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
7 // Copyright (C) 2000-2001 Washington University School of Medicine
8 // and Howard Hughes Medical Institute
11 // This library is free software; you can redistribute it and/or
12 // modify it under the terms of the GNU Lesser General Public
13 // License as published by the Free Software Foundation; either
14 // version 2.1 of the License, or (at your option) any later version.
16 // This library is distributed in the hope that it will be useful,
17 // but WITHOUT ANY WARRANTY; without even the implied warranty of
18 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
19 // Lesser General Public License for more details.
21 // You should have received a copy of the GNU Lesser General Public
22 // License along with this library; if not, write to the Free Software
23 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
25 // Contact: phylosoft @ gmail . com
26 // WWW: www.phylosoft.org/forester
28 package org.forester.application;
31 import java.io.FileWriter;
32 import java.io.PrintWriter;
33 import java.util.ArrayList;
34 import java.util.List;
36 import org.forester.io.parsers.phyloxml.PhyloXmlParser;
37 import org.forester.phylogeny.Phylogeny;
38 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
39 import org.forester.phylogeny.factories.PhylogenyFactory;
40 import org.forester.sdi.RIO;
41 import org.forester.util.CommandLineArguments;
42 import org.forester.util.ForesterUtil;
46 final static private String PRG_NAME = "rio";
47 final static private String PRG_VERSION = "3.00 beta 1";
48 final static private String PRG_DATE = "2010.01.15";
49 final static private String E_MAIL = "czmasek@burnham.org";
50 final static private String WWW = "www.phylosoft.org/forester/";
51 final static private String HELP_OPTION_1 = "help";
52 final static private String HELP_OPTION_2 = "h";
53 final static private String QUERY_OPTION = "q";
54 final static private String SORT_OPTION = "s";
55 final static private String OUTPUT_ULTRA_P_OPTION = "u";
56 final static private String CUTOFF_ULTRA_P_OPTION = "cu";
57 final static private String CUTOFF_ORTHO_OPTION = "co";
58 final static private String TABLE_OUTPUT_OPTION = "t";
60 public static void main( final String[] args ) {
61 ForesterUtil.printProgramInformation( PRG_NAME,
62 "resampled inference of orthologs",
67 ForesterUtil.getForesterLibraryInformation() );
68 CommandLineArguments cla = null;
70 cla = new CommandLineArguments( args );
72 catch ( final Exception e ) {
73 ForesterUtil.fatalError( PRG_NAME, e.getMessage() );
75 if ( cla.isOptionSet( HELP_OPTION_1 ) || cla.isOptionSet( HELP_OPTION_2 ) || ( args.length == 0 ) ) {
79 if ( ( args.length < 3 ) || ( args.length > 10 ) ) {
81 System.out.println( "[" + PRG_NAME + "] incorrect number of arguments" );
86 final List<String> allowed_options = new ArrayList<String>();
87 allowed_options.add( QUERY_OPTION );
88 allowed_options.add( SORT_OPTION );
89 allowed_options.add( CUTOFF_ULTRA_P_OPTION );
90 allowed_options.add( CUTOFF_ORTHO_OPTION );
91 allowed_options.add( TABLE_OUTPUT_OPTION );
92 allowed_options.add( OUTPUT_ULTRA_P_OPTION );
93 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
94 if ( dissallowed_options.length() > 0 ) {
95 ForesterUtil.fatalError( PRG_NAME, "unknown option(s): " + dissallowed_options );
97 final File multiple_trees_file = cla.getFile( 0 );
98 final File species_tree_file = cla.getFile( 1 );
99 final File outfile = cla.getFile( 2 );
100 ForesterUtil.fatalErrorIfFileNotReadable( PRG_NAME, multiple_trees_file );
101 ForesterUtil.fatalErrorIfFileNotReadable( PRG_NAME, species_tree_file );
102 if ( outfile.exists() ) {
103 ForesterUtil.fatalError( PRG_NAME, "[" + outfile + "] already exists" );
105 String seq_name = null;
106 if ( cla.isOptionSet( QUERY_OPTION ) ) {
107 seq_name = cla.getOptionValue( QUERY_OPTION );
109 File table_outfile = null;
110 if ( cla.isOptionSet( TABLE_OUTPUT_OPTION ) ) {
111 table_outfile = new File( cla.getOptionValue( TABLE_OUTPUT_OPTION ) );
112 if ( table_outfile.exists() ) {
113 ForesterUtil.fatalError( PRG_NAME, "[" + outfile + "] already exists" );
116 boolean output_ultraparalogs = false;
117 if ( cla.isOptionSet( OUTPUT_ULTRA_P_OPTION ) ) {
118 output_ultraparalogs = true;
120 double t_orthologs = 0.0;
121 double threshold_ultra_paralogs = 0.0;
124 if ( cla.isOptionSet( CUTOFF_ORTHO_OPTION ) ) {
125 t_orthologs = cla.getOptionValueAsDouble( CUTOFF_ORTHO_OPTION );
127 if ( cla.isOptionSet( CUTOFF_ULTRA_P_OPTION ) ) {
128 threshold_ultra_paralogs = cla.getOptionValueAsDouble( CUTOFF_ULTRA_P_OPTION );
130 if ( cla.isOptionSet( SORT_OPTION ) ) {
131 sort = cla.getOptionValueAsInt( SORT_OPTION );
134 catch ( final Exception e ) {
135 ForesterUtil.fatalError( PRG_NAME, "error in command line: " + e.getLocalizedMessage() );
140 else if ( sort > 2 ) {
144 System.out.println( "\n" );
145 System.out.println( "Gene trees: " + multiple_trees_file );
146 System.out.println( "Species tree: " + species_tree_file );
147 System.out.println( "Query: " + seq_name );
148 System.out.println( "Outfile: " + outfile );
149 System.out.println( "Outfile: " + table_outfile );
150 System.out.println( "Sort: " + sort );
151 System.out.println( "Threshold orthologs: " + t_orthologs );
152 if ( output_ultraparalogs ) {
153 System.out.println( "Threshold ultra paralogs: " + threshold_ultra_paralogs );
155 time = System.currentTimeMillis();
156 Phylogeny species_tree = null;
158 final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
159 species_tree = factory.create( species_tree_file, new PhyloXmlParser() )[ 0 ];
161 catch ( final Exception e ) {
165 if ( !species_tree.isRooted() ) {
166 ForesterUtil.printErrorMessage( PRG_NAME, "Species tree is not rooted" );
169 if ( !species_tree.isCompletelyBinary() ) {
170 ForesterUtil.printErrorMessage( PRG_NAME, "Species tree is not completely binary" );
173 final RIO rio_instance = new RIO();
174 final StringBuffer output = new StringBuffer();
175 PrintWriter out = null;
177 rio_instance.inferOrthologs( multiple_trees_file, species_tree.copy(), seq_name );
178 output.append( rio_instance.inferredOrthologsToString( seq_name, sort, t_orthologs ) );
179 if ( output_ultraparalogs ) {
180 output.append( "\n\nUltra paralogs:\n" );
181 output.append( rio_instance.inferredUltraParalogsToString( seq_name, threshold_ultra_paralogs ) );
183 output.append( "\n\nSort priority: " + RIO.getOrder( sort ) );
184 output.append( "\nExt nodes : " + rio_instance.getExtNodesOfAnalyzedGeneTrees() );
185 output.append( "\nSamples : " + rio_instance.getNumberOfSamples() + "\n" );
186 out = new PrintWriter( new FileWriter( outfile ), true );
188 catch ( final Exception e ) {
189 ForesterUtil.printErrorMessage( PRG_NAME, e.getLocalizedMessage() );
193 out.println( output );
195 ForesterUtil.programMessage( PRG_NAME, "wrote results to \"" + outfile + "\"" );
196 time = System.currentTimeMillis() - time;
197 ForesterUtil.programMessage( PRG_NAME, "time: " + time + "ms" );
198 ForesterUtil.programMessage( PRG_NAME, "OK." );
202 private final static void printHelp() {
203 System.out.println( "Usage:" );
204 System.out.println();
205 System.out.println( PRG_NAME + " [options] <gene trees file> <species tree file> [outfile]" );
206 System.out.println();
207 System.out.println( "options:" );
208 System.out.println();
209 // System.out.println( " -" + STRICT_OPTION
210 // + " : strict [default: non-strict]: all nodes between 'target' and 'evaluators' must match" );
211 // System.out.println( " -" + NORMALIZE_OPTION
212 // + "=<d>: normalize to this value (e.g. 100 for most bootstrap analyses) [default: no normalization]" );
213 // System.out.println( " -" + FIRST_OPTION + "=<i>: first evaluator topology to use (0-based) [default: 0]" );
214 // System.out.println( " -" + LAST_OPTION
215 // + "=<i>: last evaluator topology to use (0-based) [default: use all until final topology]" );
216 // System.out.println();
217 // System.out.println( "M= (String) Multiple gene tree file (mandatory)" );
218 // System.out.println( "N= (String) Query sequence name (mandatory)" );
219 // System.out.println( "S= (String) Species tree file (mandatory)" );
220 // System.out.println( "O= (String) Output file name -- overwritten without warning! (mandatory)" );
221 // System.out.println( "P= (int) Sort priority" );
222 // System.out.println( "L= (double) Threshold orthologs for output" );
223 // System.out.println( " Sort priority (\"P=\"):" );
224 System.out.println( RIO.getOrderHelp().toString() );
225 System.out.println();
227 .println( " Example: \"rio -q=D_NEMVE -s=1 -t=out -u Bcl-2_e1_20_mafft_05_40_fme.mlt species.xml out\"" );
228 System.out.println();