rio
[jalview.git] / forester / java / src / org / forester / archaeopteryx / MainFrameApplication.java
index 2c674fe..14b480f 100644 (file)
@@ -79,6 +79,7 @@ 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;
@@ -91,13 +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.GSDIR;
+import org.forester.sdi.SDIException;
 import org.forester.sdi.SDIR;
 import org.forester.sequence.Sequence;
 import org.forester.util.BasicDescriptiveStatistics;
@@ -203,6 +206,7 @@ public final class MainFrameApplication extends MainFrame {
     private JMenu                            _analysis_menu;
     private JMenuItem                        _load_species_tree_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 +222,7 @@ 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
@@ -555,8 +560,8 @@ 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() ) {
@@ -579,6 +584,12 @@ 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;
@@ -616,8 +627,8 @@ 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() );
             }
@@ -627,8 +638,8 @@ 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() );
@@ -652,12 +663,14 @@ public final class MainFrameApplication extends MainFrame {
     void buildAnalysisMenu() {
         _analysis_menu = MainFrame.createMenu( "Analysis", getConfiguration() );
         _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( _gsdi_item );
+        customizeJMenuItem( _gsdir_item );
         customizeJMenuItem( _root_min_dups_item );
         customizeJMenuItem( _root_min_cost_l_item );
         customizeJMenuItem( _load_species_tree_item );
@@ -843,8 +856,21 @@ 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 ) );
@@ -884,8 +910,12 @@ 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() );
@@ -914,6 +944,9 @@ 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();
@@ -939,10 +972,6 @@ 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
@@ -952,9 +981,9 @@ 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" ) );
-        customizeJMenuItem( _obtain_uniprot_seq_information_jmi );
-        _obtain_uniprot_seq_information_jmi.setToolTipText( "To add additional sequence information" );
+        _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" ) );
@@ -1208,11 +1237,20 @@ public final class MainFrameApplication extends MainFrame {
         gene_tree.setAllNodesToNotCollapse();
         gene_tree.recalculateNumberOfExternalDescendants( false );
         GSDI gsdi = null;
+        final Phylogeny species_tree = _species_tree.copy();
         try {
-            gsdi = new GSDI( gene_tree, _species_tree.copy(), false, true, true );
+            gsdi = new GSDI( gene_tree, species_tree, false, true, true );
+        }
+        catch ( final SDIException e ) {
+            JOptionPane.showMessageDialog( this,
+                                           e.getLocalizedMessage(),
+                                           "Error during GSDI",
+                                           JOptionPane.ERROR_MESSAGE );
+            return;
         }
         catch ( final Exception e ) {
-            JOptionPane.showMessageDialog( this, e.toString(), "Error during GSDI", JOptionPane.ERROR_MESSAGE );
+            AptxUtil.unexpectedException( e );
+            return;
         }
         gene_tree.setRerootable( false );
         _mainpanel.getCurrentTreePanel().setTree( gene_tree );
@@ -1223,7 +1261,7 @@ public final class MainFrameApplication extends MainFrame {
         getControlPanel().setShowEvents( true );
         showWhole();
         final int selected = _mainpanel.getTabbedPane().getSelectedIndex();
-        _mainpanel.addPhylogenyInNewTab( gsdi.getSpeciesTree(), getConfiguration(), "species tree", null );
+        _mainpanel.addPhylogenyInNewTab( species_tree, getConfiguration(), "species tree", null );
         showWhole();
         _mainpanel.getTabbedPane().setSelectedIndex( selected );
         showWhole();
@@ -1233,6 +1271,54 @@ public final class MainFrameApplication extends MainFrame {
                 + 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;
+        final Phylogeny species_tree = _species_tree.copy();
+        try {
+            gsdir = new GSDIR( gene_tree, species_tree, 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 List<Phylogeny> assigned_trees = gsdir.getMinDuplicationsSumGeneTrees();
+        final List<Integer> shortests = GSDIR.getIndexesOfShortestTree( assigned_trees );
+        final Phylogeny result_gene_tree = assigned_trees.get( shortests.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 );
+        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 (min): " + gsdir.getMinDuplicationsSum() + "\n" + "Speciations: "
+                                               + gsdir.getSpeciationsSum() + "\n"
+                                               + "Number of root positions minimizing duplications sum: "
+                                               + gsdir.getMinDuplicationsSumGeneTrees().size() + "\n"
+                                               + "Number of shortest trees: " + shortests.size(),
+                                       "GSDIR successfully completed",
+                                       JOptionPane.INFORMATION_MESSAGE );
+    }
+
     void executeFunctionAnalysis() {
         if ( ( _mainpanel.getCurrentPhylogeny() == null ) || ( _mainpanel.getCurrentPhylogeny().isEmpty() ) ) {
             return;
@@ -1355,7 +1441,7 @@ public final class MainFrameApplication extends MainFrame {
                     final String name = n.getName().trim();
                     if ( !ForesterUtil.isEmpty( name ) ) {
                         final String code = ParserUtils
-                                .extractTaxonomyCodeFromNodeName( name, PhylogenyMethods.TAXONOMY_EXTRACTION.YES );
+                                .extractTaxonomyCodeFromNodeName( name, NHXParser.TAXONOMY_EXTRACTION.YES );
                         if ( !ForesterUtil.isEmpty( code ) ) {
                             PhylogenyMethods.setTaxonomyCode( n, code );
                         }
@@ -1512,7 +1598,7 @@ public final class MainFrameApplication extends MainFrame {
         }
     }
 
-    private void obtainUniProtSequenceInformation() {
+    private void obtainSequenceInformation() {
         if ( getCurrentTreePanel() != null ) {
             final Phylogeny phy = getCurrentTreePanel().getPhylogeny();
             if ( ( phy != null ) && !phy.isEmpty() ) {
@@ -2254,11 +2340,7 @@ 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() {