@datagrok/bio 2.10.26 → 2.10.28

package/files/tests/sepComplex.csv

@@ -0,0 +1,4 @@
+seq
+Ac(1)-F-K(AEEA-AEEA-R-Ac)-L-mF-V-Y-mNle-D-W-N-mF-C(1)-G-NH2
+Ac(1)-F-K(AEEA-ARRA-W-Ac)-L-mF-V-Y-mNle-D-W-N-mF-C(1)-G-NH2
+Ac(1)-F-K(AEEA-AEEA-Ac)-L-mF-V-Y-mNle-D-W-N-mF-C(1)-G-NH2

package/package.json

@@ -5,7 +5,7 @@
     "name": "Leonid Stolbov",
     "email": "lstolbov@datagrok.ai"
   },
-  "version": "2.10.26",
+  "version": "2.10.28",
   "description": "Bioinformatics support (import/export of sequences, conversion, visualization, analysis). [See more](https://github.com/datagrok-ai/public/blob/master/packages/Bio/README.md) for details.",
   "repository": {
     "type": "git",
@@ -36,7 +36,7 @@
     "@biowasm/aioli": "^3.1.0",
     "@datagrok-libraries/bio": "^5.38.13",
     "@datagrok-libraries/chem-meta": "^1.0.1",
-    "@datagrok-libraries/ml": "^6.3.49",
+    "@datagrok-libraries/ml": "^6.3.50",
     "@datagrok-libraries/tutorials": "^1.3.6",
     "@datagrok-libraries/utils": "^4.0.17",
     "cash-dom": "^8.0.0",
@@ -55,6 +55,7 @@
     "@types/wu": "latest",
     "@typescript-eslint/eslint-plugin": "latest",
     "@typescript-eslint/parser": "latest",
+    "datagrok-tools": "latest",
     "eslint": "latest",
     "eslint-config-google": "latest",
     "source-map-loader": "^4.0.1",
@@ -100,5 +101,36 @@
   "sources": [
     "css/helm.css"
   ],
-  "category": "Bioinformatics"
+  "category": "Bioinformatics",
+  "meta": {
+    "menu": {
+      "Bio": {
+        "Analyze": {
+          "SAR...": null,
+          "Sequence Space...": null,
+          "Hierarchical Clustering...": null,
+          "Activity Cliffs...": null,
+          "Sequence Space": null,
+          "MSA...": null,
+          "Composition": null
+        },
+        "Search": {
+          "Diversity Search": null,
+          "Similarity Search": null,
+          "Subsequence Search...": null
+        },
+        "Calculate": {
+          "Identity...": null,
+          "Similarity...": null
+        },
+        "Convert": {
+          "Split to Monomerts...": null,
+          "Get Region...": null,
+          "Notation...": null,
+          "SDF to JSON Library...": null,
+          "To Atomic Level...": null
+        }
+      }
+    }
+  }
 }

package/src/package.ts

@@ -74,6 +74,7 @@ import {DIMENSIONALITY_REDUCER_TERMINATE_EVENT}
   from '@datagrok-libraries/ml/src/workers/dimensionality-reducing-worker-creator';
 import {Options} from '@datagrok-libraries/utils/src/type-declarations';
 import {sequenceToMolfile} from './utils/sequence-to-mol';
+import {SHOW_SCATTERPLOT_PROGRESS} from '@datagrok-libraries/ml/src/functionEditors/seq-space-base-editor';
 
 export const _package = new BioPackage();
 
@@ -465,8 +466,9 @@ export async function activityCliffs(df: DG.DataFrame, macroMolecule: DG.Column<
 //input: string methodName { choices:["UMAP", "t-SNE"] }
 //input: string similarityMetric { choices:["Hamming", "Levenshtein", "Monomer chemical distance"] }
 //input: bool plotEmbeddings = true
-//input: double sparseMatrixThreshold = 0.8 [Similarity Threshold for sparse matrix calculation]
+//input: double sparseMatrixThreshold = 0 [Similarity Threshold for sparse matrix calculation]
 //input: object options {optional: true}
+//output: viewer result
 //editor: Bio:SequenceSpaceEditor
 export async function sequenceSpaceTopMenu(
   table: DG.DataFrame, macroMolecule: DG.Column, methodName: DimReductionMethods,
@@ -497,8 +499,11 @@ export async function sequenceSpaceTopMenu(
         embedYCol = table.columns.byName(embedColsNames[1]);
       }
 
-      embedXCol.init((i) => embeddings[i] ? embeddings[i][0] : undefined);
-      embedYCol.init((i) => embeddings[i] ? embeddings[i][1] : undefined);
+      if (options?.[SHOW_SCATTERPLOT_PROGRESS]) {
+        scatterPlot?.root && ui.setUpdateIndicator(scatterPlot!.root, false);
+        embedXCol.init((i) => embeddings[i] ? embeddings[i][0] : undefined);
+        embedYCol.init((i) => embeddings[i] ? embeddings[i][1] : undefined);
+      }
       const progress = (_nEpoch / epochsLength * 100);
       pg.update(progress, `Running sequence space ... ${progress.toFixed(0)}%`);
     }
@@ -524,6 +529,14 @@ export async function sequenceSpaceTopMenu(
     }
 
     async function getSeqSpace() {
+      table.columns.add(DG.Column.float(embedColsNames[0], table.rowCount));
+      table.columns.add(DG.Column.float(embedColsNames[1], table.rowCount));
+      if (plotEmbeddings) {
+        scatterPlot = grok.shell
+          .tableView(table.name)
+          .scatterPlot({x: embedColsNames[0], y: embedColsNames[1], title: 'Sequence space'});
+        ui.setUpdateIndicator(scatterPlot.root, true);
+      }
       let resolveF: Function | null = null;
 
       const sub = grok.events.onViewerClosed.subscribe((args) => {
@@ -579,6 +592,7 @@ export async function sequenceSpaceTopMenu(
             .tableView(table.name)
             .scatterPlot({x: embedColsNames[0], y: embedColsNames[1], title: 'Sequence space'});
         }
+        ui.setUpdateIndicator(scatterPlot.root, false);
         return scatterPlot;
       }
     }

package/src/tests/WebLogo-positions-test.ts

@@ -32,7 +32,7 @@ ATC-G-TTGC--
     const wlViewer: WebLogoViewer = (await df.plot.fromType('WebLogo')) as WebLogoViewer;
     await testEvent(wlViewer.onLayoutCalculated, () => {}, () => {
       tv.dockManager.dock(wlViewer.root, DG.DOCK_TYPE.DOWN);
-    }, 300);
+    }, 500);
     const positions: PI[] = wlViewer['positions'];
 
     const resAllDf1: PI[] = [
@@ -122,7 +122,7 @@ ATC-G-TTGC--
       {'skipEmptyPositions': true})) as WebLogoViewer;
     await testEvent(wlViewer.onLayoutCalculated, () => {}, () => {
       tv.dockManager.dock(wlViewer.root, DG.DOCK_TYPE.DOWN);
-    }, 300);
+    }, 500);
     const resPosList: PI[] = wlViewer['positions'];
 
     const tgtPosList: PI[] = [
@@ -158,7 +158,7 @@ ATC-G-TTGC--
     })) as WebLogoViewer;
     await testEvent(wlViewer.onLayoutCalculated, () => {}, () => {
       tv.dockManager.dock(wlViewer.root, DG.DOCK_TYPE.DOWN);
-    }, 300);
+    }, 500);
     const resPosList: PI[] = wlViewer['positions'];
     const tgtPosList: PI[] = [
       new PI(2, '3', {'C': new PMI(5)}),
@@ -194,7 +194,7 @@ ATC-G-TTGC--
     const wlViewer: WebLogoViewer = (await df.plot.fromType('WebLogo')) as WebLogoViewer;
     await testEvent(wlViewer.onLayoutCalculated, () => {}, () => {
       tv.dockManager.dock(wlViewer.root, DG.DOCK_TYPE.DOWN);
-    }, 300);
+    }, 500);
     const resPosList: PI[] = wlViewer['positions'];
   });
 });

package/src/tests/detectors-benchmark-tests.ts

@@ -25,7 +25,7 @@ category('detectorsBenchmark', () => {
   });
 
   test('fastaDnaShorts50Many1E6', async () => {
-    await detectMacromoleculeBenchmark(10, NOTATION.FASTA, ALPHABET.DNA, 50, 1E6);
+    await detectMacromoleculeBenchmark(20, NOTATION.FASTA, ALPHABET.DNA, 50, 1E6);
   });
 
   test('fastaDnaLong1e6Few50', async () => {

package/src/tests/detectors-tests.ts

@@ -39,6 +39,7 @@ category('detectors', () => {
     sepUn2 = 'sepUn2',
     sepMsaDna1 = 'sepMsaDna1',
     sepMsaUnWEmpty = 'sepMsaUnWEmpty',
+    sepComplex = 'sepComplex',
     fastaMsaDna1 = 'fastaMsaDna1',
     fastaMsaPt1 = 'fastaMsaPt1',
   }
@@ -115,6 +116,10 @@ m1-M-m3-mon4-mon5-N-T-MON8-N9
 m1-mon2-m3-mon4-mon5-Num--MON8-N9
 
 mon1-M-mon3-mon4-mon5---MON8-N9`;
+    [csvTests.sepComplex]: string = `seq
+Ac(1)-F-K(AEEA-AEEA-R-Ac)-L-mF-V-Y-mNle-D-W-N-mF-C(1)-G-NH2
+Ac(1)-F-K(AEEA-ARRA-W-Ac)-L-mF-V-Y-mNle-D-W-N-mF-C(1)-G-NH2
+Ac(1)-F-K(AEEA-AEEA-Ac)-L-mF-V-Y-mNle-D-W-N-mF-C(1)-G-NH2`;
     [csvTests.fastaMsaDna1]: string = `seq
 AC-GT-CT
 CAC-T-GT
@@ -244,10 +249,6 @@ MWRSWY-CKHP`;
       NOTATION.FASTA, ALIGNMENT.SEQ_MSA, ALPHABET.UN, 12, true);
   });
 
-  test('SepMsaUnWEmpty', async () => {
-    await _testPos(readCsv(csvTests.sepMsaUnWEmpty), 'seq',
-      NOTATION.SEPARATOR, ALIGNMENT.SEQ_MSA, ALPHABET.UN, 14, true);
-  });
   test('FastaMsaDna1', async () => {
     await _testPos(readCsv(csvTests.fastaMsaDna1), 'seq',
       NOTATION.FASTA, ALIGNMENT.SEQ_MSA, ALPHABET.DNA, 4, false);
@@ -284,6 +285,16 @@ MWRSWY-CKHP`;
       NOTATION.SEPARATOR, ALIGNMENT.SEQ_MSA, ALPHABET.DNA, 4, false, '-');
   });
 
+  test('SepMsaUnWEmpty', async () => {
+    await _testPos(readCsv(csvTests.sepMsaUnWEmpty), 'seq',
+      NOTATION.SEPARATOR, ALIGNMENT.SEQ_MSA, ALPHABET.UN, 14, true);
+  });
+
+  test('SepComplex', async () => {
+    await _testPos(readCsv(csvTests.sepComplex), 'seq',
+      NOTATION.SEPARATOR, ALIGNMENT.SEQ, ALPHABET.UN, 18, true);
+  });
+
   test('samplesFastaCsv', async () => {
     await _testDf(readSamples(Samples.fastaCsv), {
       'Sequence': new PosCol(NOTATION.FASTA, ALIGNMENT.SEQ, ALPHABET.PT, 20, false),

package/tsconfig.json

@@ -61,8 +61,8 @@
     // "inlineSources": true,                       /* Emit the source alongside the sourcemaps within a single file; requires '--inlineSourceMap' or '--sourceMap' to be set. */
 
     /* Experimental Options */
-    // "experimentalDecorators": true,              /* Enables experimental support for ES7 decorators. */
-    // "emitDecoratorMetadata": true,               /* Enables experimental support for emitting type metadata for decorators. */
+    "experimentalDecorators": true,                 /* Enables experimental support for ES7 decorators. */
+    "emitDecoratorMetadata": true,                  /* Enables experimental support for emitting type metadata for decorators. */
 
     /* Advanced Options */
     "skipLibCheck": false,                          /* Skip type checking of declaration files. */

package/webpack.config.js

@@ -1,4 +1,5 @@
 const path = require('path');
+const FuncGeneratorPlugin = require('datagrok-tools/plugins/func-gen-plugin');
 const packageName = path.parse(require('./package.json').name).name.toLowerCase().replace(/-/g, '');
 
 module.exports = {
@@ -22,6 +23,9 @@ module.exports = {
       {test: /\.css$/, use: ['style-loader', 'css-loader']},
     ],
   },
+  plugins: [
+    new FuncGeneratorPlugin({outputPath: './src/package.g.ts'}),
+  ],
   devtool: 'source-map',
   externals: {
     'datagrok-api/dg': 'DG',