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: www.phylosoft.org/forester
26 package org.forester.archaeopteryx.tools;
28 import java.io.BufferedWriter;
30 import java.io.FileWriter;
31 import java.io.IOException;
32 import java.util.ArrayList;
33 import java.util.List;
34 import java.util.regex.Matcher;
36 import javax.swing.JOptionPane;
38 import org.forester.archaeopteryx.AptxUtil;
39 import org.forester.archaeopteryx.MainFrameApplication;
40 import org.forester.evoinference.distance.NeighborJoining;
41 import org.forester.evoinference.distance.PairwiseDistanceCalculator;
42 import org.forester.evoinference.matrix.distance.BasicSymmetricalDistanceMatrix;
43 import org.forester.evoinference.tools.BootstrapResampler;
44 import org.forester.io.parsers.FastaParser;
45 import org.forester.io.writers.SequenceWriter;
46 import org.forester.io.writers.SequenceWriter.SEQ_FORMAT;
47 import org.forester.msa.BasicMsa;
48 import org.forester.msa.Mafft;
49 import org.forester.msa.Msa;
50 import org.forester.msa.MsaInferrer;
51 import org.forester.msa.MsaMethods;
52 import org.forester.msa.ResampleableMsa;
53 import org.forester.phylogeny.Phylogeny;
54 import org.forester.phylogeny.PhylogenyNode;
55 import org.forester.phylogeny.data.Accession;
56 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
57 import org.forester.sequence.Sequence;
58 import org.forester.tools.ConfidenceAssessor;
59 import org.forester.util.ForesterUtil;
61 public class PhylogeneticInferrer extends RunnableProcess {
64 private final MainFrameApplication _mf;
65 private final PhylogeneticInferenceOptions _options;
66 private final List<Sequence> _seqs;
67 private final boolean DEBUG = true;
68 public final static String MSA_FILE_SUFFIX = ".aln";
69 public final static String PWD_FILE_SUFFIX = ".pwd";
71 public PhylogeneticInferrer( final List<Sequence> seqs,
72 final PhylogeneticInferenceOptions options,
73 final MainFrameApplication mf ) {
80 public PhylogeneticInferrer( final Msa msa,
81 final PhylogeneticInferenceOptions options,
82 final MainFrameApplication mf ) {
89 private Msa inferMsa() throws IOException, InterruptedException {
90 final File temp_seqs_file = File.createTempFile( "__msa__temp__", ".fasta" );
93 System.out.println( "temp file: " + temp_seqs_file );
96 //final File temp_seqs_file = new File( _options.getTempDir() + ForesterUtil.FILE_SEPARATOR + "s.fasta" );
97 final BufferedWriter writer = new BufferedWriter( new FileWriter( temp_seqs_file ) );
98 SequenceWriter.writeSeqs( _seqs, writer, SEQ_FORMAT.FASTA, 100 );
100 final List<String> opts = processMafftOptions();
101 return runMAFFT( temp_seqs_file, opts );
104 private List<String> processMafftOptions() {
105 final String opts_str = _options.getMsaPrgParameters().trim().toLowerCase();
106 final String[] opts_ary = opts_str.split( " " );
107 final List<String> opts = new ArrayList<String>();
108 boolean saw_quiet = false;
109 for( final String opt : opts_ary ) {
111 if ( opt.equals( "--quiet" ) ) {
116 opts.add( "--quiet" );
121 private Phylogeny inferPhylogeny( final Msa msa ) {
122 BasicSymmetricalDistanceMatrix m = null;
123 switch ( _options.getPwdDistanceMethod() ) {
124 case KIMURA_DISTANCE:
125 m = PairwiseDistanceCalculator.calcKimuraDistances( msa );
127 case POISSON_DISTANCE:
128 m = PairwiseDistanceCalculator.calcPoissonDistances( msa );
130 case FRACTIONAL_DISSIMILARITY:
131 m = PairwiseDistanceCalculator.calcFractionalDissimilarities( msa );
134 throw new RuntimeException( "invalid pwd method" );
136 if ( !ForesterUtil.isEmpty( _options.getIntermediateFilesBase() ) ) {
137 BufferedWriter pwd_writer;
139 pwd_writer = new BufferedWriter( new FileWriter( _options.getIntermediateFilesBase() + PWD_FILE_SUFFIX ) );
140 m.write( pwd_writer );
143 catch ( final IOException e ) {
144 // TODO Auto-generated catch block
148 final NeighborJoining nj = NeighborJoining.createInstance();
149 final Phylogeny phy = nj.execute( m );
150 PhylogeneticInferrer.extractFastaInformation( phy );
154 private void infer() throws InterruptedException {
155 //_mf.getMainPanel().getCurrentTreePanel().setWaitCursor();
156 if ( ( _msa == null ) && ( _seqs == null ) ) {
157 throw new IllegalArgumentException( "cannot run phylogenetic analysis with null msa and seq array" );
159 start( _mf, "phylogenetic inference" );
160 if ( _msa == null ) {
165 catch ( final IOException e ) {
167 JOptionPane.showMessageDialog( _mf,
168 "Could not create multiple sequence alignment with \""
169 + _options.getMsaPrg() + "\" and the following parameters:\n\""
170 + _options.getMsaPrgParameters() + "\"\nError: "
171 + e.getLocalizedMessage(),
172 "Failed to Calculate MSA",
173 JOptionPane.ERROR_MESSAGE );
179 catch ( final Exception e ) {
181 JOptionPane.showMessageDialog( _mf,
182 "Could not create multiple sequence alignment with \""
183 + _options.getMsaPrg() + "\" and the following parameters:\n\""
184 + _options.getMsaPrgParameters() + "\"\nError: "
185 + e.getLocalizedMessage(),
186 "Unexpected Exception During MSA Calculation",
187 JOptionPane.ERROR_MESSAGE );
195 JOptionPane.showMessageDialog( _mf,
196 "Could not create multiple sequence alignment with "
197 + _options.getMsaPrg() + "\nand the following parameters:\n\""
198 + _options.getMsaPrgParameters() + "\"",
199 "Failed to Calculate MSA",
200 JOptionPane.ERROR_MESSAGE );
204 System.out.println( msa.toString() );
205 System.out.println( MsaMethods.calcBasicGapinessStatistics( msa ).toString() );
207 final MsaMethods msa_tools = MsaMethods.createInstance();
208 if ( _options.isExecuteMsaProcessing() ) {
209 msa = msa_tools.removeGapColumns( _options.getMsaProcessingMaxAllowedGapRatio(),
210 _options.getMsaProcessingMinAllowedLength(),
214 JOptionPane.showMessageDialog( _mf,
215 "Less than two sequences longer than "
216 + _options.getMsaProcessingMinAllowedLength()
217 + " residues left after MSA processing",
218 "MSA Processing Settings Too Stringent",
219 JOptionPane.ERROR_MESSAGE );
224 System.out.println( msa_tools.getIgnoredSequenceIds() );
225 System.out.println( msa.toString() );
226 System.out.println( MsaMethods.calcBasicGapinessStatistics( msa ).toString() );
230 final int n = _options.getBootstrapSamples();
231 final long seed = _options.getRandomNumberGeneratorSeed();
232 final Phylogeny master_phy = inferPhylogeny( _msa );
233 if ( _options.isPerformBootstrapResampling() && ( n > 0 ) ) {
234 final ResampleableMsa resampleable_msa = new ResampleableMsa( ( BasicMsa ) _msa );
235 final int[][] resampled_column_positions = BootstrapResampler.createResampledColumnPositions( _msa
236 .getLength(), n, seed );
237 final Phylogeny[] eval_phys = new Phylogeny[ n ];
238 for( int i = 0; i < n; ++i ) {
239 resampleable_msa.resample( resampled_column_positions[ i ] );
240 eval_phys[ i ] = inferPhylogeny( resampleable_msa );
242 ConfidenceAssessor.evaluate( "bootstrap", eval_phys, master_phy, true, 1 );
244 _mf.getMainPanel().addPhylogenyInNewTab( master_phy, _mf.getConfiguration(), "nj", "njpath" );
245 // _mf.getMainPanel().getCurrentTreePanel().setArrowCursor();
247 JOptionPane.showMessageDialog( _mf,
248 "Inference successfully completed",
249 "Inference Completed",
250 JOptionPane.INFORMATION_MESSAGE );
258 catch ( final InterruptedException e ) {
259 // TODO need to handle this exception SOMEHOW!
260 // TODO Auto-generated catch block
265 private Msa runMAFFT( final File input_seqs, final List<String> opts ) throws IOException, InterruptedException {
267 final MsaInferrer mafft = Mafft.createInstance();
269 msa = mafft.infer( input_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 );
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 static void extractFastaInformation( final Phylogeny phy ) {
296 for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) {
297 final PhylogenyNode node = iter.next();
298 if ( !ForesterUtil.isEmpty( node.getName() ) ) {
299 final Matcher name_m = FastaParser.FASTA_DESC_LINE.matcher( node.getName() );
300 if ( name_m.lookingAt() ) {
301 System.out.println();
302 // System.out.println( name_m.group( 1 ) );
303 // System.out.println( name_m.group( 2 ) );
304 // System.out.println( name_m.group( 3 ) );
305 // System.out.println( name_m.group( 4 ) );
306 final String acc_source = name_m.group( 1 );
307 final String acc = name_m.group( 2 );
308 final String seq_name = name_m.group( 3 );
309 final String tax_sn = name_m.group( 4 );
310 if ( !ForesterUtil.isEmpty( acc_source ) && !ForesterUtil.isEmpty( acc ) ) {
311 AptxUtil.ensurePresenceOfSequence( node );
312 node.getNodeData().getSequence( 0 ).setAccession( new Accession( acc, acc_source ) );
314 if ( !ForesterUtil.isEmpty( seq_name ) ) {
315 AptxUtil.ensurePresenceOfSequence( node );
316 node.getNodeData().getSequence( 0 ).setName( seq_name );
318 if ( !ForesterUtil.isEmpty( tax_sn ) ) {
319 AptxUtil.ensurePresenceOfTaxonomy( node );
320 node.getNodeData().getTaxonomy( 0 ).setScientificName( tax_sn );