rio - gsdir work...
[jalview.git] / forester / java / src / org / forester / archaeopteryx / MainFrameApplication.java
index f717323..babcf6d 100644 (file)
@@ -36,6 +36,7 @@ import java.awt.event.WindowEvent;
 import java.io.File;
 import java.io.FileInputStream;
 import java.io.IOException;
+import java.io.InputStream;
 import java.net.MalformedURLException;
 import java.net.URL;
 import java.util.ArrayList;
@@ -59,17 +60,18 @@ import javax.swing.event.ChangeListener;
 import javax.swing.filechooser.FileFilter;
 import javax.swing.plaf.synth.SynthLookAndFeel;
 
+import org.forester.analysis.TaxonomyDataManager;
 import org.forester.archaeopteryx.AptxUtil.GraphicsExportType;
 import org.forester.archaeopteryx.Options.CLADOGRAM_TYPE;
 import org.forester.archaeopteryx.Options.NODE_LABEL_DIRECTION;
 import org.forester.archaeopteryx.Options.PHYLOGENY_GRAPHICS_TYPE;
 import org.forester.archaeopteryx.tools.AncestralTaxonomyInferrer;
 import org.forester.archaeopteryx.tools.GoAnnotation;
+import org.forester.archaeopteryx.tools.InferenceManager;
 import org.forester.archaeopteryx.tools.PhyloInferenceDialog;
 import org.forester.archaeopteryx.tools.PhylogeneticInferenceOptions;
 import org.forester.archaeopteryx.tools.PhylogeneticInferrer;
 import org.forester.archaeopteryx.tools.SequenceDataRetriver;
-import org.forester.archaeopteryx.tools.TaxonomyDataObtainer;
 import org.forester.archaeopteryx.webservices.PhylogeniesWebserviceClient;
 import org.forester.archaeopteryx.webservices.WebservicesManager;
 import org.forester.io.parsers.FastaParser;
@@ -77,6 +79,8 @@ import org.forester.io.parsers.GeneralMsaParser;
 import org.forester.io.parsers.PhylogenyParser;
 import org.forester.io.parsers.nexus.NexusPhylogeniesParser;
 import org.forester.io.parsers.nhx.NHXParser;
+import org.forester.io.parsers.nhx.NHXParser.TAXONOMY_EXTRACTION;
+import org.forester.io.parsers.phyloxml.PhyloXmlDataFormatException;
 import org.forester.io.parsers.phyloxml.PhyloXmlParser;
 import org.forester.io.parsers.phyloxml.PhyloXmlUtil;
 import org.forester.io.parsers.tol.TolParser;
@@ -88,16 +92,15 @@ import org.forester.msa.MsaFormatException;
 import org.forester.phylogeny.Phylogeny;
 import org.forester.phylogeny.PhylogenyMethods;
 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.Confidence;
 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.sdi.GSDI;
-import org.forester.sdi.SDI;
+import org.forester.sdi.GSDIR;
 import org.forester.sdi.SDIR;
-import org.forester.sdi.SDIse;
 import org.forester.sequence.Sequence;
 import org.forester.util.BasicDescriptiveStatistics;
 import org.forester.util.BasicTable;
@@ -201,8 +204,8 @@ public final class MainFrameApplication extends MainFrame {
     // Analysis menu
     private JMenu                            _analysis_menu;
     private JMenuItem                        _load_species_tree_item;
-    private JMenuItem                        _sdi_item;
     private JMenuItem                        _gsdi_item;
+    private JMenuItem                        _gsdir_item;
     private JMenuItem                        _root_min_dups_item;
     private JMenuItem                        _root_min_cost_l_item;
     private JMenuItem                        _lineage_inference;
@@ -218,6 +221,7 @@ public final class MainFrameApplication extends MainFrame {
     private Phylogeny                        _species_tree;
     private File                             _current_dir;
     private ButtonGroup                      _radio_group_1;
+    private ButtonGroup                      _radio_group_2;
     // Others:
     double                                   _min_not_collapse                     = Constants.MIN_NOT_COLLAPSE_DEFAULT;
     // Phylogeny Inference menu
@@ -234,6 +238,14 @@ public final class MainFrameApplication extends MainFrame {
     JMenuItem                                _read_values_jmi;
 
     private MainFrameApplication( final Phylogeny[] phys, final Configuration config, final String title ) {
+        this( phys, config, title, null );
+    }
+
+    private MainFrameApplication( final Phylogeny[] phys,
+                                  final Configuration config,
+                                  final String title,
+                                  final File current_dir ) {
+        super();
         _configuration = config;
         if ( _configuration == null ) {
             throw new IllegalArgumentException( "configuration is null" );
@@ -279,11 +291,15 @@ public final class MainFrameApplication extends MainFrame {
         catch ( final Exception e ) {
             AptxUtil.dieWithSystemError( e.toString() );
         }
+        if ( ( current_dir != null ) && current_dir.canRead() && current_dir.isDirectory() ) {
+            setCurrentDir( current_dir );
+        }
         // hide until everything is ready
         setVisible( false );
         setOptions( Options.createInstance( _configuration ) );
+        setInferenceManager( InferenceManager.createInstance( _configuration ) );
         setPhylogeneticInferenceOptions( PhylogeneticInferenceOptions.createInstance( _configuration ) );
-        _textframe = null;
+        //     _textframe = null; #~~~~
         _species_tree = null;
         // set title
         setTitle( Constants.PRG_NAME + " " + Constants.VERSION + " (" + Constants.PRG_DATE + ")" );
@@ -518,12 +534,6 @@ public final class MainFrameApplication extends MainFrame {
             else if ( o == _load_species_tree_item ) {
                 readSpeciesTreeFromFile();
             }
-            else if ( o == _sdi_item ) {
-                if ( isSubtreeDisplayed() ) {
-                    return;
-                }
-                executeSDI();
-            }
             else if ( o == _lineage_inference ) {
                 if ( isSubtreeDisplayed() ) {
                     JOptionPane.showMessageDialog( this,
@@ -549,8 +559,8 @@ public final class MainFrameApplication extends MainFrame {
                 }
                 obtainDetailedTaxonomicInformationDelete();
             }
-            else if ( o == _obtain_uniprot_seq_information_jmi ) {
-                obtainUniProtSequenceInformation();
+            else if ( o == _obtain_seq_information_jmi ) {
+                obtainSequenceInformation();
             }
             else if ( o == _read_values_jmi ) {
                 if ( isSubtreeDisplayed() ) {
@@ -573,6 +583,12 @@ public final class MainFrameApplication extends MainFrame {
                 }
                 executeGSDI();
             }
+            else if ( o == _gsdir_item ) {
+                if ( isSubtreeDisplayed() ) {
+                    return;
+                }
+                executeGSDIR();
+            }
             else if ( o == _root_min_dups_item ) {
                 if ( isSubtreeDisplayed() ) {
                     return;
@@ -610,8 +626,8 @@ public final class MainFrameApplication extends MainFrame {
                 updateOptions( getOptions() );
             }
             else if ( o == _replace_underscores_cbmi ) {
-                if ( ( _extract_pfam_style_tax_codes_cbmi != null ) && _replace_underscores_cbmi.isSelected() ) {
-                    _extract_pfam_style_tax_codes_cbmi.setSelected( false );
+                if ( ( _extract_taxonomy_no_rbmi != null ) && !_extract_taxonomy_no_rbmi.isSelected() ) {
+                    _extract_taxonomy_no_rbmi.setSelected( true );
                 }
                 updateOptions( getOptions() );
             }
@@ -621,8 +637,8 @@ public final class MainFrameApplication extends MainFrame {
                 }
                 collapseBelowThreshold();
             }
-            else if ( o == _extract_pfam_style_tax_codes_cbmi ) {
-                if ( ( _replace_underscores_cbmi != null ) && _extract_pfam_style_tax_codes_cbmi.isSelected() ) {
+            else if ( ( o == _extract_taxonomy_pfam_rbmi ) || ( o == _extract_taxonomy_yes_rbmi ) ) {
+                if ( _replace_underscores_cbmi != null ) {
                     _replace_underscores_cbmi.setSelected( false );
                 }
                 updateOptions( getOptions() );
@@ -645,17 +661,15 @@ public final class MainFrameApplication extends MainFrame {
 
     void buildAnalysisMenu() {
         _analysis_menu = MainFrame.createMenu( "Analysis", getConfiguration() );
-        _analysis_menu.add( _sdi_item = new JMenuItem( "SDI (Speciation Duplication Inference)" ) );
-        if ( !Constants.__RELEASE && !Constants.__SNAPSHOT_RELEASE ) {
-            _analysis_menu.add( _gsdi_item = new JMenuItem( "GSDI (Generalized Speciation Duplication Inference)" ) );
-        }
+        _analysis_menu.add( _gsdi_item = new JMenuItem( "GSDI (Generalized Speciation Duplication Inference)" ) );
+        _analysis_menu.add( _gsdir_item = new JMenuItem( "GSDIR (re-rooting)" ) );
         _analysis_menu.addSeparator();
         _analysis_menu.add( _root_min_dups_item = new JMenuItem( "Root by Minimizing Duplications | Height (SDI)" ) );
         _analysis_menu.add( _root_min_cost_l_item = new JMenuItem( "Root by Minimizing Cost L | Height (SDI)" ) );
         _analysis_menu.addSeparator();
         _analysis_menu.add( _load_species_tree_item = new JMenuItem( "Load Species Tree..." ) );
-        customizeJMenuItem( _sdi_item );
         customizeJMenuItem( _gsdi_item );
+        customizeJMenuItem( _gsdir_item );
         customizeJMenuItem( _root_min_dups_item );
         customizeJMenuItem( _root_min_cost_l_item );
         customizeJMenuItem( _load_species_tree_item );
@@ -667,15 +681,23 @@ public final class MainFrameApplication extends MainFrame {
     }
 
     void buildPhylogeneticInferenceMenu() {
+        final InferenceManager im = getInferenceManager();
         _inference_menu = MainFrame.createMenu( "Inference", getConfiguration() );
-        _inference_menu
-                .add( _inference_from_msa_item = new JMenuItem( "From Multiple Sequence Alignment...(EXPERIMENTAL - DO NOT USE!!) " ) );
+        _inference_menu.add( _inference_from_msa_item = new JMenuItem( "From Multiple Sequence Alignment..." ) );
         customizeJMenuItem( _inference_from_msa_item );
         _inference_from_msa_item.setToolTipText( "Basic phylogenetic inference from MSA" );
-        _inference_menu
-                .add( _inference_from_seqs_item = new JMenuItem( "From Unaligned Sequences...(EXPERIMENTAL - DO NOT USE!!) " ) );
-        customizeJMenuItem( _inference_from_seqs_item );
-        _inference_from_seqs_item.setToolTipText( "Basic phylogenetic inference including multiple sequence alignment" );
+        if ( im.canDoMsa() ) {
+            _inference_menu.add( _inference_from_seqs_item = new JMenuItem( "From Unaligned Sequences..." ) );
+            customizeJMenuItem( _inference_from_seqs_item );
+            _inference_from_seqs_item
+                    .setToolTipText( "Basic phylogenetic inference including multiple sequence alignment" );
+        }
+        else {
+            _inference_menu
+                    .add( _inference_from_seqs_item = new JMenuItem( "From Unaligned Sequences (no program found)" ) );
+            customizeJMenuItem( _inference_from_seqs_item );
+            _inference_from_seqs_item.setEnabled( false );
+        }
         _jmenubar.add( _inference_menu );
     }
 
@@ -833,8 +855,21 @@ public final class MainFrameApplication extends MainFrame {
         _options_jmenu
                 .add( _internal_number_are_confidence_for_nh_parsing_cbmi = new JCheckBoxMenuItem( "Internal Node Names are Confidence Values" ) );
         _options_jmenu.add( _replace_underscores_cbmi = new JCheckBoxMenuItem( "Replace Underscores with Spaces" ) );
+        //
+        _options_jmenu.add( _extract_taxonomy_no_rbmi = new JRadioButtonMenuItem( "No Taxonomy Extraction" ) );
+        _options_jmenu
+                .add( _extract_taxonomy_pfam_rbmi = new JRadioButtonMenuItem( "Extract Taxonomy Codes from Pfam-style Node Names" ) );
+        _extract_taxonomy_pfam_rbmi
+                .setToolTipText( "To extract 5-letter taxonomy codes from node names in the form of \"BCL2_MOUSE/134-298\"" );
         _options_jmenu
-                .add( _extract_pfam_style_tax_codes_cbmi = new JCheckBoxMenuItem( "Extract Taxonomy Codes from Pfam-style Labels" ) );
+                .add( _extract_taxonomy_yes_rbmi = new JRadioButtonMenuItem( "Extract Taxonomy Codes from Node Names" ) );
+        _extract_taxonomy_yes_rbmi
+                .setToolTipText( "To extract 5-letter taxonomy codes from node names in the form of \"BCL2_MOUSE\" or \"BCL2_MOUSE B-cell lymphoma 2...\"" );
+        _radio_group_2 = new ButtonGroup();
+        _radio_group_2.add( _extract_taxonomy_no_rbmi );
+        _radio_group_2.add( _extract_taxonomy_pfam_rbmi );
+        _radio_group_2.add( _extract_taxonomy_yes_rbmi );
+        // 
         _options_jmenu.add( customizeMenuItemAsLabel( new JMenuItem( "Newick/Nexus Output:" ), getConfiguration() ) );
         _options_jmenu
                 .add( _use_brackets_for_conf_in_nh_export_cbmi = new JCheckBoxMenuItem( USE_BRACKETS_FOR_CONF_IN_NH_LABEL ) );
@@ -874,8 +909,12 @@ public final class MainFrameApplication extends MainFrame {
         customizeCheckBoxMenuItem( _print_black_and_white_cbmi, getOptions().isPrintBlackAndWhite() );
         customizeCheckBoxMenuItem( _internal_number_are_confidence_for_nh_parsing_cbmi, getOptions()
                 .isInternalNumberAreConfidenceForNhParsing() );
-        customizeCheckBoxMenuItem( _extract_pfam_style_tax_codes_cbmi, getOptions()
-                .isExtractPfamTaxonomyCodesInNhParsing() );
+        customizeRadioButtonMenuItem( _extract_taxonomy_no_rbmi,
+                                      getOptions().getTaxonomyExtraction() == TAXONOMY_EXTRACTION.NO );
+        customizeRadioButtonMenuItem( _extract_taxonomy_yes_rbmi,
+                                      getOptions().getTaxonomyExtraction() == TAXONOMY_EXTRACTION.YES );
+        customizeRadioButtonMenuItem( _extract_taxonomy_pfam_rbmi,
+                                      getOptions().getTaxonomyExtraction() == TAXONOMY_EXTRACTION.PFAM_STYLE_ONLY );
         customizeCheckBoxMenuItem( _replace_underscores_cbmi, getOptions().isReplaceUnderscoresInNhParsing() );
         customizeCheckBoxMenuItem( _search_whole_words_only_cbmi, getOptions().isMatchWholeTermsOnly() );
         customizeCheckBoxMenuItem( _inverse_search_result_cbmi, getOptions().isInverseSearchResult() );
@@ -904,6 +943,9 @@ public final class MainFrameApplication extends MainFrame {
         _remove_branch_color_item.setToolTipText( "To delete branch color values from the current phylogeny" );
         customizeJMenuItem( _remove_branch_color_item );
         _tools_menu.addSeparator();
+        _tools_menu.add( _annotate_item = new JMenuItem( "Annotate Sequences of Selected Nodes" ) );
+        customizeJMenuItem( _annotate_item );
+        _tools_menu.addSeparator();
         _tools_menu.add( _midpoint_root_item = new JMenuItem( "Midpoint-Root" ) );
         customizeJMenuItem( _midpoint_root_item );
         _tools_menu.addSeparator();
@@ -929,10 +971,6 @@ public final class MainFrameApplication extends MainFrame {
                 .setToolTipText( "To extract taxonomic codes (mnemonics) from nodes names in the form of 'xyz_ECOLI'" );
         _tools_menu.addSeparator();
         _tools_menu
-                .add( _infer_common_sn_names_item = new JMenuItem( "Infer Common Parts of Internal Scientific Names" ) );
-        customizeJMenuItem( _infer_common_sn_names_item );
-        _tools_menu.addSeparator();
-        _tools_menu
                 .add( _obtain_detailed_taxonomic_information_jmi = new JMenuItem( OBTAIN_DETAILED_TAXONOMIC_INFORMATION ) );
         customizeJMenuItem( _obtain_detailed_taxonomic_information_jmi );
         _obtain_detailed_taxonomic_information_jmi
@@ -942,10 +980,9 @@ public final class MainFrameApplication extends MainFrame {
         customizeJMenuItem( _obtain_detailed_taxonomic_information_deleting_jmi );
         _obtain_detailed_taxonomic_information_deleting_jmi
                 .setToolTipText( "To add additional taxonomic information, deletes nodes for which taxonomy cannot found (from UniProt Taxonomy)" );
-        _tools_menu
-                .add( _obtain_uniprot_seq_information_jmi = new JMenuItem( "Obtain Sequence Information (from UniProt)" ) );
-        customizeJMenuItem( _obtain_uniprot_seq_information_jmi );
-        _obtain_uniprot_seq_information_jmi.setToolTipText( "To add additional sequence information (from UniProt)" );
+        _tools_menu.add( _obtain_seq_information_jmi = new JMenuItem( "Obtain Sequence Information" ) );
+        customizeJMenuItem( _obtain_seq_information_jmi );
+        _obtain_seq_information_jmi.setToolTipText( "To add additional sequence information" );
         _tools_menu.addSeparator();
         if ( !Constants.__RELEASE ) {
             _tools_menu.add( _function_analysis = new JMenuItem( "Add UniProtKB Annotations" ) );
@@ -1100,10 +1137,10 @@ public final class MainFrameApplication extends MainFrame {
             }
             if ( to_be_removed.size() > 0 ) {
                 phy.externalNodesHaveChanged();
-                phy.hashIDs();
+                phy.clearHashIdToNodeMap();
                 phy.recalculateNumberOfExternalDescendants( true );
                 getCurrentTreePanel().resetNodeIdToDistToLeafMap();
-                getCurrentTreePanel().updateSetOfCollapsedExternalNodes( phy );
+                getCurrentTreePanel().updateSetOfCollapsedExternalNodes();
                 getCurrentTreePanel().calculateLongestExtNodeInfo();
                 getCurrentTreePanel().setNodeInPreorderToNull();
                 getCurrentTreePanel().recalculateMaxDistanceToRoot();
@@ -1199,22 +1236,70 @@ public final class MainFrameApplication extends MainFrame {
         gene_tree.setAllNodesToNotCollapse();
         gene_tree.recalculateNumberOfExternalDescendants( false );
         GSDI gsdi = null;
-        int duplications = -1;
+        Phylogeny species_tree = _species_tree.copy();
         try {
-            gsdi = new GSDI( gene_tree, _species_tree.copy(), true );
-            duplications = gsdi.getDuplicationsSum();
+            gsdi = new GSDI( gene_tree, species_tree, false, true, true );
         }
         catch ( final Exception e ) {
             JOptionPane.showMessageDialog( this, e.toString(), "Error during GSDI", JOptionPane.ERROR_MESSAGE );
+            return;
         }
         gene_tree.setRerootable( false );
         _mainpanel.getCurrentTreePanel().setTree( gene_tree );
+        _mainpanel.getCurrentPhylogeny().clearHashIdToNodeMap();
+        _mainpanel.getCurrentPhylogeny().recalculateNumberOfExternalDescendants( true );
+        _mainpanel.getCurrentTreePanel().resetNodeIdToDistToLeafMap();
+        _mainpanel.getCurrentTreePanel().setEdited( true );
         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 );
+        JOptionPane.showMessageDialog( this, "Duplications: " + gsdi.getDuplicationsSum() + "\n"
+                + "Potential duplications: " + gsdi.getSpeciationOrDuplicationEventsSum() + "\n" + "Speciations: "
+                + gsdi.getSpeciationsSum(), "GSDI successfully completed", JOptionPane.INFORMATION_MESSAGE );
+    }
+
+    void executeGSDIR() {
+        if ( !isOKforSDI( false, true ) ) {
+            return;
+        }
+        final Phylogeny gene_tree = _mainpanel.getCurrentPhylogeny().copy();
+        gene_tree.setAllNodesToNotCollapse();
+        gene_tree.recalculateNumberOfExternalDescendants( false );
+        GSDIR gsdir = null;
+        Phylogeny species_tree = _species_tree.copy();
+        try {
+            gsdir = new GSDIR( gene_tree, species_tree, true, true );
+        }
+        catch ( final Exception e ) {
+            JOptionPane.showMessageDialog( this, e.toString(), "Error during GSDIR", JOptionPane.ERROR_MESSAGE );
+            return;
+        }
+        final Phylogeny result_gene_tree = gsdir.getMinDuplicationsSumGeneTrees().get( 0 );
+        result_gene_tree.setRerootable( false );
+        result_gene_tree.clearHashIdToNodeMap();
+        result_gene_tree.recalculateNumberOfExternalDescendants( true );
+        _mainpanel.addPhylogenyInNewTab( result_gene_tree, getConfiguration(), "gene tree", null );
+        //_mainpanel.getCurrentTreePanel().setTree( gene_tree );
+        // _mainpanel.getCurrentTreePanel().setEdited( true );
+        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 );
         JOptionPane.showMessageDialog( this,
-                                       "Number of duplications: " + duplications,
-                                       "GSDI successfully completed",
+                                       "Duplications: " + gsdir.getMinDuplicationsSum() + "\n" + "Speciations: "
+                                               + gsdir.getSpeciationsSum() + "\n"
+                                               + "Number of root positions minimizing duplications sum: "
+                                               + gsdir.getMinDuplicationsSumGeneTrees().size(),
+                                       "GSDIR successfully completed",
                                        JOptionPane.INFORMATION_MESSAGE );
     }
 
@@ -1283,40 +1368,6 @@ public final class MainFrameApplication extends MainFrame {
         }
     }
 
-    void executeSDI() {
-        if ( !isOKforSDI( true, true ) ) {
-            return;
-        }
-        if ( !_mainpanel.getCurrentPhylogeny().isRooted() ) {
-            JOptionPane.showMessageDialog( this,
-                                           "Gene tree is not rooted",
-                                           "Cannot execute SDI",
-                                           JOptionPane.ERROR_MESSAGE );
-            return;
-        }
-        final Phylogeny gene_tree = _mainpanel.getCurrentPhylogeny().copy();
-        gene_tree.setAllNodesToNotCollapse();
-        gene_tree.recalculateNumberOfExternalDescendants( false );
-        SDI sdi = null;
-        int duplications = -1;
-        try {
-            sdi = new SDIse( gene_tree, _species_tree.copy() );
-            duplications = sdi.getDuplicationsSum();
-        }
-        catch ( final Exception e ) {
-            JOptionPane.showMessageDialog( this, e.toString(), "Error during SDI", JOptionPane.ERROR_MESSAGE );
-        }
-        gene_tree.setRerootable( false );
-        _mainpanel.getCurrentTreePanel().setTree( gene_tree );
-        getControlPanel().setShowEvents( true );
-        showWhole();
-        _mainpanel.getCurrentTreePanel().setEdited( true );
-        JOptionPane.showMessageDialog( this,
-                                       "Number of duplications: " + duplications,
-                                       "SDI successfully completed",
-                                       JOptionPane.INFORMATION_MESSAGE );
-    }
-
     void executeSDIR( final boolean minimize_cost ) {
         if ( !isOKforSDI( true, true ) ) {
             return;
@@ -1349,7 +1400,7 @@ public final class MainFrameApplication extends MainFrame {
     }
 
     void exit() {
-        removeTextFrame();
+        removeAllTextFrames();
         _mainpanel.terminate();
         _contentpane.removeAll();
         setVisible( false );
@@ -1364,7 +1415,7 @@ public final class MainFrameApplication extends MainFrame {
         dispose();
     }
 
-    private void extractTaxCodeFromNodeNames() {
+    private void extractTaxCodeFromNodeNames() throws PhyloXmlDataFormatException {
         if ( getCurrentTreePanel() != null ) {
             final Phylogeny phy = getCurrentTreePanel().getPhylogeny();
             if ( ( phy != null ) && !phy.isEmpty() ) {
@@ -1374,7 +1425,7 @@ public final class MainFrameApplication extends MainFrame {
                     final String name = n.getName().trim();
                     if ( !ForesterUtil.isEmpty( name ) ) {
                         final String code = ParserUtils
-                                .extractTaxonomyCodeFromNodeName( name, false, PhylogenyMethods.TAXONOMY_EXTRACTION.YES );
+                                .extractTaxonomyCodeFromNodeName( name, NHXParser.TAXONOMY_EXTRACTION.YES );
                         if ( !ForesterUtil.isEmpty( code ) ) {
                             PhylogenyMethods.setTaxonomyCode( n, code );
                         }
@@ -1390,7 +1441,7 @@ public final class MainFrameApplication extends MainFrame {
 
     private File getCurrentDir() {
         if ( ( _current_dir == null ) || !_current_dir.canRead() ) {
-            if ( ForesterUtil.OS_NAME.toLowerCase().indexOf( "win" ) > -1 ) {
+            if ( ForesterUtil.isWindowns() ) {
                 try {
                     _current_dir = new File( WindowsUtils.getCurrentUserDesktopPath() );
                 }
@@ -1459,21 +1510,23 @@ public final class MainFrameApplication extends MainFrame {
         return false;
     }
 
-    private void moveNodeNamesToSeqNames() {
+    private void moveNodeNamesToSeqNames() throws PhyloXmlDataFormatException {
         if ( getCurrentTreePanel() != null ) {
             final Phylogeny phy = getCurrentTreePanel().getPhylogeny();
             if ( ( phy != null ) && !phy.isEmpty() ) {
-                PhylogenyMethods.transferNodeNameToField( phy, PhylogenyMethods.PhylogenyNodeField.SEQUENCE_NAME );
+                PhylogenyMethods
+                        .transferNodeNameToField( phy, PhylogenyMethods.PhylogenyNodeField.SEQUENCE_NAME, false );
             }
         }
     }
 
-    private void moveNodeNamesToTaxSn() {
+    private void moveNodeNamesToTaxSn() throws PhyloXmlDataFormatException {
         if ( getCurrentTreePanel() != null ) {
             final Phylogeny phy = getCurrentTreePanel().getPhylogeny();
             if ( ( phy != null ) && !phy.isEmpty() ) {
                 PhylogenyMethods.transferNodeNameToField( phy,
-                                                          PhylogenyMethods.PhylogenyNodeField.TAXONOMY_SCIENTIFIC_NAME );
+                                                          PhylogenyMethods.PhylogenyNodeField.TAXONOMY_SCIENTIFIC_NAME,
+                                                          false );
             }
         }
     }
@@ -1505,9 +1558,11 @@ public final class MainFrameApplication extends MainFrame {
         if ( getCurrentTreePanel() != null ) {
             final Phylogeny phy = getCurrentTreePanel().getPhylogeny();
             if ( ( phy != null ) && !phy.isEmpty() ) {
-                final TaxonomyDataObtainer t = new TaxonomyDataObtainer( this,
-                                                                         _mainpanel.getCurrentTreePanel(),
-                                                                         phy.copy() );
+                final TaxonomyDataManager t = new TaxonomyDataManager( this,
+                                                                       _mainpanel.getCurrentTreePanel(),
+                                                                       phy.copy(),
+                                                                       false,
+                                                                       true );
                 new Thread( t ).start();
             }
         }
@@ -1517,16 +1572,17 @@ public final class MainFrameApplication extends MainFrame {
         if ( getCurrentTreePanel() != null ) {
             final Phylogeny phy = getCurrentTreePanel().getPhylogeny();
             if ( ( phy != null ) && !phy.isEmpty() ) {
-                final TaxonomyDataObtainer t = new TaxonomyDataObtainer( this,
-                                                                         _mainpanel.getCurrentTreePanel(),
-                                                                         phy.copy(),
-                                                                         true );
+                final TaxonomyDataManager t = new TaxonomyDataManager( this,
+                                                                       _mainpanel.getCurrentTreePanel(),
+                                                                       phy.copy(),
+                                                                       true,
+                                                                       true );
                 new Thread( t ).start();
             }
         }
     }
 
-    private void obtainUniProtSequenceInformation() {
+    private void obtainSequenceInformation() {
         if ( getCurrentTreePanel() != null ) {
             final Phylogeny phy = getCurrentTreePanel().getPhylogeny();
             if ( ( phy != null ) && !phy.isEmpty() ) {
@@ -1991,12 +2047,12 @@ public final class MainFrameApplication extends MainFrame {
             setMsa( null );
             Msa msa = null;
             try {
-                if ( FastaParser.isLikelyFasta( new FileInputStream( file ) ) ) {
-                    msa = FastaParser.parseMsa( new FileInputStream( file ) );
-                    System.out.println( msa.toString() );
+                final InputStream is = new FileInputStream( file );
+                if ( FastaParser.isLikelyFasta( file ) ) {
+                    msa = FastaParser.parseMsa( is );
                 }
                 else {
-                    msa = GeneralMsaParser.parse( new FileInputStream( file ) );
+                    msa = GeneralMsaParser.parse( is );
                 }
             }
             catch ( final MsaFormatException e ) {
@@ -2268,11 +2324,7 @@ public final class MainFrameApplication extends MainFrame {
 
     private void setSpecialOptionsForNhxParser( final NHXParser nhx ) {
         nhx.setReplaceUnderscores( getOptions().isReplaceUnderscoresInNhParsing() );
-        PhylogenyMethods.TAXONOMY_EXTRACTION te = PhylogenyMethods.TAXONOMY_EXTRACTION.NO;
-        if ( getOptions().isExtractPfamTaxonomyCodesInNhParsing() ) {
-            te = PhylogenyMethods.TAXONOMY_EXTRACTION.YES;
-        }
-        nhx.setTaxonomyExtraction( te );
+        nhx.setTaxonomyExtraction( getOptions().getTaxonomyExtraction() );
     }
 
     private void writeAllToFile() {
@@ -2609,6 +2661,13 @@ public final class MainFrameApplication extends MainFrame {
         return new MainFrameApplication( phys, config_file_name, title );
     }
 
+    public static MainFrame createInstance( final Phylogeny[] phys,
+                                            final Configuration config,
+                                            final String title,
+                                            final File current_dir ) {
+        return new MainFrameApplication( phys, config, title, current_dir );
+    }
+
     static void setTextForGraphicsSizeChooserMenuItem( final JMenuItem mi, final Options o ) {
         mi.setText( "Enter Default Size for Graphics Export... (current: " + o.getPrintSizeX() + ", "
                 + o.getPrintSizeY() + ")" );