@datagrok/bio 2.22.12 → 2.23.1

package/package.json

@@ -5,7 +5,7 @@
     "name": "Davit Rizhinashvili",
     "email": "drizhinashvili@datagrok.ai"
   },
-  "version": "2.22.12",
+  "version": "2.23.1",
   "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": "^5.54.7",
-    "@datagrok-libraries/chem-meta": "^1.2.7",
-    "@datagrok-libraries/math": "^1.2.4",
-    "@datagrok-libraries/ml": "^6.10.4",
-    "@datagrok-libraries/tutorials": "^1.6.1",
-    "@datagrok-libraries/utils": "^4.6.5",
+    "@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": "^1.7.4",
+    "@datagrok-libraries/utils": "^4.6.9",
     "@webgpu/types": "^0.1.40",
     "ajv": "^8.12.0",
     "ajv-errors": "^3.0.0",

package/src/package-api.ts

@@ -44,6 +44,13 @@ export namespace funcs {
     return await grok.functions.call('Bio:StandardiseMonomerLibrary', { library });
   }
 
+  /**
+  Matches molecules in a column with monomers from the selected library(s)
+  */
+  export async function matchWithMonomerLibrary(table: DG.DataFrame , molecules: DG.Column , polymerType: string ): Promise<void> {
+    return await grok.functions.call('Bio:MatchWithMonomerLibrary', { table, molecules, polymerType });
+  }
+
   export async function getBioLib(): Promise<any> {
     return await grok.functions.call('Bio:GetBioLib', {});
   }

package/src/package.g.ts

@@ -110,6 +110,23 @@ export function separatorSequenceCellRenderer() : any {
   return PackageFunctions.separatorSequenceCellRenderer();
 }
 
+//tags: cellRenderer
+//output: grid_cell_renderer result
+//meta.cellType: sequence
+//meta.columnTags: quality=Macromolecule, units=biln
+export function bilnSequenceCellRenderer() : any {
+  return PackageFunctions.bilnSequenceCellRenderer();
+}
+
+//tags: notationRefiner
+//input: column col 
+//input: object stats 
+//input: string separator { nullable: true; optional: true }
+//output: bool result
+export function refineNotationProviderForBiln(col: DG.Column<any>, stats: any, separator: any) : boolean {
+  return PackageFunctions.refineNotationProviderForBiln(col, stats, separator);
+}
+
 //name: Bioinformatics | Sequence Renderer
 //tags: panel
 //input: column molColumn { semType: Macromolecule }
@@ -327,7 +344,7 @@ export function importBam(fileContent: string) : any {
   return PackageFunctions.importBam(fileContent);
 }
 
-//top-menu: Bio | Transform | Convert Notation...
+//top-menu: Bio | Transform | Convert Sequence Notation...
 export function convertDialog() : void {
   PackageFunctions.convertDialog();
 }

package/src/package.ts

@@ -30,7 +30,7 @@ import {getUserLibSettings, setUserLibSettings} from '@datagrok-libraries/bio/sr
 import {ISeqHelper} from '@datagrok-libraries/bio/src/utils/seq-helper';
 import {RDModule as _RDMoule} from '@datagrok-libraries/chem-meta/src/rdkit-api';
 import {getRdKitModule} from '@datagrok-libraries/bio/src/chem/rdkit-module';
-import {ISeqHandler} from '@datagrok-libraries/bio/src/utils/macromolecule/seq-handler';
+import {ISeqHandler, SeqTemps} from '@datagrok-libraries/bio/src/utils/macromolecule/seq-handler';
 import {MmcrTemps} from '@datagrok-libraries/bio/src/utils/cell-renderer-consts';
 
 import {getMacromoleculeColumns} from './utils/ui-utils';
@@ -77,6 +77,7 @@ import {_toAtomicLevel} from '@datagrok-libraries/bio/src/monomer-works/to-atomi
 import {molecular3DStructureWidget, toAtomicLevelWidget} 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';
 export const _package = new BioPackage(/*{debug: true}/**/);
 export * from './package.g';
 
@@ -297,6 +298,49 @@ export class PackageFunctions {
     return new MacromoleculeSequenceCellRenderer();
   }
 
+  @grok.decorators.func({
+    name: 'bilnSequenceCellRenderer',
+    tags: ['cellRenderer'],
+    meta: {
+      cellType: 'sequence',
+      columnTags: 'quality=Macromolecule, units=biln'
+    },
+    outputs: [{type: 'grid_cell_renderer', name: 'result'}]
+  })
+  static bilnSequenceCellRenderer(): MacromoleculeSequenceCellRenderer {
+    return new MacromoleculeSequenceCellRenderer();
+  }
+
+  @grok.decorators.func({
+    name: 'refineNotationProviderForBiln',
+    tags: ['notationRefiner'],
+    outputs: [{type: 'bool', name: 'result'}]
+  })
+  static refineNotationProviderForBiln(
+    @grok.decorators.param({type: 'column'}) col: DG.Column<string>,
+    @grok.decorators.param({type: 'object'}) stats: {freq: { [key: string]: number; }, sameLength: boolean},
+    @grok.decorators.param({type: 'string', options: {nullable: true, optional: true}}) separator: string | null
+  ): boolean {
+    if (separator !== '-')
+      return false;// biln uses '-' as a separator
+    const reCons = Object.keys(stats.freq).some((om) => om.match(/^.+\(\d{1,2},\d{1,2}\)$/));
+    if (!reCons) {
+      // biln might also encode monomers with hyphens in names encoded by []
+      // here we know that there are no monomers with connections like (1,2) in names, so we can check for []
+      const reBrackets = Object.keys(stats.freq).some((om) => om.includes('[') || om.includes(']'));
+      if (!reBrackets)
+        return false;
+    }
+    // refine the notation provider
+    col.setTag('aligned', 'SEQ');
+    col.setTag('alphabet', 'UN');
+    col.setTag('.alphabetIsMultichar', 'true');
+    col.meta.units = NOTATION.BILN;
+    col.temp[SeqTemps.notationProvider] = new BilnNotationProvider(separator, _package.seqHelper, col);
+
+    return true;
+  }
+
   // // -- Property panels --
 
   @grok.decorators.panel({name: 'Bioinformatics | Sequence Renderer'})
@@ -757,7 +801,7 @@ export class PackageFunctions {
 
   @grok.decorators.func({
     name: 'convertDialog',
-    'top-menu': 'Bio | Transform | Convert Notation...'
+    'top-menu': 'Bio | Transform | Convert Sequence Notation...'
   })
   static convertDialog() {
     const col: DG.Column<string> | undefined = getMacromoleculeColumns()[0];

package/src/tests/biln-tests.ts

@@ -0,0 +1,167 @@
+/* eslint-disable max-len */
+/* eslint-disable max-lines */
+/* eslint-disable max-lines-per-function */
+import * as grok from 'datagrok-api/grok';
+import * as ui from 'datagrok-api/ui';
+import * as DG from 'datagrok-api/dg';
+
+import {category, test, expect, before} from '@datagrok-libraries/utils/src/test';
+
+import {ALIGNMENT, ALPHABET, NOTATION, TAGS as bioTAGS} from '@datagrok-libraries/bio/src/utils/macromolecule';
+import {ISeqHelper, getSeqHelper} from '@datagrok-libraries/bio/src/utils/seq-helper';
+
+import {_testNeg, _testPos, DetectorTestData, DfReaderFunc, PosCol} from './utils/detectors-utils';
+import {SeqTemps} from '@datagrok-libraries/bio/src/utils/macromolecule/seq-handler';
+
+export async function prepareBiln(list: string[], seqHelper: ISeqHelper): Promise<DG.Column> {
+  const col: DG.Column = DG.Column.fromList(DG.TYPE.STRING, 'seq', list);
+  const semType: string = await grok.functions.call('Bio:detectMacromolecule', {col: col});
+  if (semType)
+    col.semType = semType;
+  expect(col.semType, DG.SEMTYPE.MACROMOLECULE);
+  const sh = seqHelper.getSeqHandler(col);
+  await sh.refinerPromise; // wait for refiner to finish
+  const _newSh = seqHelper.getSeqHandler(col);
+  return col;
+}
+
+
+export async function _testBilnDetection(list: string[], seqHelper: ISeqHelper, negativeTest = false): Promise<void> {
+  const col = await prepareBiln(list, seqHelper);
+  expect(col.meta.units === NOTATION.BILN, !negativeTest, `Incorrectly detected as ${col.meta.units}`);
+  expect(col.temp[SeqTemps.notationProvider] != null, !negativeTest, `No notation provider for BILN`);
+}
+
+export async function _testBilnToHelm(list: string[], expectedHelm: string[], seqHelper: ISeqHelper): Promise<void> {
+  const col = await prepareBiln(list, seqHelper);
+  const sh = seqHelper.getSeqHandler(col);
+  for (let i = 0; i < list.length; i++) {
+    const helm = sh.getHelm(i);
+    expect(helm === expectedHelm[i], true, `Incorrect HELM conversion for ${list[i]}: Expected ${expectedHelm[i]} \n Got ${helm}`);
+  }
+  // also test through converter
+  const converter = sh.getConverter(NOTATION.HELM);
+  for (let i = 0; i < list.length; i++) {
+    const helm = converter(list[i]);
+    expect(helm === expectedHelm[i], true, `Incorrect HELM conversion for ${list[i]}: Expected ${expectedHelm[i]} \n Got ${helm}`);
+  }
+}
+
+export async function _testHelmToBiln(helmList: string[], expectedBiln: string[], seqHelper: ISeqHelper): Promise<void> {
+  const col: DG.Column = DG.Column.fromList(DG.TYPE.STRING, 'helm', helmList);
+  const df = DG.DataFrame.fromColumns([col]);
+  await df.meta.detectSemanticTypes();
+  await grok.data.detectSemanticTypes(df);
+  expect(col.semType === DG.SEMTYPE.MACROMOLECULE, true, `Incorrectly detected as ${col.semType}`);
+  expect(col.meta.units === NOTATION.HELM, true, `Incorrectly detected as ${col.meta.units}`);
+  const sh = seqHelper.getSeqHandler(col);
+  const converter = sh.getConverter(NOTATION.BILN);
+  for (let i = 0; i < helmList.length; i++) {
+    const biln = converter(helmList[i]);
+    expect(biln === expectedBiln[i], true, `Incorrect BILN conversion for ${helmList[i]}: Expected ${expectedBiln[i]} \n Got ${biln}`);
+  }
+}
+
+export const detectorTestsDataForBiln: {name: string, seqs: string[], negative: boolean}[] = [
+  {
+    name: 'Valid Biln',
+    seqs: [
+      'A-C(1,3)-G-G-H-A-V-E-A-K-Y-L-V-C(3,3)-S.G-I-V-E-A-C(2,3)-C(1,3)-T-S-I-C(2,3)-S-L-Y-Q-L-E-N-Y-C(3,3)-Y',
+      'A-C(1,3)-G-G-H-A-V-E-A-K-Y-L-V-C(3,3)-S.G-I-V-E-A-C(2,3)-C(1,3)-T-S-I-C(2,3)-S-L-Y-Q-L-E-N-Y-C(3,3)-Y',
+      'C-C(1,3)-S-W-P-A-R-C(2,3)-L-H-Q-D-L-C(3,3)-NH2.C(1,1)(2,2)(3,3)',
+      'C-C(1,3)-S-W-P-A-R-C(2,3)-L-H-Q-D-L-C(3,3)-NH2.[C](1,1)(2,2)(3,3)',
+      'D-T-H-F-P-I-C(1,3)-I-F-C(2,3)-C(3,3)-G-C(2,3)-C(4,3)-H-R-S-K-C(3,3)-G-M-C(4,3)-C(1,3)-K-T'
+    ], negative: false
+  }, {
+    name: 'Simple Separator Neg',
+    seqs: [
+      'meI/hHis/Aca/N/T/dE/Thr_PO3H2/Aca/D-Tyr_Et/Tyr_ab-dehydroMe/dV/E/N/D-Orn/D-aThr//Phe_4Me',
+      'meI/hHis/Aca/Cys_SEt/T/dK/Thr_PO3H2/Aca/Tyr_PO3H2/D-Chg/dV/Phe_ab-dehydro/N/D-Orn/D-aThr//Phe_4Me',
+      'Lys_Boc/hHis/Aca/Cys_SEt/T/dK/Thr_PO3H2/Aca/Tyr_PO3H2/D-Chg/dV/Thr_PO3H2/N/D-Orn/D-aThr//Phe_4Me',
+      'meI/hHis/Aca/Cys_SEt/T/dK/Thr_PO3H2/Aca/Tyr_PO3H2/D-Chg/dV/Thr_PO3H2/N/D-Orn/D-aThr//Phe_4Me',
+      'meI/hHis/Aca/N/T/dK/Thr_PO3H2/Aca/D-Tyr_Et/Tyr_ab-dehydroMe/dV/Chg/N/D-Orn/D-aThr//Phe_4Me'
+    ], negative: true
+  }, {
+    name: 'Valid Biln without cyclization',
+    seqs: [
+      'meI-hHis-Aca-N-T-dE-Thr_PO3H2-Aca-[D-Tyr_Et]-[Tyr_ab-dehydroMe]-dV-E-N-[D-Orn]-[D-aThr]--Phe_4Me',
+      'meI-hHis-Aca-Cys_SEt-T-dK-Thr_PO3H2-Aca-Tyr_PO3H2-[D-Chg]-dV-[Phe_ab-dehydro]-N-[D-Orn]-[D-aThr]--Phe_4Me',
+      'Lys_Boc-hHis-Aca-Cys_SEt-T-dK-Thr_PO3H2-Aca-Tyr_PO3H2-[D-Chg]-dV-Thr_PO3H2-N-[D-Orn]-[D-aThr]--Phe_4Me',
+      'meI-hHis-Aca-Cys_SEt-T-dK-Thr_PO3H2-Aca-Tyr_PO3H2-[D-Chg]-dV-Thr_PO3H2-N-[D-Orn]-[D-aThr]--Phe_4Me',
+      'meI-hHis-Aca-N-T-dK-Thr_PO3H2-Aca-[D-Tyr_Et]-[Tyr_ab-dehydroMe]-dV-Chg-N-[D-Orn]-[D-aThr]--Phe_4Me',
+      'meI-hHis-Aca-N-T-dK-Thr_PO3H2-Aca-[D-Tyr_Et]-Tyr_Bn-dV-E-N-dV---Phe_4Me',
+      'meI-hHis-Aca-N-T-dK-Thr_PO3H2-Aca-[D-Tyr_Et]-Aze-dV-E-N-dV---Phe_4Me',
+      'meI-hHis-Aca-N-T-dK-Thr_PO3H2-Aca-[D-Tyr_Et]-meQ-dV-E-N-dV---Phe_4Me'
+    ], negative: false
+  }
+];
+
+export const bilnToHelmTestsData: {name: string, biln: string[], helm: string[]}[] = [
+  {
+    name: 'Linear',
+    biln: ['meI-hHis-Aca-N-T-dE-Thr_PO3H2-Aca-[D-Tyr_Et]-[Tyr_ab-dehydroMe]-dV-E-N-[D-Orn]-[D-aThr]--Phe_4Me',
+      'meI-hHis-Aca-Cys_SEt-T-dK-Thr_PO3H2-Aca-Tyr_PO3H2-[D-Chg]-dV-[Phe_ab-dehydro]-N-[D-Orn]-[D-aThr]--Phe_4Me',
+      'Lys_Boc-hHis-Aca-Cys_SEt-T-dK-Thr_PO3H2-Aca-Tyr_PO3H2-[D-Chg]-dV-Thr_PO3H2-N-[D-Orn]-[D-aThr]--Phe_4Me',
+      'meI-hHis-Aca-Cys_SEt-T-dK-Thr_PO3H2-Aca-Tyr_PO3H2-[D-Chg]-dV-Thr_PO3H2-N-[D-Orn]-[D-aThr]--Phe_4Me',
+      'meI-hHis-Aca-N-T-dK-Thr_PO3H2-Aca-[D-Tyr_Et]-[Tyr_ab-dehydroMe]-dV-Chg-N-[D-Orn]-[D-aThr]--Phe_4Me'],
+    helm: [
+      'PEPTIDE1{[meI].[hHis].[Aca].N.T.[dE].[Thr_PO3H2].[Aca].[D-Tyr_Et].[Tyr_ab-dehydroMe].[dV].E.N.[D-Orn].[D-aThr].*.[Phe_4Me]}$$$$',
+      'PEPTIDE1{[meI].[hHis].[Aca].[Cys_SEt].T.[dK].[Thr_PO3H2].[Aca].[Tyr_PO3H2].[D-Chg].[dV].[Phe_ab-dehydro].N.[D-Orn].[D-aThr].*.[Phe_4Me]}$$$$',
+      'PEPTIDE1{[Lys_Boc].[hHis].[Aca].[Cys_SEt].T.[dK].[Thr_PO3H2].[Aca].[Tyr_PO3H2].[D-Chg].[dV].[Thr_PO3H2].N.[D-Orn].[D-aThr].*.[Phe_4Me]}$$$$',
+      'PEPTIDE1{[meI].[hHis].[Aca].[Cys_SEt].T.[dK].[Thr_PO3H2].[Aca].[Tyr_PO3H2].[D-Chg].[dV].[Thr_PO3H2].N.[D-Orn].[D-aThr].*.[Phe_4Me]}$$$$',
+      'PEPTIDE1{[meI].[hHis].[Aca].N.T.[dK].[Thr_PO3H2].[Aca].[D-Tyr_Et].[Tyr_ab-dehydroMe].[dV].[Chg].N.[D-Orn].[D-aThr].*.[Phe_4Me]}$$$$'
+    ]
+  }, {
+    name: 'Cyclic',
+    biln: [
+      'C-C(1,3)-S-W-P-A-R-C(2,3)-L-H-Q-D-L-C(3,3)-NH2.[C](1,1)(2,2)(3,3)',
+      'D-T-H-F-P-I-C(1,3)-I-F-C(2,3)-C(3,3)-G-C(2,3)-C(4,3)-H-R-S-K-C(3,3)-G-M-C(4,3)-C(1,3)-K-T',
+      'L-C(1,3)-G-S-H-L-V-E-A-L-Y-L-V-C(2,3)-G.G-I-V-E-Q-C(3,3)-C(1,3)-T-S-I-C(3,3)-S-L-Y-Q-L-E-N-Y-C(2,3)-N',
+      'H-Aib-E-G-T-F-T-S-D(2,3)-V-S-S-Y-L-E-G-Q-A-A-K(1,3)-E-F-I-A-W-L-V-R-G-R-G.C(2,3)-gGlu-G-G(1,2)',
+      'F(4,2).dI(1,1)(3,3)-Trp_Ome-Asp_OMe-Cys_Bn-meG-Phe_3Cl-dD-T-dI(4,3)-T-dK-aG-3Pal-xiIle-meD-Ala_tBu(1,2).L(2,1)-Pro_4Me3OH-S-NMe2Abz-Q-3Pal-xiIle-D-Hyp-Ala_tBu-dI(3,3)-Trp_Ome-Asp_OMe-N-meG-Phe_34diCl-Phe_34diCl(2,2)'
+    ],
+    helm: [
+      'PEPTIDE1{C.C.S.W.P.A.R.C.L.H.Q.D.L.C.[NH2]}|PEPTIDE2{C}$PEPTIDE1,PEPTIDE2,14:R3-1:R3|PEPTIDE1,PEPTIDE2,8:R3-1:R2|PEPTIDE1,PEPTIDE2,2:R3-1:R1$$$V2.0',
+      'PEPTIDE1{D.T.H.F.P.I.C.I.F.C.C.G.C.C.H.R.S.K.C.G.M.C.C.K.T}$PEPTIDE1,PEPTIDE1,10:R3-13:R3|PEPTIDE1,PEPTIDE1,11:R3-19:R3|PEPTIDE1,PEPTIDE1,14:R3-22:R3|PEPTIDE1,PEPTIDE1,7:R3-23:R3$$$V2.0',
+      'PEPTIDE1{L.C.G.S.H.L.V.E.A.L.Y.L.V.C.G}|PEPTIDE2{G.I.V.E.Q.C.C.T.S.I.C.S.L.Y.Q.L.E.N.Y.C.N}$PEPTIDE1,PEPTIDE2,2:R3-7:R3|PEPTIDE2,PEPTIDE2,6:R3-11:R3|PEPTIDE1,PEPTIDE2,14:R3-20:R3$$$V2.0',
+      'PEPTIDE1{H.[Aib].E.G.T.F.T.S.D.V.S.S.Y.L.E.G.Q.A.A.K.E.F.I.A.W.L.V.R.G.R.G}|PEPTIDE2{C.[gGlu].G.G}$PEPTIDE1,PEPTIDE2,9:R3-1:R3|PEPTIDE1,PEPTIDE2,20:R3-4:R2$$$V2.0',
+      'PEPTIDE1{F}|PEPTIDE2{[dI].[Trp_Ome].[Asp_OMe].[Cys_Bn].[meG].[Phe_3Cl].[dD].T.[dI].T.[dK].[aG].[3Pal].[xiIle].[meD].[Ala_tBu]}|PEPTIDE3{L.[Pro_4Me3OH].S.[NMe2Abz].Q.[3Pal].[xiIle].D.[Hyp].[Ala_tBu].[dI].[Trp_Ome].[Asp_OMe].N.[meG].[Phe_34diCl].[Phe_34diCl]}$PEPTIDE1,PEPTIDE2,1:R2-9:R3|PEPTIDE2,PEPTIDE2,1:R1-16:R2|PEPTIDE2,PEPTIDE3,1:R3-11:R3|PEPTIDE3,PEPTIDE3,1:R1-17:R2$$$V2.0'
+    ]
+  }
+];
+
+export const helmToBilnTestsData: {name: string, helm: string[], biln: string[]}[] = [
+  {
+    name: 'Linear',
+    biln: [
+      'meI-hHis-Aca-N-T-dE-Thr_PO3H2-Aca-[D-Tyr_Et]-[Tyr_ab-dehydroMe]-dV-E-N-[D-Orn]-[D-aThr]--Phe_4Me',
+      'meI-hHis-Aca-Cys_SEt-T-dK-Thr_PO3H2-Aca-Tyr_PO3H2-[D-Chg]-dV-[Phe_ab-dehydro]-N-[D-Orn]-[D-aThr]--Phe_4Me',
+      'Lys_Boc-hHis-Aca-Cys_SEt-T-dK-Thr_PO3H2-Aca-Tyr_PO3H2-[D-Chg]-dV-Thr_PO3H2-N-[D-Orn]-[D-aThr]--Phe_4Me',
+      'meI-hHis-Aca-Cys_SEt-T-dK-Thr_PO3H2-Aca-Tyr_PO3H2-[D-Chg]-dV-Thr_PO3H2-N-[D-Orn]-[D-aThr]--Phe_4Me',
+      'meI-hHis-Aca-N-T-dK-Thr_PO3H2-Aca-[D-Tyr_Et]-[Tyr_ab-dehydroMe]-dV-Chg-N-[D-Orn]-[D-aThr]--Phe_4Me'
+    ],
+    helm: [
+      'PEPTIDE1{[meI].[hHis].[Aca].N.T.[dE].[Thr_PO3H2].[Aca].[D-Tyr_Et].[Tyr_ab-dehydroMe].[dV].E.N.[D-Orn].[D-aThr].*.[Phe_4Me]}$$$$',
+      'PEPTIDE1{[meI].[hHis].[Aca].[Cys_SEt].T.[dK].[Thr_PO3H2].[Aca].[Tyr_PO3H2].[D-Chg].[dV].[Phe_ab-dehydro].N.[D-Orn].[D-aThr].*.[Phe_4Me]}$$$$',
+      'PEPTIDE1{[Lys_Boc].[hHis].[Aca].[Cys_SEt].T.[dK].[Thr_PO3H2].[Aca].[Tyr_PO3H2].[D-Chg].[dV].[Thr_PO3H2].N.[D-Orn].[D-aThr].*.[Phe_4Me]}$$$$',
+      'PEPTIDE1{[meI].[hHis].[Aca].[Cys_SEt].T.[dK].[Thr_PO3H2].[Aca].[Tyr_PO3H2].[D-Chg].[dV].[Thr_PO3H2].N.[D-Orn].[D-aThr].*.[Phe_4Me]}$$$$',
+      'PEPTIDE1{[meI].[hHis].[Aca].N.T.[dK].[Thr_PO3H2].[Aca].[D-Tyr_Et].[Tyr_ab-dehydroMe].[dV].[Chg].N.[D-Orn].[D-aThr].*.[Phe_4Me]}$$$$'
+    ]
+  }, {
+    name: 'Cyclic',
+    biln: [
+      'C-C(3,3)-S-W-P-A-R-C(2,3)-L-H-Q-D-L-C(1,3)-NH2.C(1,3)(2,2)(3,1)',
+      'D-T-H-F-P-I-C(4,3)-I-F-C(1,3)-C(2,3)-G-C(1,3)-C(3,3)-H-R-S-K-C(2,3)-G-M-C(3,3)-C(4,3)-K-T',
+      'L-C(1,3)-G-S-H-L-V-E-A-L-Y-L-V-C(3,3)-G.G-I-V-E-Q-C(2,3)-C(1,3)-T-S-I-C(2,3)-S-L-Y-Q-L-E-N-Y-C(3,3)-N',
+      'H-Aib-E-G-T-F-T-S-D(1,3)-V-S-S-Y-L-E-G-Q-A-A-K(2,3)-E-F-I-A-W-L-V-R-G-R-G.C(1,3)-gGlu-G-G(2,2)',
+      'F(1,2).dI(2,1)(3,3)-Trp_Ome-Asp_OMe-Cys_Bn-meG-Phe_3Cl-dD-T-dI(1,3)-T-dK-aG-3Pal-xiIle-meD-Ala_tBu(2,2).L(4,1)-Pro_4Me3OH-S-NMe2Abz-Q-3Pal-xiIle-D-Hyp-Ala_tBu-dI(3,3)-Trp_Ome-Asp_OMe-N-meG-Phe_34diCl-Phe_34diCl(4,2)'
+    ],
+    helm: [
+      'PEPTIDE1{C.C.S.W.P.A.R.C.L.H.Q.D.L.C.[NH2]}|PEPTIDE2{C}$PEPTIDE1,PEPTIDE2,14:R3-1:R3|PEPTIDE1,PEPTIDE2,8:R3-1:R2|PEPTIDE1,PEPTIDE2,2:R3-1:R1$$$V2.0',
+      'PEPTIDE1{D.T.H.F.P.I.C.I.F.C.C.G.C.C.H.R.S.K.C.G.M.C.C.K.T}$PEPTIDE1,PEPTIDE1,10:R3-13:R3|PEPTIDE1,PEPTIDE1,11:R3-19:R3|PEPTIDE1,PEPTIDE1,14:R3-22:R3|PEPTIDE1,PEPTIDE1,7:R3-23:R3$$$V2.0',
+      'PEPTIDE1{L.C.G.S.H.L.V.E.A.L.Y.L.V.C.G}|PEPTIDE2{G.I.V.E.Q.C.C.T.S.I.C.S.L.Y.Q.L.E.N.Y.C.N}$PEPTIDE1,PEPTIDE2,2:R3-7:R3|PEPTIDE2,PEPTIDE2,6:R3-11:R3|PEPTIDE1,PEPTIDE2,14:R3-20:R3$$$V2.0',
+      'PEPTIDE1{H.[Aib].E.G.T.F.T.S.D.V.S.S.Y.L.E.G.Q.A.A.K.E.F.I.A.W.L.V.R.G.R.G}|PEPTIDE2{C.[gGlu].G.G}$PEPTIDE1,PEPTIDE2,9:R3-1:R3|PEPTIDE1,PEPTIDE2,20:R3-4:R2$$$V2.0',
+      'PEPTIDE1{F}|PEPTIDE2{[dI].[Trp_Ome].[Asp_OMe].[Cys_Bn].[meG].[Phe_3Cl].[dD].T.[dI].T.[dK].[aG].[3Pal].[xiIle].[meD].[Ala_tBu]}|PEPTIDE3{L.[Pro_4Me3OH].S.[NMe2Abz].Q.[3Pal].[xiIle].D.[Hyp].[Ala_tBu].[dI].[Trp_Ome].[Asp_OMe].N.[meG].[Phe_34diCl].[Phe_34diCl]}$PEPTIDE1,PEPTIDE2,1:R2-9:R3|PEPTIDE2,PEPTIDE2,1:R1-16:R2|PEPTIDE2,PEPTIDE3,1:R3-11:R3|PEPTIDE3,PEPTIDE3,1:R1-17:R2$$$V2.0'
+    ]
+  }
+];

package/src/tests/converters-test.ts

@@ -1,3 +1,5 @@
+/* eslint-disable max-lines */
+/* eslint-disable max-lines-per-function */
 import * as DG from 'datagrok-api/dg';
 import * as grok from 'datagrok-api/grok';
 
@@ -7,6 +9,7 @@ import {ISeqHelper, getSeqHelper} from '@datagrok-libraries/bio/src/utils/seq-he
 import {ISeqHandler} from '@datagrok-libraries/bio/src/utils/macromolecule/seq-handler';
 
 import {ConverterFunc} from './types';
+import {_testBilnToHelm, _testHelmToBiln, bilnToHelmTestsData, helmToBilnTestsData} from './biln-tests';
 
 
 category('converters', () => {
@@ -287,4 +290,15 @@ RNA1{p.r(U)p.r(U)p.r(C)p.r(A)p.r(A)p.r(C)p.r(U)p.r(U)p.r(C)p.r(A)p.r(A)p.r(C)p.p
   test('testHelmLonePhosphorus', async () => {
     await _testConvert(Samples.helmLonePhosphorus, converter(NOTATION.FASTA), Samples.fastaRna);
   });
+
+  for (const sample of bilnToHelmTestsData) {
+    test(`testBilnToHelm_${sample.name}`, async () => {
+      await _testBilnToHelm(sample.biln, sample.helm, seqHelper);
+    });
+  }
+  for (const sample of helmToBilnTestsData) {
+    test(`testHelmToBiln_${sample.name}`, async () => {
+      await _testHelmToBiln(sample.helm, sample.biln, seqHelper);
+    });
+  }
 });

package/src/tests/detectors-tests.ts

@@ -10,6 +10,8 @@ import {ALIGNMENT, ALPHABET, NOTATION, TAGS as bioTAGS} from '@datagrok-librarie
 import {ISeqHelper, getSeqHelper} from '@datagrok-libraries/bio/src/utils/seq-helper';
 
 import {_testNeg, _testPos, DetectorTestData, DfReaderFunc, PosCol} from './utils/detectors-utils';
+import { SeqTemps } from '@datagrok-libraries/bio/src/utils/macromolecule/seq-handler';
+import { _testBilnDetection, detectorTestsDataForBiln } from './biln-tests';
 
 /*
 // snippet to list df columns of semType='Macromolecule' (false positive)
@@ -418,6 +420,11 @@ MWRSWY-CKHPMWRSWY-CKHP`;
     }, seqHelper);
   });
 
+  for (const bilnT of detectorTestsDataForBiln) {
+    test(bilnT.name, async () => {
+      await _testBilnDetection(bilnT.seqs, seqHelper, bilnT.negative);
+    });
+  }
   // test('samplesFastaFasta', async () => {
   //   await _testDf(readSamples(Samples.fastaFasta), {
   //     'sequence': new PosCol(NOTATION.FASTA, ALIGNMENT.SEQ, ALPHABET.PT, 20, false),

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/biln.ts

@@ -0,0 +1,69 @@
+/* eslint-disable max-len */
+/* eslint-disable max-len */
+import * as grok from 'datagrok-api/grok';
+import * as ui from 'datagrok-api/ui';
+import * as DG from 'datagrok-api/dg';
+
+/* eslint-disable max-len */
+import {ISeqHelper} from '@datagrok-libraries/bio/src/utils/seq-helper';
+import {INotationProvider, SplitterFunc} from '@datagrok-libraries/bio/src/utils/macromolecule/types';
+import {NOTATION} from '@datagrok-libraries/bio/src/utils/macromolecule/consts';
+import {CellRendererBackBase} from '@datagrok-libraries/bio/src/utils/cell-renderer-back-base';
+import {MonomerPlacer} from '@datagrok-libraries/bio/src/utils/cell-renderer-monomer-placer';
+import {monomerToShort, splitterAsBiln} from '@datagrok-libraries/bio/src/utils/macromolecule/utils';
+import {_package} from '../package';
+/* eslint-enable max-len */
+
+export class BilnNotationProvider implements INotationProvider {
+  public readonly splitter: SplitterFunc;
+
+  get defaultGapOriginal(): string { return ''; }
+
+  constructor(
+    public readonly separator: string,
+    public readonly seqHelper: ISeqHelper,
+    public readonly seqCol: DG.Column
+  ) {
+    this.splitter = splitterAsBiln.bind(this);
+  }
+
+  setUnits(): void {}
+
+  public getHelm(seq: string, _options?: any): string {
+    // return resPseudoHelm;
+    // generate helm from biln
+    const seqSplitted = this.splitter(seq);
+    const sh = this.seqHelper.getSeqHandler(this.seqCol);
+    return sh.getJoiner({notation: NOTATION.HELM})(seqSplitted);
+  }
+
+  public createCellRendererBack(gridCol: DG.GridColumn | null, tableCol: DG.Column<string>):
+  CellRendererBackBase<string> {
+    const maxLengthOfMonomer = _package.properties.maxMonomerLength || 4;
+    // (_package.bioProperties ? _package.bioProperties.maxMonomerLength : 4) ?? 50;
+    const back = new BilnCellRendererBack(gridCol, tableCol,
+      maxLengthOfMonomer, this.seqHelper);
+
+    back.init().then(() => {});
+    return back;
+  }
+}
+
+export class BilnCellRendererBack extends MonomerPlacer {
+  constructor(
+    gridCol: DG.GridColumn | null, tableCol: DG.Column,
+    maxLengthOfMonomer: number, seqHelper: ISeqHelper
+  ) {
+    super(gridCol, tableCol, _package.logger, maxLengthOfMonomer, () => {
+      const sh = seqHelper.getSeqHandler(tableCol);
+      const {font, fontWidth} = MonomerPlacer.getFontSettings(tableCol);
+      return {
+        seqHandler: sh,
+        font: font,
+        fontCharWidth: fontWidth,
+        separatorWidth: 0,
+        monomerToShort: monomerToShort,
+      };
+    });
+  }
+}

package/src/utils/cell-renderer.ts

@@ -81,10 +81,9 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
 
   getRendererBack(gridCell: DG.GridCell): CellRendererBackBase<string> | null {
     const [gridCol, tableCol, _temp] = getGridCellColTemp<string, any>(gridCell);
-    if (tableCol.meta.units !== NOTATION.CUSTOM)
+    if (_temp.rendererBack)
       return _temp.rendererBack;
     let back: CellRendererBackBase<string> | null = null;
-
     if (this.seqHelper) {
       const sh = this.seqHelper.getSeqHandler(tableCol);
       back = sh.getRendererBack(gridCol, tableCol);
@@ -96,10 +95,8 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
     const colTemp: TempType = gridCell.cell.column.temp;
     colTemp[tempTAGS.currentWord] = gridCell.cell.value;
     gridCell.grid.invalidate();
-    if (gridCell.cell.column.meta.units === NOTATION.CUSTOM) {
-      const back = this.getRendererBack(gridCell);
-      back?.onClick(gridCell, _e);
-    }
+    const back = this.getRendererBack(gridCell);
+    back?.onClick(gridCell, _e);
   }
 
   override onMouseEnter(gridCell: DG.GridCell, e: MouseEvent) {
@@ -195,12 +192,11 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
   }
 
   override render(g: CanvasRenderingContext2D, x: number, y: number, w: number, h: number, gridCell: DG.GridCell, cellStyle: DG.GridCellStyle): void {
-    if (gridCell.cell.column?.meta?.units === NOTATION.CUSTOM) {
-      const back = this.getRendererBack(gridCell);
+    const back = this.getRendererBack(gridCell);
+    if (back)
       back?.render(g, x, y, w, h, gridCell, cellStyle);
-      return;
-    }
-    this.renderInt(g, x, y, w, h, gridCell, cellStyle);
+    else
+      this.renderInt(g, x, y, w, h, gridCell, cellStyle);
   }
 }
 

package/src/utils/convert.ts

@@ -39,6 +39,7 @@ export function convert(col: DG.Column<string> | undefined, seqHelper: ISeqHelpe
     NOTATION.FASTA,
     NOTATION.SEPARATOR,
     NOTATION.HELM,
+    NOTATION.BILN
   ];
   const toggleColumn = (newCol: DG.Column) => {
     srcCol = newCol;
@@ -47,7 +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);
+    filteredNotations = notations;//.filter((e) => e !== currentNotation); TEMPORARY DO NOT FORGET TO UNCOMMENT
     targetNotationInput = ui.input.choice('Convert to', {
       value: filteredNotations[0], items: filteredNotations,
       onValueChanged: toggleSeparator
@@ -70,7 +71,7 @@ export function convert(col: DG.Column<string> | undefined, seqHelper: ISeqHelpe
   });
 
   const separatorArray = ['-', '.', '/'];
-  let filteredNotations = notations.filter((e) => e !== currentNotation);
+  let filteredNotations = notations;//.filter((e) => e !== currentNotation); // TEMPORARY DO NOT FORGET TO UNCOMMENT
 
   const separatorInput = ui.input.choice('Separator', {value: separatorArray[0], items: separatorArray});
 

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/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);
     }