subtree deletion changed
[jalview.git] / forester / java / src / org / forester / phylogeny / PhylogenyMethods.java
index 2d238a2..bb13e65 100644 (file)
 package org.forester.phylogeny;
 
 import java.awt.Color;
+import java.io.File;
+import java.io.IOException;
 import java.util.ArrayList;
 import java.util.Arrays;
+import java.util.Collections;
+import java.util.Comparator;
 import java.util.HashSet;
 import java.util.Iterator;
 import java.util.List;
@@ -35,11 +39,19 @@ import java.util.Set;
 import java.util.SortedMap;
 import java.util.TreeMap;
 
+import org.forester.io.parsers.PhylogenyParser;
+import org.forester.io.parsers.phyloxml.PhyloXmlUtil;
+import org.forester.io.parsers.util.PhylogenyParserException;
 import org.forester.phylogeny.data.BranchColor;
 import org.forester.phylogeny.data.BranchWidth;
 import org.forester.phylogeny.data.Confidence;
 import org.forester.phylogeny.data.DomainArchitecture;
+import org.forester.phylogeny.data.Identifier;
+import org.forester.phylogeny.data.PhylogenyDataUtil;
+import org.forester.phylogeny.data.Sequence;
 import org.forester.phylogeny.data.Taxonomy;
+import org.forester.phylogeny.factories.ParserBasedPhylogenyFactory;
+import org.forester.phylogeny.factories.PhylogenyFactory;
 import org.forester.phylogeny.iterators.PhylogenyNodeIterator;
 import org.forester.util.BasicDescriptiveStatistics;
 import org.forester.util.DescriptiveStatistics;
@@ -170,6 +182,310 @@ public class PhylogenyMethods {
         return !obtainLCA( node1, node2 ).isDuplication();
     }
 
+    public final static Phylogeny[] readPhylogenies( final PhylogenyParser parser, final File file ) throws IOException {
+        final PhylogenyFactory factory = ParserBasedPhylogenyFactory.getInstance();
+        final Phylogeny[] trees = factory.create( file, parser );
+        if ( ( trees == null ) || ( trees.length == 0 ) ) {
+            throw new PhylogenyParserException( "Unable to parse phylogeny from file: " + file );
+        }
+        return trees;
+    }
+
+    final static public void transferInternalNodeNamesToConfidence( final Phylogeny phy ) {
+        final PhylogenyNodeIterator it = phy.iteratorPostorder();
+        while ( it.hasNext() ) {
+            final PhylogenyNode n = it.next();
+            if ( !n.isExternal() && !n.getBranchData().isHasConfidences() ) {
+                if ( !ForesterUtil.isEmpty( n.getName() ) ) {
+                    double d = -1.0;
+                    try {
+                        d = Double.parseDouble( n.getName() );
+                    }
+                    catch ( final Exception e ) {
+                        d = -1.0;
+                    }
+                    if ( d >= 0.0 ) {
+                        n.getBranchData().addConfidence( new Confidence( d, "" ) );
+                        n.setName( "" );
+                    }
+                }
+            }
+        }
+    }
+
+    final static public void transferInternalNamesToBootstrapSupport( final Phylogeny phy ) {
+        final PhylogenyNodeIterator it = phy.iteratorPostorder();
+        while ( it.hasNext() ) {
+            final PhylogenyNode n = it.next();
+            if ( !n.isExternal() && !ForesterUtil.isEmpty( n.getName() ) ) {
+                double value = -1;
+                try {
+                    value = Double.parseDouble( n.getName() );
+                }
+                catch ( final NumberFormatException e ) {
+                    throw new IllegalArgumentException( "failed to parse number from [" + n.getName() + "]: "
+                            + e.getLocalizedMessage() );
+                }
+                if ( value >= 0.0 ) {
+                    n.getBranchData().addConfidence( new Confidence( value, "bootstrap" ) );
+                    n.setName( "" );
+                }
+            }
+        }
+    }
+
+    final static public void sortNodeDescendents( final PhylogenyNode node, final DESCENDANT_SORT_PRIORITY pri ) {
+        class PhylogenyNodeSortTaxonomyPriority implements Comparator<PhylogenyNode> {
+
+            @Override
+            public int compare( final PhylogenyNode n1, final PhylogenyNode n2 ) {
+                if ( n1.getNodeData().isHasTaxonomy() && n2.getNodeData().isHasTaxonomy() ) {
+                    if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getScientificName() ) )
+                            && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getScientificName() ) ) ) {
+                        return n1.getNodeData().getTaxonomy().getScientificName().toLowerCase()
+                                .compareTo( n2.getNodeData().getTaxonomy().getScientificName().toLowerCase() );
+                    }
+                    if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getTaxonomyCode() ) )
+                            && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getTaxonomyCode() ) ) ) {
+                        return n1.getNodeData().getTaxonomy().getTaxonomyCode()
+                                .compareTo( n2.getNodeData().getTaxonomy().getTaxonomyCode() );
+                    }
+                    if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getCommonName() ) )
+                            && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getCommonName() ) ) ) {
+                        return n1.getNodeData().getTaxonomy().getCommonName().toLowerCase()
+                                .compareTo( n2.getNodeData().getTaxonomy().getCommonName().toLowerCase() );
+                    }
+                }
+                if ( n1.getNodeData().isHasSequence() && n2.getNodeData().isHasSequence() ) {
+                    if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getName() ) )
+                            && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getName() ) ) ) {
+                        return n1.getNodeData().getSequence().getName().toLowerCase()
+                                .compareTo( n2.getNodeData().getSequence().getName().toLowerCase() );
+                    }
+                    if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getSymbol() ) )
+                            && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getSymbol() ) ) ) {
+                        return n1.getNodeData().getSequence().getSymbol()
+                                .compareTo( n2.getNodeData().getSequence().getSymbol() );
+                    }
+                    if ( ( n1.getNodeData().getSequence().getAccession() != null )
+                            && ( n2.getNodeData().getSequence().getAccession() != null )
+                            && !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getAccession().getValue() )
+                            && !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getAccession().getValue() ) ) {
+                        return n1.getNodeData().getSequence().getAccession().getValue()
+                                .compareTo( n2.getNodeData().getSequence().getAccession().getValue() );
+                    }
+                }
+                if ( ( !ForesterUtil.isEmpty( n1.getName() ) ) && ( !ForesterUtil.isEmpty( n2.getName() ) ) ) {
+                    return n1.getName().toLowerCase().compareTo( n2.getName().toLowerCase() );
+                }
+                return 0;
+            }
+        }
+        class PhylogenyNodeSortSequencePriority implements Comparator<PhylogenyNode> {
+
+            @Override
+            public int compare( final PhylogenyNode n1, final PhylogenyNode n2 ) {
+                if ( n1.getNodeData().isHasSequence() && n2.getNodeData().isHasSequence() ) {
+                    if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getName() ) )
+                            && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getName() ) ) ) {
+                        return n1.getNodeData().getSequence().getName().toLowerCase()
+                                .compareTo( n2.getNodeData().getSequence().getName().toLowerCase() );
+                    }
+                    if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getSymbol() ) )
+                            && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getSymbol() ) ) ) {
+                        return n1.getNodeData().getSequence().getSymbol()
+                                .compareTo( n2.getNodeData().getSequence().getSymbol() );
+                    }
+                    if ( ( n1.getNodeData().getSequence().getAccession() != null )
+                            && ( n2.getNodeData().getSequence().getAccession() != null )
+                            && !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getAccession().getValue() )
+                            && !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getAccession().getValue() ) ) {
+                        return n1.getNodeData().getSequence().getAccession().getValue()
+                                .compareTo( n2.getNodeData().getSequence().getAccession().getValue() );
+                    }
+                }
+                if ( n1.getNodeData().isHasTaxonomy() && n2.getNodeData().isHasTaxonomy() ) {
+                    if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getScientificName() ) )
+                            && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getScientificName() ) ) ) {
+                        return n1.getNodeData().getTaxonomy().getScientificName().toLowerCase()
+                                .compareTo( n2.getNodeData().getTaxonomy().getScientificName().toLowerCase() );
+                    }
+                    if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getTaxonomyCode() ) )
+                            && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getTaxonomyCode() ) ) ) {
+                        return n1.getNodeData().getTaxonomy().getTaxonomyCode()
+                                .compareTo( n2.getNodeData().getTaxonomy().getTaxonomyCode() );
+                    }
+                    if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getCommonName() ) )
+                            && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getCommonName() ) ) ) {
+                        return n1.getNodeData().getTaxonomy().getCommonName().toLowerCase()
+                                .compareTo( n2.getNodeData().getTaxonomy().getCommonName().toLowerCase() );
+                    }
+                }
+                if ( ( !ForesterUtil.isEmpty( n1.getName() ) ) && ( !ForesterUtil.isEmpty( n2.getName() ) ) ) {
+                    return n1.getName().toLowerCase().compareTo( n2.getName().toLowerCase() );
+                }
+                return 0;
+            }
+        }
+        class PhylogenyNodeSortNodeNamePriority implements Comparator<PhylogenyNode> {
+
+            @Override
+            public int compare( final PhylogenyNode n1, final PhylogenyNode n2 ) {
+                if ( ( !ForesterUtil.isEmpty( n1.getName() ) ) && ( !ForesterUtil.isEmpty( n2.getName() ) ) ) {
+                    return n1.getName().toLowerCase().compareTo( n2.getName().toLowerCase() );
+                }
+                if ( n1.getNodeData().isHasTaxonomy() && n2.getNodeData().isHasTaxonomy() ) {
+                    if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getScientificName() ) )
+                            && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getScientificName() ) ) ) {
+                        return n1.getNodeData().getTaxonomy().getScientificName().toLowerCase()
+                                .compareTo( n2.getNodeData().getTaxonomy().getScientificName().toLowerCase() );
+                    }
+                    if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getTaxonomyCode() ) )
+                            && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getTaxonomyCode() ) ) ) {
+                        return n1.getNodeData().getTaxonomy().getTaxonomyCode()
+                                .compareTo( n2.getNodeData().getTaxonomy().getTaxonomyCode() );
+                    }
+                    if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getTaxonomy().getCommonName() ) )
+                            && ( !ForesterUtil.isEmpty( n2.getNodeData().getTaxonomy().getCommonName() ) ) ) {
+                        return n1.getNodeData().getTaxonomy().getCommonName().toLowerCase()
+                                .compareTo( n2.getNodeData().getTaxonomy().getCommonName().toLowerCase() );
+                    }
+                }
+                if ( n1.getNodeData().isHasSequence() && n2.getNodeData().isHasSequence() ) {
+                    if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getName() ) )
+                            && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getName() ) ) ) {
+                        return n1.getNodeData().getSequence().getName().toLowerCase()
+                                .compareTo( n2.getNodeData().getSequence().getName().toLowerCase() );
+                    }
+                    if ( ( !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getSymbol() ) )
+                            && ( !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getSymbol() ) ) ) {
+                        return n1.getNodeData().getSequence().getSymbol()
+                                .compareTo( n2.getNodeData().getSequence().getSymbol() );
+                    }
+                    if ( ( n1.getNodeData().getSequence().getAccession() != null )
+                            && ( n2.getNodeData().getSequence().getAccession() != null )
+                            && !ForesterUtil.isEmpty( n1.getNodeData().getSequence().getAccession().getValue() )
+                            && !ForesterUtil.isEmpty( n2.getNodeData().getSequence().getAccession().getValue() ) ) {
+                        return n1.getNodeData().getSequence().getAccession().getValue()
+                                .compareTo( n2.getNodeData().getSequence().getAccession().getValue() );
+                    }
+                }
+                return 0;
+            }
+        }
+        Comparator<PhylogenyNode> c;
+        switch ( pri ) {
+            case SEQUENCE:
+                c = new PhylogenyNodeSortSequencePriority();
+                break;
+            case NODE_NAME:
+                c = new PhylogenyNodeSortNodeNamePriority();
+                break;
+            default:
+                c = new PhylogenyNodeSortTaxonomyPriority();
+        }
+        final List<PhylogenyNode> descs = node.getDescendants();
+        Collections.sort( descs, c );
+        int i = 0;
+        for( final PhylogenyNode desc : descs ) {
+            node.setChildNode( i++, desc );
+        }
+    }
+
+    final static public void transferNodeNameToField( final Phylogeny phy,
+                                                      final PhylogenyMethods.PhylogenyNodeField field ) {
+        final PhylogenyNodeIterator it = phy.iteratorPostorder();
+        while ( it.hasNext() ) {
+            final PhylogenyNode n = it.next();
+            final String name = n.getName().trim();
+            if ( !ForesterUtil.isEmpty( name ) ) {
+                switch ( field ) {
+                    case TAXONOMY_CODE:
+                        //temp hack
+                        //                        if ( name.length() > 5 ) {
+                        //                            n.setName( "" );
+                        //                            if ( !n.getNodeData().isHasTaxonomy() ) {
+                        //                                n.getNodeData().setTaxonomy( new Taxonomy() );
+                        //                            }
+                        //                            n.getNodeData().getTaxonomy().setScientificName( name );
+                        //                            break;
+                        //                        }
+                        //
+                        n.setName( "" );
+                        setTaxonomyCode( n, name );
+                        break;
+                    case TAXONOMY_SCIENTIFIC_NAME:
+                        n.setName( "" );
+                        if ( !n.getNodeData().isHasTaxonomy() ) {
+                            n.getNodeData().setTaxonomy( new Taxonomy() );
+                        }
+                        n.getNodeData().getTaxonomy().setScientificName( name );
+                        break;
+                    case TAXONOMY_COMMON_NAME:
+                        n.setName( "" );
+                        if ( !n.getNodeData().isHasTaxonomy() ) {
+                            n.getNodeData().setTaxonomy( new Taxonomy() );
+                        }
+                        n.getNodeData().getTaxonomy().setCommonName( name );
+                        break;
+                    case SEQUENCE_SYMBOL:
+                        n.setName( "" );
+                        if ( !n.getNodeData().isHasSequence() ) {
+                            n.getNodeData().setSequence( new Sequence() );
+                        }
+                        n.getNodeData().getSequence().setSymbol( name );
+                        break;
+                    case SEQUENCE_NAME:
+                        n.setName( "" );
+                        if ( !n.getNodeData().isHasSequence() ) {
+                            n.getNodeData().setSequence( new Sequence() );
+                        }
+                        n.getNodeData().getSequence().setName( name );
+                        break;
+                    case TAXONOMY_ID_UNIPROT_1: {
+                        if ( !n.getNodeData().isHasTaxonomy() ) {
+                            n.getNodeData().setTaxonomy( new Taxonomy() );
+                        }
+                        String id = name;
+                        final int i = name.indexOf( '_' );
+                        if ( i > 0 ) {
+                            id = name.substring( 0, i );
+                        }
+                        else {
+                            n.setName( "" );
+                        }
+                        n.getNodeData().getTaxonomy()
+                                .setIdentifier( new Identifier( id, PhyloXmlUtil.UNIPROT_TAX_PROVIDER ) );
+                        break;
+                    }
+                    case TAXONOMY_ID_UNIPROT_2: {
+                        if ( !n.getNodeData().isHasTaxonomy() ) {
+                            n.getNodeData().setTaxonomy( new Taxonomy() );
+                        }
+                        String id = name;
+                        final int i = name.indexOf( '_' );
+                        if ( i > 0 ) {
+                            id = name.substring( i + 1, name.length() );
+                        }
+                        else {
+                            n.setName( "" );
+                        }
+                        n.getNodeData().getTaxonomy()
+                                .setIdentifier( new Identifier( id, PhyloXmlUtil.UNIPROT_TAX_PROVIDER ) );
+                        break;
+                    }
+                    case TAXONOMY_ID: {
+                        if ( !n.getNodeData().isHasTaxonomy() ) {
+                            n.getNodeData().setTaxonomy( new Taxonomy() );
+                        }
+                        n.getNodeData().getTaxonomy().setIdentifier( new Identifier( name ) );
+                        break;
+                    }
+                }
+            }
+        }
+    }
+
     static double addPhylogenyDistances( final double a, final double b ) {
         if ( ( a >= 0.0 ) && ( b >= 0.0 ) ) {
             return a + b;
@@ -180,7 +496,7 @@ public class PhylogenyMethods {
         else if ( b >= 0.0 ) {
             return b;
         }
-        return PhylogenyNode.DISTANCE_DEFAULT;
+        return PhylogenyDataUtil.BRANCH_LENGTH_DEFAULT;
     }
 
     // Helper for getUltraParalogousNodes( PhylogenyNode ).
@@ -284,13 +600,39 @@ public class PhylogenyMethods {
         return stats;
     }
 
-    public static DescriptiveStatistics calculatConfidenceStatistics( final Phylogeny phy ) {
+    public static DescriptiveStatistics calculatBranchLengthStatistics( final Phylogeny phy ) {
         final DescriptiveStatistics stats = new BasicDescriptiveStatistics();
         for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
             final PhylogenyNode n = iter.next();
-            if ( !n.isExternal() ) {
+            if ( !n.isRoot() && ( n.getDistanceToParent() >= 0.0 ) ) {
+                stats.addValue( n.getDistanceToParent() );
+            }
+        }
+        return stats;
+    }
+
+    public static List<DescriptiveStatistics> calculatConfidenceStatistics( final Phylogeny phy ) {
+        final List<DescriptiveStatistics> stats = new ArrayList<DescriptiveStatistics>();
+        for( final PhylogenyNodeIterator iter = phy.iteratorPreorder(); iter.hasNext(); ) {
+            final PhylogenyNode n = iter.next();
+            if ( !n.isExternal() && !n.isRoot() ) {
                 if ( n.getBranchData().isHasConfidences() ) {
-                    stats.addValue( n.getBranchData().getConfidence( 0 ).getValue() );
+                    for( int i = 0; i < n.getBranchData().getConfidences().size(); ++i ) {
+                        final Confidence c = n.getBranchData().getConfidences().get( i );
+                        if ( ( i > ( stats.size() - 1 ) ) || ( stats.get( i ) == null ) ) {
+                            stats.add( i, new BasicDescriptiveStatistics() );
+                        }
+                        if ( !ForesterUtil.isEmpty( c.getType() ) ) {
+                            if ( !ForesterUtil.isEmpty( stats.get( i ).getDescription() ) ) {
+                                if ( !stats.get( i ).getDescription().equalsIgnoreCase( c.getType() ) ) {
+                                    throw new IllegalArgumentException( "support values in node [" + n.toString()
+                                            + "] appear inconsistently ordered" );
+                                }
+                            }
+                            stats.get( i ).setDescription( c.getType() );
+                        }
+                        stats.get( i ).addValue( ( ( c != null ) && ( c.getValue() >= 0 ) ) ? c.getValue() : 0 );
+                    }
                 }
             }
         }
@@ -1013,16 +1355,16 @@ public class PhylogenyMethods {
                 }
             }
             if ( !match && ( node.getNodeData().getBinaryCharacters() != null ) ) {
-                final String[] bcp_ary = node.getNodeData().getBinaryCharacters().getPresentCharactersAsStringArray();
-                I: for( final String bc : bcp_ary ) {
-                    if ( match( bc, query, case_sensitive, partial ) ) {
+                Iterator<String> it = node.getNodeData().getBinaryCharacters().getPresentCharacters().iterator();
+                I: while ( it.hasNext() ) {
+                    if ( match( it.next(), query, case_sensitive, partial ) ) {
                         match = true;
                         break I;
                     }
                 }
-                final String[] bcg_ary = node.getNodeData().getBinaryCharacters().getGainedCharactersAsStringArray();
-                I: for( final String bc : bcg_ary ) {
-                    if ( match( bc, query, case_sensitive, partial ) ) {
+                it = node.getNodeData().getBinaryCharacters().getGainedCharacters().iterator();
+                I: while ( it.hasNext() ) {
+                    if ( match( it.next(), query, case_sensitive, partial ) ) {
                         match = true;
                         break I;
                     }
@@ -1112,22 +1454,36 @@ public class PhylogenyMethods {
                     }
                 }
                 if ( !match && ( node.getNodeData().getBinaryCharacters() != null ) ) {
-                    final String[] bcp_ary = node.getNodeData().getBinaryCharacters()
-                            .getPresentCharactersAsStringArray();
-                    I: for( final String bc : bcp_ary ) {
-                        if ( match( bc, query, case_sensitive, partial ) ) {
+                    Iterator<String> it = node.getNodeData().getBinaryCharacters().getPresentCharacters().iterator();
+                    I: while ( it.hasNext() ) {
+                        if ( match( it.next(), query, case_sensitive, partial ) ) {
                             match = true;
                             break I;
                         }
                     }
-                    final String[] bcg_ary = node.getNodeData().getBinaryCharacters()
-                            .getGainedCharactersAsStringArray();
-                    I: for( final String bc : bcg_ary ) {
-                        if ( match( bc, query, case_sensitive, partial ) ) {
+                    it = node.getNodeData().getBinaryCharacters().getGainedCharacters().iterator();
+                    I: while ( it.hasNext() ) {
+                        if ( match( it.next(), query, case_sensitive, partial ) ) {
                             match = true;
                             break I;
                         }
                     }
+                    //                    final String[] bcp_ary = node.getNodeData().getBinaryCharacters()
+                    //                            .getPresentCharactersAsStringArray();
+                    //                    I: for( final String bc : bcp_ary ) {
+                    //                        if ( match( bc, query, case_sensitive, partial ) ) {
+                    //                            match = true;
+                    //                            break I;
+                    //                        }
+                    //                    }
+                    //                    final String[] bcg_ary = node.getNodeData().getBinaryCharacters()
+                    //                            .getGainedCharactersAsStringArray();
+                    //                    I: for( final String bc : bcg_ary ) {
+                    //                        if ( match( bc, query, case_sensitive, partial ) ) {
+                    //                            match = true;
+                    //                            break I;
+                    //                        }
+                    //                    }
                 }
                 if ( !match ) {
                     all_matched = false;
@@ -1236,4 +1592,67 @@ public class PhylogenyMethods {
         }
         return nodes_to_delete.size();
     }
+
+    /**
+     * Arranges the order of childern for each node of this Phylogeny in such a
+     * way that either the branch with more children is on top (right) or on
+     * bottom (left), dependent on the value of boolean order.
+     * 
+     * @param order
+     *            decides in which direction to order
+     * @param pri 
+     */
+    public static void orderAppearance( final PhylogenyNode n,
+                                        final boolean order,
+                                        final boolean order_ext_alphabetically,
+                                        final DESCENDANT_SORT_PRIORITY pri ) {
+        if ( n.isExternal() ) {
+            return;
+        }
+        else {
+            PhylogenyNode temp = null;
+            if ( ( n.getNumberOfDescendants() == 2 )
+                    && ( n.getChildNode1().getNumberOfExternalNodes() != n.getChildNode2().getNumberOfExternalNodes() )
+                    && ( ( n.getChildNode1().getNumberOfExternalNodes() < n.getChildNode2().getNumberOfExternalNodes() ) == order ) ) {
+                temp = n.getChildNode1();
+                n.setChild1( n.getChildNode2() );
+                n.setChild2( temp );
+            }
+            else if ( order_ext_alphabetically ) {
+                boolean all_ext = true;
+                for( final PhylogenyNode i : n.getDescendants() ) {
+                    if ( !i.isExternal() ) {
+                        all_ext = false;
+                        break;
+                    }
+                }
+                if ( all_ext ) {
+                    PhylogenyMethods.sortNodeDescendents( n, pri );
+                }
+            }
+            for( int i = 0; i < n.getNumberOfDescendants(); ++i ) {
+                orderAppearance( n.getChildNode( i ), order, order_ext_alphabetically, pri );
+            }
+        }
+    }
+
+    public static enum PhylogenyNodeField {
+        CLADE_NAME,
+        TAXONOMY_CODE,
+        TAXONOMY_SCIENTIFIC_NAME,
+        TAXONOMY_COMMON_NAME,
+        SEQUENCE_SYMBOL,
+        SEQUENCE_NAME,
+        TAXONOMY_ID_UNIPROT_1,
+        TAXONOMY_ID_UNIPROT_2,
+        TAXONOMY_ID;
+    }
+
+    public static enum TAXONOMY_EXTRACTION {
+        NO, YES, PFAM_STYLE_ONLY;
+    }
+
+    public static enum DESCENDANT_SORT_PRIORITY {
+        TAXONOMY, SEQUENCE, NODE_NAME;
+    }
 }