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.util.ArrayList;
31 import java.util.Arrays;
32 import java.util.List;
34 import org.forester.io.parsers.PhylogenyParser;
35 import org.forester.io.parsers.util.ParserUtils;
36 import org.forester.io.writers.PhylogenyWriter;
37 import org.forester.phylogeny.Phylogeny;
38 import org.forester.phylogeny.PhylogenyMethods;
39 import org.forester.phylogeny.PhylogenyNode;
40 import org.forester.phylogeny.data.Confidence;
41 import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
42 import org.forester.phylogeny.factories.PhylogenyFactory;
43 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
44 import org.forester.tools.SupportCount;
45 import org.forester.util.CommandLineArguments;
46 import org.forester.util.ForesterUtil;
48 public class count_support {
50 final static private String PRG_NAME = "count_support";
51 final static private String PRG_VERSION = "1.0";
52 final static private String PRG_DATE = "2008.03.04";
53 final static private String E_MAIL = "phylosoft@gmail.com";
54 final static private String WWW = "www.phylosoft.org/forester/";
55 private final static boolean WRITE_EVALUATORS_AS_NHX = false;
57 public static void main( final String args[] ) {
58 ForesterUtil.printProgramInformation( PRG_NAME,
64 ForesterUtil.getForesterLibraryInformation() );
65 if ( ( args.length < 3 ) || ( args.length > 7 ) ) {
67 System.out.println( count_support.PRG_NAME + ": wrong number of arguments" );
70 .println( "Usage: \"count_support [options] <file containing phylogeny to be evaluated> <file with phylogenies to be used for evaluation> <outfile> [outfile for evaluator phylogenies, "
71 + "always unstripped if -t=<d> option is used, otherwise strippedness is dependent on -s option]\"\n" );
73 .println( " Options: -s strip external nodes from evaluator phylogenies not found in phylogeny to be evaluated" );
74 System.out.println( " : -t=<d> threshold for similarity (0.0 to 1.0)" );
75 System.out.println( " : -n no branch lengths in outfile for evaluator phylogenies" );
79 CommandLineArguments cla = null;
81 cla = new CommandLineArguments( args );
83 catch ( final Exception e ) {
84 ForesterUtil.fatalError( PRG_NAME, e.getMessage() );
86 final List<String> allowed_options = new ArrayList<String>();
87 allowed_options.add( "s" );
88 allowed_options.add( "t" );
89 allowed_options.add( "n" );
90 final String dissallowed_options = cla.validateAllowedOptionsAsString( allowed_options );
91 if ( dissallowed_options.length() > 0 ) {
92 ForesterUtil.fatalError( count_support.PRG_NAME, "Unknown option(s): " + dissallowed_options );
94 final File phylogeny_infile = cla.getFile( 0 );
95 final File evaluators_infile = cla.getFile( 1 );
96 final File phylogeny_outfile = cla.getFile( 2 );
97 File evaluators_outfile = null;
98 boolean branch_lengths_in_ev_out = true;
99 if ( cla.isOptionSet( "n" ) ) {
100 branch_lengths_in_ev_out = false;
102 if ( cla.getNumberOfNames() == 4 ) {
103 evaluators_outfile = cla.getFile( 3 );
106 if ( !branch_lengths_in_ev_out ) {
107 ForesterUtil.fatalError( count_support.PRG_NAME,
108 "Cannot use -n option if no outfile for evaluators specified" );
112 Phylogeny[] ev = null;
114 final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
115 final PhylogenyParser pp = ParserUtils.createParserDependingOnFileType( phylogeny_infile, true );
116 p = factory.create( phylogeny_infile, pp )[ 0 ];
118 catch ( final Exception e ) {
119 ForesterUtil.fatalError( count_support.PRG_NAME,
120 "Could not read \"" + phylogeny_infile + "\" [" + e.getMessage() + "]" );
123 final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
124 final PhylogenyParser pp = ParserUtils.createParserDependingOnFileType( evaluators_infile, true );
125 ev = factory.create( evaluators_infile, pp );
127 catch ( final Exception e ) {
128 ForesterUtil.fatalError( count_support.PRG_NAME,
129 "Could not read \"" + evaluators_infile + "\" [" + e.getMessage() + "]" );
131 boolean strip = false;
132 if ( cla.isOptionSet( "s" ) ) {
135 double threshhold = -1.0;
136 if ( cla.isOptionSet( "t" ) ) {
138 threshhold = cla.getOptionValueAsDouble( "t" );
140 catch ( final Exception e ) {
141 ForesterUtil.fatalError( count_support.PRG_NAME, "error in command line arguments: " + e.getMessage() );
143 if ( ( threshhold < 0 ) || ( threshhold > 1.0 ) ) {
144 ForesterUtil.fatalError( count_support.PRG_NAME,
145 "support threshold has to be between 0.0 and 1.0 (inclusive)" );
148 List<Phylogeny> evaluator_phylogenies_above_threshold = null;
150 if ( threshhold >= 0 ) {
151 evaluator_phylogenies_above_threshold = SupportCount.count( p, ev, strip, threshhold, true );
152 if ( evaluator_phylogenies_above_threshold.size() < 1 ) {
153 ForesterUtil.fatalError( "count_support", "appears like threshold for similarity is set too high" );
157 SupportCount.count( p, ev, strip, true );
160 catch ( final Exception e ) {
161 ForesterUtil.fatalError( count_support.PRG_NAME, "Failure during support counting: " + e.getMessage() );
163 if ( threshhold >= 0 ) {
164 count_support.normalizeSupport( p, 100, evaluator_phylogenies_above_threshold.size() );
165 System.out.println( evaluator_phylogenies_above_threshold.size() + " out of " + ev.length
166 + " evaluator phylogenies are above threshold of " + threshhold );
169 final PhylogenyWriter w = new PhylogenyWriter();
170 w.toPhyloXML( phylogeny_outfile, p, 1 );
172 catch ( final IOException e ) {
173 ForesterUtil.fatalError( count_support.PRG_NAME, "Failure to write output [" + e.getMessage() + "]" );
175 System.out.println();
176 System.out.println( "Wrote phylogeny with support values to: " + phylogeny_outfile );
177 if ( evaluators_outfile != null ) {
179 final PhylogenyWriter w = new PhylogenyWriter();
180 if ( evaluator_phylogenies_above_threshold != null ) {
181 System.out.println( "Writing " + evaluator_phylogenies_above_threshold.size()
182 + " evaluator phylogenies above threshold of " + threshhold + " to: " + evaluators_outfile );
183 if ( count_support.WRITE_EVALUATORS_AS_NHX ) {
184 w.toNewHampshireX( evaluator_phylogenies_above_threshold, evaluators_outfile, ";"
185 + ForesterUtil.getLineSeparator() );
188 w.toNewHampshire( evaluator_phylogenies_above_threshold,
190 branch_lengths_in_ev_out,
192 ";" + ForesterUtil.getLineSeparator() );
196 System.out.println( "Writing " + ev.length + " evaluator phylogenies to :" + evaluators_outfile );
197 if ( count_support.WRITE_EVALUATORS_AS_NHX ) {
198 w.toNewHampshireX( Arrays.asList( ev ),
200 ";" + ForesterUtil.getLineSeparator() );
203 w.toNewHampshire( Arrays.asList( ev ), true, branch_lengths_in_ev_out, evaluators_outfile, ";"
204 + ForesterUtil.getLineSeparator() );
208 catch ( final IOException e ) {
209 ForesterUtil.fatalError( count_support.PRG_NAME, "Failure to write output [" + e.getMessage() + "]" );
212 System.out.println();
213 System.out.println( "Done." );
214 System.out.println();
217 private static void normalizeSupport( final Phylogeny p, final double normalized_max, final int number_phylos ) {
218 double min = Double.MAX_VALUE;
219 double max = -Double.MAX_VALUE;
222 for( final PhylogenyNodeIterator iter = p.iteratorPostorder(); iter.hasNext(); ) {
223 final PhylogenyNode node = iter.next();
224 if ( !node.isRoot() && !node.isExternal() ) {
225 final double b = PhylogenyMethods.getConfidenceValue( node );
229 if ( ( b >= 0 ) && ( b < min ) ) {
237 System.out.println( "Max support before normalization is : " + max );
238 System.out.println( "Min support before normalization is : " + min );
239 System.out.println( "Average support before normalization is: " + av + " (=" + sum + "/" + n + ")" );
240 System.out.println( "Normalizing so that theoretical maximum support value is: " + normalized_max );
241 System.out.println( "Number of phylogenies used in support analysis: " + number_phylos );
242 final double f = normalized_max / number_phylos;
243 min = Double.MAX_VALUE;
244 max = -Double.MAX_VALUE;
247 for( final PhylogenyNodeIterator iter = p.iteratorPostorder(); iter.hasNext(); ) {
248 final PhylogenyNode node = iter.next();
249 if ( node.isRoot() || node.isExternal() ) {
250 PhylogenyMethods.setBootstrapConfidence( node, Confidence.CONFIDENCE_DEFAULT_VALUE );
253 double b = PhylogenyMethods.getConfidenceValue( node );
255 PhylogenyMethods.setBootstrapConfidence( node, b );
259 if ( ( b >= 0 ) && ( b < min ) ) {
267 System.out.println( "Max support after normalization is : " + max );
268 System.out.println( "Min support after normalization is : " + min );
269 System.out.println( "Average support after normalization is: " + av + " (=" + sum + "/" + n + ")" );