@datagrok/bio 2.11.2 → 2.11.3

package/package.json

@@ -5,7 +5,7 @@
     "name": "Leonid Stolbov",
     "email": "lstolbov@datagrok.ai"
   },
-  "version": "2.11.2",
+  "version": "2.11.3",
   "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",

package/src/package.ts

@@ -7,7 +7,6 @@ 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';
@@ -51,9 +50,6 @@ import {BioSubstructureFilter} from './widgets/bio-substructure-filter';
 import {WebLogoViewer} from './viewers/web-logo-viewer';
 import {
   MonomerLibHelper,
-  getUserLibSettings,
-  setUserLibSetting,
-  getLibFileNameList,
   getLibraryPanelUI
 } from './utils/monomer-lib';
 import {demoBio01UI} from './demo/bio01-similarity-diversity';
@@ -72,12 +68,11 @@ import {PackageSettingsEditorWidget} from './widgets/package-settings-editor-wid
 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/enumerator-tools';
+import {getPolyToolDialog} from './utils/poly-tool/ui';
 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';
-import {HelmToMolfileConverter} from './utils/helm-to-molfile';
 import {sequenceToMolfile} from './utils/sequence-to-mol';
 import {errInfo} from './utils/err-info';
 
@@ -459,7 +454,7 @@ export async function activityCliffs(df: DG.DataFrame, macroMolecule: DG.Column<
     Do you want to continue?`))
         .onOK(async () => {
           const progressBar = DG.TaskBarProgressIndicator.create(`Running sequence activity cliffs ...`);
-          runCliffs().then((res) => resolve(res)).catch((err) => reject(err)).finally(() => { progressBar.close();});
+          runCliffs().then((res) => resolve(res)).catch((err) => reject(err)).finally(() => { progressBar.close(); });
         })
         .show();
     } else {

package/src/utils/helm-to-molfile.ts

@@ -43,18 +43,29 @@ type PositionInBonds = {
 
 /** Translate HELM column into molfile column and append to the dataframe */
 export async function helm2mol(df: DG.DataFrame, helmCol: DG.Column<string>): Promise<void> {
-  // const df = await _package.files.readCsv('./samples/helm-to-molfile.csv');
-  // grok.shell.addTableView(df);
-  // const helmCol = df.col('HELM');
-  // if (!helmCol) {
-  //   grok.shell.error('HELM column not found');
-  //   return;
-  // }
+  const molCol = await getMolColumnFromHelm(df, helmCol);
+  df.columns.add(molCol, true);
+  await grok.data.detectSemanticTypes(df);
+}
+
+
+/** Translate HELM column into molfile column and append to the dataframe */
+export async function getMolColumnFromHelm(
+  df: DG.DataFrame, helmCol: DG.Column<string>
+): Promise<DG.Column<string>> {
   const converter = new HelmToMolfileConverter(helmCol, df);
   const molCol = await converter.convertToRdKitBeautifiedMolfileColumn();
   molCol.semType = DG.SEMTYPE.MOLECULE;
-  df.columns.add(molCol, true);
-  await grok.data.detectSemanticTypes(df);
+  return molCol;
+}
+
+export async function getSmilesColumnFromHelm(
+  df: DG.DataFrame, helmCol: DG.Column<string>
+): Promise<DG.Column<string>> {
+  const converter = new HelmToMolfileConverter(helmCol, df);
+  const smilesCol = await converter.convertToSmiles();
+  smilesCol.semType = DG.SEMTYPE.MOLECULE;
+  return smilesCol;
 }
 
 export class HelmToMolfileConverter {
@@ -62,9 +73,24 @@ export class HelmToMolfileConverter {
     this.helmColumn = helmColumn;
   }
 
-  async convertToRdKitBeautifiedMolfileColumn(): Promise<DG.Column<string>> {
+  async convertToSmiles(): Promise<DG.Column<string>> {
+    const smiles = await this.getSmilesList();
+    const columnName = this.df.columns.getUnusedName(`smiles(${this.helmColumn.name})`);
+    return DG.Column.fromStrings(columnName, smiles.map((molecule) => {
+      if (molecule === null)
+        return '';
+      return molecule;
+    }));
+  }
+
+  private async getSmilesList(): Promise<string[]> {
     const molfilesV2K = (await this.convertToMolfileV2KColumn()).toList();
     const smiles = molfilesV2K.map((mol) => DG.chem.convert(mol, DG.chem.Notation.MolBlock, DG.chem.Notation.Smiles));
+    return smiles;
+  }
+
+  async convertToRdKitBeautifiedMolfileColumn(): Promise<DG.Column<string>> {
+    const smiles = await this.getSmilesList();
     const rdKitModule: RDModule = await grok.functions.call('Chem:getRdKitModule');
     const beautifiedMols = smiles.map((item) =>{
       if (item === '')
@@ -75,8 +101,7 @@ export class HelmToMolfileConverter {
       mol.normalize_depiction(1);
       mol.straighten_depiction(true);
       return mol;
-    }
-    );
+    });
     const columnName = this.df.columns.getUnusedName(`molfile(${this.helmColumn.name})`);
     return DG.Column.fromStrings(columnName, beautifiedMols.map((mol) => {
       if (mol === null)

package/src/utils/poly-tool/{enumerator-tools.ts → transformation.ts}

@@ -1,17 +1,14 @@
-
 import * as grok from 'datagrok-api/grok';
 import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
 
 import {NOTATION} from '@datagrok-libraries/bio/src/utils/macromolecule';
 import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
-import {HELM_POLYMER_TYPE} from '@datagrok-libraries/bio/src/utils/const';
-import {MonomerLibHelper} from '../../utils/monomer-lib';
 import {_package} from '../../package';
 import {addCommonTags} from './utils';
-import * as rxjs from 'rxjs';
-import {HELM_WRAPPER, ALL_MONOMERS, CYCLIZATION_TYPE, TRANSFORMATION_TYPE} from './const';
+import {HELM_WRAPPER, ALL_MONOMERS, CYCLIZATION_TYPE} from './const';
 import {MetaData, ConnectionData} from './types';
+import {getMolColumnFromHelm} from '../helm-to-molfile';
 
 abstract class TransformationBase {
   constructor(helmColumn: DG.Column<string>, meta: MetaData) {
@@ -44,15 +41,21 @@ class TransformationNCys extends TransformationBase {
   }
 
   protected hasTerminals(helm: string): boolean {
-    if (! helm.includes(this.rightTerminal + HELM_WRAPPER.RIGHT))
-      return false;
-    if (this.leftTerminal === ALL_MONOMERS)
-      return true;
-    return helm.includes(HELM_WRAPPER.LEFT + this.leftTerminal);
+    // if (! helm.includes(this.rightTerminal + HELM_WRAPPER.RIGHT))
+    //   return false;
+    // if (this.leftTerminal === ALL_MONOMERS)
+    //   return true;
+    // return helm.includes(HELM_WRAPPER.LEFT + this.leftTerminal);
+    const positions = this.getLinkedPositions(helm);
+    return positions.every((el) => el > 0);
   }
 
   protected getLinkedPositions(helm: string): [number, number] {
-    return [1, getNumberOfMonomers(helm)];
+    const seq = helm.replace(HELM_WRAPPER.LEFT, '').replace(HELM_WRAPPER.RIGHT, '');
+    const monomers = seq.split('.');
+    const start = 0;
+    const end = monomers.findIndex((el, idx) => el === this.rightTerminal && idx > start);
+    return [start + 1, end + 1];
   }
 
   protected getTransformedHelm(helm: string): string {
@@ -145,133 +148,28 @@ function getHelmCycle(helm: string, source: ConnectionData, target: ConnectionDa
   );
 }
 
-async function addTransformedColumn(
-  molColumn: DG.Column<string>, meta: MetaData
+export async function addTransformedColumn(
+  molColumn: DG.Column<string>, meta: MetaData, addHelm: boolean
 ): Promise<void> {
   const df = molColumn.dataFrame;
   const uh = UnitsHandler.getOrCreate(molColumn);
   const sourceHelmCol = uh.convert(NOTATION.HELM);
   const pt = PolymerTransformation.getInstance(sourceHelmCol, meta);
   const targetList = pt.transform();
-  const colName = df.columns.getUnusedName(`${meta.transformationType}(` + molColumn.name + ')');
-  const targetHelmCol = DG.Column.fromList('string', colName, targetList);
+  const helmColName = df.columns.getUnusedName(`${meta.transformationType}(` + molColumn.name + ')');
+  const targetHelmCol = DG.Column.fromList('string', helmColName, targetList);
 
   addCommonTags(targetHelmCol);
   targetHelmCol.setTag('units', NOTATION.HELM);
-  targetHelmCol.setTag('cell.renderer', 'helm');
 
-  df.columns.add(targetHelmCol);
-  await grok.data.detectSemanticTypes(df);
-}
-
-export function getPolyToolDialog(): DG.Dialog {
-  function getMonomerList(cyclizationType: CYCLIZATION_TYPE): string[] {
-    if (cyclizationType === cyclizationTypes[0]) {
-      return [ALL_MONOMERS].concat(
-        monomerLib.getMonomerSymbolsByType(HELM_POLYMER_TYPE.PEPTIDE)
-      );
-    }
-    if (cyclizationType === cyclizationTypes[1]) {
-      return [ALL_MONOMERS].concat(
-        monomerLib.getMonomerSymbolsByRGroup(3, HELM_POLYMER_TYPE.PEPTIDE)
-      );
-    }
-    return ['C'];
-  }
+  const molCol = await getMolColumnFromHelm(df, targetHelmCol);
+  molCol.name = df.columns.getUnusedName(`${meta.transformationType}_molfile(` + molColumn.name + ')');
 
-  function updateMonomerList(): void {
-    if (cyclizationTypeChoice.value === CYCLIZATION_TYPE.NCys) {
-      monomerList1 = getMonomerList(CYCLIZATION_TYPE.NO);
-      monomerList2 = getMonomerList(CYCLIZATION_TYPE.NCys);
-    } else {
-      monomerList1 = getMonomerList(cyclizationTypeChoice.value as CYCLIZATION_TYPE);
-      monomerList2 = [...monomerList1];
-    }
-
-    leftTerminalChoice = ui.choiceInput(
-      'R1:', monomerList1[0], monomerList1, () => { onRGroupValueChange.next(); }
-    );
-    rightTerminalChoice = ui.choiceInput('R2:', monomerList2[0], monomerList2, () => { onRGroupValueChange.next(); });
-    onRGroupValueChange.next();
-    ui.empty(terminalControls);
-    [leftTerminalChoice, rightTerminalChoice].forEach((el) => { terminalControls.appendChild(el.root); });
+  if (addHelm) {
+    targetHelmCol.setTag('cell.renderer', 'helm');
+    df.columns.add(targetHelmCol);
   }
+  df.columns.add(molCol, true);
 
-  const onCyclizationChoice = new rxjs.Subject<string>();
-  const onRGroupValueChange = new rxjs.Subject<string>();
-  onCyclizationChoice.subscribe(() => {
-    meta.cyclizationType = cyclizationTypeChoice.value!;
-    updateMonomerList();
-  });
-  onRGroupValueChange.subscribe(() => {
-    meta.rightTerminal = rightTerminalChoice.value!;
-    meta.leftTerminal = leftTerminalChoice.value!;
-  });
-
-
-  const meta = {} as MetaData;
-  const transformations = [TRANSFORMATION_TYPE.CYCLIZATION];
-  const transformationChoice = ui.choiceInput(
-    'Modification', transformations[0], transformations, () => meta.transformationType = transformationChoice.value!
-  );
-
-  const cyclizationTypes = [CYCLIZATION_TYPE.NO, CYCLIZATION_TYPE.R3, CYCLIZATION_TYPE.NCys];
-  const cyclizationTypeChoice = ui.choiceInput(
-    'Type', cyclizationTypes[0], cyclizationTypes, () => { onCyclizationChoice.next(); }
-  );
-
-  const monomerLib = MonomerLibHelper.instance.getBioLib();
-  let monomerList1: string[] = [];
-  let monomerList2: string[] = [];
-  let leftTerminalChoice = ui.choiceInput(
-    'R1:', monomerList1[0], monomerList1, () => {
-      meta.leftTerminal = leftTerminalChoice.value!;
-    }
-  );
-  let rightTerminalChoice = ui.choiceInput('R2:', monomerList2[0], monomerList2, () => {
-    meta.rightTerminal = rightTerminalChoice.value!;
-  });
-  const terminalControls = ui.divV([leftTerminalChoice.root, rightTerminalChoice.root]);
-
-  function updateMeta() {
-    meta.cyclizationType = cyclizationTypeChoice.value!;
-    meta.leftTerminal = leftTerminalChoice.value!;
-    meta.rightTerminal = rightTerminalChoice.value!;
-    meta.transformationType = transformationChoice.value!;
-  }
-
-  updateMonomerList();
-
-  updateMeta();
-
-  const targetColumns = grok.shell.t.columns.bySemTypeAll(DG.SEMTYPE.MACROMOLECULE);
-  if (!targetColumns)
-    throw new Error('No dataframe with maceomolecule columns open');
-
-
-  const targetColumnInput = ui.columnInput(
-    'Column', grok.shell.t, targetColumns[0], null,
-    {filter: (col: DG.Column) => col.semType === DG.SEMTYPE.MACROMOLECULE}
-  );
-
-  const div = ui.div([
-    targetColumnInput,
-    transformationChoice,
-    cyclizationTypeChoice,
-    terminalControls,
-  ]);
-
-  const dialog = ui.dialog('Poly Tool')
-    .add(div)
-    .onOK(async () => {
-      const molCol = targetColumnInput.value;
-      if (!molCol) {
-        grok.shell.warning('No marcomolecule column chosen!');
-        return;
-      }
-      addTransformedColumn(molCol!, meta);
-    }
-    );
-
-  return dialog;
+  await grok.data.detectSemanticTypes(df);
 }

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

@@ -0,0 +1,125 @@
+/* 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_POLYMER_TYPE} from '@datagrok-libraries/bio/src/utils/const';
+import {MonomerLibHelper} from '../../utils/monomer-lib';
+import {ALL_MONOMERS, CYCLIZATION_TYPE, TRANSFORMATION_TYPE} from './const';
+import {addTransformedColumn} from './transformation';
+import * as rxjs from 'rxjs';
+import {MetaData} from './types';
+
+export function getPolyToolDialog(): DG.Dialog {
+  function getMonomerList(cyclizationType: CYCLIZATION_TYPE): string[] {
+    if (cyclizationType === cyclizationTypes[0]) {
+      return [ALL_MONOMERS].concat(
+        monomerLib.getMonomerSymbolsByType(HELM_POLYMER_TYPE.PEPTIDE)
+      );
+    }
+    if (cyclizationType === cyclizationTypes[1]) {
+      return [ALL_MONOMERS].concat(
+        monomerLib.getMonomerSymbolsByRGroup(3, HELM_POLYMER_TYPE.PEPTIDE)
+      );
+    }
+    return ['C'];
+  }
+
+  function updateMonomerList(): void {
+    if (cyclizationTypeChoice.value === CYCLIZATION_TYPE.NCys) {
+      monomerList1 = getMonomerList(CYCLIZATION_TYPE.NO);
+      monomerList2 = getMonomerList(CYCLIZATION_TYPE.NCys);
+    } else {
+      monomerList1 = getMonomerList(cyclizationTypeChoice.value as CYCLIZATION_TYPE);
+      monomerList2 = [...monomerList1];
+    }
+
+    leftTerminalChoice = ui.choiceInput(
+      'R1:', monomerList1[0], monomerList1, () => { onRGroupValueChange.next(); }
+    );
+    rightTerminalChoice = ui.choiceInput('R2:', monomerList2[0], monomerList2, () => { onRGroupValueChange.next(); });
+    onRGroupValueChange.next();
+    ui.empty(terminalControls);
+    [leftTerminalChoice, rightTerminalChoice].forEach((el) => { terminalControls.appendChild(el.root); });
+  }
+
+  function updateMeta() {
+    meta.cyclizationType = cyclizationTypeChoice.value!;
+    meta.leftTerminal = leftTerminalChoice.value!;
+    meta.rightTerminal = rightTerminalChoice.value!;
+    meta.transformationType = transformationChoice.value!;
+  }
+
+
+  const onCyclizationChoice = new rxjs.Subject<string>();
+  const onRGroupValueChange = new rxjs.Subject<string>();
+  onCyclizationChoice.subscribe(() => {
+    meta.cyclizationType = cyclizationTypeChoice.value!;
+    updateMonomerList();
+  });
+  onRGroupValueChange.subscribe(() => {
+    meta.rightTerminal = rightTerminalChoice.value!;
+    meta.leftTerminal = leftTerminalChoice.value!;
+  });
+
+  const meta = {} as MetaData;
+  const transformations = [TRANSFORMATION_TYPE.CYCLIZATION];
+  const transformationChoice = ui.choiceInput(
+    'Modification', transformations[0], transformations, () => meta.transformationType = transformationChoice.value!
+  );
+
+  const cyclizationTypes = [CYCLIZATION_TYPE.NO, CYCLIZATION_TYPE.R3, CYCLIZATION_TYPE.NCys];
+  const cyclizationTypeChoice = ui.choiceInput(
+    'Type', cyclizationTypes[2], cyclizationTypes, () => { onCyclizationChoice.next(); }
+  );
+
+  const monomerLib = MonomerLibHelper.instance.getBioLib();
+  let monomerList1: string[] = [];
+  let monomerList2: string[] = [];
+  let leftTerminalChoice = ui.choiceInput(
+    'R1:', monomerList1[0], monomerList1, () => {
+      meta.leftTerminal = leftTerminalChoice.value!;
+    }
+  );
+  let rightTerminalChoice = ui.choiceInput('R2:', monomerList2[0], monomerList2, () => {
+    meta.rightTerminal = rightTerminalChoice.value!;
+  });
+  const terminalControls = ui.divV([leftTerminalChoice.root, rightTerminalChoice.root]);
+  updateMonomerList();
+
+  updateMeta();
+
+  const targetColumns = grok.shell.t.columns.bySemTypeAll(DG.SEMTYPE.MACROMOLECULE);
+  if (!targetColumns)
+    throw new Error('No dataframe with maceomolecule columns open');
+
+  const targetColumnInput = ui.columnInput(
+    'Column', grok.shell.t, targetColumns[0], null,
+    {filter: (col: DG.Column) => col.semType === DG.SEMTYPE.MACROMOLECULE}
+  );
+
+  const generateHelmChoiceInput = ui.boolInput('Get HELM', true);
+  ui.tooltip.bind(generateHelmChoiceInput.root, 'Add HELM column');
+
+  const div = ui.div([
+    targetColumnInput,
+    transformationChoice,
+    cyclizationTypeChoice,
+    terminalControls,
+    generateHelmChoiceInput,
+  ]);
+
+  const dialog = ui.dialog('Poly Tool')
+    .add(div)
+    .onOK(async () => {
+      const molCol = targetColumnInput.value;
+      if (!molCol) {
+        grok.shell.warning('No marcomolecule column chosen!');
+        return;
+      }
+      addTransformedColumn(molCol!, meta, generateHelmChoiceInput.value!);
+    }
+    );
+
+  return dialog;
+}