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.parsers.util.ParserUtils;
58 import org.forester.io.writers.PhylogenyWriter;
59 import org.forester.phylogeny.Phylogeny;
60 import org.forester.phylogeny.PhylogenyMethods;
61 import org.forester.phylogeny.PhylogenyNode;
62 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
63 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
64 import org.forester.surfacing.BasicDomainSimilarityCalculator;
65 import org.forester.surfacing.BasicGenomeWideCombinableDomains;
66 import org.forester.surfacing.BasicSpecies;
67 import org.forester.surfacing.BinaryDomainCombination;
68 import org.forester.surfacing.CombinationsBasedPairwiseDomainSimilarityCalculator;
69 import org.forester.surfacing.DomainCountsBasedPairwiseSimilarityCalculator;
70 import org.forester.surfacing.DomainCountsDifferenceUtil;
71 import org.forester.surfacing.DomainId;
72 import org.forester.surfacing.DomainLengthsTable;
73 import org.forester.surfacing.DomainParsimonyCalculator;
74 import org.forester.surfacing.DomainSimilarity;
75 import org.forester.surfacing.DomainSimilarity.DomainSimilarityScoring;
76 import org.forester.surfacing.DomainSimilarity.DomainSimilaritySortField;
77 import org.forester.surfacing.DomainSimilarityCalculator;
78 import org.forester.surfacing.DomainSimilarityCalculator.Detailedness;
79 import org.forester.surfacing.GenomeWideCombinableDomains;
80 import org.forester.surfacing.GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder;
81 import org.forester.surfacing.MappingResults;
82 import org.forester.surfacing.PairwiseDomainSimilarityCalculator;
83 import org.forester.surfacing.PairwiseGenomeComparator;
84 import org.forester.surfacing.PrintableDomainSimilarity;
85 import org.forester.surfacing.PrintableDomainSimilarity.PRINT_OPTION;
86 import org.forester.surfacing.Protein;
87 import org.forester.surfacing.ProteinCountsBasedPairwiseDomainSimilarityCalculator;
88 import org.forester.surfacing.Species;
89 import org.forester.surfacing.SurfacingUtil;
90 import org.forester.util.BasicDescriptiveStatistics;
91 import org.forester.util.BasicTable;
92 import org.forester.util.BasicTableParser;
93 import org.forester.util.CommandLineArguments;
94 import org.forester.util.DescriptiveStatistics;
95 import org.forester.util.ForesterConstants;
96 import org.forester.util.ForesterUtil;
98 public class surfacing {
100 public final static String DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS = "graph_analysis_out";
101 public final static String DOMAIN_COMBINITONS_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_dc.dot";
102 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC_OUTPUTFILE_SUFFIX_FOR_GRAPH_ANALYSIS = "_fitch_present_dc.dot";
103 public final static String DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX = ".dcc";
105 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_DOMAINS = "_dollo_gl_d";
106 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_gl_dc";
107 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_DOMAINS = "_fitch_gl_d";
108 public final static String PARSIMONY_OUTPUT_GL_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_gl_dc";
110 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_DOMAINS = "_dollo_glc_d";
111 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_BINARY_COMBINATIONS = "_dollo_glc_dc";
112 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_DOMAINS = "_fitch_glc_d";
113 public final static String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_FITCH_BINARY_COMBINATIONS = "_fitch_glc_dc";
115 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_BC = "_fitch_gains_dc";
116 public final static String PARSIMONY_OUTPUT_FITCH_GAINS_HTML_BC = "_fitch_gains_dc.html";
117 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_BC = "_fitch_losses_dc";
118 public final static String PARSIMONY_OUTPUT_FITCH_LOSSES_HTML_BC = "_fitch_losses_dc.html";
119 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_BC = "_fitch_present_dc";
120 public final static String PARSIMONY_OUTPUT_FITCH_PRESENT_HTML_BC = "_fitch_present_dc.html";
121 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_D = "_dollo_gains_d";
122 public final static String PARSIMONY_OUTPUT_DOLLO_GAINS_HTML_D = "_dollo_gains_d.html";
123 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_D = "_dollo_losses_d";
124 public final static String PARSIMONY_OUTPUT_DOLLO_LOSSES_HTML_D = "_dollo_losses_d.html";
125 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_D = "_dollo_present_d";
126 public final static String PARSIMONY_OUTPUT_DOLLO_PRESENT_HTML_D = "_dollo_present_d.html";
127 public final static String DOMAINS_PRESENT_NEXUS = "_dom.nex";
128 public final static String BDC_PRESENT_NEXUS = "_dc.nex";
130 public final static String PRG_NAME = "surfacing";
131 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_d_dollo"
132 + ForesterConstants.PHYLO_XML_SUFFIX;
133 public static final String DOMAINS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_d_fitch"
134 + ForesterConstants.PHYLO_XML_SUFFIX;
135 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_dc_dollo"
136 + ForesterConstants.PHYLO_XML_SUFFIX;
137 public static final String BINARY_DOMAIN_COMBINATIONS_PARSIMONY_TREE_OUTPUT_SUFFIX_FITCH = "_dc_fitch"
138 + ForesterConstants.PHYLO_XML_SUFFIX;
139 public static final String NEXUS_EXTERNAL_DOMAINS = "_dom.nex";
140 public static final String NEXUS_EXTERNAL_DOMAIN_COMBINATIONS = "_dc.nex";
141 public static final String NEXUS_SECONDARY_FEATURES = "_secondary_features.nex";
142 public static final String PARSIMONY_OUTPUT_GL_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_gl_secondary_features";
143 public static final String PARSIMONY_OUTPUT_GL_COUNTS_SUFFIX_DOLLO_SECONDARY_FEATURES = "_dollo_glc_secondary_features";
144 public static final String PARSIMONY_OUTPUT_DOLLO_GAINS_SECONDARY_FEATURES = "_dollo_gains_secondary_features";
145 public static final String PARSIMONY_OUTPUT_DOLLO_LOSSES_SECONDARY_FEATURES = "_dollo_losses_secondary_features";
146 public static final String PARSIMONY_OUTPUT_DOLLO_PRESENT_SECONDARY_FEATURES = "_dollo_present_secondary_features";
147 public static final String SECONDARY_FEATURES_PARSIMONY_TREE_OUTPUT_SUFFIX_DOLLO = "_secondary_features_dollo"
148 + ForesterConstants.PHYLO_XML_SUFFIX;
149 public static final String PARSIMONY_OUTPUT_DOLLO_ALL_GOID_D_ALL_NAMESPACES = "_dollo_goid_d";
150 public static final String PARSIMONY_OUTPUT_FITCH_ALL_GOID_BC_ALL_NAMESPACES = "_fitch_goid_dc";
151 final static private String HELP_OPTION_1 = "help";
152 final static private String HELP_OPTION_2 = "h";
153 final static private String OUTPUT_DIR_OPTION = "out_dir";
154 final static private String SCORING_OPTION = "scoring";
155 private static final DomainSimilarityScoring SCORING_DEFAULT = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
156 final static private String SCORING_DOMAIN_COUNT_BASED = "domains";
157 final static private String SCORING_PROTEIN_COUNT_BASED = "proteins";
158 final static private String SCORING_COMBINATION_BASED = "combinations";
159 final static private String DETAILEDNESS_OPTION = "detail";
160 private final static Detailedness DETAILEDNESS_DEFAULT = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
161 final static private String SPECIES_MATRIX_OPTION = "smatrix";
162 final static private String DETAILEDNESS_BASIC = "basic";
163 final static private String DETAILEDNESS_LIST_IDS = "list_ids";
164 final static private String DETAILEDNESS_PUNCTILIOUS = "punctilious";
165 final static private String DOMAIN_SIMILARITY_SORT_OPTION = "sort";
166 private static final DomainSimilaritySortField DOMAIN_SORT_FILD_DEFAULT = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
167 final static private String DOMAIN_SIMILARITY_SORT_MIN = "min";
168 final static private String DOMAIN_SIMILARITY_SORT_MAX = "max";
169 final static private String DOMAIN_SIMILARITY_SORT_SD = "sd";
170 final static private String DOMAIN_SIMILARITY_SORT_MEAN = "mean";
171 final static private String DOMAIN_SIMILARITY_SORT_DIFF = "diff";
172 final static private String DOMAIN_SIMILARITY_SORT_COUNTS_DIFF = "count_diff";
173 final static private String DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF = "abs_count_diff";
174 final static private String DOMAIN_SIMILARITY_SORT_SPECIES_COUNT = "species";
175 final static private String DOMAIN_SIMILARITY_SORT_ALPHA = "alpha";
176 final static private String DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION = "species_first";
177 final static private String DOMAIN_COUNT_SORT_OPTION = "dc_sort";
178 private static final GenomeWideCombinableDomainsSortOrder DOMAINS_SORT_ORDER_DEFAULT = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
179 final static private String DOMAIN_COUNT_SORT_ALPHA = "alpha";
180 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT = "dom";
181 final static private String DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT = "prot";
182 final static private String DOMAIN_COUNT_SORT_COMBINATIONS_COUNT = "comb";
183 final static private String CUTOFF_SCORE_FILE_OPTION = "cos";
184 final static private String NOT_IGNORE_DUFS_OPTION = "dufs";
185 final static private String MAX_E_VALUE_OPTION = "e";
186 final static private String MAX_ALLOWED_OVERLAP_OPTION = "mo";
187 final static private String NO_ENGULFING_OVERLAP_OPTION = "no_eo";
188 final static private String IGNORE_COMBINATION_WITH_SAME_OPTION = "ignore_self_comb";
189 final static private String PAIRWISE_DOMAIN_COMPARISONS_PREFIX = "pwc_";
190 final static private String PAIRWISE_DOMAIN_COMPARISONS_OPTION = "pwc";
191 final static private String OUTPUT_FILE_OPTION = "o";
192 final static private String PFAM_TO_GO_FILE_USE_OPTION = "p2g";
193 final static private String GO_OBO_FILE_USE_OPTION = "obo";
194 final static private String GO_NAMESPACE_LIMIT_OPTION = "go_namespace";
195 final static private String GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION = "molecular_function";
196 final static private String GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS = "biological_process";
197 final static private String GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT = "cellular_component";
198 final static private String SECONDARY_FEATURES_PARSIMONY_MAP_FILE = "secondary";
199 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED = "simple_tab";
200 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML = "simple_html";
201 final static private String DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML = "detailed_html";
202 final static private String DOMAIN_SIMILARITY_PRINT_OPTION = "ds_output";
203 private static final PRINT_OPTION DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT = PrintableDomainSimilarity.PRINT_OPTION.HTML;
204 final static private String IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION = "ignore_singlet_domains";
205 final static private String IGNORE_VIRAL_IDS = "ignore_viral_ids";
206 final static private boolean IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT = false;
207 final static private String IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION = "ignore_species_specific_domains";
208 final static private boolean IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT = false;
209 final static private String MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score.pwd";
210 final static private String MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains.pwd";
211 final static private String MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations.pwd";
212 final static private String NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX = "_mean_score_NJ"
213 + ForesterConstants.PHYLO_XML_SUFFIX;
214 final static private String NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX = "_domains_NJ"
215 + ForesterConstants.PHYLO_XML_SUFFIX;
216 final static private String NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX = "_bin_combinations_NJ"
217 + ForesterConstants.PHYLO_XML_SUFFIX;
218 final static private String JACKNIFE_OPTION = "jack";
219 final static private String JACKNIFE_RANDOM_SEED_OPTION = "seed";
220 final static private String JACKNIFE_RATIO_OPTION = "jack_ratio";
221 private static final int JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT = 100;
222 final static private long JACKNIFE_RANDOM_SEED_DEFAULT = 19;
223 final static private double JACKNIFE_RATIO_DEFAULT = 0.5;
224 //final static private String INFER_SPECIES_TREES_OPTION = "species_tree_inference";
225 final static private String INFERRED_SD_BASED_NJ_SPECIES_TREE_SUFFIX = "_sd_nj.nh";
226 final static private String INFERRED_SBC_BASED_NJ_SPECIES_TREE_SUFFIX = "_sbc_nj.nh";
227 final static private String FILTER_POSITIVE_OPTION = "pos_filter";
228 final static private String FILTER_NEGATIVE_OPTION = "neg_filter";
229 final static private String FILTER_NEGATIVE_DOMAINS_OPTION = "neg_dom_filter";
230 final static private String INPUT_FILES_FROM_FILE_OPTION = "input";
231 final static private String INPUT_SPECIES_TREE_OPTION = "species_tree";
232 final static private String SEQ_EXTRACT_OPTION = "prot_extract";
233 final static private char SEPARATOR_FOR_INPUT_VALUES = '#';
234 final static private String PRG_VERSION = "2.200";
235 final static private String PRG_DATE = "2011.10.18";
236 final static private String E_MAIL = "czmasek@burnham.org";
237 final static private String WWW = "www.phylosoft.org/forester/applications/surfacing";
238 final static private boolean IGNORE_DUFS_DEFAULT = true;
239 final static private boolean IGNORE_COMBINATION_WITH_SAME_DEFAULLT = false;
240 final static private double MAX_E_VALUE_DEFAULT = -1;
241 final static private int MAX_ALLOWED_OVERLAP_DEFAULT = -1;
242 private static final String RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION = "random_seed";
243 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS = "consider_bdc_direction";
244 private static final String CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY = "consider_bdc_adj";
245 private static final String SEQ_EXTRACT_SUFFIX = ".prot";
246 private static final String PLUS_MINUS_ANALYSIS_OPTION = "plus_minus";
247 private static final String PLUS_MINUS_DOM_SUFFIX = "_plus_minus_dom.txt";
248 private static final String PLUS_MINUS_DOM_SUFFIX_HTML = "_plus_minus_dom.html";
249 private static final String PLUS_MINUS_DC_SUFFIX_HTML = "_plus_minus_dc.html";
250 private static final int PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT = 0;
251 private static final double PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT = 1.0;
252 private static final String PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_all.txt";
253 private static final String PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX = "_plus_minus_go_ids_passing.txt";
254 private static final String OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS = "all_prot";
255 private static final boolean VERBOSE = false;
256 private static final String OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_gains_counts";
257 private static final String OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX = "_fitch_dc_losses_counts";
258 private static final String DOMAIN_LENGTHS_ANALYSIS_SUFFIX = "_domain_lengths_analysis";
259 private static final boolean PERFORM_DOMAIN_LENGTH_ANALYSIS = true;
260 public static final String ALL_PFAMS_ENCOUNTERED_SUFFIX = "_all_encountered_pfams";
261 public static final String ALL_PFAMS_ENCOUNTERED_WITH_GO_ANNOTATION_SUFFIX = "_all_encountered_pfams_with_go_annotation";
262 public static final String ENCOUNTERED_PFAMS_SUMMARY_SUFFIX = "_encountered_pfams_summary";
263 public static final String ALL_PFAMS_GAINED_AS_DOMAINS_SUFFIX = "_all_pfams_gained_as_domains";
264 public static final String ALL_PFAMS_LOST_AS_DOMAINS_SUFFIX = "_all_pfams_lost_as_domains";
265 public static final String ALL_PFAMS_GAINED_AS_DC_SUFFIX = "_all_pfams_gained_as_dc";
266 public static final String ALL_PFAMS_LOST_AS_DC_SUFFIX = "_all_pfams_lost_as_dc";
267 public static final String BASE_DIRECTORY_PER_NODE_DOMAIN_GAIN_LOSS_FILES = "PER_NODE_EVENTS";
268 public static final String BASE_DIRECTORY_PER_SUBTREE_DOMAIN_GAIN_LOSS_FILES = "PER_SUBTREE_EVENTS";
269 public static final String D_PROMISCUITY_FILE_SUFFIX = "_domain_promiscuities";
270 private static final String LOG_FILE_SUFFIX = "_log.txt";
271 private static final String DATA_FILE_SUFFIX = "_domain_combination_data.txt";
272 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";
273 private static final INDIVIDUAL_SCORE_CUTOFF INDIVIDUAL_SCORE_CUTOFF_DEFAULT = INDIVIDUAL_SCORE_CUTOFF.FULL_SEQUENCE;
274 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_COUNTS_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_counts.txt";
275 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists.txt";
276 public static final String INDEPENDENT_DC_GAINS_FITCH_PARS_DC_FOR_GO_MAPPING_OUTPUT_SUFFIX = "_indep_dc_gains_fitch_lists_for_go_mapping.txt";
277 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";
279 private static void checkWriteabilityForPairwiseComparisons( final PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option,
280 final String[][] input_file_properties,
281 final String automated_pairwise_comparison_suffix,
282 final File outdir ) {
283 for( int i = 0; i < input_file_properties.length; ++i ) {
284 for( int j = 0; j < i; ++j ) {
285 final String species_i = input_file_properties[ i ][ 1 ];
286 final String species_j = input_file_properties[ j ][ 1 ];
287 String pairwise_similarities_output_file_str = PAIRWISE_DOMAIN_COMPARISONS_PREFIX + species_i + "_"
288 + species_j + automated_pairwise_comparison_suffix;
289 switch ( domain_similarity_print_option ) {
291 if ( !pairwise_similarities_output_file_str.endsWith( ".html" ) ) {
292 pairwise_similarities_output_file_str += ".html";
296 final String error = ForesterUtil
297 .isWritableFile( new File( outdir == null ? pairwise_similarities_output_file_str : outdir
298 + ForesterUtil.FILE_SEPARATOR + pairwise_similarities_output_file_str ) );
299 if ( !ForesterUtil.isEmpty( error ) ) {
300 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
306 private static StringBuilder createParametersAsString( final boolean ignore_dufs,
307 final double e_value_max,
308 final int max_allowed_overlap,
309 final boolean no_engulfing_overlaps,
310 final File cutoff_scores_file,
311 final BinaryDomainCombination.DomainCombinationType dc_type ) {
312 final StringBuilder parameters_sb = new StringBuilder();
313 parameters_sb.append( "E-value: " + e_value_max );
314 if ( cutoff_scores_file != null ) {
315 parameters_sb.append( ", Cutoff-scores-file: " + cutoff_scores_file );
318 parameters_sb.append( ", Cutoff-scores-file: not-set" );
320 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
321 parameters_sb.append( ", Max-overlap: " + max_allowed_overlap );
324 parameters_sb.append( ", Max-overlap: not-set" );
326 if ( no_engulfing_overlaps ) {
327 parameters_sb.append( ", Engulfing-overlaps: not-allowed" );
330 parameters_sb.append( ", Engulfing-overlaps: allowed" );
333 parameters_sb.append( ", Ignore-dufs: true" );
336 parameters_sb.append( ", Ignore-dufs: false" );
338 parameters_sb.append( ", DC type (if applicable): " + dc_type );
339 return parameters_sb;
343 * Warning: This side-effects 'all_bin_domain_combinations_encountered'!
347 * @param all_bin_domain_combinations_changed
348 * @param sum_of_all_domains_encountered
349 * @param all_bin_domain_combinations_encountered
350 * @param is_gains_analysis
351 * @throws IOException
353 private static void executeFitchGainsAnalysis( final File output_file,
354 final List<BinaryDomainCombination> all_bin_domain_combinations_changed,
355 final int sum_of_all_domains_encountered,
356 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered,
357 final boolean is_gains_analysis ) throws IOException {
358 SurfacingUtil.checkForOutputFileWriteability( output_file );
359 final Writer out = ForesterUtil.createBufferedWriter( output_file );
360 final SortedMap<Object, Integer> bdc_to_counts = ForesterUtil
361 .listToSortedCountsMap( all_bin_domain_combinations_changed );
362 final SortedSet<DomainId> all_domains_in_combination_changed_more_than_once = new TreeSet<DomainId>();
363 final SortedSet<DomainId> all_domains_in_combination_changed_only_once = new TreeSet<DomainId>();
366 for( final Object bdc_object : bdc_to_counts.keySet() ) {
367 final BinaryDomainCombination bdc = ( BinaryDomainCombination ) bdc_object;
368 final int count = bdc_to_counts.get( bdc_object );
370 ForesterUtil.unexpectedFatalError( PRG_NAME, "count < 1 " );
372 out.write( bdc + "\t" + count + ForesterUtil.LINE_SEPARATOR );
374 all_domains_in_combination_changed_more_than_once.add( bdc.getId0() );
375 all_domains_in_combination_changed_more_than_once.add( bdc.getId1() );
378 else if ( count == 1 ) {
379 all_domains_in_combination_changed_only_once.add( bdc.getId0() );
380 all_domains_in_combination_changed_only_once.add( bdc.getId1() );
384 final int all = all_bin_domain_combinations_encountered.size();
386 if ( !is_gains_analysis ) {
387 all_bin_domain_combinations_encountered.removeAll( all_bin_domain_combinations_changed );
388 never_lost = all_bin_domain_combinations_encountered.size();
389 for( final BinaryDomainCombination bdc : all_bin_domain_combinations_encountered ) {
390 out.write( bdc + "\t" + "0" + ForesterUtil.LINE_SEPARATOR );
393 if ( is_gains_analysis ) {
394 out.write( "Sum of all distinct domain combinations appearing once : " + one
395 + ForesterUtil.LINE_SEPARATOR );
396 out.write( "Sum of all distinct domain combinations appearing more than once : " + above_one
397 + ForesterUtil.LINE_SEPARATOR );
398 out.write( "Sum of all distinct domains in combinations apppearing only once : "
399 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
400 out.write( "Sum of all distinct domains in combinations apppearing more than once: "
401 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
404 out.write( "Sum of all distinct domain combinations never lost : " + never_lost
405 + ForesterUtil.LINE_SEPARATOR );
406 out.write( "Sum of all distinct domain combinations lost once : " + one
407 + ForesterUtil.LINE_SEPARATOR );
408 out.write( "Sum of all distinct domain combinations lost more than once : " + above_one
409 + ForesterUtil.LINE_SEPARATOR );
410 out.write( "Sum of all distinct domains in combinations lost only once : "
411 + all_domains_in_combination_changed_only_once.size() + ForesterUtil.LINE_SEPARATOR );
412 out.write( "Sum of all distinct domains in combinations lost more than once: "
413 + all_domains_in_combination_changed_more_than_once.size() + ForesterUtil.LINE_SEPARATOR );
415 out.write( "All binary combinations : " + all
416 + ForesterUtil.LINE_SEPARATOR );
417 out.write( "All domains : "
418 + sum_of_all_domains_encountered );
420 ForesterUtil.programMessage( surfacing.PRG_NAME,
421 "Wrote fitch domain combination dynamics counts analysis to \"" + output_file
425 private static void executePlusMinusAnalysis( final File output_file,
426 final List<String> plus_minus_analysis_high_copy_base,
427 final List<String> plus_minus_analysis_high_copy_target,
428 final List<String> plus_minus_analysis_low_copy,
429 final List<GenomeWideCombinableDomains> gwcd_list,
430 final SortedMap<Species, List<Protein>> protein_lists_per_species,
431 final Map<DomainId, List<GoId>> domain_id_to_go_ids_map,
432 final Map<GoId, GoTerm> go_id_to_term_map,
433 final List<Object> plus_minus_analysis_numbers ) {
434 final Set<String> all_spec = new HashSet<String>();
435 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
436 all_spec.add( gwcd.getSpecies().getSpeciesId() );
438 final File html_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX_HTML );
439 final File plain_out_dom = new File( output_file + PLUS_MINUS_DOM_SUFFIX );
440 final File html_out_dc = new File( output_file + PLUS_MINUS_DC_SUFFIX_HTML );
441 final File all_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_ALL_GO_IDS_DOM_SUFFIX );
442 final File passing_domains_go_ids_out_dom = new File( output_file + PLUS_MINUS_PASSING_GO_IDS_DOM_SUFFIX );
443 final File proteins_file_base = new File( output_file + "" );
444 final int min_diff = ( ( Integer ) plus_minus_analysis_numbers.get( 0 ) ).intValue();
445 final double factor = ( ( Double ) plus_minus_analysis_numbers.get( 1 ) ).doubleValue();
447 DomainCountsDifferenceUtil.calculateCopyNumberDifferences( gwcd_list,
448 protein_lists_per_species,
449 plus_minus_analysis_high_copy_base,
450 plus_minus_analysis_high_copy_target,
451 plus_minus_analysis_low_copy,
457 domain_id_to_go_ids_map,
459 all_domains_go_ids_out_dom,
460 passing_domains_go_ids_out_dom,
461 proteins_file_base );
463 catch ( final IOException e ) {
464 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
466 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
467 + html_out_dom + "\"" );
468 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \""
469 + plain_out_dom + "\"" );
470 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis results to \"" + html_out_dc
472 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based passing GO ids to \""
473 + passing_domains_go_ids_out_dom + "\"" );
474 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote plus minus domain analysis based all GO ids to \""
475 + all_domains_go_ids_out_dom + "\"" );
478 private static Phylogeny[] getIntrees( final File[] intree_files,
479 final int number_of_genomes,
480 final String[][] input_file_properties ) {
481 final Phylogeny[] intrees = new Phylogeny[ intree_files.length ];
483 for( final File intree_file : intree_files ) {
484 Phylogeny intree = null;
485 final String error = ForesterUtil.isReadableFile( intree_file );
486 if ( !ForesterUtil.isEmpty( error ) ) {
487 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read input tree file [" + intree_file + "]: "
491 final Phylogeny[] p_array = ParserBasedPhylogenyFactory.getInstance()
492 .create( intree_file, ParserUtils.createParserDependingOnFileType( intree_file, true ) );
493 if ( p_array.length < 1 ) {
494 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
495 + "] does not contain any phylogeny in phyloXML format" );
497 else if ( p_array.length > 1 ) {
498 ForesterUtil.fatalError( surfacing.PRG_NAME, "file [" + intree_file
499 + "] contains more than one phylogeny in phyloXML format" );
501 intree = p_array[ 0 ];
503 catch ( final Exception e ) {
504 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read input tree from file [" + intree_file
507 if ( ( intree == null ) || intree.isEmpty() ) {
508 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is empty" );
510 if ( !intree.isRooted() ) {
511 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] is not rooted" );
513 if ( intree.getNumberOfExternalNodes() < number_of_genomes ) {
514 ForesterUtil.fatalError( surfacing.PRG_NAME,
515 "number of external nodes [" + intree.getNumberOfExternalNodes()
516 + "] of input tree [" + intree_file
517 + "] is smaller than the number of genomes the be analyzed ["
518 + number_of_genomes + "]" );
520 final StringBuilder parent_names = new StringBuilder();
521 final int nodes_lacking_name = SurfacingUtil.getNumberOfNodesLackingName( intree, parent_names );
522 if ( nodes_lacking_name > 0 ) {
523 ForesterUtil.fatalError( surfacing.PRG_NAME, "input tree [" + intree_file + "] has "
524 + nodes_lacking_name + " node(s) lacking a name [parent names:" + parent_names + "]" );
526 preparePhylogenyForParsimonyAnalyses( intree, input_file_properties );
527 if ( !intree.isCompletelyBinary() ) {
528 ForesterUtil.printWarningMessage( surfacing.PRG_NAME, "input tree [" + intree_file
529 + "] is not completely binary" );
531 intrees[ i++ ] = intree;
536 private static List<Phylogeny> inferSpeciesTrees( final File outfile, final List<DistanceMatrix> distances_list ) {
537 final NeighborJoining nj = NeighborJoining.createInstance();
538 final List<Phylogeny> phylogenies = nj.execute( distances_list );
539 final PhylogenyWriter w = new PhylogenyWriter();
541 w.toNewHampshire( phylogenies, true, true, outfile, ";" );
543 catch ( final IOException e ) {
544 ForesterUtil.fatalError( PRG_NAME, "failed to write to outfile [" + outfile + "]: " + e.getMessage() );
549 private static void log( final String msg, final Writer w ) {
552 w.write( ForesterUtil.LINE_SEPARATOR );
554 catch ( final IOException e ) {
555 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
559 public static void main( final String args[] ) {
560 final long start_time = new Date().getTime();
561 // final StringBuffer log = new StringBuffer();
562 final StringBuilder html_desc = new StringBuilder();
563 ForesterUtil.printProgramInformation( surfacing.PRG_NAME,
564 surfacing.PRG_VERSION,
568 final String nl = ForesterUtil.LINE_SEPARATOR;
569 html_desc.append( "<table>" + nl );
570 html_desc.append( "<tr><td>Produced by:</td><td>" + surfacing.PRG_NAME + "</td></tr>" + nl );
571 html_desc.append( "<tr><td>Version:</td><td>" + surfacing.PRG_VERSION + "</td></tr>" + nl );
572 html_desc.append( "<tr><td>Release Date:</td><td>" + surfacing.PRG_DATE + "</td></tr>" + nl );
573 html_desc.append( "<tr><td>Contact:</td><td>" + surfacing.E_MAIL + "</td></tr>" + nl );
574 html_desc.append( "<tr><td>WWW:</td><td>" + surfacing.WWW + "</td></tr>" + nl );
575 CommandLineArguments cla = null;
577 cla = new CommandLineArguments( args );
579 catch ( final Exception e ) {
580 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
582 if ( cla.isOptionSet( surfacing.HELP_OPTION_1 ) || cla.isOptionSet( surfacing.HELP_OPTION_2 ) ) {
583 surfacing.printHelp();
586 if ( ( args.length < 1 ) ) {
587 surfacing.printHelp();
590 final List<String> allowed_options = new ArrayList<String>();
591 allowed_options.add( surfacing.NOT_IGNORE_DUFS_OPTION );
592 allowed_options.add( surfacing.MAX_E_VALUE_OPTION );
593 allowed_options.add( surfacing.DETAILEDNESS_OPTION );
594 allowed_options.add( surfacing.OUTPUT_FILE_OPTION );
595 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_OPTION );
596 allowed_options.add( surfacing.SPECIES_MATRIX_OPTION );
597 allowed_options.add( surfacing.SCORING_OPTION );
598 allowed_options.add( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
599 allowed_options.add( surfacing.NO_ENGULFING_OVERLAP_OPTION );
600 allowed_options.add( surfacing.DOMAIN_COUNT_SORT_OPTION );
601 allowed_options.add( surfacing.CUTOFF_SCORE_FILE_OPTION );
602 allowed_options.add( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION );
603 allowed_options.add( surfacing.OUTPUT_DIR_OPTION );
604 allowed_options.add( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION );
605 allowed_options.add( surfacing.PFAM_TO_GO_FILE_USE_OPTION );
606 allowed_options.add( surfacing.GO_OBO_FILE_USE_OPTION );
607 allowed_options.add( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION );
608 allowed_options.add( surfacing.GO_NAMESPACE_LIMIT_OPTION );
609 allowed_options.add( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
610 allowed_options.add( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION );
611 allowed_options.add( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS );
612 allowed_options.add( JACKNIFE_OPTION );
613 allowed_options.add( JACKNIFE_RANDOM_SEED_OPTION );
614 allowed_options.add( JACKNIFE_RATIO_OPTION );
615 allowed_options.add( INPUT_SPECIES_TREE_OPTION );
616 //allowed_options.add( INFER_SPECIES_TREES_OPTION );
617 allowed_options.add( FILTER_POSITIVE_OPTION );
618 allowed_options.add( FILTER_NEGATIVE_OPTION );
619 allowed_options.add( INPUT_FILES_FROM_FILE_OPTION );
620 allowed_options.add( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
621 allowed_options.add( FILTER_NEGATIVE_DOMAINS_OPTION );
622 allowed_options.add( IGNORE_VIRAL_IDS );
623 allowed_options.add( SEQ_EXTRACT_OPTION );
624 allowed_options.add( SECONDARY_FEATURES_PARSIMONY_MAP_FILE );
625 allowed_options.add( PLUS_MINUS_ANALYSIS_OPTION );
626 allowed_options.add( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS );
627 allowed_options.add( OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS );
628 allowed_options.add( CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY );
629 boolean ignore_dufs = surfacing.IGNORE_DUFS_DEFAULT;
630 boolean ignore_combination_with_same = surfacing.IGNORE_COMBINATION_WITH_SAME_DEFAULLT;
631 double e_value_max = surfacing.MAX_E_VALUE_DEFAULT;
632 int max_allowed_overlap = surfacing.MAX_ALLOWED_OVERLAP_DEFAULT;
633 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
634 if ( dissallowed_options.length() > 0 ) {
635 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown option(s): " + dissallowed_options );
637 boolean output_binary_domain_combinationsfor_graph_analysis = false;
638 if ( cla.isOptionSet( DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS ) ) {
639 output_binary_domain_combinationsfor_graph_analysis = true;
641 if ( cla.isOptionSet( surfacing.MAX_E_VALUE_OPTION ) ) {
643 e_value_max = cla.getOptionValueAsDouble( surfacing.MAX_E_VALUE_OPTION );
645 catch ( final Exception e ) {
646 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for E-value maximum" );
649 if ( cla.isOptionSet( surfacing.MAX_ALLOWED_OVERLAP_OPTION ) ) {
651 max_allowed_overlap = cla.getOptionValueAsInt( surfacing.MAX_ALLOWED_OVERLAP_OPTION );
653 catch ( final Exception e ) {
654 ForesterUtil.fatalError( surfacing.PRG_NAME, "no acceptable value for maximal allowed domain overlap" );
657 boolean no_engulfing_overlaps = false;
658 if ( cla.isOptionSet( surfacing.NO_ENGULFING_OVERLAP_OPTION ) ) {
659 no_engulfing_overlaps = true;
661 boolean ignore_virus_like_ids = false;
662 if ( cla.isOptionSet( surfacing.IGNORE_VIRAL_IDS ) ) {
663 ignore_virus_like_ids = true;
665 if ( cla.isOptionSet( surfacing.NOT_IGNORE_DUFS_OPTION ) ) {
668 if ( cla.isOptionSet( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION ) ) {
669 ignore_combination_with_same = true;
671 boolean ignore_domains_without_combs_in_all_spec = IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_DEFAULT;
672 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION ) ) {
673 ignore_domains_without_combs_in_all_spec = true;
675 boolean ignore_species_specific_domains = IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION_DEFAULT;
676 if ( cla.isOptionSet( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION ) ) {
677 ignore_species_specific_domains = true;
679 File output_file = null;
680 if ( cla.isOptionSet( surfacing.OUTPUT_FILE_OPTION ) ) {
681 if ( !cla.isOptionValueSet( surfacing.OUTPUT_FILE_OPTION ) ) {
682 ForesterUtil.fatalError( surfacing.PRG_NAME,
683 "no value for domain combinations similarities output file: -"
684 + surfacing.OUTPUT_FILE_OPTION + "=<file>" );
686 output_file = new File( cla.getOptionValue( surfacing.OUTPUT_FILE_OPTION ) );
687 SurfacingUtil.checkForOutputFileWriteability( output_file );
689 File cutoff_scores_file = null;
690 Map<String, Double> individual_score_cutoffs = null;
691 if ( cla.isOptionSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
692 if ( !cla.isOptionValueSet( surfacing.CUTOFF_SCORE_FILE_OPTION ) ) {
693 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for individual domain score cutoffs file: -"
694 + surfacing.CUTOFF_SCORE_FILE_OPTION + "=<file>" );
696 cutoff_scores_file = new File( cla.getOptionValue( surfacing.CUTOFF_SCORE_FILE_OPTION ) );
697 final String error = ForesterUtil.isReadableFile( cutoff_scores_file );
698 if ( !ForesterUtil.isEmpty( error ) ) {
699 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read individual domain score cutoffs file: "
703 final BasicTable<String> scores_table = BasicTableParser.parse( cutoff_scores_file, " " );
704 individual_score_cutoffs = scores_table.getColumnsAsMapDouble( 0, 1 );
706 catch ( final IOException e ) {
707 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from individual score cutoffs file: " + e );
710 BinaryDomainCombination.DomainCombinationType dc_type = BinaryDomainCombination.DomainCombinationType.BASIC;
711 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS ) ) {
712 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED;
714 if ( cla.isOptionSet( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY ) ) {
715 dc_type = BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT;
718 if ( cla.isOptionSet( surfacing.OUTPUT_DIR_OPTION ) ) {
719 if ( !cla.isOptionValueSet( surfacing.OUTPUT_DIR_OPTION ) ) {
720 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for output directory: -"
721 + surfacing.OUTPUT_DIR_OPTION + "=<dir>" );
723 out_dir = new File( cla.getOptionValue( surfacing.OUTPUT_DIR_OPTION ) );
724 if ( out_dir.exists() && ( out_dir.listFiles().length > 0 ) ) {
725 ForesterUtil.fatalError( surfacing.PRG_NAME, "\"" + out_dir + "\" aready exists and is not empty" );
727 if ( !out_dir.exists() ) {
728 final boolean success = out_dir.mkdir();
729 if ( !success || !out_dir.exists() ) {
730 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to create \"" + out_dir + "\"" );
733 if ( !out_dir.canWrite() ) {
734 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot write to \"" + out_dir + "\"" );
737 File positive_filter_file = null;
738 File negative_filter_file = null;
739 File negative_domains_filter_file = null;
740 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) && cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
741 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use both negative and positive protein filter" );
743 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION )
744 && ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) || cla
745 .isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) ) {
747 .fatalError( surfacing.PRG_NAME,
748 "attempt to use both negative or positive protein filter together wirh a negative domains filter" );
750 if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
751 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_OPTION ) ) {
752 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative filter: -"
753 + surfacing.FILTER_NEGATIVE_OPTION + "=<file>" );
755 negative_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_OPTION ) );
756 final String msg = ForesterUtil.isReadableFile( negative_filter_file );
757 if ( !ForesterUtil.isEmpty( msg ) ) {
758 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_filter_file + "\": "
762 else if ( cla.isOptionSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
763 if ( !cla.isOptionValueSet( surfacing.FILTER_POSITIVE_OPTION ) ) {
764 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for positive filter: -"
765 + surfacing.FILTER_POSITIVE_OPTION + "=<file>" );
767 positive_filter_file = new File( cla.getOptionValue( surfacing.FILTER_POSITIVE_OPTION ) );
768 final String msg = ForesterUtil.isReadableFile( positive_filter_file );
769 if ( !ForesterUtil.isEmpty( msg ) ) {
770 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + positive_filter_file + "\": "
774 else if ( cla.isOptionSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
775 if ( !cla.isOptionValueSet( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) ) {
776 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for negative domains filter: -"
777 + surfacing.FILTER_NEGATIVE_DOMAINS_OPTION + "=<file>" );
779 negative_domains_filter_file = new File( cla.getOptionValue( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION ) );
780 final String msg = ForesterUtil.isReadableFile( negative_domains_filter_file );
781 if ( !ForesterUtil.isEmpty( msg ) ) {
782 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + negative_domains_filter_file
786 final List<String> plus_minus_analysis_high_copy_base_species = new ArrayList<String>();
787 final List<String> plus_minus_analysis_high_copy_target_species = new ArrayList<String>();
788 final List<String> plus_minus_analysis_high_low_copy_species = new ArrayList<String>();
789 final List<Object> plus_minus_analysis_numbers = new ArrayList<Object>();
790 processPlusMinusAnalysisOption( cla,
791 plus_minus_analysis_high_copy_base_species,
792 plus_minus_analysis_high_copy_target_species,
793 plus_minus_analysis_high_low_copy_species,
794 plus_minus_analysis_numbers );
795 File input_files_file = null;
796 String[] input_file_names_from_file = null;
797 if ( cla.isOptionSet( surfacing.INPUT_FILES_FROM_FILE_OPTION ) ) {
798 if ( !cla.isOptionValueSet( surfacing.INPUT_FILES_FROM_FILE_OPTION ) ) {
799 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input files file: -"
800 + surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>" );
802 input_files_file = new File( cla.getOptionValue( surfacing.INPUT_FILES_FROM_FILE_OPTION ) );
803 final String msg = ForesterUtil.isReadableFile( input_files_file );
804 if ( !ForesterUtil.isEmpty( msg ) ) {
805 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + input_files_file + "\": " + msg );
808 input_file_names_from_file = ForesterUtil.file2array( input_files_file );
810 catch ( final IOException e ) {
811 ForesterUtil.fatalError( surfacing.PRG_NAME, "failed to read from \"" + input_files_file + "\": " + e );
814 if ( ( cla.getNumberOfNames() < 1 )
815 && ( ( input_file_names_from_file == null ) || ( input_file_names_from_file.length < 1 ) ) ) {
816 ForesterUtil.fatalError( surfacing.PRG_NAME,
817 "No hmmpfam output file indicated is input: use comand line directly or "
818 + surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>" );
820 DomainSimilarity.DomainSimilarityScoring scoring = SCORING_DEFAULT;
821 if ( cla.isOptionSet( surfacing.SCORING_OPTION ) ) {
822 if ( !cla.isOptionValueSet( surfacing.SCORING_OPTION ) ) {
823 ForesterUtil.fatalError( surfacing.PRG_NAME,
824 "no value for scoring method for domain combinations similarity calculation: -"
825 + surfacing.SCORING_OPTION + "=<"
826 + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
827 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|"
828 + surfacing.SCORING_COMBINATION_BASED + ">\"" );
830 final String scoring_str = cla.getOptionValue( surfacing.SCORING_OPTION );
831 if ( scoring_str.equals( surfacing.SCORING_DOMAIN_COUNT_BASED ) ) {
832 scoring = DomainSimilarity.DomainSimilarityScoring.DOMAINS;
834 else if ( scoring_str.equals( surfacing.SCORING_COMBINATION_BASED ) ) {
835 scoring = DomainSimilarity.DomainSimilarityScoring.COMBINATIONS;
837 else if ( scoring_str.equals( surfacing.SCORING_PROTEIN_COUNT_BASED ) ) {
838 scoring = DomainSimilarity.DomainSimilarityScoring.PROTEINS;
841 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + scoring_str
842 + "\" for scoring method for domain combinations similarity calculation: \"-"
843 + surfacing.SCORING_OPTION + "=<" + surfacing.SCORING_DOMAIN_COUNT_BASED + "|"
844 + surfacing.SCORING_PROTEIN_COUNT_BASED + "|" + surfacing.SCORING_COMBINATION_BASED + ">\"" );
847 boolean sort_by_species_count_first = false;
848 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION ) ) {
849 sort_by_species_count_first = true;
851 boolean species_matrix = false;
852 if ( cla.isOptionSet( surfacing.SPECIES_MATRIX_OPTION ) ) {
853 species_matrix = true;
855 boolean output_protein_lists_for_all_domains = false;
856 if ( cla.isOptionSet( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS ) ) {
857 output_protein_lists_for_all_domains = true;
859 Detailedness detailedness = DETAILEDNESS_DEFAULT;
860 if ( cla.isOptionSet( surfacing.DETAILEDNESS_OPTION ) ) {
861 if ( !cla.isOptionValueSet( surfacing.DETAILEDNESS_OPTION ) ) {
862 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for -" + surfacing.DETAILEDNESS_OPTION + "=<"
863 + surfacing.DETAILEDNESS_BASIC + "|" + surfacing.DETAILEDNESS_LIST_IDS + "|"
864 + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
866 final String detness = cla.getOptionValue( surfacing.DETAILEDNESS_OPTION ).toLowerCase();
867 if ( detness.equals( surfacing.DETAILEDNESS_BASIC ) ) {
868 detailedness = DomainSimilarityCalculator.Detailedness.BASIC;
870 else if ( detness.equals( surfacing.DETAILEDNESS_LIST_IDS ) ) {
871 detailedness = DomainSimilarityCalculator.Detailedness.LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES;
873 else if ( detness.equals( surfacing.DETAILEDNESS_PUNCTILIOUS ) ) {
874 detailedness = DomainSimilarityCalculator.Detailedness.PUNCTILIOUS;
877 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + detness + "\" for detailedness: \"-"
878 + surfacing.DETAILEDNESS_OPTION + "=<" + surfacing.DETAILEDNESS_BASIC + "|"
879 + surfacing.DETAILEDNESS_LIST_IDS + "|" + surfacing.DETAILEDNESS_PUNCTILIOUS + ">\"" );
882 String automated_pairwise_comparison_suffix = null;
883 boolean perform_pwc = false;
884 boolean write_pwc_files = false;
885 if ( cla.isOptionSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
887 if ( !cla.isOptionValueSet( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION ) ) {
888 write_pwc_files = false;
891 write_pwc_files = true;
892 automated_pairwise_comparison_suffix = "_"
893 + cla.getOptionValue( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION );
896 String query_domain_ids = null;
897 if ( cla.isOptionSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
898 if ( !cla.isOptionValueSet( surfacing.SEQ_EXTRACT_OPTION ) ) {
900 .fatalError( surfacing.PRG_NAME,
901 "no domain ids given for sequences with given domains to be extracted : -"
902 + surfacing.SEQ_EXTRACT_OPTION
903 + "=<ordered domain sequences, domain ids separated by '~', sequences separated by '#'>" );
905 query_domain_ids = cla.getOptionValue( surfacing.SEQ_EXTRACT_OPTION );
907 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field = DOMAIN_SORT_FILD_DEFAULT;
908 DomainSimilarity.DomainSimilaritySortField domain_similarity_sort_field_for_automated_pwc = DOMAIN_SORT_FILD_DEFAULT;
909 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
910 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ) ) {
911 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for domain combinations similarities sorting: -"
912 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
913 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
914 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
915 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
916 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|"
917 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
920 final String sort_str = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_SORT_OPTION ).toLowerCase();
921 if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ALPHA ) ) {
922 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
923 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
925 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MAX ) ) {
926 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX;
927 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
929 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MIN ) ) {
930 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MIN;
931 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
933 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_MEAN ) ) {
934 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MEAN;
935 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MEAN;
937 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT ) ) {
938 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SPECIES_COUNT;
939 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
941 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_SD ) ) {
942 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.SD;
943 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.DOMAIN_ID;
945 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_DIFF ) ) {
946 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
947 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_DIFFERENCE;
949 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF ) ) {
950 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
951 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
953 else if ( sort_str.equals( surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF ) ) {
954 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
955 domain_similarity_sort_field_for_automated_pwc = DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE;
958 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort_str
959 + "\" for domain combinations similarities sorting: \"-"
960 + surfacing.DOMAIN_SIMILARITY_SORT_OPTION + "=<" + surfacing.DOMAIN_SIMILARITY_SORT_ALPHA + "|"
961 + surfacing.DOMAIN_SIMILARITY_SORT_MAX + "|" + surfacing.DOMAIN_SIMILARITY_SORT_MIN + "|"
962 + surfacing.DOMAIN_SIMILARITY_SORT_MEAN + "|" + surfacing.DOMAIN_SIMILARITY_SORT_DIFF + "|"
963 + surfacing.DOMAIN_SIMILARITY_SORT_ABS_COUNTS_DIFF + "|"
964 + surfacing.DOMAIN_SIMILARITY_SORT_COUNTS_DIFF + "|" + "|"
965 + surfacing.DOMAIN_SIMILARITY_SORT_SPECIES_COUNT + "|" + surfacing.DOMAIN_SIMILARITY_SORT_SD
969 PrintableDomainSimilarity.PRINT_OPTION domain_similarity_print_option = DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT;
970 if ( cla.isOptionSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
971 if ( !cla.isOptionValueSet( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ) ) {
972 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for print option: -"
973 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
974 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
975 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
977 final String sort = cla.getOptionValue( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION ).toLowerCase();
978 if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML ) ) {
979 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.HTML;
981 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML ) ) {
982 // domain_similarity_print_option =
983 // DomainSimilarity.PRINT_OPTION.SIMPLE_HTML;
984 ForesterUtil.fatalError( surfacing.PRG_NAME, "simple HTML output not implemented yet :(" );
986 else if ( sort.equals( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED ) ) {
987 domain_similarity_print_option = PrintableDomainSimilarity.PRINT_OPTION.SIMPLE_TAB_DELIMITED;
990 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort + "\" for print option: -"
991 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_DETAILED_HTML + "|"
992 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_HTML + "|"
993 + surfacing.DOMAIN_SIMILARITY_PRINT_OPTION_SIMPLE_TAB_DELIMITED + ">\"" );
996 GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder dc_sort_order = DOMAINS_SORT_ORDER_DEFAULT;
997 if ( cla.isOptionSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
998 if ( !cla.isOptionValueSet( surfacing.DOMAIN_COUNT_SORT_OPTION ) ) {
999 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for sorting of domain counts: -"
1000 + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<" + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|"
1001 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1002 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1003 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1005 final String sort = cla.getOptionValue( surfacing.DOMAIN_COUNT_SORT_OPTION ).toLowerCase();
1006 if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_ALPHA ) ) {
1007 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.ALPHABETICAL_KEY_ID;
1009 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT ) ) {
1010 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_COUNT;
1012 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT ) ) {
1013 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.KEY_DOMAIN_PROTEINS_COUNT;
1015 else if ( sort.equals( surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT ) ) {
1016 dc_sort_order = GenomeWideCombinableDomains.GenomeWideCombinableDomainsSortOrder.COMBINATIONS_COUNT;
1019 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + sort
1020 + "\" for sorting of domain counts: \"-" + surfacing.DOMAIN_COUNT_SORT_OPTION + "=<"
1021 + surfacing.DOMAIN_COUNT_SORT_ALPHA + "|" + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_COUNT + "|"
1022 + surfacing.DOMAIN_COUNT_SORT_KEY_DOMAIN_PROTEINS_COUNT + "|"
1023 + surfacing.DOMAIN_COUNT_SORT_COMBINATIONS_COUNT + ">\"" );
1026 String[][] input_file_properties = null;
1027 if ( input_file_names_from_file != null ) {
1028 input_file_properties = surfacing.processInputFileNames( input_file_names_from_file );
1031 input_file_properties = surfacing.processInputFileNames( cla.getNames() );
1033 final int number_of_genomes = input_file_properties.length;
1034 if ( number_of_genomes < 2 ) {
1035 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot analyze less than two files" );
1037 if ( ( number_of_genomes < 3 ) && perform_pwc ) {
1038 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use : -"
1039 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1040 + "=<suffix> to turn on pairwise analyses with less than three input files" );
1042 checkWriteabilityForPairwiseComparisons( domain_similarity_print_option,
1043 input_file_properties,
1044 automated_pairwise_comparison_suffix,
1046 for( int i = 0; i < number_of_genomes; i++ ) {
1047 File dcc_outfile = new File( input_file_properties[ i ][ 0 ]
1048 + surfacing.DOMAIN_COMBINITON_COUNTS_OUTPUTFILE_SUFFIX );
1049 if ( out_dir != null ) {
1050 dcc_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + dcc_outfile );
1052 SurfacingUtil.checkForOutputFileWriteability( dcc_outfile );
1054 File pfam_to_go_file = null;
1055 Map<DomainId, List<GoId>> domain_id_to_go_ids_map = null;
1056 int domain_id_to_go_ids_count = 0;
1057 if ( cla.isOptionSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1058 if ( !cla.isOptionValueSet( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) ) {
1059 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for Pfam to GO mapping file: -"
1060 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>" );
1062 pfam_to_go_file = new File( cla.getOptionValue( surfacing.PFAM_TO_GO_FILE_USE_OPTION ) );
1063 final String error = ForesterUtil.isReadableFile( pfam_to_go_file );
1064 if ( !ForesterUtil.isEmpty( error ) ) {
1065 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read Pfam to GO mapping file: " + error );
1068 final PfamToGoParser parser = new PfamToGoParser( pfam_to_go_file );
1069 final List<PfamToGoMapping> pfam_to_go_mappings = parser.parse();
1070 domain_id_to_go_ids_map = SurfacingUtil.createDomainIdToGoIdMap( pfam_to_go_mappings );
1071 if ( parser.getMappingCount() < domain_id_to_go_ids_map.size() ) {
1072 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME,
1073 "parser.getMappingCount() < domain_id_to_go_ids_map.size()" );
1075 domain_id_to_go_ids_count = parser.getMappingCount();
1077 catch ( final IOException e ) {
1078 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from Pfam to GO mapping file: " + e );
1081 File go_obo_file = null;
1082 List<GoTerm> go_terms = null;
1083 if ( cla.isOptionSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1084 if ( !cla.isOptionValueSet( surfacing.GO_OBO_FILE_USE_OPTION ) ) {
1085 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO OBO file: -"
1086 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>" );
1088 if ( ( domain_id_to_go_ids_map == null ) || ( domain_id_to_go_ids_map.size() < 1 ) ) {
1089 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO OBO file (-"
1090 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>) without Pfam to GO mapping file ("
1091 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1093 go_obo_file = new File( cla.getOptionValue( surfacing.GO_OBO_FILE_USE_OPTION ) );
1094 final String error = ForesterUtil.isReadableFile( go_obo_file );
1095 if ( !ForesterUtil.isEmpty( error ) ) {
1096 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read GO OBO file: " + error );
1099 final OBOparser parser = new OBOparser( go_obo_file, OBOparser.ReturnType.BASIC_GO_TERM );
1100 go_terms = parser.parse();
1101 if ( parser.getGoTermCount() != go_terms.size() ) {
1103 .unexpectedFatalError( surfacing.PRG_NAME, "parser.getGoTermCount() != go_terms.size()" );
1106 catch ( final IOException e ) {
1107 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read from GO OBO file: " + e );
1110 Map<GoId, GoTerm> go_id_to_term_map = null;
1111 if ( ( ( domain_id_to_go_ids_map != null ) && ( domain_id_to_go_ids_map.size() > 0 ) )
1112 && ( ( go_terms != null ) && ( go_terms.size() > 0 ) ) ) {
1113 go_id_to_term_map = GoUtils.createGoIdToGoTermMap( go_terms );
1115 GoNameSpace go_namespace_limit = null;
1116 if ( cla.isOptionSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1117 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1118 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use GO namespace limit (-"
1119 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<namespace>) without Pfam to GO mapping file ("
1120 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>) and GO OBO file (-"
1121 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1123 if ( !cla.isOptionValueSet( surfacing.GO_NAMESPACE_LIMIT_OPTION ) ) {
1124 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for GO namespace limit: \"-"
1125 + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1126 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1127 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1128 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1130 final String go_namespace_limit_str = cla.getOptionValue( surfacing.GO_NAMESPACE_LIMIT_OPTION )
1132 if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION ) ) {
1133 go_namespace_limit = GoNameSpace.createMolecularFunction();
1135 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS ) ) {
1136 go_namespace_limit = GoNameSpace.createBiologicalProcess();
1138 else if ( go_namespace_limit_str.equals( surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT ) ) {
1139 go_namespace_limit = GoNameSpace.createCellularComponent();
1142 ForesterUtil.fatalError( surfacing.PRG_NAME, "unknown value \"" + go_namespace_limit_str
1143 + "\" for GO namespace limit: \"-" + surfacing.GO_NAMESPACE_LIMIT_OPTION + "=<"
1144 + surfacing.GO_NAMESPACE_LIMIT_OPTION_MOLECULAR_FUNCTION + "|"
1145 + surfacing.GO_NAMESPACE_LIMIT_OPTION_BIOLOGICAL_PROCESS + "|"
1146 + surfacing.GO_NAMESPACE_LIMIT_OPTION_CELLULAR_COMPONENT + ">\"" );
1149 if ( ( domain_similarity_sort_field == DomainSimilarity.DomainSimilaritySortField.MAX_COUNTS_DIFFERENCE )
1150 && ( number_of_genomes > 2 ) ) {
1151 domain_similarity_sort_field = DomainSimilarity.DomainSimilaritySortField.ABS_MAX_COUNTS_DIFFERENCE;
1153 boolean jacknifed_distances = false;
1154 int jacknife_resamplings = JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT;
1155 double jacknife_ratio = JACKNIFE_RATIO_DEFAULT;
1156 long random_seed = JACKNIFE_RANDOM_SEED_DEFAULT;
1157 if ( cla.isOptionSet( surfacing.JACKNIFE_OPTION ) ) {
1158 if ( ( number_of_genomes < 3 ) || !perform_pwc ) {
1159 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot use jacknife resampling analysis (-"
1160 + surfacing.JACKNIFE_OPTION + "[=<number of resamplings>]) without pairwise analyses ("
1161 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1162 + "=<suffix for pairwise comparison output files>)" );
1164 jacknifed_distances = true;
1165 if ( cla.isOptionHasAValue( surfacing.JACKNIFE_OPTION ) ) {
1167 jacknife_resamplings = cla.getOptionValueAsInt( surfacing.JACKNIFE_OPTION );
1169 catch ( final IOException e ) {
1170 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for number of resamplings" );
1172 if ( jacknife_resamplings < 2 ) {
1173 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use less than 2 resamplings" );
1176 if ( cla.isOptionSet( surfacing.JACKNIFE_RATIO_OPTION )
1177 && cla.isOptionHasAValue( surfacing.JACKNIFE_RATIO_OPTION ) ) {
1179 jacknife_ratio = cla.getOptionValueAsDouble( surfacing.JACKNIFE_RATIO_OPTION );
1181 catch ( final IOException e ) {
1182 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for jacknife ratio" );
1184 if ( ( jacknife_ratio <= 0.0 ) || ( jacknife_ratio >= 1.0 ) ) {
1185 ForesterUtil.fatalError( surfacing.PRG_NAME, "attempt to use illegal value for jacknife ratio: "
1189 if ( cla.isOptionSet( surfacing.JACKNIFE_RANDOM_SEED_OPTION )
1190 && cla.isOptionHasAValue( surfacing.JACKNIFE_RANDOM_SEED_OPTION ) ) {
1192 random_seed = cla.getOptionValueAsLong( surfacing.JACKNIFE_RANDOM_SEED_OPTION );
1194 catch ( final IOException e ) {
1195 ForesterUtil.fatalError( surfacing.PRG_NAME, "illegal format for random generator seed" );
1199 // boolean infer_species_trees = false;
1200 // if ( cla.isOptionSet( surfacing.INFER_SPECIES_TREES_OPTION ) ) {
1201 // if ( ( output_file == null ) || ( number_of_genomes < 3 )
1202 // || ForesterUtil.isEmpty( automated_pairwise_comparison_suffix ) ) {
1203 // ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer species trees (-"
1204 // + surfacing.INFER_SPECIES_TREES_OPTION + " without pairwise analyses ("
1205 // + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1206 // + "=<suffix for pairwise comparison output files>)" );
1208 // infer_species_trees = true;
1210 File[] intree_files = null;
1211 Phylogeny[] intrees = null;
1212 if ( cla.isOptionSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1213 // TODO FIXME if jacknife.... maybe not
1214 if ( number_of_genomes < 3 ) {
1215 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot infer gains and losses on input species trees (-"
1216 + surfacing.INPUT_SPECIES_TREE_OPTION + " without pairwise analyses ("
1217 + surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
1218 + "=<suffix for pairwise comparison output files>)" );
1220 if ( !cla.isOptionValueSet( surfacing.INPUT_SPECIES_TREE_OPTION ) ) {
1221 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for input tree: -"
1222 + surfacing.INPUT_SPECIES_TREE_OPTION + "=<tree file in phyloXML format>" );
1224 final String intrees_str = cla.getOptionValue( surfacing.INPUT_SPECIES_TREE_OPTION );
1225 if ( intrees_str.indexOf( "#" ) > 0 ) {
1226 final String[] intrees_strs = intrees_str.split( "#" );
1227 intree_files = new File[ intrees_strs.length ];
1229 for( final String s : intrees_strs ) {
1230 intree_files[ i++ ] = new File( s.trim() );
1234 intree_files = new File[ 1 ];
1235 intree_files[ 0 ] = new File( intrees_str );
1237 intrees = getIntrees( intree_files, number_of_genomes, input_file_properties );
1239 long random_number_seed_for_fitch_parsimony = 0l;
1240 boolean radomize_fitch_parsimony = false;
1241 if ( cla.isOptionSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1242 if ( !cla.isOptionValueSet( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION ) ) {
1243 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for random number seed: -"
1244 + surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION + "=<seed>" );
1247 random_number_seed_for_fitch_parsimony = cla
1248 .getOptionValueAsLong( RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION );
1250 catch ( final IOException e ) {
1251 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1253 radomize_fitch_parsimony = true;
1255 SortedSet<DomainId> filter = null;
1256 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1257 || ( negative_domains_filter_file != null ) ) {
1258 filter = new TreeSet<DomainId>();
1259 if ( positive_filter_file != null ) {
1260 processFilter( positive_filter_file, filter );
1262 else if ( negative_filter_file != null ) {
1263 processFilter( negative_filter_file, filter );
1265 else if ( negative_domains_filter_file != null ) {
1266 processFilter( negative_domains_filter_file, filter );
1269 Map<DomainId, Set<String>>[] domain_id_to_secondary_features_maps = null;
1270 File[] secondary_features_map_files = null;
1271 final File domain_lengths_analysis_outfile = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1272 + DOMAIN_LENGTHS_ANALYSIS_SUFFIX );
1273 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
1274 SurfacingUtil.checkForOutputFileWriteability( domain_lengths_analysis_outfile );
1276 if ( cla.isOptionSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1277 if ( !cla.isOptionValueSet( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ) ) {
1278 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for secondary features map file: -"
1279 + surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE + "=<file>" );
1281 final String[] secondary_features_map_files_strs = cla
1282 .getOptionValue( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE ).split( "#" );
1283 secondary_features_map_files = new File[ secondary_features_map_files_strs.length ];
1284 domain_id_to_secondary_features_maps = new Map[ secondary_features_map_files_strs.length ];
1286 for( final String secondary_features_map_files_str : secondary_features_map_files_strs ) {
1287 secondary_features_map_files[ i ] = new File( secondary_features_map_files_str );
1288 final String error = ForesterUtil.isReadableFile( secondary_features_map_files[ i ] );
1289 if ( !ForesterUtil.isEmpty( error ) ) {
1290 ForesterUtil.fatalError( surfacing.PRG_NAME, "cannot read secondary features map file: " + error );
1293 domain_id_to_secondary_features_maps[ i ] = SurfacingUtil
1294 .createDomainIdToSecondaryFeaturesMap( secondary_features_map_files[ i ] );
1296 catch ( final IOException e ) {
1297 ForesterUtil.fatalError( surfacing.PRG_NAME,
1298 "cannot read secondary features map file: " + e.getMessage() );
1300 catch ( final Exception e ) {
1301 ForesterUtil.fatalError( surfacing.PRG_NAME, "problem with contents of features map file ["
1302 + secondary_features_map_files[ i ] + "]: " + e.getMessage() );
1307 if ( out_dir == null ) {
1308 ForesterUtil.fatalError( surfacing.PRG_NAME, "no output directory indicated (-"
1309 + surfacing.OUTPUT_DIR_OPTION + "=<dir>)" );
1311 if ( output_file == null ) {
1312 ForesterUtil.fatalError( surfacing.PRG_NAME, "no name for (main) output file indicated (-"
1313 + surfacing.OUTPUT_FILE_OPTION + "=<file>)" );
1315 if ( ( domain_id_to_go_ids_map == null ) || domain_id_to_go_ids_map.isEmpty() ) {
1316 ForesterUtil.fatalError( surfacing.PRG_NAME,
1317 "no (acceptable) Pfam to GO id mapping file provided ('pfam2go file') (-"
1318 + surfacing.PFAM_TO_GO_FILE_USE_OPTION + "=<file>)" );
1320 if ( ( go_id_to_term_map == null ) || go_id_to_term_map.isEmpty() ) {
1321 ForesterUtil.fatalError( surfacing.PRG_NAME,
1322 "no (acceptable) go id to term mapping file provided ('GO OBO file') (-"
1323 + surfacing.GO_OBO_FILE_USE_OPTION + "=<file>)" );
1325 System.out.println( "Output directory : " + out_dir );
1326 if ( input_file_names_from_file != null ) {
1327 System.out.println( "Input files names from : " + input_files_file + " ["
1328 + input_file_names_from_file.length + " input files]" );
1329 html_desc.append( "<tr><td>Input files names from:</td><td>" + input_files_file + " ["
1330 + input_file_names_from_file.length + " input files]</td></tr>" + nl );
1332 if ( positive_filter_file != null ) {
1333 final int filter_size = filter.size();
1334 System.out.println( "Positive protein filter : " + positive_filter_file + " [" + filter_size
1336 html_desc.append( "<tr><td>Positive protein filter:</td><td>" + positive_filter_file + " [" + filter_size
1337 + " domain ids]</td></tr>" + nl );
1339 if ( negative_filter_file != null ) {
1340 final int filter_size = filter.size();
1341 System.out.println( "Negative protein filter : " + negative_filter_file + " [" + filter_size
1343 html_desc.append( "<tr><td>Negative protein filter:</td><td>" + negative_filter_file + " [" + filter_size
1344 + " domain ids]</td></tr>" + nl );
1346 if ( negative_domains_filter_file != null ) {
1347 final int filter_size = filter.size();
1348 System.out.println( "Negative domain filter : " + negative_domains_filter_file + " [" + filter_size
1350 html_desc.append( "<tr><td>Negative domain filter:</td><td>" + negative_domains_filter_file + " ["
1351 + filter_size + " domain ids]</td></tr>" + nl );
1353 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
1355 for( final String s : plus_minus_analysis_high_copy_base_species ) {
1356 plus0 += "+" + s + " ";
1359 for( final String s : plus_minus_analysis_high_copy_target_species ) {
1360 plus1 += "*" + s + " ";
1363 for( final String s : plus_minus_analysis_high_low_copy_species ) {
1364 minus += "-" + s + " ";
1366 System.out.println( "Plus-minus analysis : " + plus1 + "&& " + plus0 + "&& " + minus );
1367 html_desc.append( "<tr><td>Plus-minus analysis:</td><td>" + plus1 + "&& " + plus0 + "&& " + minus
1368 + "</td></tr>" + nl );
1370 if ( cutoff_scores_file != null ) {
1371 System.out.println( "Cutoff scores file : " + cutoff_scores_file );
1372 html_desc.append( "<tr><td>Cutoff scores file:</td><td>" + cutoff_scores_file + "</td></tr>" + nl );
1374 if ( e_value_max >= 0.0 ) {
1375 System.out.println( "E-value maximum (inclusive) : " + e_value_max );
1376 html_desc.append( "<tr><td>E-value maximum (inclusive):</td><td>" + e_value_max + "</td></tr>" + nl );
1378 System.out.println( "Ignore DUFs : " + ignore_dufs );
1379 if ( ignore_virus_like_ids ) {
1380 System.out.println( "Ignore virus like ids : " + ignore_virus_like_ids );
1381 html_desc.append( "<tr><td>Ignore virus, phage, transposition related ids:</td><td>"
1382 + ignore_virus_like_ids + "</td></tr>" + nl );
1384 html_desc.append( "<tr><td>Ignore DUFs:</td><td>" + ignore_dufs + "</td></tr>" + nl );
1385 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1386 System.out.println( "Max allowed domain overlap : " + max_allowed_overlap );
1387 html_desc.append( "<tr><td>Max allowed domain overlap:</td><td>" + max_allowed_overlap + "</td></tr>" + nl );
1389 if ( no_engulfing_overlaps ) {
1390 System.out.println( "Ignore engulfed domains : " + no_engulfing_overlaps );
1391 html_desc.append( "<tr><td>Ignore (lower confidence) engulfed domains:</td><td>" + no_engulfing_overlaps
1392 + "</td></tr>" + nl );
1394 System.out.println( "Ignore singlet domains : " + ignore_domains_without_combs_in_all_spec );
1396 .append( "<tr><td>Ignore singlet domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1397 + ignore_domains_without_combs_in_all_spec + "</td></tr>" + nl );
1398 System.out.println( "Ignore species specific doms: " + ignore_species_specific_domains );
1400 .append( "<tr><td>Ignore species specific domains for domain combination similarity analyses (not for parsimony analyses):</td><td>"
1401 + ignore_species_specific_domains + "</td></tr>" + nl );
1402 System.out.println( "Ignore combination with self: " + ignore_combination_with_same );
1403 html_desc.append( "<tr><td>Ignore combination with self for domain combination similarity analyses:</td><td>"
1404 + ignore_combination_with_same + "</td></tr>" + nl );
1406 System.out.println( "Consider directedness : "
1407 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) );
1408 html_desc.append( "<tr><td>Consider directedness of binary domain combinations:</td><td>"
1409 + ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) + "</td></tr>" + nl );
1410 if ( dc_type != BinaryDomainCombination.DomainCombinationType.BASIC ) {
1411 System.out.println( "Consider adjacency : "
1412 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) );
1413 html_desc.append( "<tr><td>Consider djacency of binary domain combinations:</td><td>"
1414 + ( dc_type == BinaryDomainCombination.DomainCombinationType.DIRECTED_ADJACTANT ) + "</td></tr>"
1417 System.out.print( "Domain counts sort order : " );
1418 switch ( dc_sort_order ) {
1419 case ALPHABETICAL_KEY_ID:
1420 System.out.println( "alphabetical" );
1422 case KEY_DOMAIN_COUNT:
1423 System.out.println( "domain count" );
1425 case KEY_DOMAIN_PROTEINS_COUNT:
1426 System.out.println( "domain proteins count" );
1428 case COMBINATIONS_COUNT:
1429 System.out.println( "domain combinations count" );
1432 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for dc sort order" );
1434 if ( domain_id_to_go_ids_map != null ) {
1435 System.out.println( "Pfam to GO mappings from : " + pfam_to_go_file + " [" + domain_id_to_go_ids_count
1437 html_desc.append( "<tr><td>Pfam to GO mappings from:</td><td>" + pfam_to_go_file + " ["
1438 + domain_id_to_go_ids_count + " mappings]" + "</td></tr>" + nl );
1440 if ( go_terms != null ) {
1441 System.out.println( "GO terms from : " + go_obo_file + " [" + go_terms.size() + " terms]" );
1442 html_desc.append( "<tr><td>GO terms from:</td><td>" + go_obo_file + " [" + go_terms.size() + " terms]"
1443 + "</td></tr>" + nl );
1445 if ( go_namespace_limit != null ) {
1446 System.out.println( "Limit GO terms to : " + go_namespace_limit.toString() );
1447 html_desc.append( "<tr><td>Limit GO terms to</td><td>" + go_namespace_limit + "</td></tr>" + nl );
1449 if ( perform_pwc ) {
1450 System.out.println( "Suffix for PWC files : " + automated_pairwise_comparison_suffix );
1451 html_desc.append( "<tr><td>Suffix for PWC files</td><td>" + automated_pairwise_comparison_suffix
1452 + "</td></tr>" + nl );
1454 if ( out_dir != null ) {
1455 System.out.println( "Output directory : " + out_dir );
1457 if ( query_domain_ids != null ) {
1458 System.out.println( "Query domains (ordered) : " + query_domain_ids );
1459 html_desc.append( "<tr><td></td><td>" + query_domain_ids + "</td></tr>" + nl );
1461 System.out.println( "Write similarities to : " + output_file );
1462 System.out.print( " Scoring method : " );
1463 html_desc.append( "<tr><td>Scoring method:</td><td>" );
1464 switch ( scoring ) {
1466 System.out.println( "domain combinations based" );
1467 html_desc.append( "domain combinations based" + "</td></tr>" + nl );
1470 System.out.println( "domain counts based" );
1471 html_desc.append( "domain counts based" + "</td></tr>" + nl );
1474 System.out.println( "domain proteins counts based" );
1475 html_desc.append( "domain proteins counts based" + "</td></tr>" + nl );
1478 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
1480 System.out.print( " Sort by : " );
1481 html_desc.append( "<tr><td>Sort by:</td><td>" );
1482 switch ( domain_similarity_sort_field ) {
1484 System.out.print( "score minimum" );
1485 html_desc.append( "score minimum" );
1488 System.out.print( "score maximum" );
1489 html_desc.append( "score maximum" );
1492 System.out.print( "score mean" );
1493 html_desc.append( "score mean" );
1496 System.out.print( "score standard deviation" );
1497 html_desc.append( "score standard deviation" );
1500 System.out.print( "species number" );
1501 html_desc.append( "species number" );
1504 System.out.print( "alphabetical domain identifier" );
1505 html_desc.append( "alphabetical domain identifier" );
1507 case MAX_DIFFERENCE:
1508 System.out.print( "(maximal) difference" );
1509 html_desc.append( "(maximal) difference" );
1511 case ABS_MAX_COUNTS_DIFFERENCE:
1512 System.out.print( "absolute (maximal) counts difference" );
1513 html_desc.append( "absolute (maximal) counts difference" );
1515 case MAX_COUNTS_DIFFERENCE:
1516 System.out.print( "(maximal) counts difference" );
1517 html_desc.append( "(maximal) counts difference" );
1520 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1522 if ( sort_by_species_count_first ) {
1523 System.out.println( " (sort by species count first)" );
1524 html_desc.append( " (sort by species count first)" );
1527 System.out.println();
1529 html_desc.append( "</td></tr>" + nl );
1530 System.out.print( " Detailedness : " );
1531 switch ( detailedness ) {
1533 System.out.println( "basic" );
1535 case LIST_COMBINING_DOMAIN_FOR_EACH_SPECIES:
1536 System.out.println( "list combining domains for each species" );
1539 System.out.println( "punctilious" );
1542 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for detailedness" );
1544 System.out.print( " Print option : " );
1545 switch ( domain_similarity_print_option ) {
1547 System.out.println( "HTML" );
1549 case SIMPLE_TAB_DELIMITED:
1550 System.out.println( "simple tab delimited" );
1553 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for print option" );
1555 System.out.print( " Species matrix : " + species_matrix );
1556 System.out.println();
1557 final File dc_data_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + DATA_FILE_SUFFIX );
1558 System.out.println( "Domain comb data output : " + dc_data_file );
1559 html_desc.append( "<tr><td>Domain combination data output:</td><td> " + dc_data_file + " </td></tr>" );
1560 System.out.println();
1561 if ( perform_pwc ) {
1562 System.out.println( "Pairwise comparisons: " );
1563 html_desc.append( "<tr><td>Pairwise comparisons:</td><td></td></tr>" );
1564 System.out.print( " Sort by : " );
1565 html_desc.append( "<tr><td>Sort by:</td><td>" );
1566 switch ( domain_similarity_sort_field_for_automated_pwc ) {
1568 System.out.print( "score mean" );
1569 html_desc.append( "score mean" );
1572 System.out.print( "alphabetical domain identifier" );
1573 html_desc.append( "alphabetical domain identifier" );
1575 case MAX_DIFFERENCE:
1576 System.out.print( "difference" );
1577 html_desc.append( "difference" );
1579 case ABS_MAX_COUNTS_DIFFERENCE:
1580 System.out.print( "absolute counts difference" );
1581 html_desc.append( "absolute counts difference" );
1583 case MAX_COUNTS_DIFFERENCE:
1584 System.out.print( "counts difference" );
1585 html_desc.append( "counts difference" );
1589 .unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for similarities" );
1591 System.out.println();
1592 html_desc.append( "</td></tr>" + nl );
1593 if ( jacknifed_distances ) {
1594 html_desc.append( "<tr><td>Jacknife:</td><td>" + jacknife_resamplings + " resamplings</td></tr>" + nl );
1595 html_desc.append( "<tr><td>Jacknife ratio:</td><td>" + ForesterUtil.round( jacknife_ratio, 2 )
1596 + "</td></tr>" + nl );
1597 html_desc.append( "<tr><td>Jacknife random number seed:</td><td>" + random_seed + "</td></tr>" + nl );
1598 System.out.println( " Jacknife : " + jacknife_resamplings + " resamplings" );
1599 System.out.println( " Ratio : " + ForesterUtil.round( jacknife_ratio, 2 ) );
1600 System.out.println( " Random number seed : " + random_seed );
1602 // if ( infer_species_trees ) {
1603 // html_desc.append( "<tr><td>Infer species trees:</td><td>true</td></tr>" + nl );
1604 // System.out.println( " Infer species trees : true" );
1606 if ( ( intrees != null ) && ( intrees.length > 0 ) ) {
1607 for( final File intree_file : intree_files ) {
1608 html_desc.append( "<tr><td>Intree for gain/loss parsimony analysis:</td><td>" + intree_file
1609 + "</td></tr>" + nl );
1610 System.out.println( " Intree for gain/loss pars.: " + intree_file );
1613 if ( radomize_fitch_parsimony ) {
1614 html_desc.append( "<tr><td> Random number seed for Fitch parsimony analysis:</td><td>"
1615 + random_number_seed_for_fitch_parsimony + "</td></tr>" + nl );
1616 System.out.println( " Random number seed : " + random_number_seed_for_fitch_parsimony );
1618 if ( ( domain_id_to_secondary_features_maps != null ) && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
1619 for( int i = 0; i < secondary_features_map_files.length; i++ ) {
1620 html_desc.append( "<tr><td>Secondary features map file:</td><td>"
1621 + secondary_features_map_files[ i ] + "</td></tr>" + nl );
1622 System.out.println( "Secondary features map file : " + secondary_features_map_files[ i ]
1623 + " [mappings for " + domain_id_to_secondary_features_maps[ i ].size() + " domain ids]" );
1625 System.out.println();
1626 System.out.println( "Domain ids to secondary features map:" );
1627 for( final DomainId domain_id : domain_id_to_secondary_features_maps[ i ].keySet() ) {
1628 System.out.print( domain_id.getId() );
1629 System.out.print( " => " );
1630 for( final String sec : domain_id_to_secondary_features_maps[ i ].get( domain_id ) ) {
1631 System.out.print( sec );
1632 System.out.print( " " );
1634 System.out.println();
1639 } // if ( perform_pwc ) {
1640 System.out.println();
1641 html_desc.append( "<tr><td>Command line:</td><td>\n" + cla.getCommandLineArgsAsString() + "\n</td></tr>" + nl );
1642 System.out.println( "Command line : " + cla.getCommandLineArgsAsString() );
1643 BufferedWriter[] query_domains_writer_ary = null;
1644 List<DomainId>[] query_domain_ids_array = null;
1645 if ( query_domain_ids != null ) {
1646 final String[] query_domain_ids_str_array = query_domain_ids.split( "#" );
1647 query_domain_ids_array = new ArrayList[ query_domain_ids_str_array.length ];
1648 query_domains_writer_ary = new BufferedWriter[ query_domain_ids_str_array.length ];
1649 for( int i = 0; i < query_domain_ids_str_array.length; i++ ) {
1650 String query_domain_ids_str = query_domain_ids_str_array[ i ];
1651 final String[] query_domain_ids_str_ary = query_domain_ids_str.split( "~" );
1652 final List<DomainId> query = new ArrayList<DomainId>();
1653 for( final String element : query_domain_ids_str_ary ) {
1654 query.add( new DomainId( element ) );
1656 query_domain_ids_array[ i ] = query;
1657 query_domain_ids_str = query_domain_ids_str.replace( '~', '_' );
1658 String protein_names_writer_str = query_domain_ids_str + surfacing.SEQ_EXTRACT_SUFFIX;
1659 if ( out_dir != null ) {
1660 protein_names_writer_str = out_dir + ForesterUtil.FILE_SEPARATOR + protein_names_writer_str;
1663 query_domains_writer_ary[ i ] = new BufferedWriter( new FileWriter( protein_names_writer_str ) );
1665 catch ( final IOException e ) {
1666 ForesterUtil.fatalError( surfacing.PRG_NAME, "Could not open [" + protein_names_writer_str + "]: "
1667 + e.getLocalizedMessage() );
1671 SortedMap<Species, List<Protein>> protein_lists_per_species = null; //This will only be created if neede.
1672 boolean need_protein_lists_per_species = false;
1673 if ( ( plus_minus_analysis_high_copy_base_species.size() > 0 ) || output_protein_lists_for_all_domains ) {
1674 need_protein_lists_per_species = true;
1676 if ( need_protein_lists_per_species ) {
1677 protein_lists_per_species = new TreeMap<Species, List<Protein>>();
1679 final List<GenomeWideCombinableDomains> gwcd_list = new ArrayList<GenomeWideCombinableDomains>( number_of_genomes );
1680 final SortedSet<DomainId> all_domains_encountered = new TreeSet<DomainId>();
1681 final SortedSet<BinaryDomainCombination> all_bin_domain_combinations_encountered = new TreeSet<BinaryDomainCombination>();
1682 List<BinaryDomainCombination> all_bin_domain_combinations_gained_fitch = null;
1683 List<BinaryDomainCombination> all_bin_domain_combinations_lost_fitch = null;
1684 if ( ( intrees != null ) && ( intrees.length == 1 ) ) {
1685 all_bin_domain_combinations_gained_fitch = new ArrayList<BinaryDomainCombination>();
1686 all_bin_domain_combinations_lost_fitch = new ArrayList<BinaryDomainCombination>();
1688 final DomainLengthsTable domain_lengths_table = new DomainLengthsTable();
1689 final File per_genome_domain_promiscuity_statistics_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR
1690 + output_file + D_PROMISCUITY_FILE_SUFFIX );
1691 BufferedWriter per_genome_domain_promiscuity_statistics_writer = null;
1693 per_genome_domain_promiscuity_statistics_writer = new BufferedWriter( new FileWriter( per_genome_domain_promiscuity_statistics_file ) );
1694 per_genome_domain_promiscuity_statistics_writer.write( "Species:\t" );
1695 per_genome_domain_promiscuity_statistics_writer.write( "Mean:\t" );
1696 per_genome_domain_promiscuity_statistics_writer.write( "SD:\t" );
1697 per_genome_domain_promiscuity_statistics_writer.write( "Median:\t" );
1698 per_genome_domain_promiscuity_statistics_writer.write( "Min:\t" );
1699 per_genome_domain_promiscuity_statistics_writer.write( "Max:\t" );
1700 per_genome_domain_promiscuity_statistics_writer.write( "N:\t" );
1701 per_genome_domain_promiscuity_statistics_writer.write( "Max Promiscuous Domains:"
1702 + ForesterUtil.LINE_SEPARATOR );
1704 catch ( final IOException e2 ) {
1705 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1707 final File log_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file + LOG_FILE_SUFFIX );
1708 BufferedWriter log_writer = null;
1710 log_writer = new BufferedWriter( new FileWriter( log_file ) );
1712 catch ( final IOException e2 ) {
1713 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1715 BufferedWriter dc_data_writer = null;
1717 dc_data_writer = new BufferedWriter( new FileWriter( dc_data_file ) );
1718 dc_data_writer.write( DATA_FILE_DESC );
1719 dc_data_writer.write( ForesterUtil.LINE_SEPARATOR );
1721 catch ( final IOException e2 ) {
1722 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getMessage() );
1724 final DescriptiveStatistics all_genomes_domains_per_potein_stats = new BasicDescriptiveStatistics();
1725 final SortedMap<Integer, Integer> all_genomes_domains_per_potein_histo = new TreeMap<Integer, Integer>();
1726 final SortedSet<String> domains_which_are_always_single = new TreeSet<String>();
1727 final SortedSet<String> domains_which_are_sometimes_single_sometimes_not = new TreeSet<String>();
1728 final SortedSet<String> domains_which_never_single = new TreeSet<String>();
1729 BufferedWriter domains_per_potein_stats_writer = null;
1731 domains_per_potein_stats_writer = new BufferedWriter( new FileWriter( out_dir + ForesterUtil.FILE_SEPARATOR
1732 + output_file + "__domains_per_potein_stats.txt" ) );
1733 domains_per_potein_stats_writer.write( "Genome" );
1734 domains_per_potein_stats_writer.write( "\t" );
1735 domains_per_potein_stats_writer.write( "Mean" );
1736 domains_per_potein_stats_writer.write( "\t" );
1737 domains_per_potein_stats_writer.write( "SD" );
1738 domains_per_potein_stats_writer.write( "\t" );
1739 domains_per_potein_stats_writer.write( "Median" );
1740 domains_per_potein_stats_writer.write( "\t" );
1741 domains_per_potein_stats_writer.write( "N" );
1742 domains_per_potein_stats_writer.write( "\t" );
1743 domains_per_potein_stats_writer.write( "Min" );
1744 domains_per_potein_stats_writer.write( "\t" );
1745 domains_per_potein_stats_writer.write( "Max" );
1746 domains_per_potein_stats_writer.write( "\n" );
1748 catch ( final IOException e3 ) {
1749 e3.printStackTrace();
1751 for( int i = 0; i < number_of_genomes; ++i ) {
1752 System.out.println();
1753 System.out.println( ( i + 1 ) + "/" + number_of_genomes );
1754 log( ( i + 1 ) + "/" + number_of_genomes, log_writer );
1755 System.out.println( "Processing : " + input_file_properties[ i ][ 0 ] );
1756 log( "Genome : " + input_file_properties[ i ][ 0 ], log_writer );
1757 HmmscanPerDomainTableParser parser = null;
1758 INDIVIDUAL_SCORE_CUTOFF ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF.NONE;
1759 if ( individual_score_cutoffs != null ) {
1760 ind_score_cutoff = INDIVIDUAL_SCORE_CUTOFF_DEFAULT;
1762 if ( ( positive_filter_file != null ) || ( negative_filter_file != null )
1763 || ( negative_domains_filter_file != null ) ) {
1764 HmmscanPerDomainTableParser.FilterType filter_type = HmmscanPerDomainTableParser.FilterType.NONE;
1765 if ( positive_filter_file != null ) {
1766 filter_type = HmmscanPerDomainTableParser.FilterType.POSITIVE_PROTEIN;
1768 else if ( negative_filter_file != null ) {
1769 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_PROTEIN;
1771 else if ( negative_domains_filter_file != null ) {
1772 filter_type = HmmscanPerDomainTableParser.FilterType.NEGATIVE_DOMAIN;
1774 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1775 input_file_properties[ i ][ 1 ],
1781 parser = new HmmscanPerDomainTableParser( new File( input_file_properties[ i ][ 0 ] ),
1782 input_file_properties[ i ][ 1 ],
1785 if ( e_value_max >= 0.0 ) {
1786 parser.setEValueMaximum( e_value_max );
1788 parser.setIgnoreDufs( ignore_dufs );
1789 parser.setIgnoreVirusLikeIds( ignore_virus_like_ids );
1790 parser.setIgnoreEngulfedDomains( no_engulfing_overlaps );
1791 if ( max_allowed_overlap != surfacing.MAX_ALLOWED_OVERLAP_DEFAULT ) {
1792 parser.setMaxAllowedOverlap( max_allowed_overlap );
1794 parser.setReturnType( HmmscanPerDomainTableParser.ReturnType.UNORDERED_PROTEIN_DOMAIN_COLLECTION_PER_PROTEIN );
1795 if ( individual_score_cutoffs != null ) {
1796 parser.setIndividualScoreCutoffs( individual_score_cutoffs );
1798 List<Protein> protein_list = null;
1800 protein_list = parser.parse();
1802 catch ( final IOException e ) {
1803 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
1805 catch ( final Exception e ) {
1806 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, e.getMessage(), e );
1809 System.out.println( "Domains ignored due to negative domain filter: " );
1810 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToNegativeDomainFilterCountsMap() );
1811 System.out.println( "Domains ignored due to virus like id: " );
1812 ForesterUtil.printCountingMap( parser.getDomainsIgnoredDueToVirusLikeIdCountsMap() );
1814 System.out.println( "Number of proteins encountered : " + parser.getProteinsEncountered() );
1815 log( "Number of proteins encountered : " + parser.getProteinsEncountered(), log_writer );
1816 System.out.println( "Number of proteins stored : " + protein_list.size() );
1817 log( "Number of proteins stored : " + protein_list.size(), log_writer );
1818 System.out.println( "Domains encountered : " + parser.getDomainsEncountered() );
1819 log( "Domains encountered : " + parser.getDomainsEncountered(), log_writer );
1820 System.out.println( "Domains stored : " + parser.getDomainsStored() );
1821 log( "Domains stored : " + parser.getDomainsStored(), log_writer );
1822 System.out.println( "Distinct domains stored : "
1823 + parser.getDomainsStoredSet().size() );
1824 log( "Distinct domains stored : " + parser.getDomainsStoredSet().size(), log_writer );
1825 System.out.println( "Domains ignored due to individual score cutoffs: "
1826 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() );
1827 log( "Domains ignored due to individual score cutoffs: "
1828 + parser.getDomainsIgnoredDueToIndividualScoreCutoff(),
1830 System.out.println( "Domains ignored due to E-value : "
1831 + parser.getDomainsIgnoredDueToEval() );
1832 log( "Domains ignored due to E-value : " + parser.getDomainsIgnoredDueToEval(), log_writer );
1833 System.out.println( "Domains ignored due to DUF designation : "
1834 + parser.getDomainsIgnoredDueToDuf() );
1835 log( "Domains ignored due to DUF designation : " + parser.getDomainsIgnoredDueToDuf(), log_writer );
1836 if ( ignore_virus_like_ids ) {
1837 System.out.println( "Domains ignored due virus like ids : "
1838 + parser.getDomainsIgnoredDueToVirusLikeIds() );
1839 log( "Domains ignored due virus like ids : " + parser.getDomainsIgnoredDueToVirusLikeIds(),
1842 System.out.println( "Domains ignored due negative domain filter : "
1843 + parser.getDomainsIgnoredDueToNegativeDomainFilter() );
1844 log( "Domains ignored due negative domain filter : "
1845 + parser.getDomainsIgnoredDueToNegativeDomainFilter(),
1847 System.out.println( "Domains ignored due to overlap : "
1848 + parser.getDomainsIgnoredDueToOverlap() );
1849 log( "Domains ignored due to overlap : " + parser.getDomainsIgnoredDueToOverlap(),
1851 if ( negative_filter_file != null ) {
1852 System.out.println( "Proteins ignored due to negative filter : "
1853 + parser.getProteinsIgnoredDueToFilter() );
1854 log( "Proteins ignored due to negative filter : " + parser.getProteinsIgnoredDueToFilter(),
1857 if ( positive_filter_file != null ) {
1858 System.out.println( "Proteins ignored due to positive filter : "
1859 + parser.getProteinsIgnoredDueToFilter() );
1860 log( "Proteins ignored due to positive filter : " + parser.getProteinsIgnoredDueToFilter(),
1863 System.out.println( "Time for processing : " + parser.getTime() + "ms" );
1864 log( "", log_writer );
1865 html_desc.append( "<tr><td>" + input_file_properties[ i ][ 0 ] + " [species: "
1866 + input_file_properties[ i ][ 1 ] + "]" + ":</td><td>domains analyzed: "
1867 + parser.getDomainsStored() + "; domains ignored: [ind score cutoffs: "
1868 + parser.getDomainsIgnoredDueToIndividualScoreCutoff() + "] [E-value cutoff: "
1869 + parser.getDomainsIgnoredDueToEval() + "] [DUF: " + parser.getDomainsIgnoredDueToDuf()
1870 + "] [virus like ids: " + parser.getDomainsIgnoredDueToVirusLikeIds()
1871 + "] [negative domain filter: " + parser.getDomainsIgnoredDueToNegativeDomainFilter()
1872 + "] [overlap: " + parser.getDomainsIgnoredDueToOverlap() + "]" );
1873 if ( negative_filter_file != null ) {
1874 html_desc.append( "; proteins ignored due to negative filter: "
1875 + parser.getProteinsIgnoredDueToFilter() );
1877 if ( positive_filter_file != null ) {
1878 html_desc.append( "; proteins ignored due to positive filter: "
1879 + parser.getProteinsIgnoredDueToFilter() );
1881 html_desc.append( "</td></tr>" + nl );
1882 // domain_partner_counts_array[ i ] =
1883 // Methods.getDomainPartnerCounts( protein_domain_collections_array[
1885 // false, input_file_properties[ i ][ 1 ] );
1888 for( final Protein protein : protein_list ) {
1889 dc_data_writer.write( SurfacingUtil.proteinToDomainCombinations( protein, count + "", "\t" )
1894 catch ( final IOException e ) {
1895 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
1897 SurfacingUtil.domainsPerProteinsStatistics( input_file_properties[ i ][ 0 ],
1899 all_genomes_domains_per_potein_stats,
1900 all_genomes_domains_per_potein_histo,
1901 domains_which_are_always_single,
1902 domains_which_are_sometimes_single_sometimes_not,
1903 domains_which_never_single,
1904 domains_per_potein_stats_writer );
1905 gwcd_list.add( BasicGenomeWideCombinableDomains
1906 .createInstance( protein_list,
1907 ignore_combination_with_same,
1908 new BasicSpecies( input_file_properties[ i ][ 1 ] ),
1909 domain_id_to_go_ids_map,
1911 domain_lengths_table.addLengths( protein_list );
1912 if ( gwcd_list.get( i ).getSize() > 0 ) {
1913 SurfacingUtil.writeDomainCombinationsCountsFile( input_file_properties,
1915 per_genome_domain_promiscuity_statistics_writer,
1919 if ( output_binary_domain_combinationsfor_graph_analysis ) {
1920 SurfacingUtil.writeBinaryDomainCombinationsFileForGraphAnalysis( input_file_properties,
1926 SurfacingUtil.addAllDomainIdsToSet( gwcd_list.get( i ), all_domains_encountered );
1927 SurfacingUtil.addAllBinaryDomainCombinationToSet( gwcd_list.get( i ),
1928 all_bin_domain_combinations_encountered );
1930 if ( query_domains_writer_ary != null ) {
1931 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
1933 SurfacingUtil.extractProteinNames( protein_list,
1934 query_domain_ids_array[ j ],
1935 query_domains_writer_ary[ j ],
1937 query_domains_writer_ary[ j ].flush();
1939 catch ( final IOException e ) {
1940 e.printStackTrace();
1944 if ( need_protein_lists_per_species ) {
1945 protein_lists_per_species.put( new BasicSpecies( input_file_properties[ i ][ 1 ] ), protein_list );
1950 catch ( final IOException e2 ) {
1951 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1954 } // for( int i = 0; i < number_of_genomes; ++i ) {
1956 per_genome_domain_promiscuity_statistics_writer.flush();
1957 per_genome_domain_promiscuity_statistics_writer.close();
1958 dc_data_writer.flush();
1959 dc_data_writer.close();
1963 catch ( final IOException e2 ) {
1964 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1966 ForesterUtil.programMessage( PRG_NAME, "Wrote domain promiscuities to: "
1967 + per_genome_domain_promiscuity_statistics_file );
1970 domains_per_potein_stats_writer.write( "ALL" );
1971 domains_per_potein_stats_writer.write( "\t" );
1972 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.arithmeticMean() + "" );
1973 domains_per_potein_stats_writer.write( "\t" );
1974 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.sampleStandardDeviation() + "" );
1975 domains_per_potein_stats_writer.write( "\t" );
1976 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.median() + "" );
1977 domains_per_potein_stats_writer.write( "\t" );
1978 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getN() + "" );
1979 domains_per_potein_stats_writer.write( "\t" );
1980 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMin() + "" );
1981 domains_per_potein_stats_writer.write( "\t" );
1982 domains_per_potein_stats_writer.write( all_genomes_domains_per_potein_stats.getMax() + "" );
1983 domains_per_potein_stats_writer.write( "\n" );
1984 domains_per_potein_stats_writer.flush();
1985 domains_per_potein_stats_writer.close();
1986 ForesterUtil.map2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1987 + "__all_genomes_domains_per_potein_histo.txt" ), all_genomes_domains_per_potein_histo, "\t", "\n" );
1988 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1989 + "__domains_always_single_.txt" ), domains_which_are_always_single, "\n" );
1990 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1991 + "__domains_single_or_combined.txt" ), domains_which_are_sometimes_single_sometimes_not, "\n" );
1992 ForesterUtil.collection2file( new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file
1993 + "__domains_always_combined.txt" ), domains_which_never_single, "\n" );
1995 catch ( final IOException e2 ) {
1996 ForesterUtil.fatalError( surfacing.PRG_NAME, e2.getLocalizedMessage() );
1998 if ( query_domains_writer_ary != null ) {
1999 for( int j = 0; j < query_domain_ids_array.length; j++ ) {
2001 query_domains_writer_ary[ j ].close();
2003 catch ( final IOException e ) {
2004 ForesterUtil.fatalError( surfacing.PRG_NAME, e.toString() );
2008 if ( PERFORM_DOMAIN_LENGTH_ANALYSIS ) {
2010 SurfacingUtil.executeDomainLengthAnalysis( input_file_properties,
2012 domain_lengths_table,
2013 domain_lengths_analysis_outfile );
2015 catch ( final IOException e1 ) {
2016 ForesterUtil.fatalError( surfacing.PRG_NAME, e1.toString() );
2018 System.out.println();
2019 ForesterUtil.programMessage( PRG_NAME, "Wrote domain length data to: " + domain_lengths_analysis_outfile );
2020 System.out.println();
2022 final long analysis_start_time = new Date().getTime();
2023 PairwiseDomainSimilarityCalculator pw_calc = null;
2024 // double[] values_for_all_scores_histogram = null;
2025 final DomainSimilarityCalculator calc = new BasicDomainSimilarityCalculator( domain_similarity_sort_field,
2026 sort_by_species_count_first,
2027 number_of_genomes == 2 );
2028 switch ( scoring ) {
2030 pw_calc = new CombinationsBasedPairwiseDomainSimilarityCalculator();
2033 pw_calc = new DomainCountsBasedPairwiseSimilarityCalculator();
2036 pw_calc = new ProteinCountsBasedPairwiseDomainSimilarityCalculator();
2039 ForesterUtil.unexpectedFatalError( surfacing.PRG_NAME, "unknown value for sorting for scoring" );
2041 DomainSimilarityCalculator.GoAnnotationOutput go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.NONE;
2042 if ( domain_id_to_go_ids_map != null ) {
2043 go_annotation_output = DomainSimilarityCalculator.GoAnnotationOutput.ALL;
2045 final SortedSet<DomainSimilarity> similarities = calc
2046 .calculateSimilarities( pw_calc,
2048 ignore_domains_without_combs_in_all_spec,
2049 ignore_species_specific_domains );
2050 SurfacingUtil.decoratePrintableDomainSimilarities( similarities,
2052 go_annotation_output,
2054 go_namespace_limit );
2055 DescriptiveStatistics pw_stats = null;
2057 String my_outfile = output_file.toString();
2058 if ( !my_outfile.endsWith( ".html" ) ) {
2059 my_outfile += ".html";
2061 final Writer writer = new BufferedWriter( new FileWriter( out_dir == null ? my_outfile : out_dir
2062 + ForesterUtil.FILE_SEPARATOR + my_outfile ) );
2063 List<Species> species_order = null;
2064 if ( species_matrix ) {
2065 species_order = new ArrayList<Species>();
2066 for( int i = 0; i < number_of_genomes; i++ ) {
2067 species_order.add( new BasicSpecies( input_file_properties[ i ][ 1 ] ) );
2070 html_desc.append( "<tr><td>Sum of all distinct binary combinations:</td><td>"
2071 + all_bin_domain_combinations_encountered.size() + "</td></tr>" + nl );
2072 html_desc.append( "<tr><td>Sum of all distinct domains:</td><td>" + all_domains_encountered.size()
2073 + "</td></tr>" + nl );
2074 html_desc.append( "<tr><td>Analysis date/time:</td><td>"
2075 + new java.text.SimpleDateFormat( "yyyy.MM.dd HH:mm:ss" ).format( new java.util.Date() )
2076 + "</td></tr>" + nl );
2077 html_desc.append( "</table>" + nl );
2078 pw_stats = SurfacingUtil
2079 .writeDomainSimilaritiesToFile( html_desc,
2080 new StringBuilder( number_of_genomes + " genomes" ),
2083 number_of_genomes == 2,
2085 domain_similarity_print_option,
2086 domain_similarity_sort_field,
2089 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote main output (includes domain similarities) to: \""
2090 + ( out_dir == null ? my_outfile : out_dir + ForesterUtil.FILE_SEPARATOR + my_outfile ) + "\"" );
2092 catch ( final IOException e ) {
2093 ForesterUtil.fatalError( surfacing.PRG_NAME, "Failed to write similarites to: \"" + output_file + "\" ["
2094 + e.getMessage() + "]" );
2096 System.out.println();
2097 // values_for_all_scores_histogram = pw_stats.getDataAsDoubleArray();
2098 final Species[] species = new Species[ number_of_genomes ];
2099 for( int i = 0; i < number_of_genomes; ++i ) {
2100 species[ i ] = new BasicSpecies( input_file_properties[ i ][ 1 ] );
2102 List<Phylogeny> inferred_trees = null;
2103 if ( ( number_of_genomes > 2 ) && perform_pwc ) {
2104 final PairwiseGenomeComparator pwgc = new PairwiseGenomeComparator();
2105 pwgc.performPairwiseComparisons( html_desc,
2106 sort_by_species_count_first,
2108 ignore_domains_without_combs_in_all_spec,
2109 ignore_species_specific_domains,
2110 domain_similarity_sort_field_for_automated_pwc,
2111 domain_similarity_print_option,
2113 domain_id_to_go_ids_map,
2120 automated_pairwise_comparison_suffix,
2122 surfacing.PAIRWISE_DOMAIN_COMPARISONS_PREFIX,
2126 String matrix_output_file = new String( output_file.toString() );
2127 if ( matrix_output_file.indexOf( '.' ) > 1 ) {
2128 matrix_output_file = matrix_output_file.substring( 0, matrix_output_file.indexOf( '.' ) );
2130 if ( out_dir != null ) {
2131 matrix_output_file = out_dir + ForesterUtil.FILE_SEPARATOR + matrix_output_file;
2132 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2134 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2135 + surfacing.MATRIX_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans() );
2137 .writeMatrixToFile( new File( matrix_output_file
2138 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2139 pwgc.getSharedBinaryCombinationsBasedDistances() );
2140 SurfacingUtil.writeMatrixToFile( new File( matrix_output_file
2141 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2142 pwgc.getSharedDomainsBasedDistances() );
2143 final Phylogeny nj_gd = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2144 + surfacing.NJ_TREE_MEAN_SCORE_BASED_GENOME_DISTANCE_SUFFIX ), pwgc.getDomainDistanceScoresMeans()
2146 final Phylogeny nj_bc = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2147 + surfacing.NJ_TREE_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2148 .getSharedBinaryCombinationsBasedDistances().get( 0 ) );
2149 final Phylogeny nj_d = SurfacingUtil.createNjTreeBasedOnMatrixToFile( new File( matrix_output_file
2150 + surfacing.NJ_TREE_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ), pwgc
2151 .getSharedDomainsBasedDistances().get( 0 ) );
2152 inferred_trees = new ArrayList<Phylogeny>();
2153 inferred_trees.add( nj_gd );
2154 inferred_trees.add( nj_bc );
2155 inferred_trees.add( nj_d );
2156 if ( jacknifed_distances ) {
2157 pwgc.performPairwiseComparisonsJacknifed( species,
2161 jacknife_resamplings,
2165 .writeMatrixToFile( new File( matrix_output_file
2167 + ForesterUtil.round( jacknife_ratio, 2 )
2169 + jacknife_resamplings
2170 + surfacing.MATRIX_SHARED_BIN_COMBINATIONS_BASED_GENOME_DISTANCE_SUFFIX ),
2171 pwgc.getSharedBinaryCombinationsBasedDistances() );
2173 .writeMatrixToFile( new File( matrix_output_file + "_" + ForesterUtil.round( jacknife_ratio, 2 )
2174 + "_" + jacknife_resamplings
2175 + surfacing.MATRIX_SHARED_DOMAINS_BASED_GENOME_DISTANCE_SUFFIX ),
2176 pwgc.getSharedDomainsBasedDistances() );
2177 // if ( infer_species_trees ) {
2178 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2179 // + INFERRED_SBC_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc
2180 // .getSharedBinaryCombinationsBasedDistances() );
2181 // inferSpeciesTrees( new File( output_file + "_" + jacknife_resamplings
2182 // + INFERRED_SD_BASED_NJ_SPECIES_TREE_SUFFIX ), pwgc.getSharedDomainsBasedDistances() );
2185 } // if ( ( output_file != null ) && ( number_of_genomes > 2 ) && !isEmpty( automated_pairwise_comparison_suffix ) )
2186 if ( ( out_dir != null ) && ( !perform_pwc ) ) {
2187 output_file = new File( out_dir + ForesterUtil.FILE_SEPARATOR + output_file );
2189 writePresentToNexus( output_file, positive_filter_file, filter, gwcd_list );
2190 if ( ( ( intrees != null ) && ( intrees.length > 0 ) ) && ( number_of_genomes > 2 ) ) {
2191 final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
2193 max_allowed_overlap,
2194 no_engulfing_overlaps,
2198 if ( radomize_fitch_parsimony ) {
2199 s += random_number_seed_for_fitch_parsimony + "_";
2202 for( final Phylogeny intree : intrees ) {
2203 final String outfile_name = ForesterUtil.removeSuffix( output_file.toString() ) + s
2204 + ForesterUtil.removeSuffix( intree_files[ i ].toString() );
2205 final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator.createInstance( intree,
2207 SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
2208 radomize_fitch_parsimony,
2212 domain_id_to_go_ids_map,
2215 parameters_sb.toString(),
2216 domain_id_to_secondary_features_maps,
2217 positive_filter_file == null ? null : filter,
2218 output_binary_domain_combinationsfor_graph_analysis,
2219 all_bin_domain_combinations_gained_fitch,
2220 all_bin_domain_combinations_lost_fitch,
2222 // Listing of all domain combinations gained is only done if only one input tree is used.
2223 if ( ( domain_id_to_secondary_features_maps != null )
2224 && ( domain_id_to_secondary_features_maps.length > 0 ) ) {
2226 for( final Map<DomainId, Set<String>> domain_id_to_secondary_features_map : domain_id_to_secondary_features_maps ) {
2227 final Map<Species, MappingResults> mapping_results_map = new TreeMap<Species, MappingResults>();
2228 final DomainParsimonyCalculator secondary_features_parsimony = DomainParsimonyCalculator
2229 .createInstance( intree, gwcd_list, domain_id_to_secondary_features_map );
2231 .executeParsimonyAnalysisForSecondaryFeatures( outfile_name
2233 + secondary_features_map_files[ j++ ],
2234 secondary_features_parsimony,
2236 parameters_sb.toString(),
2237 mapping_results_map );
2239 System.out.println();
2240 System.out.println( "Mapping to secondary features:" );
2241 for( final Species spec : mapping_results_map.keySet() ) {
2242 final MappingResults mapping_results = mapping_results_map.get( spec );
2243 final int total_domains = mapping_results.getSumOfFailures()
2244 + mapping_results.getSumOfSuccesses();
2245 System.out.print( spec + ":" );
2246 System.out.print( " mapped domains = " + mapping_results.getSumOfSuccesses() );
2247 System.out.print( ", not mapped domains = " + mapping_results.getSumOfFailures() );
2248 if ( total_domains > 0 ) {
2249 System.out.println( ", mapped ratio = "
2250 + ( 100 * mapping_results.getSumOfSuccesses() / total_domains ) + "%" );
2253 System.out.println( ", mapped ratio = n/a (total domains = 0 )" );
2260 } // for( final Phylogeny intree : intrees ) {
2262 if ( plus_minus_analysis_high_copy_base_species.size() > 0 ) {
2263 executePlusMinusAnalysis( output_file,
2264 plus_minus_analysis_high_copy_base_species,
2265 plus_minus_analysis_high_copy_target_species,
2266 plus_minus_analysis_high_low_copy_species,
2268 protein_lists_per_species,
2269 domain_id_to_go_ids_map,
2271 plus_minus_analysis_numbers );
2273 if ( output_protein_lists_for_all_domains ) {
2274 writeProteinListsForAllSpecies( out_dir, protein_lists_per_species, gwcd_list );
2276 // if ( ( intrees != null ) && ( intrees.length > 0 ) && ( inferred_trees != null ) && ( inferred_trees.size() > 0 ) ) {
2277 // final StringBuilder parameters_sb = createParametersAsString( ignore_dufs,
2279 // max_allowed_overlap,
2280 // no_engulfing_overlaps,
2281 // cutoff_scores_file );
2283 // if ( radomize_fitch_parsimony ) {
2284 // s += random_number_seed_for_fitch_parsimony + "_";
2287 // for( final Phylogeny inferred_tree : inferred_trees ) {
2288 // if ( !inferred_tree.isRooted() ) {
2289 // intrees[ 0 ].getRoot().getName();
2292 // final String outfile_name = ForesterUtil.removeSuffix( inferred_tree.getName() ) + s;
2293 // final DomainParsimonyCalculator domain_parsimony = DomainParsimonyCalculator
2294 // .createInstance( inferred_tree, gwcd_list );
2295 // SurfacingUtil.executeParsimonyAnalysis( random_number_seed_for_fitch_parsimony,
2296 // radomize_fitch_parsimony,
2298 // domain_parsimony,
2300 // domain_id_to_go_ids_map,
2301 // go_id_to_term_map,
2302 // go_namespace_limit,
2303 // parameters_sb.toString() );
2307 if ( all_bin_domain_combinations_gained_fitch != null ) {
2309 executeFitchGainsAnalysis( new File( output_file
2310 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_GAINED_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2311 all_bin_domain_combinations_gained_fitch,
2312 all_domains_encountered.size(),
2313 all_bin_domain_combinations_encountered,
2316 catch ( final IOException e ) {
2317 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2320 if ( all_bin_domain_combinations_lost_fitch != null ) {
2322 executeFitchGainsAnalysis( new File( output_file
2323 + surfacing.OUTPUT_DOMAIN_COMBINATIONS_LOST_MORE_THAN_ONCE_ANALYSIS_SUFFIX ),
2324 all_bin_domain_combinations_lost_fitch,
2325 all_domains_encountered.size(),
2326 all_bin_domain_combinations_encountered,
2329 catch ( final IOException e ) {
2330 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
2333 final Runtime rt = java.lang.Runtime.getRuntime();
2334 final long free_memory = rt.freeMemory() / 1000000;
2335 final long total_memory = rt.totalMemory() / 1000000;
2336 System.out.println();
2337 System.out.println( "Time for analysis : " + ( new Date().getTime() - analysis_start_time ) + "ms" );
2338 System.out.println( "Total running time: " + ( new Date().getTime() - start_time ) + "ms " );
2339 System.out.println( "Free memory : " + free_memory + "MB, total memory: " + total_memory + "MB" );
2340 System.out.println();
2341 System.out.println( "If this application is useful to you, please cite:" );
2342 System.out.println( surfacing.WWW );
2343 System.out.println();
2344 ForesterUtil.programMessage( PRG_NAME, "OK" );
2345 System.out.println();
2348 private static void preparePhylogenyForParsimonyAnalyses( final Phylogeny intree,
2349 final String[][] input_file_properties ) {
2350 final String[] genomes = new String[ input_file_properties.length ];
2351 for( int i = 0; i < input_file_properties.length; ++i ) {
2352 if ( intree.getNodes( input_file_properties[ i ][ 1 ] ).size() > 1 ) {
2353 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
2354 + "] is not unique in input tree " + intree.getName() );
2356 genomes[ i ] = input_file_properties[ i ][ 1 ];
2359 final PhylogenyNodeIterator it = intree.iteratorPostorder();
2360 while ( it.hasNext() ) {
2361 final PhylogenyNode n = it.next();
2362 if ( ForesterUtil.isEmpty( n.getName() ) ) {
2363 if ( n.getNodeData().isHasTaxonomy()
2364 && !ForesterUtil.isEmpty( n.getNodeData().getTaxonomy().getScientificName() ) ) {
2365 n.setName( n.getNodeData().getTaxonomy().getScientificName() );
2368 ForesterUtil.fatalError( surfacing.PRG_NAME,
2369 "node without both name and scientific taxonomy name found" );
2374 final List<String> igns = PhylogenyMethods.deleteExternalNodesPositiveSelection( genomes, intree );
2375 if ( igns.size() > 0 ) {
2376 System.out.println( "Not using the following " + igns.size() + " nodes:" );
2377 for( int i = 0; i < igns.size(); ++i ) {
2378 System.out.println( " " + i + ": " + igns.get( i ) );
2380 System.out.println( "--" );
2382 for( int i = 0; i < input_file_properties.length; ++i ) {
2384 intree.getNode( input_file_properties[ i ][ 1 ] );
2386 catch ( final IllegalArgumentException e ) {
2387 ForesterUtil.fatalError( surfacing.PRG_NAME, "node named [" + input_file_properties[ i ][ 1 ]
2388 + "] not present/not unique in input tree" );
2393 // public static StringBuffer stringCombinableDomainsMapToStringBuffer(
2394 // final SortedMap<String, CombinableDomains> map ) {
2395 // final StringBuffer sb = new StringBuffer();
2396 // for( final Iterator<String> iter = map.keySet().iterator();
2397 // iter.hasNext(); ) {
2398 // final Object key = iter.next();
2399 // sb.append( ForesterUtil.pad( new StringBuffer( key.toString() ), 18, ' ',
2401 // final CombinableDomains domain_combination = map.get( key );
2402 // sb.append( ForesterUtil.pad( new StringBuffer( "" +
2403 // domain_combination.getNumberOfCombiningDomains() ), 8,
2405 // sb.append( domain_combination.toStringBuffer() );
2406 // sb.append( ForesterUtil.getLineSeparator() );
2410 private static void printHelp() {
2411 System.out.println();
2412 System.out.println( "Usage:" );
2413 System.out.println();
2414 System.out.println( "% java -Xms256m -Xmx512m -cp forester.jar org.forester.applications." + surfacing.PRG_NAME
2415 + " [options] <phylogen(y|ies) infile> [external node name 1] [name 2] ... [name n]" );
2416 System.out.println();
2417 System.out.println( " Note: This software might need a significant amount of memory (heap space);" );
2419 .println( " hence use \"-Xms128m -Xmx512m\" (or more) to prevent a \"java.lang.OutOfMemoryError\"." );
2420 System.out.println();
2421 System.out.println( " Options: " );
2422 System.out.println( surfacing.DETAILEDNESS_OPTION + ": level of detail for similarities output file (default:"
2423 + DETAILEDNESS_DEFAULT + ")" );
2424 System.out.println( surfacing.IGNORE_COMBINATION_WITH_SAME_OPTION
2425 + ": to ignore combinations with self (default: not to ignore)" );
2427 .println( surfacing.IGNORE_DOMAINS_WITHOUT_COMBINATIONS_IN_ALL_SPECIES_OPTION
2428 + ": to ignore domains without combinations in any species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2430 .println( surfacing.IGNORE_DOMAINS_SPECIFIC_TO_ONE_SPECIES_OPTION
2431 + ": to ignore domains specific to one species (for similarity calc purposes, not for parsimony analyses) (default: not to ignore)" );
2432 System.out.println( surfacing.NOT_IGNORE_DUFS_OPTION
2433 + ": to _not_ ignore DUFs (domains with unknown function) (default: ignore DUFs)" );
2435 .println( surfacing.IGNORE_VIRAL_IDS
2436 + ": to ignore domains with ids containing 'vir', 'retro', 'transpos', 'phage', or starting with 'rv' or 'gag_'" );
2437 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_OPTION + ": sorting for similarities (default: "
2438 + DOMAIN_SORT_FILD_DEFAULT + ")" );
2439 System.out.println( surfacing.OUTPUT_FILE_OPTION + ": name for (main) output file (mandatory)" );
2440 System.out.println( surfacing.MAX_E_VALUE_OPTION + ": max (inclusive) E-value" );
2441 System.out.println( surfacing.MAX_ALLOWED_OVERLAP_OPTION + ": maximal allowed domain overlap" );
2442 System.out.println( surfacing.NO_ENGULFING_OVERLAP_OPTION + ": to ignore engulfed lower confidence domains" );
2443 System.out.println( surfacing.SPECIES_MATRIX_OPTION + ": species matrix" );
2444 System.out.println( surfacing.SCORING_OPTION + ": scoring (default:" + SCORING_DEFAULT + ")" );
2445 System.out.println( surfacing.DOMAIN_COUNT_SORT_OPTION + ": sorting for domain counts (default:"
2446 + DOMAINS_SORT_ORDER_DEFAULT + ")" );
2447 System.out.println( surfacing.DOMAIN_SIMILARITY_PRINT_OPTION + ": domain similarity print option (default:"
2448 + DOMAIN_SIMILARITY_PRINT_OPTION_DEFAULT + ")" );
2449 System.out.println( surfacing.CUTOFF_SCORE_FILE_OPTION + ": cutoff score file" );
2450 System.out.println( surfacing.DOMAIN_SIMILARITY_SORT_BY_SPECIES_COUNT_FIRST_OPTION
2451 + ": sort by species count first" );
2452 System.out.println( surfacing.OUTPUT_DIR_OPTION + ": output directory" );
2453 System.out.println( surfacing.PFAM_TO_GO_FILE_USE_OPTION + ": Pfam to GO mapping file" );
2454 System.out.println( surfacing.GO_OBO_FILE_USE_OPTION + ": GO terms file (OBO format)" );
2455 System.out.println( surfacing.GO_NAMESPACE_LIMIT_OPTION + ": limit GO term to one GO namespace" );
2456 System.out.println( surfacing.PAIRWISE_DOMAIN_COMPARISONS_OPTION
2457 + "[=<suffix for pairwise comparison output files>]: to perform pairwise comparison based analyses" );
2458 System.out.println( surfacing.INPUT_SPECIES_TREE_OPTION
2459 + ": species tree, to perform (Dollo, Fitch) parismony analyses" );
2461 .println( JACKNIFE_OPTION
2462 + ": perform jacknife resampling for domain and binary domain combination based distance matrices [default resamplings: "
2463 + JACKNIFE_NUMBER_OF_RESAMPLINGS_DEFAULT + "]" );
2464 System.out.println( JACKNIFE_RATIO_OPTION + ": ratio for jacknife resampling [default: "
2465 + JACKNIFE_RATIO_DEFAULT + "]" );
2466 System.out.println( JACKNIFE_RANDOM_SEED_OPTION
2467 + ": seed for random number generator for jacknife resampling [default: "
2468 + JACKNIFE_RANDOM_SEED_DEFAULT + "]" );
2469 // System.out.println( surfacing.INFER_SPECIES_TREES_OPTION
2470 // + ": to infer NJ species trees based on shared domains/binary domain combinations" );
2472 .println( surfacing.INPUT_SPECIES_TREE_OPTION
2473 + "=<treefiles in phyloXML format, separated by #>: to infer domain/binary domain combination gains/losses on given species trees" );
2474 System.out.println( surfacing.FILTER_POSITIVE_OPTION
2475 + "=<file>: to filter out proteins not containing at least one domain listed in <file>" );
2476 System.out.println( surfacing.FILTER_NEGATIVE_OPTION
2477 + "=<file>: to filter out proteins containing at least one domain listed in <file>" );
2478 System.out.println( surfacing.FILTER_NEGATIVE_DOMAINS_OPTION
2479 + "=<file>: to filter out (ignore) domains listed in <file>" );
2480 System.out.println( surfacing.INPUT_FILES_FROM_FILE_OPTION + "=<file>: to read input files from <file>" );
2482 .println( surfacing.RANDOM_SEED_FOR_FITCH_PARSIMONY_OPTION
2483 + "=<seed>: seed for random number generator for Fitch Parsimony analysis (type: long, default: no randomization - given a choice, prefer absence" );
2484 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS
2485 + ": to consider directedness in binary combinations: e.g. A-B != B-A" );
2486 System.out.println( surfacing.CONSIDER_DOMAIN_COMBINATION_DIRECTEDNESS_AND_ADJACENCY
2487 + ": to consider directedness and adjacency in binary combinations" );
2489 .println( surfacing.SEQ_EXTRACT_OPTION
2490 + "=<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')" );
2491 System.out.println( surfacing.SECONDARY_FEATURES_PARSIMONY_MAP_FILE
2492 + "=<file>: to perfom parsimony analysis on secondary features" );
2493 System.out.println( surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>: to presence/absence genome analysis" );
2494 System.out.println( surfacing.DOMAIN_COMBINITONS_OUTPUT_OPTION_FOR_GRAPH_ANALYSIS
2495 + ": to output binary domain combinations for (downstream) graph analysis" );
2496 System.out.println( surfacing.OUTPUT_LIST_OF_ALL_PROTEINS_OPTIONS + ": to output all proteins per domain" );
2497 System.out.println();
2498 System.out.println();
2499 System.out.println( "Example: java -Xms128m -Xmx512m -cp path/to/forester.jar"
2500 + " org.forester.application.surfacing -detail=punctilious -o=TEST.html -pwc=TEST"
2501 + " -cos=Pfam_ls_22_TC2 -p2g=pfam2go -obo=gene_ontology_edit.obo "
2502 + "-dc_sort=dom -ignore_with_self -no_singles -e=0.001 -mo=1 -no_eo "
2503 + "-ds_output=detailed_html -scoring=domains -sort=alpha -" + JACKNIFE_OPTION
2504 + "=50 human mouse brafl strpu" );
2505 System.out.println();
2508 private static void processFilter( final File filter_file, final SortedSet<DomainId> filter ) {
2509 SortedSet<String> filter_str = null;
2511 filter_str = ForesterUtil.file2set( filter_file );
2513 catch ( final IOException e ) {
2514 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2516 if ( filter_str != null ) {
2517 for( final String string : filter_str ) {
2518 filter.add( new DomainId( string ) );
2522 System.out.println( "Filter:" );
2523 for( final DomainId domainId : filter ) {
2524 System.out.println( domainId.getId() );
2529 private static String[][] processInputFileNames( final String[] names ) {
2530 final String[][] input_file_properties = new String[ names.length ][];
2531 for( int i = 0; i < names.length; ++i ) {
2532 if ( names[ i ].indexOf( SEPARATOR_FOR_INPUT_VALUES ) < 0 ) {
2533 input_file_properties[ i ] = new String[ 2 ];
2534 input_file_properties[ i ][ 0 ] = names[ i ];
2535 input_file_properties[ i ][ 1 ] = names[ i ];
2538 input_file_properties[ i ] = names[ i ].split( surfacing.SEPARATOR_FOR_INPUT_VALUES + "" );
2539 if ( input_file_properties[ i ].length != 3 ) {
2541 .fatalError( surfacing.PRG_NAME,
2542 "properties for the input files (hmmpfam output) are expected "
2543 + "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 \""
2544 + names[ i ] + "\"" );
2547 final String error = ForesterUtil.isReadableFile( new File( input_file_properties[ i ][ 0 ] ) );
2548 if ( !ForesterUtil.isEmpty( error ) ) {
2549 ForesterUtil.fatalError( surfacing.PRG_NAME, error );
2552 return input_file_properties;
2555 private static void processPlusMinusAnalysisOption( final CommandLineArguments cla,
2556 final List<String> high_copy_base,
2557 final List<String> high_copy_target,
2558 final List<String> low_copy,
2559 final List<Object> numbers ) {
2560 if ( cla.isOptionSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2561 if ( !cla.isOptionValueSet( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) ) {
2562 ForesterUtil.fatalError( surfacing.PRG_NAME, "no value for 'plus-minus' file: -"
2563 + surfacing.PLUS_MINUS_ANALYSIS_OPTION + "=<file>" );
2565 final File plus_minus_file = new File( cla.getOptionValue( surfacing.PLUS_MINUS_ANALYSIS_OPTION ) );
2566 final String msg = ForesterUtil.isReadableFile( plus_minus_file );
2567 if ( !ForesterUtil.isEmpty( msg ) ) {
2568 ForesterUtil.fatalError( surfacing.PRG_NAME, "can not read from \"" + plus_minus_file + "\": " + msg );
2570 processPlusMinusFile( plus_minus_file, high_copy_base, high_copy_target, low_copy, numbers );
2574 // First numbers is minimal difference, second is factor.
2575 private static void processPlusMinusFile( final File plus_minus_file,
2576 final List<String> high_copy_base,
2577 final List<String> high_copy_target,
2578 final List<String> low_copy,
2579 final List<Object> numbers ) {
2580 Set<String> species_set = null;
2581 int min_diff = PLUS_MINUS_ANALYSIS_MIN_DIFF_DEFAULT;
2582 double factor = PLUS_MINUS_ANALYSIS_FACTOR_DEFAULT;
2584 species_set = ForesterUtil.file2set( plus_minus_file );
2586 catch ( final IOException e ) {
2587 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getMessage() );
2589 if ( species_set != null ) {
2590 for( final String species : species_set ) {
2591 final String species_trimmed = species.substring( 1 );
2592 if ( species.startsWith( "+" ) ) {
2593 if ( low_copy.contains( species_trimmed ) ) {
2594 ForesterUtil.fatalError( surfacing.PRG_NAME,
2595 "species/genome names can not appear with both '+' and '-' suffix, as appears the case for: \""
2596 + species_trimmed + "\"" );
2598 high_copy_base.add( species_trimmed );
2600 else if ( species.startsWith( "*" ) ) {
2601 if ( low_copy.contains( species_trimmed ) ) {
2602 ForesterUtil.fatalError( surfacing.PRG_NAME,
2603 "species/genome names can not appear with both '*' and '-' suffix, as appears the case for: \""
2604 + species_trimmed + "\"" );
2606 high_copy_target.add( species_trimmed );
2608 else if ( species.startsWith( "-" ) ) {
2609 if ( high_copy_base.contains( species_trimmed ) || high_copy_target.contains( species_trimmed ) ) {
2610 ForesterUtil.fatalError( surfacing.PRG_NAME,
2611 "species/genome names can not appear with both '+' or '*' and '-' suffix, as appears the case for: \""
2612 + species_trimmed + "\"" );
2614 low_copy.add( species_trimmed );
2616 else if ( species.startsWith( "$D" ) ) {
2618 min_diff = Integer.parseInt( species.substring( 3 ) );
2620 catch ( final NumberFormatException e ) {
2621 ForesterUtil.fatalError( surfacing.PRG_NAME,
2622 "could not parse integer value for minimal difference from: \""
2623 + species.substring( 3 ) + "\"" );
2626 else if ( species.startsWith( "$F" ) ) {
2628 factor = Double.parseDouble( species.substring( 3 ) );
2630 catch ( final NumberFormatException e ) {
2631 ForesterUtil.fatalError( surfacing.PRG_NAME, "could not parse double value for factor from: \""
2632 + species.substring( 3 ) + "\"" );
2635 else if ( species.startsWith( "#" ) ) {
2640 .fatalError( surfacing.PRG_NAME,
2641 "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: \""
2644 numbers.add( new Integer( min_diff + "" ) );
2645 numbers.add( new Double( factor + "" ) );
2649 ForesterUtil.fatalError( surfacing.PRG_NAME, "'plus minus' file [" + plus_minus_file + "] appears empty" );
2653 private static void writePresentToNexus( final File output_file,
2654 final File positive_filter_file,
2655 final SortedSet<DomainId> filter,
2656 final List<GenomeWideCombinableDomains> gwcd_list ) {
2659 .writeMatrixToFile( DomainParsimonyCalculator
2660 .createMatrixOfDomainPresenceOrAbsence( gwcd_list, positive_filter_file == null ? null
2661 : filter ), output_file + DOMAINS_PRESENT_NEXUS, Format.NEXUS_BINARY );
2662 SurfacingUtil.writeMatrixToFile( DomainParsimonyCalculator
2663 .createMatrixOfBinaryDomainCombinationPresenceOrAbsence( gwcd_list ), output_file
2664 + BDC_PRESENT_NEXUS, Format.NEXUS_BINARY );
2666 catch ( final Exception e ) {
2667 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2671 private static void writeProteinListsForAllSpecies( final File output_dir,
2672 final SortedMap<Species, List<Protein>> protein_lists_per_species,
2673 final List<GenomeWideCombinableDomains> gwcd_list ) {
2674 final SortedSet<DomainId> all_domains = new TreeSet<DomainId>();
2675 for( final GenomeWideCombinableDomains gwcd : gwcd_list ) {
2676 all_domains.addAll( gwcd.getAllDomainIds() );
2678 for( final DomainId domain : all_domains ) {
2679 final File out = new File( output_dir + ForesterUtil.FILE_SEPARATOR + domain + SEQ_EXTRACT_SUFFIX );
2680 SurfacingUtil.checkForOutputFileWriteability( out );
2682 final Writer proteins_file_writer = new BufferedWriter( new FileWriter( out ) );
2683 SurfacingUtil.extractProteinNames( protein_lists_per_species, domain, proteins_file_writer, "\t" );
2684 proteins_file_writer.close();
2686 catch ( final IOException e ) {
2687 ForesterUtil.fatalError( surfacing.PRG_NAME, e.getLocalizedMessage() );
2689 ForesterUtil.programMessage( surfacing.PRG_NAME, "Wrote proteins list to \"" + out + "\"" );