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.util.ArrayList;
31 import java.util.Date;
32 import java.util.List;
35 import org.forester.io.parsers.PhylogenyParser;
36 import org.forester.io.parsers.nhx.NHXParser;
37 import org.forester.io.parsers.phyloxml.PhyloXmlParser;
38 import org.forester.io.parsers.util.ParserUtils;
39 import org.forester.io.writers.PhylogenyWriter;
40 import org.forester.phylogeny.Phylogeny;
41 import org.forester.phylogeny.PhylogenyMethods;
42 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
43 import org.forester.phylogeny.factories.PhylogenyFactory;
44 import org.forester.sdi.GSDI;
45 import org.forester.sdi.SDI;
46 import org.forester.sdi.SDIse;
47 import org.forester.util.CommandLineArguments;
48 import org.forester.util.ForesterUtil;
50 public final class gsdi {
52 final static public boolean REPLACE_UNDERSCORES_IN_NH_SPECIES_TREE = true;
53 final static private String STRIP_OPTION = "s";
54 final static private String SDI_OPTION = "b";
55 final static private String MOST_PARSIMONIOUS_OPTION = "m";
56 final static private String GUESS_FORMAT_OF_SPECIES_TREE = "q";
57 final static private String HELP_OPTION_1 = "help";
58 final static private String HELP_OPTION_2 = "h";
59 final static private String DEFAULT_OUTFILE = "gsdi_out.phylo.xml";
60 final static private String PRG_NAME = "gsdi";
61 final static private String PRG_VERSION = "0.5";
62 final static private String PRG_DATE = "120608";
63 final static private String PRG_DESC = "general speciation duplication inference";
64 final static private String E_MAIL = "phylosoft@gmail.com";
65 final static private String WWW = "www.phylosoft.org/forester";
67 public static void main( final String args[] ) {
68 ForesterUtil.printProgramInformation( PRG_NAME,
74 ForesterUtil.getForesterLibraryInformation() );
75 CommandLineArguments cla = null;
77 cla = new CommandLineArguments( args );
79 catch ( final Exception e ) {
80 ForesterUtil.fatalError( PRG_NAME, e.getMessage() );
82 if ( cla.isOptionSet( gsdi.HELP_OPTION_1 ) || cla.isOptionSet( gsdi.HELP_OPTION_2 ) ) {
87 else if ( ( args.length < 2 ) || ( cla.getNumberOfNames() < 2 ) || ( cla.getNumberOfNames() > 3 ) ) {
89 System.out.println( "Wrong number of arguments." );
94 final List<String> allowed_options = new ArrayList<String>();
95 allowed_options.add( gsdi.STRIP_OPTION );
96 allowed_options.add( gsdi.SDI_OPTION );
97 allowed_options.add( gsdi.GUESS_FORMAT_OF_SPECIES_TREE );
98 allowed_options.add( gsdi.MOST_PARSIMONIOUS_OPTION );
99 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
100 if ( dissallowed_options.length() > 0 ) {
101 ForesterUtil.fatalError( gsdi.PRG_NAME, "unknown option(s): " + dissallowed_options );
103 boolean use_sdise = false;
104 boolean strip = false;
105 boolean most_parsimonous_duplication_model = false;
106 boolean species_tree_in_phyloxml = true;
107 if ( cla.isOptionSet( gsdi.STRIP_OPTION ) ) {
110 if ( cla.isOptionSet( gsdi.SDI_OPTION ) ) {
113 if ( cla.isOptionSet( gsdi.MOST_PARSIMONIOUS_OPTION ) ) {
115 ForesterUtil.fatalError( gsdi.PRG_NAME, "Can only use most parsimonious duplication mode with GSDI" );
117 most_parsimonous_duplication_model = true;
119 if ( cla.isOptionSet( gsdi.GUESS_FORMAT_OF_SPECIES_TREE ) ) {
120 species_tree_in_phyloxml = false;
122 Phylogeny species_tree = null;
123 Phylogeny gene_tree = null;
124 File gene_tree_file = null;
125 File species_tree_file = null;
126 File out_file = null;
128 gene_tree_file = cla.getFile( 0 );
129 species_tree_file = cla.getFile( 1 );
130 if ( cla.getNumberOfNames() == 3 ) {
131 out_file = cla.getFile( 2 );
134 out_file = new File( gsdi.DEFAULT_OUTFILE );
137 catch ( final IllegalArgumentException e ) {
138 ForesterUtil.fatalError( gsdi.PRG_NAME, "error in command line: " + e.getMessage() );
140 if ( ForesterUtil.isReadableFile( gene_tree_file ) != null ) {
141 ForesterUtil.fatalError( gsdi.PRG_NAME, ForesterUtil.isReadableFile( gene_tree_file ) );
143 if ( ForesterUtil.isReadableFile( species_tree_file ) != null ) {
144 ForesterUtil.fatalError( gsdi.PRG_NAME, ForesterUtil.isReadableFile( species_tree_file ) );
146 if ( ForesterUtil.isWritableFile( out_file ) != null ) {
147 ForesterUtil.fatalError( gsdi.PRG_NAME, ForesterUtil.isWritableFile( out_file ) );
150 final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
151 if ( species_tree_in_phyloxml ) {
152 species_tree = factory.create( species_tree_file, new PhyloXmlParser() )[ 0 ];
155 final PhylogenyParser p = ParserUtils.createParserDependingOnFileType( species_tree_file, true );
156 if ( REPLACE_UNDERSCORES_IN_NH_SPECIES_TREE && p instanceof NHXParser ) {
157 (( NHXParser ) p ).setReplaceUnderscores( true );
159 species_tree = factory.create( species_tree_file, p )[ 0 ];
160 PhylogenyMethods.transferNodeNameToField( species_tree,
161 PhylogenyMethods.PhylogenyNodeField.TAXONOMY_SCIENTIFIC_NAME );
165 catch ( final IOException e ) {
166 ForesterUtil.fatalError( gsdi.PRG_NAME,
167 "Failed to read species tree from [" + gene_tree_file + "]: " + e.getMessage() );
171 final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
172 gene_tree = factory.create( gene_tree_file, new PhyloXmlParser() )[ 0 ];
174 catch ( final IOException e ) {
175 ForesterUtil.fatalError( gsdi.PRG_NAME,
176 "Failed to read gene tree from [" + gene_tree_file + "]: " + e.getMessage() );
178 gene_tree.setRooted( true );
179 species_tree.setRooted( true );
180 if ( !gene_tree.isCompletelyBinary() ) {
181 ForesterUtil.fatalError( gsdi.PRG_NAME, "gene tree (\"" + gene_tree_file + "\") is not completely binary" );
184 if ( !species_tree.isCompletelyBinary() ) {
185 ForesterUtil.fatalError( gsdi.PRG_NAME, "species tree (\"" + species_tree_file
186 + "\") is not completely binary" );
190 // gene_tree = Helper.createBalancedTree( 10 );
191 // species_tree = Helper.createBalancedTree( 13 );
192 // species_tree = Helper.createUnbalancedTree( 1024 );
193 // gene_tree = Helper.createUnbalancedTree( 8192 );
194 // species_tree = gene_tree.copyTree();
195 // gene_tree = species_tree.copyTree();
196 // Helper.numberSpeciesInOrder( species_tree );
197 // Helper.numberSpeciesInOrder( gene_tree );
198 // Helper.randomizeSpecies( 1, 8192, gene_tree );
199 // Helper.intervalNumberSpecies( gene_tree, 4096 );
200 // Helper.numberSpeciesInDescOrder( gene_tree );
201 System.out.println();
202 System.out.println( "Strip species tree: " + strip );
204 final long start_time = new Date().getTime();
207 System.out.println();
208 System.out.println( "Using SDIse algorithm" );
209 sdi = new SDIse( gene_tree, species_tree );
212 System.out.println();
213 System.out.println( "Using GSDI algorithm" );
214 System.out.println();
215 System.out.println( "Use most parsimonous duplication model: " + most_parsimonous_duplication_model );
216 sdi = new GSDI( gene_tree, species_tree, most_parsimonous_duplication_model, true );
219 catch ( final Exception e ) {
220 ForesterUtil.fatalError( PRG_NAME, e.getLocalizedMessage() );
222 System.out.println();
223 System.out.println( "Running time (excluding I/O): " + ( new Date().getTime() - start_time ) + "ms" );
225 final PhylogenyWriter writer = new PhylogenyWriter();
226 writer.toPhyloXML( out_file, gene_tree, 0 );
228 catch ( final IOException e ) {
229 ForesterUtil.fatalError( PRG_NAME, "Failed to write to [" + out_file + "]: " + e.getMessage() );
231 System.out.println();
232 System.out.println( "Successfully wrote resulting gene tree to: " + out_file );
233 System.out.println();
235 sdi.computeMappingCostL();
236 System.out.println( "Mapping cost : " + sdi.computeMappingCostL() );
238 System.out.println( "Number of duplications : " + sdi.getDuplicationsSum() );
239 if ( !use_sdise && !most_parsimonous_duplication_model ) {
240 System.out.println( "Number of potential duplications: "
241 + ( ( GSDI ) sdi ).getSpeciationOrDuplicationEventsSum() );
244 System.out.println( "Number speciations : " + ( ( GSDI ) sdi ).getSpeciationsSum() );
246 System.out.println();
249 private static void print_help() {
250 System.out.println( "Usage: " + gsdi.PRG_NAME
251 + " [-options] <gene tree in phyloXML format> <species tree in phyloXML format> [outfile]" );
252 System.out.println();
253 System.out.println( "Options:" );
254 System.out.println( " -" + gsdi.STRIP_OPTION + ": to strip the species tree prior to duplication inference" );
255 System.out.println( " -" + gsdi.SDI_OPTION + ": to use SDI algorithm instead of GSDI algorithm" );
256 System.out.println( " -" + gsdi.MOST_PARSIMONIOUS_OPTION
257 + ": use most parimonious duplication model for GSDI: " );
258 System.out.println( " assign nodes as speciations which would otherwise be assiged" );
259 System.out.println( " as unknown because of polytomies in the species tree" );
260 System.out.println( " -" + gsdi.GUESS_FORMAT_OF_SPECIES_TREE + ": to allow species tree in other formats than" );
261 System.out.println( " phyloXML (Newick, NHX, Nexus)" );
262 System.out.println();
263 System.out.println( "Species tree:" );
264 System.out.println( " In phyloXML format (unless option -" + gsdi.GUESS_FORMAT_OF_SPECIES_TREE
265 + " is used), with taxonomy data in appropriate fields" );
266 System.out.println();
267 System.out.println( "Gene tree:" );
268 System.out.println( " In phyloXM format, with taxonomy and sequence data in appropriate fields" );
269 System.out.println();
270 System.out.println( "Note -- GSDI algorithm is under development" );
271 System.out.println();