@datagrok/bio 2.4.44 → 2.4.45

package/package.json

@@ -5,7 +5,7 @@
     "name": "Leonid Stolbov",
     "email": "lstolbov@datagrok.ai"
   },
-  "version": "2.4.44",
+  "version": "2.4.45",
   "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",

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

@@ -0,0 +1,42 @@
+import * as grok from 'datagrok-api/grok';
+import * as ui from 'datagrok-api/ui';
+import * as DG from 'datagrok-api/dg';
+
+export class SplitToMonomersFunctionEditor {
+  tableInput: DG.InputBase;
+  seqColInput: DG.InputBase;
+
+  funcParamsDiv: HTMLDivElement;
+
+  get funcParams(): {} {
+    return {
+      table: this.tableInput.value!,
+      sequence: this.seqColInput.value!,
+    };
+  }
+
+  get paramsUI(): HTMLDivElement {
+    return this.funcParamsDiv;
+  }
+
+  constructor() {
+    this.tableInput = ui.tableInput('Table', grok.shell.tv.dataFrame, undefined, () => {
+      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.funcParamsDiv = ui.inputs([
+      this.tableInput,
+      this.seqColInput,
+    ], {style: {minWidth: '320px'}});
+  }
+
+  onTableInputChanged(): void {
+    this.seqColInput = ui.columnInput('Sequence', this.tableInput.value!,
+      this.tableInput.value!.columns.bySemType(DG.SEMTYPE.MACROMOLECULE));
+  }
+}

package/src/package-test.ts

@@ -8,7 +8,9 @@ import './tests/detectors-tests';
 import './tests/detectors-weak-and-likely-tests';
 import './tests/detectors-benchmark-tests';
 import './tests/msa-tests';
-import './tests/splitters-test';
+
+import './tests/splitters-test'; //Unhandled exceptions.exceptions : Cannot read properties of null (reading 'f')
+
 import './tests/monomer-libraries-tests';
 import './tests/renderers-test';
 import './tests/converters-test';

package/src/package.ts

@@ -2,8 +2,9 @@
 import * as grok from 'datagrok-api/grok';
 import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
+
 import {
-  MacromoleculeDifferenceCellRenderer, MacromoleculeSequenceCellRenderer, MonomerCellRenderer,
+  MacromoleculeDifferenceCellRenderer, MacromoleculeSequenceCellRenderer,
 } from './utils/cell-renderer';
 import {VdRegionsViewer} from './viewers/vd-regions-viewer';
 import {SequenceAlignment} from './seq_align';
@@ -18,8 +19,6 @@ import {_toAtomicLevel} from '@datagrok-libraries/bio/src/monomer-works/to-atomi
 import {FastaFileHandler} from '@datagrok-libraries/bio/src/utils/fasta-handler';
 import {removeEmptyStringRows} from '@datagrok-libraries/utils/src/dataframe-utils';
 
-import {splitAlignedSequences} from '@datagrok-libraries/bio/src/utils/splitter';
-import * as C from './utils/constants';
 import {SequenceSimilarityViewer} from './analysis/sequence-similarity-viewer';
 import {SequenceDiversityViewer} from './analysis/sequence-diversity-viewer';
 import {substructureSearchDialog} from './substructure-search/substructure-search';
@@ -39,6 +38,7 @@ import {getMacromoleculeColumn} from './utils/ui-utils';
 import {DimReductionMethods, ITSNEOptions, IUMAPOptions} from '@datagrok-libraries/ml/src/reduce-dimensionality';
 import {SequenceSpaceFunctionEditor} from '@datagrok-libraries/ml/src/functionEditors/seq-space-editor';
 import {ActivityCliffsFunctionEditor} from '@datagrok-libraries/ml/src/functionEditors/activity-cliffs-editor';
+
 import {demoBio01UI} from './demo/bio01-similarity-diversity';
 import {demoBio01aUI} from './demo/bio01a-hierarchical-clustering-and-sequence-space';
 import {demoBio01bUI} from './demo/bio01b-hierarchical-clustering-and-activity-cliffs';
@@ -50,6 +50,9 @@ import {MmDistanceFunctionsNames} from '@datagrok-libraries/ml/src/macromolecule
 import {BitArrayMetrics, BitArrayMetricsNames} from '@datagrok-libraries/ml/src/typed-metrics';
 import {NotationConverter} from '@datagrok-libraries/bio/src/utils/notation-converter';
 import {WebLogoApp} from './apps/web-logo-app';
+import {SplitToMonomersFunctionEditor} from './function-edtiors/split-to-monomers-editor';
+import {splitToMonomersUI} from './utils/split-to-monomers';
+import {MonomerCellRenderer} from './utils/monomer-cell-renderer';
 
 export const _package = new DG.Package();
 
@@ -248,7 +251,7 @@ export function SeqActivityCliffsEditor(call: DG.FuncCall) {
   ui.dialog({title: 'Activity Cliffs'})
     .add(funcEditor.paramsUI)
     .onOK(async () => {
-      call.func.prepare(funcEditor.funcParams).call(true);
+      return call.func.prepare(funcEditor.funcParams).call(true);
     })
     .show();
 }
@@ -342,7 +345,7 @@ export function SequenceSpaceEditor(call: DG.FuncCall) {
   ui.dialog({title: 'Sequence Space'})
     .add(funcEditor.paramsUI)
     .onOK(async () => {
-      call.func.prepare(funcEditor.funcParams).call(true);
+      return call.func.prepare(funcEditor.funcParams).call(true);
     })
     .show();
 }
@@ -364,8 +367,7 @@ export async function sequenceSpaceTopMenu(
   // Delay is required for initial function dialog to close before starting invalidating of molfiles.
   // Otherwise, dialog is freezing
   await delay(10);
-  if (!checkInputColumnUI(macroMolecule, 'Sequence space'))
-    return;
+  if (!checkInputColumnUI(macroMolecule, 'Sequence space')) return;
 
   const embedColsNames = getEmbeddingColsNames(table);
   const withoutEmptyValues = DG.DataFrame.fromColumns([macroMolecule]).clone();
@@ -586,6 +588,7 @@ export function convertDialog() {
 //name: monomerCellRenderer
 //tags: cellRenderer
 //meta.cellType: Monomer
+//meta.columnTags: quality=Monomer
 //output: grid_cell_renderer result
 export function monomerCellRenderer(): MonomerCellRenderer {
   return new MonomerCellRenderer();
@@ -642,20 +645,27 @@ export async function testDetectMacromolecule(path: string): Promise<DG.DataFram
   return resDf;
 }
 
-//top-menu: Bio | Split to monomers
-//name: splitToMonomers
-export function splitToMonomers(): void {
-  const col = getMacromoleculeColumn();
-  const tempDf = splitAlignedSequences(col);
-  const originalDf = col.dataFrame;
-  for (const tempCol of tempDf.columns) {
-    const newCol = originalDf.columns.add(tempCol);
-    newCol.semType = C.SEM_TYPES.MONOMER;
-    // TODO: GROK-
-    //newCol.setTag(DG.TAGS.CELL_RENDERER, C.SEM_TYPES.MONOMER);
-    newCol.setTag(bioTAGS.alphabet, col.getTag(bioTAGS.alphabet));
-  }
-  grok.shell.tv.grid.invalidate();
+//name: SplitToMonomersEditor
+//tags: editor
+//input: funccall call
+export function SplitToMonomersEditor(call: DG.FuncCall): void {
+  const funcEditor = new SplitToMonomersFunctionEditor();
+  ui.dialog({title: 'Split to Monomers'})
+    .add(funcEditor.paramsUI)
+    .onOK(async () => {
+      return call.func.prepare(funcEditor.funcParams).call(true);
+    })
+    .show();
+}
+
+//top-menu: Bio | Split to Monomers
+//name: Split to Monomers
+//input: dataframe table
+//input: column sequence { semType: Macromolecule }
+//output: dataframe result
+//editor: Bio:SplitToMonomersEditor
+export async function splitToMonomersTopMenu(table: DG.DataFrame, sequence: DG.Column): Promise<void> {
+  await splitToMonomersUI(table, sequence);
 }
 
 //name: Bio: getHelmMonomers

package/src/tests/splitters-test.ts

@@ -6,6 +6,7 @@ import {after, before, category, test, expect, expectArray, delay} from '@datagr
 import * as C from '../utils/constants';
 import {_package, getHelmMonomers} from '../package';
 import {TAGS as bioTAGS, splitterAsFasta, splitterAsHelm} from '@datagrok-libraries/bio/src/utils/macromolecule';
+import {splitToMonomersUI} from '../utils/split-to-monomers';
 
 
 category('splitters', async () => {
@@ -77,14 +78,15 @@ category('splitters', async () => {
       seqCol.semType = semType;
     seqCol.setTag(bioTAGS.aligned, C.MSA);
 
-    const _tv: DG.TableView = grok.shell.addTableView(df);
-    await delay(500); // needed to account for table adding
-    // call to calculate 'cell.renderer' tag
-    await grok.data.detectSemanticTypes(df);
+    const newDf = await splitToMonomersUI(df, seqCol);
+    expect(newDf.columns.names().includes('17'), true);
 
-    await grok.functions.call('Bio:splitToMonomers');
-    expect(df.columns.names().includes('17'), true);
-  });
+    // TODO: Check cell.renderer for columns of monomers
+    // const _tv: DG.TableView = grok.shell.addTableView(df);
+    // await delay(500); // needed to account for table adding
+    // // call to calculate 'cell.renderer' tag
+    // await grok.data.detectSemanticTypes(df);
+  }, {skipReason: 'GROK-13300'});
 
   test('getHelmMonomers', async () => {
     const df: DG.DataFrame = DG.DataFrame.fromCsv(

package/src/utils/cell-renderer.ts

@@ -3,9 +3,8 @@ import * as DG from 'datagrok-api/dg';
 import * as ui from 'datagrok-api/ui';
 
 import {printLeftOrCentered, DrawStyle} from '@datagrok-libraries/bio/src/utils/cell-renderer';
-import * as C from './constants';
 import {
-  ALIGNMENT,
+  ALIGNMENT, ALPHABET,
   getPaletteByType,
   getSplitter,
   monomerToShort,
@@ -15,6 +14,10 @@ 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 {MonomerWorks} from '@datagrok-libraries/bio/src/monomer-works/monomer-works';
+
+import {_package, getMonomerLibHelper} from '../package';
+import * as C from './constants';
 
 const enum tempTAGS {
   referenceSequence = 'reference-sequence',
@@ -215,58 +218,6 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
   }
 }
 
-export class MonomerCellRenderer extends DG.GridCellRenderer {
-  get name(): string { return C.SEM_TYPES.MONOMER; }
-
-  get cellType(): string { return C.SEM_TYPES.MONOMER; }
-
-  get defaultHeight(): number { return 15; }
-
-  get defaultWidth(): number { return 30; }
-
-  /**
-   * Cell renderer function.
-   *
-   * @param {CanvasRenderingContext2D} g Canvas rendering context.
-   * @param {number} x x coordinate on the canvas.
-   * @param {number} y y coordinate on the canvas.
-   * @param {number} w width of the cell.
-   * @param {number} h height of the cell.
-   * @param {DG.GridCell} gridCell Grid cell.
-   * @param {DG.GridCellStyle} _cellStyle Cell style.
-   */
-  render(
-    g: CanvasRenderingContext2D, x: number, y: number, w: number, h: number, gridCell: DG.GridCell,
-    _cellStyle: DG.GridCellStyle): void {
-    g.font = `12px monospace`;
-    g.textBaseline = 'middle';
-    g.textAlign = 'center';
-
-    const palette = getPaletteByType(gridCell.cell.column.getTag(bioTAGS.alphabet));
-    const s: string = gridCell.cell.value;
-    if (!s)
-      return;
-    const color = palette.get(s);
-
-    g.fillStyle = color;
-    g.fillText(monomerToShort(s, 3), x + (w / 2), y + (h / 2), w);
-  }
-
-  svgMolOptions = {autoCrop: true, autoCropMargin: 0, suppressChiralText: true};
-
-  onMouseEnter(gridCell: DG.GridCell, e: MouseEvent) {
-    super.onMouseEnter(gridCell, e);
-
-    // TODO: Display monomer structure within tooltip
-    // const monomerName = gridCell.cell.value;
-    // const mw = getMonomerWorksInstance();
-    // // TODO: Display monomer structure in Tooltip
-    // const nameDiv = ui.div(monomerName);
-    // const molDiv = grok.chem.svgMol(monomerMol, undefined, undefined, svgMolOptions);
-    //
-    // ui.tooltip.show(ui.divV([nameDiv, molEl,]), x, y);
-  }
-}
 
 export class MacromoleculeDifferenceCellRenderer extends DG.GridCellRenderer {
   get name(): string { return 'MacromoleculeDifferenceCR'; }

package/src/utils/monomer-cell-renderer.ts

@@ -0,0 +1,100 @@
+import * as grok from 'datagrok-api/grok';
+import * as DG from 'datagrok-api/dg';
+import * as ui from 'datagrok-api/ui';
+
+import {ALPHABET, getPaletteByType, monomerToShort} from '@datagrok-libraries/bio/src/utils/macromolecule';
+import {TAGS as bioTAGS} from '@datagrok-libraries/bio/src/utils/macromolecule/consts';
+import {MonomerWorks} from '@datagrok-libraries/bio/src/monomer-works/monomer-works';
+
+import {getMonomerLibHelper} from '../package';
+import * as C from './constants';
+
+const Tags = new class {
+  tooltipHandlerTemp = 'tooltip-handler.Monomer';
+}();
+
+const svgMolOptions = {autoCrop: true, autoCropMargin: 0, suppressChiralText: true};
+
+export class MonomerTooltipHandler {
+  private readonly grid: DG.Grid;
+
+  constructor(grid: DG.Grid) {
+    this.grid = grid;
+    this.grid.onCellTooltip(this.onCellTooltip.bind(this));
+  }
+
+  private onCellTooltip(gridCell: DG.GridCell, x: number, y: number): any {
+    if (gridCell.grid.dart != this.grid.dart || !gridCell.tableColumn || !gridCell.isTableCell ||
+      gridCell.tableColumn.semType != 'Monomer') return false;
+
+    const alphabet = gridCell.tableColumn.getTag(bioTAGS.alphabet);
+    const monomerName = gridCell.cell.value;
+    const mw = new MonomerWorks(getMonomerLibHelper().getBioLib());
+    const monomerType: string = (alphabet === ALPHABET.DNA || alphabet === ALPHABET.RNA) ? 'RNA' :
+      alphabet === ALPHABET.PT ? 'PEPTIDE' : 'PEPTIDE';
+
+    const monomerMol: string | null = mw.getCappedRotatedMonomer(monomerType, monomerName);
+    const nameDiv = ui.div(monomerName);
+    const molDiv = !monomerMol ? null :
+      grok.chem.svgMol(monomerMol, undefined, undefined, svgMolOptions);
+
+    const canvasClientRect = gridCell.grid.canvas.getBoundingClientRect();
+    const x1 = gridCell.bounds.right + canvasClientRect.left - 4;
+    const y1 = gridCell.bounds.bottom + canvasClientRect.top - 4;
+    ui.tooltip.show(ui.divV([nameDiv, ...(molDiv ? [molDiv] : [])]), x1, y1);
+
+    return true; // To prevent default tooltip behaviour
+  }
+
+  public static getOrCreate(grid: DG.Grid): MonomerTooltipHandler {
+    const gridTemp: { [tempName: string]: any } = grid.dataFrame.temp;
+    if (!(Tags.tooltipHandlerTemp in gridTemp)) {
+      gridTemp[Tags.tooltipHandlerTemp] = new MonomerTooltipHandler(grid);
+      grid.temp = gridTemp;
+    }
+    return gridTemp[Tags.tooltipHandlerTemp];
+  }
+}
+
+export class MonomerCellRenderer extends DG.GridCellRenderer {
+  get name(): string { return C.SEM_TYPES.MONOMER; }
+
+  get cellType(): string { return C.SEM_TYPES.MONOMER; }
+
+  get defaultHeight(): number { return 15; }
+
+  get defaultWidth(): number { return 30; }
+
+  /**
+   * Cell renderer function.
+   *
+   * @param {CanvasRenderingContext2D} g Canvas rendering context.
+   * @param {number} x x coordinate on the canvas.
+   * @param {number} y y coordinate on the canvas.
+   * @param {number} w width of the cell.
+   * @param {number} h height of the cell.
+   * @param {DG.GridCell} gridCell Grid cell.
+   * @param {DG.GridCellStyle} _cellStyle Cell style.
+   */
+  render(
+    g: CanvasRenderingContext2D, x: number, y: number, w: number, h: number, gridCell: DG.GridCell,
+    _cellStyle: DG.GridCellStyle
+  ): void {
+    if (gridCell.gridRow < 0) return;
+    MonomerTooltipHandler.getOrCreate(gridCell.grid);
+
+
+    g.font = `12px monospace`;
+    g.textBaseline = 'middle';
+    g.textAlign = 'center';
+
+    const palette = getPaletteByType(gridCell.cell.column.getTag(bioTAGS.alphabet));
+    const s: string = gridCell.cell.value;
+    if (!s)
+      return;
+    const color = palette.get(s);
+
+    g.fillStyle = color;
+    g.fillText(monomerToShort(s, 3), x + (w / 2), y + (h / 2), w);
+  }
+}

package/src/utils/split-to-monomers.ts

@@ -0,0 +1,29 @@
+import {delay} from '@datagrok-libraries/utils/src/test';
+import {checkInputColumnUI} from './check-input-column';
+import {splitAlignedSequences} from '@datagrok-libraries/bio/src/utils/splitter';
+import * as C from './constants';
+import {TAGS as bioTAGS} from '@datagrok-libraries/bio/src/utils/macromolecule/consts';
+import * as grok from 'datagrok-api/grok';
+import * as DG from 'datagrok-api/dg';
+
+
+export async function splitToMonomersUI(table: DG.DataFrame, seqCol: DG.Column<string>): Promise<DG.DataFrame> {
+  // Delay is required for initial function dialog to close before starting invalidating of molfiles.
+  // Otherwise, dialog is freezing
+  await delay(10);
+  if (!checkInputColumnUI(seqCol, 'Sequence space')) return table;
+
+  const tempDf = splitAlignedSequences(seqCol);
+  const originalDf = seqCol.dataFrame;
+  for (const tempCol of tempDf.columns) {
+    // TODO: GROK-11212
+    // tempCol.setTag(DG.TAGS.CELL_RENDERER, C.SEM_TYPES.MONOMER);
+    tempCol.semType = C.SEM_TYPES.MONOMER;
+    tempCol.setTag(bioTAGS.alphabet, seqCol.getTag(bioTAGS.alphabet));
+  }
+  // Create the new data frame to enable platform to setup cell renderers
+  const newDf = originalDf.join(tempDf, [], [], undefined, undefined, DG.JOIN_TYPE.LEFT, false);
+  grok.shell.addTableView(newDf);
+
+  return newDf;
+}