@datagrok/bio 2.11.42 → 2.12.0

package/src/utils/cell-renderer.ts

@@ -16,7 +16,10 @@ import {
 } from '@datagrok-libraries/bio/src/utils/macromolecule';
 import {SeqPalette} from '@datagrok-libraries/bio/src/seq-palettes';
 import {UnknownSeqPalettes} from '@datagrok-libraries/bio/src/unknown';
-import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
+import {GapOriginals, SeqHandler} from '@datagrok-libraries/bio/src/utils/seq-handler';
+import {ISeqSplitted} from '@datagrok-libraries/bio/src/utils/macromolecule/types';
+import {getSplitter} from '@datagrok-libraries/bio/src/utils/macromolecule/utils';
+import {errInfo} from '@datagrok-libraries/bio/src/utils/err-info';
 
 import {
   Temps as mmcrTemps, Tags as mmcrTags,
@@ -25,10 +28,6 @@ import {
 import * as C from './constants';
 
 import {_package, getBioLib} from '../package';
-import {ISeqSplitted} from '@datagrok-libraries/bio/src/utils/macromolecule/types';
-import {getSplitter} from '@datagrok-libraries/bio/src/utils/macromolecule/utils';
-import {errInfo} from '@datagrok-libraries/bio/src/utils/err-info';
-
 
 type TempType = { [tagName: string]: any };
 
@@ -39,7 +38,7 @@ function getUpdatedWidth(grid: DG.Grid | null, g: CanvasRenderingContext2D, x: n
   return !!grid ? Math.max(Math.min(grid.canvas.width / dpr - x, w)) : Math.max(g.canvas.width / dpr - x, 0);
 }
 
-export function processSequence(subParts: ISeqSplitted): [string[], boolean] {
+export function processSequence(subParts: string[]): [string[], boolean] {
   const simplified = !wu.enumerate(subParts).some(([amino, index]) =>
     amino.length > 1 &&
     index != 0 &&
@@ -99,6 +98,7 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
       const monomerSymbol: string = seqMonList[left];
       const tooltipElements: HTMLElement[] = [ui.div(monomerSymbol)];
       if (seqColTemp._monomerStructureMap[monomerSymbol]) {
+        //
         tooltipElements.push(seqColTemp._monomerStructureMap[monomerSymbol]);
       } else {
         const monomer = seqColTemp.getMonomer(monomerSymbol);
@@ -111,6 +111,7 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
       }
       ui.tooltip.show(ui.divV(tooltipElements), e.x + 16, e.y + 16);
     } else {
+      //
       ui.tooltip.hide();
     }
   }
@@ -163,10 +164,10 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
     if (!seqColTemp) {
       seqColTemp = new MonomerPlacer(grid, tableCol,
         () => {
-          const uh = UnitsHandler.getOrCreate(tableCol);
+          const sh = SeqHandler.forColumn(tableCol);
           return {
-            unitsHandler: uh,
-            monomerCharWidth: 7, separatorWidth: !uh.isMsa() ? gapLength : msaGapLength,
+            seqHandler: sh,
+            monomerCharWidth: 7, separatorWidth: !sh.isMsa() ? gapLength : msaGapLength,
             monomerToShort: monomerToShortFunction, monomerLengthLimit: maxLengthOfMonomer,
             monomerLib: getBioLib()
           };
@@ -193,6 +194,7 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
       const dpr = window.devicePixelRatio;
       const grid = gridCell.gridRow !== -1 ? gridCell.grid : null;
       const value: any = gridCell.cell.value;
+      const rowIdx = gridCell.cell.rowIndex;
       const paletteType = tableCol.getTag(bioTAGS.alphabet);
       const minDistanceRenderer = 50;
       w = getUpdatedWidth(grid, g, x, w, dpr);
@@ -210,18 +212,22 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
 
       const separator = tableCol.getTag(bioTAGS.separator) ?? '';
       const splitLimit = w / 5;
-      const uh = UnitsHandler.getOrCreate(tableCol);
-      const splitterFunc: SplitterFunc = uh.getSplitter(splitLimit);
+      const sh = SeqHandler.forColumn(tableCol);
 
       const tempReferenceSequence: string | null = tableColTemp[tempTAGS.referenceSequence];
       const tempCurrentWord: string | null = tableColTemp[tempTAGS.currentWord];
       if (tempCurrentWord && tableCol?.dataFrame?.currentRowIdx === -1)
         tableColTemp[tempTAGS.currentWord] = null;
-      const referenceSequence: ISeqSplitted = splitterFunc(
-        ((tempReferenceSequence != null) && (tempReferenceSequence != '')) ?
-          tempReferenceSequence : tempCurrentWord ?? '');
 
-      const subParts: ISeqSplitted = splitterFunc(value);
+      const referenceSequence: string[] = (() => {
+        // @ts-ignore
+        const splitterFunc: SplitterFunc = sh.getSplitter(splitLimit);
+        return wu(splitterFunc(
+          ((tempReferenceSequence != null) && (tempReferenceSequence != '')) ?
+            tempReferenceSequence : tempCurrentWord ?? '').originals).toArray();
+      })();
+
+      const subParts: ISeqSplitted = sh.getSplitted(rowIdx);
       /* let x1 = x; */
       let color = undefinedColor;
       let drawStyle = DrawStyle.classic;
@@ -229,14 +235,15 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
       if (aligned && aligned.includes('MSA') && units == NOTATION.SEPARATOR)
         drawStyle = DrawStyle.MSA;
 
-      for (const [amino, index] of wu.enumerate(subParts)) {
+      for (let posIdx: number = 0; posIdx < subParts.length; ++posIdx) {
+        const amino: string = subParts.getOriginal(posIdx);
         color = palette.get(amino);
         g.fillStyle = undefinedColor;
-        const last = index === subParts.length - 1;
+        const last = posIdx === subParts.length - 1;
         /*x1 = */
         printLeftOrCentered(x + this.padding, y, w, h,
           g, amino, color, 0, true, 1.0, separator, last, drawStyle,
-          maxLengthWordsSum, index, gridCell, referenceSequence, maxLengthOfMonomer, seqColTemp._monomerLengthMap);
+          maxLengthWordsSum, posIdx, gridCell, referenceSequence, maxLengthOfMonomer, seqColTemp._monomerLengthMap);
         if (minDistanceRenderer > w) break;
       }
     } catch (err: any) {
@@ -285,8 +292,8 @@ export class MacromoleculeDifferenceCellRenderer extends DG.GridCellRenderer {
     //TODO: can this be replaced/merged with splitSequence?
     const [s1, s2] = s.split('#');
     const splitter = getSplitter(units, separator);
-    const subParts1 = splitter(s1);
-    const subParts2 = splitter(s2);
+    const subParts1 = wu(splitter(s1).canonicals).toArray();
+    const subParts2 = wu(splitter(s2).canonicals).toArray();
     drawMoleculeDifferenceOnCanvas(g, x, y, w, h, subParts1, subParts2, units);
   }
 }
@@ -297,14 +304,14 @@ export function drawMoleculeDifferenceOnCanvas(
   y: number,
   w: number,
   h: number,
-  subParts1: ISeqSplitted,
-  subParts2: ISeqSplitted,
+  subParts1: string[],
+  subParts2: string[],
   units: string,
   fullStringLength?: boolean,
   molDifferences?: { [key: number]: HTMLCanvasElement },
 ): void {
   if (subParts1.length !== subParts2.length) {
-    const sequences: IComparedSequences = fillShorterSequence(wu(subParts1).toArray(), wu(subParts2).toArray());
+    const sequences: IComparedSequences = fillShorterSequence(subParts1, subParts2);
     subParts1 = sequences.subParts1;
     subParts2 = sequences.subParts2;
   }
@@ -343,7 +350,10 @@ export function drawMoleculeDifferenceOnCanvas(
       updatedX = Math.max(subX1, subX0);
       if (molDifferences)
         molDifferences[i] = createDifferenceCanvas(amino1, amino2, color1, color2, updatedY, vShift, h);
-    } else { updatedX = printLeftOrCentered(updatedX, updatedY, w, h, g, amino1, color1, 0, true, 0.5); }
+    } else {
+      //
+      updatedX = printLeftOrCentered(updatedX, updatedY, w, h, g, amino1, color1, 0, true, 0.5);
+    }
     updatedX += 4;
   }
   g.restore();
@@ -354,14 +364,9 @@ interface IComparedSequences {
   subParts2: string[];
 }
 
-function createDifferenceCanvas(
-  amino1: string,
-  amino2: string,
-  color1: string,
-  color2: string,
-  y: number,
-  shift: number,
-  h: number): HTMLCanvasElement {
+function createDifferenceCanvas(amino1: string, amino2: string, color1: string, color2: string,
+  y: number, shift: number, h: number
+): HTMLCanvasElement {
   const canvas = document.createElement('canvas');
   const context = canvas.getContext('2d')!;
   context.font = '12px monospace';
@@ -394,7 +399,8 @@ function fillShorterSequence(subParts1: string[], subParts2: string[]): ICompare
       numIdenticalEnd++;
   }
 
-  const emptyMonomersArray = new Array<string>(Math.abs(subParts1.length - subParts2.length)).fill('');
+  const emptyMonomersArray = new Array<string>(Math.abs(subParts1.length - subParts2.length))
+    .fill(GapOriginals[NOTATION.FASTA]);
 
   function concatWithEmptyVals(subparts: string[]): string[] {
     return numIdenticalStart > numIdenticalEnd ?
@@ -402,6 +408,6 @@ function fillShorterSequence(subParts1: string[], subParts2: string[]): ICompare
   }
 
   subParts1.length > subParts2.length ?
-    subParts2 = concatWithEmptyVals(subParts2) : subParts1 = concatWithEmptyVals(subParts1);
+    subParts2 = concatWithEmptyVals(wu(subParts2).toArray()) : subParts1 = concatWithEmptyVals(wu(subParts1).toArray());
   return {subParts1: subParts1, subParts2: subParts2};
 }

package/src/utils/check-input-column.ts

@@ -2,7 +2,7 @@ import * as grok from 'datagrok-api/grok';
 import * as DG from 'datagrok-api/dg';
 import * as ui from 'datagrok-api/ui';
 
-import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
+import {SeqHandler} from '@datagrok-libraries/bio/src/utils/seq-handler';
 
 /**
  * Checks if the column is suitable for the analysis.
@@ -35,12 +35,12 @@ export function checkInputColumn(
   let res: boolean = true;
   let msg: string = '';
 
-  const uh = UnitsHandler.getOrCreate(col);
+  const sh = SeqHandler.forColumn(col);
   if (col.semType !== DG.SEMTYPE.MACROMOLECULE) {
     grok.shell.warning(name + ' analysis is allowed for Macromolecules semantic type');
     res = false;
   } else {
-    const notation: string = uh.notation;
+    const notation: string = sh.notation;
     if (allowedNotations.length > 0 &&
       !allowedNotations.some((n) => notation.toUpperCase() == (n.toUpperCase()))
     ) {
@@ -48,9 +48,9 @@ export function checkInputColumn(
         (`notation${allowedNotations.length > 1 ? 's' : ''} ${allowedNotations.map((n) => `"${n}"`).join(', ')} `);
       msg = `${name} + ' analysis is allowed for Macromolecules with notation ${notationAdd}.`;
       res = false;
-    } else if (!uh.isHelm()) {
+    } else if (!sh.isHelm()) {
       // alphabet is not specified for 'helm' notation
-      const alphabet: string = uh.alphabet;
+      const alphabet: string = sh.alphabet;
       if (
         allowedAlphabets.length > 0 &&
         !allowedAlphabets.some((a) => alphabet.toUpperCase() == (a.toUpperCase()))

package/src/utils/context-menu.ts

@@ -2,22 +2,25 @@ import * as grok from 'datagrok-api/grok';
 import * as DG from 'datagrok-api/dg';
 import * as ui from 'datagrok-api/ui';
 
-import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
+import {SeqHandler} from '@datagrok-libraries/bio/src/utils/seq-handler';
 import {NOTATION} from '@datagrok-libraries/bio/src/utils/macromolecule';
 
 import {_package} from '../package';
 
 
 export function addCopyMenuUI(cell: DG.Cell, menu: DG.Menu): void {
-  const uh = UnitsHandler.getOrCreate(cell.column);
-  const tgtNotationList: string[] = Object.values(NOTATION).filter((v) => v !== uh.units);
+  const sh = SeqHandler.forColumn(cell.column);
+  const tgtNotationList: string[] = Object.values(NOTATION).filter((v) => v !== sh.units);
 
   menu.group('Copy')
     .items(tgtNotationList, (tgtNotation) => {
-      const ncUH = UnitsHandler.getOrCreate(cell.column);
+      const srcCol = cell.column;
+      const srcRowIdx = cell.rowIndex;
+      const srcSh = SeqHandler.forColumn(srcCol);
       const separator = tgtNotation === NOTATION.SEPARATOR ? _package.properties.DefaultSeparator : undefined;
-      const converter = ncUH.getConverter(tgtNotation as NOTATION, separator);
-      const tgtSeq = converter(cell.value);
+      const joiner = srcSh.getJoiner({notation: tgtNotation as NOTATION, separator});
+      const srcSS = srcSh.getSplitted(srcRowIdx);
+      const tgtSeq = joiner(srcSS);
 
       if (!navigator.clipboard) {
         grok.shell.warning('The clipboard functionality requires a secure origin — either HTTPS or localhost');

package/src/utils/convert.ts

@@ -4,9 +4,9 @@ import * as grok from 'datagrok-api/grok';
 
 import $ from 'cash-dom';
 import {Subscription} from 'rxjs';
-import {NOTATION, TAGS as bioTAGS} from '@datagrok-libraries/bio/src/utils/macromolecule';
-import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
-import {expect} from '@datagrok-libraries/utils/src/test';
+
+import {NOTATION} from '@datagrok-libraries/bio/src/utils/macromolecule';
+import {SeqHandler} from '@datagrok-libraries/bio/src/utils/seq-handler';
 
 
 let convertDialog: DG.Dialog | null = null;
@@ -21,8 +21,8 @@ export function convert(col?: DG.Column): void {
   let tgtCol = col ?? grok.shell.t.columns.bySemType('Macromolecule')!;
   if (!tgtCol)
     throw new Error('No column with Macromolecule semantic type found');
-  let converterUH = UnitsHandler.getOrCreate(tgtCol);
-  let currentNotation: NOTATION = converterUH.notation;
+  let converterSh = SeqHandler.forColumn(tgtCol);
+  let currentNotation: NOTATION = converterSh.notation;
   const dialogHeader = ui.divText(
     'Current notation: ' + currentNotation,
     {
@@ -46,8 +46,8 @@ export function convert(col?: DG.Column): void {
     }
 
     tgtCol = newCol;
-    converterUH = UnitsHandler.getOrCreate(tgtCol);
-    currentNotation = converterUH.notation;
+    converterSh = SeqHandler.forColumn(tgtCol);
+    currentNotation = converterSh.notation;
     if (currentNotation === NOTATION.HELM)
       separatorInput.value = '/'; // helm monomers can have - in the name like D-aThr;
     dialogHeader.textContent = 'Current notation: ' + currentNotation;
@@ -116,8 +116,8 @@ export function convert(col?: DG.Column): void {
  * @param {string | null} separator Separator for SEPARATOR notation
  */
 export async function convertDo(srcCol: DG.Column, targetNotation: NOTATION, separator?: string): Promise<DG.Column> {
-  const converterUH = UnitsHandler.getOrCreate(srcCol);
-  const newColumn = converterUH.convert(targetNotation, separator);
+  const converterSh = SeqHandler.forColumn(srcCol);
+  const newColumn = converterSh.convert(targetNotation, separator);
   srcCol.dataFrame.columns.add(newColumn);
 
   // Call detector directly to escape some error on detectSemanticTypes

package/src/utils/get-region-func-editor.ts

@@ -3,6 +3,9 @@ import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
 
 import {TAGS as bioTAGS} from '@datagrok-libraries/bio/src/utils/macromolecule';
+import {SeqHandler} from '@datagrok-libraries/bio/src/utils/seq-handler';
+
+import {_package} from '../package';
 
 export interface GetRegionParams {
   table: DG.DataFrame,
@@ -12,9 +15,6 @@ export interface GetRegionParams {
   /** Name for the column with sequence of the region  */ name: string | null,
 }
 
-import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
-import {_package} from '../package';
-
 export interface SeqRegion {
   name: string,
   description: string,
@@ -70,7 +70,7 @@ export class GetRegionFuncEditor {
 
   private sequenceInputChanged(): void {
     const seqCol = this.inputs.sequence.value;
-    const uh = seqCol ? UnitsHandler.getOrCreate(seqCol) : null;
+    const sh = seqCol ? SeqHandler.forColumn(seqCol) : null;
     this.updateRegionItems();
     this.updateStartEndInputItems();
     this.updateRegion(true);
@@ -89,9 +89,9 @@ export class GetRegionFuncEditor {
         this.inputs.start.value = reg?.start;
         this.inputs.end.value = reg?.end;
       } else {
-        const uh = UnitsHandler.getOrCreate(this.inputs.sequence.value!);
-        this.inputs.start.value = uh.posList[0];
-        this.inputs.end.value = uh.posList[uh.posList.length - 1];
+        const sh = SeqHandler.forColumn(this.inputs.sequence.value!);
+        this.inputs.start.value = sh.posList[0];
+        this.inputs.end.value = sh.posList[sh.posList.length - 1];
       }
     } finally {
       this.fixRegion = false;
@@ -122,13 +122,13 @@ export class GetRegionFuncEditor {
 
   private updateStartEndInputItems(): void {
     const seqCol = this.inputs.sequence.value;
-    const uh = seqCol ? UnitsHandler.getOrCreate(seqCol) : null;
+    const sh = seqCol ? SeqHandler.forColumn(seqCol) : null;
 
     const startSE = (this.inputs.start.input as HTMLSelectElement);
     const endSE = (this.inputs.end.input as HTMLSelectElement);
     for (let i = startSE.options.length - 1; i >= 0; --i) startSE.options.remove(i);
     for (let i = endSE.options.length - 1; i >= 0; --i) endSE.options.remove(i);
-    for (const pos of uh?.posList ?? []) {
+    for (const pos of sh?.posList ?? []) {
       const startPosOE = document.createElement('option');
       const endPosOE = document.createElement('option');
       startPosOE.text = endPosOE.text = pos;
@@ -136,8 +136,8 @@ export class GetRegionFuncEditor {
       startSE.options.add(startPosOE);
       endSE.options.add(endPosOE);
     }
-    startSE.value = uh?.posList[0] ?? '';
-    endSE.value = uh?.posList[uh?.posList.length - 1] ?? '';
+    startSE.value = sh?.posList[0] ?? '';
+    endSE.value = sh?.posList[sh?.posList.length - 1] ?? '';
   }
 
   private updateRegionItems(): void {

package/src/utils/get-region.ts

@@ -2,18 +2,16 @@ import * as grok from 'datagrok-api/grok';
 import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
 
-import {TAGS as bioTAGS} from '@datagrok-libraries/bio/src/utils/macromolecule';
-import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
-import {getRegion} from '../package';
+import {SeqHandler} from '@datagrok-libraries/bio/src/utils/seq-handler';
 import {TaskBarProgressIndicator} from 'datagrok-api/dg';
 
 export function getRegionUI(col: DG.Column<string>): void {
-  const uh = UnitsHandler.getOrCreate(col);
+  const sh = SeqHandler.forColumn(col);
 
   const nameInput = ui.stringInput('Name', '');
-  const startPositionInput = ui.choiceInput('Start Position', uh.posList[0], uh.posList,
+  const startPositionInput = ui.choiceInput('Start Position', sh.posList[0], sh.posList,
     () => { /* TODO: update name placeholder with getDefaultName() */ });
-  const endPositionInput = ui.choiceInput('End Position', uh.posList[uh.posList.length], uh.posList,
+  const endPositionInput = ui.choiceInput('End Position', sh.posList[sh.posList.length], sh.posList,
     () => { /* TODO: update name placeholder with getDefaultName() */ });
 
   const getDefaultName = (): string => {
@@ -41,25 +39,25 @@ export function getRegionUI(col: DG.Column<string>): void {
 export function getRegionDo(
   col: DG.Column<string>, startPosName: string | null, endPosName: string | null, name: string | null
 ): DG.Column<string> {
-  const uh = UnitsHandler.getOrCreate(col);
+  const sh = SeqHandler.forColumn(col);
 
   let startPosIdx: number | null = null;
   let endPosIdx: number | null = null;
 
-  for (let posJ: number = 0; posJ < uh.posList.length; ++posJ) {
-    if (uh.posList[posJ] == startPosName) startPosIdx = posJ;
-    if (uh.posList[posJ] == endPosName) endPosIdx = posJ;
+  for (let posJ: number = 0; posJ < sh.posList.length; ++posJ) {
+    if (sh.posList[posJ] == startPosName) startPosIdx = posJ;
+    if (sh.posList[posJ] == endPosName) endPosIdx = posJ;
   }
   if (startPosIdx === null && startPosName !== null)
     throw new Error(`Start position ${startPosName} not found.`);
   if (endPosIdx === null && endPosName !== null)
     throw new Error(`End position ${endPosName} not found.`);
 
-  if (uh.posList.length < endPosIdx!)
+  if (sh.posList.length < endPosIdx!)
     throw new Error(`End position ${endPosIdx} exceeds positions length`);
 
   const regColName: string = !!name ? name : `${col.name}: (${startPosName ?? ''}-${endPosName ?? ''})`;
 
-  const regCol = uh.getRegion(startPosIdx, endPosIdx, regColName);
+  const regCol = sh.getRegion(startPosIdx, endPosIdx, regColName);
   return regCol;
 }

package/src/utils/macromolecule-column-widget.ts

@@ -3,10 +3,11 @@ import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
 
 import {TAGS as wlTAGS} from '@datagrok-libraries/bio/src/viewers/web-logo';
+import {SeqHandler} from '@datagrok-libraries/bio/src/utils/seq-handler';
+
 import {WebLogoViewer} from '../viewers/web-logo-viewer';
 
 import {_package} from '../package';
-import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
 
 /** Used in Macromolecule column tooltip */
 export class MacromoleculeColumnWidget extends DG.Widget {
@@ -23,7 +24,7 @@ export class MacromoleculeColumnWidget extends DG.Widget {
   }
 
   async init(): Promise<void> {
-    const uh = UnitsHandler.getOrCreate(this.seqCol);
+    const sh = SeqHandler.forColumn(this.seqCol);
     const pkgTooltipWebLogo = _package.properties.TooltipWebLogo;
     const colTooltipWebLogo = this.seqCol.getTag(wlTAGS.tooltipWebLogo);
 
@@ -32,7 +33,7 @@ export class MacromoleculeColumnWidget extends DG.Widget {
         sequenceColumnName: this.seqCol.name,
         backgroundColor: 0x00000000,
         positionHeight: 'Entropy',
-        positionWidth: (uh.getAlphabetIsMultichar() ? 24 : 16),
+        positionWidth: (sh.getAlphabetIsMultichar() ? 24 : 16),
         fixWidth: true,
         fitArea: false,
         // maxHeight: 100,

package/src/utils/monomer-lib/library-file-manager/event-manager.ts

@@ -26,7 +26,7 @@ export class MonomerLibFileEventManager {
   // WARNING: a temporary solution
   async getValidLibraryPathsAsynchronously(): Promise<string[]> {
     return new Promise((resolve) => {
-      this._libraryFilesUpdateSubject$.pipe(
+      this._libraryFilesUpdateSubject$.pipe<string[]>(
         skip(1)
       ).subscribe((fileNames) => {
         resolve(fileNames);

package/src/utils/multiple-sequence-alignment-ui.ts

@@ -3,7 +3,7 @@ import * as DG from 'datagrok-api/dg';
 import * as ui from 'datagrok-api/ui';
 
 import {ALPHABET, NOTATION} from '@datagrok-libraries/bio/src/utils/macromolecule';
-import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
+import {SeqHandler} from '@datagrok-libraries/bio/src/utils/seq-handler';
 import {ColumnInputOptions} from '@datagrok-libraries/utils/src/type-declarations';
 
 import {runKalign} from './multiple-sequence-alignment';
@@ -160,9 +160,9 @@ async function onColInputChange(
       gapOpenInput.value = null;
       gapExtendInput.value = null;
       terminalGapInput.value = null;
-      const potentialColUH = UnitsHandler.getOrCreate(col);
-      const performCol: DG.Column<string> = potentialColUH.isFasta() ? col :
-        potentialColUH.convert(NOTATION.FASTA);
+      const potentialColSh = SeqHandler.forColumn(col);
+      const performCol: DG.Column<string> = potentialColSh.isFasta() ? col :
+        potentialColSh.convert(NOTATION.FASTA);
       return async () => await runKalign(performCol, false, unusedName, clustersColInput.value);
     } else if (checkInputColumnUI(col, col.name,
       [NOTATION.HELM], [], false)
@@ -178,8 +178,8 @@ async function onColInputChange(
       };
     } else if (checkInputColumnUI(col, col.name, [NOTATION.SEPARATOR], [ALPHABET.UN], false)) {
       //if the column is separator with unknown alphabet, it might be helm. check if it can be converted to helm
-      const potentialColUH = UnitsHandler.getOrCreate(col);
-      const helmCol = potentialColUH.convert(NOTATION.HELM);
+      const potentialColSh = SeqHandler.forColumn(col);
+      const helmCol = potentialColSh.convert(NOTATION.HELM);
       switchDialog(pepseaInputRootStyles, kalignInputRootStyles, 'pepsea');
       gapOpenInput.value ??= msaDefaultOptions.pepsea.gapOpen;
       gapExtendInput.value ??= msaDefaultOptions.pepsea.gapExtend;

package/src/utils/pepsea.ts

@@ -132,6 +132,7 @@ async function requestAlignedObjects(
     }
     responseObj = await response.json();
   } else {
+    // @ts-ignore
     const responseStr = await grok.dapi.docker.dockerContainers.request(dockerfileId, path, params)!;
     if (!responseStr)
       throw new Error('Empty response');

package/src/utils/poly-tool/transformation.ts

@@ -3,7 +3,7 @@ import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
 
 import {NOTATION} from '@datagrok-libraries/bio/src/utils/macromolecule';
-import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
+import {SeqHandler} from '@datagrok-libraries/bio/src/utils/seq-handler';
 import {ALIGNMENT, ALPHABET} from '@datagrok-libraries/bio/src/utils/macromolecule';
 
 import {HELM_WRAPPER} from './const';
@@ -224,8 +224,8 @@ export async function addTransformedColumn(
   molColumn: DG.Column<string>, addHelm: boolean, ruleFiles: string[], chiralityEngine?: boolean
 ): Promise<void> {
   const df = molColumn.dataFrame;
-  const uh = UnitsHandler.getOrCreate(molColumn);
-  const sourceHelmCol = uh.convert(NOTATION.HELM);
+  const sh = SeqHandler.forColumn(molColumn);
+  const sourceHelmCol = sh.convert(NOTATION.HELM);
   const pt = PolymerTransformation.getInstance(sourceHelmCol);
   const fileSource = new DG.FileSource(RULES_PATH);
 

package/src/utils/save-as-fasta.ts

@@ -3,8 +3,8 @@ import * as ui from 'datagrok-api/ui';
 import * as grok from 'datagrok-api/grok';
 
 import wu from 'wu';
-import {splitterAsFasta, SplitterFunc} from '@datagrok-libraries/bio/src/utils/macromolecule';
-import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
+import {SeqHandler} from '@datagrok-libraries/bio/src/utils/seq-handler';
+import {ISeqSplitted} from '@datagrok-libraries/bio/src/utils/macromolecule/types';
 
 const FASTA_LINE_WIDTH = 60;
 
@@ -28,8 +28,8 @@ export function saveAsFastaUI() {
     .filter((gc: DG.GridColumn) => {
       const col: DG.Column | null = gc.column;
       if (col && col.semType === DG.SEMTYPE.MACROMOLECULE) {
-        const uh = UnitsHandler.getOrCreate(col);
-        return uh.isFasta();
+        const sh = SeqHandler.forColumn(col);
+        return sh.isFasta();
       }
       return false;
     }).toArray();
@@ -77,17 +77,16 @@ export function saveAsFastaUI() {
 export function saveAsFastaDo(
   idColList: DG.Column[], seqCol: DG.Column, lineWidth: number = FASTA_LINE_WIDTH, lineSeparator: string = '\n',
 ): string {
-  const splitter: SplitterFunc = splitterAsFasta;
-
+  const sh = SeqHandler.forColumn(seqCol);
   const fastaLines: string[] = [];
 
-  for (let rowI: number = 0; rowI < seqCol.length; rowI++) {
+  for (let rowIdx: number = 0; rowIdx < seqCol.length; rowIdx++) {
     // multiple identifiers separated by vertical bars
     // https://en.wikipedia.org/wiki/FASTA_format
 
-    const seqId: string = idColList.map((col) => col.get(rowI).toString()).join('|');
-    const seq: string = seqCol.get(rowI);
-    const seqLineList: string[] = wrapSequence(seq, splitter, lineWidth);
+    const seqId: string = idColList.map((col) => col.get(rowIdx).toString()).join('|');
+    const srcSS = sh.getSplitted(rowIdx);
+    const seqLineList: string[] = wrapSequence(srcSS, lineWidth);
 
     fastaLines.push(`>${seqId}${lineSeparator}`);
     for (const line of seqLineList)
@@ -99,16 +98,16 @@ export function saveAsFastaDo(
 }
 
 /* split sequence for monomers to prevent wrapping monomer partially */
-export function wrapSequence(seq: string, splitter: SplitterFunc, lineWidth: number = FASTA_LINE_WIDTH): string[] {
-  const seqMonomerList = splitter(seq);
+export function wrapSequence(srcSS: ISeqSplitted, lineWidth: number = FASTA_LINE_WIDTH): string[] {
   let seqPos: number = 0;
-  const seqLength: number = seqMonomerList.length;
+  const seqLength: number = srcSS.length;
 
   const seqLineList: string[] = [];
   while (seqPos < seqLength) {
     /* join sliced monomer into line */
-    const seqLine: string[] = wu(seqMonomerList).slice(seqPos, seqPos + lineWidth).toArray();
-    const seqLineTxt: string = seqLine.map((m) => m.length > 1 ? `[${m}]` : m).join('');
+    const seqLine = wu(srcSS.originals).slice(seqPos, seqPos + lineWidth).toArray();
+    const seqLineTxt: string = seqLine.map((om) => om.length > 1 ? `[${om}]` : om)
+      .reduce((a, b) => a + b, '');
     seqLineList.push(seqLineTxt);
     seqPos += seqLine.length;
   }

package/src/utils/sequence-to-mol.ts

@@ -8,7 +8,7 @@ import {helm2mol} from './helm-to-molfile';
 import {IMonomerLib} from '@datagrok-libraries/bio/src/types';
 import {checkInputColumnUI} from './check-input-column';
 import {getMonomerLibHelper} from '../package';
-import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
+import {SeqHandler} from '@datagrok-libraries/bio/src/utils/seq-handler';
 import {NOTATION} from '@datagrok-libraries/bio/src/utils/macromolecule';
 
 export async function sequenceToMolfile(df: DG.DataFrame, macroMolecule: DG.Column, nonlinear: boolean): Promise<void> {
@@ -17,9 +17,9 @@ export async function sequenceToMolfile(df: DG.DataFrame, macroMolecule: DG.Colu
     return;
   }
   if (nonlinear) {
-    const seqUh = UnitsHandler.getOrCreate(macroMolecule);
-    if (!seqUh.isHelm())
-      macroMolecule = seqUh.convert(NOTATION.HELM);
+    const seqSh = SeqHandler.forColumn(macroMolecule);
+    if (!seqSh.isHelm())
+      macroMolecule = seqSh.convert(NOTATION.HELM);
     helm2mol(df, macroMolecule);
     return;
   }