@datagrok/bio 2.4.45 → 2.4.47

package/package.json

@@ -5,16 +5,24 @@
     "name": "Leonid Stolbov",
     "email": "lstolbov@datagrok.ai"
   },
-  "version": "2.4.45",
+  "version": "2.4.47",
   "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",
     "url": "https://github.com/datagrok-ai/public.git",
     "directory": "packages/Bio"
   },
+  "properties": [
+    {
+      "name": "MaxMonomerLength",
+      "propertyType": "int",
+      "defaultValue": 3,
+      "nullable": false
+    }
+  ],
   "dependencies": {
     "@biowasm/aioli": "^3.1.0",
-    "@datagrok-libraries/bio": "^5.32.3",
+    "@datagrok-libraries/bio": "^5.32.5",
     "@datagrok-libraries/chem-meta": "^1.0.1",
     "@datagrok-libraries/ml": "^6.3.39",
     "@datagrok-libraries/tutorials": "^1.3.2",

package/scripts/sequence_generator.py

@@ -16,6 +16,14 @@
 # input: double fasta_separator = '' [Separator for a FASTA notation]
 # output: dataframe sequences
 
+"""
+The most simple options set running from command line
+  python sequence_generator.py -c 4 -s 50 > output_file.tsv
+Basic options:
+  -с number of clusters
+  -s cluster size (number of sequences per cluster)
+"""
+
 import random
 import argparse
 import sys

package/src/package-types.ts

@@ -0,0 +1,40 @@
+import * as grok from 'datagrok-api/grok';
+import * as DG from 'datagrok-api/dg';
+import * as ui from 'datagrok-api/ui';
+
+import {Observable, Subject} from 'rxjs';
+import {ObjectPropertyBag} from 'datagrok-api/dg';
+
+/** Names of package properties/settings declared in properties section of {@link './package.json'} */
+export const enum BioPackagePropertiesNames {
+  MaxMonomerLength = 'MaxMonomerLength',
+}
+
+
+export class BioPackageProperties extends Map<string, any> {
+
+  private _onPropertyChanged: Subject<string> = new Subject<string>();
+  public get onPropertyChanged(): Observable<string> { return this._onPropertyChanged; }
+
+  /** Monomer name maximum length displayed in short mode. */
+  public get maxMonomerLength(): number {
+    return super.get(BioPackagePropertiesNames.MaxMonomerLength) as unknown as number;
+  }
+
+  public set maxMonomerLength(value: number) {
+    super.set(BioPackagePropertiesNames.MaxMonomerLength, value as unknown as object);
+    this._onPropertyChanged.next(BioPackagePropertiesNames.MaxMonomerLength);
+  }
+
+  constructor(source: any) {
+    super(Object.entries(source));
+  }
+}
+
+export class BioPackage extends DG.Package {
+  private _properties: BioPackageProperties;
+  /** Package properties/settings declared in properties section of {@link './package.json'} */
+  public get properties(): BioPackageProperties { return this._properties; };
+
+  public set properties(value: BioPackageProperties) { this._properties = value; }
+}

package/src/package.ts

@@ -14,7 +14,7 @@ import {
   createLinesGrid, createPropPanelElement, createTooltipElement, getChemSimilaritiesMatrix,
 } from './analysis/sequence-activity-cliffs';
 import {convert} from './utils/convert';
-import {getMacroMolColumnPropertyPanel} from './widgets/representations';
+import {getMacromoleculeColumnPropertyPanel} from './widgets/representations';
 import {_toAtomicLevel} from '@datagrok-libraries/bio/src/monomer-works/to-atomic-level';
 import {FastaFileHandler} from '@datagrok-libraries/bio/src/utils/fasta-handler';
 import {removeEmptyStringRows} from '@datagrok-libraries/utils/src/dataframe-utils';
@@ -53,8 +53,12 @@ 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';
+import {BioPackage, BioPackageProperties} from './package-types';
+import {RDModule} from '@datagrok-libraries/chem-meta/src/rdkit-api';
+import {ObjectPropertyBag} from 'datagrok-api/dg';
+import {PackageSettingsEditorWidget} from './widgets/package-settings-editor-widget';
 
-export const _package = new DG.Package();
+export const _package = new BioPackage();
 
 // /** Avoid reassinging {@link monomerLib} because consumers subscribe to {@link IMonomerLib.onChanged} event */
 // let monomerLib: MonomerLib | null = null;
@@ -82,11 +86,20 @@ export class SeqPaletteCustom implements SeqPalette {
 
 //tags: init
 export async function initBio() {
-  await MonomerLibHelper.instance.loadLibraries();
+  let module: RDModule;
+  await Promise.all([
+    (async () => { await MonomerLibHelper.instance.loadLibraries(); })(),
+    (async () => { module = await grok.functions.call('Chem:getRdKitModule'); })(),
+    (async () => {
+      const pkgProps = await _package.getProperties();
+      const bioPkgProps = new BioPackageProperties(pkgProps);
+      _package.properties = bioPkgProps;
+    })(),
+  ]);
+
   const monomerLib = MonomerLibHelper.instance.getBioLib();
   const monomers: string[] = [];
   const logPs: number[] = [];
-  const module = await grok.functions.call('Chem:getRdKitModule');
 
   const series = monomerLib!.getMonomerMolsByPolymerType('PEPTIDE')!;
   Object.keys(series).forEach((symbol) => {
@@ -173,6 +186,21 @@ export async function libraryPanel(_seqColumn: DG.Column): Promise<DG.Widget> {
   return new DG.Widget(ui.divV([inputsForm, ui.div(filesButton)]));
 }
 
+// -- Package settings editor --
+
+//name: packageSettingsEditor
+//description: The database connection
+//tags: packageSettingsEditor
+//input: object propList
+//output: widget result
+export function packageSettingsEditor(propList: DG.Property[]): DG.Widget {
+  const widget = new PackageSettingsEditorWidget(propList);
+  widget.init().then(); // Ignore promise returned
+  return widget;
+}
+
+// -- Cell renderers --
+
 //name: fastaSequenceCellRenderer
 //tags: cellRenderer
 //meta.cellType: sequence
@@ -187,7 +215,7 @@ export function fastaSequenceCellRenderer(): MacromoleculeSequenceCellRenderer {
 //tags: panel
 //output: widget result
 export function macroMolColumnPropertyPanel(molColumn: DG.Column): DG.Widget {
-  return getMacroMolColumnPropertyPanel(molColumn);
+  return getMacromoleculeColumnPropertyPanel(molColumn);
 }
 
 //name: separatorSequenceCellRenderer
@@ -743,7 +771,7 @@ export async function webLogoLargeApp(): Promise<void> {
   const pi = DG.TaskBarProgressIndicator.create('WebLogo');
   try {
     const app = new WebLogoApp();
-    const df: DG.DataFrame = await _package.files.readCsv('data/sample_PT_10000.csv');
+    const df: DG.DataFrame = await _package.files.readCsv('data/sample_PT_100000x5.csv');
     await grok.data.detectSemanticTypes(df);
     await app.init(df, 'webLogoLargeApp');
   } finally {

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

@@ -61,8 +61,8 @@ ATC-G-TTGC--
 
     for (let i = 0; i < positions.length; i++) {
       expect(positions[i].name, resAllDf1[i].name);
-      for (const key in positions[i].freq)
-        expect(positions[i].freq[key].count, resAllDf1[i].freq[key].count);
+      for (const m of positions[i].getMonomers())
+        expect(positions[i].getFreq(m).count, resAllDf1[i].getFreq(m).count);
     }
   }, {skipReason: 'GROK-13300'});
 
@@ -109,8 +109,8 @@ ATC-G-TTGC--
 
     for (let i = 0; i < positions.length; i++) {
       expect(positions[i].name, resAllDf1[i].name);
-      for (const key in positions[i].freq)
-        expect(positions[i].freq[key].count, resAllDf1[i].freq[key].count);
+      for (const m of positions[i].getMonomers())
+        expect(positions[i].getFreq(m).count, resAllDf1[i].getFreq(m).count);
     }
   }, {skipReason: 'GROK-13300'});
 
@@ -187,10 +187,10 @@ ATC-G-TTGC--
 
 function expectPositionInfo(actualPos: PI, expectedPos: PI): void {
   expect(actualPos.name, expectedPos.name);
-  expectArray(Object.keys(actualPos.freq), Object.keys(expectedPos.freq));
-  for (const key in actualPos.freq) {
+  expectArray(actualPos.getMonomers(), expectedPos.getMonomers());
+  for (const key of actualPos.getMonomers()) {
     //
-    expect(actualPos.freq[key].count, expectedPos.freq[key].count);
+    expect(actualPos.getFreq(key).count, expectedPos.getFreq(key).count);
   }
 }
 

package/src/tests/msa-tests.ts

@@ -9,9 +9,6 @@ import {multipleSequenceAlignmentUI} from '../utils/multiple-sequence-alignment-
 import {awaitContainerStart} from './utils';
 //import * as grok from 'datagrok-api/grok';
 
-export const _package = new DG.Package();
-
-
 category('MSA', async () => {
   //table = await grok.data.files.openTable('Demo:Files/bio/peptides.csv');
   const fromCsv = `seq

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

@@ -0,0 +1,27 @@
+import * as grok from 'datagrok-api/grok';
+import * as ui from 'datagrok-api/ui';
+import * as DG from 'datagrok-api/dg';
+
+export enum MonomerWidthMode {
+  long = 'long',
+  short = 'short',
+}
+
+export const enum Tags {
+  calculated = '.mm.cellRenderer.calculated',
+}
+
+export const enum Temps {
+  monomerWidth = '.mm.cellRenderer.monomerWidth',
+  maxMonomerLength = '.mm.cellRenderer.maxMonomerLength',
+  colorCode = '.mm.cellRenderer.colorCode',
+  compareWithCurrent = '.mm.cellRenderer.compareWithCurrent',
+  highlightDifference = '.mm.cellRenderer.highlightDifference',
+}
+
+// export const MacromoleculeCellRendererDefaults = new class {
+//   monomerWidth: MonomerWidthMode = MonomerWidthMode.short;
+//   maxMonomerLength: number = 3;
+//   colorCode: boolean = true;
+//   compareWithCurrent: boolean = true;
+// }();

package/src/utils/cell-renderer.ts

@@ -15,9 +15,10 @@ import {
 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 {Tags as mmcrTags, Temps as mmcrTemps} from '../utils/cell-renderer-consts';
 
-import {_package, getMonomerLibHelper} from '../package';
 import * as C from './constants';
+import {_package} from '../package';
 
 const enum tempTAGS {
   referenceSequence = 'reference-sequence',
@@ -154,19 +155,19 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
     const referenceSequence: string[] = splitterFunc(
       ((tempReferenceSequence != null) && (tempReferenceSequence != '')) ?
         tempReferenceSequence : tempCurrentWord ?? '');
-    const monomerWidth: string = (tempMonomerWidth != null) ? tempMonomerWidth : 'short';
+    const monomerWidth: string = tempMonomerWidth ?? 'short';
 
     let gapRenderer = 5;
     let maxIndex = 0;
-    let maxLengthOfMonomer = 8;
+    let maxLengthOfMonomer: number = 8;
 
     if (monomerWidth === 'short') {
       gapRenderer = 12;
-      maxLengthOfMonomer = 1;
+      maxLengthOfMonomer = colTemp[mmcrTemps.maxMonomerLength] ?? _package.properties.maxMonomerLength;
     }
 
     let maxLengthWords: any = {};
-    if (gridCell.cell.column.getTag('.calculatedCellRender') !== splitLimit.toString()) {
+    if (gridCell.cell.column.getTag(mmcrTags.calculated) !== splitLimit.toString()) {
       let samples = 0;
       while (samples < Math.min(gridCell.cell.column.length, 100)) {
         const column = gridCell.cell.column.get(samples);
@@ -188,7 +189,7 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
         colTemp[tempTAGS.bioSumMaxLengthWords] = maxLengthWordSum;
         colTemp[tempTAGS.bioMaxIndex] = maxIndex;
         colTemp[tempTAGS.bioMaxLengthWords] = maxLengthWords;
-        gridCell.cell.column.setTag('.calculatedCellRender', splitLimit.toString());
+        gridCell.cell.column.setTag(mmcrTags.calculated, splitLimit.toString());
       }
     } else {
       maxLengthWords = colTemp[tempTAGS.bioMaxLengthWords];