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.ClustalOmega;
49 import org.forester.msa.Mafft;
50 import org.forester.msa.Msa;
51 import org.forester.msa.MsaInferrer;
52 import org.forester.msa.MsaMethods;
53 import org.forester.msa.ResampleableMsa;
54 import org.forester.phylogeny.Phylogeny;
55 import org.forester.phylogeny.PhylogenyNode;
56 import org.forester.phylogeny.data.Accession;
57 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
58 import org.forester.sequence.Sequence;
59 import org.forester.tools.ConfidenceAssessor;
60 import org.forester.util.ForesterUtil;
62 public class PhylogeneticInferrer extends RunnableProcess {
65 private final MainFrameApplication _mf;
66 private final PhylogeneticInferenceOptions _options;
67 private final List<Sequence> _seqs;
68 private final boolean DEBUG = true;
69 public final static String MSA_FILE_SUFFIX = ".aln";
70 public final static String PWD_FILE_SUFFIX = ".pwd";
72 public PhylogeneticInferrer( final List<Sequence> seqs,
73 final PhylogeneticInferenceOptions options,
74 final MainFrameApplication mf ) {
81 public PhylogeneticInferrer( final Msa msa,
82 final PhylogeneticInferenceOptions options,
83 final MainFrameApplication mf ) {
90 private Msa inferMsa() throws IOException, InterruptedException {
91 final File temp_seqs_file = File.createTempFile( "__msa__temp__", ".fasta" );
94 System.out.println( "temp file: " + temp_seqs_file );
97 //final File temp_seqs_file = new File( _options.getTempDir() + ForesterUtil.FILE_SEPARATOR + "s.fasta" );
98 final BufferedWriter writer = new BufferedWriter( new FileWriter( temp_seqs_file ) );
99 SequenceWriter.writeSeqs( _seqs, writer, SEQ_FORMAT.FASTA, 100 );
101 final List<String> opts = processMafftOptions();
102 return runMAFFT( temp_seqs_file, opts );
105 private List<String> processMafftOptions() {
106 final String opts_str = _options.getMsaPrgParameters().trim().toLowerCase();
107 final String[] opts_ary = opts_str.split( " " );
108 final List<String> opts = new ArrayList<String>();
109 boolean saw_quiet = false;
110 for( final String opt : opts_ary ) {
112 if ( opt.equals( "--quiet" ) ) {
117 opts.add( "--quiet" );
122 private Phylogeny inferPhylogeny( final Msa msa ) {
123 BasicSymmetricalDistanceMatrix m = null;
124 switch ( _options.getPwdDistanceMethod() ) {
125 case KIMURA_DISTANCE:
126 m = PairwiseDistanceCalculator.calcKimuraDistances( msa );
128 case POISSON_DISTANCE:
129 m = PairwiseDistanceCalculator.calcPoissonDistances( msa );
131 case FRACTIONAL_DISSIMILARITY:
132 m = PairwiseDistanceCalculator.calcFractionalDissimilarities( msa );
135 throw new RuntimeException( "invalid pwd method" );
137 if ( !ForesterUtil.isEmpty( _options.getIntermediateFilesBase() ) ) {
138 BufferedWriter pwd_writer;
140 pwd_writer = new BufferedWriter( new FileWriter( _options.getIntermediateFilesBase() + PWD_FILE_SUFFIX ) );
141 m.write( pwd_writer );
144 catch ( final IOException e ) {
145 // TODO Auto-generated catch block
149 final NeighborJoining nj = NeighborJoining.createInstance();
150 final Phylogeny phy = nj.execute( m );
151 PhylogeneticInferrer.extractFastaInformation( phy );
155 private void infer() throws InterruptedException {
156 //_mf.getMainPanel().getCurrentTreePanel().setWaitCursor();
157 if ( ( _msa == null ) && ( _seqs == null ) ) {
158 throw new IllegalArgumentException( "cannot run phylogenetic analysis with null msa and seq array" );
160 start( _mf, "phylogenetic inference" );
161 if ( _msa == null ) {
166 catch ( final IOException e ) {
168 JOptionPane.showMessageDialog( _mf,
169 "Could not create multiple sequence alignment with \""
170 + _options.getMsaPrg() + "\" and the following parameters:\n\""
171 + _options.getMsaPrgParameters() + "\"\nError: "
172 + e.getLocalizedMessage(),
173 "Failed to Calculate MSA",
174 JOptionPane.ERROR_MESSAGE );
180 catch ( final Exception e ) {
182 JOptionPane.showMessageDialog( _mf,
183 "Could not create multiple sequence alignment with \""
184 + _options.getMsaPrg() + "\" and the following parameters:\n\""
185 + _options.getMsaPrgParameters() + "\"\nError: "
186 + e.getLocalizedMessage(),
187 "Unexpected Exception During MSA Calculation",
188 JOptionPane.ERROR_MESSAGE );
196 JOptionPane.showMessageDialog( _mf,
197 "Could not create multiple sequence alignment with "
198 + _options.getMsaPrg() + "\nand the following parameters:\n\""
199 + _options.getMsaPrgParameters() + "\"",
200 "Failed to Calculate MSA",
201 JOptionPane.ERROR_MESSAGE );
205 System.out.println( msa.toString() );
206 System.out.println( MsaMethods.calcBasicGapinessStatistics( msa ).toString() );
208 final MsaMethods msa_tools = MsaMethods.createInstance();
209 if ( _options.isExecuteMsaProcessing() ) {
210 msa = msa_tools.removeGapColumns( _options.getMsaProcessingMaxAllowedGapRatio(),
211 _options.getMsaProcessingMinAllowedLength(),
215 JOptionPane.showMessageDialog( _mf,
216 "Less than two sequences longer than "
217 + _options.getMsaProcessingMinAllowedLength()
218 + " residues left after MSA processing",
219 "MSA Processing Settings Too Stringent",
220 JOptionPane.ERROR_MESSAGE );
225 System.out.println( msa_tools.getIgnoredSequenceIds() );
226 System.out.println( msa.toString() );
227 System.out.println( MsaMethods.calcBasicGapinessStatistics( msa ).toString() );
231 final int n = _options.getBootstrapSamples();
232 final long seed = _options.getRandomNumberGeneratorSeed();
233 final Phylogeny master_phy = inferPhylogeny( _msa );
234 if ( _options.isPerformBootstrapResampling() && ( n > 0 ) ) {
235 final ResampleableMsa resampleable_msa = new ResampleableMsa( ( BasicMsa ) _msa );
236 final int[][] resampled_column_positions = BootstrapResampler.createResampledColumnPositions( _msa
237 .getLength(), n, seed );
238 final Phylogeny[] eval_phys = new Phylogeny[ n ];
239 for( int i = 0; i < n; ++i ) {
240 resampleable_msa.resample( resampled_column_positions[ i ] );
241 eval_phys[ i ] = inferPhylogeny( resampleable_msa );
243 ConfidenceAssessor.evaluate( "bootstrap", eval_phys, master_phy, true, 1 );
245 _mf.getMainPanel().addPhylogenyInNewTab( master_phy, _mf.getConfiguration(), "nj", "njpath" );
246 // _mf.getMainPanel().getCurrentTreePanel().setArrowCursor();
248 JOptionPane.showMessageDialog( _mf,
249 "Inference successfully completed",
250 "Inference Completed",
251 JOptionPane.INFORMATION_MESSAGE );
259 catch ( final InterruptedException e ) {
260 // TODO need to handle this exception SOMEHOW!
261 // TODO Auto-generated catch block
266 private Msa runMAFFT( final File input_seqs, final List<String> opts ) throws IOException, InterruptedException {
268 final MsaInferrer mafft = Mafft.createInstance( _mf.getInferenceManager().getPathToLocalMafft()
269 .getCanonicalPath() );
271 msa = mafft.infer( input_seqs, opts );
273 catch ( final IOException e ) {
274 System.out.println( mafft.getErrorDescription() );
279 private Msa runClustalOmega( final File input_seqs, final List<String> opts ) throws IOException,
280 InterruptedException {
282 final MsaInferrer clustalo = ClustalOmega.createInstance( _mf.getInferenceManager().getPathToLocalClustalo()
283 .getCanonicalPath() );
285 msa = clustalo.infer( input_seqs, opts );
287 catch ( final IOException e ) {
288 System.out.println( clustalo.getErrorDescription() );
293 private void writeToFiles( final BasicSymmetricalDistanceMatrix m ) {
294 if ( !ForesterUtil.isEmpty( _options.getIntermediateFilesBase() ) ) {
296 final BufferedWriter msa_writer = new BufferedWriter( new FileWriter( _options.getIntermediateFilesBase()
297 + MSA_FILE_SUFFIX ) );
298 _msa.write( msa_writer );
300 final BufferedWriter pwd_writer = new BufferedWriter( new FileWriter( _options.getIntermediateFilesBase()
301 + PWD_FILE_SUFFIX ) );
302 m.write( pwd_writer );
305 catch ( final Exception e ) {
306 System.out.println( "Error: " + e.getMessage() );
311 public static void extractFastaInformation( final Phylogeny phy ) {
312 for( final PhylogenyNodeIterator iter = phy.iteratorExternalForward(); iter.hasNext(); ) {
313 final PhylogenyNode node = iter.next();
314 if ( !ForesterUtil.isEmpty( node.getName() ) ) {
315 final Matcher name_m = FastaParser.FASTA_DESC_LINE.matcher( node.getName() );
316 if ( name_m.lookingAt() ) {
317 System.out.println();
318 // System.out.println( name_m.group( 1 ) );
319 // System.out.println( name_m.group( 2 ) );
320 // System.out.println( name_m.group( 3 ) );
321 // System.out.println( name_m.group( 4 ) );
322 final String acc_source = name_m.group( 1 );
323 final String acc = name_m.group( 2 );
324 final String seq_name = name_m.group( 3 );
325 final String tax_sn = name_m.group( 4 );
326 if ( !ForesterUtil.isEmpty( acc_source ) && !ForesterUtil.isEmpty( acc ) ) {
327 AptxUtil.ensurePresenceOfSequence( node );
328 node.getNodeData().getSequence( 0 ).setAccession( new Accession( acc, acc_source ) );
330 if ( !ForesterUtil.isEmpty( seq_name ) ) {
331 AptxUtil.ensurePresenceOfSequence( node );
332 node.getNodeData().getSequence( 0 ).setName( seq_name );
334 if ( !ForesterUtil.isEmpty( tax_sn ) ) {
335 AptxUtil.ensurePresenceOfTaxonomy( node );
336 node.getNodeData().getTaxonomy( 0 ).setScientificName( tax_sn );