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: https://sites.google.com/site/cmzmasek/home/software/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.nhx.NHXParser.TAXONOMY_EXTRACTION;
40 import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException;
41 import org.forester.io.parsers.phyloxml.PhyloXmlParser;
42 import org.forester.io.writers.PhylogenyWriter;
43 import org.forester.phylogeny.Phylogeny;
44 import org.forester.phylogeny.PhylogenyMethods;
45 import org.forester.phylogeny.PhylogenyNode;
46 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
47 import org.forester.phylogeny.factories.PhylogenyFactory;
48 import org.forester.sdi.GSDI;
49 import org.forester.sdi.GSDII;
50 import org.forester.sdi.GSDIR;
51 import org.forester.sdi.SDIException;
52 import org.forester.sdi.SDIutil;
53 import org.forester.sdi.SDIutil.ALGORITHM;
54 import org.forester.util.CommandLineArguments;
55 import org.forester.util.EasyWriter;
56 import org.forester.util.ForesterConstants;
57 import org.forester.util.ForesterUtil;
59 public final class gsdi {
61 final static public boolean REPLACE_UNDERSCORES_IN_NH_SPECIES_TREE = true;
62 final static private String ALLOW_STRIPPING_OF_GENE_TREE_OPTION = "g";
63 final static private String GSDIR_OPTION = "r";
64 final static private String MOST_PARSIMONIOUS_OPTION = "m";
65 final static private String GUESS_FORMAT_OF_SPECIES_TREE = "q";
66 final static private String TRANSFER_TAXONOMY_OPTION = "t";
67 final static private String HELP_OPTION_1 = "help";
68 final static private String HELP_OPTION_2 = "h";
69 final static private String SUFFIX_FOR_SPECIES_TREE_USED = "_species_tree_used.xml";
70 final static private String LOGFILE_SUFFIX = "_gsdi_log.txt";
71 final static private String REMAPPED_SUFFIX = "_gsdi_remapped.txt";
72 final static private String PRG_NAME = "gsdi";
73 final static private String PRG_VERSION = "1.001";
74 final static private String PRG_DATE = "130325";
75 final static private String PRG_DESC = "general speciation duplication inference";
76 final static private String E_MAIL = "phylosoft@gmail.com";
77 final static private String WWW = "https://sites.google.com/site/cmzmasek/home/software/forester";
79 public static void main( final String args[] ) {
81 ForesterUtil.printProgramInformation( PRG_NAME,
87 ForesterUtil.getForesterLibraryInformation() );
88 CommandLineArguments cla = null;
90 cla = new CommandLineArguments( args );
92 catch ( final Exception e ) {
93 ForesterUtil.fatalError( PRG_NAME, e.getMessage() );
95 if ( cla.isOptionSet( gsdi.HELP_OPTION_1 ) || cla.isOptionSet( gsdi.HELP_OPTION_2 ) ) {
100 else if ( ( args.length < 2 ) || ( cla.getNumberOfNames() != 3 ) ) {
101 System.out.println();
102 System.out.println( "Wrong number of arguments." );
103 System.out.println();
107 final List<String> allowed_options = new ArrayList<String>();
108 allowed_options.add( gsdi.GSDIR_OPTION );
109 allowed_options.add( gsdi.GUESS_FORMAT_OF_SPECIES_TREE );
110 allowed_options.add( gsdi.MOST_PARSIMONIOUS_OPTION );
111 allowed_options.add( gsdi.ALLOW_STRIPPING_OF_GENE_TREE_OPTION );
112 allowed_options.add( TRANSFER_TAXONOMY_OPTION );
113 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
114 if ( dissallowed_options.length() > 0 ) {
115 ForesterUtil.fatalError( gsdi.PRG_NAME, "unknown option(s): " + dissallowed_options );
119 catch ( final IOException e ) {
120 ForesterUtil.fatalError( gsdi.PRG_NAME, e.getMessage() );
124 private static void execute( final CommandLineArguments cla ) throws IOException {
125 ALGORITHM base_algorithm = ALGORITHM.GSDI;
126 boolean most_parsimonous_duplication_model = false;
127 boolean allow_stripping_of_gene_tree = false;
128 if ( cla.isOptionSet( gsdi.GSDIR_OPTION ) ) {
129 base_algorithm = ALGORITHM.GSDIR;
131 if ( cla.isOptionSet( gsdi.MOST_PARSIMONIOUS_OPTION ) ) {
132 if ( base_algorithm == ALGORITHM.SDI ) {
133 ForesterUtil.fatalError( gsdi.PRG_NAME, "Cannot use most parsimonious duplication mode with SDI" );
135 most_parsimonous_duplication_model = true;
137 if ( cla.isOptionSet( gsdi.ALLOW_STRIPPING_OF_GENE_TREE_OPTION ) ) {
138 if ( base_algorithm == ALGORITHM.SDI ) {
139 ForesterUtil.fatalError( gsdi.PRG_NAME, "Cannot allow stripping of gene tree with SDI" );
141 allow_stripping_of_gene_tree = true;
143 boolean transfer_taxonomy = false;
144 if ( cla.isOptionSet( TRANSFER_TAXONOMY_OPTION ) ) {
145 transfer_taxonomy = true;
147 Phylogeny species_tree = null;
148 Phylogeny gene_tree = null;
149 File gene_tree_file = null;
150 File species_tree_file = null;
151 File out_file = null;
152 File log_file = null;
153 EasyWriter log_writer = null;
155 gene_tree_file = cla.getFile( 0 );
156 species_tree_file = cla.getFile( 1 );
157 out_file = cla.getFile( 2 );
158 log_file = new File( ForesterUtil.removeSuffix( out_file.toString() ) + LOGFILE_SUFFIX );
160 catch ( final IllegalArgumentException e ) {
161 ForesterUtil.fatalError( gsdi.PRG_NAME, "error in command line: " + e.getMessage() );
163 if ( ForesterUtil.isReadableFile( gene_tree_file ) != null ) {
164 ForesterUtil.fatalError( gsdi.PRG_NAME, ForesterUtil.isReadableFile( gene_tree_file ) );
166 if ( ForesterUtil.isReadableFile( species_tree_file ) != null ) {
167 ForesterUtil.fatalError( gsdi.PRG_NAME, ForesterUtil.isReadableFile( species_tree_file ) );
169 if ( ForesterUtil.isWritableFile( out_file ) != null ) {
170 ForesterUtil.fatalError( gsdi.PRG_NAME, ForesterUtil.isWritableFile( out_file ) );
172 if ( ForesterUtil.isWritableFile( log_file ) != null ) {
173 ForesterUtil.fatalError( gsdi.PRG_NAME, ForesterUtil.isWritableFile( log_file ) );
176 log_writer = ForesterUtil.createEasyWriter( log_file );
178 catch ( final IOException e ) {
179 ForesterUtil.fatalError( gsdi.PRG_NAME, "Failed to create [" + log_file + "]: " + e.getMessage() );
182 final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
183 gene_tree = factory.create( gene_tree_file, PhyloXmlParser.createPhyloXmlParserXsdValidating() )[ 0 ];
185 catch ( final IOException e ) {
187 "failed to read gene tree from [" + gene_tree_file + "]: " + e.getMessage(),
191 species_tree = SDIutil.parseSpeciesTree( gene_tree,
193 REPLACE_UNDERSCORES_IN_NH_SPECIES_TREE,
195 TAXONOMY_EXTRACTION.NO );
197 catch ( final PhyloXmlDataFormatException e ) {
198 fatalError( "user error",
199 "failed to transfer general node name, in [" + species_tree_file + "]: " + e.getMessage(),
202 catch ( final SDIException e ) {
203 fatalError( "user error", e.getMessage(), log_writer );
205 catch ( final IOException e ) {
207 "Failed to read species tree from [" + species_tree_file + "]: " + e.getMessage(),
210 gene_tree.setRooted( true );
211 species_tree.setRooted( true );
212 if ( !gene_tree.isCompletelyBinary() ) {
213 fatalError( "user error", "gene tree is not completely binary", log_writer );
215 if ( base_algorithm == ALGORITHM.SDI ) {
216 if ( !species_tree.isCompletelyBinary() ) {
217 fatalError( "user error",
218 "species tree is not completely binary, use GSDI or GSDIR instead",
222 log_writer.println( PRG_NAME + " - " + PRG_DESC );
223 log_writer.println( " version : " + PRG_VERSION );
224 log_writer.println( " date : " + PRG_DATE );
225 log_writer.println( " forester version: " + ForesterConstants.FORESTER_VERSION );
226 log_writer.println();
227 log_writer.println( "Start time : "
228 + new SimpleDateFormat( "yyyyMMdd HH:mm:ss" ).format( new Date() ) );
229 System.out.println( "Start time : "
230 + new SimpleDateFormat( "yyyyMMdd HH:mm:ss" ).format( new Date() ) );
231 log_writer.println( "Gene tree file : " + gene_tree_file.getCanonicalPath() );
232 System.out.println( "Gene tree file : " + gene_tree_file.getCanonicalPath() );
233 log_writer.println( "Gene tree name : "
234 + ( ForesterUtil.isEmpty( gene_tree.getName() ) ? "" : gene_tree.getName() ) );
235 System.out.println( "Gene tree name : "
236 + ( ForesterUtil.isEmpty( gene_tree.getName() ) ? "" : gene_tree.getName() ) );
237 log_writer.println( "Species tree file : " + species_tree_file.getCanonicalPath() );
238 System.out.println( "Species tree file : " + species_tree_file.getCanonicalPath() );
239 log_writer.println( "Species tree name : "
240 + ( ForesterUtil.isEmpty( species_tree.getName() ) ? "" : gene_tree.getName() ) );
241 System.out.println( "Species tree name : "
242 + ( ForesterUtil.isEmpty( species_tree.getName() ) ? "" : gene_tree.getName() ) );
243 System.out.println( "Transfer taxonomy : " + transfer_taxonomy );
245 final long start_time = new Date().getTime();
247 if ( base_algorithm == ALGORITHM.GSDI ) {
248 System.out.println( "Algorithm : GSDI" );
249 log_writer.println( "Algorithm : GSDI" );
251 else if ( base_algorithm == ALGORITHM.GSDIR ) {
252 System.out.println( "Algorithm : GSDIR" );
253 log_writer.println( "Algorithm : GSDIR" );
255 System.out.println( "Use most parsimonous duplication model : " + most_parsimonous_duplication_model );
256 System.out.println( "Allow stripping of gene tree nodes : " + allow_stripping_of_gene_tree );
257 log_writer.println( "Use most parsimonous duplication model : " + most_parsimonous_duplication_model );
258 log_writer.println( "Allow stripping of gene tree nodes : " + allow_stripping_of_gene_tree );
260 if ( base_algorithm == ALGORITHM.GSDI ) {
261 gsdii = new GSDI( gene_tree,
263 most_parsimonous_duplication_model,
264 allow_stripping_of_gene_tree,
268 else if ( base_algorithm == ALGORITHM.GSDIR ) {
269 gsdii = new GSDIR( gene_tree, species_tree, allow_stripping_of_gene_tree, true, transfer_taxonomy );
272 catch ( final SDIException e ) {
273 fatalError( "user error", e.getLocalizedMessage(), log_writer );
275 catch ( final IOException e ) {
276 fatalError( "error", e.toString(), log_writer );
278 catch ( final OutOfMemoryError e ) {
279 ForesterUtil.outOfMemoryError( e );
281 catch ( final Exception e ) {
283 fatalError( "unexpected error", e.toString(), log_writer );
285 System.out.println( "Running time (excluding I/O) : " + ( new Date().getTime() - start_time )
287 log_writer.println( "Running time (excluding I/O) : " + ( new Date().getTime() - start_time )
289 System.out.println( "Mapping based on : " + gsdii.getTaxCompBase() );
290 log_writer.println( "Mapping based on : " + gsdii.getTaxCompBase() );
292 final PhylogenyWriter writer = new PhylogenyWriter();
293 if ( base_algorithm == ALGORITHM.GSDIR ) {
294 writer.toPhyloXML( out_file, ( ( GSDIR ) gsdii ).getMinDuplicationsSumGeneTree(), 0 );
297 writer.toPhyloXML( out_file, gene_tree, 0 );
300 catch ( final IOException e ) {
301 ForesterUtil.fatalError( PRG_NAME,
302 "Failed to write to [" + out_file.getCanonicalPath() + "]: " + e.getMessage() );
304 System.out.println( "Wrote resulting gene tree to : " + out_file.getCanonicalPath() );
305 log_writer.println( "Wrote resulting gene tree to : " + out_file.getCanonicalPath() );
306 final File species_tree_used_file = new File( ForesterUtil.removeSuffix( out_file.toString() )
307 + SUFFIX_FOR_SPECIES_TREE_USED );
309 final PhylogenyWriter writer = new PhylogenyWriter();
310 writer.toPhyloXML( species_tree_used_file, species_tree, 0 );
312 catch ( final IOException e ) {
313 ForesterUtil.fatalError( PRG_NAME, "Failed to write to [" + species_tree_used_file.getCanonicalPath()
314 + "]: " + e.getMessage() );
316 System.out.println( "Wrote (stripped) species tree to : " + species_tree_used_file.getCanonicalPath() );
317 log_writer.println( "Wrote (stripped) species tree to : " + species_tree_used_file.getCanonicalPath() );
318 if ( ( gsdii.getReMappedScientificNamesFromGeneTree() != null )
319 && !gsdii.getReMappedScientificNamesFromGeneTree().isEmpty() ) {
320 System.out.println( "Number of gene tree species remapped : "
321 + gsdii.getReMappedScientificNamesFromGeneTree().size() );
322 log_writer.println( "Number of gene tree species remapped : "
323 + gsdii.getReMappedScientificNamesFromGeneTree().size() );
324 writeToRemappedFile( out_file, gsdii.getReMappedScientificNamesFromGeneTree(), log_writer );
326 System.out.println( "Number of external nodes in gene tree : " + gene_tree.getNumberOfExternalNodes() );
327 log_writer.println( "Number of external nodes in gene tree : " + gene_tree.getNumberOfExternalNodes() );
328 System.out.println( "Number of external nodes in species tree : " + species_tree.getNumberOfExternalNodes() );
329 log_writer.println( "Number of external nodes in species tree : " + species_tree.getNumberOfExternalNodes() );
330 final int poly = PhylogenyMethods.countNumberOfPolytomies( species_tree );
331 System.out.println( "Number of polytomies in species tree : " + poly );
332 log_writer.println( "Number of polytomies in species tree : " + poly );
333 System.out.println( "External nodes stripped from gene tree : "
334 + gsdii.getStrippedExternalGeneTreeNodes().size() );
335 log_writer.println( "External nodes stripped from gene tree : "
336 + gsdii.getStrippedExternalGeneTreeNodes().size() );
337 System.out.println( "External nodes stripped from species tree: " + gsdii.getStrippedSpeciesTreeNodes().size() );
338 log_writer.println( "External nodes stripped from species tree: " + gsdii.getStrippedSpeciesTreeNodes().size() );
339 System.out.println();
340 System.out.println( "Number of speciations : " + gsdii.getSpeciationsSum() );
341 log_writer.println( "Number of speciations : " + gsdii.getSpeciationsSum() );
342 if ( ( base_algorithm == ALGORITHM.GSDIR ) ) {
343 final GSDIR gsdir = ( GSDIR ) gsdii;
344 System.out.println( "Minimal number of duplications : " + gsdir.getMinDuplicationsSum() );
345 log_writer.println( "Minimal number of duplications : " + gsdir.getMinDuplicationsSum() );
347 else if ( ( base_algorithm == ALGORITHM.GSDI ) ) {
348 final GSDI gsdi = ( GSDI ) gsdii;
349 System.out.println( "Number of duplications : " + gsdi.getDuplicationsSum() );
350 log_writer.println( "Number of duplications : " + gsdi.getDuplicationsSum() );
351 if ( !most_parsimonous_duplication_model ) {
352 final int u = gsdi.getSpeciationOrDuplicationEventsSum();
353 System.out.println( "Number of potential duplications : " + u );
354 log_writer.println( "Number of potential duplications : " + u );
357 log_writer.println();
358 printMappedNodesToLog( log_writer, gsdii );
359 log_writer.println();
360 printStrippedGeneTreeNodesToLog( log_writer, gsdii );
361 System.out.println();
362 System.out.println( "Wrote log to : " + log_file.getCanonicalPath() );
363 System.out.println();
367 private static void fatalError( final String type, final String msg, final EasyWriter log_writer ) {
370 log_writer.println();
371 log_writer.print( type.toUpperCase() + ": " );
372 log_writer.println( msg );
375 catch ( final IOException e ) {
378 ForesterUtil.fatalError( gsdi.PRG_NAME, msg );
381 private static void print_help() {
382 System.out.println( "Usage: " + gsdi.PRG_NAME
383 + " [-options] <gene tree in phyloXML format> <species tree> <outfile>" );
384 System.out.println();
385 System.out.println( "Options:" );
386 System.out.println( " -" + gsdi.ALLOW_STRIPPING_OF_GENE_TREE_OPTION
387 + ": to allow stripping of gene tree nodes without a matching species" );
388 System.out.println( " -" + gsdi.MOST_PARSIMONIOUS_OPTION
389 + ": use most parimonious duplication model for GSDI: " );
390 System.out.println( " assign nodes as speciations which would otherwise be assiged" );
391 System.out.println( " as potential duplications due to polytomies in the species tree" );
392 System.out.println( " -" + gsdi.GUESS_FORMAT_OF_SPECIES_TREE
393 + ": to allow species tree in other formats than phyloXML (i.e. Newick, NHX, Nexus)" );
394 System.out.println( " -" + gsdi.GSDIR_OPTION
395 + ": to use GSDIR algorithm instead of GSDI algorithm (re-rooting)" );
396 System.out.println( " -" + TRANSFER_TAXONOMY_OPTION
397 + ": to transfer taxonomic data from species tree to gene tree\n" );
398 System.out.println();
399 System.out.println( "Gene tree:" );
400 System.out.println( " in phyloXM format, with taxonomy and sequence data in appropriate fields" );
401 System.out.println();
402 System.out.println( "Species tree:" );
403 System.out.println( " in phyloXML format (unless option -" + gsdi.GUESS_FORMAT_OF_SPECIES_TREE + " is used)" );
404 System.out.println();
405 System.out.println( "Example: gsdi -" + ALLOW_STRIPPING_OF_GENE_TREE_OPTION
406 + " gene_tree.xml tree_of_life.xml out.xml" );
407 System.out.println();
410 private static void printMappedNodesToLog( final EasyWriter log_writer, final GSDII gsdi ) throws IOException {
411 final SortedSet<String> ss = new TreeSet<String>();
412 for( final PhylogenyNode n : gsdi.getMappedExternalSpeciesTreeNodes() ) {
413 ss.add( n.toString() );
415 log_writer.println( "The following " + ss.size() + " species were used: " );
416 for( final String s : ss ) {
417 log_writer.println( " " + s );
421 private static void printStrippedGeneTreeNodesToLog( final EasyWriter log_writer, final GSDII gsdi )
423 final SortedMap<String, Integer> sm = new TreeMap<String, Integer>();
424 for( final PhylogenyNode n : gsdi.getStrippedExternalGeneTreeNodes() ) {
425 final String s = n.toString();
426 if ( sm.containsKey( s ) ) {
427 sm.put( s, sm.get( s ) + 1 );
433 log_writer.println( "The following " + sm.size() + " nodes were stripped from the gene tree: " );
434 for( final String s : sm.keySet() ) {
435 final int count = sm.get( s );
437 log_writer.println( " " + s );
440 log_writer.println( " " + s + " [" + count + "]" );
445 private static void writeToRemappedFile( final File out_file,
446 final SortedSet<String> remapped,
447 final EasyWriter log_writer ) throws IOException {
448 final File file = new File( ForesterUtil.removeSuffix( out_file.toString() ) + REMAPPED_SUFFIX );
449 final EasyWriter remapped_writer = ForesterUtil.createEasyWriter( file );
450 for( final String s : remapped ) {
451 remapped_writer.println( s );
453 remapped_writer.close();
454 System.out.println( "Wrote remapped gene tree species to : " + file.getCanonicalPath() );
455 log_writer.println( "Wrote remapped gene tree species to : " + file.getCanonicalPath() );