@datagrok/peptides 1.18.7 → 1.19.1

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@datagrok/peptides",
   "friendlyName": "Peptides",
-  "version": "1.18.7",
+  "version": "1.19.1",
   "author": {
     "name": "Davit Rizhinashvili",
     "email": "drizhinashvili@datagrok.ai"
@@ -13,13 +13,13 @@
     "directory": "packages/Peptides"
   },
   "dependencies": {
-    "@datagrok-libraries/bio": "^5.44.5",
+    "@datagrok-libraries/bio": "^5.46.1",
     "@datagrok-libraries/math": "^1.2.3",
-    "@datagrok-libraries/ml": "^6.7.4",
+    "@datagrok-libraries/ml": "^6.7.5",
     "@datagrok-libraries/statistics": "^1.2.12",
     "@datagrok-libraries/tutorials": "^1.4.2",
-    "@datagrok-libraries/utils": "^4.3.0",
-    "datagrok-api": "^1.21.1",
+    "@datagrok-libraries/utils": "^4.3.10",
+    "datagrok-api": "^1.22.0",
     "@webgpu/types": "^0.1.40",
     "cash-dom": "^8.1.5",
     "file-loader": "^6.2.0",
@@ -30,10 +30,10 @@
   "devDependencies": {
     "@datagrok-libraries/helm-web-editor": "^1.1.7",
     "@datagrok-libraries/js-draw-lite": "^0.0.5",
-    "@datagrok/bio": "^2.15.0",
+    "@datagrok/bio": "^2.16.9",
     "@datagrok/chem": "^1.12.0",
     "@datagrok/dendrogram": "^1.2.33",
-    "@datagrok/helm": "^2.5.0",
+    "@datagrok/helm": "^2.5.9",
     "@types/uuid": "^10.0.0",
     "@types/wu": "^2.1.44",
     "@typescript-eslint/eslint-plugin": "^8.8.1",

package/src/model.ts

@@ -1,3 +1,4 @@
+/* eslint-disable max-len */
 import * as ui from 'datagrok-api/ui';
 import * as grok from 'datagrok-api/grok';
 import * as DG from 'datagrok-api/dg';
@@ -13,7 +14,7 @@ import {DistanceMatrix} from '@datagrok-libraries/ml/src/distance-matrix';
 import {BitArrayMetrics} from '@datagrok-libraries/ml/src/typed-metrics';
 import {TAGS as _treeTAGS} from '@datagrok-libraries/bio/src/trees';
 import BitArray from '@datagrok-libraries/utils/src/bit-array';
-import {SeqHandler} from '@datagrok-libraries/bio/src/utils/seq-handler';
+import {getSeqHelper} from '@datagrok-libraries/bio/src/utils/seq-helper';
 import wu from 'wu';
 import * as rxjs from 'rxjs';
 import $ from 'cash-dom';
@@ -54,6 +55,7 @@ import {markovCluster} from '@datagrok-libraries/ml/src/MCL/clustering-view';
 import {DistanceAggregationMethods} from '@datagrok-libraries/ml/src/distance-matrix/types';
 import {ClusterMaxActivityViewer, IClusterMaxActivity} from './viewers/cluster-max-activity-viewer';
 import {MCL_OPTIONS_TAG, MCLSerializableOptions} from '@datagrok-libraries/ml/src/MCL';
+import {PeptideUtils} from './peptideUtils';
 
 export enum VIEWER_TYPE {
   SEQUENCE_VARIABILITY_MAP = 'Sequence Variability Map',
@@ -613,7 +615,7 @@ export class PeptidesModel {
             (requestSource as SARViewer | LogoSummaryTable).getScaledActivityColumn(),
           gridColumns: trueModel.analysisView.grid.columns,
           colorPalette: pickUpPalette(trueModel.df.getCol(isModelSource ? trueModel.settings!.sequenceColumnName :
-            (requestSource as SARViewer | LogoSummaryTable).sequenceColumnName)),
+            (requestSource as SARViewer | LogoSummaryTable).sequenceColumnName), PeptideUtils.getSeqHelper()),
           tableSelection: trueModel.getCombinedSelection(),
           isAnalysis: trueModel.settings !== null && (isModelSource ||
         areObjectsEqual(trueModel.settings.columns, (requestSource as PeptideViewer).getAggregationColumns())),
@@ -652,7 +654,7 @@ export class PeptidesModel {
       selectionCallback: (monomerPosition: type.SelectionItem, options: type.SelectionOptions): void =>
         this.modifyWebLogoSelection(monomerPosition, options),
       unhighlightCallback: (): void => this.unhighlight(),
-      colorPalette: () => pickUpPalette(this.df.getCol(this.settings!.sequenceColumnName)),
+      colorPalette: () => pickUpPalette(this.df.getCol(this.settings!.sequenceColumnName), PeptideUtils.getSeqHelper()),
       webLogoBounds: () => this.webLogoBounds,
       cachedWebLogoTooltip: () => this.cachedWebLogoTooltip,
       highlightCallback: (mp: type.SelectionItem, df: DG.DataFrame, mpStats: MonomerPositionStats): void =>
@@ -686,7 +688,7 @@ export class PeptidesModel {
     // append splitSeqDf columns to source table and make sure columns are not added more than once
     const name = this.df.name;
     const cols = this.df.columns;
-    const splitSeqDf = splitAlignedSequences(this.df.getCol(this.settings!.sequenceColumnName));
+    const splitSeqDf = splitAlignedSequences(this.df.getCol(this.settings!.sequenceColumnName), PeptideUtils.getSeqHelper());
     const positionColumns = splitSeqDf.columns.names();
     for (const colName of positionColumns) {
       let col = this.df.col(colName);
@@ -1049,7 +1051,7 @@ export class PeptidesModel {
         'Adds a column with fractions of matching monomers against sequence in the current row');
       calculateIdentity.onclick = (): void => {
         const seqCol = this.df.getCol(this.settings!.sequenceColumnName);
-        calculateScores(this.df, seqCol, seqCol.get(this.df.currentRowIdx), SCORE.IDENTITY)
+        calculateScores(this.df, seqCol, seqCol.get(this.df.currentRowIdx), SCORE.IDENTITY, PeptideUtils.getSeqHelper())
           .then((col: DG.Column<number>) => col.setTag(C.TAGS.IDENTITY_TEMPLATE, seqCol.get(this.df.currentRowIdx)))
           .catch((e) => _package.logger.debug(e));
       };
@@ -1061,7 +1063,7 @@ export class PeptidesModel {
         'Adds a column with sequence similarity scores against sequence in the current row');
       calculateSimilarity.onclick = (): void => {
         const seqCol = this.df.getCol(this.settings!.sequenceColumnName);
-        calculateScores(this.df, seqCol, seqCol.get(this.df.currentRowIdx), SCORE.SIMILARITY)
+        calculateScores(this.df, seqCol, seqCol.get(this.df.currentRowIdx), SCORE.SIMILARITY, PeptideUtils.getSeqHelper())
           .then((col: DG.Column<number>) => col.setTag(C.TAGS.SIMILARITY_TEMPLATE, seqCol.get(this.df.currentRowIdx)))
           .catch((e) => _package.logger.debug(e));
       };
@@ -1356,7 +1358,7 @@ export class PeptidesModel {
       this._sequenceSpaceCols.forEach((col) => this.df.columns.remove(col));
     this._sequenceSpaceCols = [];
     let seqCol = this.df.getCol(this.settings!.sequenceColumnName!);
-    const sh = SeqHandler.forColumn(seqCol);
+    const sh = PeptideUtils.getSeqHelper().getSeqHandler(seqCol);
     const isHelm = sh.isHelm();
     if (isHelm) {
       try {
@@ -1460,7 +1462,7 @@ export class PeptidesModel {
         menu.item('Modify Sequence space parameters', () => {
           getSettingsDialog(this);
         });
-      } catch (e) {
+      } catch (_) {
       }
     });
   }

package/src/package-test.ts

@@ -21,7 +21,7 @@ export async function test(category: string, test: string, testContext: TestCont
   // const helmInit = DG.Func.find({name: 'initHelm'})[0];
   // if (helmInit)
   //   await helmInit.apply();
-  testContext.catchUnhandled = false;
+  testContext?.catchUnhandled && (testContext.catchUnhandled = false);
   const data = await runTests({category, test, testContext});
   return DG.DataFrame.fromObjects(data)!;
 }

package/src/package.ts

@@ -1,3 +1,4 @@
+/* eslint-disable max-len */
 /* Do not change these import lines. Datagrok will import API library in exactly the same manner */
 import * as grok from 'datagrok-api/grok';
 import * as ui from 'datagrok-api/ui';
@@ -15,6 +16,7 @@ import {macromoleculeSarFastaDemoUI} from './demo/fasta';
 import {u2} from '@datagrok-libraries/utils/src/u2';
 import {ClusterMaxActivityViewer} from './viewers/cluster-max-activity-viewer';
 import {LSTPieChartRenderer} from './utils/cell-renderer';
+import {PeptideUtils} from './peptideUtils';
 
 let monomerWorks: MonomerWorks | null = null;
 let treeHelper: ITreeHelper;
@@ -34,6 +36,7 @@ export async function initPeptides(): Promise<void> {
   try {
     monomerWorks ??= new MonomerWorks(await grok.functions.call('Bio:getBioLib'));
     treeHelper ??= await getTreeHelper();
+    await PeptideUtils.loadSeqHelper();
   } catch (e) {
     grok.log.error(e as string);
   }
@@ -90,6 +93,12 @@ export function peptidesDialog(): DG.Dialog | null {
     grok.shell.warning('SAR Analysis requires an active table with Macromolecule column');
     return null;
   }
+
+  if (!DG.Utils.firstOrNull(grok.shell.t.columns.numerical)) {
+    grok.shell.warning('SAR Analysis requires an active table with at least one numerical column for activity');
+    return null;
+  }
+
   const analyzeObject = analyzePeptidesUI(grok.shell.t);
   const dialog = ui.dialog('Analyze Peptides').add(analyzeObject.host).onOK(async () => {
     const startSuccess = analyzeObject.callback();
@@ -112,6 +121,8 @@ export async function testInitFunctionPeptides(v: DG.Viewer): Promise<void> {
 //input: column col {semType: Macromolecule}
 //output: widget result
 export function peptidesPanel(col: DG.Column): DG.Widget {
+  if (!col.dataFrame || !DG.Utils.firstOrNull(col.dataFrame.columns.numerical))
+    return new DG.Widget(ui.divText('SAR Analysis requires an active table with at least one numerical column for activity'));
   const analyzeObject = analyzePeptidesUI(col.dataFrame, col);
   return new DG.Widget(analyzeObject.host);
 }
@@ -169,6 +180,7 @@ export function manualAlignment(_monomer: string): DG.Widget {
 //name: Macromolecule SAR Analysis
 //description: Macromolecule SAR Analysis demo on peptide sequences in FASTA format
 //meta.demoPath: Bioinformatics | Macromolecule SAR Analysis
+//meta.demoSkip: GROK-14320
 export async function macromoleculeSarFastaDemo(): Promise<void> {
   return await macromoleculeSarFastaDemoUI();
 }

package/src/peptideUtils.ts

@@ -0,0 +1,14 @@
+import {getSeqHelper, ISeqHelper} from '@datagrok-libraries/bio/src/utils/seq-helper';
+
+export class PeptideUtils {
+  private static _secHelper: ISeqHelper;
+  public static getSeqHelper(): ISeqHelper {
+    if (!this._secHelper)
+      throw new Error('SeqHelper is not initialized');
+    return this._secHelper;
+  }
+
+  public static async loadSeqHelper(): Promise<void> {
+    this._secHelper ??= await getSeqHelper();
+  }
+}

package/src/tests/benchmarks.ts

@@ -1,7 +1,7 @@
 import * as grok from 'datagrok-api/grok';
 import * as DG from 'datagrok-api/dg';
 
-import {category, test} from '@datagrok-libraries/utils/src/test';
+import {before, category, test} from '@datagrok-libraries/utils/src/test';
 import {NOTATION} from '@datagrok-libraries/bio/src/utils/macromolecule';
 
 import {_package} from '../package-test';
@@ -10,16 +10,23 @@ import * as type from '../utils/types';
 import {scaleActivity} from '../utils/misc';
 import {startAnalysis} from '../widgets/peptides';
 import * as C from '../utils/constants';
+import {PeptideUtils} from '../peptideUtils';
 
 
 const benchmarkDatasetSizes = [5, 50, 100, 200];
 
 category('Benchmarks: Mutation Cliffs', () => {
+  before(async () => {
+    await PeptideUtils.loadSeqHelper();
+  });
   for (const size of benchmarkDatasetSizes)
     test(`${size}k sequences`, async () => await mutationCliffsBenchmark(size), {timeout: 300000});
 }, {benchmarks: true});
 
 category('Benchmarks: Cluster stats', () => {
+  before(async () => {
+    await PeptideUtils.loadSeqHelper();
+  });
   for (const size of benchmarkDatasetSizes) {
     test(`${size}k sequences`, async () => {
       if (!DG.Test.isInBenchmark)
@@ -41,6 +48,9 @@ category('Benchmarks: Cluster stats', () => {
 }, {benchmarks: true});
 
 category('Benchmarks: Monomer-Position stats', () => {
+  before(async () => {
+    await PeptideUtils.loadSeqHelper();
+  });
   for (const size of benchmarkDatasetSizes) {
     test(`${size}k sequences`, async () => {
       if (!DG.Test.isInBenchmark)
@@ -67,6 +77,9 @@ category('Benchmarks: Monomer-Position stats', () => {
 }, {benchmarks: true});
 
 category('Benchmarks: Analysis start', () => {
+  before(async () => {
+    await PeptideUtils.loadSeqHelper();
+  });
   for (const size of benchmarkDatasetSizes) {
     test(`${size}k sequences`, async () => {
       if (!DG.Test.isInBenchmark)

package/src/tests/core.ts

@@ -1,7 +1,7 @@
 import * as grok from 'datagrok-api/grok';
 import * as DG from 'datagrok-api/dg';
 
-import {awaitCheck, category, delay, expect, test} from '@datagrok-libraries/utils/src/test';
+import {awaitCheck, before, category, delay, expect, test} from '@datagrok-libraries/utils/src/test';
 
 import {_package} from '../package-test';
 import {startAnalysis} from '../widgets/peptides';
@@ -10,10 +10,13 @@ import * as C from '../utils/constants';
 import {scaleActivity} from '../utils/misc';
 import {ALIGNMENT, ALPHABET, NOTATION, TAGS as bioTAGS} from '@datagrok-libraries/bio/src/utils/macromolecule';
 import {MonomerPosition} from '../viewers/sar-viewer';
+import {PeptideUtils} from '../peptideUtils';
 
 category('Core', () => {
   const alignedSequenceCol = 'AlignedSequence';
-
+  before(async () => {
+    await PeptideUtils.loadSeqHelper();
+  });
   let model: PeptidesModel | null = null;
   test('Start analysis: simple', async () => {
     const simpleActivityColName = 'IC50';

package/src/tests/misc.ts

@@ -5,6 +5,7 @@ import {before, category, expect, test} from '@datagrok-libraries/utils/src/test
 import {findMutations, MutationCliffsOptions} from '../utils/algorithms';
 import * as type from '../utils/types';
 import {extractColInfo} from '../utils/misc';
+import {PeptideUtils} from '../peptideUtils';
 
 category('Algorithms', () => {
   let activityCol: type.RawData;
@@ -13,6 +14,8 @@ category('Algorithms', () => {
   let targetCol: type.RawColumn;
 
   before(async () => {
+    await PeptideUtils.loadSeqHelper();
+
     activityCol = DG.Column.fromList('int', 'test', [1, 2, 5]).getRawData();
     monomerColumns = [
       DG.Column.fromList('string', '1', 'AAA'.split('')),

package/src/tests/model.ts

@@ -43,6 +43,7 @@ import {
 import {
   MonomerPosition,
 } from '../viewers/sar-viewer';
+import {PeptideUtils} from '../peptideUtils';
 
 category('Model: Settings', () => {
   let df: DG.DataFrame;
@@ -62,6 +63,7 @@ category('Model: Settings', () => {
   };
 
   before(async () => {
+    await PeptideUtils.loadSeqHelper();
     df = DG.DataFrame.fromCsv(await _package.files.readAsText('tests/HELM_small.csv'));
     activityCol = df.getCol(TEST_COLUMN_NAMES.ACTIVITY);
     sequenceCol = df.getCol(TEST_COLUMN_NAMES.SEQUENCE);

package/src/tests/table-view.ts

@@ -10,6 +10,7 @@ import {COLUMNS_NAMES, SCALING_METHODS} from '../utils/constants';
 import {TEST_COLUMN_NAMES} from './utils';
 import {CLUSTER_TYPE, LogoSummaryTable} from '../viewers/logo-summary';
 import {MonomerPosition} from '../viewers/sar-viewer';
+import {PeptideUtils} from '../peptideUtils';
 
 category('Table view', () => {
   let df: DG.DataFrame;
@@ -26,6 +27,8 @@ category('Table view', () => {
   const secondCluster = {monomerOrCluster: '1', positionOrClusterType: CLUSTER_TYPE.ORIGINAL, count: 3};
 
   before(async () => {
+    await PeptideUtils.loadSeqHelper();
+
     df = DG.DataFrame.fromCsv(await _package.files.readAsText('tests/HELM_small.csv'));
     activityCol = df.getCol(TEST_COLUMN_NAMES.ACTIVITY);
     sequenceCol = df.getCol(TEST_COLUMN_NAMES.SEQUENCE);

package/src/tests/viewers.ts

@@ -12,11 +12,14 @@ import {CLUSTER_TYPE, LogoSummaryTable, LST_PROPERTIES} from '../viewers/logo-su
 import {PositionHeight} from '@datagrok-libraries/bio/src/viewers/web-logo';
 import {TEST_COLUMN_NAMES} from './utils';
 import {showTooltip} from '../utils/tooltips';
+import {PeptideUtils} from '../peptideUtils';
 
 category('Viewers: Basic', () => {
   let df: DG.DataFrame;
 
   before(async () => {
+    await PeptideUtils.loadSeqHelper();
+
     df = DG.DataFrame.fromCsv(await _package.files.readAsText('tests/HELM_small.csv'));
     await delay(500);
   });

package/src/tests/widgets.ts

@@ -15,6 +15,7 @@ import {TEST_COLUMN_NAMES} from './utils';
 import wu from 'wu';
 import {CLUSTER_TYPE, LogoSummaryTable} from '../viewers/logo-summary';
 import {MonomerPosition} from '../viewers/sar-viewer';
+import {PeptideUtils} from '../peptideUtils';
 
 category('Widgets: Settings', () => {
   let df: DG.DataFrame;
@@ -25,6 +26,8 @@ category('Widgets: Settings', () => {
   let scaledActivityCol: DG.Column<number>;
 
   before(async () => {
+    await PeptideUtils.loadSeqHelper();
+
     df = DG.DataFrame.fromCsv(await _package.files.readAsText('tests/HELM_small.csv'));
     activityCol = df.getCol(TEST_COLUMN_NAMES.ACTIVITY);
     sequenceCol = df.getCol(TEST_COLUMN_NAMES.SEQUENCE);
@@ -70,6 +73,8 @@ category('Widgets: Distribution panel', () => {
   let scaledActivityCol: DG.Column<number>;
 
   before(async () => {
+    await PeptideUtils.loadSeqHelper();
+
     df = DG.DataFrame.fromCsv(await _package.files.readAsText('tests/HELM_small.csv'));
     activityCol = df.getCol(TEST_COLUMN_NAMES.ACTIVITY);
     sequenceCol = df.getCol(TEST_COLUMN_NAMES.SEQUENCE);
@@ -109,6 +114,8 @@ category('Widgets: Mutation cliffs', () => {
   let scaledActivityCol: DG.Column<number>;
 
   before(async () => {
+    await PeptideUtils.loadSeqHelper();
+
     df = DG.DataFrame.fromCsv(await _package.files.readAsText('tests/HELM_small.csv'));
     activityCol = df.getCol(TEST_COLUMN_NAMES.ACTIVITY);
     sequenceCol = df.getCol(TEST_COLUMN_NAMES.SEQUENCE);
@@ -152,6 +159,8 @@ category('Widgets: Actions', () => {
   let scaledActivityCol: DG.Column<number>;
 
   before(async () => {
+    await PeptideUtils.loadSeqHelper();
+
     df = DG.DataFrame.fromCsv(await _package.files.readAsText('tests/HELM_small.csv'));
     await df.meta.detectSemanticTypes();
     activityCol = df.getCol(TEST_COLUMN_NAMES.ACTIVITY);

package/src/viewers/logo-summary.ts

@@ -34,6 +34,7 @@ import {_package} from '../package';
 import {calculateClusterStatistics} from '../utils/algorithms';
 import {splitAlignedSequences} from '@datagrok-libraries/bio/src/utils/splitter';
 import {SARViewer} from './sar-viewer';
+import {PeptideUtils} from '../peptideUtils';
 
 const getAggregatedColName = (aggF: string, colName: string): string => `${aggF}(${colName})`;
 
@@ -229,7 +230,8 @@ export class LogoSummaryTable extends DG.JsViewer implements ILogoSummaryTable {
 
     this._positionColumns ??= getSharedPositionColumns(VIEWER_TYPE.SEQUENCE_VARIABILITY_MAP) ??
       getSharedPositionColumns(VIEWER_TYPE.MOST_POTENT_RESIDUES) ??
-      splitAlignedSequences(this.dataFrame.getCol(this.sequenceColumnName)).columns.toList();
+      splitAlignedSequences(this.dataFrame.getCol(this.sequenceColumnName),
+        PeptideUtils.getSeqHelper()).columns.toList();
     return this._positionColumns!;
   }
 

package/src/viewers/sar-viewer.ts

@@ -40,6 +40,7 @@ import {TAGS as bioTAGS} from '@datagrok-libraries/bio/src/utils/macromolecule/c
 import {ALPHABET} from '@datagrok-libraries/bio/src/utils/macromolecule';
 import {getMonomerLibHelper} from '@datagrok-libraries/bio/src/monomer-works/monomer-utils';
 import {PolymerTypes} from '@datagrok-libraries/bio/src/helm/consts';
+import {PeptideUtils} from '../peptideUtils';
 
 export enum SELECTION_MODE {
   MUTATION_CLIFFS = 'Mutation Cliffs',
@@ -231,7 +232,7 @@ export abstract class SARViewer extends DG.JsViewer implements ISARViewer {
 
 
     this._positionColumns ??= getSharedPositionColumns(VIEWER_TYPE.LOGO_SUMMARY_TABLE) ??
-      splitAlignedSequences(this.dataFrame.getCol(this.sequenceColumnName)).columns.toList();
+      splitAlignedSequences(this.dataFrame.getCol(this.sequenceColumnName), PeptideUtils.getSeqHelper()).columns.toList();
     return this._positionColumns!;
   }
 

package/src/widgets/manual-alignment.ts

@@ -5,7 +5,7 @@ import * as DG from 'datagrok-api/dg';
 import $ from 'cash-dom';
 import '../styles.css';
 import {PeptidesModel} from '../model';
-import {SeqHandler} from '@datagrok-libraries/bio/src/utils/seq-handler';
+import {PeptideUtils} from '../peptideUtils';
 
 /**
  * Allows to edit sequence and apply changes to the table and analysis.
@@ -18,9 +18,9 @@ export function manualAlignmentWidget(alignedSequenceCol: DG.Column<string>, cur
   $(sequenceInput.root).addClass('pep-textinput');
 
   const applyChangesBtn = ui.button('Apply', async () => {
-    const sh = SeqHandler.forColumn(alignedSequenceCol);
+    const sh = PeptideUtils.getSeqHelper().getSeqHandler(alignedSequenceCol);
     const newSequence = sequenceInput.value;
-    const splitSequence = sh.split(newSequence);
+    const splitSequence = sh.splitter(newSequence);
     const affectedRowIndex = currentDf.currentRowIdx;
     alignedSequenceCol.set(affectedRowIndex, newSequence);
     for (let i = 0; i < splitSequence.length; i++) {