2 // FORESTER -- software libraries and applications
3 // for evolutionary biology research and applications.
5 // Copyright (C) 2008-2009 Christian M. Zmasek
6 // Copyright (C) 2008-2009 Burnham Institute for Medical Research
9 // This library is free software; you can redistribute it and/or
10 // modify it under the terms of the GNU Lesser General Public
11 // License as published by the Free Software Foundation; either
12 // version 2.1 of the License, or (at your option) any later version.
14 // This library is distributed in the hope that it will be useful,
15 // but WITHOUT ANY WARRANTY; without even the implied warranty of
16 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
17 // Lesser General Public License for more details.
19 // You should have received a copy of the GNU Lesser General Public
20 // License along with this library; if not, write to the Free Software
21 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
23 // Contact: phylosoft @ gmail . com
24 // WWW: www.phylosoft.org/forester
26 package org.forester.application;
29 import java.io.IOException;
30 import java.text.SimpleDateFormat;
31 import java.util.ArrayList;
32 import java.util.Date;
33 import java.util.List;
34 import java.util.SortedMap;
35 import java.util.SortedSet;
36 import java.util.TreeMap;
37 import java.util.TreeSet;
39 import org.forester.io.parsers.PhylogenyParser;
40 import org.forester.io.parsers.nhx.NHXParser;
41 import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException;
42 import org.forester.io.parsers.phyloxml.PhyloXmlParser;
43 import org.forester.io.parsers.util.ParserUtils;
44 import org.forester.io.writers.PhylogenyWriter;
45 import org.forester.phylogeny.Phylogeny;
46 import org.forester.phylogeny.PhylogenyMethods;
47 import org.forester.phylogeny.PhylogenyNode;
48 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
49 import org.forester.phylogeny.factories.PhylogenyFactory;
50 import org.forester.sdi.GSDI;
51 import org.forester.sdi.SDI;
52 import org.forester.sdi.SDI.TaxonomyComparisonBase;
53 import org.forester.sdi.SDIException;
54 import org.forester.sdi.SDIse;
55 import org.forester.util.CommandLineArguments;
56 import org.forester.util.EasyWriter;
57 import org.forester.util.ForesterConstants;
58 import org.forester.util.ForesterUtil;
60 public final class gsdi {
62 private enum BASE_ALGORITHM {
65 final static public boolean REPLACE_UNDERSCORES_IN_NH_SPECIES_TREE = true;
66 final static private String ALLOW_STRIPPING_OF_GENE_TREE_OPTION = "g";
67 final static private String SDISE_OPTION = "b";
68 final static private String MOST_PARSIMONIOUS_OPTION = "m";
69 final static private String GUESS_FORMAT_OF_SPECIES_TREE = "q";
70 final static private String HELP_OPTION_1 = "help";
71 final static private String HELP_OPTION_2 = "h";
72 final static private String SUFFIX_FOR_SPECIES_TREE_USED = "_species_tree_used.xml";
73 final static private String LOGFILE_SUFFIX = "_gsdi_log.txt";
74 final static private String REMAPPED_SUFFIX = "_gsdi_remapped.txt";
75 final static private String PRG_NAME = "gsdi";
76 final static private String PRG_VERSION = "1.000";
77 final static private String PRG_DATE = "120629";
78 final static private String PRG_DESC = "general speciation duplication inference";
79 final static private String E_MAIL = "phylosoft@gmail.com";
80 final static private String WWW = "www.phylosoft.org/forester";
82 public static void main( final String args[] ) {
84 ForesterUtil.printProgramInformation( PRG_NAME,
90 ForesterUtil.getForesterLibraryInformation() );
91 CommandLineArguments cla = null;
93 cla = new CommandLineArguments( args );
95 catch ( final Exception e ) {
96 ForesterUtil.fatalError( PRG_NAME, e.getMessage() );
98 if ( cla.isOptionSet( gsdi.HELP_OPTION_1 ) || cla.isOptionSet( gsdi.HELP_OPTION_2 ) ) {
103 else if ( ( args.length < 2 ) || ( cla.getNumberOfNames() != 3 ) ) {
104 System.out.println();
105 System.out.println( "Wrong number of arguments." );
106 System.out.println();
110 final List<String> allowed_options = new ArrayList<String>();
111 allowed_options.add( gsdi.SDISE_OPTION );
112 allowed_options.add( gsdi.GUESS_FORMAT_OF_SPECIES_TREE );
113 allowed_options.add( gsdi.MOST_PARSIMONIOUS_OPTION );
114 allowed_options.add( gsdi.ALLOW_STRIPPING_OF_GENE_TREE_OPTION );
115 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
116 if ( dissallowed_options.length() > 0 ) {
117 ForesterUtil.fatalError( gsdi.PRG_NAME, "unknown option(s): " + dissallowed_options );
121 catch ( final IOException e ) {
122 ForesterUtil.fatalError( gsdi.PRG_NAME, e.getMessage() );
126 private static void execute( final CommandLineArguments cla ) throws IOException {
127 BASE_ALGORITHM base_algorithm = BASE_ALGORITHM.GSDI;
128 boolean most_parsimonous_duplication_model = false;
129 boolean allow_stripping_of_gene_tree = false;
130 if ( cla.isOptionSet( gsdi.SDISE_OPTION ) ) {
131 base_algorithm = BASE_ALGORITHM.SDI;
133 if ( cla.isOptionSet( gsdi.MOST_PARSIMONIOUS_OPTION ) ) {
134 if ( base_algorithm != BASE_ALGORITHM.GSDI ) {
135 ForesterUtil.fatalError( gsdi.PRG_NAME, "Can only use most parsimonious duplication mode with GSDI" );
137 most_parsimonous_duplication_model = true;
139 if ( cla.isOptionSet( gsdi.ALLOW_STRIPPING_OF_GENE_TREE_OPTION ) ) {
140 if ( base_algorithm != BASE_ALGORITHM.GSDI ) {
141 ForesterUtil.fatalError( gsdi.PRG_NAME, "Can only allow stripping of gene tree with GSDI" );
143 allow_stripping_of_gene_tree = true;
145 Phylogeny species_tree = null;
146 Phylogeny gene_tree = null;
147 File gene_tree_file = null;
148 File species_tree_file = null;
149 File out_file = null;
150 File log_file = null;
151 EasyWriter log_writer = null;
153 gene_tree_file = cla.getFile( 0 );
154 species_tree_file = cla.getFile( 1 );
155 out_file = cla.getFile( 2 );
156 log_file = new File( ForesterUtil.removeSuffix( out_file.toString() ) + LOGFILE_SUFFIX );
158 catch ( final IllegalArgumentException e ) {
159 ForesterUtil.fatalError( gsdi.PRG_NAME, "error in command line: " + e.getMessage() );
161 if ( ForesterUtil.isReadableFile( gene_tree_file ) != null ) {
162 ForesterUtil.fatalError( gsdi.PRG_NAME, ForesterUtil.isReadableFile( gene_tree_file ) );
164 if ( ForesterUtil.isReadableFile( species_tree_file ) != null ) {
165 ForesterUtil.fatalError( gsdi.PRG_NAME, ForesterUtil.isReadableFile( species_tree_file ) );
167 if ( ForesterUtil.isWritableFile( out_file ) != null ) {
168 ForesterUtil.fatalError( gsdi.PRG_NAME, ForesterUtil.isWritableFile( out_file ) );
170 if ( ForesterUtil.isWritableFile( log_file ) != null ) {
171 ForesterUtil.fatalError( gsdi.PRG_NAME, ForesterUtil.isWritableFile( log_file ) );
174 log_writer = ForesterUtil.createEasyWriter( log_file );
176 catch ( final IOException e ) {
177 ForesterUtil.fatalError( gsdi.PRG_NAME, "Failed to create [" + log_file + "]: " + e.getMessage() );
180 final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
181 gene_tree = factory.create( gene_tree_file, new PhyloXmlParser() )[ 0 ];
183 catch ( final IOException e ) {
185 "Failed to read gene tree from [" + gene_tree_file + "]: " + e.getMessage(),
189 final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
190 final PhylogenyParser p = ParserUtils.createParserDependingOnFileType( species_tree_file, true );
191 if ( p instanceof PhyloXmlParser ) {
192 species_tree = factory.create( species_tree_file, p )[ 0 ];
195 if ( REPLACE_UNDERSCORES_IN_NH_SPECIES_TREE && ( p instanceof NHXParser ) ) {
196 ( ( NHXParser ) p ).setReplaceUnderscores( true );
198 species_tree = factory.create( species_tree_file, p )[ 0 ];
199 final TaxonomyComparisonBase comp_base = GSDI.determineTaxonomyComparisonBase( gene_tree );
200 switch ( comp_base ) {
201 case SCIENTIFIC_NAME:
204 .transferNodeNameToField( species_tree,
205 PhylogenyMethods.PhylogenyNodeField.TAXONOMY_SCIENTIFIC_NAME,
208 catch ( final PhyloXmlDataFormatException e ) {
209 fatalError( "USER ERROR", "Failed to transfer general node name to scientific name, in ["
210 + species_tree_file + "]: " + e.getMessage(), log_writer );
216 .transferNodeNameToField( species_tree,
217 PhylogenyMethods.PhylogenyNodeField.TAXONOMY_CODE,
220 catch ( final PhyloXmlDataFormatException e ) {
221 fatalError( "USER ERROR", "Failed to transfer general node name to taxonomy code, in ["
222 + species_tree_file + "]: " + e.getMessage(), log_writer );
227 PhylogenyMethods.transferNodeNameToField( species_tree,
228 PhylogenyMethods.PhylogenyNodeField.TAXONOMY_ID,
231 catch ( final PhyloXmlDataFormatException e ) {
232 fatalError( "USER ERROR", "Failed to transfer general node name to taxonomy id, in ["
233 + species_tree_file + "]: " + e.getMessage(), log_writer );
237 fatalError( "UNEXPECTED ERROR", "unable to determine comparison base", log_writer );
241 catch ( final IOException e ) {
243 "Failed to read species tree from [" + species_tree_file + "]: " + e.getMessage(),
246 gene_tree.setRooted( true );
247 species_tree.setRooted( true );
248 if ( !gene_tree.isCompletelyBinary() ) {
249 fatalError( "user error", "gene tree is not completely binary", log_writer );
251 if ( base_algorithm != BASE_ALGORITHM.GSDI ) {
252 if ( !species_tree.isCompletelyBinary() ) {
253 fatalError( "user error", "species tree is not completely binary, use GSDI instead", log_writer );
256 log_writer.println( PRG_NAME + " - " + PRG_DESC );
257 log_writer.println( " version : " + PRG_VERSION );
258 log_writer.println( " date : " + PRG_DATE );
259 log_writer.println( " forester version: " + ForesterConstants.FORESTER_VERSION );
260 log_writer.println();
261 log_writer.println( "Start time : "
262 + new SimpleDateFormat( "yyyyMMdd HH:mm:ss" ).format( new Date() ) );
263 System.out.println( "Start time : "
264 + new SimpleDateFormat( "yyyyMMdd HH:mm:ss" ).format( new Date() ) );
265 log_writer.println( "Gene tree file : " + gene_tree_file.getCanonicalPath() );
266 System.out.println( "Gene tree file : " + gene_tree_file.getCanonicalPath() );
267 log_writer.println( "Gene tree name : "
268 + ( ForesterUtil.isEmpty( gene_tree.getName() ) ? "" : gene_tree.getName() ) );
269 System.out.println( "Gene tree name : "
270 + ( ForesterUtil.isEmpty( gene_tree.getName() ) ? "" : gene_tree.getName() ) );
271 log_writer.println( "Species tree file : " + species_tree_file.getCanonicalPath() );
272 System.out.println( "Species tree file : " + species_tree_file.getCanonicalPath() );
273 log_writer.println( "Species tree name : "
274 + ( ForesterUtil.isEmpty( species_tree.getName() ) ? "" : gene_tree.getName() ) );
275 System.out.println( "Species tree name : "
276 + ( ForesterUtil.isEmpty( species_tree.getName() ) ? "" : gene_tree.getName() ) );
278 final long start_time = new Date().getTime();
280 if ( base_algorithm == BASE_ALGORITHM.GSDI ) {
281 System.out.println( "Use most parsimonous duplication model : " + most_parsimonous_duplication_model );
282 System.out.println( "Allow stripping of gene tree nodes : " + allow_stripping_of_gene_tree );
283 log_writer.println( "Use most parsimonous duplication model : " + most_parsimonous_duplication_model );
284 log_writer.println( "Allow stripping of gene tree nodes : " + allow_stripping_of_gene_tree );
286 sdi = new GSDI( gene_tree,
288 most_parsimonous_duplication_model,
289 allow_stripping_of_gene_tree,
293 System.out.println();
294 System.out.println( "Using SDIse algorithm" );
295 log_writer.println( "Using SDIse algorithm" );
297 sdi = new SDIse( gene_tree, species_tree );
300 catch ( final SDIException e ) {
301 fatalError( "user error", e.getLocalizedMessage(), log_writer );
303 catch ( final IOException e ) {
304 fatalError( "error", e.toString(), log_writer );
306 catch ( final Exception e ) {
308 fatalError( "unexpected error", e.toString(), log_writer );
310 System.out.println( "Running time (excluding I/O) : " + ( new Date().getTime() - start_time )
312 log_writer.println( "Running time (excluding I/O) : " + ( new Date().getTime() - start_time )
314 if ( ( base_algorithm == BASE_ALGORITHM.GSDI ) ) {
315 final GSDI gsdi = ( GSDI ) sdi;
316 System.out.println( "Mapping based on : " + gsdi.getTaxCompBase() );
317 log_writer.println( "Mapping based on : " + gsdi.getTaxCompBase() );
320 final PhylogenyWriter writer = new PhylogenyWriter();
321 writer.toPhyloXML( out_file, gene_tree, 0 );
323 catch ( final IOException e ) {
324 ForesterUtil.fatalError( PRG_NAME,
325 "Failed to write to [" + out_file.getCanonicalPath() + "]: " + e.getMessage() );
327 System.out.println( "Wrote resulting gene tree to : " + out_file.getCanonicalPath() );
328 log_writer.println( "Wrote resulting gene tree to : " + out_file.getCanonicalPath() );
329 if ( base_algorithm == BASE_ALGORITHM.SDI ) {
330 sdi.computeMappingCostL();
331 System.out.println( "Mapping cost : " + sdi.computeMappingCostL() );
332 log_writer.println( "Mapping cost : " + sdi.computeMappingCostL() );
334 else if ( ( base_algorithm == BASE_ALGORITHM.GSDI ) ) {
335 final GSDI gsdi = ( GSDI ) sdi;
336 final File species_tree_used_file = new File( ForesterUtil.removeSuffix( out_file.toString() )
337 + SUFFIX_FOR_SPECIES_TREE_USED );
339 final PhylogenyWriter writer = new PhylogenyWriter();
340 writer.toPhyloXML( species_tree_used_file, gsdi.getSpeciesTree(), 0 );
342 catch ( final IOException e ) {
343 ForesterUtil.fatalError( PRG_NAME, "Failed to write to [" + species_tree_used_file.getCanonicalPath()
344 + "]: " + e.getMessage() );
346 System.out.println( "Wrote (stripped) species tree to : "
347 + species_tree_used_file.getCanonicalPath() );
348 log_writer.println( "Wrote (stripped) species tree to : "
349 + species_tree_used_file.getCanonicalPath() );
350 if ( ( gsdi.getReMappedScientificNamesFromGeneTree() != null )
351 && !gsdi.getReMappedScientificNamesFromGeneTree().isEmpty() ) {
352 System.out.println( "Number of gene tree species remapped : "
353 + gsdi.getReMappedScientificNamesFromGeneTree().size() );
354 log_writer.println( "Number of gene tree species remapped : "
355 + gsdi.getReMappedScientificNamesFromGeneTree().size() );
356 writeToRemappedFile( out_file, gsdi.getReMappedScientificNamesFromGeneTree(), log_writer );
359 System.out.println( "Number of external nodes in gene tree : " + gene_tree.getNumberOfExternalNodes() );
360 log_writer.println( "Number of external nodes in gene tree : " + gene_tree.getNumberOfExternalNodes() );
361 System.out.println( "Number of external nodes in species tree : "
362 + sdi.getSpeciesTree().getNumberOfExternalNodes() );
363 log_writer.println( "Number of external nodes in species tree : "
364 + sdi.getSpeciesTree().getNumberOfExternalNodes() );
365 if ( ( base_algorithm == BASE_ALGORITHM.GSDI ) ) {
366 final GSDI gsdi = ( GSDI ) sdi;
367 final int poly = PhylogenyMethods.countNumberOfPolytomies( gsdi.getSpeciesTree() );
368 System.out.println( "Number of polytomies in species tree : " + poly );
369 log_writer.println( "Number of polytomies in species tree : " + poly );
370 System.out.println( "External nodes stripped from gene tree : "
371 + gsdi.getStrippedExternalGeneTreeNodes().size() );
372 log_writer.println( "External nodes stripped from gene tree : "
373 + gsdi.getStrippedExternalGeneTreeNodes().size() );
374 System.out.println( "External nodes stripped from species tree: "
375 + gsdi.getStrippedSpeciesTreeNodes().size() );
376 log_writer.println( "External nodes stripped from species tree: "
377 + gsdi.getStrippedSpeciesTreeNodes().size() );
379 System.out.println();
380 System.out.println( "Number of duplications : " + sdi.getDuplicationsSum() );
381 log_writer.println( "Number of duplications : " + sdi.getDuplicationsSum() );
382 if ( ( base_algorithm == BASE_ALGORITHM.GSDI ) ) {
383 final GSDI gsdi = ( GSDI ) sdi;
384 if ( !most_parsimonous_duplication_model ) {
385 final int u = gsdi.getSpeciationOrDuplicationEventsSum();
386 System.out.println( "Number of potential duplications : " + u );
387 log_writer.println( "Number of potential duplications : " + u );
389 System.out.println( "Number of speciations : " + gsdi.getSpeciationsSum() );
390 log_writer.println( "Number of speciations : " + gsdi.getSpeciationsSum() );
391 log_writer.println();
392 printMappedNodesToLog( log_writer, gsdi );
393 log_writer.println();
394 printStrippedGeneTreeNodesToLog( log_writer, gsdi );
396 System.out.println();
397 System.out.println( "Wrote log to : " + log_file.getCanonicalPath() );
398 System.out.println();
402 private static void writeToRemappedFile( final File out_file,
403 final SortedSet<String> remapped,
404 final EasyWriter log_writer ) throws IOException {
405 final File file = new File( ForesterUtil.removeSuffix( out_file.toString() ) + REMAPPED_SUFFIX );
406 final EasyWriter remapped_writer = ForesterUtil.createEasyWriter( file );
407 for( final String s : remapped ) {
408 remapped_writer.println( s );
410 remapped_writer.close();
411 System.out.println( "Wrote remapped gene tree species to : " + file.getCanonicalPath() );
412 log_writer.println( "Wrote remapped gene tree species to : " + file.getCanonicalPath() );
415 private static void printMappedNodesToLog( final EasyWriter log_writer, final GSDI gsdi ) throws IOException {
416 final SortedSet<String> ss = new TreeSet<String>();
417 for( final PhylogenyNode n : gsdi.getMappedExternalSpeciesTreeNodes() ) {
418 ss.add( n.toString() );
420 log_writer.println( "The following " + ss.size() + " species were used: " );
421 for( final String s : ss ) {
422 log_writer.println( " " + s );
426 private static void fatalError( final String type, final String msg, final EasyWriter log_writer ) {
429 log_writer.println();
430 log_writer.print( type.toUpperCase() + ": " );
431 log_writer.println( msg );
434 catch ( final IOException e ) {
437 ForesterUtil.fatalError( gsdi.PRG_NAME, msg );
440 private static void printStrippedGeneTreeNodesToLog( final EasyWriter log_writer, final GSDI gsdi )
442 final SortedMap<String, Integer> sm = new TreeMap<String, Integer>();
443 for( final PhylogenyNode n : gsdi.getStrippedExternalGeneTreeNodes() ) {
444 final String s = n.toString();
445 if ( sm.containsKey( s ) ) {
446 sm.put( s, sm.get( s ) + 1 );
452 log_writer.println( "The following " + sm.size() + " nodes were stripped from the gene tree: " );
453 for( final String s : sm.keySet() ) {
454 final int count = sm.get( s );
456 log_writer.println( " " + s );
459 log_writer.println( " " + s + " [" + count + "]" );
464 private static void print_help() {
465 System.out.println( "Usage: " + gsdi.PRG_NAME
466 + " [-options] <gene tree in phyloXML format> <species tree> <outfile>" );
467 System.out.println();
468 System.out.println( "Options:" );
469 System.out.println( " -" + gsdi.ALLOW_STRIPPING_OF_GENE_TREE_OPTION
470 + ": to allow stripping of gene tree nodes without a matching species" );
471 System.out.println( " -" + gsdi.MOST_PARSIMONIOUS_OPTION
472 + ": use most parimonious duplication model for GSDI: " );
473 System.out.println( " assign nodes as speciations which would otherwise be assiged" );
474 System.out.println( " as potential duplications due to polytomies in the species tree" );
475 System.out.println( " -" + gsdi.GUESS_FORMAT_OF_SPECIES_TREE
476 + ": to allow species tree in other formats than phyloXML (i.e. Newick, NHX, Nexus)" );
477 System.out.println( " -" + gsdi.SDISE_OPTION
478 + ": to use SDIse algorithm instead of GSDI algorithm (for binary species trees)" );
479 System.out.println();
480 System.out.println( "Gene tree:" );
481 System.out.println( " in phyloXM format, with taxonomy and sequence data in appropriate fields" );
482 System.out.println();
483 System.out.println( "Species tree:" );
484 System.out.println( " in phyloXML format (unless option -" + gsdi.GUESS_FORMAT_OF_SPECIES_TREE + " is used)" );
485 System.out.println();
486 System.out.println( "Example: gsdi -" + ALLOW_STRIPPING_OF_GENE_TREE_OPTION
487 + " gene_tree.xml tree_of_life.xml out.xml" );
488 System.out.println();