X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fjava%2Fsrc%2Forg%2Fforester%2Fmsa_compactor%2FMsaCompactor.java;h=8a13b5cc6bdb2ff28954e78fdb04751ad8c850d9;hb=665e671efec73fcb36a9aac45f119330f290fa81;hp=81f22da21024d3d4e2c96855aec323a586f0be6e;hpb=e49ac25b5d578ea326900b7b56495ee33c3cb92c;p=jalview.git diff --git a/forester/java/src/org/forester/msa_compactor/MsaCompactor.java b/forester/java/src/org/forester/msa_compactor/MsaCompactor.java index 81f22da..8a13b5c 100644 --- a/forester/java/src/org/forester/msa_compactor/MsaCompactor.java +++ b/forester/java/src/org/forester/msa_compactor/MsaCompactor.java @@ -64,7 +64,7 @@ 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.Sequence; +import org.forester.sequence.MolecularSequence; import org.forester.tools.ConfidenceAssessor; import org.forester.util.BasicDescriptiveStatistics; import org.forester.util.DescriptiveStatistics; @@ -72,28 +72,28 @@ import org.forester.util.ForesterUtil; public class MsaCompactor { - 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; + 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 String _infile_name = null; - private final short _longest_id_length; + private String _infile_name = null; + private final short _longest_id_length; // - 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 String _maffts_opts = "--auto"; + private DeleteableMsa _msa = null; + private boolean _normalize_for_effective_seq_length = 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 _removed_seq_ids; - private final ArrayList _removed_seqs; - private File _removed_seqs_out_base = null; - private int _step = -1; - private int _step_for_diagnostics = -1; + private boolean _realign = false; + private final SortedSet _removed_seq_ids; + private final ArrayList _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 ); @@ -104,7 +104,7 @@ public class MsaCompactor { _msa = msa; _removed_seq_ids = new TreeSet(); _longest_id_length = _msa.determineMaxIdLength(); - _removed_seqs = new ArrayList(); + _removed_seqs = new ArrayList(); } public final Phylogeny calcTree() { @@ -130,9 +130,9 @@ public class MsaCompactor { return phy; } - public final List chart( final int step, final boolean realign, final boolean norm ) + public final List chart( final int step, final boolean realign, final boolean normalize_for_effective_seq_length ) throws IOException, InterruptedException { - final GapContribution stats[] = calcGapContribtionsStats( norm ); + final GapContribution stats[] = calcGapContribtionsStats( normalize_for_effective_seq_length ); final List to_remove_ids = new ArrayList(); final List msa_props = new ArrayList(); for( final GapContribution gap_gontribution : stats ) { @@ -143,6 +143,7 @@ public class MsaCompactor { System.out.println( "calculating phylogentic tree..." ); System.out.println(); phy = calcTree(); + addSeqs2Tree( _msa, phy ); } if ( !_realign ) { _step = -1; @@ -178,6 +179,7 @@ public class MsaCompactor { } ++i; } + if ( _phylogentic_inference ) { decorateTree( phy, msa_props, true ); displayTree( phy ); @@ -185,7 +187,26 @@ public class MsaCompactor { return msa_props; } - public final void decorateTree( final Phylogeny phy, final List msa_props, final boolean chart_only ) { + private final static void addSeqs2Tree( final Msa msa, final Phylogeny phy ) { + for( int i = 0; i < msa.getNumberOfSequences(); ++i ) { + final MolecularSequence seq = msa.getSequence( i ); + final String seq_name = seq.getIdentifier(); + final PhylogenyNode n = phy.getNode( seq_name ); + if ( !n.getNodeData().isHasSequence() ) { + n.getNodeData().addSequence( new org.forester.phylogeny.data.Sequence() ); + } + else { + throw new IllegalArgumentException( "this should not have happened" ); + } + n.getNodeData().getSequence().setMolecularSequence( seq.getMolecularSequenceAsString() ); + n.getNodeData().getSequence().setMolecularSequenceAligned( true ); + n.getNodeData().getSequence().setName( seq_name ); + } + } + + private final static void decorateTree( final Phylogeny phy, + final List 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 ); @@ -225,14 +246,14 @@ public class MsaCompactor { } else { n.getNodeData() - .getNodeVisualData() - .setNodeColor( ForesterUtil.calcColor( msa_prop.getLength(), - min, - max, - mean, - min_color, - max_color, - mean_color ) ); + .getNodeVisualData() + .setNodeColor( ForesterUtil.calcColor( msa_prop.getLength(), + min, + max, + mean, + min_color, + max_color, + mean_color ) ); } } } @@ -252,6 +273,7 @@ public class MsaCompactor { config.setDisplaySequenceNames( false ); config.setDisplaySequenceSymbols( false ); config.setDisplayGeneNames( false ); + config.setDisplayMultipleSequenceAlignment( true ); config.setShowScale( true ); config.setAddTaxonomyImagesCB( false ); config.setBaseFontSize( 9 ); @@ -282,8 +304,8 @@ public class MsaCompactor { } public final List removeViaGapAverage( final double mean_gapiness ) throws IOException, - InterruptedException { - final GapContribution stats[] = calcGapContribtionsStats( _norm ); + InterruptedException { + final GapContribution stats[] = calcGapContribtionsStats( _normalize_for_effective_seq_length ); final List to_remove_ids = new ArrayList(); final List msa_props = new ArrayList(); for( final GapContribution gap_gontribution : stats ) { @@ -294,6 +316,7 @@ public class MsaCompactor { System.out.println( "calculating phylogentic tree..." ); System.out.println(); phy = calcTree(); + addSeqs2Tree( _msa, phy ); } printTableHeader(); MsaProperties msa_prop = new MsaProperties( _msa, "", _calculate_shannon_entropy ); @@ -304,7 +327,7 @@ public class MsaCompactor { while ( MsaMethods.calcGapRatio( _msa ) > mean_gapiness ) { final String id = to_remove_ids.get( i ); _removed_seq_ids.add( id ); - final Sequence deleted = _msa.deleteRow( id, true ); + final MolecularSequence deleted = _msa.deleteRow( id, true ); _removed_seqs.add( deleted ); removeGapColumns(); if ( isPrintMsaStatsWriteOutfileAndRealign( i ) || ( MsaMethods.calcGapRatio( _msa ) <= mean_gapiness ) ) { @@ -328,12 +351,19 @@ public class MsaCompactor { if ( _phylogentic_inference ) { decorateTree( phy, msa_props, false ); displayTree( phy ); - } + System.out.println( "calculating phylogentic tree..." ); + System.out.println(); + final Phylogeny phy2 = calcTree(); + addSeqs2Tree( _msa, phy2 ); + displayTree( phy2 ); + } + + return msa_props; } public List removeViaLength( final int length ) throws IOException, InterruptedException { - final GapContribution stats[] = calcGapContribtionsStats( _norm ); + final GapContribution stats[] = calcGapContribtionsStats( _normalize_for_effective_seq_length ); final List to_remove_ids = new ArrayList(); final List msa_props = new ArrayList(); for( final GapContribution gap_gontribution : stats ) { @@ -344,6 +374,7 @@ public class MsaCompactor { System.out.println( "calculating phylogentic tree..." ); System.out.println(); phy = calcTree(); + addSeqs2Tree( _msa, phy ); } printTableHeader(); MsaProperties msa_prop = new MsaProperties( _msa, "", _calculate_shannon_entropy ); @@ -354,7 +385,7 @@ public class MsaCompactor { while ( _msa.getLength() > length ) { final String id = to_remove_ids.get( i ); _removed_seq_ids.add( id ); - final Sequence deleted = _msa.deleteRow( id, true ); + final MolecularSequence deleted = _msa.deleteRow( id, true ); _removed_seqs.add( deleted ); removeGapColumns(); if ( isPrintMsaStatsWriteOutfileAndRealign( i ) || ( _msa.getLength() <= length ) ) { @@ -378,13 +409,19 @@ public class MsaCompactor { if ( _phylogentic_inference ) { decorateTree( phy, msa_props, false ); displayTree( phy ); - } + System.out.println( "calculating phylogentic tree..." ); + System.out.println(); + final Phylogeny phy2 = calcTree(); + addSeqs2Tree( _msa, phy2 ); + displayTree( phy2 ); + } + return msa_props; } public final List removeWorstOffenders( final int to_remove ) throws IOException, - InterruptedException { - final GapContribution stats[] = calcGapContribtionsStats( _norm ); + InterruptedException { + final GapContribution stats[] = calcGapContribtionsStats( _normalize_for_effective_seq_length ); final List to_remove_ids = new ArrayList(); final List msa_props = new ArrayList(); for( int j = 0; j < to_remove; ++j ) { @@ -395,6 +432,7 @@ public class MsaCompactor { System.out.println( "calculating phylogentic tree..." ); System.out.println(); phy = calcTree(); + addSeqs2Tree( _msa, phy ); } printTableHeader(); MsaProperties msa_prop = new MsaProperties( _msa, "", _calculate_shannon_entropy ); @@ -404,7 +442,7 @@ public class MsaCompactor { for( int i = 0; i < to_remove_ids.size(); ++i ) { final String id = to_remove_ids.get( i ); _removed_seq_ids.add( id ); - final Sequence deleted = _msa.deleteRow( id, true ); + final MolecularSequence deleted = _msa.deleteRow( id, true ); _removed_seqs.add( deleted ); removeGapColumns(); if ( isPrintMsaStatsWriteOutfileAndRealign( i ) || ( i == ( to_remove_ids.size() - 1 ) ) ) { @@ -427,7 +465,13 @@ public class MsaCompactor { if ( _phylogentic_inference ) { decorateTree( phy, msa_props, false ); displayTree( phy ); - } + System.out.println( "calculating phylogentic tree..." ); + System.out.println(); + final Phylogeny phy2 = calcTree(); + addSeqs2Tree( _msa, phy2 ); + displayTree( phy2 ); + } + return msa_props; } @@ -443,8 +487,8 @@ public class MsaCompactor { _maffts_opts = maffts_opts; } - public final void setNorm( final boolean norm ) { - _norm = norm; + public final void setNorm( final boolean normalize_for_effective_seq_length ) { + _normalize_for_effective_seq_length = normalize_for_effective_seq_length; } final public void setOutFileBase( final File out_file_base ) { @@ -510,7 +554,7 @@ public class MsaCompactor { 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 ) ) { @@ -540,8 +584,8 @@ public class MsaCompactor { return stats; } - final private GapContribution[] calcGapContribtionsStats( final boolean norm ) { - final GapContribution stats[] = calcGapContribtions( norm ); + final private GapContribution[] calcGapContribtionsStats( final boolean normalize_for_effective_seq_length ) { + final GapContribution stats[] = calcGapContribtions( normalize_for_effective_seq_length ); Arrays.sort( stats ); return stats; } @@ -556,6 +600,12 @@ public class MsaCompactor { 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, @@ -602,6 +652,8 @@ public class MsaCompactor { sb.append( msa_properties.getLength() ); sb.append( "\t" ); sb.append( NF_4.format( msa_properties.getGapRatio() ) ); + sb.append( "\t" ); + sb.append( NF_1.format( msa_properties.getAvgNumberOfGaps() ) ); if ( _calculate_shannon_entropy ) { sb.append( "\t" ); sb.append( NF_4.format( msa_properties.getEntropy7() ) ); @@ -669,6 +721,8 @@ public class MsaCompactor { System.out.print( "\t" ); System.out.print( "Length" ); System.out.print( "\t" ); + System.out.print( "Gap R" ); + System.out.print( "\t" ); System.out.print( "Gaps" ); System.out.print( "\t" ); if ( _calculate_shannon_entropy ) {