package org.forester.msa_compactor;
+import java.awt.Color;
import java.io.File;
import java.io.IOException;
import java.io.Writer;
import java.util.SortedSet;
import java.util.TreeSet;
+import org.forester.archaeopteryx.Archaeopteryx;
+import org.forester.archaeopteryx.Configuration;
import org.forester.evoinference.distance.NeighborJoiningF;
import org.forester.evoinference.distance.PairwiseDistanceCalculator;
import org.forester.evoinference.distance.PairwiseDistanceCalculator.PWD_DISTANCE_METHOD;
import org.forester.evoinference.matrix.distance.BasicSymmetricalDistanceMatrix;
import org.forester.evoinference.tools.BootstrapResampler;
+import org.forester.io.parsers.nhx.NHXParser.TAXONOMY_EXTRACTION;
+import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException;
+import org.forester.io.parsers.util.ParserUtils;
+import org.forester.io.writers.SequenceWriter;
+import org.forester.io.writers.SequenceWriter.SEQ_FORMAT;
import org.forester.msa.DeleteableMsa;
import org.forester.msa.Mafft;
import org.forester.msa.Msa;
import org.forester.msa.ResampleableMsa;
import org.forester.phylogeny.Phylogeny;
import org.forester.phylogeny.PhylogenyMethods;
-import org.forester.sequence.Sequence;
+import org.forester.phylogeny.PhylogenyMethods.DESCENDANT_SORT_PRIORITY;
+import org.forester.phylogeny.PhylogenyNode;
+import org.forester.phylogeny.data.NodeVisualData;
+import org.forester.phylogeny.data.NodeVisualData.NodeFill;
+import org.forester.phylogeny.data.NodeVisualData.NodeShape;
+import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
+import org.forester.sequence.MolecularSequence;
import org.forester.tools.ConfidenceAssessor;
+import org.forester.util.BasicDescriptiveStatistics;
+import org.forester.util.DescriptiveStatistics;
import org.forester.util.ForesterUtil;
public class MsaCompactor {
- final private static NumberFormat NF_3 = new DecimalFormat( "#.###" );
- final private static NumberFormat NF_4 = new DecimalFormat( "#.####" );
- private double _gap_ratio = -1;
+ final private static NumberFormat NF_1 = new DecimalFormat( "0.#" );
+ final private static NumberFormat NF_3 = new DecimalFormat( "0.###" );
+ final private static NumberFormat NF_4 = new DecimalFormat( "0.####" );
+ private boolean _calculate_shannon_entropy = false;
//
- private final String _maffts_opts = "--auto";
- private int _min_length = -1;
+ private String _infile_name = null;
+ private final short _longest_id_length;
//
- private DeleteableMsa _msa = null;
- private boolean _norm = true;
- private File _out_file_base = null;
- private MSA_FORMAT _output_format = MSA_FORMAT.FASTA;
- private String _path_to_mafft = null;
+ private String _maffts_opts = "--auto";
+ private DeleteableMsa _msa = null;
+ private boolean _norm = true;
+ private File _out_file_base = null;
+ private MSA_FORMAT _output_format = MSA_FORMAT.FASTA;
+ private String _path_to_mafft = null;
+ private boolean _phylogentic_inference = false;
//
- private boolean _realign = false;
- private final SortedSet<String> _removed_seq_ids;
- private final File _removed_seqs_out_base = null;
- private boolean _report_aln_mean_identity = false;
- private int _step = -1;
- private int _step_for_diagnostics = -1;
+ private boolean _realign = false;
+ private final SortedSet<String> _removed_seq_ids;
+ private final ArrayList<MolecularSequence> _removed_seqs;
+ private File _removed_seqs_out_base = null;
+ private int _step = -1;
+ private int _step_for_diagnostics = -1;
static {
+ NF_1.setRoundingMode( RoundingMode.HALF_UP );
NF_4.setRoundingMode( RoundingMode.HALF_UP );
NF_3.setRoundingMode( RoundingMode.HALF_UP );
}
public MsaCompactor( final DeleteableMsa msa ) {
_msa = msa;
_removed_seq_ids = new TreeSet<String>();
+ _longest_id_length = _msa.determineMaxIdLength();
+ _removed_seqs = new ArrayList<MolecularSequence>();
+ }
+
+ public final Phylogeny calcTree() {
+ final Phylogeny phy = inferNJphylogeny( PWD_DISTANCE_METHOD.KIMURA_DISTANCE, _msa, false, "" );
+ PhylogenyMethods.midpointRoot( phy );
+ PhylogenyMethods.orderAppearance( phy.getRoot(), true, true, DESCENDANT_SORT_PRIORITY.NODE_NAME );
+ final boolean x = PhylogenyMethods.extractFastaInformation( phy );
+ if ( !x ) {
+ final PhylogenyNodeIterator it = phy.iteratorExternalForward();
+ while ( it.hasNext() ) {
+ final PhylogenyNode n = it.next();
+ final String name = n.getName().trim();
+ if ( !ForesterUtil.isEmpty( name ) ) {
+ try {
+ ParserUtils.extractTaxonomyDataFromNodeName( n, TAXONOMY_EXTRACTION.AGGRESSIVE );
+ }
+ catch ( final PhyloXmlDataFormatException e ) {
+ // Ignore.
+ }
+ }
+ }
+ }
+ return phy;
}
- final public Msa getMsa() {
- return _msa;
- }
-
- final public SortedSet<String> getRemovedSeqIds() {
- return _removed_seq_ids;
- }
-
- public final void removeViaGapAverage( final double mean_gapiness, final boolean verbose ) throws IOException,
- InterruptedException {
- final GapContribution stats[] = calcGapContribtionsStats( _norm );
+ public final List<MsaProperties> chart( final int step, final boolean realign, final boolean norm )
+ throws IOException, InterruptedException {
+ final GapContribution stats[] = calcGapContribtionsStats( norm );
final List<String> to_remove_ids = new ArrayList<String>();
+ final List<MsaProperties> msa_props = new ArrayList<MsaProperties>();
for( final GapContribution gap_gontribution : stats ) {
to_remove_ids.add( gap_gontribution.getId() );
}
- if ( verbose ) {
- printTableHeader();
+ Phylogeny phy = null;
+ if ( _phylogentic_inference ) {
+ System.out.println( "calculating phylogentic tree..." );
+ System.out.println();
+ phy = calcTree();
+ }
+ if ( !_realign ) {
+ _step = -1;
+ }
+ int x = ForesterUtil.roundToInt( _msa.getNumberOfSequences() / 10.0 );
+ if ( x < 2 ) {
+ x = 2;
}
+ MsaProperties msa_prop = new MsaProperties( _msa, "", _calculate_shannon_entropy );
+ msa_props.add( msa_prop );
+ printTableHeader();
+ printMsaProperties( msa_prop );
+ System.out.println();
int i = 0;
- while ( MsaMethods.calcGapRatio( _msa ) > mean_gapiness ) {
+ while ( _msa.getNumberOfSequences() > x ) {
final String id = to_remove_ids.get( i );
- _msa.deleteRow( id );
- removeGapColumns();
- if ( ( ( _step > 0 ) && ( ( ( i + 1 ) % _step ) == 0 ) )
- || ( MsaMethods.calcGapRatio( _msa ) <= mean_gapiness ) ) {
- printMsaStatsWriteOutfileAndRealign( _realign, id );
- }
- else if ( verbose ) {
- final MsaProperties msa_prop = new MsaProperties( _msa, _report_aln_mean_identity );
- printMsaProperties( id, msa_prop );
+ _msa.deleteRow( id, false );
+ if ( realign && isPrintMsaStatsWriteOutfileAndRealign( i ) ) {
+ removeGapColumns();
+ realignWithMafft();
+ msa_prop = new MsaProperties( _msa, id, _calculate_shannon_entropy );
+ msa_props.add( msa_prop );
+ printMsaProperties( msa_prop );
+ System.out.print( "(realigned)" );
+ System.out.println();
}
- if ( verbose ) {
+ else if ( isPrintMsaStats( i ) ) {
+ removeGapColumns();
+ msa_prop = new MsaProperties( _msa, id, _calculate_shannon_entropy );
+ msa_props.add( msa_prop );
+ printMsaProperties( msa_prop );
System.out.println();
}
++i;
}
+ if ( _phylogentic_inference ) {
+ decorateTree( phy, msa_props, true );
+ displayTree( phy );
+ }
+ return msa_props;
+ }
+
+ public final void decorateTree( final Phylogeny phy, final List<MsaProperties> msa_props, final boolean chart_only ) {
+ final BasicDescriptiveStatistics length_stats = new BasicDescriptiveStatistics();
+ for( int i = 0; i < msa_props.size(); ++i ) {
+ final MsaProperties msa_prop = msa_props.get( i );
+ final String id = msa_prop.getRemovedSeq();
+ if ( !ForesterUtil.isEmpty( id ) ) {
+ length_stats.addValue( msa_prop.getLength() );
+ }
+ }
+ final double mean = length_stats.arithmeticMean();
+ final double min = length_stats.getMin();
+ final double max = length_stats.getMax();
+ final Color min_color = new Color( 0, 255, 0 );
+ final Color max_color = new Color( 255, 0, 0 );
+ final Color mean_color = new Color( 255, 255, 0 );
+ final PhylogenyNodeIterator it = phy.iteratorExternalForward();
+ if ( chart_only ) {
+ while ( it.hasNext() ) {
+ final NodeVisualData vis = new NodeVisualData();
+ vis.setFillType( NodeFill.SOLID );
+ vis.setShape( NodeShape.RECTANGLE );
+ vis.setNodeColor( min_color );
+ it.next().getNodeData().setNodeVisualData( vis );
+ }
+ }
+ for( int i = 0; i < msa_props.size(); ++i ) {
+ final MsaProperties msa_prop = msa_props.get( i );
+ final String id = msa_prop.getRemovedSeq();
+ if ( !ForesterUtil.isEmpty( id ) ) {
+ final PhylogenyNode n = phy.getNode( id );
+ n.setName( n.getName() + " [" + i + "]" );
+ if ( !chart_only ) {
+ final NodeVisualData vis = new NodeVisualData();
+ vis.setFillType( NodeFill.SOLID );
+ vis.setShape( NodeShape.RECTANGLE );
+ vis.setNodeColor( ForesterUtil.calcColor( msa_prop.getLength(), min, max, mean_color, max_color ) );
+ n.getNodeData().setNodeVisualData( vis );
+ }
+ else {
+ n.getNodeData()
+ .getNodeVisualData()
+ .setNodeColor( ForesterUtil.calcColor( msa_prop.getLength(),
+ min,
+ max,
+ mean,
+ min_color,
+ max_color,
+ mean_color ) );
+ }
+ }
+ }
+ }
+
+ final public void deleteGapColumns( final double max_allowed_gap_ratio ) {
+ _msa.deleteGapColumns( max_allowed_gap_ratio );
+ }
+
+ public final void displayTree( final Phylogeny phy ) {
+ final Configuration config = new Configuration();
+ config.setDisplayAsPhylogram( true );
+ config.setUseStyle( true );
+ config.setDisplayTaxonomyCode( false );
+ config.setDisplayTaxonomyCommonNames( false );
+ config.setDisplayTaxonomyScientificNames( false );
+ config.setDisplaySequenceNames( false );
+ config.setDisplaySequenceSymbols( false );
+ config.setDisplayGeneNames( false );
+ config.setShowScale( true );
+ config.setAddTaxonomyImagesCB( false );
+ config.setBaseFontSize( 9 );
+ config.setBaseFontFamilyName( "Arial" );
+ Archaeopteryx.createApplication( phy, config, _infile_name );
+ }
+
+ final public Msa getMsa() {
+ return _msa;
+ }
+
+ public final void removeSequencesByMinimalLength( final int min_effective_length ) throws IOException {
+ _msa = DeleteableMsa.createInstance( MsaMethods.removeSequencesByMinimalLength( _msa, min_effective_length ) );
+ removeGapColumns();
+ final String s = writeOutfile();
+ final DescriptiveStatistics msa_stats = MsaMethods.calculateEffectiveLengthStatistics( _msa );
+ System.out.println( "Output MSA : " + s );
+ System.out.println( " MSA length : " + _msa.getLength() );
+ System.out.println( " Number of sequences : " + _msa.getNumberOfSequences() );
+ System.out.println( " Median sequence length : " + NF_1.format( msa_stats.median() ) );
+ System.out.println( " Mean sequence length : " + NF_1.format( msa_stats.arithmeticMean() ) );
+ System.out.println( " Max sequence length : " + ( ( int ) msa_stats.getMax() ) );
+ System.out.println( " Min sequence length : " + ( ( int ) msa_stats.getMin() ) );
+ System.out.println( " Gap ratio : " + NF_4.format( MsaMethods.calcGapRatio( _msa ) ) );
+ System.out.println( " Normalized Shannon Entropy (entn21): "
+ + NF_4.format( MsaMethods.calcNormalizedShannonsEntropy( 21, _msa ) ) );
+ System.out.println();
}
- public void removeViaLength( final int length, final boolean verbose ) throws IOException, InterruptedException {
+ public final List<MsaProperties> removeViaGapAverage( final double mean_gapiness ) throws IOException,
+ InterruptedException {
final GapContribution stats[] = calcGapContribtionsStats( _norm );
final List<String> to_remove_ids = new ArrayList<String>();
+ final List<MsaProperties> msa_props = new ArrayList<MsaProperties>();
for( final GapContribution gap_gontribution : stats ) {
to_remove_ids.add( gap_gontribution.getId() );
}
- if ( verbose ) {
- printTableHeader();
+ Phylogeny phy = null;
+ if ( _phylogentic_inference ) {
+ System.out.println( "calculating phylogentic tree..." );
+ System.out.println();
+ phy = calcTree();
}
+ printTableHeader();
+ MsaProperties msa_prop = new MsaProperties( _msa, "", _calculate_shannon_entropy );
+ msa_props.add( msa_prop );
+ printMsaProperties( msa_prop );
+ System.out.println();
int i = 0;
- while ( _msa.getLength() > length ) {
+ while ( MsaMethods.calcGapRatio( _msa ) > mean_gapiness ) {
final String id = to_remove_ids.get( i );
- _msa.deleteRow( id );
+ _removed_seq_ids.add( id );
+ final MolecularSequence deleted = _msa.deleteRow( id, true );
+ _removed_seqs.add( deleted );
removeGapColumns();
- if ( ( ( _step > 0 ) && ( ( ( i + 1 ) % _step ) == 0 ) ) || ( _msa.getLength() <= length ) ) {
- printMsaStatsWriteOutfileAndRealign( _realign, id );
- }
- else if ( verbose ) {
- final MsaProperties msa_prop = new MsaProperties( _msa, _report_aln_mean_identity );
- printMsaProperties( id, msa_prop );
+ if ( isPrintMsaStatsWriteOutfileAndRealign( i ) || ( MsaMethods.calcGapRatio( _msa ) <= mean_gapiness ) ) {
+ msa_prop = printMsaStatsWriteOutfileAndRealign( _realign, id );
+ msa_props.add( msa_prop );
+ System.out.println();
}
- if ( verbose ) {
+ else if ( isPrintMsaStats( i ) ) {
+ msa_prop = new MsaProperties( _msa, id, _calculate_shannon_entropy );
+ msa_props.add( msa_prop );
+ printMsaProperties( msa_prop );
System.out.println();
}
++i;
}
+ if ( _removed_seqs_out_base != null ) {
+ final String msg = writeAndAlignRemovedSeqs();
+ System.out.println();
+ System.out.println( msg );
+ }
+ if ( _phylogentic_inference ) {
+ decorateTree( phy, msa_props, false );
+ displayTree( phy );
+ }
+ return msa_props;
}
- public final void removeWorstOffenders( final int to_remove ) throws IOException, InterruptedException {
+ public List<MsaProperties> removeViaLength( final int length ) throws IOException, InterruptedException {
final GapContribution stats[] = calcGapContribtionsStats( _norm );
final List<String> to_remove_ids = new ArrayList<String>();
- for( int j = 0; j < to_remove; ++j ) {
- to_remove_ids.add( stats[ j ].getId() );
- _removed_seq_ids.add( stats[ j ].getId() );
+ final List<MsaProperties> msa_props = new ArrayList<MsaProperties>();
+ for( final GapContribution gap_gontribution : stats ) {
+ to_remove_ids.add( gap_gontribution.getId() );
+ }
+ Phylogeny phy = null;
+ if ( _phylogentic_inference ) {
+ System.out.println( "calculating phylogentic tree..." );
+ System.out.println();
+ phy = calcTree();
}
printTableHeader();
- for( int i = 0; i < to_remove_ids.size(); ++i ) {
+ MsaProperties msa_prop = new MsaProperties( _msa, "", _calculate_shannon_entropy );
+ msa_props.add( msa_prop );
+ printMsaProperties( msa_prop );
+ System.out.println();
+ int i = 0;
+ while ( _msa.getLength() > length ) {
final String id = to_remove_ids.get( i );
- _msa.deleteRow( id );
+ _removed_seq_ids.add( id );
+ final MolecularSequence deleted = _msa.deleteRow( id, true );
+ _removed_seqs.add( deleted );
removeGapColumns();
- if ( isPrintMsaStatsWriteOutfileAndRealign( i ) || ( i == ( to_remove_ids.size() - 1 ) ) ) {
- printMsaStatsWriteOutfileAndRealign( _realign, id );
+ if ( isPrintMsaStatsWriteOutfileAndRealign( i ) || ( _msa.getLength() <= length ) ) {
+ msa_prop = printMsaStatsWriteOutfileAndRealign( _realign, id );
+ msa_props.add( msa_prop );
System.out.println();
}
else if ( isPrintMsaStats( i ) ) {
- final MsaProperties msa_prop = new MsaProperties( _msa, _report_aln_mean_identity );
- printMsaProperties( id, msa_prop );
+ msa_prop = new MsaProperties( _msa, id, _calculate_shannon_entropy );
+ printMsaProperties( msa_prop );
+ msa_props.add( msa_prop );
System.out.println();
}
+ ++i;
+ }
+ if ( _removed_seqs_out_base != null ) {
+ final String msg = writeAndAlignRemovedSeqs();
+ System.out.println();
+ System.out.println( msg );
}
+ if ( _phylogentic_inference ) {
+ decorateTree( phy, msa_props, false );
+ displayTree( phy );
+ }
+ return msa_props;
}
- public final List<MsaProperties> chart( final int step, final boolean realign, final boolean norm )
- throws IOException, InterruptedException {
- final GapContribution stats[] = calcGapContribtionsStats( norm );
+ public final List<MsaProperties> removeWorstOffenders( final int to_remove ) throws IOException,
+ InterruptedException {
+ final GapContribution stats[] = calcGapContribtionsStats( _norm );
final List<String> to_remove_ids = new ArrayList<String>();
final List<MsaProperties> msa_props = new ArrayList<MsaProperties>();
- for( final GapContribution gap_gontribution : stats ) {
- to_remove_ids.add( gap_gontribution.getId() );
+ for( int j = 0; j < to_remove; ++j ) {
+ to_remove_ids.add( stats[ j ].getId() );
+ }
+ Phylogeny phy = null;
+ if ( _phylogentic_inference ) {
+ System.out.println( "calculating phylogentic tree..." );
+ System.out.println();
+ phy = calcTree();
}
printTableHeader();
- int i = 0;
- final int x = ForesterUtil.roundToInt( _msa.getNumberOfSequences() / 20.0 );
- MsaProperties msa_prop = new MsaProperties( _msa, _report_aln_mean_identity );
+ MsaProperties msa_prop = new MsaProperties( _msa, "", _calculate_shannon_entropy );
msa_props.add( msa_prop );
- printMsaProperties( "", msa_prop );
+ printMsaProperties( msa_prop );
System.out.println();
- while ( _msa.getNumberOfSequences() > x ) {
+ for( int i = 0; i < to_remove_ids.size(); ++i ) {
final String id = to_remove_ids.get( i );
- _msa.deleteRow( id );
- if ( realign && isPrintMsaStatsWriteOutfileAndRealign( i ) ) {
- removeGapColumns();
- realignWithMafft();
- msa_prop = new MsaProperties( _msa, _report_aln_mean_identity );
+ _removed_seq_ids.add( id );
+ final MolecularSequence deleted = _msa.deleteRow( id, true );
+ _removed_seqs.add( deleted );
+ removeGapColumns();
+ if ( isPrintMsaStatsWriteOutfileAndRealign( i ) || ( i == ( to_remove_ids.size() - 1 ) ) ) {
+ msa_prop = printMsaStatsWriteOutfileAndRealign( _realign, id );
msa_props.add( msa_prop );
- printMsaProperties( id, msa_prop );
- System.out.print( "(realigned)" );
System.out.println();
}
else if ( isPrintMsaStats( i ) ) {
- removeGapColumns();
- msa_prop = new MsaProperties( _msa, _report_aln_mean_identity );
+ msa_prop = new MsaProperties( _msa, id, _calculate_shannon_entropy );
msa_props.add( msa_prop );
- printMsaProperties( id, msa_prop );
+ printMsaProperties( msa_prop );
System.out.println();
}
- ++i;
+ }
+ if ( _removed_seqs_out_base != null ) {
+ final String msg = writeAndAlignRemovedSeqs();
+ System.out.println();
+ System.out.println( msg );
+ }
+ if ( _phylogentic_inference ) {
+ decorateTree( phy, msa_props, false );
+ displayTree( phy );
}
return msa_props;
}
- private final boolean isPrintMsaStats( final int i ) {
- return ( ( _step_for_diagnostics < 2 ) || ( ( ( i + 1 ) % _step_for_diagnostics ) == 0 ) );
- }
-
- private final boolean isPrintMsaStatsWriteOutfileAndRealign( final int i ) {
- return ( ( _step < 2 ) || ( ( ( i + 1 ) % _step ) == 0 ) );
+ public final void setCalculateNormalizedShannonEntropy( final boolean calculate_shannon_entropy ) {
+ _calculate_shannon_entropy = calculate_shannon_entropy;
}
- public final void setGapRatio( final double gap_ratio ) {
- _gap_ratio = gap_ratio;
+ public void setInfileName( final String infile_name ) {
+ _infile_name = infile_name;
}
- public final void setMinLength( final int min_length ) {
- _min_length = min_length;
+ public final void setMafftOptions( final String maffts_opts ) {
+ _maffts_opts = maffts_opts;
}
public final void setNorm( final boolean norm ) {
_path_to_mafft = path_to_mafft;
}
+ public void setPeformPhylogenticInference( final boolean phylogentic_inference ) {
+ _phylogentic_inference = phylogentic_inference;
+ }
+
public final void setRealign( final boolean realign ) {
_realign = realign;
}
+ public final void setRemovedSeqsOutBase( final File removed_seqs_out_base ) {
+ _removed_seqs_out_base = removed_seqs_out_base;
+ }
+
public final void setStep( final int step ) {
_step = step;
}
_step_for_diagnostics = step_for_diagnostics;
}
- public final void setReportAlnMeanIdentity( final boolean report_aln_mean_identity ) {
- _report_aln_mean_identity = report_aln_mean_identity;
+ final public String writeAndAlignRemovedSeqs() throws IOException, InterruptedException {
+ final StringBuilder msg = new StringBuilder();
+ final String n = _removed_seqs_out_base + "_" + _removed_seqs.size() + ".fasta";
+ SequenceWriter.writeSeqs( _removed_seqs, new File( n ), SEQ_FORMAT.FASTA, 100 );
+ msg.append( "wrote " + _removed_seqs.size() + " removed sequences to " + "\"" + n + "\"" );
+ if ( _realign ) {
+ final MsaInferrer mafft = Mafft.createInstance( _path_to_mafft );
+ final List<String> opts = new ArrayList<String>();
+ for( final String o : _maffts_opts.split( "\\s" ) ) {
+ opts.add( o );
+ }
+ final Msa removed_msa = mafft.infer( _removed_seqs, opts );
+ final Double gr = MsaMethods.calcGapRatio( removed_msa );
+ String s = _removed_seqs_out_base + "_" + removed_msa.getNumberOfSequences() + "_"
+ + removed_msa.getLength() + "_" + ForesterUtil.roundToInt( gr * 100 );
+ final String suffix = obtainSuffix();
+ s += suffix;
+ writeMsa( removed_msa, s, _output_format );
+ msg.append( ", and as MSA of length " + removed_msa.getLength() + " to \"" + s + "\"" );
+ }
+ return msg.toString();
}
- final public String writeMsa( final File outfile, final MSA_FORMAT format, final String suffix ) throws IOException {
+ final public String writeMsa( final File outfile ) throws IOException {
final Double gr = MsaMethods.calcGapRatio( _msa );
final String s = outfile + "_" + _msa.getNumberOfSequences() + "_" + _msa.getLength() + "_"
+ ForesterUtil.roundToInt( gr * 100 );
- writeMsa( s + suffix, format );
+ writeMsa( _msa, s + obtainSuffix(), _output_format );
return s;
}
- final int calcNonGapResidues( final Sequence seq ) {
+ final int calcNonGapResidues( final MolecularSequence seq ) {
int ng = 0;
for( int i = 0; i < seq.getLength(); ++i ) {
if ( !seq.isGapAt( i ) ) {
return gappiness;
}
+ private final Phylogeny collapse( final Msa msa, final int threshold ) {
+ final BasicSymmetricalDistanceMatrix m = PairwiseDistanceCalculator.calcFractionalDissimilarities( msa );
+ //TODO
+ return null;
+ }
+
private final Phylogeny inferNJphylogeny( final PWD_DISTANCE_METHOD pwd_distance_method,
final Msa msa,
final boolean write_matrix,
return phy;
}
- private final Phylogeny pi( final String matrix ) {
+ private final boolean isPrintMsaStats( final int i ) {
+ return ( ( ( _step == 1 ) && ( _step_for_diagnostics == 1 ) ) || ( ( _step_for_diagnostics > 0 ) && ( ( ( i + 1 ) % _step_for_diagnostics ) == 0 ) ) );
+ }
+
+ private final boolean isPrintMsaStatsWriteOutfileAndRealign( final int i ) {
+ return ( ( ( _step == 1 ) && ( _step_for_diagnostics == 1 ) ) || ( ( _step > 0 ) && ( ( ( i + 1 ) % _step ) == 0 ) ) );
+ }
+
+ private final StringBuilder msaPropertiesAsSB( final MsaProperties msa_properties ) {
+ final StringBuilder sb = new StringBuilder();
+ sb.append( msa_properties.getNumberOfSequences() );
+ sb.append( "\t" );
+ sb.append( msa_properties.getLength() );
+ sb.append( "\t" );
+ sb.append( NF_4.format( msa_properties.getGapRatio() ) );
+ if ( _calculate_shannon_entropy ) {
+ sb.append( "\t" );
+ sb.append( NF_4.format( msa_properties.getEntropy7() ) );
+ sb.append( "\t" );
+ sb.append( NF_4.format( msa_properties.getEntropy21() ) );
+ }
+ return sb;
+ }
+
+ private String obtainSuffix() {
+ if ( _output_format == MSA_FORMAT.FASTA ) {
+ return ".fasta";
+ }
+ else if ( _output_format == MSA_FORMAT.PHYLIP ) {
+ return ".aln";
+ }
+ return "";
+ }
+
+ private final Phylogeny pi( final String matrix, final int boostrap ) {
final Phylogeny master_phy = inferNJphylogeny( PWD_DISTANCE_METHOD.KIMURA_DISTANCE, _msa, true, matrix );
final int seed = 15;
final int n = 100;
return master_phy;
}
- private final static void printMsaProperties( final String id, final MsaProperties msa_properties ) {
- System.out.print( ForesterUtil.pad( id, 20, ' ', false ) );
- System.out.print( "\t" );
- final StringBuilder sb = msaPropertiesAsSB( msa_properties );
- System.out.print( sb );
- System.out.print( "\t" );
- }
-
- private final static StringBuilder msaPropertiesAsSB( final MsaProperties msa_properties ) {
- final StringBuilder sb = new StringBuilder();
- sb.append( msa_properties.getNumberOfSequences() );
- sb.append( "\t" );
- sb.append( msa_properties.getLength() );
- sb.append( "\t" );
- sb.append( NF_4.format( msa_properties.getGapRatio() ) );
- if ( msa_properties.getAverageIdentityRatio() >= 0 ) {
- sb.append( "\t" );
- sb.append( NF_4.format( msa_properties.getAverageIdentityRatio() ) );
+ private final void printMsaProperties( final MsaProperties msa_properties ) {
+ if ( ( _step == 1 ) || ( _step_for_diagnostics == 1 ) ) {
+ System.out.print( ForesterUtil.pad( msa_properties.getRemovedSeq(), _longest_id_length, ' ', false ) );
+ System.out.print( "\t" );
}
- return sb;
+ System.out.print( msaPropertiesAsSB( msa_properties ) );
+ System.out.print( "\t" );
}
- final private void printMsaStatsWriteOutfileAndRealign( final boolean realign, final String id )
+ final private MsaProperties printMsaStatsWriteOutfileAndRealign( final boolean realign, final String id )
throws IOException, InterruptedException {
if ( realign ) {
realignWithMafft();
}
- final MsaProperties msa_prop = new MsaProperties( _msa, _report_aln_mean_identity );
- printMsaProperties( id, msa_prop );
+ final MsaProperties msa_prop = new MsaProperties( _msa, id, _calculate_shannon_entropy );
+ printMsaProperties( msa_prop );
final String s = writeOutfile();
System.out.print( "-> " + s + ( realign ? "\t(realigned)" : "" ) );
+ return msa_prop;
+ }
+
+ private final void printTableHeader() {
+ if ( ( _step == 1 ) || ( _step_for_diagnostics == 1 ) ) {
+ System.out.print( ForesterUtil.pad( "Id", _longest_id_length, ' ', false ) );
+ System.out.print( "\t" );
+ }
+ System.out.print( "Seqs" );
+ System.out.print( "\t" );
+ System.out.print( "Length" );
+ System.out.print( "\t" );
+ System.out.print( "Gaps" );
+ System.out.print( "\t" );
+ if ( _calculate_shannon_entropy ) {
+ System.out.print( "entn7" );
+ System.out.print( "\t" );
+ System.out.print( "entn21" );
+ System.out.print( "\t" );
+ }
+ System.out.println();
}
final private void realignWithMafft() throws IOException, InterruptedException {
- // final MsaInferrer mafft = Mafft
- // .createInstance( "/home/czmasek/SOFTWARE/MSA/MAFFT/mafft-7.130-without-extensions/scripts/mafft" );
final MsaInferrer mafft = Mafft.createInstance( _path_to_mafft );
final List<String> opts = new ArrayList<String>();
for( final String o : _maffts_opts.split( "\\s" ) ) {
_msa.deleteGapOnlyColumns();
}
- final private void writeMsa( final String outfile, final MSA_FORMAT format ) throws IOException {
- final Writer w = ForesterUtil.createBufferedWriter( outfile );
- _msa.write( w, format );
- w.close();
- }
-
private final String writeOutfile() throws IOException {
- final String s = writeMsa( _out_file_base, MSA_FORMAT.PHYLIP, ".aln" );
- //writeMsa( _out_file_base, MSA_FORMAT.FASTA, ".fasta" );
+ final String s = writeMsa( _out_file_base );
return s;
}
return null;
}
- private final static void printTableHeader() {
- System.out.print( ForesterUtil.pad( "Id", 20, ' ', false ) );
- System.out.print( "\t" );
- System.out.print( "Seqs" );
- System.out.print( "\t" );
- System.out.print( "Length" );
- System.out.print( "\t" );
- System.out.print( "Gaps" );
- System.out.print( "\t" );
- System.out.print( "MSA qual" );
- System.out.print( "\t" );
- System.out.println();
+ final private static void writeMsa( final Msa msa, final String outfile, final MSA_FORMAT format )
+ throws IOException {
+ final Writer w = ForesterUtil.createBufferedWriter( outfile );
+ msa.write( w, format );
+ w.close();
}
}