@datagrok/bio 2.13.3 → 2.13.6

package/files/cache_config.json

@@ -0,0 +1,7 @@
+[
+  {
+    "path": "/monomer-libraries",
+    "invalidateOn": "0 0 * * *",
+    "preflight": true
+  }
+]

package/package.json

@@ -5,7 +5,7 @@
     "name": "Aleksandr Tanas",
     "email": "atanas@datagrok.ai"
   },
-  "version": "2.13.3",
+  "version": "2.13.6",
   "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",
@@ -37,18 +37,18 @@
   ],
   "dependencies": {
     "@biowasm/aioli": "^3.1.0",
-    "@datagrok-libraries/bio": "^5.42.3",
+    "@datagrok-libraries/bio": "^5.42.6",
     "@datagrok-libraries/chem-meta": "^1.2.5",
     "@datagrok-libraries/math": "^1.1.5",
     "@datagrok-libraries/ml": "^6.6.12",
     "@datagrok-libraries/tutorials": "^1.3.12",
-    "@datagrok-libraries/utils": "^4.2.11",
+    "@datagrok-libraries/utils": "^4.2.12",
     "@webgpu/types": "^0.1.40",
     "ajv": "^8.12.0",
     "ajv-errors": "^3.0.0",
     "cash-dom": "^8.0.0",
     "css-loader": "^6.7.3",
-    "datagrok-api": "^1.18.6",
+    "datagrok-api": "^1.20.0",
     "dayjs": "^1.11.4",
     "fastest-levenshtein": "^1.0.16",
     "openchemlib": "^7.2.3",
@@ -58,8 +58,8 @@
     "wu": "latest"
   },
   "devDependencies": {
-    "@datagrok-libraries/helm-web-editor": "^1.1.5",
-    "@datagrok-libraries/js-draw-lite": "^0.0.3",
+    "@datagrok-libraries/helm-web-editor": "^1.1.6",
+    "@datagrok-libraries/js-draw-lite": "^0.0.4",
     "@datagrok/chem": "^1.9.2",
     "@datagrok/dendrogram": "^1.2.29",
     "@datagrok/helm": "^2.2.1",
@@ -70,12 +70,13 @@
     "datagrok-tools": "latest",
     "eslint": "latest",
     "eslint-config-google": "latest",
-    "source-map-loader": "^4.0.1",
-    "ts-loader": "^9.2.5",
-    "typescript": "^4.8.4",
-    "webpack": "^5.76.3",
+    "eslint-plugin-rxjs": "latest",
+    "source-map-loader": "latest",
+    "ts-loader": "^9.5.1",
+    "typescript": "^5.5.3",
+    "webpack": "^5.92.1",
     "webpack-bundle-analyzer": "latest",
-    "webpack-cli": "^4.9.1"
+    "webpack-cli": "^5.1.4"
   },
   "scripts": {
     "link-api": "npm link datagrok-api",

package/src/analysis/sequence-activity-cliffs.ts

@@ -164,7 +164,7 @@ export function createLinesGrid(df: DG.DataFrame, colNames: string[]): DG.Grid {
   const seqDiffCol = DG.Column.string('seq_diff', df.rowCount)
     .init((i) => `${df.get(colNames[0], i)}#${df.get(colNames[1], i)}`);
   seqDiffCol.semType = 'MacromoleculeDifference';
-  seqDiffCol.setTag(DG.TAGS.UNITS, df.col(colNames[0])!.getTag(DG.TAGS.UNITS));
+  seqDiffCol.meta.units = df.col(colNames[0])!.meta.units;
   seqDiffCol.setTag(bioTAGS.separator, df.col(colNames[0])!.getTag(bioTAGS.separator));
   df.columns.add(seqDiffCol);
   const grid = df.plot.grid();

package/src/function-edtiors/split-to-monomers-editor.ts

@@ -20,14 +20,13 @@ export class SplitToMonomersFunctionEditor {
   }
 
   constructor() {
-    this.tableInput = ui.tableInput('Table', grok.shell.tv.dataFrame, undefined, () => {
+    this.tableInput = ui.input.table('Table', {value: grok.shell.tv.dataFrame, onValueChanged: () => {
       this.onTableInputChanged();
-    });
+    }});
     //TODO: remove when the new version of datagrok-api is available
     const seqColValue = this.tableInput.value!.columns.bySemType(DG.SEMTYPE.MACROMOLECULE);
-    const seqColOptions = {filter: (col: DG.Column) => col.semType === DG.SEMTYPE.MACROMOLECULE};
-    //@ts-ignore
-    this.seqColInput = ui.columnInput('Sequence', this.tableInput.value!, seqColValue, null, seqColOptions);
+    this.seqColInput = ui.input.column('Sequence', {table: this.tableInput.value!, value: seqColValue,
+      filter: (col: DG.Column) => col.semType === DG.SEMTYPE.MACROMOLECULE});
 
     this.funcParamsDiv = ui.inputs([
       this.tableInput,
@@ -36,7 +35,7 @@ export class SplitToMonomersFunctionEditor {
   }
 
   onTableInputChanged(): void {
-    this.seqColInput = ui.columnInput('Sequence', this.tableInput.value!,
-      this.tableInput.value!.columns.bySemType(DG.SEMTYPE.MACROMOLECULE));
+    this.seqColInput = ui.input.column('Sequence', {table: this.tableInput.value!,
+      value: this.tableInput.value!.columns.bySemType(DG.SEMTYPE.MACROMOLECULE)});
   }
 }

package/src/package-types.ts

@@ -3,8 +3,9 @@ import * as DG from 'datagrok-api/dg';
 import * as ui from 'datagrok-api/ui';
 
 import {Observable, Subject} from 'rxjs';
+
 import {errInfo} from '@datagrok-libraries/bio/src/utils/err-info';
-import {Group} from 'datagrok-api/dg';
+import {LoggerWrapper} from '@datagrok-libraries/bio/src/utils/logger';
 
 /** Names of package properties/settings declared in properties section of {@link './package.json'} */
 export const enum BioPackagePropertiesNames {
@@ -20,31 +21,31 @@ export class BioPackageProperties extends Map<string, any> {
   public get onPropertyChanged(): Observable<string> { return this._onPropertyChanged; }
 
   /** Monomer symbol maximum length displayed, null for unlimited. */
-  public get MaxMonomerLength(): number | null {
+  public get maxMonomerLength(): number | null {
     const vs = super.get(BioPackagePropertiesNames.MaxMonomerLength);
     return vs === 'long' ? null : parseInt(vs);
   }
 
-  public set MaxMonomerLength(value: number | null) {
+  public set maxMonomerLength(value: number | null) {
     const vs = value === null ? 'long' : value.toString();
     super.set(BioPackagePropertiesNames.MaxMonomerLength, vs);
     this._onPropertyChanged.next(BioPackagePropertiesNames.MaxMonomerLength);
   }
 
-  public get TooltipWebLogo(): boolean {
+  public get tooltipWebLogo(): boolean {
     return super.get(BioPackagePropertiesNames.TooltipWebLogo) as boolean;
   }
 
-  public set TooltipWebLogo(value: boolean) {
+  public set tooltipWebLogo(value: boolean) {
     super.set(BioPackagePropertiesNames.TooltipWebLogo, value);
     this._onPropertyChanged.next(BioPackagePropertiesNames.TooltipWebLogo);
   }
 
-  public get DefaultSeparator(): string {
+  public get defaultSeparator(): string {
     return super.get(BioPackagePropertiesNames.DefaultSeparator) as string;
   }
 
-  public set DefaultSeparator(value: string) {
+  public set defaultSeparator(value: string) {
     if (value.length !== 1) throw new Error('The separator must be of length one.');
     super.set(BioPackagePropertiesNames.DefaultSeparator, value);
     this._onPropertyChanged.next(BioPackagePropertiesNames.DefaultSeparator);
@@ -66,6 +67,12 @@ export class BioPackage extends DG.Package {
 
   public get initialized(): boolean { return this._initialized; }
 
+  constructor(opts: { debug: boolean } = {debug: false}) {
+    super();
+    // @ts-ignore
+    super._logger = new LoggerWrapper(super.logger, opts.debug);
+  }
+
   public completeInit(): void { this._initialized = true; }
 
   handleErrorUI(err: any) {

package/src/package.ts

@@ -447,7 +447,7 @@ export async function activityCliffs(table: DG.DataFrame, molecules: DG.Column<s
     return;
   const axesNames = getEmbeddingColsNames(table);
   const tags = {
-    'units': molecules.getTag(DG.TAGS.UNITS),
+    'units': molecules.meta.units!,
     'aligned': molecules.getTag(bioTAGS.aligned),
     'separator': molecules.getTag(bioTAGS.separator),
     'alphabet': molecules.getTag(bioTAGS.alphabet),
@@ -665,8 +665,8 @@ export async function compositionAnalysis(): Promise<void> {
   } else if (colList.length > 1) {
     const colListNames: string [] = colList.map((col) => col.name);
     const selectedCol = colList.find((c) => { return SeqHandler.forColumn(c).isMsa(); });
-    const colInput: DG.InputBase = ui.choiceInput(
-      'Column', selectedCol ? selectedCol.name : colListNames[0], colListNames);
+    const colInput: DG.InputBase = ui.input.choice(
+      'Column', {value: selectedCol ? selectedCol.name : colListNames[0], items: colListNames});
     ui.dialog({
       title: 'Composition Analysis',
       helpUrl: 'https://datagrok.ai/help/datagrok/solutions/domains/bio/#sequence-composition',
@@ -750,13 +750,13 @@ export async function testDetectMacromolecule(path: string): Promise<DG.DataFram
         const semType = await grok.functions.call('Bio:detectMacromolecule', {col: col});
         if (semType === DG.SEMTYPE.MACROMOLECULE) {
           //console.warn(`file: ${fileInfo.path}, column: ${col.name}, ` +
-          //  `semType: ${semType}, units: ${col.getTag(DG.TAGS.UNITS)}`);
+          //  `semType: ${semType}, units: ${col.meta.units}`);
           // console.warn('file: "' + fileInfo.path + '", semType: "' + semType + '", ' +
-          //   'units: "' + col.getTag(DG.TAGS.UNITS) + '"');
+          //   'units: "' + col.meta.units + '"');
 
           res.push({
             file: fileInfo.path, result: 'detected', column: col.name,
-            message: `units: ${col.getTag(DG.TAGS.UNITS)}`,
+            message: `units: ${col.meta.units}`,
           });
         }
       }

package/src/substructure-search/substructure-search.ts

@@ -54,7 +54,7 @@ export class SubstructureSearchDialog {
   }
 
   updateNotationDiv(): void {
-    this.units = this.col.getTag(DG.TAGS.UNITS);
+    this.units = this.col.meta.units!;
     this.separator = this.col.getTag(bioTAGS.separator);
     const notationDiv = this.dialog.root.getElementsByClassName('notation-text')[0];
     if (notationDiv)
@@ -63,26 +63,25 @@ export class SubstructureSearchDialog {
 
   createUI(): void {
     const dataframe = grok.shell.tv.dataFrame;
-    const seqColOptions = {filter: (col: DG.Column) => col.semType === DG.SEMTYPE.MACROMOLECULE};
-    this.columnsInput = ui.columnInput('Column', dataframe, this.col, (column: DG.Column) => {
-      this.col = column;
+    this.columnsInput = ui.input.column('Column', {table: dataframe, value: this.col, onValueChanged: (input) => {
+      this.col = input.value;
       this.updateNotationDiv();
       this.updateInputs();
-    }, seqColOptions);
+    }, filter: (col: DG.Column) => col.semType === DG.SEMTYPE.MACROMOLECULE});
 
-    this.substructureInput = ui.stringInput('Substructure', '');
+    this.substructureInput = ui.input.string('Substructure', {value: ''});
 
     this.editHelmLink = ui.link('Edit helm', () => this.editHelmLinkAction(), undefined, {style: {position: 'relative', left: '95px'}});
 
     const df = DG.DataFrame.create(1);
     df.columns.addNewString(SUBSTR_HELM_COL_NAME).init((_i) => '');
     df.col(SUBSTR_HELM_COL_NAME)!.semType = this.col.semType;
-    df.col(SUBSTR_HELM_COL_NAME)!.setTag(DG.TAGS.UNITS, NOTATION.HELM);
+    df.col(SUBSTR_HELM_COL_NAME)!.meta.units = NOTATION.HELM;
     this.grid = df.plot.grid();
-    this.separatorInput = ui.stringInput('Separator', this.separator);
+    this.separatorInput = ui.input.string('Separator', {value: this.separator});
 
     this.inputsDiv = ui.div();
-    this.units = this.col.getTag(DG.TAGS.UNITS);
+    this.units = this.col.meta.units!;
     this.separator = this.col.getTag(bioTAGS.separator);
     this.updateInputs();
 
@@ -135,7 +134,7 @@ export async function helmSubstructureSearch(substructure: string, col: DG.Colum
     await invalidateMols(col, true);
   const substructureCol: DG.Column<string> = DG.Column.string('helm', 1).init((_i) => substructure);
   substructureCol.semType = DG.SEMTYPE.MACROMOLECULE;
-  substructureCol.setTag(DG.TAGS.UNITS, NOTATION.HELM);
+  substructureCol.meta.units = NOTATION.HELM;
   const substructureMolsCol =
     await getMonomericMols(substructureCol, true, col.temp[MONOMERIC_COL_TAGS.MONOMERS_DICT]);
   const matchesCol = await grok.functions.call('Chem:searchSubstructure', {

package/src/tests/WebLogo-positions-test.ts

@@ -29,7 +29,7 @@ ATC-G-TTGC--
 
     const seqCol: DG.Column = df.getCol('seq');
     seqCol.semType = DG.SEMTYPE.MACROMOLECULE;
-    seqCol.setTag(DG.TAGS.UNITS, NOTATION.FASTA);
+    seqCol.meta.units = NOTATION.FASTA;
     seqCol.setTag(bioTAGS.alphabet, ALPHABET.DNA);
     seqCol.setTag(bioTAGS.aligned, 'SEQ.MSA');
 
@@ -77,7 +77,7 @@ ATC-G-TTGC--
 
     const seqCol: DG.Column = df.getCol('seq');
     seqCol.semType = DG.SEMTYPE.MACROMOLECULE;
-    seqCol.setTag(DG.TAGS.UNITS, NOTATION.FASTA);
+    seqCol.meta.units = NOTATION.FASTA;
     seqCol.setTag(bioTAGS.alphabet, ALPHABET.DNA);
     seqCol.setTag(bioTAGS.aligned, 'SEQ');
 
@@ -120,7 +120,7 @@ ATC-G-TTGC--
 
     const seqCol: DG.Column = df.getCol('seq');
     seqCol.semType = DG.SEMTYPE.MACROMOLECULE;
-    seqCol.setTag(DG.TAGS.UNITS, NOTATION.FASTA);
+    seqCol.meta.units = NOTATION.FASTA;
     seqCol.setTag(bioTAGS.alphabet, ALPHABET.DNA);
     seqCol.setTag(bioTAGS.aligned, 'SEQ.MSA');
 
@@ -191,8 +191,8 @@ ATC-G-TTGC--
   test('empty', async () => {
     const df: DG.DataFrame = DG.DataFrame.fromColumns([(() => {
       const col = DG.Column.fromStrings('seq', []);
-      col.setTag(DG.TAGS.SEMTYPE, DG.SEMTYPE.MACROMOLECULE);
-      col.setTag(DG.TAGS.UNITS, NOTATION.FASTA);
+      col.semType = DG.SEMTYPE.MACROMOLECULE;
+      col.meta.units = NOTATION.FASTA;
       col.setTag(bioTAGS.alphabet, ALPHABET.DNA);
       return col;
     })()]);
@@ -222,7 +222,7 @@ function buildDfWithSeqCol(csv: string, notation: NOTATION, alphabet: ALPHABET,
 
   const seqCol: DG.Column = df.getCol('seq');
   seqCol.semType = DG.SEMTYPE.MACROMOLECULE;
-  seqCol.setTag(DG.TAGS.UNITS, notation);
+  seqCol.meta.units = notation;
   seqCol.setTag(bioTAGS.alphabet, alphabet);
   seqCol.setTag(bioTAGS.aligned, aligned);
 

package/src/tests/activity-cliffs-tests.ts

@@ -13,21 +13,24 @@ import {
   getUserLibSettings, setUserLibSettings, setUserLibSettingsForTests
 } from '@datagrok-libraries/bio/src/monomer-works/lib-settings';
 import {UserLibSettings} from '@datagrok-libraries/bio/src/monomer-works/types';
+import {DimReductionMethods} from '@datagrok-libraries/ml/src/multi-column-dimensionality-reduction/types';
+import {getHelmHelper, IHelmHelper} from '@datagrok-libraries/bio/src/helm/helm-helper';
 
 import {_package} from '../package-test';
-import {DimReductionMethods} from '@datagrok-libraries/ml/src/multi-column-dimensionality-reduction/types';
 
 
 category('activityCliffs', async () => {
   let viewList: DG.ViewBase[] = [];
   let dfList: DG.DataFrame[] = [];
 
+  let helmHelper: IHelmHelper;
   let monomerLibHelper: IMonomerLibHelper;
   /** Backup actual user's monomer libraries settings */
   let userLibSettings: UserLibSettings;
   const seqEncodingFunc = DG.Func.find({name: 'macromoleculePreprocessingFunction', package: 'Bio'})[0];
   const helmEncodingFunc = DG.Func.find({name: 'helmPreprocessingFunction', package: 'Bio'})[0];
   before(async () => {
+    helmHelper = await getHelmHelper(); // init Helm package
     monomerLibHelper = await getMonomerLibHelper();
     userLibSettings = await getUserLibSettings();
 
@@ -59,7 +62,7 @@ category('activityCliffs', async () => {
 
     await _testActivityCliffsOpen(actCliffsDf, DimReductionMethods.UMAP,
       'sequence', 'Activity', 90, cliffsNum, MmDistanceFunctionsNames.LEVENSHTEIN, seqEncodingFunc);
-  });
+  }, {benchmark: true});
 
   test('activityCliffsWithEmptyRows', async () => {
     const actCliffsDfWithEmptyRows = await readDataframe('tests/100_3_clustests_empty_vals.csv');

package/src/tests/bio-tests.ts

@@ -58,7 +58,7 @@ PEPTIDE1{meI}$$$$`;
     const df: DG.DataFrame = DG.DataFrame.fromCsv(csv);
     const seqCol: DG.Column = df.getCol('seq')!;
     seqCol.semType = DG.SEMTYPE.MACROMOLECULE;
-    seqCol.setTag(DG.TAGS.UNITS, NOTATION.HELM);
+    seqCol.meta.units = NOTATION.HELM;
     const stats = getStatsForCol(seqCol, 1, splitterAsHelm);
 
     expectObject(stats.freq, {
@@ -129,7 +129,7 @@ export async function _testGetStats(csvDfN1: string) {
   const dfN1: DG.DataFrame = DG.DataFrame.fromCsv(csvDfN1);
   const seqCol: DG.Column = dfN1.col('seq')!;
   seqCol.semType = DG.SEMTYPE.MACROMOLECULE;
-  seqCol.setTag(DG.TAGS.UNITS, NOTATION.FASTA);
+  seqCol.meta.units = NOTATION.FASTA;
   const stats = getStatsForCol(seqCol, 5, splitterAsFasta);
 
   expectObject(stats.freq, {
@@ -159,7 +159,7 @@ export async function _testPickupPaletteN1(csvDfN1: string) {
   const df: DG.DataFrame = DG.DataFrame.fromCsv(csvDfN1);
   const col: DG.Column = df.col('seq')!;
   col.semType = DG.SEMTYPE.MACROMOLECULE;
-  col.setTag(DG.TAGS.UNITS, NOTATION.FASTA);
+  col.meta.units = NOTATION.FASTA;
   const cp = pickUpPalette(col);
 
   expect(cp instanceof NucleotidesPalettes, true);
@@ -169,7 +169,7 @@ export async function _testPickupPaletteN1e(csvDfN1e: string) {
   const df: DG.DataFrame = DG.DataFrame.fromCsv(csvDfN1e);
   const col: DG.Column = df.col('seq')!;
   col.semType = DG.SEMTYPE.MACROMOLECULE;
-  col.setTag(DG.TAGS.UNITS, NOTATION.FASTA);
+  col.meta.units = NOTATION.FASTA;
   const cp = pickUpPalette(col);
 
   expect(cp instanceof NucleotidesPalettes, true);
@@ -179,7 +179,7 @@ export async function _testPickupPaletteAA1(csvDfAA1: string) {
   const df: DG.DataFrame = DG.DataFrame.fromCsv(csvDfAA1);
   const col: DG.Column = df.col('seq')!;
   col.semType = DG.SEMTYPE.MACROMOLECULE;
-  col.setTag(DG.TAGS.UNITS, NOTATION.FASTA);
+  col.meta.units = NOTATION.FASTA;
   const cp = pickUpPalette(col);
 
   expect(cp instanceof AminoacidsPalettes, true);
@@ -189,7 +189,7 @@ export async function _testPickupPaletteX(csvDfX: string) {
   const df: DG.DataFrame = DG.DataFrame.fromCsv(csvDfX);
   const col: DG.Column = df.col('seq')!;
   col.semType = DG.SEMTYPE.MACROMOLECULE;
-  col.setTag(DG.TAGS.UNITS, NOTATION.FASTA);
+  col.meta.units = NOTATION.FASTA;
   const cp = pickUpPalette(col);
 
   expect(cp instanceof UnknownSeqPalette, true);

package/src/tests/checkInputColumn-tests.ts

@@ -18,7 +18,7 @@ seq4`;
     const df: DG.DataFrame = DG.DataFrame.fromCsv(csv);
     const col: DG.Column = df.getCol('seq');
     col.semType = DG.SEMTYPE.MACROMOLECULE;
-    col.setTag(DG.TAGS.UNITS, NOTATION.FASTA);
+    col.meta.units = NOTATION.FASTA;
     col.setTag(bioTAGS.alphabet, ALPHABET.DNA);
     col.setTag(bioTAGS.aligned, 'SEQ');
 
@@ -33,7 +33,7 @@ seq4`;
     const df: DG.DataFrame = DG.DataFrame.fromCsv(csv);
     const col: DG.Column = df.getCol('seq');
     col.semType = DG.SEMTYPE.MACROMOLECULE;
-    col.setTag(DG.TAGS.UNITS, NOTATION.HELM);
+    col.meta.units = NOTATION.HELM;
     // col.setTag(bio.TAGS.alphabetSize, '11');
     col.setTag(bioTAGS.alphabetIsMultichar, 'true');
 
@@ -48,7 +48,7 @@ seq4`;
     const df: DG.DataFrame = DG.DataFrame.fromCsv(csv);
     const col: DG.Column = df.getCol('seq');
     col.semType = DG.SEMTYPE.MACROMOLECULE;
-    col.setTag(DG.TAGS.UNITS, NOTATION.FASTA);
+    col.meta.units = NOTATION.FASTA;
     col.setTag(bioTAGS.alphabet, 'UN');
     col.setTag(bioTAGS.alphabetSize, '11');
     col.setTag(bioTAGS.alphabetIsMultichar, 'true');

package/src/tests/converters-test.ts

@@ -135,7 +135,7 @@ 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
     return function(srcCol: DG.Column): DG.Column {
       const converterSh = SeqHandler.forColumn(srcCol);
       const resCol = converterSh.convert(tgtNotation, tgtSeparator);
-      expect(resCol.getTag(DG.TAGS.UNITS), tgtNotation);
+      expect(resCol.meta.units, tgtNotation);
       return resCol;
     };
   }

package/src/tests/detectors-tests.ts

@@ -99,6 +99,15 @@ C1CCCCC1
 CCCCCC`,
       neg: ['col1'],
     },
+    'negFastaUnSingleChar': {
+      csv: `col1
+Alanine
+Cysteine
+Aspartic acid
+Glutamic acid
+Phenylalanine`,
+      neg: ['col1']
+    },
 
     // Same length
     'fastaMsaSameLength': {
@@ -122,30 +131,33 @@ YN[Re]VYNR[Ac]WYV
 [Me]EYVMPSFW[Me]H`,
       pos: {'seq': new PosCol(NOTATION.FASTA, ALIGNMENT.SEQ_MSA, ALPHABET.UN, 14, true, undefined)},
     },
+    'fastaMsaExtManyMinus': {
+      csv: `seq
+[D-Tic]-------[D-Tyr_Et][Tyr_ab-dehydroMe][dV][Cys_SEt]N[D-Orn][D-aThr]-[Phe_4Me]
+[Phe_2F]--------[Tyr_ab-dehydroMe][dV][Aca]N[D-Orn][D-aThr]-[Phe_4Me]
+[D-Tic]-[Hcy]QTWQ[Phe_4NH2][D-Tyr_Et][Tyr_ab-dehydroMe][dV][Cys_SEt]----[Phe_4Me]`,
+      pos: {'seq': new PosCol(NOTATION.FASTA, ALIGNMENT.SEQ_MSA, ALPHABET.UN, 17, true, undefined)}
+    },
     'sepSameLength': {
       csv: `seq
 Ac(1)-A-A-A-A-A-A-A-A-A-A-A-A-A-C(1)-G-NH2
 Ac(1)-A-A-A-A-A-A-A-A-A-A-A-A-A-C(1)-G-NH2
-Ac(1)-A-A-A-A-A-A-A-A-A-A-A-A-A-C(1)-G-NH2`, pos: {
-        'seq': new PosCol(NOTATION.SEPARATOR, ALIGNMENT.SEQ_MSA, ALPHABET.UN, 5, true, '-'),
-      }
+Ac(1)-A-A-A-A-A-A-A-A-A-A-A-A-A-C(1)-G-NH2`,
+      pos: {'seq': new PosCol(NOTATION.SEPARATOR, ALIGNMENT.SEQ_MSA, ALPHABET.UN, 5, true, '-')}
     },
     'sepMsaSameLength': {
       csv: `seq
 Ac(1)-A-A-A-A-A-A-A-A-A-A-A-A-A-C(1)-G-NH2
 Ac(1)-A-A(2)-A-A-A-C(2)-A-A-A-A-C(1)-G-NH2
-Ac(1)-A-A-A-A-A-A-A-A-A-A-A-A-A-C(1)-G-NH2`, pos: {
-        'seq': new PosCol(NOTATION.SEPARATOR, ALIGNMENT.SEQ, ALPHABET.UN, 5, true, '-'),
-      }
+Ac(1)-A-A-A-A-A-A-A-A-A-A-A-A-A-C(1)-G-NH2`,
+      pos: {'seq': new PosCol(NOTATION.SEPARATOR, ALIGNMENT.SEQ, ALPHABET.UN, 5, true, '-')}
     },
     'helmSameLength': {
       csv: `seq
 PEPTIDE1{Ac(1).A.A.A.A.A.A.A.A.A.A.A.A.A.C(1).G.NH2}$$$$
 PEPTIDE1{Ab(1).Y.V.K.H.P.F.W.R.W.Y.A.A.A.C(1).G.NH2}$$$$
 PEPTIDE1{Ad(1).S.W.Y.C.K.H.P.M.W.A.A.A.A.C(1)-G-NH2}$$$$`,
-      pos: {
-        'seq': new PosCol(NOTATION.HELM, null, null, 19, undefined, undefined)
-      }
+      pos: {'seq': new PosCol(NOTATION.HELM, null, null, 19, undefined, undefined)}
     },
   };
 
@@ -493,7 +505,7 @@ export async function _testNegList(list: string[]): Promise<void> {
   const col: DG.Column = DG.Column.fromList(DG.TYPE.STRING, 'col1', list);
   const semType: string = await grok.functions.call('Bio:detectMacromolecule', {col: col});
   if (col.semType === DG.SEMTYPE.MACROMOLECULE) {
-    const msg = `Negative test detected semType='${col.semType}', units='${col.getTag(DG.TAGS.UNITS)}'.`;
+    const msg = `Negative test detected semType='${col.semType}', units='${col.meta.units}'.`;
     throw new Error(msg);
   }
 }
@@ -507,7 +519,7 @@ export async function _testNeg(readDf: DfReaderFunc, colName: string) {
     col.semType = semType;
 
   if (col.semType === DG.SEMTYPE.MACROMOLECULE) {
-    const msg = `Negative test detected semType='${col.semType}', units='${col.getTag(DG.TAGS.UNITS)}'.`;
+    const msg = `Negative test detected semType='${col.semType}', units='${col.meta.units}'.`;
     throw new Error(msg);
   }
 }
@@ -522,7 +534,7 @@ export async function _testPosList(list: string[], units: NOTATION,
     col.semType = semType;
 
   expect(col.semType, DG.SEMTYPE.MACROMOLECULE);
-  expect(col.getTag(DG.TAGS.UNITS), units);
+  expect(col.meta.units, units);
   expect(col.getTag(bioTAGS.aligned), aligned);
   expect(col.getTag(bioTAGS.alphabet), alphabet);
   if (separator)
@@ -550,7 +562,7 @@ export async function _testPos(
     col.semType = semType;
 
   expect(col.semType, DG.SEMTYPE.MACROMOLECULE);
-  expect(col.getTag(DG.TAGS.UNITS), units);
+  expect(col.meta.units, units);
   expect(col.getTag(bioTAGS.aligned), aligned);
   expect(col.getTag(bioTAGS.alphabet), alphabet);
   if (separator)

package/src/tests/fasta-export-tests.ts

@@ -91,7 +91,7 @@ MRGGL
     const srcSeq: string = wrapData[testKey].src;
     const col = DG.Column.fromStrings('src', [srcSeq]);
     col.semType = DG.SEMTYPE.MACROMOLECULE;
-    col.setTag(DG.TAGS.UNITS, NOTATION.FASTA);
+    col.meta.units = NOTATION.FASTA;
     const sh = SeqHandler.forColumn(col);
     const srcSS = sh.getSplitted(0);
     const wrapRes: string[] = wrapSequence(srcSS, lineWidth);
@@ -105,7 +105,7 @@ MRGGL
 
     const seqCol: DG.Column = df.getCol(args.seqCol);
     seqCol.semType = DG.SEMTYPE.MACROMOLECULE;
-    seqCol.setTag(DG.TAGS.UNITS, NOTATION.FASTA);
+    seqCol.meta.units = NOTATION.FASTA;
     const idCols: DG.Column[] = args.idCols.map((colName) => df.getCol(colName));
 
     const fastaRes: string = saveAsFastaDo(idCols, seqCol, args.lineWidth);

package/src/tests/mm-distance-tests.ts

@@ -122,7 +122,7 @@ ATCGAATCGA`;
       const seq2 = Array(10000).fill('FYWRRY').join('');
       _testDistance(seq1, seq2, df, 0.667);
     } else { _testDistance(prot5, prot6, df, 1.143); }
-  });
+  }, {benchmark: true});
 });
 
 async function _initMacromoleculeColumn(csv: string): Promise<SeqHandler> {

package/src/tests/msa-tests.ts

@@ -125,14 +125,14 @@ async function _testMSAOnColumn(
   const tgtCol = tgtDf.getCol('seq')!;
   const srcCol: DG.Column = srcDf.getCol('seq')!;
   expect(srcCol.semType, DG.SEMTYPE.MACROMOLECULE);
-  expect(srcCol.getTag(DG.TAGS.UNITS), srcNotation);
+  expect(srcCol.meta.units, srcNotation);
   if (alphabet)
     expect(srcCol.getTag(bioTAGS.alphabet), alphabet);
 
   const msaSeqCol = await multipleSequenceAlignmentUI({col: srcCol, pepsea: {method: pepseaMethod}});
   expect(msaSeqCol.semType, DG.SEMTYPE.MACROMOLECULE);
   expect(msaSeqCol.semType, DG.SEMTYPE.MACROMOLECULE);
-  expect(msaSeqCol.getTag(DG.TAGS.UNITS), tgtNotation);
+  expect(msaSeqCol.meta.units, tgtNotation);
   expect(msaSeqCol.getTag(bioTAGS.aligned), ALIGNMENT.SEQ_MSA);
   if (alphabet)
     expect(msaSeqCol.getTag(bioTAGS.alphabet), alphabet);

package/src/tests/renderers-test.ts

@@ -103,7 +103,7 @@ category('renderers', () => {
   async function _rendererMacromoleculeDifference() {
     const seqDiffCol: DG.Column = DG.Column.fromStrings('SequencesDiff',
       ['meI/hHis/Aca/N/T/dK/Thr_PO3H2/Aca#D-Tyr_Et/Tyr_ab-dehydroMe/meN/E/N/dV']);
-    seqDiffCol.setTag(DG.TAGS.UNITS, NOTATION.SEPARATOR);
+    seqDiffCol.meta.units = NOTATION.SEPARATOR;
     seqDiffCol.setTag(bioTAGS.separator, '/');
     seqDiffCol.setTag(bioTAGS.aligned, 'SEQ');
     seqDiffCol.setTag(bioTAGS.alphabet, 'UN');
@@ -140,10 +140,10 @@ category('renderers', () => {
     expect(tv.grid.dataFrame.id, df.id);
 
     console.log('Bio: tests/renderers/afterMsa, src before test ' +
-      `semType="${srcSeqCol!.semType}", units="${srcSeqCol!.getTag(DG.TAGS.UNITS)}", ` +
+      `semType="${srcSeqCol!.semType}", units="${srcSeqCol!.meta.units}", ` +
       `cell.renderer="${srcSeqCol!.getTag(DG.TAGS.CELL_RENDERER)}"`);
     expect(srcSeqCol.semType, DG.SEMTYPE.MACROMOLECULE);
-    expect(srcSeqCol.getTag(DG.TAGS.UNITS), NOTATION.FASTA);
+    expect(srcSeqCol.meta.units, NOTATION.FASTA);
     expect(srcSeqCol.getTag(bioTAGS.aligned), ALIGNMENT.SEQ);
     expect(srcSeqCol.getTag(bioTAGS.alphabet), ALPHABET.PT);
     expect(srcSeqCol.getTag(DG.TAGS.CELL_RENDERER), 'sequence');
@@ -153,7 +153,7 @@ category('renderers', () => {
     expect(tv.grid.dataFrame.id, df.id);
 
     expect(msaSeqCol.semType, DG.SEMTYPE.MACROMOLECULE);
-    expect(msaSeqCol.getTag(DG.TAGS.UNITS), NOTATION.FASTA);
+    expect(msaSeqCol.meta.units, NOTATION.FASTA);
     expect(msaSeqCol.getTag(bioTAGS.aligned), ALIGNMENT.SEQ_MSA);
     expect(msaSeqCol.getTag(bioTAGS.alphabet), ALPHABET.PT);
     expect(msaSeqCol.getTag(DG.TAGS.CELL_RENDERER), 'sequence');
@@ -205,7 +205,7 @@ category('renderers', () => {
     /**/
     const seqDiffCol: DG.Column = DG.Column.fromStrings('SequencesDiff',
       ['meI/hHis/Aca/N/T/dK/Thr_PO3H2/Aca#D-Tyr_Et/Tyr_ab-dehydroMe/meN/E/N/dV']);
-    seqDiffCol.setTag(DG.TAGS.UNITS, NOTATION.SEPARATOR);
+    seqDiffCol.meta.units = NOTATION.SEPARATOR;
     seqDiffCol.setTag(bioTAGS.separator, '/');
     seqDiffCol.setTag(bioTAGS.aligned, 'SEQ');
     seqDiffCol.setTag(bioTAGS.alphabet, 'UN');