@datagrok/bio 2.22.11 → 2.23.0

package/package.json

@@ -5,7 +5,7 @@
     "name": "Davit Rizhinashvili",
     "email": "drizhinashvili@datagrok.ai"
   },
-  "version": "2.22.11",
+  "version": "2.23.0",
   "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/bio": "^5.55.0",
     "@datagrok-libraries/chem-meta": "^1.2.7",
-    "@datagrok-libraries/math": "^1.2.4",
-    "@datagrok-libraries/ml": "^6.10.4",
+    "@datagrok-libraries/math": "^1.2.6",
+    "@datagrok-libraries/ml": "^6.10.6",
     "@datagrok-libraries/tutorials": "^1.6.1",
-    "@datagrok-libraries/utils": "^4.6.3",
+    "@datagrok-libraries/utils": "^4.6.5",
     "@webgpu/types": "^0.1.40",
     "ajv": "^8.12.0",
     "ajv-errors": "^3.0.0",
@@ -73,7 +73,7 @@
     "@types/wu": "^2.1.44",
     "@typescript-eslint/eslint-plugin": "^8.8.1",
     "@typescript-eslint/parser": "^8.8.1",
-    "datagrok-tools": "^4.14.48",
+    "datagrok-tools": "^4.14.57",
     "eslint": "^8.57.1",
     "eslint-config-google": "^0.14.0",
     "eslint-plugin-rxjs": "^5.0.3",

package/src/package-api.ts

@@ -40,6 +40,17 @@ export namespace funcs {
     return await grok.functions.call('Bio:SequenceTooltip', { col });
   }
 
+  export async function standardiseMonomerLibrary(library: string ): Promise<string> {
+    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

@@ -25,6 +25,15 @@ export async function standardiseMonomerLibrary(library: string) : Promise<strin
   return await PackageFunctions.standardiseMonomerLibrary(library);
 }
 
+//description: Matches molecules in a column with monomers from the selected library(s)
+//input: dataframe table 
+//input: column molecules { semType: Molecule }
+//input: string polymerType = 'PEPTIDE' { choices: ["PEPTIDE","RNA","CHEM"]; caption: Polymer Type }
+//top-menu: Bio | Manage | Match with Monomer Library...
+export async function matchWithMonomerLibrary(table: DG.DataFrame, molecules: DG.Column, polymerType: any) : Promise<void> {
+  await PackageFunctions.matchWithMonomerLibrary(table, molecules, polymerType);
+}
+
 //output: object monomerLib
 export function getBioLib() : any {
   return PackageFunctions.getBioLib();
@@ -101,6 +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 }
@@ -126,8 +152,8 @@ export function macromoleculeDifferenceCellRenderer() : any {
   return PackageFunctions.macromoleculeDifferenceCellRenderer();
 }
 
-//input: string alignType { choices: ['Local alignment','Global alignment'] }
-//input: string alignTable { choices: ['AUTO','NUCLEOTIDES','BLOSUM45','BLOSUM50','BLOSUM62','BLOSUM80','BLOSUM90','PAM30','PAM70','PAM250','SCHNEIDER','TRANS'] }
+//input: string alignType { choices: ["Local alignment","Global alignment"] }
+//input: string alignTable { choices: ["AUTO","NUCLEOTIDES","BLOSUM45","BLOSUM50","BLOSUM62","BLOSUM80","BLOSUM90","PAM30","PAM70","PAM250","SCHNEIDER","TRANS"] }
 //input: double gap 
 //input: string seq1 
 //input: string seq2 
@@ -182,9 +208,9 @@ export async function getRegionTopMenu(table: DG.DataFrame, sequence: DG.Column,
 //input: dataframe table { description: Input data table }
 //input: string molecules { semType: Macromolecule; description: Input data table }
 //input: column activities 
-//input: double similarity { default: 80; description: Similarity cutoff }
-//input: string methodName { choices: ['UMAP','t-SNE'] }
-//input: string similarityMetric { choices: ['Hamming','Levenshtein','Monomer chemical distance'] }
+//input: double similarity = 80 { description: Similarity cutoff }
+//input: string methodName { choices: ["UMAP","t-SNE"] }
+//input: string similarityMetric { choices: ["Hamming","Levenshtein","Monomer chemical distance"] }
 //input: func preprocessingFunction 
 //input: object options { optional: true }
 //input: bool demo { optional: true }
@@ -198,9 +224,9 @@ export async function activityCliffs(table: DG.DataFrame, molecules: DG.Column<a
 //tags: dim-red-preprocessing-function
 //input: column col { semType: Macromolecule }
 //input: string metric 
-//input: double gapOpen { default: 1; caption: Gap open penalty; optional: true }
-//input: double gapExtend { default: 0.6; caption: Gap extension penalty; optional: true }
-//input: string fingerprintType { caption: Fingerprint type; default: Morgan; choices: ['Morgan','RDKit','Pattern','AtomPair','MACCS','TopologicalTorsion']; optional: true }
+//input: double gapOpen = 1 { caption: Gap open penalty; optional: true }
+//input: double gapExtend = 0.6 { caption: Gap extension penalty; optional: true }
+//input: string fingerprintType = 'Morgan' { caption: Fingerprint type; choices: ["Morgan","RDKit","Pattern","AtomPair","MACCS","TopologicalTorsion"]; optional: true }
 //output: object result
 //meta.supportedSemTypes: Macromolecule
 //meta.supportedTypes: string
@@ -225,12 +251,12 @@ export async function helmPreprocessingFunction(col: DG.Column<any>, _metric: an
 //description: Creates 2D sequence space with projected sequences by pairwise distance
 //input: dataframe table 
 //input: column molecules { semType: Macromolecule }
-//input: string methodName { choices: ['UMAP','t-SNE'] }
-//input: string similarityMetric { choices: ['Hamming','Levenshtein','Monomer chemical distance'] }
-//input: bool plotEmbeddings { default: true }
+//input: string methodName { choices: ["UMAP","t-SNE"] }
+//input: string similarityMetric { choices: ["Hamming","Levenshtein","Monomer chemical distance"] }
+//input: bool plotEmbeddings = true 
 //input: func preprocessingFunction { optional: true }
 //input: object options { optional: true }
-//input: bool clusterEmbeddings { optional: true; default: true }
+//input: bool clusterEmbeddings = true { optional: true }
 //input: bool isDemo { optional: true }
 //top-menu: Bio | Analyze | Sequence Space...
 //editor: Bio:SequenceSpaceEditor
@@ -242,8 +268,8 @@ export async function sequenceSpaceTopMenu(table: DG.DataFrame, molecules: DG.Co
 //description: Converts sequences to molblocks
 //input: dataframe table { description: Input data table }
 //input: column seqCol { semType: Macromolecule; caption: Sequence }
-//input: bool nonlinear { default: false; caption: Non-linear; description: Slower mode for cycling/branching HELM structures }
-//input: bool highlight { default: false; caption: Highlight monomers; description: Highlight monomers' substructures of the molecule }
+//input: bool nonlinear = false { 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> {
   await PackageFunctions.toAtomicLevel(table, seqCol, nonlinear, highlight);
@@ -318,7 +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();
 }
@@ -338,7 +364,7 @@ export function monomerCellRenderer() : any {
   return PackageFunctions.monomerCellRenderer();
 }
 
-//input: string path { choices: ['Demo:Files/','System:AppData/'] }
+//input: string path { choices: ["Demo:Files/","System:AppData/"] }
 //output: dataframe result
 export async function testDetectMacromolecule(path: string) : Promise<any> {
   return await PackageFunctions.testDetectMacromolecule(path);
@@ -408,7 +434,7 @@ export function SubsequenceSearchTopMenu(macromolecules: DG.Column) : void {
   PackageFunctions.SubsequenceSearchTopMenu(macromolecules);
 }
 
-//name: Identity Scoring
+//name: Identity
 //description: Adds a column with fraction of matching monomers
 //input: dataframe table { description: Table containing Macromolecule column }
 //input: column macromolecule { semType: Macromolecule; description: Sequences to score }
@@ -419,7 +445,7 @@ export async function sequenceIdentityScoring(table: DG.DataFrame, macromolecule
   return await PackageFunctions.sequenceIdentityScoring(table, macromolecule, reference);
 }
 
-//name: Similarity Scoring
+//name: Similarity
 //description: Adds a column with similarity scores, calculated as sum of monomer fingerprint similarities
 //input: dataframe table { description: Table containing Macromolecule column }
 //input: column macromolecule { semType: Macromolecule; description: Sequences to score }
@@ -486,30 +512,37 @@ export function bioSubstructureFilterTest() : any {
   return PackageFunctions.bioSubstructureFilterTest();
 }
 
+//name: webLogoLargeApp
 export async function webLogoLargeApp() : Promise<void> {
   await PackageFunctions.webLogoLargeApp();
 }
 
+//name: webLogoAggApp
 export async function webLogoAggApp() : Promise<void> {
   await PackageFunctions.webLogoAggApp();
 }
 
+//name: getRegionApp
 export async function getRegionApp() : Promise<void> {
   await PackageFunctions.getRegionApp();
 }
 
+//name: getRegionHelmApp
 export async function getRegionHelmApp() : Promise<void> {
   await PackageFunctions.getRegionHelmApp();
 }
 
+//name: longSeqTableSeparator
 export function longSeqTableSeparator() : void {
   PackageFunctions.longSeqTableSeparator();
 }
 
+//name: longSeqTableFasta
 export function longSeqTableFasta() : void {
   PackageFunctions.longSeqTableFasta();
 }
 
+//name: longSeqTableHelm
 export function longSeqTableHelm() : void {
   PackageFunctions.longSeqTableHelm();
 }
@@ -523,15 +556,14 @@ export function addCopyMenu(cell: any, menu: any) : void {
 //description: Sequence similarity tracking and evaluation dataset diversity
 //meta.demoPath: Bioinformatics | Similarity, Diversity
 //meta.path: /apps/Tutorials/Demo/Bioinformatics/Similarity,%20Diversity
-//meta.demoSkip: GROK-14320
 export async function demoBioSimilarityDiversity() : Promise<void> {
   await PackageFunctions.demoBioSimilarityDiversity();
 }
 
 //description: Exploring sequence space of Macromolecules, comparison with hierarchical clustering results
+//meta.isDemoDashboard: true
 //meta.demoPath: Bioinformatics | Sequence Space
 //meta.path: /apps/Tutorials/Demo/Bioinformatics/Sequence%20Space
-//meta.demoSkip: GROK-14320
 export async function demoBioSequenceSpace() : Promise<void> {
   await PackageFunctions.demoBioSequenceSpace();
 }
@@ -539,7 +571,6 @@ export async function demoBioSequenceSpace() : Promise<void> {
 //description: Activity Cliffs analysis on Macromolecules data
 //meta.demoPath: Bioinformatics | Activity Cliffs
 //meta.path: /apps/Tutorials/Demo/Bioinformatics/Activity%20Cliffs
-//meta.demoSkip: GROK-14320
 export async function demoBioActivityCliffs() : Promise<void> {
   await PackageFunctions.demoBioActivityCliffs();
 }
@@ -547,7 +578,6 @@ export async function demoBioActivityCliffs() : Promise<void> {
 //description: Atomic level structure of Macromolecules
 //meta.demoPath: Bioinformatics | Atomic Level
 //meta.path: /apps/Tutorials/Demo/Bioinformatics/Atomic%20Level
-//meta.demoSkip: GROK-14320
 export async function demoBioAtomicLevel() : Promise<void> {
   await PackageFunctions.demoBioAtomicLevel();
 }
@@ -578,7 +608,7 @@ export async function seqIdentity(seq: string, ref: string) : Promise<any> {
 
 //input: file file 
 //input: string colName 
-//input: double probeCount { default: 100 }
+//input: double probeCount = 100 
 export async function detectMacromoleculeProbe(file: DG.FileInfo, colName: string, probeCount: number) : Promise<void> {
   await PackageFunctions.detectMacromoleculeProbe(file, colName, probeCount);
 }
@@ -590,7 +620,7 @@ export async function getSeqHelper() : Promise<any> {
 
 //input: dataframe df 
 //input: column helmCol 
-//input: bool chiralityEngine { default: true }
+//input: bool chiralityEngine = true 
 //output: column result
 export async function getMolFromHelm(df: DG.DataFrame, helmCol: DG.Column<any>, chiralityEngine: boolean) : Promise<any> {
   return await PackageFunctions.getMolFromHelm(df, helmCol, chiralityEngine);

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';
@@ -70,12 +70,14 @@ import {GetRegionFuncEditor} from './utils/get-region-func-editor';
 import {sequenceToMolfile} from './utils/sequence-to-mol';
 import {detectMacromoleculeProbeDo} from './utils/detect-macromolecule-probe';
 import {getMolColumnFromHelm} from './utils/helm-to-molfile/utils';
-import {MonomerManager, standardizeMonomerLibrary} from './utils/monomer-lib/monomer-manager/monomer-manager';
+import {matchMoleculesWithMonomers, MonomerManager, standardizeMonomerLibrary} from './utils/monomer-lib/monomer-manager/monomer-manager';
 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 {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';
 
@@ -143,6 +145,14 @@ export class PackageFunctions {
     return await standardizeMonomerLibrary(library);
   }
 
+  @grok.decorators.func({'top-menu': 'Bio | Manage | Match with Monomer Library...', description: 'Matches molecules in a column with monomers from the selected library(s)',})
+  static async matchWithMonomerLibrary(table: DG.DataFrame,
+      @grok.decorators.param({type: 'column', options: {semType: 'Molecule'}})molecules: DG.Column,
+      @grok.decorators.param({type: 'string', options: {choices: ['PEPTIDE', 'RNA', 'CHEM'], initialValue: 'PEPTIDE', caption: 'Polymer Type'}})polymerType: PolymerType = 'PEPTIDE') {
+    const matchDF = await matchMoleculesWithMonomers(table, molecules.name, _package.monomerLib, polymerType);
+    grok.shell.addTableView(matchDF);
+  }
+
   // Keep for backward compatibility
   @grok.decorators.func({outputs: [{type: 'object', name: 'monomerLib'}]})
   static getBioLib(): IMonomerLib {
@@ -288,6 +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'})
@@ -748,7 +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];
@@ -939,14 +992,14 @@ export class PackageFunctions {
   }
 
   @grok.decorators.func({
-    name: 'Identity Scoring',
+    name: 'Identity',
     description: 'Adds a column with fraction of matching monomers',
     'top-menu': 'Bio | Calculate | Identity...',
   })
   static async sequenceIdentityScoring(
-    @grok.decorators.param({options: {description: 'Table containing Macromolecule column'}})table: DG.DataFrame,
+    @grok.decorators.param({options: {description: 'Table containing Macromolecule column'}}) table: DG.DataFrame,
     @grok.decorators.param({options: {semType: 'Macromolecule', description: 'Sequences to score'}}) macromolecule: DG.Column,
-    @grok.decorators.param({options: {description: 'Sequence,matching column format'}})reference: string
+    @grok.decorators.param({options: {description: 'Sequence,matching column format'}}) reference: string
   ): Promise<DG.Column<number>> {
     const seqHelper = _package.seqHelper;
     const scores = calculateScoresWithEmptyValues(table, macromolecule, reference, SCORE.IDENTITY, seqHelper);
@@ -954,14 +1007,14 @@ export class PackageFunctions {
   }
 
   @grok.decorators.func({
-    name: 'Similarity Scoring',
+    name: 'Similarity',
     description: 'Adds a column with similarity scores, calculated as sum of monomer fingerprint similarities',
     'top-menu': 'Bio | Calculate | Similarity...',
   })
   static async sequenceSimilarityScoring(
-    @grok.decorators.param({options: {description: 'Table containing Macromolecule column'}})table: DG.DataFrame,
+    @grok.decorators.param({options: {description: 'Table containing Macromolecule column'}}) table: DG.DataFrame,
     @grok.decorators.param({options: {semType: 'Macromolecule', description: 'Sequences to score'}}) macromolecule: DG.Column,
-    @grok.decorators.param({options: {description: 'Sequence,matching column format'}})reference: string
+    @grok.decorators.param({options: {description: 'Sequence,matching column format'}}) reference: string
   ): Promise<DG.Column<number>> {
     const seqHelper = _package.seqHelper;
     const scores = calculateScoresWithEmptyValues(table, macromolecule, reference, SCORE.SIMILARITY, seqHelper);
@@ -1137,7 +1190,6 @@ export class PackageFunctions {
     description: 'Sequence similarity tracking and evaluation dataset diversity',
     demoPath: 'Bioinformatics | Similarity, Diversity',
     path: '/apps/Tutorials/Demo/Bioinformatics/Similarity,%20Diversity',
-    demoSkip: 'GROK-14320'
   })
   static async demoBioSimilarityDiversity(): Promise<void> {
     await demoBioSimDiv();
@@ -1147,7 +1199,9 @@ export class PackageFunctions {
     description: 'Exploring sequence space of Macromolecules, comparison with hierarchical clustering results',
     demoPath: 'Bioinformatics | Sequence Space',
     path: '/apps/Tutorials/Demo/Bioinformatics/Sequence%20Space',
-    demoSkip: 'GROK-14320'
+    meta: {
+      isDemoDashboard: 'true'
+    }
   })
   static async demoBioSequenceSpace(): Promise<void> {
     await demoSeqSpace();
@@ -1157,7 +1211,6 @@ export class PackageFunctions {
     description: 'Activity Cliffs analysis on Macromolecules data',
     demoPath: 'Bioinformatics | Activity Cliffs',
     path: '/apps/Tutorials/Demo/Bioinformatics/Activity%20Cliffs',
-    demoSkip: 'GROK-14320'
   })
   static async demoBioActivityCliffs(): Promise<void> {
     await demoActivityCliffsCyclic();
@@ -1167,7 +1220,6 @@ export class PackageFunctions {
     description: 'Atomic level structure of Macromolecules',
     demoPath: 'Bioinformatics | Atomic Level',
     path: '/apps/Tutorials/Demo/Bioinformatics/Atomic%20Level',
-    demoSkip: 'GROK-14320'
   })
   static async demoBioAtomicLevel(): Promise<void> {
     await demoToAtomicLevel();

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);
+    });
+  }
 });