@datagrok/bio 2.25.3 → 2.25.5

package/src/package.g.ts

@@ -277,7 +277,7 @@ export async function moleculesToHelmTopMenu(table: DG.DataFrame, molecules: DG.
 //description: Converts sequences to molblocks
 //input: dataframe table { description: Input data table }
 //input: column seqCol { semType: Macromolecule; caption: Sequence }
-//input: bool nonlinear = false { caption: Non-linear; description: Slower mode for cycling/branching HELM structures }
+//input: bool nonlinear = true { caption: Non-linear; description: Slower mode for cycling/branching HELM structures }
 //input: bool highlight = false { caption: Highlight monomers; description: Highlight monomers' substructures of the molecule }
 //top-menu: Bio | Transform | To Atomic Level...
 export async function toAtomicLevel(table: DG.DataFrame, seqCol: DG.Column, nonlinear: boolean, highlight: boolean) : Promise<void> {

package/src/package.ts

@@ -651,7 +651,7 @@ export class PackageFunctions {
   static async toAtomicLevel(
     @grok.decorators.param({options: {description: 'Input data table'}})table: DG.DataFrame,
     @grok.decorators.param({options: {semType: 'Macromolecule', caption: 'Sequence'}})seqCol: DG.Column,
-    @grok.decorators.param({options: {initialValue: 'false', caption: 'Non-linear', description: 'Slower mode for cycling/branching HELM structures'}}) nonlinear: boolean,
+    @grok.decorators.param({options: {initialValue: 'true', caption: 'Non-linear', description: 'Slower mode for cycling/branching HELM structures'}}) nonlinear: boolean = true,
     @grok.decorators.param({options: {initialValue: 'false', caption: 'Highlight monomers', description: 'Highlight monomers\' substructures of the molecule'}}) highlight: boolean = false
   ): Promise<void> {
     const pi = DG.TaskBarProgressIndicator.create('Converting to atomic level ...');

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

@@ -0,0 +1,40 @@
+import {RGroup} from '@datagrok-libraries/bio/src/types/monomer-library';
+
+export const STANDRARD_R_GROUPS: RGroup[] = [
+  {
+    alternateId: 'R1-H',
+    capGroupName: 'H',
+    capGroupSmiles: '[*:1][H]',
+    label: 'R1'
+  },
+  {
+    alternateId: 'R2-OH',
+    capGroupName: 'OH',
+    capGroupSmiles: 'O[*:2]',
+    label: 'R2'
+  },
+  {
+    alternateId: 'R3-H',
+    capGroupName: 'H',
+    capGroupSmiles: '[*:3][H]',
+    label: 'R3'
+  },
+  {
+    alternateId: 'R4-H',
+    capGroupName: 'H',
+    capGroupSmiles: '[*:4][H]',
+    label: 'R4'
+  },
+  {
+    alternateId: 'R5-H',
+    capGroupName: 'H',
+    capGroupSmiles: '[*:5][H]',
+    label: 'R5'
+  },
+  {
+    alternateId: 'R6-H',
+    capGroupName: 'H',
+    capGroupSmiles: '[*:6][H]',
+    label: 'R6'
+  },
+];

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

@@ -19,7 +19,7 @@ import {BioTags} from '@datagrok-libraries/bio/src/utils/macromolecule/consts';
 //@ts-ignore
 import '../../../../css/monomer-manager.css';
 import {Subscription} from 'rxjs';
-
+import {STANDRARD_R_GROUPS} from './const';
 
 // columns of monomers dataframe, note that rgroups is hidden and will be displayed as separate columns
 export enum MONOMER_DF_COLUMN_NAMES {
@@ -69,6 +69,9 @@ export async function matchMoleculesWithMonomers(molDf: DG.DataFrame, molColName
   // first: stamdardize monomers
   const monomers = monomerLib.getMonomerSymbolsByType(polymerType).map((s) => monomerLib.getMonomer(polymerType, s)!).filter((m) => m && (m.smiles || m.molfile));
   const fixedMonomers = await standardiseMonomers(monomers);
+  fixedMonomers.forEach((m, i) => {
+    m.lib = monomers[i].lib;
+  });
   const unCappedMonomerSmilesMap = fixedMonomers.filter((m) => !!m.smiles).reduce((acc, m) => {
     acc[m.smiles] = {symbol: m.symbol, smiles: m.smiles, original: m.smiles, source: m.lib?.source}; return acc;
   }, {} as {[smiles: string]: {symbol: string, smiles: string, original: string | undefined, source: string | undefined}});
@@ -115,7 +118,15 @@ export async function matchMoleculesWithMonomers(molDf: DG.DataFrame, molColName
   for (let i = 0; i < canonicalizedMolecules.length; i++) {
     const mol = canonicalizedMolecules[i];
     if (!mol) continue;
-    const match = cappedMonomerSmilesMap[mol] ?? unCappedMonomerSmilesMap[mol];
+    let match = cappedMonomerSmilesMap[mol] ?? unCappedMonomerSmilesMap[mol];
+    if (!match) {
+      // try capping the molecule and matching again
+      const cappedMol = capSmiles(mol, STANDRARD_R_GROUPS);
+      if (cappedMol !== mol) {
+        const correctedMol = grok.chem.convert(cappedMol, DG.chem.Notation.Unknown, DG.chem.Notation.Smiles);
+        match = cappedMonomerSmilesMap[correctedMol] ?? unCappedMonomerSmilesMap[correctedMol];
+      }
+    }
     if (match) {
       const matchSymbol = match.symbol;
       const sources = (duplicates[matchSymbol]?.length ?? 0) > 0 ? duplicates[matchSymbol].map((m) => m?.lib?.source).filter((s) => !!s).join(', ') : (match.source ?? '');