Merge branch 'develop'

package.json

@@ -1,6 +1,6 @@
 {
   "name": "genoverse",
-  "version": "4.0.7",
+  "version": "4.0.8",
   "description": "Genoverse is a portable, customizable, back-end independent JavaScript and HTML5 based genome browser which allows the user to explore data in a dynamic and interactive manner.",
   "main": "src/js/Genoverse.js",
   "directories": {

src/js/Track/View/Gene/Ensembl.js

@@ -1,46 +1,64 @@
 import View from '../Gene';
 
+/**
+  * Provides a function setFeatureColor for defining the feature colour and legend label
+  * for ensembl genes and transcripts based on their logic_name and biotype properties.
+  *
+  * Biotypes are defined in
+  *   https://www.ensembl.org/info/genome/genebuild/biotypes.html
+  *
+  * Ensembl colours are defined in
+  *   https://github.com/Ensembl/ensembl-webcode/blob/main/conf/ini-files/COLOUR.ini
+  */
+
 export default View.extend({
   setFeatureColor: function (feature) {
     const processedTranscript = {
-      'sense_intronic'           : 1,
-      'sense_overlapping'        : 1,
-      'processed_transcript'     : 1,
-      'nonsense_mediated_decay'  : 1,
-      'non_stop_decay'           : 1,
-      'antisense'                : 1,
-      'retained_intron'          : 1,
-      'tec'                      : 1,
-      'non_coding'               : 1,
-      'ambiguous_orf'            : 1,
-      'disrupted_domain'         : 1,
-      '3prime_overlapping_ncrna' : 1,
+      'sense_intronic'                 : 1,
+      'sense_overlapping'              : 1,
+      'processed_transcript'           : 1,
+      'nonsense_mediated_decay'        : 1,
+      'non_stop_decay'                 : 1,
+      'antisense'                      : 1,
+      'retained_intron'                : 1,
+      'tec'                            : 1,
+      'non_coding'                     : 1,
+      'ambiguous_orf'                  : 1,
+      'disrupted_domain'               : 1,
+      '3prime_overlapping_ncrna'       : 1,
+      'protein_coding_CDS_not_defined' : 1, // new in e108
     };
 
     feature.color = '#000000';
 
-    if (feature.logic_name.indexOf('ensembl_havana') === 0) {
+    const logicName = feature.logic_name || '';
+    const biotype   = (feature.biotype || '').toLowerCase();
+
+    if (logicName.indexOf('ensembl_havana') === 0) {
       feature.color      = '#CD9B1D';
       feature.labelColor = '#B78000';
       feature.legend     = 'Merged Ensembl/Havana';
-    } else if (processedTranscript[feature.biotype.toLowerCase()]) {
+    } else if (processedTranscript[biotype]) {
       feature.color  = '#0000FF';
       feature.legend = 'Processed transcript';
-    } else if (feature.biotype === 'protein_coding') {
+    } else if (feature.biotype.indexOf('protein_coding') > -1) {
       feature.color  = '#A00000';
       feature.legend = 'Protein coding';
-    } else if (feature.biotype.indexOf('pseudogene') > -1) {
+    } else if (feature.biotype === 'artifact' || biotype.indexOf('pseudogene') > -1) {
       feature.color  = '#666666';
       feature.legend = 'Pseudogene';
-    } else if (/rna/i.test(feature.biotype) || feature.biotype === 'ribozyme') {
+    } else if (/rna/.test(biotype) || biotype === 'ribozyme') {
       feature.color  = '#8B668B';
       feature.legend = 'RNA gene';
-    } else if (/^tr_.+_gene$/i.test(feature.biotype)) {
+    } else if (/^tr(?:_.+)?_gene$/.test(biotype)) {
       feature.color  = '#CD6600';
       feature.legend = 'TR gene';
-    } else if (/^ig_.+_gene$/i.test(feature.biotype)) {
+    } else if (/^ig_.+_gene$/.test(biotype)) {
       feature.color  = '#8B4500';
       feature.legend = 'IG gene';
+    } else if (biotype === 'lrg_gene') {
+      feature.color  = '#8080FF';
+      feature.legend = 'LRG gene';
     }
 
     feature.labelColor = feature.labelColor || feature.color;

test/View/calculate-biotype-legend.test.js

@@ -0,0 +1,28 @@
+const { $, Genoverse, afterTest } = require('../utils');
+
+describe('All ensembl biotypes should be categorised by setFeatureColor:', () => {
+  afterEach(afterTest);
+
+  // select * from (select distinct(biotype) from transcript union select distinct(biotype) from gene) biotypes order by biotype;
+  const ensemblBiotypes = [ 'artifact', 'IG_C_gene', 'IG_C_pseudogene', 'IG_D_gene', 'IG_J_gene', 'IG_J_pseudogene', 'IG_pseudogene', 'IG_V_gene', 'IG_V_pseudogene', 'lncRNA', 'LRG_gene', 'miRNA', 'misc_RNA', 'Mt_rRNA', 'Mt_tRNA', 'nonsense_mediated_decay', 'non_stop_decay', 'processed_pseudogene', 'processed_transcript', 'protein_coding', 'protein_coding_LoF', 'pseudogene', 'retained_intron', 'ribozyme', 'rRNA', 'rRNA_pseudogene', 'scaRNA', 'scRNA', 'snoRNA', 'snRNA', 'sRNA', 'TEC', 'transcribed_processed_pseudogene', 'transcribed_unitary_pseudogene', 'transcribed_unprocessed_pseudogene', 'translated_processed_pseudogene', 'translated_unprocessed_pseudogene', 'TR_C_gene', 'TR_D_gene', 'TR_J_gene', 'TR_J_pseudogene', 'TR_V_gene', 'TR_V_pseudogene', 'unitary_pseudogene', 'unprocessed_pseudogene', 'vault_RNA' ];
+
+  ensemblBiotypes.forEach(
+    biotype => it(
+      `${biotype} should be categorised by setFeatureColor`, () => {
+        const feature = { logic_name: '', biotype: biotype };
+
+        const [ track ] = new Genoverse({
+          chr            : 1,
+          start          : 1,
+          end            : 100,
+          chromosomeSize : 100,
+          tracks         : [ Genoverse.Track.Gene.extend($.extend(true, {}, { data: [ feature ] })) ],
+        }).tracks;
+
+        track.view.setFeatureColor(feature);
+
+        expect(feature.legend).toBeDefined();
+      }
+    )
+  );
+});