package org.forester.msa_compactor;
+import java.awt.Color;
import java.io.File;
import java.io.IOException;
import java.io.Writer;
import org.forester.msa.ResampleableMsa;
import org.forester.phylogeny.Phylogeny;
import org.forester.phylogeny.PhylogenyMethods;
+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.Sequence;
import org.forester.tools.ConfidenceAssessor;
+import org.forester.util.BasicDescriptiveStatistics;
import org.forester.util.ForesterUtil;
public class MsaCompactor {
for( final GapContribution gap_gontribution : stats ) {
to_remove_ids.add( gap_gontribution.getId() );
}
- if ( _phylogentic_inference ) {
- System.out.println( "calculating phylegentic tree..." );
- System.out.println();
- pi();
- }
if ( !_realign ) {
_step = -1;
}
- printTableHeader();
int x = ForesterUtil.roundToInt( _msa.getNumberOfSequences() / 20.0 );
if ( x < 1 ) {
x = 1;
}
- MsaProperties msa_prop = new MsaProperties( _msa, _report_aln_mean_identity );
+ MsaProperties msa_prop = new MsaProperties( _msa, "", _report_aln_mean_identity );
msa_props.add( msa_prop );
+ Phylogeny phy = null;
+ if ( _phylogentic_inference ) {
+ System.out.println( "calculating phylogentic tree..." );
+ System.out.println();
+ phy = calcTree();
+ }
+ printTableHeader();
printMsaProperties( "", msa_prop );
System.out.println();
int i = 0;
if ( realign && isPrintMsaStatsWriteOutfileAndRealign( i ) ) {
removeGapColumns();
realignWithMafft();
- msa_prop = new MsaProperties( _msa, _report_aln_mean_identity );
+ msa_prop = new MsaProperties( _msa, id, _report_aln_mean_identity );
msa_props.add( msa_prop );
printMsaProperties( id, msa_prop );
System.out.print( "(realigned)" );
}
else if ( isPrintMsaStats( i ) ) {
removeGapColumns();
- msa_prop = new MsaProperties( _msa, _report_aln_mean_identity );
+ msa_prop = new MsaProperties( _msa, id, _report_aln_mean_identity );
msa_props.add( msa_prop );
printMsaProperties( id, msa_prop );
System.out.println();
}
++i;
}
+ if ( _phylogentic_inference ) {
+ final Phylogeny p2 = phy.copy();
+ decorateTree( p2, to_remove_ids );
+ decorateTree2( phy, msa_props );
+ displayTree( p2 );
+ displayTree( phy );
+ }
return msa_props;
}
}
public final void removeSequencesByMinimalLength( final int min_effective_length ) {
- printMsaProperties( "", new MsaProperties( _msa, _report_aln_mean_identity ) );
+ printMsaProperties( "", new MsaProperties( _msa, "", _report_aln_mean_identity ) );
System.out.println();
_msa = DeleteableMsa.createInstance( MsaMethods.removeSequencesByMinimalLength( _msa, min_effective_length ) );
removeGapColumns();
- printMsaProperties( "", new MsaProperties( _msa, _report_aln_mean_identity ) );
+ printMsaProperties( "", new MsaProperties( _msa, "", _report_aln_mean_identity ) );
System.out.println();
}
to_remove_ids.add( gap_gontribution.getId() );
}
printTableHeader();
- MsaProperties msa_prop = new MsaProperties( _msa, _report_aln_mean_identity );
+ MsaProperties msa_prop = new MsaProperties( _msa, "", _report_aln_mean_identity );
msa_props.add( msa_prop );
printMsaProperties( "", msa_prop );
System.out.println();
System.out.println();
}
else if ( isPrintMsaStats( i ) ) {
- msa_prop = new MsaProperties( _msa, _report_aln_mean_identity );
+ msa_prop = new MsaProperties( _msa, id, _report_aln_mean_identity );
msa_props.add( msa_prop );
printMsaProperties( id, msa_prop );
System.out.println();
to_remove_ids.add( gap_gontribution.getId() );
}
printTableHeader();
- MsaProperties msa_prop = new MsaProperties( _msa, _report_aln_mean_identity );
+ MsaProperties msa_prop = new MsaProperties( _msa, "", _report_aln_mean_identity );
msa_props.add( msa_prop );
printMsaProperties( "", msa_prop );
System.out.println();
System.out.println();
}
else if ( isPrintMsaStats( i ) ) {
- msa_prop = new MsaProperties( _msa, _report_aln_mean_identity );
+ msa_prop = new MsaProperties( _msa, id, _report_aln_mean_identity );
printMsaProperties( id, msa_prop );
msa_props.add( msa_prop );
System.out.println();
_removed_seq_ids.add( stats[ j ].getId() );
}
printTableHeader();
- MsaProperties msa_prop = new MsaProperties( _msa, _report_aln_mean_identity );
+ MsaProperties msa_prop = new MsaProperties( _msa, "", _report_aln_mean_identity );
msa_props.add( msa_prop );
printMsaProperties( "", msa_prop );
System.out.println();
System.out.println();
}
else if ( isPrintMsaStats( i ) ) {
- msa_prop = new MsaProperties( _msa, _report_aln_mean_identity );
+ msa_prop = new MsaProperties( _msa, id, _report_aln_mean_identity );
msa_props.add( msa_prop );
printMsaProperties( id, msa_prop );
System.out.println();
return master_phy;
}
- private final Phylogeny pi() {
+ 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();
}
}
}
+ return phy;
+ }
+
+ public final void decorateTree( final Phylogeny phy, final List<String> to_remove_ids ) {
+ for( int i = 0; i < to_remove_ids.size(); ++i ) {
+ final String id = to_remove_ids.get( i );
+ final PhylogenyNode n = phy.getNode( id );
+ n.setName( n.getName() + " [" + ( i + 1 ) + "]" );
+ final NodeVisualData vis = new NodeVisualData();
+ vis.setFillType( NodeFill.SOLID );
+ vis.setShape( NodeShape.RECTANGLE );
+ vis.setSize( 6 );
+ vis.setNodeColor( new Color( i > 255 ? 0 : 255 - i, 0, 0 ) );
+ n.getNodeData().setNodeVisualData( vis );
+ }
+ }
+
+ public final void decorateTree2( final Phylogeny phy, final List<MsaProperties> msa_props ) {
+ 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();
+ while ( it.hasNext() ) {
+ final NodeVisualData vis = new NodeVisualData();
+ vis.setFillType( NodeFill.SOLID );
+ vis.setShape( NodeShape.RECTANGLE );
+ vis.setSize( 6 );
+ 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 + "]" );
+ n.getNodeData()
+ .getNodeVisualData()
+ .setNodeColor( ForesterUtil.calcColor( msa_prop.getLength(),
+ min,
+ max,
+ mean,
+ min_color,
+ max_color,
+ mean_color ) );
+ }
+ }
+ }
+
+ 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 );
- return phy;
}
private final void printMsaProperties( final String id, final MsaProperties msa_properties ) {
if ( realign ) {
realignWithMafft();
}
- final MsaProperties msa_prop = new MsaProperties( _msa, _report_aln_mean_identity );
+ final MsaProperties msa_prop = new MsaProperties( _msa, id, _report_aln_mean_identity );
printMsaProperties( id, msa_prop );
final String s = writeOutfile();
System.out.print( "-> " + s + ( realign ? "\t(realigned)" : "" ) );