@datagrok/bio 2.12.16 → 2.12.17

package/package.json

@@ -5,7 +5,7 @@
     "name": "Aleksandr Tanas",
     "email": "atanas@datagrok.ai"
   },
-  "version": "2.12.16",
+  "version": "2.12.17",
   "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",
@@ -34,12 +34,12 @@
   ],
   "dependencies": {
     "@biowasm/aioli": "^3.1.0",
-    "@datagrok-libraries/bio": "^5.40.8",
+    "@datagrok-libraries/bio": "^5.41.0",
     "@datagrok-libraries/chem-meta": "^1.2.5",
     "@datagrok-libraries/math": "^1.1.5",
     "@datagrok-libraries/ml": "^6.6.5",
     "@datagrok-libraries/tutorials": "^1.3.12",
-    "@datagrok-libraries/utils": "^4.2.0",
+    "@datagrok-libraries/utils": "^4.2.2",
     "@webgpu/types": "^0.1.40",
     "ajv": "^8.12.0",
     "ajv-errors": "^3.0.0",
@@ -55,9 +55,9 @@
     "wu": "latest"
   },
   "devDependencies": {
-    "@datagrok/chem": "^1.9.0",
-    "@datagrok/dendrogram": "^1.2.27",
-    "@datagrok/helm": "^2.1.30",
+    "@datagrok/chem": "^1.9.2",
+    "@datagrok/dendrogram": "^1.2.29",
+    "@datagrok/helm": "^2.1.34",
     "@types/node": "^17.0.24",
     "@types/wu": "latest",
     "@typescript-eslint/eslint-plugin": "latest",

package/src/package.ts

@@ -3,6 +3,8 @@ import * as grok from 'datagrok-api/grok';
 import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
 
+import '@datagrok-libraries/bio/src/types/helm';
+
 import {Options} from '@datagrok-libraries/utils/src/type-declarations';
 import {DimReductionBaseEditor, PreprocessFunctionReturnType}
   from '@datagrok-libraries/ml/src/functionEditors/dimensionality-reduction-editor';
@@ -55,13 +57,9 @@ import {SplitToMonomersFunctionEditor} from './function-edtiors/split-to-monomer
 import {splitToMonomersUI} from './utils/split-to-monomers';
 import {MonomerCellRenderer} from './utils/monomer-cell-renderer';
 import {BioPackage, BioPackageProperties} from './package-types';
-// import {PackageSettingsEditorWidget} from './widgets/package-settings-editor-widget';
 import {getCompositionAnalysisWidget} from './widgets/composition-analysis-widget';
 import {MacromoleculeColumnWidget} from './utils/macromolecule-column-widget';
 import {addCopyMenuUI} from './utils/context-menu';
-import {getPolyToolDialog} from './utils/poly-tool/ui';
-import {PolyToolCsvLibHandler} from './utils/poly-tool/csv-to-json-monomer-lib-converter';
-import {_setPeptideColumn} from './utils/poly-tool/utils';
 import {getRegionDo} from './utils/get-region';
 import {GetRegionApp} from './apps/get-region-app';
 import {GetRegionFuncEditor} from './utils/get-region-func-editor';
@@ -77,7 +75,8 @@ 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 {CyclizedNotationProvider} from './utils/poly-tool/cyclized';
+import {CyclizedNotationProvider} from './utils/cyclized';
+import {getMolColumnFromHelm} from './utils/helm-to-molfile/utils';
 
 export const _package = new BioPackage();
 
@@ -685,19 +684,6 @@ export function convertDialog() {
   convert(col);
 }
 
-//top-menu: Bio | Convert | PolyTool
-//name: polyTool
-//description: Perform cyclization of polymers
-export async function polyTool(): Promise<void> {
-  let dialog: DG.Dialog;
-  try {
-    dialog = await getPolyToolDialog();
-    dialog.show();
-  } catch (err: any) {
-    grok.shell.warning('To run PolyTool, open a dataframe with macromolecules');
-  }
-}
-
 //name: monomerCellRenderer
 //tags: cellRenderer
 //meta.cellType: Monomer
@@ -1010,25 +996,6 @@ export async function demoBioHelmMsaSequenceSpace(): Promise<void> {
   await demoBio05UI();
 }
 
-//name: polyToolColumnChoice
-//input: dataframe df [Input data table]
-//input: column macroMolecule
-export async function polyToolColumnChoice(df: DG.DataFrame, macroMolecule: DG.Column): Promise<void> {
-  _setPeptideColumn(macroMolecule);
-  await grok.data.detectSemanticTypes(df);
-}
-
-//name: createMonomerLibraryForPolyTool
-//input: file file
-export async function createMonomerLibraryForPolyTool(file: DG.FileInfo) {
-  const fileContent = await file.readAsString();
-  const libHandler = new PolyToolCsvLibHandler(file.fileName, fileContent);
-  const libObject = await libHandler.getJson();
-  const jsonFileName = file.fileName.replace(/\.csv$/, '.json');
-  const jsonFileContent = JSON.stringify(libObject, null, 2);
-  DG.Utils.download(jsonFileName, jsonFileContent);
-}
-
 //name: SDF to JSON Library
 //input: dataframe table
 export async function sdfToJsonLib(table: DG.DataFrame) {
@@ -1048,6 +1015,17 @@ export async function detectMacromoleculeProbe(file: DG.FileInfo, colName: strin
   await detectMacromoleculeProbeDo(csv, colName, probeCount);
 }
 
+//name: getMolFromHelm
+//input: dataframe df
+//input: column helmCol
+//input: bool chiralityEngine
+//output: column result
+export async function getMolFromHelm(
+  df: DG.DataFrame, helmCol: DG.Column<string>, chiralityEngine?: boolean
+): Promise<DG.Column<string>> {
+  return getMolColumnFromHelm(df, helmCol, chiralityEngine);
+}
+
 // -- Custom notation providers --
 
 //name: applyNotationProviderForCyclized

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

@@ -95,7 +95,7 @@ id3,QHIRE--LT
       const monLength: number = 3;
       const charWidth: number = 7;
       const sepWidth: number = 12;
-      const colTemp: MonomerPlacer = new MonomerPlacer(null, seqCol, () => {
+      const colTemp: MonomerPlacer = new MonomerPlacer(null, seqCol, _package.logger, () => {
         const sh = SeqHandler.forColumn(seqCol);
         return {
           seqHandler: sh,

package/src/utils/cell-renderer.ts

@@ -23,6 +23,7 @@ import {ISeqSplitted, SeqSplittedBase} from '@datagrok-libraries/bio/src/utils/m
 import {getSplitter} from '@datagrok-libraries/bio/src/utils/macromolecule/utils';
 import {errInfo} from '@datagrok-libraries/bio/src/utils/err-info';
 import {alphabetPolymerTypes, IMonomerLib} from '@datagrok-libraries/bio/src/types/index';
+import {getGridCellRendererBack} from '@datagrok-libraries/bio/src/utils/cell-renderer-back-base';
 
 import {
   Temps as mmcrTemps, Tags as mmcrTags,
@@ -63,27 +64,6 @@ type RendererGridCellTemp = {
   [mmcrTemps.monomerPlacer]: MonomerPlacer
 }
 
-function getRendererFridCellTempTemp(gridCell: DG.GridCell): RendererGridCellTemp {
-  /** Primarily store/get MonomerPlacer at GridColumn, fallback at (Table) Column for scatter plot tooltip  */
-  let temp: RendererGridCellTemp | null = null;
-
-  let gridCol: DG.GridColumn | null = null;
-  try { gridCol = gridCell.gridColumn; } catch { gridCol = null; }
-  temp = gridCol && gridCol.dart ? gridCol.temp as RendererGridCellTemp : null;
-
-  if (!temp) {
-    let tableCol: DG.Column | null = null;
-    try { tableCol = gridCell.cell.column; } catch { tableCol = null; }
-    if (!tableCol) {
-      const k = 42;
-    }
-    temp = tableCol ? tableCol.temp as RendererGridCellTemp : null;
-  }
-  if (temp === null)
-    throw new Error(`Monomer placer store (GridColumn or Column) not found.`);
-  return temp;
-}
-
 export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
   private padding: number = 5;
 
@@ -105,9 +85,9 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
     // if (gridCell.cell.column.getTag(bioTAGS.aligned) !== ALIGNMENT.SEQ_MSA)
     //   return;
 
-    const tableCol: DG.Column = gridCell.cell.column;
-    //const tableColTemp: TempType = tableCol.temp;
-    const seqColTemp: MonomerPlacer = getRendererFridCellTempTemp(gridCell)[mmcrTemps.monomerPlacer];
+    const [_gridCol, tableCol, temp] =
+      getGridCellRendererBack<string, MonomerPlacer>(gridCell);
+    const seqColTemp: MonomerPlacer = temp['rendererBack'];
     if (!seqColTemp) return; // Can do nothing without precalculated data
 
     const gridCellBounds: DG.Rect = gridCell.bounds;
@@ -121,7 +101,7 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
     const argsX = e.offsetX - gridCell.gridColumn.left + (gridCell.gridColumn.left - gridCellBounds.x);
     const left: number | null = seqColTemp.getPosition(gridCell.tableRowIndex!, argsX);
 
-    const seqCList: SeqSplittedBase = SeqHandler.forColumn(seqColTemp.col)
+    const seqCList: SeqSplittedBase = SeqHandler.forColumn(tableCol)
       .getSplitted(gridCell.tableRowIndex!).canonicals;
     if (left !== null && left < seqCList.length) {
       const monomerSymbol: string = seqCList[left];
@@ -190,9 +170,11 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
         (!isNaN(tagMaxMonomerLength) ? tagMaxMonomerLength : _package.properties?.MaxMonomerLength) ?? 4;
     }
 
-    let seqColTemp: MonomerPlacer = getRendererFridCellTempTemp(gridCell)[mmcrTemps.monomerPlacer];
+    const [gridCol, _tc, temp] =
+      getGridCellRendererBack<string, MonomerPlacer>(gridCell);
+    let seqColTemp: MonomerPlacer = temp['rendererBack'];
     if (!seqColTemp) {
-      seqColTemp = new MonomerPlacer(grid, tableCol,
+      seqColTemp = new MonomerPlacer(gridCol, tableCol, _package.logger,
         () => {
           const sh = SeqHandler.forColumn(tableCol);
           return {
@@ -217,7 +199,7 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
     const _maxIndex = maxLengthWords.length;
 
     // Store updated seqColTemp to the col temp
-    if (seqColTemp.updated) getRendererFridCellTempTemp(gridCell)[mmcrTemps.monomerPlacer] = seqColTemp;
+    if (seqColTemp.updated) temp['rendererBack'] = seqColTemp;
 
     g.save();
     try {

package/src/utils/{poly-tool/cyclized.ts → cyclized.ts}

@@ -1,8 +1,5 @@
-import * as grok from 'datagrok-api/grok';
-import * as ui from 'datagrok-api/ui';
-import * as DG from 'datagrok-api/dg';
-
-import {GAP_SYMBOL, INotationProvider, ISeqSplitted, SeqSplittedBase, SplitterFunc} from '@datagrok-libraries/bio/src/utils/macromolecule/types';
+import {GAP_SYMBOL, INotationProvider, ISeqSplitted, SeqSplittedBase, SplitterFunc}
+  from '@datagrok-libraries/bio/src/utils/macromolecule/types';
 import {getSplitterWithSeparator, StringListSeqSplitted} from '@datagrok-libraries/bio/src/utils/macromolecule/utils';
 import {GapOriginals} from '@datagrok-libraries/bio/src/utils/seq-handler';
 import {NOTATION} from '@datagrok-libraries/bio/src/utils/macromolecule';
@@ -33,9 +30,8 @@ export class CyclizedSeqSplitted extends StringListSeqSplitted {
     if (!this._canonicals) {
       const len = this.length;
       this._canonicals = new Array<string>(len);
-      for (let posIdx = 0; posIdx < len; ++posIdx) {
+      for (let posIdx = 0; posIdx < len; ++posIdx)
         this._canonicals[posIdx] = this.getCanonical(posIdx);
-      }
     }
     return this._canonicals;
   }

package/src/utils/monomer-lib/monomer-lib.ts

@@ -116,6 +116,14 @@ export class MonomerLib implements IMonomerLib {
     this._onChanged.next();
   }
 
+  getSummary(): string {
+    const monTypeList: string[] = this.getPolymerTypes();
+    const resStr: string = monTypeList.length == 0 ? 'empty' : monTypeList.map((monType) => {
+      return `${monType} ${this.getMonomerSymbolsByType(monType).length}`;
+    }).join('\n');
+    return resStr;
+  }
+
   getTooltip(polymerType: string, monomerSymbol: string): HTMLElement {
     // getTooltip(monomer: Monomer): HTMLElement;
     // getTooltip(monomerOrPolymerType: string | Monomer, symbol?: string): HTMLElement {
@@ -163,8 +171,12 @@ export class MonomerLib implements IMonomerLib {
         label('Source'),
         ui.divText(monomer.lib?.source ?? 'unknown', {classes: 'ui-input-text'}),
       ], {classes: 'ui-input-root'}));
-    } else
-      res.append(ui.divText('Monomer not found'));
+    } else {
+      res.append(ui.divV([
+        ui.divText(`Monomer '${monomerSymbol}' of type '${polymerType}' not found.`),
+        ui.divText('Open the Context Panel, then expand Manage Libraries'),
+      ]));
+    }
     return res;
   }
 }

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

@@ -2,14 +2,15 @@ import * as grok from 'datagrok-api/grok';
 import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
 
+import * as org from 'org';
 import $ from 'cash-dom';
-import {fromEvent, Observable, Subject, Unsubscribable} from 'rxjs';
+import {fromEvent, Unsubscribable} from 'rxjs';
 
-import {IHelmWebEditor, IWebEditorApp} from '@datagrok-libraries/bio/src/helm/types';
+import {IHelmWebEditor} from '@datagrok-libraries/bio/src/helm/types';
 import {getHelmHelper} from '@datagrok-libraries/bio/src/helm/helm-helper';
 import {ILogger} from '@datagrok-libraries/bio/src/utils/logger';
 import {errInfo} from '@datagrok-libraries/bio/src/utils/err-info';
-import {delay, testEvent} from '@datagrok-libraries/utils/src/test';
+import {delay} from '@datagrok-libraries/utils/src/test';
 
 import {updateDivInnerHTML} from '../utils/ui-utils';
 import {helmSubstructureSearch} from '../substructure-search/substructure-search';
@@ -54,7 +55,7 @@ export class HelmBioFilter extends BioFilterBase<BioFilterProps> /* implements I
       this.logger.warning('TEST: HelmBioFilter.init().sync() waitForElementInDom ready');
       this.updateFilterPanel();
       let webEditorHost: HTMLDivElement | null;
-      let webEditorApp: IWebEditorApp | null;
+      let webEditorApp: org.helm.IWebEditorApp | null;
       // TODO: Unsubscribe 'click' and 'sizeChanged'
       this.viewSubs.push(fromEvent(this._filterPanel, 'click').subscribe(() => {
         webEditorHost = ui.div();

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

@@ -16,7 +16,6 @@ import {TAGS as bioTAGS, NOTATION} from '@datagrok-libraries/bio/src/utils/macro
 import {errInfo} from '@datagrok-libraries/bio/src/utils/err-info';
 import {delay, testEvent} from '@datagrok-libraries/utils/src/test';
 import {getHelmHelper} from '@datagrok-libraries/bio/src/helm/helm-helper';
-import {IHelmWebEditor, IWebEditorApp} from '@datagrok-libraries/bio/src/helm/types';
 import {SeqHandler} from '@datagrok-libraries/bio/src/utils/seq-handler';
 import {IRenderer} from '@datagrok-libraries/bio/src/types/renderer';
 import {ILogger} from '@datagrok-libraries/bio/src/utils/logger';

package/webpack.config.js

@@ -41,6 +41,8 @@ module.exports = {
     'cash-dom': '$',
     'dayjs': 'dayjs',
     'wu': 'wu',
+    'scil': 'scil',
+    'org': 'org',
   },
   output: {
     filename: '[name].js',

package/src/utils/poly-tool/const.ts

@@ -1,40 +0,0 @@
-import {HELM_REQUIRED_FIELD} from '@datagrok-libraries/bio/src/utils/const';
-
-export const ALL_MONOMERS = '<All>';
-
-export const enum TRANSFORMATION_TYPE {
-  CYCLIZATION = 'Cyclization',
-}
-
-export const enum CYCLIZATION_TYPE {
-  NO = 'N-O',
-  NCys = 'N-Cys',
-  R3 = 'R3-R3',
-}
-
-export const helmFieldsToPolyToolInputFields = {
-  [HELM_REQUIRED_FIELD.SYMBOL]: 'Short Name',
-  [HELM_REQUIRED_FIELD.NAME]: 'Medium Name',
-  [HELM_REQUIRED_FIELD.SMILES]: 'SMILES',
-};
-
-export const R_GROUP_BLOCK_DUMMY = [
-  {
-    'capGroupSMILES': '[*:1][H]',
-    'alternateId': 'R1-H',
-    'capGroupName': 'H',
-    'label': 'R1'
-  },
-  {
-    'capGroupSMILES': 'O[*:2]',
-    'alternateId': 'R2-OH',
-    'capGroupName': 'OH',
-    'label': 'R2'
-  },
-  {
-    'capGroupSMILES': '[*:3][H]',
-    'alternateId': 'R3-H',
-    'capGroupName': 'H',
-    'label': 'R3'
-  }
-];

package/src/utils/poly-tool/csv-to-json-monomer-lib-converter.ts

@@ -1,40 +0,0 @@
-import * as DG from 'datagrok-api/dg';
-
-import {PolyToolMonomerLibHandler} from './monomer-lib-handler';
-
-/** Handler of custom monomer libs for PolyTool  */
-export class PolyToolCsvLibHandler {
-  constructor(private fileName: string, private fileContent: string) {
-    this.validateFileType();
-    const df = DG.DataFrame.fromCsv(this.fileContent);
-    const json = this.toJson(df);
-    this.polyToolMonomerLib = new PolyToolMonomerLibHandler(json);
-    this.validateContent();
-  }
-
-  private polyToolMonomerLib: PolyToolMonomerLibHandler;
-
-  async getJson(): Promise<any> {
-    const rawLibData = this.polyToolMonomerLib.getJsonMonomerLib();
-    return rawLibData;
-  }
-
-  private toJson(df: DG.DataFrame): any[] {
-    return Array.from({length: df.rowCount}, (_, idx) =>
-      df.columns.names().reduce((entry: { [key: string]: any }, colName) => {
-        entry[colName] = df.get(colName, idx);
-        return entry;
-      }, {})
-    );
-  }
-
-  private validateFileType(): void {
-    if (!this.fileName.endsWith('.csv'))
-      throw new Error(`File ${this.fileName} is not an CSV file`);
-  }
-
-  private validateContent(): void {
-    if (!this.polyToolMonomerLib.isValid())
-      throw new Error('Invalid format of CSV monomer lib');
-  }
-}

package/src/utils/poly-tool/monomer-lib-handler.ts

@@ -1,115 +0,0 @@
-/* Do not change these import lines to match external modules in webpack configuration */
-import * as grok from 'datagrok-api/grok';
-import * as ui from 'datagrok-api/ui';
-import * as DG from 'datagrok-api/dg';
-
-import {HELM_FIELDS, DUMMY_MONOMER} from '@datagrok-libraries/bio/src/utils/const';
-import {
-  helmFieldsToPolyToolInputFields, R_GROUP_BLOCK_DUMMY
-} from './const';
-import {Monomer, RGroup} from '@datagrok-libraries/bio/src/types/index';
-
-export class PolyToolMonomerLibHandler {
-  constructor(private rawLib: any[]) { }
-
-  isValid(): boolean {
-    return this.rawLib.every((entry) => {
-      return typeof entry === 'object' &&
-        Object.values(helmFieldsToPolyToolInputFields).every((field) => {
-          return field in entry &&
-            typeof entry[field] === 'string';
-        });
-    });
-  }
-
-  getJsonMonomerLib(): any {
-    const resultLib: any[] = [];
-    this.rawLib.forEach((rawMonomer) => {
-      const monomer = this.prepareMonomer(rawMonomer);
-      resultLib.push(monomer);
-    });
-    return resultLib;
-  }
-
-  private prepareMonomer(rawMonomer: any): Monomer {
-    const monomer: Monomer = {...DUMMY_MONOMER};
-
-    Object.entries(helmFieldsToPolyToolInputFields).forEach(([key, value]) => {
-      const monomerSymbol = rawMonomer[value] as string;
-      //@ts-ignore
-      monomer[key] = monomerSymbol;
-    });
-
-    let key = HELM_FIELDS.SMILES;
-    const rawSmiles = rawMonomer[helmFieldsToPolyToolInputFields[key]];
-    const smilesHandler = new SmilesHandler(rawSmiles);
-    const smiles = smilesHandler.getCappedSmiles();
-    monomer[key] = smiles;
-
-    key = HELM_FIELDS.RGROUPS;
-    monomer[key] = RGroupHandler.getRGroups(smilesHandler.getNumberOfRGroups());
-
-    key = HELM_FIELDS.MOLFILE;
-    monomer[key] = new MolBlockHandler(smilesHandler.getSmilesWithRGroups()).getMolfile();
-
-    return monomer;
-  }
-}
-
-class SmilesHandler {
-  constructor(rawSmiles: string) {
-    const regex = /\[R(\d+)\]/g;
-    let i = 0;
-    this.smilesWithRGroups = rawSmiles.replace(regex, (_, capturedDigit) => { ++i; return `[${capturedDigit}*]`; });
-    this.numberOfRGroups = i;
-  }
-
-  private numberOfRGroups: number;
-  private smilesWithRGroups: string;
-
-  getSmilesWithRGroups(): string {
-    return this.smilesWithRGroups;
-  }
-
-  getCappedSmiles(): string {
-    const smiles = this.capRGroups();
-    return smiles;
-  }
-
-  getNumberOfRGroups(): number {
-    return this.numberOfRGroups;
-  }
-
-  private capRGroups(): string {
-    let result = this.smilesWithRGroups.replace('[1*]', '[H:1]');
-    result = result.replace('[2*]', '[OH:2]');
-    return result.replace('[3*]', '[H:3]');
-  }
-}
-
-class RGroupHandler {
-  private constructor() {};
-
-  static getRGroups(numberOfRGroups: number): RGroup[] {
-    return R_GROUP_BLOCK_DUMMY.slice(0, numberOfRGroups);
-  }
-}
-
-class MolBlockHandler {
-  constructor(private smilesWithRGroups: string) { }
-
-  getMolfile(): string {
-    let molfile = DG.chem.convert(this.smilesWithRGroups, DG.chem.Notation.Smiles, DG.chem.Notation.MolBlock);
-    molfile = this.restoreRGPLine(molfile);
-    molfile = this.fixRGroupSymbols(molfile);
-    return molfile;
-  }
-
-  private restoreRGPLine(rawMolfile: string): string {
-    return rawMolfile.replace('M  ISO', 'M  RGP');
-  }
-
-  private fixRGroupSymbols(molfile: string): string {
-    return molfile.replace(/\bR\b/g, 'R#');
-  }
-}