@datagrok/bio 2.12.18 → 2.12.19

package/package.json

@@ -5,7 +5,7 @@
     "name": "Aleksandr Tanas",
     "email": "atanas@datagrok.ai"
   },
-  "version": "2.12.18",
+  "version": "2.12.19",
   "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",
@@ -34,7 +34,7 @@
   ],
   "dependencies": {
     "@biowasm/aioli": "^3.1.0",
-    "@datagrok-libraries/bio": "^5.41.2",
+    "@datagrok-libraries/bio": "^5.41.5",
     "@datagrok-libraries/chem-meta": "^1.2.5",
     "@datagrok-libraries/math": "^1.1.5",
     "@datagrok-libraries/ml": "^6.6.5",
@@ -57,7 +57,7 @@
   "devDependencies": {
     "@datagrok/chem": "^1.9.2",
     "@datagrok/dendrogram": "^1.2.29",
-    "@datagrok/helm": "^2.1.34",
+    "@datagrok/helm": "^2.2.1",
     "@types/node": "^17.0.24",
     "@types/wu": "latest",
     "@typescript-eslint/eslint-plugin": "latest",

package/src/package-test.ts

@@ -23,7 +23,7 @@ import './tests/WebLogo-project-tests';
 import './tests/WebLogo-layout-tests';
 import './tests/checkInputColumn-tests';
 import './tests/similarity-diversity-tests';
-// import './tests/substructure-filters-tests';
+import './tests/substructure-filters-tests';
 import './tests/pepsea-tests';
 import './tests/viewers';
 import './tests/seq-handler-tests';

package/src/package.ts

@@ -11,9 +11,7 @@ import {DimReductionBaseEditor, PreprocessFunctionReturnType}
 import {getActivityCliffs} from '@datagrok-libraries/ml/src/viewers/activity-cliffs';
 import {MmDistanceFunctionsNames} from '@datagrok-libraries/ml/src/macromolecule-distance-functions';
 import {BitArrayMetrics, KnownMetrics} from '@datagrok-libraries/ml/src/typed-metrics';
-import {
-  TAGS as bioTAGS,
-} from '@datagrok-libraries/bio/src/utils/macromolecule';
+import {NOTATION, TAGS as bioTAGS} from '@datagrok-libraries/bio/src/utils/macromolecule';
 import {SeqHandler, SeqTemps} from '@datagrok-libraries/bio/src/utils/seq-handler';
 import {IMonomerLib} from '@datagrok-libraries/bio/src/types';
 import {SeqPalette} from '@datagrok-libraries/bio/src/seq-palettes';
@@ -51,7 +49,7 @@ import {demoBio01bUI} from './demo/bio01b-hierarchical-clustering-and-activity-c
 import {demoBio03UI} from './demo/bio03-atomic-level';
 import {demoBio05UI} from './demo/bio05-helm-msa-sequence-space';
 import {checkInputColumnUI} from './utils/check-input-column';
-import {multipleSequenceAlignmentUI} from './utils/multiple-sequence-alignment-ui';
+import {MsaWarning, multipleSequenceAlignmentUI} from './utils/multiple-sequence-alignment-ui';
 import {WebLogoApp} from './apps/web-logo-app';
 import {SplitToMonomersFunctionEditor} from './function-edtiors/split-to-monomers-editor';
 import {splitToMonomersUI} from './utils/split-to-monomers';
@@ -75,6 +73,8 @@ import {DimReductionMethods} from '@datagrok-libraries/ml/src/multi-column-dimen
 import {
   ITSNEOptions, IUMAPOptions
 } from '@datagrok-libraries/ml/src/multi-column-dimensionality-reduction/multi-column-dim-reducer';
+import {generateLongSequence, generateLongSequence2} from '@datagrok-libraries/bio/src/utils/generator';
+
 import {CyclizedNotationProvider} from './utils/cyclized';
 import {getMolColumnFromHelm} from './utils/helm-to-molfile/utils';
 
@@ -598,7 +598,15 @@ export async function toAtomicLevel(table: DG.DataFrame, seqCol: DG.Column, nonl
 //description: Performs multiple sequence alignment
 //tags: bio, panel
 export function multipleSequenceAlignmentDialog(): void {
-  multipleSequenceAlignmentUI();
+  multipleSequenceAlignmentUI()
+    .catch((err: any) => {
+      const [errMsg, _errStack] = errInfo(err);
+      if (err instanceof MsaWarning) {
+        _package.logger.warning(errMsg);
+        return;
+      }
+      throw err;
+    });
 }
 
 //name: Multiple Sequence Alignment
@@ -946,6 +954,26 @@ export async function getRegionHelmApp(): Promise<void> {
   }
 }
 
+// -- Tests long seq --
+
+//name: longSeqTableSeparator
+export function longSeqTableSeparator(): void {
+  const df = DG.DataFrame.fromColumns(generateLongSequence());
+  grok.shell.addTableView(df);
+}
+
+//name: longSeqTableFasta
+export function longSeqTableFasta(): void {
+  const df = DG.DataFrame.fromColumns([generateLongSequence2(NOTATION.FASTA)]);
+  grok.shell.addTableView(df);
+}
+
+//name: longSeqTableHelm
+export function longSeqTableHelm(): void {
+  const df = DG.DataFrame.fromColumns([generateLongSequence2(NOTATION.HELM)]);
+  grok.shell.addTableView(df);
+}
+
 // -- Handle context menu --
 
 ///name: addCopyMenu

package/src/tests/renderers-monomer-placer-tests.ts

@@ -4,15 +4,36 @@ import * as ui from 'datagrok-api/ui';
 
 import wu from 'wu';
 
-import {category, test} from '@datagrok-libraries/utils/src/test';
-import {MonomerPlacer} from '@datagrok-libraries/bio/src/utils/cell-renderer-monomer-placer';
+import {after, before, category, expect, test} from '@datagrok-libraries/utils/src/test';
+import {MonomerPlacer, hitBounds} from '@datagrok-libraries/bio/src/utils/cell-renderer-monomer-placer';
 import {monomerToShort} from '@datagrok-libraries/bio/src/utils/macromolecule';
 import {SeqHandler} from '@datagrok-libraries/bio/src/utils/seq-handler';
-import {getMonomerLibHelper} from '@datagrok-libraries/bio/src/monomer-works/monomer-utils';
+import {getMonomerLibHelper, IMonomerLibHelper} from '@datagrok-libraries/bio/src/monomer-works/monomer-utils';
+import {
+  getUserLibSettings, setUserLibSettings, setUserLibSettingsForTests
+} from '@datagrok-libraries/bio/src/monomer-works/lib-settings';
+import {UserLibSettings} from '@datagrok-libraries/bio/src/monomer-works/types';
 
 import {_package} from '../package-test';
 
 category('renderers: monomerPlacer', () => {
+  let libHelper: IMonomerLibHelper;
+  let libSettings: UserLibSettings;
+
+  before(async () => {
+    libHelper = await getMonomerLibHelper();
+    libSettings = await getUserLibSettings();
+
+    await setUserLibSettingsForTests();
+    await libHelper.awaitLoaded();
+    await libHelper.loadLibraries(true);
+  });
+
+  after(async () => {
+    await setUserLibSettings(libSettings);
+    await libHelper.loadLibraries(true);
+  });
+
   const tests = {
     splitter: {
       /**
@@ -53,10 +74,10 @@ category('renderers: monomerPlacer', () => {
         {src: {row: 1, x: 5}, tgt: {pos: 0}},
         {src: {row: 1, x: 37}, tgt: {pos: 0}},
         {src: {row: 1, x: 38}, tgt: {pos: 1}},
-        {src: {row: 1, x: 170}, tgt: {pos: 4}},
+        {src: {row: 1, x: 170}, tgt: {pos: 5}},
         {src: {row: 1, x: 200}, tgt: {pos: 5}},
         {src: {row: 2, x: 20}, tgt: {pos: null}}, // empty value
-        {src: {row: 3, x: 170}, tgt: {pos: 4}},
+        {src: {row: 3, x: 170}, tgt: {pos: 5}},
         {src: {row: 3, x: 200}, tgt: {pos: 5}},
         {src: {row: 3, x: 297}, tgt: {pos: null}},
       ]
@@ -122,7 +143,32 @@ id3,QHIRE--LT
         }
       }
       if (errorList.length > 0)
-        throw new Error('Test failed error(s):\n' + errorList.join(', n'));
+        throw new Error('Test failed error(s):\n' + errorList.join(', \n'));
+    });
+  }
+});
+
+category('renderers: monomerPlacer', () => {
+  const boundsTestData = {
+    bounds: [10, 20, 30, 40, 50, 60],
+    tests: {
+      left: {x: 3, tgt: null},
+      c0left: {x: 10, tgt: 0},
+      c0mid: {x: 12, tgt: 0},
+      c0right: {x: 19, tgt: 0},
+      c1left: {x: 20, tgt: 1},
+      c2right: {x: 39, tgt: 2},
+      c4left: {x: 50, tgt: 4},
+      c4right: {x: 59, tgt: 4},
+      max: {x: 60, tgt: null},
+      right: {x: 65, tgt: null},
+    }
+  };
+
+  for (const [testName, testData] of Object.entries(boundsTestData.tests)) {
+    test('hitBounds-' + testName, async () => {
+      const res = hitBounds(boundsTestData.bounds, testData.x);
+      expect(res, testData.tgt);
     });
   }
 });

package/src/tests/renderers-test.ts

@@ -8,10 +8,11 @@ import {fromEvent} from 'rxjs';
 import {category, expect, test, delay, testEvent} from '@datagrok-libraries/utils/src/test';
 import {ALIGNMENT, ALPHABET, NOTATION, TAGS as bioTAGS} from '@datagrok-libraries/bio/src/utils/macromolecule';
 import {SeqHandler} from '@datagrok-libraries/bio/src/utils/seq-handler';
+import {generateLongSequence, generateManySequences} from '@datagrok-libraries/bio/src/utils/generator';
 
 import {importFasta} from '../package';
 import {convertDo} from '../utils/convert';
-import {generateLongSequence, generateManySequences, performanceTest} from './utils/sequences-generators';
+import {performanceTest} from './utils/sequences-generators';
 import {multipleSequenceAlignmentUI} from '../utils/multiple-sequence-alignment-ui';
 import {awaitGrid} from './utils';
 import * as C from '../utils/constants';
@@ -23,9 +24,6 @@ category('renderers', () => {
     await performanceTest(generateLongSequence, 'Long sequences');
   });
 
-  test('many sequence performance', async () => {
-    await performanceTest(generateManySequences, 'Many sequences');
-  });
   test('many sequence performance', async () => {
     await performanceTest(generateManySequences, 'Many sequences');
   });

package/src/tests/substructure-filters-tests.ts

@@ -186,7 +186,7 @@ category('bio-substructure-filters', async () => {
     }
     await filter.awaitRendered();
     await delay(3000); //TODO: await for grid.onLookChanged
-  }, {skipReason: 'GROK-15678'});
+  });
 
   // Generates unhandled exception accessing isFiltering before bioFilter created
   test('helm-view', async () => {
@@ -310,7 +310,7 @@ category('bio-substructure-filters', async () => {
     await Promise.all([f1.awaitRendered(), f2.awaitRendered()]);
     await awaitGrid(view.grid);
     await delay(3000); //TODO: await for grid.onLookChanged
-  }, {skipReason: 'GROK-15678'});
+  });
 
   // two seq columns
 

package/src/tests/utils/sequences-generators.ts

@@ -7,26 +7,6 @@ import {expect} from '@datagrok-libraries/utils/src/test';
 
 import {awaitGrid} from '../utils';
 
-
-export function generateManySequences(): DG.Column[] {
-  const columns: DG.Column[] = [];
-  columns.push(DG.Column.fromList('string', 'MSA',
-    new Array(10 ** 6).fill(
-      'meI/hHis/Aca/N/T/dE/Thr_PO3H2/Aca/D-Tyr_Et/Tyr_ab-dehydroMe/dV/E/N/D-Orn/D-aThr//Phe_4Me')),
-  );
-  columns.push(DG.Column.fromList('string', 'Activity', new Array(10 ** 6).fill('5.30751')));
-  return columns;
-}
-
-export function generateLongSequence(): DG.Column[] {
-  const columns: DG.Column[] = [];
-  const longSequence =
-    `meI/hHis/Aca/N/T/dE/Thr_PO3H2/Aca/D-Tyr_Et/Tyr_ab-dehydroMe/dV/E/N/D-Orn/D-aThr`.repeat(10 ** 5);
-  columns.push(DG.Column.fromList('string', 'MSA', new Array(10 ** 2).fill(longSequence)));
-  columns.push(DG.Column.fromList('string', 'Activity', new Array(10 ** 2).fill('7.30751')));
-  return columns;
-}
-
 export async function performanceTest(generateFunc: () => DG.Column[], testName: string) {
   const columns = generateFunc();
   const df: DG.DataFrame = DG.DataFrame.fromColumns(columns);

package/src/utils/cell-renderer.ts

@@ -214,7 +214,7 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
 
       const separator = tableCol.getTag(bioTAGS.separator) ?? '';
       const minMonWidth = seqColTemp.props.separatorWidth + 1 * seqColTemp.props.monomerCharWidth;
-      const splitLimit = w / minMonWidth;
+      const splitLimit = Math.ceil(w / minMonWidth);
       const sh = SeqHandler.forColumn(tableCol);
 
       const tempReferenceSequence: string | null = tableColTemp[tempTAGS.referenceSequence];

package/src/utils/macromolecule-column-widget.ts

@@ -38,6 +38,8 @@ export class MacromoleculeColumnWidget extends DG.Widget {
         fitArea: false,
         // maxHeight: 100,
         // minHeight: 25,
+        positionNames: '', // to ensure position names by default
+        endPositionName: '50', // limit WebLogo for visible monomers
       }) as unknown as WebLogoViewer;
       this.wlViewer.root.style.height = `50px`;
 

package/src/utils/multiple-sequence-alignment-ui.ts

@@ -2,9 +2,10 @@ import * as grok from 'datagrok-api/grok';
 import * as DG from 'datagrok-api/dg';
 import * as ui from 'datagrok-api/ui';
 
+import {ColumnInputOptions} from '@datagrok-libraries/utils/src/type-declarations';
+import {delay} from '@datagrok-libraries/utils/src/test';
 import {ALPHABET, NOTATION} from '@datagrok-libraries/bio/src/utils/macromolecule';
 import {SeqHandler} from '@datagrok-libraries/bio/src/utils/seq-handler';
-import {ColumnInputOptions} from '@datagrok-libraries/utils/src/type-declarations';
 
 import {runKalign} from './multiple-sequence-alignment';
 import {pepseaMethods, runPepsea} from './pepsea';
@@ -36,9 +37,10 @@ export async function multipleSequenceAlignmentUI(
     const table = options.col?.dataFrame ?? grok.shell.t;
     const seqCol = options.col ?? table.columns.bySemType(DG.SEMTYPE.MACROMOLECULE);
     if (seqCol == null) {
-      const errMsg = `MSAError: dataset doesn't conain any Macromolecule column`;
+      const errMsg: string = `Multiple sequence analysis requires a dataset with a macromolecule column.`;
       grok.shell.warning(errMsg);
       reject(new MsaWarning(errMsg));
+      return; // Prevents creating the MSA dialog
     }
 
     // UI for PepSea alignment
@@ -72,39 +74,50 @@ export async function multipleSequenceAlignmentUI(
 
     let performAlignment: (() => Promise<DG.Column<string> | null>) | undefined;
 
-    //TODO: remove when the new version of datagrok-api is available
-    //TODO: allow only macromolecule columns to be chosen
-    const colInput = ui.columnInput('Sequence', table, seqCol, async () => {
+    let prevSeqCol = seqCol;
+    const colInput = ui.columnInput(
+      'Sequence', table, seqCol,
+      async (valueCol: DG.Column) => {
+        if (!valueCol || valueCol.semType !== DG.SEMTYPE.MACROMOLECULE) {
+          okBtn.disabled = true;
+          await delay(0); // to
+          colInput.value = prevSeqCol as DG.Column<string>;
+          return;
+        }
+        prevSeqCol = valueCol;
+        okBtn.disabled = false;
         performAlignment = await onColInputChange(
           colInput.value, table, pepseaInputRootStyles, kalignInputRootStyles,
           methodInput, clustersColInput, gapOpenInput, gapExtendInput, terminalGapInput,
         );
-        //@ts-ignore
       }, {filter: (col: DG.Column) => col.semType === DG.SEMTYPE.MACROMOLECULE} as ColumnInputOptions
     ) as DG.InputBase<DG.Column<string>>;
     colInput.setTooltip('Sequences column to use for alignment');
     const clustersColInput = ui.columnInput('Clusters', table, options.clustersCol);
     clustersColInput.nullable = true;
-    colInput.fireChanged();
+
+    const dlg = ui.dialog('MSA')
+      .add(colInput)
+      .add(clustersColInput)
+      .add(methodInput)
+      .add(msaParamsDiv)
+      .add(msaParamsButton)
+      .add(kalignVersionDiv)
+      .onOK(async () => { await onDialogOk(colInput, table, performAlignment, resolve, reject); });
+    const okBtn = dlg.getButton('OK');
+
+    colInput.fireChanged(); // changes okBtn
     //if column is specified (from tests), run alignment and resolve with the result
     if (options.col) {
       performAlignment = await onColInputChange(
         options.col, table, pepseaInputRootStyles, kalignInputRootStyles,
         methodInput, clustersColInput, gapOpenInput, gapExtendInput, terminalGapInput,
       );
-
       await onDialogOk(colInput, table, performAlignment, resolve, reject);
-      return;
+      return; // Prevents show the dialog
     }
-    const _dlg = ui.dialog('MSA')
-      .add(colInput)
-      .add(clustersColInput)
-      .add(methodInput)
-      .add(msaParamsDiv)
-      .add(msaParamsButton)
-      .add(kalignVersionDiv)
-      .onOK(async () => { await onDialogOk(colInput, table, performAlignment, resolve, reject); })
-      .show();
+
+    dlg.show();
   });
 }
 

package/src/viewers/web-logo-viewer.ts

@@ -953,16 +953,26 @@ export class WebLogoViewer extends DG.JsViewer implements IWebLogoViewer {
 
       // region updatePositions
 
+      /** positionNames and positionLabel can be set up through the column's tags only */
+      const positionNamesTxt = this.seqCol.getTag(bioTAGS.positionNames);
+      const positionLabelsTxt = this.seqCol.getTag(bioTAGS.positionLabels);
+
+      // WebLogo in the column tooltip / widget is limited, speed up for long sequences
+      let splitLimit: number | undefined = undefined;
+      if (!positionNamesTxt && this.endPositionName && /\d+/.test(this.endPositionName))
+        splitLimit = Number(this.endPositionName);
+      else if (positionNamesTxt && this.endPositionName) {
+        splitLimit = positionNamesTxt.split(positionSeparator).indexOf(this.endPositionName);
+        splitLimit = splitLimit !== -1 ? splitLimit : undefined;
+      }
+
       const dfFilter = this.getFilter();
       const maxLength: number = dfFilter.trueCount === 0 ? this.seqHandler!.maxLength :
         wu.count(0).take(this.seqHandler!.length).map((rowIdx) => {
-          const mList = this.seqHandler!.getSplitted(rowIdx);
+          const mList = this.seqHandler!.getSplitted(rowIdx, splitLimit);
           return dfFilter.get(rowIdx) && !!mList ? mList.length : 0;
         }).reduce((max, l) => Math.max(max, l), 0);
 
-      /** positionNames and positionLabel can be set up through the column's tags only */
-      const positionNamesTxt = this.seqCol.getTag(bioTAGS.positionNames);
-      const positionLabelsTxt = this.seqCol.getTag(bioTAGS.positionLabels);
       this.positionNames = !!positionNamesTxt ? positionNamesTxt.split(positionSeparator).map((v) => v.trim()) :
         [...Array(maxLength).keys()].map((jPos) => `${jPos + 1}`)/* fallback if tag is not provided */;
       this.positionLabels = !!positionLabelsTxt ? positionLabelsTxt.split(positionSeparator).map((v) => v.trim()) :

package/src/widgets/bio-substructure-filter-helm.ts

@@ -135,9 +135,15 @@ export class HelmBioFilter extends BioFilterBase<BioFilterProps> /* implements I
   }
 
   async substructureSearch(column: DG.Column): Promise<DG.BitSet | null> {
-    await delay(10);
-    const res = await helmSubstructureSearch(this.props.substructure, column);
-    return res;
+    const logPrefix = `${this.viewerToLog()}.substructureSearch( column = <${column.name}> )`;
+    _package.logger.debug(`${logPrefix}, start`);
+    try {
+      await delay(10);
+      const res = await helmSubstructureSearch(this.props.substructure, column);
+      return res;
+    } finally {
+      _package.logger.debug(`${logPrefix}, end`);
+    }
   }
 
   // // -- IRenderer --