@datagrok/bio 1.7.0 → 1.7.3

package/src/utils/cell-renderer.ts

@@ -55,21 +55,22 @@ export function processSequence(subParts: string[]): [string[], boolean] {
  * @param {string} [color=undefinedColor] String color.
  * @param {number} [pivot=0] Pirvot.
  * @param {boolean} [left=false] Is left aligned.
- * @param {boolean} [hideMod=false] Hide amino acid redidue modifications.
  * @param {number} [transparencyRate=0.0] Transparency rate where 1.0 is fully transparent
+ * @param {string} [separator=''] Is separator for sequence.
+ * @param {boolean} [last=false] Is checker if element last or not.
  * @return {number} x coordinate to start printing at.
  */
 function printLeftOrCentered(
   x: number, y: number, w: number, h: number,
   g: CanvasRenderingContext2D, s: string, color = undefinedColor,
-  pivot: number = 0, left = false, hideMod = false, transparencyRate: number = 1.0,
+  pivot: number = 0, left = false, transparencyRate: number = 1.0,
   separator: string = '', last: boolean = false): number {
   g.textAlign = 'start';
-  let colorPart = s.substring(0);
+  const colorPart = s.substring(0);
   let grayPart = separator;
-  if (last) {
+  if (last)
     grayPart = '';
-  }
+
   const textSize = g.measureText(colorPart + grayPart);
   const indent = 5;
 
@@ -96,14 +97,13 @@ function printLeftOrCentered(
 }
 
 export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
+  get name(): string { return 'macromoleculeSequence'; }
 
-  get name(): string {return 'macromoleculeSequence';}
-
-  get cellType(): string {return C.SEM_TYPES.Macro_Molecule;}
+  get cellType(): string { return C.SEM_TYPES.Macro_Molecule; }
 
-  get defaultHeight(): number {return 30;}
+  get defaultHeight(): number { return 30; }
 
-  get defaultWidth(): number {return 230;}
+  get defaultWidth(): number { return 230; }
 
   /**
    * Cell renderer function.
@@ -119,27 +119,27 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
    */
   render(
     g: CanvasRenderingContext2D, x: number, y: number, w: number, h: number, gridCell: DG.GridCell,
-    cellStyle: DG.GridCellStyle,
+    cellStyle: DG.GridCellStyle
   ): void {
-    const grid = gridCell.grid;
+    const grid = gridCell.gridRow !== -1 ? gridCell.grid : undefined;
     const cell = gridCell.cell;
     const tag = gridCell.cell.column.getTag(DG.TAGS.UNITS);
     if (tag === 'HELM') {
-      let host = ui.div([], {style: {width: `${w}px`, height: `${h}px`}});
+      const host = ui.div([], {style: {width: `${w}px`, height: `${h}px`}});
       host.setAttribute('dataformat', 'helm');
       host.setAttribute('data', gridCell.cell.value);
       gridCell.element = host;
       //@ts-ignore
-      var canvas = new JSDraw2.Editor(host, {width: w, height: h, skin: 'w8', viewonly: true});
-      var formula = canvas.getFormula(true);
+      const canvas = new JSDraw2.Editor(host, {width: w, height: h, skin: 'w8', viewonly: true});
+      const formula = canvas.getFormula(true);
       if (!formula) {
         gridCell.element = ui.divText(gridCell.cell.value, {style: {color: 'red'}});
       } else {
         gridCell.element = host;
-        var molWeight = Math.round(canvas.getMolWeight() * 100) / 100;
-        var coef = Math.round(canvas.getExtinctionCoefficient(true) * 100) / 100;
-        var molfile = canvas.getMolfile();
-        var result = formula + ', ' + molWeight + ', ' + coef + ', ' + molfile;
+        const molWeight = Math.round(canvas.getMolWeight() * 100) / 100;
+        const coef = Math.round(canvas.getExtinctionCoefficient(true) * 100) / 100;
+        const molfile = canvas.getMolfile();
+        const result = formula + ', ' + molWeight + ', ' + coef + ', ' + molfile;
         lru.set(gridCell.cell.value, result);
       }
     } else {
@@ -159,22 +159,20 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
       const palette = getPalleteByType(paletteType);
 
       const separator = gridCell.cell.column.getTag('separator') ?? '';
-      const splitterFunc: SplitterFunc = WebLogo.getSplitter(units, gridCell.cell.column.getTag('separator'));// splitter,
+      const splitterFunc: SplitterFunc = WebLogo.getSplitter(units, gridCell.cell.column.getTag('separator'));
 
       const subParts: string[] = splitterFunc(cell.value);
       // console.log(subParts);
-
-      const textSize = g.measureText(subParts.join(''));
       let x1 = x;
       let color = undefinedColor;
       subParts.forEach((amino, index) => {
         color = palette.get(amino);
         g.fillStyle = undefinedColor;
         let last = false;
-        if (index === subParts.length - 1) {
+        if (index === subParts.length - 1)
           last = true;
-        }
-        x1 = printLeftOrCentered(x1, y, w, h, g, amino, color, 0, true, false, 1.0, separator, last);
+
+        x1 = printLeftOrCentered(x1, y, w, h, g, amino, color, 0, true, 1.0, separator, last);
       });
 
       g.restore();

package/src/utils/convert.ts

@@ -1,6 +1,6 @@
 import * as DG from 'datagrok-api/dg';
 import * as ui from 'datagrok-api/ui';
-import {NotationConverter, NOTATION} from './notation-converter';
+import {NotationConverter, NOTATION} from '@datagrok-libraries/bio/src/utils/notation-converter';
 
 /**
  * Converts notations of a Macromolecule column

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

@@ -4,7 +4,6 @@ import * as DG from 'datagrok-api/dg';
 import Aioli from '@biowasm/aioli';
 
 import {AlignedSequenceEncoder} from '@datagrok-libraries/bio/src/sequence-encoder';
-import * as C from './constants';
 
 /**
  * Converts array of sequences into simple fasta string.

package/{test-Bio-34f75e5127b8-7af21e5d.html → test-Bio-34f75e5127b8-303cfb72.html}

@@ -1,4 +1,4 @@
-<html><head><meta charset="utf-8"/><title>Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=34f75e5127b8. Commit 7af21e5d.</title><style type="text/css">html,
+<html><head><meta charset="utf-8"/><title>Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=34f75e5127b8. Commit 303cfb72.</title><style type="text/css">html,
 body {
   font-family: Arial, Helvetica, sans-serif;
   font-size: 1rem;
@@ -229,7 +229,7 @@ header {
   font-size: 1rem;
   padding: 0 0.5rem;
 }
-</style></head><body><div id="jesthtml-content"><header><h1 id="title">Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=34f75e5127b8. Commit 7af21e5d.</h1></header><div id="metadata-container"><div id="timestamp">Started: 2022-07-12 16:48:34</div><div id="summary"><div id="suite-summary"><div class="summary-total">Suites (1)</div><div class="summary-passed summary-empty">0 passed</div><div class="summary-failed">1 failed</div><div class="summary-pending summary-empty">0 pending</div></div><div id="test-summary"><div class="summary-total">Tests (1)</div><div class="summary-passed summary-empty">0 passed</div><div class="summary-failed">1 failed</div><div class="summary-pending summary-empty">0 pending</div></div></div></div><div id="suite-1" class="suite-container"><div class="suite-info"><div class="suite-path">/home/runner/work/public/public/packages/Bio/src/__jest__/remote.test.ts</div><div class="suite-time warn">113.338s</div></div><div class="suite-tests"><div class="test-result failed"><div class="test-info"><div class="test-suitename"> </div><div class="test-title">TEST</div><div class="test-status">failed</div><div class="test-duration">100.002s</div></div><div class="failureMessages"> <pre class="failureMsg">Error: thrown: "Exceeded timeout of 100000 ms for a test.
+</style></head><body><div id="jesthtml-content"><header><h1 id="title">Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=34f75e5127b8. Commit 303cfb72.</h1></header><div id="metadata-container"><div id="timestamp">Started: 2022-07-13 14:53:02</div><div id="summary"><div id="suite-summary"><div class="summary-total">Suites (1)</div><div class="summary-passed summary-empty">0 passed</div><div class="summary-failed">1 failed</div><div class="summary-pending summary-empty">0 pending</div></div><div id="test-summary"><div class="summary-total">Tests (1)</div><div class="summary-passed summary-empty">0 passed</div><div class="summary-failed">1 failed</div><div class="summary-pending summary-empty">0 pending</div></div></div></div><div id="suite-1" class="suite-container"><div class="suite-info"><div class="suite-path">/home/runner/work/public/public/packages/Bio/src/__jest__/remote.test.ts</div><div class="suite-time warn">110.084s</div></div><div class="suite-tests"><div class="test-result failed"><div class="test-info"><div class="test-suitename"> </div><div class="test-title">TEST</div><div class="test-status">failed</div><div class="test-duration">100.002s</div></div><div class="failureMessages"> <pre class="failureMsg">Error: thrown: "Exceeded timeout of 100000 ms for a test.
 Use jest.setTimeout(newTimeout) to increase the timeout value, if this is a long-running test."
     at Object.&lt;anonymous&gt; (/home/runner/work/public/public/packages/Bio/src/__jest__/remote.test.ts:22:1)
     at Runtime._execModule (/home/runner/work/public/public/packages/Bio/node_modules/jest-runtime/build/index.js:1646:24)

package/src/tests/splitter-test.ts

@@ -1,22 +0,0 @@
-import {after, before, category, test, expect, expectObject} from '@datagrok-libraries/utils/src/test';
-
-import * as grok from 'datagrok-api/grok';
-import * as ui from 'datagrok-api/ui';
-import * as DG from 'datagrok-api/dg';
-import {WebLogo, SplitterFunc} from '@datagrok-libraries/bio/src/viewers/web-logo';
-
-category('splitter', () => {
-  const helm1 = '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}$$$';
-  const helm2 = 'PEPTIDE1{meI.hHis.Hcy.Q.T.W.Q.Phe_4NH2.D-Tyr_Et.Tyr_ab-dehydroMe.dV.E.N.N.meK}$$$';
-
-  test('helm1', async () => { await _testHelmSplitter(helm1); });
-  test('helm2', async () => { await _testHelmSplitter(helm2); });
-});
-
-export async function _testHelmSplitter(txt: string) {
-  // const splitter: SplitterFunc = WebLogo.getSplitterAsHelm();
-  //
-  // const mList: string[] = splitter(txt);
-  // expect(mList.length, 12);
-}
-

package/src/utils/notation-converter.ts

@@ -1,327 +0,0 @@
-import * as DG from 'datagrok-api/dg';
-import {WebLogo} from '@datagrok-libraries/bio/src/viewers/web-logo';
-
-/** enum type to simplify setting "user-friendly" notation if necessary */
-export const enum NOTATION {
-  FASTA = 'FASTA',
-  SEPARATOR = 'SEPARATOR',
-  HELM = 'HELM'
-}
-
-/** Class for handling conversion of notation systems in Macromolecule columns */
-export class NotationConverter {
-  private _sourceColumn: DG.Column; // the column to be converted
-  private _sourceUnits: string; // units, of the form fasta:SEQ:NT, etc.
-  private _sourceNotation: NOTATION; // current notation (without :SEQ:NT, etc.)
-
-  private get sourceUnits(): string { return this._sourceUnits; }
-
-  private get sourceColumn(): DG.Column { return this._sourceColumn; }
-
-  public get sourceNotation(): NOTATION { return this._sourceNotation; }
-
-  public isFasta(): boolean { return this.sourceNotation === NOTATION.FASTA; }
-
-  public isSeparator(): boolean { return this.sourceNotation === NOTATION.SEPARATOR; }
-
-  public isHelm(): boolean { return this.sourceNotation === NOTATION.HELM; }
-
-  public toFasta(targetNotation: NOTATION): boolean { return targetNotation === NOTATION.FASTA; }
-
-  public toSeparator(targetNotation: NOTATION): boolean { return targetNotation === NOTATION.SEPARATOR; }
-
-  public toHelm(targetNotation: NOTATION): boolean { return targetNotation === NOTATION.HELM; }
-
-  public isRna(): boolean { return this.sourceUnits.toLowerCase().endsWith('rna'); }
-
-  public isDna(): boolean { return this.sourceUnits.toLowerCase().endsWith('dna'); }
-
-  public isPeptide(): boolean { return this.sourceUnits.toLowerCase().endsWith('pt'); }
-
-  /** Associate notation types with the corresponding units */
-  /**
-   * @return {NOTATION}     Notation associated with the units type
-   */
-  private determineSourceNotation(): NOTATION {
-    if (this.sourceUnits.toLowerCase().startsWith('fasta'))
-      return NOTATION.FASTA;
-    else if (this.sourceUnits.toLowerCase().startsWith('separator'))
-      return NOTATION.SEPARATOR;
-    else
-      // TODO: handle possible exceptions
-      return NOTATION.HELM;
-  }
-
-  /**
-   * Determine the separator used in SEPARATOR column
-   *
-   * @return {string} The detected separator
-   */
-  private determineSeparator(): string {
-    //   TODO: figure out how to determine the separator efficiently
-    const col = this.sourceColumn;
-    let i = 0;
-    const re = /[^a-z]/;
-    while (i < col.length) {
-      const molecule = col.get(i);
-      const foundSeparator = molecule.toLowerCase().match(re);
-      if (foundSeparator)
-        return foundSeparator[0];
-      i++;
-    }
-    throw new Error('No separators found');
-  }
-
-  /**
-   * Create a new empty column of the specified notation type and the same
-   * length as sourceColumn
-   *
-   * @param {NOTATION} targetNotation
-   * @return {DG.Column}
-   */
-  private getNewColumn(targetNotation: NOTATION): DG.Column {
-    const col = this.sourceColumn;
-    const len = col.length;
-    const name = targetNotation + '(' + col.name + ')';
-    const newColName = col.dataFrame.columns.getUnusedName(name);
-    // dummy code
-    const newColumn = DG.Column.fromList('string', newColName, new Array(len).fill(''));
-    newColumn.semType = 'Macromolecule';
-    newColumn.setTag(
-      DG.TAGS.UNITS,
-      this.sourceUnits.replace(
-        this.sourceNotation.toLowerCase().toString(),
-        targetNotation.toLowerCase().toString()
-      )
-    );
-    // TODO: specify cell renderers for all cases
-    if (this.toFasta(targetNotation)) {
-      newColumn.setTag(
-        DG.TAGS.CELL_RENDERER,
-        'Macromolecule');
-    }
-    return newColumn;
-  }
-
-  /**
-   * Convert a Macromolecule column from FASTA to SEPARATOR notation
-   *
-   * @param {string} separator  A specific separator to be used
-   * @param {string} gapSymbol  Gap symbol in FASTA, '-' by default
-   * @return {DG.Column}        A new column in SEPARATOR notation
-   */
-  private convertFastaToSeparator(separator: string, gapSymbol: string = '-'): DG.Column {
-    // a function splitting FASTA sequence into an array of monomers:
-    const splitterAsFasta = WebLogo.splitterAsFasta;
-
-    const newColumn = this.getNewColumn(NOTATION.SEPARATOR);
-    // assign the values to the newly created empty column
-    newColumn.init((idx: number) => {
-      const fastaPolymer = this.sourceColumn.get(idx);
-      const fastaMonomersArray = splitterAsFasta(fastaPolymer);
-      for (let i = 0; i < fastaMonomersArray.length; i++) {
-        if (fastaMonomersArray[i] === gapSymbol)
-          fastaMonomersArray[i] = '';
-      }
-      return fastaMonomersArray.join(separator);
-    });
-    return newColumn;
-  }
-
-  /**
-   * Convert a Macromolecule column from FASTA to HELM
-   *
-   * @param {string} fastaGapSymbol   Optional fasta gap symbol
-   * @param {string} helmGapSymbol    Optional helm gap symbol
-   * @return {DG.Column}              A new column in HELM notation
-   */
-  private convertFastaToHelm(
-    fastaGapSymbol: string = '-',
-    helmGapSymbol: string = '*'
-  ): DG.Column {
-    // a function splitting FASTA sequence into an array of monomers
-    const splitterAsFasta = WebLogo.splitterAsFasta;
-
-    const prefix = (this.isDna()) ? 'DNA1{' :
-      (this.isRna()) ? 'RNA1{' :
-        (this.isPeptide()) ? 'PEPTIDE1{' :
-          'Unknown'; // this case should be handled as exceptional
-
-    if (prefix === 'Unknown')
-      throw new Error('Neither peptide, nor nucleotide');
-
-    const postfix = '}$$$';
-    const leftWrapper = (this.isDna()) ? 'D(' :
-      (this.isRna()) ? 'R(' : ''; // no wrapper for peptides
-    const rightWrapper = (this.isDna() || this.isRna()) ? ')P' : ''; // no wrapper for peptides
-
-    const newColumn = this.getNewColumn(NOTATION.HELM);
-    // assign the values to the empty column
-    newColumn.init((idx: number) => {
-      const fastaPolymer = this.sourceColumn.get(idx);
-      const fastaMonomersArray = splitterAsFasta(fastaPolymer);
-      const helmArray = [prefix];
-      let firstIteration = true;
-      for (let i = 0; i < fastaMonomersArray.length; i++) {
-        if (fastaMonomersArray[i] === fastaGapSymbol) {
-          // TODO: verify the correctness of gap symbols handling
-          helmArray.push(helmGapSymbol);
-        } else {
-          const dot = firstIteration ? '' : '.';
-          const item = [dot, leftWrapper, fastaMonomersArray[i], rightWrapper];
-          helmArray.push(item.join(''));
-        }
-        firstIteration = false;
-      }
-      helmArray.push(postfix);
-      return helmArray.join('');
-    });
-    return newColumn;
-  }
-
-  private handleSeparatorItemForFasta(
-    idx: number,
-    separatorItemsArray: string[],
-    separator: string,
-    gapSymbol: string,
-    fastaMonomersArray: string[]
-  ): void {
-    const item = separatorItemsArray[idx];
-    if (item.length > 1) {
-      // the case of a multi-character monomer
-      const monomer = '[' + item + ']';
-      fastaMonomersArray.push(monomer);
-    }
-    if (item === separator) {
-      if (idx !== 0 && separatorItemsArray[idx - 1] === separator)
-        fastaMonomersArray.push(gapSymbol);
-    }
-  }
-
-  private convertSeparatorToFasta(
-    separator: string | null = null,
-    gapSymbol: string = '-'
-  ): DG.Column {
-    // TODO: implementation
-    // * similarly to fasta2separator, divide string into monomers
-    // * adjacent separators is a gap (symbol to be specified)
-    // * the monomers MUST be single-character onles, otherwise forbid
-    // * NO, they can be multi-characters
-    // conversion
-    // * consider automatic determining the separator
-
-    // if (separator === null)
-    //   separator = this.determineSeparator();
-
-    // a function splitting FASTA sequence into an array of monomers
-    //const splitterAsSeparator = WebLogo.getSplitterWithSeparator(separator);
-    const splitter = WebLogo.getSplitterForColumn(this._sourceColumn);
-
-    const newColumn = this.getNewColumn(NOTATION.FASTA);
-    // assign the values to the empty column
-    newColumn.init((idx: number) => {
-      const separatorPolymer = this.sourceColumn.get(idx);
-      // items can be monomers or separators
-      const separatorItemsArray = splitter(separatorPolymer);
-      const fastaMonomersArray: string[] = [];
-      for (let i = 0; i < separatorItemsArray.length; i++) {
-        const item = separatorItemsArray[i];
-        if (item.length === 0) {
-          fastaMonomersArray.push(gapSymbol);
-        } else if (item.length > 1) {
-          // the case of a multi-character monomer
-          const monomer = '[' + item + ']';
-          fastaMonomersArray.push(monomer);
-        } else {
-          fastaMonomersArray.push(item);
-        }
-      }
-      return fastaMonomersArray.join('');
-    });
-    return newColumn;
-  }
-
-  private convertSeparatorToHelm(fastaGapSymbol: string = '-', helmGapSymbol: string = '*'): DG.Column {
-    // a function splitting FASTA sequence into an array of monomers
-    const splitter = WebLogo.getSplitterForColumn(this._sourceColumn);
-
-    const prefix = (this.isDna()) ? 'DNA1{' :
-      (this.isRna()) ? 'RNA1{' :
-        (this.isPeptide()) ? 'PEPTIDE1{' :
-          'Unknown'; // this case should be handled as exceptional
-
-    if (prefix === 'Unknown')
-      throw new Error('Neither peptide, nor nucleotide');
-
-    const postfix = '}$$$';
-    const leftWrapper = (this.isDna()) ? 'D(' :
-      (this.isRna()) ? 'R(' : ''; // no wrapper for peptides
-    const rightWrapper = (this.isDna() || this.isRna()) ? ')P' : ''; // no wrapper for peptides
-
-    const newColumn = this.getNewColumn(NOTATION.HELM);
-    // assign the values to the empty column
-    newColumn.init((idx: number) => {
-      const fastaPolymer = this.sourceColumn.get(idx);
-      const fastaMonomersArray = splitter(fastaPolymer);
-      const helmArray = [prefix];
-      let firstIteration = true;
-      for (let i = 0; i < fastaMonomersArray.length; i++) {
-        if (fastaMonomersArray[i] === fastaGapSymbol) {
-          // TODO: verify the correctness of gap symbols handling
-          helmArray.push(helmGapSymbol);
-        } else {
-          const dot = firstIteration ? '' : '.';
-          const item = [dot, leftWrapper, fastaMonomersArray[i], rightWrapper];
-          helmArray.push(item.join(''));
-        }
-        firstIteration = false;
-      }
-      helmArray.push(postfix);
-      return helmArray.join('');
-    });
-    return newColumn;
-  }
-
-  private convertHelmToFasta(): DG.Column {
-    // TODO: implementation
-    return this.getNewColumn(NOTATION.FASTA);
-  }
-
-  private convertHelmToSeparator(): DG.Column {
-    // TODO: implementatioreturn this.getNewColumn();
-    return this.getNewColumn(NOTATION.SEPARATOR);
-  }
-
-  /** Dispatcher method for notation conversion
-   *
-   * @param {NOTATION} targetNotation   Notation we want to convert to
-   * @param {string | null} tgtSeparator   Possible separator
-   * @return {DG.Column}                Converted column
-   */
-  public convert(targetNotation: NOTATION, tgtSeparator: string | null = null): DG.Column {
-    // possible exceptions
-    if (this.sourceNotation === targetNotation)
-      throw new Error('Target notation is invalid');
-    if (this.toSeparator(targetNotation) && tgtSeparator === null)
-      throw new Error('Target separator is not specified');
-
-    if (this.isFasta() && this.toSeparator(targetNotation) && tgtSeparator !== null)
-      return this.convertFastaToSeparator(tgtSeparator);
-    else if (this.isFasta() && this.toHelm(targetNotation))
-      return this.convertFastaToHelm();
-    else if (this.isSeparator() && this.toFasta(targetNotation))
-      return this.convertSeparatorToFasta(tgtSeparator!);
-    else if (this.isSeparator() && this.toHelm(targetNotation))
-      return this.convertSeparatorToHelm();
-    else if (this.isHelm() && this.toFasta(targetNotation))
-      return this.convertHelmToFasta();
-    else
-      return this.convertHelmToSeparator();
-  }
-
-  public constructor(col: DG.Column) {
-    this._sourceColumn = col;
-    this._sourceUnits = this._sourceColumn.tags[DG.TAGS.UNITS];
-    this._sourceNotation = this.determineSourceNotation();
-  }
-}