@datagrok/bio 2.10.29 → 2.11.1

package/package.json

@@ -5,7 +5,7 @@
     "name": "Leonid Stolbov",
     "email": "lstolbov@datagrok.ai"
   },
-  "version": "2.10.29",
+  "version": "2.11.1",
   "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",
@@ -34,9 +34,9 @@
   ],
   "dependencies": {
     "@biowasm/aioli": "^3.1.0",
-    "@datagrok-libraries/bio": "^5.38.13",
+    "@datagrok-libraries/bio": "^5.39.0",
     "@datagrok-libraries/chem-meta": "^1.0.1",
-    "@datagrok-libraries/ml": "^6.3.50",
+    "@datagrok-libraries/ml": "^6.3.51",
     "@datagrok-libraries/tutorials": "^1.3.6",
     "@datagrok-libraries/utils": "^4.0.17",
     "cash-dom": "^8.0.0",

package/src/apps/web-logo-app.ts

@@ -4,7 +4,7 @@ import * as DG from 'datagrok-api/dg';
 
 import wu from 'wu';
 
-import {IWebLogoViewer} from '@datagrok-libraries/bio/src/viewers/web-logo';
+import {IWebLogoViewer, WebLogoProps} from '@datagrok-libraries/bio/src/viewers/web-logo';
 
 import {PROPS as wlPROPS} from '../viewers/web-logo-viewer';
 
@@ -14,7 +14,11 @@ export class WebLogoApp {
   df: DG.DataFrame;
   view: DG.TableView;
 
-  constructor(private readonly urlParams: URLSearchParams, private readonly funcName: string) {}
+  constructor(
+    private readonly urlParams: URLSearchParams,
+    private readonly funcName: string,
+    private readonly options: Partial<WebLogoProps> = {}
+  ) {}
 
   async init(df: DG.DataFrame): Promise<void> {
     this.df = df;
@@ -32,7 +36,7 @@ export class WebLogoApp {
     this.view = grok.shell.addTableView(this.df);
     this.view.path = this.view.basePath = `func/${_package.name}.${this.funcName}?${urlParamsTxt}`;
 
-    const options: { [p: string]: any } = {sequenceColumnName: 'sequence'};
+    const options: { [p: string]: any } = {...this.options, ...{sequenceColumnName: 'sequence'}};
     for (const [optName, optValue] of this.urlParams.entries()) {
       switch (optName) {
         // boolean

package/src/package.ts

@@ -3,36 +3,52 @@ import * as grok from 'datagrok-api/grok';
 import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
 
+
+import {delay} from '@datagrok-libraries/utils/src/test';
+import {removeEmptyStringRows} from '@datagrok-libraries/utils/src/dataframe-utils';
+import {Options} from '@datagrok-libraries/utils/src/type-declarations';
+import {RDMol} from '@datagrok-libraries/chem-meta/src/rdkit-api';
+import {DimReductionMethods, ITSNEOptions, IUMAPOptions} from '@datagrok-libraries/ml/src/reduce-dimensionality';
+import {SequenceSpaceFunctionEditor} from '@datagrok-libraries/ml/src/functionEditors/seq-space-editor';
+import {ActivityCliffsFunctionEditor} from '@datagrok-libraries/ml/src/functionEditors/activity-cliffs-editor';
+import {
+  ISequenceSpaceParams, getActivityCliffs, SequenceSpaceFunc
+} from '@datagrok-libraries/ml/src/viewers/activity-cliffs';
+import {MmDistanceFunctionsNames} from '@datagrok-libraries/ml/src/macromolecule-distance-functions';
+import {BitArrayMetrics, BitArrayMetricsNames} from '@datagrok-libraries/ml/src/typed-metrics';
+import {
+  TAGS as bioTAGS, ALPHABET, NOTATION,
+} from '@datagrok-libraries/bio/src/utils/macromolecule';
+import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
+import {IMonomerLib} from '@datagrok-libraries/bio/src/types';
+import {SeqPalette} from '@datagrok-libraries/bio/src/seq-palettes';
+import {FastaFileHandler} from '@datagrok-libraries/bio/src/utils/fasta-handler';
+import {_toAtomicLevel} from '@datagrok-libraries/bio/src/monomer-works/to-atomic-level';
+import {SCORE, calculateScores} from '@datagrok-libraries/bio/src/utils/macromolecule/scoring';
+import {
+  createJsonMonomerLibFromSdf, IMonomerLibHelper
+} from '@datagrok-libraries/bio/src/monomer-works/monomer-utils';
+
+import {getMacromoleculeColumns} from './utils/ui-utils';
 import {
   MacromoleculeDifferenceCellRenderer, MacromoleculeSequenceCellRenderer,
 } from './utils/cell-renderer';
 import {VdRegionsViewer} from './viewers/vd-regions-viewer';
 import {SequenceAlignment} from './seq_align';
-import {ISequenceSpaceResult, getEmbeddingColsNames, getSequenceSpace} from './analysis/sequence-space';
-import {ISequenceSpaceParams, getActivityCliffs} from '@datagrok-libraries/ml/src/viewers/activity-cliffs';
+import {
+  ISequenceSpaceResult, getEmbeddingColsNames, getSequenceSpace, sequenceSpaceByFingerprints
+} from './analysis/sequence-space';
 import {
   createLinesGrid, createPropPanelElement, createTooltipElement, getChemSimilaritiesMatrix,
 } from './analysis/sequence-activity-cliffs';
-import {convert} from './utils/convert';
-import {getMacromoleculeColumnPropertyPanel} from './widgets/representations';
-import {_toAtomicLevel} from '@datagrok-libraries/bio/src/monomer-works/to-atomic-level';
-import {FastaFileHandler} from '@datagrok-libraries/bio/src/utils/fasta-handler';
-import {removeEmptyStringRows} from '@datagrok-libraries/utils/src/dataframe-utils';
-
 import {SequenceSimilarityViewer} from './analysis/sequence-similarity-viewer';
 import {SequenceDiversityViewer} from './analysis/sequence-diversity-viewer';
 import {SubstructureSearchDialog} from './substructure-search/substructure-search';
+import {convert} from './utils/convert';
+import {getMacromoleculeColumnPropertyPanel} from './widgets/representations';
 import {saveAsFastaUI} from './utils/save-as-fasta';
 import {BioSubstructureFilter} from './widgets/bio-substructure-filter';
-import {delay} from '@datagrok-libraries/utils/src/test';
-import {
-  TAGS as bioTAGS, ALPHABET, NOTATION,
-} from '@datagrok-libraries/bio/src/utils/macromolecule';
-import {IMonomerLib} from '@datagrok-libraries/bio/src/types';
-import {SeqPalette} from '@datagrok-libraries/bio/src/seq-palettes';
-import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
 import {WebLogoViewer} from './viewers/web-logo-viewer';
-import {createJsonMonomerLibFromSdf, IMonomerLibHelper} from '@datagrok-libraries/bio/src/monomer-works/monomer-utils';
 import {
   MonomerLibHelper,
   getUserLibSettings,
@@ -40,12 +56,6 @@ import {
   getLibFileNameList,
   getLibraryPanelUI
 } from './utils/monomer-lib';
-import {getMacromoleculeColumns} from './utils/ui-utils';
-import {DimReductionMethods, ITSNEOptions, IUMAPOptions} from '@datagrok-libraries/ml/src/reduce-dimensionality';
-import {SequenceSpaceFunctionEditor} from '@datagrok-libraries/ml/src/functionEditors/seq-space-editor';
-import {ActivityCliffsFunctionEditor} from '@datagrok-libraries/ml/src/functionEditors/activity-cliffs-editor';
-import {SCORE, calculateScores} from '@datagrok-libraries/bio/src/utils/macromolecule/scoring';
-
 import {demoBio01UI} from './demo/bio01-similarity-diversity';
 import {demoBio01aUI} from './demo/bio01a-hierarchical-clustering-and-sequence-space';
 import {demoBio01bUI} from './demo/bio01b-hierarchical-clustering-and-activity-cliffs';
@@ -53,14 +63,11 @@ 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 {MmDistanceFunctionsNames} from '@datagrok-libraries/ml/src/macromolecule-distance-functions';
-import {BitArrayMetrics, BitArrayMetricsNames} from '@datagrok-libraries/ml/src/typed-metrics';
 import {WebLogoApp} from './apps/web-logo-app';
 import {SplitToMonomersFunctionEditor} from './function-edtiors/split-to-monomers-editor';
 import {splitToMonomersUI} from './utils/split-to-monomers';
 import {MonomerCellRenderer} from './utils/monomer-cell-renderer';
 import {BioPackage, BioPackageProperties} from './package-types';
-import {RDMol} from '@datagrok-libraries/chem-meta/src/rdkit-api';
 import {PackageSettingsEditorWidget} from './widgets/package-settings-editor-widget';
 import {getCompositionAnalysisWidget} from './widgets/composition-analysis-widget';
 import {MacromoleculeColumnWidget} from './utils/macromolecule-column-widget';
@@ -71,11 +78,12 @@ import {getRegionDo} from './utils/get-region';
 import {GetRegionApp} from './apps/get-region-app';
 import {GetRegionFuncEditor} from './utils/get-region-func-editor';
 import {HelmToMolfileConverter} from './utils/helm-to-molfile';
-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 {errInfo} from './utils/err-info';
+
 import {SHOW_SCATTERPLOT_PROGRESS} from '@datagrok-libraries/ml/src/functionEditors/seq-space-base-editor';
+import {DIMENSIONALITY_REDUCER_TERMINATE_EVENT}
+  from '@datagrok-libraries/ml/src/workers/dimensionality-reducing-worker-creator';
 
 export const _package = new BioPackage();
 
@@ -404,6 +412,7 @@ export async function activityCliffs(df: DG.DataFrame, macroMolecule: DG.Column<
   const ncUH = UnitsHandler.getOrCreate(macroMolecule);
   let columnDistanceMetric: BitArrayMetrics | MmDistanceFunctionsNames = BitArrayMetricsNames.Tanimoto;
   let seqCol = macroMolecule;
+  let sequenceSpaceFunc: SequenceSpaceFunc = sequenceSpaceByFingerprints;
   if (ncUH.isFasta() || (ncUH.isSeparator() && ncUH.alphabet && ncUH.alphabet !== ALPHABET.UN)) {
     if (ncUH.isFasta()) {
       columnDistanceMetric = ncUH.getDistanceFunctionName();
@@ -413,6 +422,7 @@ export async function activityCliffs(df: DG.DataFrame, macroMolecule: DG.Column<
       columnDistanceMetric = uh.getDistanceFunctionName();
       tags.units = NOTATION.FASTA;
     }
+    sequenceSpaceFunc = getSequenceSpace;
   }
   const runCliffs = async () => {
     const sp = await getActivityCliffs(
@@ -427,7 +437,7 @@ export async function activityCliffs(df: DG.DataFrame, macroMolecule: DG.Column<
       methodName,
       DG.SEMTYPE.MACROMOLECULE,
       tags,
-      getSequenceSpace,
+      sequenceSpaceFunc,
       getChemSimilaritiesMatrix,
       createTooltipElement,
       createPropPanelElement,
@@ -443,20 +453,23 @@ export async function activityCliffs(df: DG.DataFrame, macroMolecule: DG.Column<
     return;
   }
 
-  if (df.rowCount > fastRowCount && !options?.[BYPASS_LARGE_DATA_WARNING]) {
-    ui.dialog().add(ui.divText(`Activity cliffs analysis might take several minutes.
+  return new Promise<DG.Viewer>((resolve, reject) => {
+    if (df.rowCount > fastRowCount && !options?.[BYPASS_LARGE_DATA_WARNING]) {
+      ui.dialog().add(ui.divText(`Activity cliffs analysis might take several minutes.
     Do you want to continue?`))
-      .onOK(async () => {
-        const progressBar = DG.TaskBarProgressIndicator.create(`Running sequence activity cliffs ...`);
-        const res = await runCliffs();
-        progressBar.close();
-        return res;
-      })
-      .show();
-  } else {
-    const res = await runCliffs();
-    return res;
-  }
+        .onOK(async () => {
+          const progressBar = DG.TaskBarProgressIndicator.create(`Running sequence activity cliffs ...`);
+          runCliffs().then((res) => resolve(res)).catch((err) => reject(err)).finally(() => { progressBar.close();});
+        })
+        .show();
+    } else {
+      runCliffs().then((res) => resolve(res)).catch((err) => reject(err));
+    }
+  }).catch((err: any) => {
+    const [errMsg, errStack] = errInfo(err);
+    _package.logger.error(errMsg, undefined, errStack);
+    throw err;
+  });
 }
 
 //top-menu: Bio | Analyze | Sequence Space...
@@ -585,7 +598,7 @@ export async function sequenceSpaceTopMenu(
           table.columns.add(embedCol);
         }
         embedCol.init((i) => listValues[i]);
-      //table.columns.add(DG.Column.float(col.name, table.rowCount).init((i) => listValues[i]));
+        //table.columns.add(DG.Column.float(col.name, table.rowCount).init((i) => listValues[i]));
       }
       if (plotEmbeddings) {
         if (!scatterPlot) {
@@ -976,6 +989,20 @@ export async function webLogoLargeApp(): Promise<void> {
   }
 }
 
+//name: webLogoAggApp
+export async function webLogoAggApp(): Promise<void> {
+  const pi = DG.TaskBarProgressIndicator.create('WebLogo ...');
+  try {
+    const urlParams = new URLSearchParams(window.location.search);
+    const app = new WebLogoApp(urlParams, 'webLogoAggApp');
+    const df: DG.DataFrame = await _package.files.readCsv('data/sample_FASTA_PT_activity.csv');
+    await grok.data.detectSemanticTypes(df);
+    await app.init(df);
+  } finally {
+    pi.close();
+  }
+}
+
 //name: getRegionApp
 export async function getRegionApp(): Promise<void> {
   const pi = DG.TaskBarProgressIndicator.create('getRegion ...');

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

@@ -55,7 +55,7 @@ ATC-G-TTGC--
     for (let i = 0; i < positions.length; i++) {
       expect(positions[i].name, resAllDf1[i].name);
       for (const m of positions[i].getMonomers())
-        expect(positions[i].getFreq(m).count, resAllDf1[i].getFreq(m).count);
+        expect(positions[i].getFreq(m).rowCount, resAllDf1[i].getFreq(m).rowCount);
     }
   });
 
@@ -104,7 +104,7 @@ ATC-G-TTGC--
     for (let i = 0; i < positions.length; i++) {
       expect(positions[i].name, resAllDf1[i].name);
       for (const m of positions[i].getMonomers())
-        expect(positions[i].getFreq(m).count, resAllDf1[i].getFreq(m).count);
+        expect(positions[i].getFreq(m).rowCount, resAllDf1[i].getFreq(m).rowCount);
     }
   });
 
@@ -204,7 +204,7 @@ function expectPositionInfo(actualPos: PI, expectedPos: PI): void {
   expectArray(actualPos.getMonomers(), expectedPos.getMonomers());
   for (const key of actualPos.getMonomers()) {
     //
-    expect(actualPos.getFreq(key).count, expectedPos.getFreq(key).count);
+    expect(actualPos.getFreq(key).rowCount, expectedPos.getFreq(key).rowCount);
   }
 }
 

package/src/tests/activity-cliffs-tests.ts

@@ -1,5 +1,4 @@
 import * as grok from 'datagrok-api/grok';
-import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
 
 import {after, before, category, test} from '@datagrok-libraries/utils/src/test';
@@ -8,6 +7,8 @@ import {readDataframe} from './utils';
 import {_testActivityCliffsOpen} from './activity-cliffs-utils';
 import {DimReductionMethods} from '@datagrok-libraries/ml/src/reduce-dimensionality';
 
+import {_package} from '../package-test';
+
 
 category('activityCliffs', async () => {
   let actCliffsTableView: DG.TableView;
@@ -37,7 +38,8 @@ category('activityCliffs', async () => {
     viewList.push(actCliffsTableView);
     const cliffsNum = DG.Test.isInBenchmark ? 6 : 3;
 
-    await _testActivityCliffsOpen(actCliffsDf, cliffsNum, DimReductionMethods.UMAP, 'sequence');
+    await _testActivityCliffsOpen(actCliffsDf, DimReductionMethods.UMAP,
+      'sequence', 'Activity', 90, cliffsNum);
   });
 
   test('activityCliffsWithEmptyRows', async () => {
@@ -46,6 +48,15 @@ category('activityCliffs', async () => {
     actCliffsTableViewWithEmptyRows = grok.shell.addTableView(actCliffsDfWithEmptyRows);
     viewList.push(actCliffsTableViewWithEmptyRows);
 
-    await _testActivityCliffsOpen(actCliffsDfWithEmptyRows, 3, DimReductionMethods.UMAP, 'sequence');
+    await _testActivityCliffsOpen(actCliffsDfWithEmptyRows, DimReductionMethods.UMAP,
+      'sequence', 'Activity', 90, 3);
+  });
+
+  test('Helm', async () => {
+    const df = await _package.files.readCsv('samples/sample_HELM.csv');
+    const view = grok.shell.addTableView(df);
+
+    await _testActivityCliffsOpen(df, DimReductionMethods.UMAP,
+      'HELM', 'Activity', 90, 53);
   });
 });

package/src/tests/activity-cliffs-utils.ts

@@ -5,12 +5,13 @@ import {expect} from '@datagrok-libraries/utils/src/test';
 import {activityCliffs, BYPASS_LARGE_DATA_WARNING} from '../package';
 import {DimReductionMethods} from '@datagrok-libraries/ml/src/reduce-dimensionality';
 
-export async function _testActivityCliffsOpen(df: DG.DataFrame, numberCliffs: number, method: DimReductionMethods,
-  colName: string) {
+export async function _testActivityCliffsOpen(df: DG.DataFrame, drMethod: DimReductionMethods,
+  seqColName: string, activityColName: string, similarityThr: number, tgtNumberCliffs: number
+): Promise<void> {
   await grok.data.detectSemanticTypes(df);
   const scatterPlot = await activityCliffs(
-    df, df.getCol(colName), df.getCol('activity'),
-    90, method, {[`${BYPASS_LARGE_DATA_WARNING}`]: true});
+    df, df.getCol(seqColName), df.getCol(activityColName),
+    similarityThr, drMethod, {[`${BYPASS_LARGE_DATA_WARNING}`]: true});
   // const scatterPlot = (await grok.functions.call('Bio:activityCliffs', {
   //   table: df, molecules: df.getCol(colName), activities: df.getCol('Activity'),
   //   similarity: 50, methodName: method
@@ -27,5 +28,5 @@ export async function _testActivityCliffsOpen(df: DG.DataFrame, numberCliffs: nu
     const classList: string[] = el.className.split(' ');
     return ['ui-btn', 'ui-btn-ok'].every((reqClassName) => classList.includes(reqClassName));
   });
-  expect((cliffsLink as HTMLElement).innerText.toLowerCase(), `${numberCliffs} cliffs`);
+  expect((cliffsLink as HTMLElement).innerText.toLowerCase(), `${tgtNumberCliffs} cliffs`);
 }

package/src/utils/agg.ts

@@ -0,0 +1,29 @@
+import * as grok from 'datagrok-api/grok';
+import * as ui from 'datagrok-api/ui';
+import * as DG from 'datagrok-api/dg';
+
+export type AggValueListType = (number | null)[] | Float32Array | Int32Array;
+export type AggFunc = (valueList: AggValueListType) => number | null;
+
+export function getAgg(agg: DG.AggregationType): AggFunc {
+  let res: AggFunc;
+
+  function buildCol(valueList: AggValueListType): DG.Column<number> {
+    let resCol: DG.Column<number>;
+    const resColName = `agg`;
+    if (valueList instanceof Float32Array)
+      resCol = DG.Column.fromFloat32Array(resColName, valueList as Float32Array);
+    else if (valueList instanceof Int32Array)
+      resCol = DG.Column.fromInt32Array(resColName, valueList as Int32Array);
+    else
+      resCol = DG.Column.fromList(DG.COLUMN_TYPE.FLOAT, resColName, valueList as (number | null)[]);
+
+    return resCol;
+  }
+
+  return (valueList: AggValueListType): number | null => {
+    const aggCol = buildCol(valueList);
+    const res = aggCol.aggregate(agg);
+    return res;
+  };
+}