taxonomy extraction changed
[jalview.git] / forester / java / src / org / forester / archaeopteryx / MainFrame.java
index ae4f8b4..bc565ac 100644 (file)
@@ -20,7 +20,7 @@
 // Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA
 //
 // Contact: phylosoft @ gmail . com
-// WWW: www.phylosoft.org/forester
+// WWW: https://sites.google.com/site/cmzmasek/home/software/forester
 
 package org.forester.archaeopteryx;
 
@@ -34,7 +34,6 @@ import java.io.IOException;
 import java.util.LinkedList;
 import java.util.List;
 import java.util.Locale;
-import java.util.Map;
 import java.util.NoSuchElementException;
 import java.util.Set;
 
@@ -58,12 +57,18 @@ import org.forester.archaeopteryx.Options.PHYLOGENY_GRAPHICS_TYPE;
 import org.forester.archaeopteryx.tools.InferenceManager;
 import org.forester.archaeopteryx.tools.ProcessPool;
 import org.forester.archaeopteryx.tools.ProcessRunning;
+import org.forester.io.parsers.nhx.NHXParser.TAXONOMY_EXTRACTION;
 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.PhylogenyNodeI.NH_CONVERSION_SUPPORT_VALUE_STYLE;
+import org.forester.phylogeny.PhylogenyNode.NH_CONVERSION_SUPPORT_VALUE_STYLE;
 import org.forester.phylogeny.data.Annotation;
 import org.forester.phylogeny.data.NodeVisualization.NodeFill;
 import org.forester.phylogeny.data.NodeVisualization.NodeShape;
+import org.forester.sdi.GSDI;
+import org.forester.sdi.GSDIR;
+import org.forester.sdi.SDIException;
 import org.forester.util.ForesterConstants;
 import org.forester.util.ForesterUtil;
 
@@ -100,7 +105,8 @@ public abstract class MainFrame extends JFrame implements ActionListener {
     static final String         SCREEN_ANTIALIAS_LABEL                  = "Antialias";
     static final String         COLOR_LABELS_LABEL                      = "Colorize Labels Same as Parent Branch";
     static final String         BG_GRAD_LABEL                           = "Background Color Gradient";
-    static final String         DISPLAY_NODE_BOXES_LABEL                = "Show Node Shapes";
+    static final String         DISPLAY_NODE_BOXES_LABEL_EXT            = "Show External Node Shapes";
+    static final String         DISPLAY_NODE_BOXES_LABEL_INT            = "Show Internal Node Shapes";
     static final String         SHOW_OVERVIEW_LABEL                     = "Show Overview";
     static final String         FONT_SIZE_MENU_LABEL                    = "Font Size";
     static final String         NONUNIFORM_CLADOGRAMS_LABEL             = "External Node Sum Dependent Cladograms";
@@ -114,6 +120,7 @@ public abstract class MainFrame extends JFrame implements ActionListener {
     static final String         SHOW_CONF_STDDEV_LABEL                  = "Show Confidence Standard Deviations";
     static final String         USE_BRACKETS_FOR_CONF_IN_NH_LABEL       = "Use Brackets for Confidence Values";
     static final String         USE_INTERNAL_NAMES_FOR_CONF_IN_NH_LABEL = "Use Internal Node Names for Confidence Values";
+    static final String         SHOW_BASIC_TREE_INFORMATION_LABEL       = "Show Basic Tree Information";
     JMenuBar                    _jmenubar;
     JMenu                       _file_jmenu;
     JMenu                       _tools_menu;
@@ -122,6 +129,13 @@ public abstract class MainFrame extends JFrame implements ActionListener {
     JMenu                       _font_size_menu;
     JMenu                       _help_jmenu;
     JMenuItem[]                 _load_phylogeny_from_webservice_menu_items;
+    // Analysis menu
+    JMenu                       _analysis_menu;
+    JMenuItem                   _load_species_tree_item;
+    JMenuItem                   _gsdi_item;
+    JMenuItem                   _gsdir_item;
+    JMenuItem                   _lineage_inference;
+    JMenuItem                   _function_analysis;
     // file menu:
     JMenuItem                   _open_item;
     JMenuItem                   _open_url_item;
@@ -135,12 +149,11 @@ public abstract class MainFrame extends JFrame implements ActionListener {
     JMenuItem                   _taxcolor_item;
     JMenuItem                   _confcolor_item;
     JMenuItem                   _color_rank_jmi;
-    JMenuItem                   _infer_common_sn_names_item;
     JMenuItem                   _collapse_species_specific_subtrees;
     JMenuItem                   _collapse_below_threshold;                                                                                                                                                                                    //TODO implememt me
     JMenuItem                   _obtain_detailed_taxonomic_information_jmi;
     JMenuItem                   _obtain_detailed_taxonomic_information_deleting_jmi;
-    JMenuItem                   _obtain_uniprot_seq_information_jmi;
+    JMenuItem                   _obtain_seq_information_jmi;
     JMenuItem                   _move_node_names_to_tax_sn_jmi;
     JMenuItem                   _move_node_names_to_seq_names_jmi;
     JMenuItem                   _extract_tax_code_from_node_names_jmi;
@@ -170,7 +183,8 @@ public abstract class MainFrame extends JFrame implements ActionListener {
     JCheckBoxMenuItem           _color_labels_same_as_parent_branch;
     JMenuItem                   _overview_placment_mi;
     JMenuItem                   _choose_minimal_confidence_mi;
-    JCheckBoxMenuItem           _show_default_node_shapes_cbmi;
+    JCheckBoxMenuItem           _show_default_node_shapes_internal_cbmi;
+    JCheckBoxMenuItem           _show_default_node_shapes_external_cbmi;
     JMenuItem                   _cycle_node_shape_mi;
     JMenuItem                   _cycle_node_fill_mi;
     JMenuItem                   _choose_node_size_mi;
@@ -186,7 +200,10 @@ public abstract class MainFrame extends JFrame implements ActionListener {
     JMenuItem                   _choose_pdf_width_mi;
     // _  parsing
     JCheckBoxMenuItem           _internal_number_are_confidence_for_nh_parsing_cbmi;
-    JCheckBoxMenuItem           _extract_pfam_style_tax_codes_cbmi;
+    JRadioButtonMenuItem        _extract_taxonomy_no_rbmi;
+    JRadioButtonMenuItem        _extract_taxonomy_agressive_rbmi;
+    JRadioButtonMenuItem        _extract_taxonomy_pfam_strict_rbmi;
+    JRadioButtonMenuItem        _extract_taxonomy_pfam_relaxed_rbmi;
     JCheckBoxMenuItem           _replace_underscores_cbmi;
     JCheckBoxMenuItem           _use_brackets_for_conf_in_nh_export_cbmi;
     JCheckBoxMenuItem           _use_internal_names_for_conf_in_nh_export_cbmi;
@@ -206,7 +223,6 @@ public abstract class MainFrame extends JFrame implements ActionListener {
     JCheckBoxMenuItem           _circular_type_cbmi;
     // view as text menu:
     JMenuItem                   _view_as_NH_item;
-    JMenuItem                   _view_as_NHX_item;
     JMenuItem                   _view_as_XML_item;
     JMenuItem                   _view_as_nexus_item;
     JMenuItem                   _display_basic_information_item;
@@ -226,6 +242,7 @@ public abstract class MainFrame extends JFrame implements ActionListener {
     Configuration               _configuration;
     JMenuItem                   _remove_branch_color_item;
     Options                     _options;
+    private Phylogeny           _species_tree;
     InferenceManager            _inference_manager;
     final ProcessPool           _process_pool;
     private String              _previous_node_annotation_ref;
@@ -254,6 +271,18 @@ public abstract class MainFrame extends JFrame implements ActionListener {
         else if ( o == _exit_item ) {
             close();
         }
+        else if ( o == _gsdi_item ) {
+            if ( isSubtreeDisplayed() ) {
+                return;
+            }
+            executeGSDI();
+        }
+        else if ( o == _gsdir_item ) {
+            if ( isSubtreeDisplayed() ) {
+                return;
+            }
+            executeGSDIR();
+        }
         else if ( o == _taxcolor_item ) {
             taxColor();
         }
@@ -263,14 +292,6 @@ public abstract class MainFrame extends JFrame implements ActionListener {
         else if ( o == _color_rank_jmi ) {
             colorRank();
         }
-        else if ( o == _infer_common_sn_names_item ) {
-            if ( isSubtreeDisplayed() ) {
-                return;
-            }
-            if ( getCurrentTreePanel() != null ) {
-                getCurrentTreePanel().inferCommonPartOfScientificNames();
-            }
-        }
         else if ( o == _collapse_species_specific_subtrees ) {
             if ( isSubtreeDisplayed() ) {
                 return;
@@ -303,9 +324,6 @@ public abstract class MainFrame extends JFrame implements ActionListener {
         else if ( o == _view_as_NH_item ) {
             viewAsNH();
         }
-        else if ( o == _view_as_NHX_item ) {
-            viewAsNHX();
-        }
         else if ( o == _view_as_XML_item ) {
             viewAsXML();
         }
@@ -376,7 +394,10 @@ public abstract class MainFrame extends JFrame implements ActionListener {
         else if ( o == _color_labels_same_as_parent_branch ) {
             updateOptions( getOptions() );
         }
-        else if ( o == _show_default_node_shapes_cbmi ) {
+        else if ( o == _show_default_node_shapes_internal_cbmi ) {
+            updateOptions( getOptions() );
+        }
+        else if ( o == _show_default_node_shapes_external_cbmi ) {
             updateOptions( getOptions() );
         }
         else if ( o == _taxonomy_colorize_node_shapes_cbmi ) {
@@ -445,7 +466,7 @@ public abstract class MainFrame extends JFrame implements ActionListener {
             about();
         }
         else if ( o == _help_item ) {
-            help( getConfiguration().getWebLinks() );
+            help();
         }
         else if ( o == _website_item ) {
             try {
@@ -495,6 +516,26 @@ public abstract class MainFrame extends JFrame implements ActionListener {
         return _configuration;
     }
 
+    /**
+     * This method returns the current external node data which
+     * has been selected by the user by clicking the "Return ..."
+     * menu item. This method is expected to be called from Javascript or
+     * something like it.
+     * 
+     * @return current external node data as String
+     */
+    public String getCurrentExternalNodesDataBuffer() {
+        return getCurrentTreePanel().getCurrentExternalNodesDataBufferAsString();
+    }
+
+    public int getCurrentExternalNodesDataBufferChangeCounter() {
+        return getCurrentTreePanel().getCurrentExternalNodesDataBufferChangeCounter();
+    }
+
+    public int getCurrentExternalNodesDataBufferLength() {
+        return getCurrentTreePanel().getCurrentExternalNodesDataBufferAsString().length();
+    }
+
     public InferenceManager getInferenceManager() {
         return _inference_manager;
     }
@@ -612,15 +653,13 @@ public abstract class MainFrame extends JFrame implements ActionListener {
 
     void buildViewMenu() {
         _view_jmenu = createMenu( "View", getConfiguration() );
-        _view_jmenu.add( _display_basic_information_item = new JMenuItem( "Display Basic Information" ) );
+        _view_jmenu.add( _display_basic_information_item = new JMenuItem( SHOW_BASIC_TREE_INFORMATION_LABEL ) );
         _view_jmenu.addSeparator();
         _view_jmenu.add( _view_as_XML_item = new JMenuItem( "View as phyloXML" ) );
         _view_jmenu.add( _view_as_NH_item = new JMenuItem( "View as Newick" ) );
-        _view_jmenu.add( _view_as_NHX_item = new JMenuItem( "View as NHX" ) );
         _view_jmenu.add( _view_as_nexus_item = new JMenuItem( "View as Nexus" ) );
         customizeJMenuItem( _display_basic_information_item );
         customizeJMenuItem( _view_as_NH_item );
-        customizeJMenuItem( _view_as_NHX_item );
         customizeJMenuItem( _view_as_XML_item );
         customizeJMenuItem( _view_as_nexus_item );
         _jmenubar.add( _view_jmenu );
@@ -746,6 +785,148 @@ public abstract class MainFrame extends JFrame implements ActionListener {
         JOptionPane.showMessageDialog( this, "Exception" + e, "Error during File|SaveAs", JOptionPane.ERROR_MESSAGE );
     }
 
+    void executeGSDI() {
+        if ( !isOKforSDI( false, true ) ) {
+            return;
+        }
+        if ( !_mainpanel.getCurrentPhylogeny().isRooted() ) {
+            JOptionPane.showMessageDialog( this,
+                                           "Gene tree is not rooted.",
+                                           "Cannot execute GSDI",
+                                           JOptionPane.ERROR_MESSAGE );
+            return;
+        }
+        final Phylogeny gene_tree = _mainpanel.getCurrentPhylogeny().copy();
+        gene_tree.setAllNodesToNotCollapse();
+        gene_tree.recalculateNumberOfExternalDescendants( false );
+        GSDI gsdi = null;
+        final Phylogeny species_tree = getSpeciesTree().copy();
+        try {
+            gsdi = new GSDI( gene_tree, species_tree, false, true, true, true );
+        }
+        catch ( final SDIException e ) {
+            JOptionPane.showMessageDialog( this,
+                                           e.getLocalizedMessage(),
+                                           "Error during GSDI",
+                                           JOptionPane.ERROR_MESSAGE );
+            return;
+        }
+        catch ( final Exception e ) {
+            AptxUtil.unexpectedException( e );
+            return;
+        }
+        gene_tree.setRerootable( false );
+        gene_tree.clearHashIdToNodeMap();
+        gene_tree.recalculateNumberOfExternalDescendants( true );
+        _mainpanel.addPhylogenyInNewTab( gene_tree, getConfiguration(), "gene tree", null );
+        getMainPanel().getControlPanel().setShowEvents( true );
+        showWhole();
+        final int selected = _mainpanel.getTabbedPane().getSelectedIndex();
+        _mainpanel.addPhylogenyInNewTab( species_tree, getConfiguration(), "species tree", null );
+        showWhole();
+        _mainpanel.getTabbedPane().setSelectedIndex( selected );
+        showWhole();
+        _mainpanel.getCurrentTreePanel().setEdited( true );
+        final int poly = PhylogenyMethods.countNumberOfPolytomies( species_tree );
+        if ( gsdi.getStrippedExternalGeneTreeNodes().size() > 0 ) {
+            JOptionPane.showMessageDialog( this,
+                                           "Duplications: " + gsdi.getDuplicationsSum() + "\n"
+                                                   + "Potential duplications: "
+                                                   + gsdi.getSpeciationOrDuplicationEventsSum() + "\n"
+                                                   + "Speciations: " + gsdi.getSpeciationsSum() + "\n"
+                                                   + "Stripped gene tree nodes: "
+                                                   + gsdi.getStrippedExternalGeneTreeNodes().size() + "\n"
+                                                   + "Taxonomy linkage based on: " + gsdi.getTaxCompBase() + "\n"
+                                                   + "Number of polytomies in species tree used: " + poly + "\n",
+                                           "GSDI successfully completed",
+                                           JOptionPane.WARNING_MESSAGE );
+        }
+        else {
+            JOptionPane.showMessageDialog( this,
+                                           "Duplications: " + gsdi.getDuplicationsSum() + "\n"
+                                                   + "Potential duplications: "
+                                                   + gsdi.getSpeciationOrDuplicationEventsSum() + "\n"
+                                                   + "Speciations: " + gsdi.getSpeciationsSum() + "\n"
+                                                   + "Stripped gene tree nodes: "
+                                                   + gsdi.getStrippedExternalGeneTreeNodes().size() + "\n"
+                                                   + "Taxonomy linkage based on: " + gsdi.getTaxCompBase() + "\n"
+                                                   + "Number of polytomies in species tree used: " + poly + "\n",
+                                           "GSDI successfully completed",
+                                           JOptionPane.INFORMATION_MESSAGE );
+        }
+    }
+
+    void executeGSDIR() {
+        if ( !isOKforSDI( false, false ) ) {
+            return;
+        }
+        final int p = PhylogenyMethods.countNumberOfPolytomies( _mainpanel.getCurrentPhylogeny() );
+        if ( ( p > 0 )
+                && !( ( p == 1 ) && ( _mainpanel.getCurrentPhylogeny().getRoot().getNumberOfDescendants() == 3 ) ) ) {
+            JOptionPane.showMessageDialog( this,
+                                           "Gene tree is not completely binary",
+                                           "Cannot execute GSDI",
+                                           JOptionPane.ERROR_MESSAGE );
+            return;
+        }
+        final Phylogeny gene_tree = _mainpanel.getCurrentPhylogeny().copy();
+        gene_tree.setAllNodesToNotCollapse();
+        gene_tree.recalculateNumberOfExternalDescendants( false );
+        GSDIR gsdir = null;
+        final Phylogeny species_tree = getSpeciesTree().copy();
+        try {
+            gsdir = new GSDIR( gene_tree, species_tree, true, true, true );
+        }
+        catch ( final SDIException e ) {
+            JOptionPane.showMessageDialog( this,
+                                           e.getLocalizedMessage(),
+                                           "Error during GSDIR",
+                                           JOptionPane.ERROR_MESSAGE );
+            return;
+        }
+        catch ( final Exception e ) {
+            AptxUtil.unexpectedException( e );
+            return;
+        }
+        final Phylogeny result_gene_tree = gsdir.getMinDuplicationsSumGeneTree();
+        result_gene_tree.setRerootable( false );
+        result_gene_tree.clearHashIdToNodeMap();
+        result_gene_tree.recalculateNumberOfExternalDescendants( true );
+        PhylogenyMethods.orderAppearance( result_gene_tree.getRoot(), true, true, DESCENDANT_SORT_PRIORITY.NODE_NAME );
+        _mainpanel.addPhylogenyInNewTab( result_gene_tree, getConfiguration(), "gene tree", null );
+        getMainPanel().getControlPanel().setShowEvents( true );
+        showWhole();
+        final int selected = _mainpanel.getTabbedPane().getSelectedIndex();
+        _mainpanel.addPhylogenyInNewTab( species_tree, getConfiguration(), "species tree", null );
+        showWhole();
+        _mainpanel.getTabbedPane().setSelectedIndex( selected );
+        showWhole();
+        _mainpanel.getCurrentTreePanel().setEdited( true );
+        final int poly = PhylogenyMethods.countNumberOfPolytomies( species_tree );
+        if ( gsdir.getStrippedExternalGeneTreeNodes().size() > 0 ) {
+            JOptionPane.showMessageDialog( this,
+                                           "Minimal duplications: " + gsdir.getMinDuplicationsSum() + "\n"
+                                                   + "Speciations: " + gsdir.getSpeciationsSum() + "\n"
+                                                   + "Stripped gene tree nodes: "
+                                                   + gsdir.getStrippedExternalGeneTreeNodes().size() + "\n"
+                                                   + "Taxonomy linkage based on: " + gsdir.getTaxCompBase() + "\n"
+                                                   + "Number of polytomies in species tree used: " + poly + "\n",
+                                           "GSDIR successfully completed",
+                                           JOptionPane.WARNING_MESSAGE );
+        }
+        else {
+            JOptionPane.showMessageDialog( this,
+                                           "Minimal duplications: " + gsdir.getMinDuplicationsSum() + "\n"
+                                                   + "Speciations: " + gsdir.getSpeciationsSum() + "\n"
+                                                   + "Stripped gene tree nodes: "
+                                                   + gsdir.getStrippedExternalGeneTreeNodes().size() + "\n"
+                                                   + "Taxonomy linkage based on: " + gsdir.getTaxCompBase() + "\n"
+                                                   + "Number of polytomies in species tree used: " + poly + "\n",
+                                           "GSDIR successfully completed",
+                                           JOptionPane.INFORMATION_MESSAGE );
+        }
+    }
+
     boolean GAndSDoHaveMoreThanOneSpeciesInComman( final Phylogeny gene_tree ) {
         if ( ( gene_tree == null ) || gene_tree.isEmpty() ) {
             JOptionPane.showMessageDialog( this,
@@ -782,7 +963,11 @@ public abstract class MainFrame extends JFrame implements ActionListener {
         return _jmenubar;
     }
 
-    void help( final Map<String, WebLink> weblinks ) {
+    final Phylogeny getSpeciesTree() {
+        return _species_tree;
+    }
+
+    void help() {
         final StringBuilder sb = new StringBuilder();
         sb.append( "Display options\n" );
         sb.append( "-------------------\n" );
@@ -820,14 +1005,7 @@ public abstract class MainFrame extends JFrame implements ActionListener {
         sb.append( "Since the Java default memory allocation is quite small, it might by necessary (for trees\n" );
         sb.append( "with more than approximately 5000 external nodes) to increase the memory which Java can use, with\n" );
         sb.append( "the '-Xmx' Java command line option. For example:\n" );
-        sb.append( "java -Xms32m -Xmx256m -cp path\\to\\forester.jar org.forester.archaeopteryx.Archaeopteryx\n\n" );
-        if ( ( weblinks != null ) && ( weblinks.size() > 0 ) ) {
-            sb.append( "Active web links\n" );
-            sb.append( "--------------------\n" );
-            for( final String key : weblinks.keySet() ) {
-                sb.append( " " + weblinks.get( key ).toString() + "\n" );
-            }
-        }
+        sb.append( "java -Xmx1024m -cp path\\to\\forester.jar org.forester.archaeopteryx.Archaeopteryx\n\n" );
         // + "General remarks\n"
         // + "---------------\n"
         // +
@@ -868,14 +1046,13 @@ public abstract class MainFrame extends JFrame implements ActionListener {
         // + "    incorrect and need to be inferred again\n"
         // +
         // "    with: \"SDI\"|\"SDI (Speciation Duplication Inference)\n\n"
-        sb.append( "\n" );
         sb.append( "phyloXML\n" );
         sb.append( "-------------------\n" );
         sb.append( "Reference: " + Constants.PHYLOXML_REFERENCE + "\n" );
         sb.append( "Website: " + Constants.PHYLOXML_WEB_SITE + "\n" );
         sb.append( "Version: " + ForesterConstants.PHYLO_XML_VERSION + "\n" );
         sb.append( "\n" );
-        sb.append( "For more information: http://www.phylosoft.org/archaeopteryx/\n" );
+        sb.append( "For more information: https://sites.google.com/site/cmzmasek/home/software/archaeopteryx\n" );
         sb.append( "Email: " + Constants.AUTHOR_EMAIL + "\n\n" );
         TextFrame.instantiate( sb.toString(), "Help", _textframes );
     }
@@ -910,6 +1087,36 @@ public abstract class MainFrame extends JFrame implements ActionListener {
         }
     }
 
+    boolean isOKforSDI( final boolean species_tree_has_to_binary, final boolean gene_tree_has_to_binary ) {
+        if ( ( _mainpanel.getCurrentPhylogeny() == null ) || _mainpanel.getCurrentPhylogeny().isEmpty() ) {
+            return false;
+        }
+        else if ( ( getSpeciesTree() == null ) || getSpeciesTree().isEmpty() ) {
+            JOptionPane.showMessageDialog( this,
+                                           "No species tree loaded",
+                                           "Cannot execute GSDI",
+                                           JOptionPane.ERROR_MESSAGE );
+            return false;
+        }
+        else if ( species_tree_has_to_binary && !getSpeciesTree().isCompletelyBinary() ) {
+            JOptionPane.showMessageDialog( this,
+                                           "Species tree is not completely binary",
+                                           "Cannot execute GSDI",
+                                           JOptionPane.ERROR_MESSAGE );
+            return false;
+        }
+        else if ( gene_tree_has_to_binary && !_mainpanel.getCurrentPhylogeny().isCompletelyBinary() ) {
+            JOptionPane.showMessageDialog( this,
+                                           "Gene tree is not completely binary",
+                                           "Cannot execute GSDI",
+                                           JOptionPane.ERROR_MESSAGE );
+            return false;
+        }
+        else {
+            return true;
+        }
+    }
+
     boolean isSubtreeDisplayed() {
         if ( getCurrentTreePanel() != null ) {
             if ( getCurrentTreePanel().isCurrentTreeIsSubtree() ) {
@@ -990,6 +1197,10 @@ public abstract class MainFrame extends JFrame implements ActionListener {
         }
     }
 
+    final void setSpeciesTree( final Phylogeny species_tree ) {
+        _species_tree = species_tree;
+    }
+
     void setTypeMenuToAllUnselected() {
         _convex_type_cbmi.setSelected( false );
         _curved_type_cbmi.setSelected( false );
@@ -1053,8 +1264,10 @@ public abstract class MainFrame extends JFrame implements ActionListener {
                 && _abbreviate_scientific_names.isSelected() );
         options.setColorLabelsSameAsParentBranch( ( _color_labels_same_as_parent_branch != null )
                 && _color_labels_same_as_parent_branch.isSelected() );
-        options.setShowDefaultNodeShapes( ( _show_default_node_shapes_cbmi != null )
-                && _show_default_node_shapes_cbmi.isSelected() );
+        options.setShowDefaultNodeShapesInternal( ( _show_default_node_shapes_internal_cbmi != null )
+                && _show_default_node_shapes_internal_cbmi.isSelected() );
+        options.setShowDefaultNodeShapesExternal( ( _show_default_node_shapes_external_cbmi != null )
+                && _show_default_node_shapes_external_cbmi.isSelected() );
         options.setTaxonomyColorizeNodeShapes( ( _taxonomy_colorize_node_shapes_cbmi != null )
                 && _taxonomy_colorize_node_shapes_cbmi.isSelected() );
         if ( ( _non_lined_up_cladograms_rbmi != null ) && ( _non_lined_up_cladograms_rbmi.isSelected() ) ) {
@@ -1105,8 +1318,18 @@ public abstract class MainFrame extends JFrame implements ActionListener {
                 && _print_black_and_white_cbmi.isSelected() );
         options.setInternalNumberAreConfidenceForNhParsing( ( _internal_number_are_confidence_for_nh_parsing_cbmi != null )
                 && _internal_number_are_confidence_for_nh_parsing_cbmi.isSelected() );
-        options.setExtractPfamTaxonomyCodesInNhParsing( ( _extract_pfam_style_tax_codes_cbmi != null )
-                && _extract_pfam_style_tax_codes_cbmi.isSelected() );
+        if ( ( _extract_taxonomy_pfam_strict_rbmi != null ) && _extract_taxonomy_pfam_strict_rbmi.isSelected() ) {
+            options.setTaxonomyExtraction( TAXONOMY_EXTRACTION.PFAM_STYLE_STRICT );
+        }
+        else if ( ( _extract_taxonomy_pfam_relaxed_rbmi != null ) && _extract_taxonomy_pfam_relaxed_rbmi.isSelected() ) {
+            options.setTaxonomyExtraction( TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED );
+        }
+        else if ( ( _extract_taxonomy_agressive_rbmi != null ) && _extract_taxonomy_agressive_rbmi.isSelected() ) {
+            options.setTaxonomyExtraction( TAXONOMY_EXTRACTION.AGGRESSIVE );
+        }
+        else if ( ( _extract_taxonomy_no_rbmi != null ) && _extract_taxonomy_no_rbmi.isSelected() ) {
+            options.setTaxonomyExtraction( TAXONOMY_EXTRACTION.NO );
+        }
         options.setReplaceUnderscoresInNhParsing( ( _replace_underscores_cbmi != null )
                 && _replace_underscores_cbmi.isSelected() );
         options.setMatchWholeTermsOnly( ( _search_whole_words_only_cbmi != null )
@@ -1177,16 +1400,6 @@ public abstract class MainFrame extends JFrame implements ActionListener {
         }
     }
 
-    void viewAsNHX() {
-        if ( ( _mainpanel.getCurrentPhylogeny() != null ) && !_mainpanel.getCurrentPhylogeny().isEmpty() ) {
-            String title = "NHX";
-            if ( !ForesterUtil.isEmpty( _mainpanel.getCurrentPhylogeny().getName() ) ) {
-                title = _mainpanel.getCurrentPhylogeny().getName() + " " + title;
-            }
-            showTextFrame( _mainpanel.getCurrentPhylogeny().toNewHampshireX(), title );
-        }
-    }
-
     void viewAsXML() {
         if ( ( _mainpanel.getCurrentPhylogeny() != null ) && !_mainpanel.getCurrentPhylogeny().isEmpty() ) {
             String title = "phyloXML";
@@ -1199,7 +1412,7 @@ public abstract class MainFrame extends JFrame implements ActionListener {
 
     private void annotateSequences() {
         if ( getCurrentTreePanel() != null ) {
-            final Set<Integer> nodes = getCurrentTreePanel().getFoundNodes();
+            final Set<Long> nodes = getCurrentTreePanel().getFoundNodes();
             if ( ( nodes == null ) || nodes.isEmpty() ) {
                 JOptionPane
                         .showMessageDialog( this,
@@ -1210,37 +1423,45 @@ public abstract class MainFrame extends JFrame implements ActionListener {
             }
             final Phylogeny phy = getMainPanel().getCurrentPhylogeny();
             if ( ( phy != null ) && !phy.isEmpty() ) {
-                final JTextField xField = new JTextField( 10 );
-                final JTextField yField = new JTextField( 20 );
-                xField.setText( ForesterUtil.isEmpty( getPreviousNodeAnnotationReference() ) ? ""
+                final JTextField ref_field = new JTextField( 10 );
+                final JTextField desc_filed = new JTextField( 20 );
+                ref_field.setText( ForesterUtil.isEmpty( getPreviousNodeAnnotationReference() ) ? ""
                         : getPreviousNodeAnnotationReference() );
-                final JPanel myPanel = new JPanel();
-                myPanel.add( new JLabel( "Reference " ) );
-                myPanel.add( xField );
-                myPanel.add( Box.createHorizontalStrut( 15 ) );
-                myPanel.add( new JLabel( "Description " ) );
-                myPanel.add( yField );
+                final JPanel my_panel = new JPanel();
+                my_panel.add( new JLabel( "Reference " ) );
+                my_panel.add( ref_field );
+                my_panel.add( Box.createHorizontalStrut( 15 ) );
+                my_panel.add( new JLabel( "Description " ) );
+                my_panel.add( desc_filed );
                 final int result = JOptionPane.showConfirmDialog( null,
-                                                                  myPanel,
+                                                                  my_panel,
                                                                   "Enter the sequence annotation(s) for the "
                                                                           + nodes.size() + " selected nodes",
                                                                   JOptionPane.OK_CANCEL_OPTION );
                 if ( result == JOptionPane.OK_OPTION ) {
-                    String ref = xField.getText();
-                    String desc = yField.getText();
-                    if ( ref != null ) {
+                    String ref = ref_field.getText();
+                    String desc = desc_filed.getText();
+                    if ( !ForesterUtil.isEmpty( ref ) ) {
                         ref = ref.trim();
                         ref = ref.replaceAll( "\\s+", " " );
+                        if ( ( ref.indexOf( ':' ) < 1 ) || ( ref.indexOf( ':' ) > ref.length() - 2 )
+                                || ( ref.length() < 3 ) ) {
+                            JOptionPane.showMessageDialog( this,
+                                                           "Reference needs to be in the form of \"GO:1234567\"",
+                                                           "Illegal Format for Annotation Reference",
+                                                           JOptionPane.ERROR_MESSAGE );
+                            return;
+                        }
+                    }
+                    if ( ref != null ) {
+                        setPreviousNodeAnnotationReference( ref );
                     }
                     if ( desc != null ) {
                         desc = desc.trim();
                         desc = desc.replaceAll( "\\s+", " " );
                     }
-                    if ( ref != null ) {
-                        setPreviousNodeAnnotationReference( ref );
-                    }
                     if ( !ForesterUtil.isEmpty( ref ) || !ForesterUtil.isEmpty( desc ) ) {
-                        for( final Integer id : nodes ) {
+                        for( final Long id : nodes ) {
                             final PhylogenyNode n = phy.getNode( id );
                             ForesterUtil.ensurePresenceOfSequence( n );
                             final Annotation ann = ForesterUtil.isEmpty( ref ) ? new Annotation()
@@ -1251,19 +1472,12 @@ public abstract class MainFrame extends JFrame implements ActionListener {
                             n.getNodeData().getSequence().addAnnotation( ann );
                         }
                     }
+                    getMainPanel().getControlPanel().showAnnotations();
                 }
             }
         }
     }
 
-    private String getPreviousNodeAnnotationReference() {
-        return _previous_node_annotation_ref;
-    }
-
-    private void setPreviousNodeAnnotationReference( final String previous_node_annotation_ref ) {
-        _previous_node_annotation_ref = previous_node_annotation_ref;
-    }
-
     private void chooseFont() {
         final FontChooser fc = new FontChooser();
         fc.setFont( getMainPanel().getTreeFontSet().getLargeFont() );
@@ -1328,18 +1542,26 @@ public abstract class MainFrame extends JFrame implements ActionListener {
         repaint();
     }
 
+    private String getPreviousNodeAnnotationReference() {
+        return _previous_node_annotation_ref;
+    }
+
     private void removeBranchColors() {
         if ( getMainPanel().getCurrentPhylogeny() != null ) {
             AptxUtil.removeBranchColors( getMainPanel().getCurrentPhylogeny() );
         }
     }
 
+    private void setPreviousNodeAnnotationReference( final String previous_node_annotation_ref ) {
+        _previous_node_annotation_ref = previous_node_annotation_ref;
+    }
+
     /**
      * Display the about box.
      */
     static void about() {
         final StringBuffer about = new StringBuffer( "Archaeopteryx\nVersion " + Constants.VERSION + "\n" );
-        about.append( "Copyright (C) 2007-2012 Christian M. Zmasek\n" );
+        about.append( "Copyright (C) 2013 Christian M. Zmasek\n" );
         about.append( "All Rights Reserved\n" );
         about.append( "License: GNU Lesser General Public License (LGPL)\n" );
         about.append( "Last modified: " + Constants.PRG_DATE + "\n" );