@datagrok/bio 2.25.5 → 2.25.7

package/package.json

@@ -5,7 +5,7 @@
     "name": "Davit Rizhinashvili",
     "email": "drizhinashvili@datagrok.ai"
   },
-  "version": "2.25.5",
+  "version": "2.25.7",
   "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-api.ts

@@ -186,6 +186,13 @@ export namespace funcs {
     return await grok.functions.call('Bio:MoleculesToHelmTopMenu', { table, molecules });
   }
 
+  /**
+  Converts a single molecule to HELM notation without requiring a table or column
+  */
+  export async function moleculeToHelmSingle(molecule: string ): Promise<string> {
+    return await grok.functions.call('Bio:MoleculeToHelmSingle', { molecule });
+  }
+
   /**
   Converts sequences to molblocks
   */
@@ -201,6 +208,13 @@ export namespace funcs {
     return await grok.functions.call('Bio:ToAtomicLevelPanel', { sequence });
   }
 
+  /**
+  Converts a single sequence to molblock
+  */
+  export async function toAtomicLevelSingleSeq(sequence: string ): Promise<string> {
+    return await grok.functions.call('Bio:ToAtomicLevelSingleSeq', { sequence });
+  }
+
   export async function sequence3dStructureWidget(sequence: any ): Promise<any> {
     return await grok.functions.call('Bio:Sequence3dStructureWidget', { sequence });
   }

package/src/package.g.ts

@@ -273,6 +273,14 @@ export async function moleculesToHelmTopMenu(table: DG.DataFrame, molecules: DG.
   await PackageFunctions.moleculesToHelmTopMenu(table, molecules);
 }
 
+//name: Molecule to HELM Single
+//description: Converts a single molecule to HELM notation without requiring a table or column
+//input: string molecule { semType: Molecule; description: Input molecule }
+//output: string result { semType: Macromolecule; units: helm }
+export async function moleculeToHelmSingle(molecule: string) : Promise<string> {
+  return await PackageFunctions.moleculeToHelmSingle(molecule);
+}
+
 //name: To Atomic Level
 //description: Converts sequences to molblocks
 //input: dataframe table { description: Input data table }
@@ -299,6 +307,14 @@ export async function toAtomicLevelPanel(sequence: DG.SemanticValue) : Promise<a
   return await PackageFunctions.toAtomicLevelPanel(sequence);
 }
 
+//name: To Atomic Level Single sequence
+//description: Converts a single sequence to molblock
+//input: string sequence { semType: Macromolecule }
+//output: string result
+export async function toAtomicLevelSingleSeq(sequence: string) : Promise<string> {
+  return await PackageFunctions.toAtomicLevelSingleSeq(sequence);
+}
+
 //name: Molecular 3D Structure
 //tags: panel, bio, widgets
 //input: semantic_value sequence { semType: Macromolecule }

package/src/package.ts

@@ -74,7 +74,7 @@ import {matchMoleculesWithMonomers, MonomerManager, standardizeMonomerLibrary} f
 import {calculateScoresWithEmptyValues} from './utils/calculate-scores';
 import {SeqHelper} from './utils/seq-helper/seq-helper';
 import {_toAtomicLevel} from '@datagrok-libraries/bio/src/monomer-works/to-atomic-level';
-import {molecular3DStructureWidget, toAtomicLevelWidget} from './widgets/to-atomic-level-widget';
+import {molecular3DStructureWidget, toAtomicLevelWidget, toAtomicLevelSingle} from './widgets/to-atomic-level-widget';
 import {handleSequenceHeaderRendering} from './widgets/sequence-scrolling-widget';
 import {PolymerType} from '@datagrok-libraries/js-draw-lite/src/types/org';
 import {BilnNotationProvider} from './utils/biln';
@@ -642,6 +642,20 @@ export class PackageFunctions {
     }
   }
 
+  @grok.decorators.func({name: 'Molecule to HELM Single', description: 'Converts a single molecule to HELM notation without requiring a table or column', outputs: [{name: 'result', type: 'string', options: {semType: 'Macromolecule', units: 'helm'}}]})
+  static async moleculeToHelmSingle(
+    @grok.decorators.param({name: 'molecule', options: {semType: 'Molecule', description: 'Input molecule'}})molecule: string,
+  ): Promise<string> {
+    // create temporary dataframe
+    const tempCol = DG.Column.fromStrings('molecule', [molecule]);
+    tempCol.semType = DG.SEMTYPE.MOLECULE;
+    const tempDF = DG.DataFrame.fromColumns([tempCol]);
+    // call converter
+    await PackageFunctions.moleculesToHelmTopMenu(tempDF, tempCol);
+    // get result
+    const result = tempDF.columns.toList().find((c) => c.name.toLowerCase().includes('regenerated sequence'))?.get(0);
+    return result ?? '';
+  }
 
   @grok.decorators.func({
     name: 'To Atomic Level',
@@ -690,6 +704,47 @@ export class PackageFunctions {
     return toAtomicLevelWidget(sequence);
   }
 
+  @grok.decorators.func({
+    name: 'To Atomic Level Single sequence',
+    description: 'Converts a single sequence to molblock'
+  })
+  static async toAtomicLevelSingleSeq(
+    @grok.decorators.param({name: 'sequence', type: 'string', options: {semType: 'Macromolecule'}}) sequence: string,
+  ) : Promise<string> {
+    // create temporary column and table
+    const isHelm = sequence.includes('$$');
+    const isSeparator = sequence.split('').filter((c) => c == '/').length > 2;
+    const isBiln = sequence.split('').filter((c) => c == '-').length > 2; // biln is super separator basically :D
+    // const isFasta = !isHelm && !isSeparator && !isBiln;
+    const tempCol = DG.Column.fromStrings('sequence', [sequence]);
+    tempCol.semType = DG.SEMTYPE.MACROMOLECULE;
+    tempCol.meta.units = isHelm ? NOTATION.HELM : isSeparator ? NOTATION.SEPARATOR : isBiln ? NOTATION.BILN : NOTATION.FASTA;
+    tempCol.setTag(bioTAGS.aligned, 'SEQ');
+    if (isSeparator)
+      tempCol.setTag(bioTAGS.separator, '/');
+    if (isBiln)
+      tempCol.setTag(bioTAGS.separator, '-');
+    // detect alphabet
+    const dnaAlphabet = 'AGCT';
+    const RNAAlphabet = 'AGCU';
+    const isDNA = sequence.split('').every((c) => dnaAlphabet.includes(c) || c === '/' || c === '-');
+    const isRNA = !isDNA && sequence.split('').every((c) => RNAAlphabet.includes(c) || c === '/' || c === '-');
+
+    tempCol.setTag(bioTAGS.alphabet, isDNA ? ALPHABET.DNA : isRNA ? ALPHABET.RNA : 'UN');
+    tempCol.setTag(bioTAGS.alphabetIsMultichar, 'true');
+
+    const tempDF = DG.DataFrame.fromColumns([tempCol]);
+
+    // get the sell as semantic value
+    const cell = tempDF.cell(0, 'sequence');
+    const semValue = DG.SemanticValue.fromTableCell(cell);
+
+    const res = await toAtomicLevelSingle(semValue);
+    if (res.errorText || !res.mol)
+      throw new Error(res.errorText);
+    return res.mol;
+  }
+
   @grok.decorators.panel({
     name: 'Molecular 3D Structure',
     tags: ['bio', 'widgets']
@@ -1277,22 +1332,7 @@ export class PackageFunctions {
       nonlinear: boolean
   ): Promise<string | undefined> {
     if (!(seq.trim())) return '';
-    try {
-      const seqCol = DG.Column.fromList(DG.COLUMN_TYPE.STRING, `helm`, [seq]);
-      const df = DG.DataFrame.fromColumns([seqCol]);
-      const semType = await grok.functions.call('Bio:detectMacromolecule', {col: seqCol});
-      if (semType) seqCol.semType = semType;
-
-      const monomerLib = (await PackageFunctions.getMonomerLibHelper()).getMonomerLib();
-      const seqHelper = _package.seqHelper;
-      const rdKitModule = await getRdKitModule();
-      const res = (await sequenceToMolfile(df, seqCol, nonlinear, false, monomerLib, seqHelper, rdKitModule))?.molCol?.get(0);
-      return res ?? undefined;
-    } catch (err: any) {
-      const [errMsg, errStack] = errInfo(err);
-      _package.logger.error(errMsg, undefined, errStack);
-      throw err;
-    }
+    return PackageFunctions.toAtomicLevelSingleSeq(seq);
   }
 
   // //description: Gets similarity to a reference sequence