalError( surfacing.PRG_NAME, "Failed to write similarites to: \"" + output_file + "\" ["
2027 + e.getMessage() + "]" );
2029 System.out.println();
2030 // values_for_all_scores_histogram = pw_stats.getDataAsDoubleArray();
2031 final Species[] species = new Species[ number_of_genomes ];
2032 for( int i = 0; i < number_of_genomes; ++i ) {
2033 species[ i ] = new BasicSpecies( input_file_properties[ i ][ 1 ] );
2035 List<Phylogeny> inferred_trees = null;
2036 if ( ( number_of_genomes > 2 ) && perform_pwc ) {
2037 final PairwiseGenomeComparator pwgc = new PairwiseGenomeComparator();
2038 pwgc.performPairwiseComparisons( html_desc,
2039 sort_by_species_count_first,
2041 ignore_domains_without_combs_in_all_spec,
2042 ignore_species_specific_domains,
2043 domain_similarity_sort_field_for_automated_pwc,
2044 domain_similarity_print_option,
2046 domain_id_to_go_ids_map,
2053 automated_pairwise_comparison_suffix,
2055 surfacing.PAIRWISE_DOMAIN_COMPARISONS_PREFIX,
2059 String matrix_output_file = new String( output_file.toString() );
2060 if ( matrix_output_file.indexOf( '.' ) > 1 ) {
2061 matrix_output_file = matrix_output_file.substring( 0, matrix_output_file.indexOf( '.' ) );
2063 if ( out_dir != null ) {
2064 matrix_output_file = out_dir + ForesterUtil.FILE_SEPARATOR + matrix_output_file;
2065 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2067 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2068 + surfacing.MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans() );
2070 .writeMatrixToFile( new File( matrix_output_file
2071 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2072 pwgc.getSharedBinaryCombinationsBasedDistances() );
2073 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2074 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2075 pwgc.getSharedDomainsBasedDistances() );
2076 final Phylogeny nj_gd = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2077 + surfacing.NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans()
2079 final Phylogeny nj_bc = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2080 + surfacing.NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2081 .getSharedBinaryCombinationsBasedDistances().get( 0 ) );
2082 final Phylogeny nj_d = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2083 + surfacing.NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2084 .getSharedDomainsBasedDistances().get( 0 ) );
2085 inferred_trees = new ArrayList<Phylogeny>();
2086 inferred_trees.add( nj_gd );
2087 inferred_trees.add( nj_bc );
2088 inferred_trees.add( nj_d );
2089 if ( jacknifed_distances ) {
2090 pwgc.performPairwiseComparisonsJacknifed( species,
2094 jacknife_resamplings,
2098 .writeMatrixToFile( new File( matrix_output_file
2100 + ForesterUtil.round( jacknife_ratio, 2 )
2102 + jacknife_resamplings
2103 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2104 pwgc.getSharedBinaryCombinationsBasedDistances() );
2106 .writeMatrixToFile( new File( matrix_output_file + "_" + ForesterUtil.round( jacknife_ratio, 2 )
2107 + "_" + jacknife_resamplings
2108 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2109 pwgc.getSharedDomainsBasedDistances() );
2110 // if ( infer_species_trees ) {
2111 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2112 // + INFERRED_SBC_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc
2113 // .getSharedBinaryCombinationsBasedDistances() );
2114 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2115 // + INFERRED_SD_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc.getSharedDomainsBasedDistances() );
2118 } // if ( ( output_file != null ) && ( number_of_genomes > 2 ) && !isEmpty( automated_pairwise_comparison_suffix ) )
2119 if ( ( out_dir != null ) && ( !perform_pwc ) ) {
2120 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2122 writePresentToNexus( output_file, positive_filter_file, filter, gwcd_list );
2123 if ( ( ( intrees != null ) && ( intrees.length > 0 ) ) && ( number_of_genomes > 2 ) ) {
2124 final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
2126 max_allowed_overlap,
2127 no_engulfing_overlaps,
2131 if ( radomize_fitch_parsimony ) {
2132 s += random_number_seed_for_fitch_parsimony + "_";
2135 for( final Phylogeny intree : intrees ) {
2136 final String outfile_name = ForesterUtil.removeSuffix( output_file.toString() ) + s
2137 + ForesterUtil.removeSuffix( intree_files[ i ].toString() );
2138 final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator.createInstance( intree,
2140 SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
2141 radomize_fitch_parsimony,
2145 domain_id_to_go_ids_map,
2148 parameters_sb.toString(),
2149 domain_id_to_secondary_features_maps,
2150 positive_filter_file == null ? null : filter,
2151 output_binary_domain_combinationsfor_graph_analysis,
2152 all_bin_domain_combinations_gained_fitch,
2153 all_bin_domain_combinations_lost_fitch,
2155 // Listing of all domain combinations gained is only done if only one input tree is used.
2156 if ( ( domain_id_to_secondary_features_maps != null )
2157 && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
2159 for( final Map<DomainId, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
2160 final Map<Species, MappingResults> mapping_results_map = new TreeMap<Species, MappingResults>();
2161 final DomainParsimonyCalculator secondary_features_parsimony = DomainParsimonyCalculator
2162 .createInstance( intree, gwcd_list, domain_id_to_secondary_features_map );
2164 .executeParsimonyAnalysisForSecondaryFeatures( outfile_name
2166 + secondary_features_map_files[ j++ ],
2167 secondary_features_parsimony,
2169 parameters_sb.toString(),
2170 mapping_results_map );
2172 System.out.println();
2173 System.out.println( "Mapping to secondary features:" );
2174 for( final Species spec : mapping_results_map.keySet() ) {
2175 final MappingResults mapping_results = mapping_results_map.get( spec );
2176 final int total_domains = mapping_results.getSumOfFailures()
2177 + mapping_results.getSumOfSuccesses();
2178 System.out.print( spec + ":" );
2179 System.out.print( " mapped domains = " + mapping_results.getSumOfSuccesses() );
2180 System.out.print( ", not mapped domains = " + mapping_results.getSumOfFailures() );
2181 if ( total_domains > 0 ) {
2182 System.out.println( ", mapped ratio = "
2183 + ( 100 * mapping_results.getSumOfSuccesses() / total_domains ) + "%" );
2186 System.out.println( ", mapped ratio = n/a (total domains = 0 )" );
2193 } // for( final Phylogeny intree : intrees ) {
2195 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
2196 executePlusMinusAnalysis( output_file,
2197 plus_minus_analysis_high_copy_base_species,
2198 plus_minus_analysis_high_copy_target_species,
2199 plus_minus_analysis_high_low_copy_species,
2201 protein_lists_per_species,
2202 domain_id_to_go_ids_map,
2204 plus_minus_analysis_numbers );
2206 if ( output_protein_lists_for_all_domains ) {
2207 writeProteinListsForAllSpecies( out_dir, protein_lists_per_species, gwcd_list );
2209 // if ( ( intrees != null ) && ( intrees.length > 0 ) && ( inferred_trees != null ) && ( inferred_trees.size() > 0 ) ) {
2210 // final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
2212 // max_allowed_overlap,
2213 // no_engulfing_overlaps,
2214 // cutoff_scores_file );
2216 // if ( radomize_fitch_parsimony ) {
2217 // s += random_number_seed_for_fitch_parsimony + "_";
2220 // for( final Phylogeny inferred_tree : inferred_trees ) {
2221 // if ( !inferred_tree.isRooted() ) {
2222 // intrees[ 0 ].getRoot().getName();
2225 // final String outfile_name = ForesterUtil.removeSuffix( inferred_tree.getName() ) + s;
2226 // final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator
2227 // .createInstance( inferred_tree, gwcd_list );
2228 // SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
2229 // radomize_fitch_parsimony,
2231 // domain_parsimony,
2233 // domain_id_to_go_ids_map,
2234 // go_id_to_term_map,
2235 // go_namespace_limit,
2236 // parameters_sb.toString() );
2240 if ( all_bin_domain_combinations_gained_fitch != null ) {
2242 executeFitchGainsAnalysis( new File( output_file
2243 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2244 all_bin_domain_combinations_gained_fitch,
2245 all_domains_encountered.size(),
2246 all_bin_domain_combinations_encountered,
2249 catch ( final IOException e ) {
2250 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2253 if ( all_bin_domain_combinations_lost_fitch != null ) {
2255 executeFitchGainsAnalysis( new File( output_file
2256 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2257 all_bin_domain_combinations_lost_fitch,
2258 all_domains_encountered.size(),
2259 all_bin_domain_combinations_encountered,
2262 catch ( final IOException e ) {
2263 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2266 final Runtime rt = java.lang.Runtime.getRuntime();
2267 final long free_memory = rt.freeMemory() / 1000000;
2268 final long total_memory = rt.totalMemory() / 1000000;
2269 System.out.println();
2270 System.out.println( "Time for analysis : " + ( new Date().getTime() - analysis_start_time ) + "ms" );
2271 System.out.println( "Total running time: " + ( new Date().getTime() - start_time ) + "ms " );
2272 System.out.println( "Free memory : " + free_memory + "MB, total memory: " + total_memory + "MB" );
2273 System.out.println();
2274 System.out.println( "If this application is useful to you, please cite:" );
2275 System.out.println( surfacing.WWW );
2276 System.out.println();
2277 ForesterUtil.programMessage( PRG_NAME, "OK" );
2278 System.out.println();
2281 private static void preparePhylogenyForParsimonyAnalyses( final Phylogeny intree,
2282 final String[][] input_file_properties ) {
2283 final String[] genomes = new String[ input_file_properties.length ];
2284 for( int i = 0; i < input_file_properties.length; ++i ) {
2285 if ( intree.getNodes( input_file_properties[ i ][ 1 ] ).size() > 1 ) {
2286 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
2287 + "] is not unique in input tree " + intree.getName() );
2289 genomes[ i ] = input_file_properties[ i ][ 1 ];
2292 final PhylogenyNodeIterator it = intree.iteratorPostorder();
2293 while ( it.hasNext() ) {
2294 final PhylogenyNode n = it.next();
2295 if ( ForesterUtil.isEmpty( n.getName() ) ) {
2296 if ( n.getNodeData().isHasTaxonomy()
2297 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
2298 n.setName( n.getNodeData().getTaxonomy().getScientificName() );
2301 ForesterUtil.fatalError( surfacing.PRG_NAME,
2302 "node without both name and scientific taxonomy name found" );
2307 final List<String> igns = PhylogenyMethods.deleteExternalNodesPositiveSelection( genomes, intree );
2308 if ( igns.size() > 0 ) {
2309 System.out.println( "Not using the following " + igns.size() + " nodes:" );
2310 for( int i = 0; i < igns.size(); ++i ) {
2311 System.out.println( " " + i + ": " + igns.get( i ) );
2313 System.out.println( "--" );
2315 for( int i = 0; i < input_file_properties.length; ++i ) {
2317 intree.getNode( input_file_properties[ i ][ 1 ] );
2319 catch ( final IllegalArgumentException e ) {
2320 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
2321 + "] not present/not unique in input tree" );
2326 // public static StringBuffer stringCombinableDomainsMapToStringBuffer(
2327 // final SortedMap<String, CombinableDomains> map ) {
2328 // final StringBuffer sb = new StringBuffer();
2329 // for( final Iterator<String> iter = map.keySet().iterator();
2330 // iter.hasNext(); ) {
2331 // final Object key = iter.next();
2332 // sb.append( ForesterUtil.pad( new StringBuffer( key.toString() ), 18, ' ',
2334 // final CombinableDomains domain_combination = map.get( key );
2335 // sb.append( ForesterUtil.pad( new StringBuffer( "" +
2336 // domain_combination.getNumberOfCombiningDomains() ), 8,
2338 // sb.append( domain_combination.toStringBuffer() );
2339 // sb.append( ForesterUtil.getLineSeparator() );
2343 private static void printHelp() {
2344 System.out.println();
2345 System.out.println( "Usage:" );
2346 System.out.println();
2347 System.out.println( "% java -Xms256m -Xmx512m -cp forester.jar org.forester.applications." + surfacing.PRG_NAME
2348 + " [options] <phylogen(y|ies) infile> [external node name 1] [name 2] ... [name n]" );
2349 System.out.println();
2350 System.out.println( " Note: This software might need a significant amount of memory (heap space);" );
2352 .println( " hence use \"-Xms128m -Xmx512m\" (or more) to prevent a \"java.lang.OutOfMemoryError\"." );
2353 System.out.println();
2354 System.out.println( " Options: " );
2355 System.out.println( surfacing.DETAILEDNESS_OPTION + ": level of detail for similarities output file (default:"
2356 + DETAILEDNESS_DEFAULT + ")" );
2357 System.out.println( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION
2358 + ": to ignore combinations with self (default: not to ignore)" );
2360 .println( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION
2361 + ": to ignore domains without combinations in any species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2363 .println( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION
2364 + ": to ignore domains specific to one species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2365 System.out.println( surfacing.NOT_IGNORE_DUFS_OPTION
2366 + ": to _not_ ignore DUFs (domains with unknown function) (default: ignore DUFs)" );
2368 .println( surfacing.IGNORE_VIRAL_IDS
2369 + ": to ignore domains with ids containing 'vir', 'retro', 'transpos', 'phage', or starting with 'rv' or 'gag_'" );
2370 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_OPTION + ": sorting for similarities (default: "
2371 + DOMAIN_SORT_FILD_DEFAULT + ")" );
2372 System.out.println( surfacing.OUTPUT_FILE_OPTION + ": name for (main) output file (mandatory)" );
2373 System.out.println( surfacing.MAX_E_VALUE_OPTION + ": max (inclusive) E-value" );
2374 System.out.println( surfacing.MAX_ALLOWED_OVERLAP_OPTION + ": maximal allowed domain overlap" );
2375 System.out.println( surfacing.NO_ENGULFING_OVERLAP_OPTION + ": to ignore engulfed lower confidence domains" );
2376 System.out.println( surfacing.SPECIES_MATRIX_OPTION + ": species matrix" );
2377 System.out.println( surfacing.SCORING_OPTION + ": scoring (default:" + SCORING_DEFAULT + ")" );
2378 System.out.println( surfacing.DOMAIN_COUNT_SORT_OPTION + ": sorting for domain counts (default:"
2379 + DOMAINS_SORT_ORDER_DEFAULT + ")" );
2380 System.out.println( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION + ": domain similarity print option (default:"
2381 + DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT + ")" );
2382 System.out.println( surfacing.CUTOFF_SCORE_FILE_OPTION + ": cutoff score file" );
2383 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION
2384 + ": sort by species count first" );
2385 System.out.println( surfacing.OUTPUT_DIR_OPTION + ": output directory" );
2386 System.out.println( surfacing.PFAM_TO_GO_FILE_USE_OPTION + ": Pfam to GO mapping file" );
2387 System.out.println( surfacing.GO_OBO_FILE_USE_OPTION + ": GO terms file (OBO format)" );
2388 System.out.println( surfacing.GO_NAMESPACE_LIMIT_OPTION + ": limit GO term to one GO namespace" );
2389 System.out.println( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
2390 + "[=<suffix for pairwise comparison output files>]: to perform pairwise comparison based analyses" );
2391 System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION
2392 + ": species tree, to perform (Dollo, Fitch) parismony analyses" );
2394 .println( JACKNIFE_OPTION
2395 + ": perform jacknife resampling for domain and binary domain combination based distance matrices [default resamplings: "
2396 + JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT + "]" );
2397 System.out.println( JACKNIFE_RATIO_OPTION + ": ratio for jacknife resampling [default: "
2398 + JACKNIFE_RATIO_DEFAULT + "]" );
2399 System.out.println( JACKNIFE_RANDOM_SEED_OPTION
2400 + ": seed for random number generator for jacknife resampling [default: "
2401 + JACKNIFE_RANDOM_SEED_DEFAULT + "]" );
2402 // System.out.println( surfacing.INFER_SPECIES_TREES_OPTION
2403 // + ": to infer NJ species trees based on shared domains/binary domain combinations" );
2405 .println( surfacing.INPUT_SPECIES_TREE_OPTION
2406 + "=<treefiles in phyloXML format, separated by #>: to infer domain/binary domain combination gains/losses on given species trees" );
2407 System.out.println( surfacing.FILTER_POSITIVE_OPTION
2408 + "=<file>: to filter out proteins not containing at least one domain listed in <file>" );
2409 System.out.println( surfacing.FILTER_NEGATIVE_OPTION
2410 + "=<file>: to filter out proteins containing at least one domain listed in <file>" );
2411 System.out.println( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION
2412 + "=<file>: to filter out (ignore) domains listed in <file>" );
2413 System.out.println( surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>: to read input files from <file>" );
2415 .println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION
2416 + "=<seed>: seed for random number generator for Fitch Parsimony analysis (type: long, default: no randomization - given a choice, prefer absence" );
2417 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS
2418 + ": to consider directedness in binary combinations: e.g. A-B != B-A" );
2419 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY
2420 + ": to consider directedness and adjacency in binary combinations" );
2422 .println( surfacing.SEQ_EXTRACT_OPTION
2423 + "=<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')" );
2424 System.out.println( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE
2425 + "=<file>: to perfom parsimony analysis on secondary features" );
2426 System.out.println( surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>: to presence/absence genome analysis" );
2427 System.out.println( surfacing.DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS
2428 + ": to output binary domain combinations for (downstream) graph analysis" );
2429 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS + ": to output all proteins per domain" );
2430 System.out.println();
2431 System.out.println();
2432 System.out.println( "Example: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2433 + " org.forester.application.surfacing -detail=punctilious -o=TEST.html -pwc=TEST"
2434 + " -cos=Pfam_ls_22_TC2 -p2g=pfam2go -obo=gene_ontology_edit.obo "
2435 + "-dc_sort=dom -ignore_with_self -no_singles -e=0.001 -mo=1 -no_eo "
2436 + "-ds_output=detailed_html -scoring=domains -sort=alpha -" + JACKNIFE_OPTION
2437 + "=50 human mouse brafl strpu" );
2438 System.out.println();
2441 private static void processFilter( final File filter_file, final SortedSet<DomainId> filter ) {
2442 SortedSet<String> filter_str = null;
2444 filter_str = ForesterUtil.file2set( filter_file );
2446 catch ( final IOException e ) {
2447 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2449 if ( filter_str != null ) {
2450 for( final String string : filter_str ) {
2451 filter.add( new DomainId( string ) );
2455 System.out.println( "Filter:" );
2456 for( final DomainId domainId : filter ) {
2457 System.out.println( domainId.getId() );
2462 private static String[][] processInputFileNames( final String[] names ) {
2463 final String[][] input_file_properties = new String[ names.length ][];
2464 for( int i = 0; i < names.length; ++i ) {
2465 if ( names[ i ].indexOf( SEPARATOR_FOR_INPUT_VALUES ) < 0 ) {
2466 input_file_properties[ i ] = new String[ 2 ];
2467 input_file_properties[ i ][ 0 ] = names[ i ];
2468 input_file_properties[ i ][ 1 ] = names[ i ];
2471 input_file_properties[ i ] = names[ i ].split( surfacing.SEPARATOR_FOR_INPUT_VALUES + "" );
2472 if ( input_file_properties[ i ].length != 3 ) {
2474 .fatalError( surfacing.PRG_NAME,
2475 "properties for the input files (hmmpfam output) are expected "
2476 + "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 \""
2477 + names[ i ] + "\"" );
2480 final String error = ForesterUtil.isReadableFile( new File( input_file_properties[ i ][ 0 ] ) );
2481 if ( !ForesterUtil.isEmpty( error ) ) {
2482 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
2485 return input_file_properties;
2488 private static void processPlusMinusAnalysisOption( final CommandLineArguments cla,
2489 final List<String> high_copy_base,
2490 final List<String> high_copy_target,
2491 final List<String> low_copy,
2492 final List<Object> numbers ) {
2493 if ( cla.isOptionSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2494 if ( !cla.isOptionValueSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2495 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for 'plus-minus' file: -"
2496 + surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>" );
2498 final File plus_minus_file = new File( cla.getOptionValue( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) );
2499 final String msg = ForesterUtil.isReadableFile( plus_minus_file );
2500 if ( !ForesterUtil.isEmpty( msg ) ) {
2501 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + plus_minus_file + "\": " + msg );
2503 processPlusMinusFile( plus_minus_file, high_copy_base, high_copy_target, low_copy, numbers );
2507 // First numbers is minimal difference, second is factor.
2508 private static void processPlusMinusFile( final File plus_minus_file,
2509 final List<String> high_copy_base,
2510 final List<String> high_copy_target,
2511 final List<String> low_copy,
2512 final List<Object> numbers ) {
2513 Set<String> species_set = null;
2514 int min_diff = PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT;
2515 double factor = PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT;
2517 species_set = ForesterUtil.file2set( plus_minus_file );
2519 catch ( final IOException e ) {
2520 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2522 if ( species_set != null ) {
2523 for( final String species : species_set ) {
2524 final String species_trimmed = species.substring( 1 );
2525 if ( species.startsWith( "+" ) ) {
2526 if ( low_copy.contains( species_trimmed ) ) {
2527 ForesterUtil.fatalError( surfacing.PRG_NAME,
2528 "species/genome names can not appear with both '+' and '-' suffix, as appears the case for: \""
2529 + species_trimmed + "\"" );
2531 high_copy_base.add( species_trimmed );
2533 else if ( species.startsWith( "*" ) ) {
2534 if ( low_copy.contains( species_trimmed ) ) {
2535 ForesterUtil.fatalError( surfacing.PRG_NAME,
2536 "species/genome names can not appear with both '*' and '-' suffix, as appears the case for: \""
2537 + species_trimmed + "\"" );
2539 high_copy_target.add( species_trimmed );
2541 else if ( species.startsWith( "-" ) ) {
2542 if ( high_copy_base.contains( species_trimmed ) || high_copy_target.contains( species_trimmed ) ) {
2543 ForesterUtil.fatalError( surfacing.PRG_NAME,
2544 "species/genome names can not appear with both '+' or '*' and '-' suffix, as appears the case for: \""
2545 + species_trimmed + "\"" );
2547 low_copy.add( species_trimmed );
2549 else if ( species.startsWith( "$D" ) ) {
2551 min_diff = Integer.parseInt( species.substring( 3 ) );
2553 catch ( final NumberFormatException e ) {
2554 ForesterUtil.fatalError( surfacing.PRG_NAME,
2555 "could not parse integer value for minimal difference from: \""
2556 + species.substring( 3 ) + "\"" );
2559 else if ( species.startsWith( "$F" ) ) {
2561 factor = Double.parseDouble( species.substring( 3 ) );
2563 catch ( final NumberFormatException e ) {
2564 ForesterUtil.fatalError( surfacing.PRG_NAME, "could not parse double value for factor from: \""
2565 + species.substring( 3 ) + "\"" );
2568 else if ( species.startsWith( "#" ) ) {
2573 .fatalError( surfacing.PRG_NAME,
2574 "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: \""
2577 numbers.add( new Integer( min_diff + "" ) );
2578 numbers.add( new Double( factor + "" ) );
2582 ForesterUtil.fatalError( surfacing.PRG_NAME, "'plus minus' file [" + plus_minus_file + "] appears empty" );
2586 private static void writePresentToNexus( final File output_file,
2587 final File positive_filter_file,
2588 final SortedSet<DomainId> filter,
2589 final List<GenomeWideCombinableDomains> gwcd_list ) {
2592 .writeMatrixToFile( DomainParsimonyCalculator
2593 .createMatrixOfDomainPresenceOrAbsence( gwcd_list, positive_filter_file == null ? null
2594 : filter ), output_file + DOMAINS_PRESENT_NEXUS, Format.NEXUS_BINARY );
2595 SurfacingUtil.writeMatrixToFile( DomainParsimonyCalculator
2596 .createMatrixOfBinaryDomainCombinationPresenceOrAbsence( gwcd_list ), output_file
2597 + BDC_PRESENT_NEXUS, Format.NEXUS_BINARY );
2599 catch ( final Exception e ) {
2600 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2604 private static void writeProteinListsForAllSpecies( final File output_dir,
2605 final SortedMap<Species, List<Protein>> protein_lists_per_species,
2606 final List<GenomeWideCombinableDomains> gwcd_list ) {
2607 final SortedSet<DomainId> all_domains = new TreeSet<DomainId>();
2608 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
2609 all_domains.addAll( gwcd.getAllDomainIds() );
2611 for( final DomainId domain : all_domains ) {
2612 final File out = new File( output_dir + ForesterUtil.FILE_SEPARATOR + domain + SEQ_EXTRACT_SUFFIX );
2613 SurfacingUtil.checkForOutputFileWriteability( out );
2615 final Writer proteins_file_writer = new BufferedWriter( new FileWriter( out ) );
2616 SurfacingUtil.extractProteinNames( protein_lists_per_species, domain, proteins_file_writer, "\t" );
2617 proteins_file_writer.close();
2619 catch ( final IOException e ) {
2620 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2622 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote proteins list to \"" + out + "\"" );