2 // forester -- software libraries and applications
3 // for genomics and evolutionary biology research.
5 // Copyright (C) 2010 Christian M Zmasek
6 // Copyright (C) 2010 Sanford-Burnham Medical Research Institute
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.archaeopteryx.tools;
28 import java.io.BufferedWriter;
29 import java.io.FileWriter;
30 import java.io.IOException;
31 import java.util.ArrayList;
32 import java.util.List;
34 import javax.swing.JOptionPane;
36 import org.forester.archaeopteryx.MainFrameApplication;
37 import org.forester.evoinference.distance.NeighborJoiningF;
38 import org.forester.evoinference.distance.PairwiseDistanceCalculator;
39 import org.forester.evoinference.matrix.distance.BasicSymmetricalDistanceMatrix;
40 import org.forester.evoinference.tools.BootstrapResampler;
41 import org.forester.msa.BasicMsa;
42 import org.forester.msa.Mafft;
43 import org.forester.msa.Msa;
44 import org.forester.msa.Msa.MSA_FORMAT;
45 import org.forester.msa.MsaInferrer;
46 import org.forester.msa.MsaMethods;
47 import org.forester.msa.ResampleableMsa;
48 import org.forester.phylogeny.Phylogeny;
49 import org.forester.phylogeny.PhylogenyMethods;
50 import org.forester.sequence.MolecularSequence;
51 import org.forester.tools.ConfidenceAssessor;
52 import org.forester.util.ForesterUtil;
54 public class PhylogeneticInferrer extends RunnableProcess {
57 private final MainFrameApplication _mf;
58 private final PhylogeneticInferenceOptions _options;
59 private final List<MolecularSequence> _seqs;
60 private final boolean DEBUG = true;
61 public final static String MSA_FILE_SUFFIX = ".aln";
62 public final static String PWD_FILE_SUFFIX = ".pwd";
64 public PhylogeneticInferrer( final List<MolecularSequence> seqs,
65 final PhylogeneticInferenceOptions options,
66 final MainFrameApplication mf ) {
73 public PhylogeneticInferrer( final Msa msa,
74 final PhylogeneticInferenceOptions options,
75 final MainFrameApplication mf ) {
82 private Msa inferMsa( final MSA_PRG msa_prg ) throws IOException, InterruptedException {
83 // final File temp_seqs_file = File.createTempFile( "__msa__temp__", ".fasta" );
85 // System.out.println();
86 // System.out.println( "temp file: " + temp_seqs_file );
87 // System.out.println();
89 // //final File temp_seqs_file = new File( _options.getTempDir() + ForesterUtil.FILE_SEPARATOR + "s.fasta" );
90 // final BufferedWriter writer = new BufferedWriter( new FileWriter( temp_seqs_file ) );
91 // SequenceWriter.writeSeqs( _seqs, writer, SEQ_FORMAT.FASTA, 100 );
95 return runMAFFT( _seqs, processMafftOptions() );
101 private List<String> processMafftOptions() {
102 final String opts_str = _options.getMsaPrgParameters().trim().toLowerCase();
103 final String[] opts_ary = opts_str.split( " " );
104 final List<String> opts = new ArrayList<String>();
105 boolean saw_quiet = false;
106 for( final String opt : opts_ary ) {
108 if ( opt.equals( "--quiet" ) ) {
113 opts.add( "--quiet" );
118 private Phylogeny inferPhylogeny( final Msa msa ) {
119 BasicSymmetricalDistanceMatrix m = null;
120 switch ( _options.getPwdDistanceMethod() ) {
121 case KIMURA_DISTANCE:
122 m = PairwiseDistanceCalculator.calcKimuraDistances( msa );
124 case POISSON_DISTANCE:
125 m = PairwiseDistanceCalculator.calcPoissonDistances( msa );
127 case FRACTIONAL_DISSIMILARITY:
128 m = PairwiseDistanceCalculator.calcFractionalDissimilarities( msa );
131 throw new RuntimeException( "invalid pwd method" );
133 if ( !ForesterUtil.isEmpty( _options.getIntermediateFilesBase() ) ) {
134 BufferedWriter pwd_writer;
136 pwd_writer = new BufferedWriter( new FileWriter( _options.getIntermediateFilesBase() + PWD_FILE_SUFFIX ) );
137 m.write( pwd_writer );
140 catch ( final IOException e ) {
141 // TODO Auto-generated catch block
145 final NeighborJoiningF nj = NeighborJoiningF.createInstance( false, 5 );
146 final Phylogeny phy = nj.execute( m );
147 PhylogenyMethods.addMolecularSeqsToTree( phy, msa );
148 PhylogenyMethods.extractFastaInformation( phy );
152 private void infer() throws InterruptedException {
153 //_mf.getMainPanel().getCurrentTreePanel().setWaitCursor();
154 if ( ( _msa == null ) && ( _seqs == null ) ) {
155 throw new IllegalArgumentException( "cannot run phylogenetic analysis with null msa and seq array" );
157 start( _mf, "phylogenetic inference" );
158 if ( _msa == null ) {
161 msa = inferMsa( MSA_PRG.MAFFT );
163 catch ( final IOException e ) {
165 JOptionPane.showMessageDialog( _mf,
166 "Could not create multiple sequence alignment with \""
167 + _options.getMsaPrg() + "\" and the following parameters:\n\""
168 + _options.getMsaPrgParameters() + "\"\nError: "
169 + e.getLocalizedMessage(),
170 "Failed to Calculate MSA",
171 JOptionPane.ERROR_MESSAGE );
177 catch ( final Exception e ) {
179 JOptionPane.showMessageDialog( _mf,
180 "Could not create multiple sequence alignment with \""
181 + _options.getMsaPrg() + "\" and the following parameters:\n\""
182 + _options.getMsaPrgParameters() + "\"\nError: "
183 + e.getLocalizedMessage(),
184 "Unexpected Exception During MSA Calculation",
185 JOptionPane.ERROR_MESSAGE );
193 JOptionPane.showMessageDialog( _mf,
194 "Could not create multiple sequence alignment with "
195 + _options.getMsaPrg() + "\nand the following parameters:\n\""
196 + _options.getMsaPrgParameters() + "\"",
197 "Failed to Calculate MSA",
198 JOptionPane.ERROR_MESSAGE );
202 System.out.println( msa.toString() );
203 System.out.println( MsaMethods.calcGapRatio( msa ) );
205 final MsaMethods msa_tools = MsaMethods.createInstance();
206 if ( _options.isExecuteMsaProcessing() ) {
207 msa = msa_tools.deleteGapColumns( _options.getMsaProcessingMaxAllowedGapRatio(),
208 _options.getMsaProcessingMinAllowedLength(),
212 JOptionPane.showMessageDialog( _mf,
213 "Less than two sequences longer than "
214 + _options.getMsaProcessingMinAllowedLength()
215 + " residues left after MSA processing",
216 "MSA Processing Settings Too Stringent",
217 JOptionPane.ERROR_MESSAGE );
222 System.out.println( msa_tools.getIgnoredSequenceIds() );
223 System.out.println( msa.toString() );
224 System.out.println( MsaMethods.calcGapRatio( msa ) );
228 final int n = _options.getBootstrapSamples();
229 final long seed = _options.getRandomNumberGeneratorSeed();
230 final Phylogeny master_phy = inferPhylogeny( _msa );
231 if ( _options.isPerformBootstrapResampling() && ( n > 0 ) ) {
232 final ResampleableMsa resampleable_msa = new ResampleableMsa( ( BasicMsa ) _msa );
233 final int[][] resampled_column_positions = BootstrapResampler.createResampledColumnPositions( _msa
234 .getLength(), n, seed );
235 final Phylogeny[] eval_phys = new Phylogeny[ n ];
236 for( int i = 0; i < n; ++i ) {
237 resampleable_msa.resample( resampled_column_positions[ i ] );
238 eval_phys[ i ] = inferPhylogeny( resampleable_msa );
240 ConfidenceAssessor.evaluate( "bootstrap", eval_phys, master_phy, true, 1 );
242 _mf.getMainPanel().addPhylogenyInNewTab( master_phy, _mf.getConfiguration(), "nj", "njpath" );
243 // _mf.getMainPanel().getCurrentTreePanel().setArrowCursor();
245 JOptionPane.showMessageDialog( _mf,
246 "Inference successfully completed",
247 "Inference Completed",
248 JOptionPane.INFORMATION_MESSAGE );
256 catch ( final InterruptedException e ) {
257 // TODO need to handle this exception SOMEHOW!
258 // TODO Auto-generated catch block
263 private Msa runMAFFT( final List<MolecularSequence> seqs, final List<String> opts ) throws IOException,
264 InterruptedException {
266 final MsaInferrer mafft = Mafft.createInstance( _mf.getInferenceManager().getPathToLocalMafft()
267 .getCanonicalPath() );
269 msa = mafft.infer( seqs, opts );
271 catch ( final IOException e ) {
272 System.out.println( mafft.getErrorDescription() );
277 private void writeToFiles( final BasicSymmetricalDistanceMatrix m ) {
278 if ( !ForesterUtil.isEmpty( _options.getIntermediateFilesBase() ) ) {
280 final BufferedWriter msa_writer = new BufferedWriter( new FileWriter( _options.getIntermediateFilesBase()
281 + MSA_FILE_SUFFIX ) );
282 _msa.write( msa_writer, MSA_FORMAT.PHYLIP );
284 final BufferedWriter pwd_writer = new BufferedWriter( new FileWriter( _options.getIntermediateFilesBase()
285 + PWD_FILE_SUFFIX ) );
286 m.write( pwd_writer );
289 catch ( final Exception e ) {
290 System.out.println( "Error: " + e.getMessage() );
295 public enum MSA_PRG {