@datagrok/bio 2.23.0 → 2.23.2

package/package.json

@@ -5,7 +5,7 @@
     "name": "Davit Rizhinashvili",
     "email": "drizhinashvili@datagrok.ai"
   },
-  "version": "2.23.0",
+  "version": "2.23.2",
   "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",
@@ -44,12 +44,12 @@
   ],
   "dependencies": {
     "@biowasm/aioli": "^3.1.0",
-    "@datagrok-libraries/bio": "^5.55.0",
-    "@datagrok-libraries/chem-meta": "^1.2.7",
+    "@datagrok-libraries/bio": "^5.55.1",
+    "@datagrok-libraries/chem-meta": "^1.2.9",
     "@datagrok-libraries/math": "^1.2.6",
     "@datagrok-libraries/ml": "^6.10.6",
-    "@datagrok-libraries/tutorials": "^1.6.1",
-    "@datagrok-libraries/utils": "^4.6.5",
+    "@datagrok-libraries/tutorials": "^1.7.4",
+    "@datagrok-libraries/utils": "^4.6.9",
     "@webgpu/types": "^0.1.40",
     "ajv": "^8.12.0",
     "ajv-errors": "^3.0.0",
@@ -65,7 +65,7 @@
     "wu": "^2.1.0"
   },
   "devDependencies": {
-    "@datagrok-libraries/helm-web-editor": "^1.1.14",
+    "@datagrok-libraries/helm-web-editor": "^1.1.16",
     "@datagrok-libraries/js-draw-lite": "^0.0.10",
     "@datagrok/chem": "^1.15.0",
     "@datagrok/dendrogram": "^1.2.33",

package/src/package-api.ts

@@ -98,6 +98,14 @@ export namespace funcs {
     return await grok.functions.call('Bio:SeparatorSequenceCellRenderer', {});
   }
 
+  export async function bilnSequenceCellRenderer(): Promise<any> {
+    return await grok.functions.call('Bio:BilnSequenceCellRenderer', {});
+  }
+
+  export async function refineNotationProviderForBiln(col: DG.Column , stats: any , separator?: string | null): Promise<boolean> {
+    return await grok.functions.call('Bio:RefineNotationProviderForBiln', { col, stats, separator });
+  }
+
   export async function macroMolColumnPropertyPanel(molColumn: DG.Column ): Promise<any> {
     return await grok.functions.call('Bio:MacroMolColumnPropertyPanel', { molColumn });
   }

package/src/tests/pepsea-tests.ts

@@ -35,7 +35,7 @@ category('PepSeA', () => {
     const tgtMsaCol = df.getCol('MSA');
     for (let i = 0; i < resMsaCol!.length; ++i)
       expect(resMsaCol!.get(i) == tgtMsaCol.get(i), true);
-  }, {timeout: 60000 /* docker */, stressTest: true, skipReason: 'Fails in docker'});
+  }, {timeout: 60000 /* docker */, skipReason: 'Fails in docker'});
 
   test('stderr', async () => {
     const logger = new TestLogger();
@@ -45,7 +45,7 @@ category('PepSeA', () => {
     const tgtMsaCol = df.getCol('MSA');
     expectArray(resMsaCol!.toList(), tgtMsaCol.toList());
     expect(logger.warningList[0].message, pepseaStderrWarningList);
-  }, {timeout: 60000 /* docker */, stressTest: true, skipReason: 'Fails in docker'});
+  }, {timeout: 60000 /* docker */, skipReason: 'Fails in docker'});
 
   test('error', async () => {
     const logger = new TestLogger();

package/src/utils/convert.ts

@@ -48,7 +48,7 @@ export function convert(col: DG.Column<string> | undefined, seqHelper: ISeqHelpe
     if (currentNotation === NOTATION.HELM)
       separatorInput.value = '/'; // helm monomers can have - in the name like D-aThr;
     dialogHeader.textContent = 'Current notation: ' + currentNotation;
-    filteredNotations = notations;//.filter((e) => e !== currentNotation); TEMPORARY DO NOT FORGET TO UNCOMMENT
+    filteredNotations = notations.filter((e) => e !== currentNotation);
     targetNotationInput = ui.input.choice('Convert to', {
       value: filteredNotations[0], items: filteredNotations,
       onValueChanged: toggleSeparator
@@ -71,7 +71,7 @@ export function convert(col: DG.Column<string> | undefined, seqHelper: ISeqHelpe
   });
 
   const separatorArray = ['-', '.', '/'];
-  let filteredNotations = notations;//.filter((e) => e !== currentNotation); // TEMPORARY DO NOT FORGET TO UNCOMMENT
+  let filteredNotations = notations.filter((e) => e !== currentNotation);
 
   const separatorInput = ui.input.choice('Separator', {value: separatorArray[0], items: separatorArray});
 

package/src/utils/helm-to-molfile/converter/connection-list.ts

@@ -1,3 +1,4 @@
+/* eslint-disable max-len */
 import {HELM_POLYMER_TYPE} from '@datagrok-libraries/bio/src/utils/const';
 import {HELM_ITEM_SEPARATOR} from './const';
 import {Bond} from './types';
@@ -12,7 +13,7 @@ export class ConnectionList {
   public connectionItems: string[];
 
   private validateConnectionItem(connectionItem: string): void {
-    const allowedType = `(${HELM_POLYMER_TYPE.PEPTIDE}|${HELM_POLYMER_TYPE.RNA})`;
+    const allowedType = `(${HELM_POLYMER_TYPE.PEPTIDE}|${HELM_POLYMER_TYPE.RNA}|${HELM_POLYMER_TYPE.CHEM}|${HELM_POLYMER_TYPE.BLOB})`;
     const regex = new RegExp(`${allowedType}[0-9]+,${allowedType}[0-9]+,[0-9]+:R[0-9]+-[0-9]+:R[0-9]+`, 'g');
     if (!connectionItem.match(regex))
       throw new Error(`Cannot parse connection item from ${connectionItem}`);

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

@@ -55,7 +55,7 @@ export class Helm {
   private getSimplePolymerByMonomerIdx(monomerGlobalIdx: number): SimplePolymer {
     const shifts = this.getMonomerIdxShifts();
     const shiftValues = Object.values(shifts);
-    const lowerBound = shiftValues.sort((a, b) => a - b).find(
+    const lowerBound = shiftValues.sort((a, b) => b - a).find( // find the largest shift not exceeding monomerGlobalIdx
       (shift) => monomerGlobalIdx >= shift
     );
     if (lowerBound === undefined)

package/src/utils/helm-to-molfile/converter/simple-polymer.ts

@@ -28,7 +28,7 @@ export class SimplePolymer {
 
   private getPolymerType(): string {
     const regex = new RegExp(
-      `(${HELM_POLYMER_TYPE.PEPTIDE}|${HELM_POLYMER_TYPE.RNA})[0-9]+{`
+      `(${HELM_POLYMER_TYPE.PEPTIDE}|${HELM_POLYMER_TYPE.RNA}|${HELM_POLYMER_TYPE.CHEM}|${HELM_POLYMER_TYPE.BLOB})[0-9]+{`
     );
     const match = this.simplePolymer.match(regex);
     if (!match)

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

@@ -11,6 +11,10 @@ import {_package} from '../package';
 
 /** Used in Macromolecule column tooltip */
 export class MacromoleculeColumnWidget extends DG.Widget {
+  get type(): string {
+    return 'MacromoleculeColumnWidget';
+  }
+
   private viewed: boolean = false;
 
   private wlViewer: WebLogoViewer | null = null;

package/src/utils/monomer-cell-renderer.ts

@@ -3,14 +3,15 @@ import * as DG from 'datagrok-api/dg';
 import {GridCell} from 'datagrok-api/dg';
 import * as ui from 'datagrok-api/ui';
 import {ALPHABET, monomerToShort} from '@datagrok-libraries/bio/src/utils/macromolecule';
-import {GAP_SYMBOL, MONOMER_MOTIF_SPLITTER, TAGS as bioTAGS,} from '@datagrok-libraries/bio/src/utils/macromolecule/consts';
+import {BioTags, GAP_SYMBOL, MONOMER_MOTIF_SPLITTER, TAGS as bioTAGS,} from '@datagrok-libraries/bio/src/utils/macromolecule/consts';
 import {MONOMER_RENDERER_TAGS} from '@datagrok-libraries/bio/src/utils/cell-renderer';
 import {getGridCellColTemp} from '@datagrok-libraries/bio/src/utils/cell-renderer-back-base';
 
 import {CellRendererWithMonomerLibBackBase} from './monomer-cell-renderer-base';
 import * as C from './constants';
 import {undefinedColor} from '@datagrok-libraries/bio/src/utils/cell-renderer-monomer-placer';
-import {HelmTypes} from '@datagrok-libraries/js-draw-lite/src/types/org';
+import {HelmType, HelmTypes, PolymerType, PolymerTypes} from '@datagrok-libraries/js-draw-lite/src/types/org';
+import {polymerTypeToHelmType} from '@datagrok-libraries/bio/src/utils/macromolecule/utils';
 
 const Tags = new class {
   tooltipHandlerTemp = 'tooltip-handler.Monomer';
@@ -54,15 +55,17 @@ export class MonomerCellRendererBack extends CellRendererWithMonomerLibBackBase
       const biotype = alphabet === ALPHABET.RNA || alphabet === ALPHABET.DNA ? HelmTypes.NUCLEOTIDE : HelmTypes.AA;
       for (let i = 0; i < shortSymbols.length; i++) {
         const symbol: string = symbols[i];
+        const actBioType: HelmType = this.getHelmType(gridCell, biotype);
+
         let textcolor = undefinedColor;
         let backgroundcolor = 'rgb(255, 255, 255)';
         if (this.monomerLib) {
           if (applyToBackground) {
-            const colors = this.monomerLib.getMonomerColors(biotype, symbol);
+            const colors = this.monomerLib.getMonomerColors(actBioType, symbol);
             textcolor = colors?.textcolor ?? textcolor;
             backgroundcolor = colors?.backgroundcolor ?? backgroundcolor;
           } else
-            textcolor = this.monomerLib.getMonomerTextColor(biotype, symbol);
+            textcolor = this.monomerLib.getMonomerTextColor(actBioType, symbol);
         }
         if (applyToBackground && symbols.length == 1) {
           g.fillStyle = backgroundcolor;
@@ -101,7 +104,12 @@ export class MonomerCellRendererBack extends CellRendererWithMonomerLibBackBase
 
     const biotype = alphabet === ALPHABET.RNA || alphabet === ALPHABET.DNA ? HelmTypes.NUCLEOTIDE : HelmTypes.AA;
     const tooltipEls = monomerName.split(MONOMER_MOTIF_SPLITTER)
-      .map((s) => !s || s === GAP_SYMBOL || s === DASH_GAP_SYMBOL ? ui.divText('gap') : this.monomerLib!.getTooltip(biotype, s));
+      .map((s) => {
+        if (!s || s === GAP_SYMBOL || s === DASH_GAP_SYMBOL)
+          return ui.divText('gap');
+        const actBioType: HelmType = this.getHelmType(gridCell, biotype);
+        return this.monomerLib!.getTooltip(actBioType, s);
+      });
     const tooltipEl = ui.divH(tooltipEls, {style: {alignItems: 'top'}});
     // tooltip max width is 600px, so we need to shrink the canvases a bit if needed. by default, it is 250px
     const canvases = Array.from(tooltipEl.querySelectorAll('canvas'));
@@ -117,6 +125,20 @@ export class MonomerCellRendererBack extends CellRendererWithMonomerLibBackBase
     return true; // To prevent default tooltip behaviour
   }
 
+  private getHelmType(gridCell: GridCell, defaultType: HelmType): HelmType {
+    let biotype = defaultType;
+    if ((gridCell.tableRowIndex ?? -1) > -1 && gridCell.tableColumn?.getTag(BioTags.polymerTypeColumnName)) {
+      const ptColName = gridCell.tableColumn.getTag(BioTags.polymerTypeColumnName);
+      const ptCol = gridCell.tableColumn.dataFrame?.col(ptColName);
+      if (ptCol) {
+        const ptrString = ptCol.get(gridCell.tableRowIndex!);
+        if (ptrString && [PolymerTypes.BLOB, PolymerTypes.CHEM, PolymerTypes.G, PolymerTypes.PEPTIDE, PolymerTypes.RNA].includes(ptrString))
+          biotype = polymerTypeToHelmType(ptrString as PolymerType);
+      }
+    }
+    return biotype;
+  }
+
   override async awaitRendered(timeout: number = 10000, reason: string = `${timeout} timeout`): Promise<void> {
     return Promise.resolve();
   }
@@ -162,5 +184,6 @@ export class MonomerCellRenderer extends DG.GridCellRenderer {
   onMouseMove(gridCell: GridCell, e: MouseEvent) {
     const back = MonomerCellRendererBack.getOrCreate(gridCell);
     back.onMouseMove(gridCell, e);
+    e.preventDefault();
   }
 }

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

@@ -304,7 +304,7 @@ export class MonomerLibBase implements IMonomerLibBase {
       }
 
       const naSymbol: string | undefined = monomer[OPT.NATURAL_ANALOG];
-      if (!res && naSymbol)
+      if (!res && naSymbol && naSymbol !== monomer.symbol)
         return this.getMonomerColors(biotype, naSymbol);
     }
 

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

@@ -17,6 +17,7 @@ import {LIB_PATH} from '../consts';
 
 import '../../../../css/monomer-manager.css';
 import {MONOMER_RENDERER_TAGS} from '@datagrok-libraries/bio/src/utils/cell-renderer';
+import {BioTags} from '@datagrok-libraries/bio/src/utils/macromolecule/consts';
 
 // columns of monomers dataframe, note that rgroups is hidden and will be displayed as separate columns
 export enum MONOMER_DF_COLUMN_NAMES {
@@ -50,7 +51,7 @@ export const MONOMER_DF_COLUMNS = {
 } as const;
 
 export async function standardiseMonomers(monomers: Monomer[]) {
-  const df = getMonomersDataFrame(monomers);
+  const df = await getMonomersDataFrame(monomers);
   if (monomers.length !== df.rowCount)
     throw new Error(`Monomers length ${monomers.length} does not match dataframe row count ${df.rowCount}`);
   const fixedMonomers = await Promise.all(new Array(monomers.length).fill(null).map(async (_, i) => monomerFromDfRow(df.rows.get(i))));
@@ -117,7 +118,7 @@ export async function standardizeMonomerLibrary(libraryString: string) {
   return libraryStringFixed;
 }
 
-export function getMonomersDataFrame(monomers: Monomer[]) {
+export async function getMonomersDataFrame(monomers: Monomer[]) {
   try {
     const df = DG.DataFrame.create(monomers.length);
 
@@ -136,11 +137,14 @@ export function getMonomersDataFrame(monomers: Monomer[]) {
           df.columns.addNew(rgroupName, DG.COLUMN_TYPE.STRING);
       }
     }
-      df.col(MONOMER_DF_COLUMN_NAMES.SYMBOL)!.semType = 'Monomer';
-      df.col(MONOMER_DF_COLUMN_NAMES.SYMBOL)!.setTag(MONOMER_RENDERER_TAGS.applyToBackground, 'true');
-
-
-      for (let i = 0; i < monomers.length; i++) {
+    df.col(MONOMER_DF_COLUMN_NAMES.SYMBOL)!.semType = 'Monomer';
+    df.col(MONOMER_DF_COLUMN_NAMES.SYMBOL)!.setTag(MONOMER_RENDERER_TAGS.applyToBackground, 'true');
+    df.col(MONOMER_DF_COLUMN_NAMES.SYMBOL)!.setTag(BioTags.polymerTypeColumnName, MONOMER_DF_COLUMN_NAMES.POLYMER_TYPE);
+    const pg = DG.TaskBarProgressIndicator.create('Creating Monomers DataFrame...');
+    for (let i = 0; i < monomers.length; i++) {
+      if (i % 20 === 0)
+        pg.update(((i + 1) / monomers.length) * 100, 'Creating Monomers DataFrame...');
+      const doFill = () => {
         let molSmiles = getCorrectedSmiles(monomers[i].rgroups, monomers[i].smiles, monomers[i].molfile);
         molSmiles = fixRGroupsAsElementsSmiles(molSmiles);
         // r-groups here might be broken, so need to make sure they are correct
@@ -182,12 +186,33 @@ export function getMonomersDataFrame(monomers: Monomer[]) {
         } catch (e) {
           console.error(`Error setting date ${monomers[i].createDate}`, e);
         }
-      }
-      df.col(MONOMER_DF_COLUMN_NAMES.MONOMER)!.semType = DG.SEMTYPE.MOLECULE;
-      uniqueRgroupNames.forEach((rgName) => {
-        df.col(rgName)!.semType = DG.SEMTYPE.MOLECULE;
+      };
+      await new Promise<void>((resolve) => {
+        // this is done not to block the UI thread for too long
+        const inProm = () => {
+          try {
+            doFill();
+            resolve();
+          } catch (e) {
+            console.error('Error in doFill', e);
+            resolve();
+          }
+        };
+        if (i % 20 === 0) {
+          setTimeout(() => {
+            inProm();
+          });
+        } else
+          inProm();
       });
-      return df;
+    }
+    pg.close();
+    df.col(MONOMER_DF_COLUMN_NAMES.MONOMER)!.semType = DG.SEMTYPE.MOLECULE;
+
+    uniqueRgroupNames.forEach((rgName) => {
+        df.col(rgName)!.semType = DG.SEMTYPE.MOLECULE;
+    });
+    return df;
   } catch (e) {
     grok.shell.error('Error creating monomers dataframe');
     console.error(e);
@@ -506,7 +531,7 @@ export class MonomerManager implements IMonomerManager {
           return this.activeMonomerLib!.getMonomer(polymerType, symbol)!;
         });
       });
-      const df = getMonomersDataFrame(monomers);
+      const df = await getMonomersDataFrame(monomers);
       return df;
     } catch (e) {
       grok.shell.error('Error creating monomers dataframe');

package/src/widgets/composition-analysis-widget.ts

@@ -8,11 +8,12 @@ import {TAGS as bioTAGS, ALPHABET} from '@datagrok-libraries/bio/src/utils/macro
 import {GAP_SYMBOL} from '@datagrok-libraries/bio/src/utils/macromolecule/consts';
 import {IMonomerLibBase} from '@datagrok-libraries/bio/src/types';
 import {HelmType} from '@datagrok-libraries/bio/src/helm/types';
-import {HelmTypes} from '@datagrok-libraries/bio/src/helm/consts';
+import {HelmTypes, PolymerTypes} from '@datagrok-libraries/bio/src/helm/consts';
 
-import '../../css/composition-analysis.css';
 import {ISeqHelper} from '@datagrok-libraries/bio/src/utils/seq-helper';
 import {buildCompositionTable} from '@datagrok-libraries/bio/src/utils/composition-table';
+import '../../css/composition-analysis.css';
+import {polymerTypeToHelmType} from '@datagrok-libraries/bio/src/utils/macromolecule/utils';
 
 export function getCompositionAnalysisWidget(
   val: DG.SemanticValue, monomerLib: IMonomerLibBase, seqHelper: ISeqHelper
@@ -26,14 +27,22 @@ export function getCompositionAnalysisWidget(
   const sh = seqHelper.getSeqHandler(val.cell.column as DG.Column<string>);
   const rowIdx = val.cell.rowIndex;
   const seqSS = sh.getSplitted(rowIdx);
+  // in case of HELM, there might be multiple biotypes in one sequence
+  const bioTypes: {[symbol: string]: HelmType} = {};
   wu.count(0).take(seqSS.length).filter((posIdx) => !seqSS.isGap(posIdx)).forEach((posIdx) => {
     let cm = seqSS.getCanonical(posIdx);
     if (biotype === HelmTypes.NUCLEOTIDE && sh.isHelm() && cm[1] === '(' && cm[cm.length - 2] === ')')
       cm = cm.substring(2, cm.length - 2);
     const count = counts[cm] || 0;
     counts[cm] = count + 1;
+    if (!bioTypes[cm] && seqSS.graphInfo?.polymerTypes) {
+      const polymerType = seqSS.graphInfo.polymerTypes[posIdx];
+      bioTypes[cm] = polymerTypeToHelmType(polymerType);
+    }
   });
-  const table = buildCompositionTable(counts, biotype, monomerLib);
+
+
+  const table = buildCompositionTable(counts, biotype, monomerLib, Object.keys(bioTypes).length ? bioTypes : undefined);
   Array.from(table.rows).forEach((row) => {
     const barCol = (row.getElementsByClassName('macromolecule-cell-comp-analysis-bar')[0] as HTMLDivElement)
       .style.backgroundColor;

package/src/widgets/package-settings-editor-widget.ts

@@ -5,6 +5,10 @@ import {_package} from '../package';
 
 
 export class PackageSettingsEditorWidget extends DG.Widget {
+  get type(): string {
+    return 'PackageSettingsEditorWidget';
+  }
+
   maxMonomerLengthProp: DG.Property;
   tooltipWebLogo: DG.Property;
   defaultSeparator: DG.Property;

package/src/widgets/to-atomic-level-widget.ts

@@ -45,9 +45,13 @@ export async function toAtomicLevelSingle(sequence: DG.SemanticValue): Promise<{
     if (sequence.cell.column.temp[SeqTemps.notationProvider])
       singleValCol.temp[SeqTemps.notationProvider] = sequence.cell.column.temp[SeqTemps.notationProvider];
     // helm and biln will have cyclization marks, so we need to use POM to convert them
-    const shouldUsePOM = (seqSh.getSplitted(sequence.cell.rowIndex).graphInfo?.connections?.length ?? 0) > 0;
+    const seqSplitted = seqSh.getSplitted(sequence.cell.rowIndex);
+    const shouldUsePOM = (seqSplitted.graphInfo?.connections?.length ?? 0) > 0;
+    const isHelmWithMultiplePolymerTypes = seqSh.isHelm() &&
+      (new Set((seqSplitted.graphInfo?.polymerTypes ?? []))).size > 1;
+
     await PackageFunctions.toAtomicLevel(sDf, singleValCol,
-      shouldUsePOM, false);
+      shouldUsePOM || isHelmWithMultiplePolymerTypes, false);
     if (sDf.columns.length < 2) {
       errorText = 'No structure generated';
       return {errorText, mol: ''};