inprogress
[jalview.git] / forester / java / src / org / forester / archaeopteryx / MainFrameApplication.java
index f414cd7..c146900 100644 (file)
@@ -66,7 +66,6 @@ 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;
@@ -466,9 +465,6 @@ public final class MainFrameApplication extends MainFrame {
                 }
                 executeLineageInference();
             }
-            else if ( o == _function_analysis ) {
-                executeFunctionAnalysis();
-            }
             else if ( o == _obtain_detailed_taxonomic_information_jmi ) {
                 if ( isSubtreeDisplayed() ) {
                     return;
@@ -541,12 +537,16 @@ public final class MainFrameApplication extends MainFrame {
                 }
                 collapseBelowThreshold();
             }
-            else if ( ( o == _extract_taxonomy_pfam_rbmi ) || ( o == _extract_taxonomy_yes_rbmi ) ) {
+            else if ( ( o == _extract_taxonomy_pfam_strict_rbmi ) || ( o == _extract_taxonomy_pfam_relaxed_rbmi )
+                    || ( o == _extract_taxonomy_agressive_rbmi ) ) {
                 if ( _replace_underscores_cbmi != null ) {
                     _replace_underscores_cbmi.setSelected( false );
                 }
                 updateOptions( getOptions() );
             }
+            else if ( o == _extract_taxonomy_no_rbmi ) {
+                updateOptions( getOptions() );
+            }
             else if ( o == _inference_from_msa_item ) {
                 executePhyleneticInference( false );
             }
@@ -884,34 +884,38 @@ public final class MainFrameApplication extends MainFrame {
         _radio_group_1.add( _ext_node_dependent_cladogram_rbmi );
         _radio_group_1.add( _uniform_cladograms_rbmi );
         _radio_group_1.add( _non_lined_up_cladograms_rbmi );
+        ///////
         _options_jmenu.add( _show_overview_cbmi = new JCheckBoxMenuItem( SHOW_OVERVIEW_LABEL ) );
         _options_jmenu.add( _show_scale_cbmi = new JCheckBoxMenuItem( DISPLAY_SCALE_LABEL ) );
         _options_jmenu
                 .add( _show_branch_length_values_cbmi = new JCheckBoxMenuItem( DISPLAY_BRANCH_LENGTH_VALUES_LABEL ) );
-        _options_jmenu.add( _show_confidence_stddev_cbmi = new JCheckBoxMenuItem( SHOW_CONF_STDDEV_LABEL ) );
         _options_jmenu
                 .add( _show_default_node_shapes_internal_cbmi = new JCheckBoxMenuItem( DISPLAY_NODE_BOXES_LABEL_INT ) );
         _options_jmenu
                 .add( _show_default_node_shapes_external_cbmi = new JCheckBoxMenuItem( DISPLAY_NODE_BOXES_LABEL_EXT ) );
+        if ( getConfiguration().doDisplayOption( Configuration.show_domain_architectures ) ) {
+            _options_jmenu.add( _show_domain_labels = new JCheckBoxMenuItem( SHOW_DOMAIN_LABELS_LABEL ) );
+        }
+        _options_jmenu.add( _show_annotation_ref_source = new JCheckBoxMenuItem( SHOW_ANN_REF_SOURCE_LABEL ) );
+        _options_jmenu.add( _show_confidence_stddev_cbmi = new JCheckBoxMenuItem( SHOW_CONF_STDDEV_LABEL ) );
+        _options_jmenu.add( _color_by_taxonomic_group_cbmi = new JCheckBoxMenuItem( COLOR_BY_TAXONOMIC_GROUP ) );
         _options_jmenu
                 .add( _taxonomy_colorize_node_shapes_cbmi = new JCheckBoxMenuItem( MainFrame.TAXONOMY_COLORIZE_NODE_SHAPES_LABEL ) );
-        _options_jmenu.add( _cycle_node_shape_mi = new JMenuItem( MainFrame.CYCLE_NODE_SHAPE_LABEL ) );
-        _options_jmenu.add( _cycle_node_fill_mi = new JMenuItem( MainFrame.CYCLE_NODE_FILL_LABEL ) );
-        _options_jmenu.add( _choose_node_size_mi = new JMenuItem( MainFrame.CHOOSE_NODE_SIZE_LABEL ) );
-        _options_jmenu.add( _label_direction_cbmi = new JCheckBoxMenuItem( LABEL_DIRECTION_LABEL ) );
-        _label_direction_cbmi.setToolTipText( LABEL_DIRECTION_TIP );
         _options_jmenu.add( _color_labels_same_as_parent_branch = new JCheckBoxMenuItem( COLOR_LABELS_LABEL ) );
         _color_labels_same_as_parent_branch.setToolTipText( MainFrame.COLOR_LABELS_TIP );
         _options_jmenu.add( _abbreviate_scientific_names = new JCheckBoxMenuItem( ABBREV_SN_LABEL ) );
+        _options_jmenu.add( _label_direction_cbmi = new JCheckBoxMenuItem( LABEL_DIRECTION_LABEL ) );
+        _label_direction_cbmi.setToolTipText( LABEL_DIRECTION_TIP );
         _options_jmenu.add( _screen_antialias_cbmi = new JCheckBoxMenuItem( SCREEN_ANTIALIAS_LABEL ) );
         _options_jmenu.add( _background_gradient_cbmi = new JCheckBoxMenuItem( BG_GRAD_LABEL ) );
-        if ( getConfiguration().doDisplayOption( Configuration.show_domain_architectures ) ) {
-            _options_jmenu.add( _show_domain_labels = new JCheckBoxMenuItem( SHOW_DOMAIN_LABELS_LABEL ) );
-        }
+        _options_jmenu.add( _cycle_node_shape_mi = new JMenuItem( MainFrame.CYCLE_NODE_SHAPE_LABEL ) );
+        _options_jmenu.add( _cycle_node_fill_mi = new JMenuItem( MainFrame.CYCLE_NODE_FILL_LABEL ) );
+        _options_jmenu.add( _choose_node_size_mi = new JMenuItem( MainFrame.CHOOSE_NODE_SIZE_LABEL ) );
         _options_jmenu.add( _choose_minimal_confidence_mi = new JMenuItem( "" ) );
         _options_jmenu.add( _overview_placment_mi = new JMenuItem( "" ) );
         _options_jmenu.add( _switch_colors_mi = new JMenuItem( "" ) );
         _options_jmenu.add( _choose_font_mi = new JMenuItem( "" ) );
+        ///////
         _options_jmenu.addSeparator();
         _options_jmenu.add( customizeMenuItemAsLabel( new JMenuItem( SEARCH_SUBHEADER ), getConfiguration() ) );
         _options_jmenu.add( _search_case_senstive_cbmi = new JCheckBoxMenuItem( SEARCH_CASE_SENSITIVE_LABEL ) );
@@ -938,17 +942,22 @@ public final class MainFrameApplication extends MainFrame {
         //
         _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\"" );
+                .add( _extract_taxonomy_pfam_strict_rbmi = new JRadioButtonMenuItem( "Extract Taxonomy Codes/Ids from Pfam-style Node Names" ) );
+        _options_jmenu
+                .add( _extract_taxonomy_pfam_relaxed_rbmi = new JRadioButtonMenuItem( "Extract Taxonomy Codes/Ids from Pfam-style like Node Names" ) );
         _options_jmenu
-                .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...\"" );
+                .add( _extract_taxonomy_agressive_rbmi = new JRadioButtonMenuItem( "Extract Taxonomy Codes/Ids/Scientific Names from Node Names" ) );
+        _extract_taxonomy_pfam_strict_rbmi
+                .setToolTipText( "To extract taxonomy codes/ids from node names in the form of e.g. \"BCL2_MOUSE/123-304\" or \"BCL2_10090/123-304\"" );
+        _extract_taxonomy_pfam_relaxed_rbmi
+                .setToolTipText( "To extract taxonomy codes/ids from node names in the form of e.g. \"bax_MOUSE\" or \"bax_10090\"" );
+        _extract_taxonomy_agressive_rbmi
+                .setToolTipText( "To extract taxonomy codes/ids or scientific names from node names in the form of e.g. \"MOUSE\" or \"10090\" or \"xyz_Nematostella_vectensis\"" );
         _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 );
+        _radio_group_2.add( _extract_taxonomy_pfam_strict_rbmi );
+        _radio_group_2.add( _extract_taxonomy_pfam_relaxed_rbmi );
+        _radio_group_2.add( _extract_taxonomy_agressive_rbmi );
         // 
         _options_jmenu.add( customizeMenuItemAsLabel( new JMenuItem( "Newick/Nexus Output:" ), getConfiguration() ) );
         _options_jmenu
@@ -972,9 +981,11 @@ public final class MainFrameApplication extends MainFrame {
         customizeJMenuItem( _cycle_node_fill_mi );
         customizeJMenuItem( _choose_node_size_mi );
         customizeCheckBoxMenuItem( _color_labels_same_as_parent_branch, getOptions().isColorLabelsSameAsParentBranch() );
+        customizeCheckBoxMenuItem( _color_by_taxonomic_group_cbmi, getOptions().isColorByTaxonomicGroup() );
         customizeCheckBoxMenuItem( _screen_antialias_cbmi, getOptions().isAntialiasScreen() );
         customizeCheckBoxMenuItem( _background_gradient_cbmi, getOptions().isBackgroundColorGradient() );
         customizeCheckBoxMenuItem( _show_domain_labels, getOptions().isShowDomainLabels() );
+        customizeCheckBoxMenuItem( _show_annotation_ref_source, getOptions().isShowAnnotationRefSource() );
         customizeCheckBoxMenuItem( _abbreviate_scientific_names, getOptions().isAbbreviateScientificTaxonNames() );
         customizeCheckBoxMenuItem( _search_case_senstive_cbmi, getOptions().isSearchCaseSensitive() );
         customizeCheckBoxMenuItem( _show_scale_cbmi, getOptions().isShowScale() );
@@ -994,10 +1005,12 @@ public final class MainFrameApplication extends MainFrame {
                 .isInternalNumberAreConfidenceForNhParsing() );
         customizeRadioButtonMenuItem( _extract_taxonomy_no_rbmi,
                                       getOptions().getTaxonomyExtraction() == TAXONOMY_EXTRACTION.NO );
-        customizeRadioButtonMenuItem( _extract_taxonomy_yes_rbmi,
-                                      getOptions().getTaxonomyExtraction() == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED );
-        customizeRadioButtonMenuItem( _extract_taxonomy_pfam_rbmi,
+        customizeRadioButtonMenuItem( _extract_taxonomy_pfam_strict_rbmi,
                                       getOptions().getTaxonomyExtraction() == TAXONOMY_EXTRACTION.PFAM_STYLE_STRICT );
+        customizeRadioButtonMenuItem( _extract_taxonomy_pfam_relaxed_rbmi,
+                                      getOptions().getTaxonomyExtraction() == TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED );
+        customizeRadioButtonMenuItem( _extract_taxonomy_agressive_rbmi,
+                                      getOptions().getTaxonomyExtraction() == TAXONOMY_EXTRACTION.AGGRESSIVE );
         customizeCheckBoxMenuItem( _replace_underscores_cbmi, getOptions().isReplaceUnderscoresInNhParsing() );
         customizeCheckBoxMenuItem( _search_whole_words_only_cbmi, getOptions().isMatchWholeTermsOnly() );
         customizeCheckBoxMenuItem( _inverse_search_result_cbmi, getOptions().isInverseSearchResult() );
@@ -1074,6 +1087,9 @@ public final class MainFrameApplication extends MainFrame {
         customizeJMenuItem( _move_node_names_to_seq_names_jmi );
         _move_node_names_to_seq_names_jmi.setToolTipText( "To interpret node names as sequence (protein, gene) names" );
         _tools_menu.addSeparator();
+        _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
                 .add( _obtain_detailed_taxonomic_information_jmi = new JMenuItem( OBTAIN_DETAILED_TAXONOMIC_INFORMATION ) );
         customizeJMenuItem( _obtain_detailed_taxonomic_information_jmi );
@@ -1084,17 +1100,7 @@ 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_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" ) );
-            customizeJMenuItem( _function_analysis );
-            _function_analysis
-                    .setToolTipText( "To add UniProtKB annotations for sequences with appropriate identifiers" );
-            _tools_menu.addSeparator();
-        }
         _tools_menu.add( _read_values_jmi = new JMenuItem( "Attach Vector/Expression Values" ) );
         customizeJMenuItem( _read_values_jmi );
         _read_values_jmi.setToolTipText( "To attach vector (e.g. gene expression) values to tree nodes (beta)" );
@@ -1120,16 +1126,6 @@ public final class MainFrameApplication extends MainFrame {
         exit();
     }
 
-    void executeFunctionAnalysis() {
-        if ( ( _mainpanel.getCurrentPhylogeny() == null ) || ( _mainpanel.getCurrentPhylogeny().isEmpty() ) ) {
-            return;
-        }
-        final GoAnnotation a = new GoAnnotation( this,
-                                                 _mainpanel.getCurrentTreePanel(),
-                                                 _mainpanel.getCurrentPhylogeny() );
-        new Thread( a ).start();
-    }
-
     void executeLineageInference() {
         if ( ( _mainpanel.getCurrentPhylogeny() == null ) || ( _mainpanel.getCurrentPhylogeny().isEmpty() ) ) {
             return;
@@ -1308,12 +1304,12 @@ public final class MainFrameApplication extends MainFrame {
         if ( ( file != null ) && ( file.length() > 0 ) && ( result == JFileChooser.APPROVE_OPTION ) ) {
             BasicTable<String> t = null;
             try {
-                t = BasicTableParser.parse( file, "\t" );
+                t = BasicTableParser.parse( file, '\t' );
                 if ( t.getNumberOfColumns() < 2 ) {
-                    t = BasicTableParser.parse( file, "," );
+                    t = BasicTableParser.parse( file, ',' );
                 }
                 if ( t.getNumberOfColumns() < 2 ) {
-                    t = BasicTableParser.parse( file, " " );
+                    t = BasicTableParser.parse( file, ' ' );
                 }
             }
             catch ( final IOException e ) {
@@ -1481,6 +1477,9 @@ public final class MainFrameApplication extends MainFrame {
                         nodes = phy.getNodesViaSequenceSymbol( seq_name );
                     }
                     if ( nodes.isEmpty() ) {
+                        nodes = phy.getNodesViaGeneName( seq_name );
+                    }
+                    if ( nodes.isEmpty() ) {
                         nodes = phy.getNodes( seq_name );
                     }
                     if ( nodes.size() > 1 ) {
@@ -1764,7 +1763,7 @@ public final class MainFrameApplication extends MainFrame {
             }
         }
         if ( xml_parser == null ) {
-            xml_parser = new PhyloXmlParser();
+            xml_parser = PhyloXmlParser.createPhyloXmlParser();
         }
         return xml_parser;
     }
@@ -1819,8 +1818,8 @@ public final class MainFrameApplication extends MainFrame {
                     final PhylogenyNode n = it.next();
                     final String name = n.getName().trim();
                     if ( !ForesterUtil.isEmpty( name ) ) {
-                        final String nt = ParserUtils
-                                .extractTaxonomyDataFromNodeName( n, TAXONOMY_EXTRACTION.PFAM_STYLE_RELAXED );
+                        final String nt = ParserUtils.extractTaxonomyDataFromNodeName( n,
+                                                                                       TAXONOMY_EXTRACTION.AGGRESSIVE );
                         if ( !ForesterUtil.isEmpty( nt ) ) {
                             if ( counter < 15 ) {
                                 sb.append( name + ": " + nt + "\n" );
@@ -1875,7 +1874,7 @@ public final class MainFrameApplication extends MainFrame {
 
     private File getCurrentDir() {
         if ( ( _current_dir == null ) || !_current_dir.canRead() ) {
-            if ( ForesterUtil.isWindowns() ) {
+            if ( ForesterUtil.isWindows() ) {
                 try {
                     _current_dir = new File( WindowsUtils.getCurrentUserDesktopPath() );
                 }
@@ -2230,7 +2229,8 @@ public final class MainFrameApplication extends MainFrame {
         if ( ( file != null ) && ( result == JFileChooser.APPROVE_OPTION ) ) {
             if ( _open_filechooser_for_species_tree.getFileFilter() == MainFrameApplication.xmlfilter ) {
                 try {
-                    final Phylogeny[] trees = PhylogenyMethods.readPhylogenies( new PhyloXmlParser(), file );
+                    final Phylogeny[] trees = PhylogenyMethods.readPhylogenies( PhyloXmlParser
+                            .createPhyloXmlParserXsdValidating(), file );
                     t = trees[ 0 ];
                 }
                 catch ( final Exception e ) {
@@ -2251,7 +2251,8 @@ public final class MainFrameApplication extends MainFrame {
             // "*.*":
             else {
                 try {
-                    final Phylogeny[] trees = PhylogenyMethods.readPhylogenies( new PhyloXmlParser(), file );
+                    final Phylogeny[] trees = PhylogenyMethods.readPhylogenies( PhyloXmlParser
+                            .createPhyloXmlParserXsdValidating(), file );
                     t = trees[ 0 ];
                 }
                 catch ( final Exception e ) {