@datagrok/bio 2.10.28 → 2.11.0

package/package.json

@@ -5,7 +5,7 @@
     "name": "Leonid Stolbov",
     "email": "lstolbov@datagrok.ai"
   },
-  "version": "2.10.28",
+  "version": "2.11.0",
   "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",
@@ -34,7 +34,7 @@
   ],
   "dependencies": {
     "@biowasm/aioli": "^3.1.0",
-    "@datagrok-libraries/bio": "^5.38.13",
+    "@datagrok-libraries/bio": "^5.39.0",
     "@datagrok-libraries/chem-meta": "^1.0.1",
     "@datagrok-libraries/ml": "^6.3.50",
     "@datagrok-libraries/tutorials": "^1.3.6",

package/src/apps/web-logo-app.ts

@@ -4,7 +4,7 @@ import * as DG from 'datagrok-api/dg';
 
 import wu from 'wu';
 
-import {IWebLogoViewer} from '@datagrok-libraries/bio/src/viewers/web-logo';
+import {IWebLogoViewer, WebLogoProps} from '@datagrok-libraries/bio/src/viewers/web-logo';
 
 import {PROPS as wlPROPS} from '../viewers/web-logo-viewer';
 
@@ -14,7 +14,11 @@ export class WebLogoApp {
   df: DG.DataFrame;
   view: DG.TableView;
 
-  constructor(private readonly urlParams: URLSearchParams, private readonly funcName: string) {}
+  constructor(
+    private readonly urlParams: URLSearchParams,
+    private readonly funcName: string,
+    private readonly options: Partial<WebLogoProps> = {}
+  ) {}
 
   async init(df: DG.DataFrame): Promise<void> {
     this.df = df;
@@ -32,7 +36,7 @@ export class WebLogoApp {
     this.view = grok.shell.addTableView(this.df);
     this.view.path = this.view.basePath = `func/${_package.name}.${this.funcName}?${urlParamsTxt}`;
 
-    const options: { [p: string]: any } = {sequenceColumnName: 'sequence'};
+    const options: { [p: string]: any } = {...this.options, ...{sequenceColumnName: 'sequence'}};
     for (const [optName, optValue] of this.urlParams.entries()) {
       switch (optName) {
         // boolean

package/src/package.ts

@@ -65,7 +65,8 @@ import {PackageSettingsEditorWidget} from './widgets/package-settings-editor-wid
 import {getCompositionAnalysisWidget} from './widgets/composition-analysis-widget';
 import {MacromoleculeColumnWidget} from './utils/macromolecule-column-widget';
 import {addCopyMenuUI} from './utils/context-menu';
-import {_getEnumeratorWidget, _setPeptideColumn} from './utils/enumerator-tools';
+import {getPolyToolDialog} from './utils/poly-tool/enumerator-tools';
+import {_setPeptideColumn} from './utils/poly-tool/utils';
 import {getRegionDo} from './utils/get-region';
 import {GetRegionApp} from './apps/get-region-app';
 import {GetRegionFuncEditor} from './utils/get-region-func-editor';
@@ -763,6 +764,19 @@ export function convertDialog() {
   convert(col);
 }
 
+//top-menu: Bio | Convert | PolyTool
+//name: polyTool
+//description: Perform cyclization of polymers
+export function polyTool(): void {
+  let dialog: DG.Dialog;
+  try {
+    dialog = getPolyToolDialog();
+    dialog.show();
+  } catch (err: any) {
+    grok.shell.warning('To run PolyTool, open a dataframe with macromolecules');
+  }
+}
+
 //name: monomerCellRenderer
 //tags: cellRenderer
 //meta.cellType: Monomer
@@ -962,6 +976,20 @@ export async function webLogoLargeApp(): Promise<void> {
   }
 }
 
+//name: webLogoAggApp
+export async function webLogoAggApp(): Promise<void> {
+  const pi = DG.TaskBarProgressIndicator.create('WebLogo ...');
+  try {
+    const urlParams = new URLSearchParams(window.location.search);
+    const app = new WebLogoApp(urlParams, 'webLogoAggApp');
+    const df: DG.DataFrame = await _package.files.readCsv('data/sample_FASTA_PT_activity.csv');
+    await grok.data.detectSemanticTypes(df);
+    await app.init(df);
+  } finally {
+    pi.close();
+  }
+}
+
 //name: getRegionApp
 export async function getRegionApp(): Promise<void> {
   const pi = DG.TaskBarProgressIndicator.create('getRegion ...');
@@ -1056,15 +1084,6 @@ export async function enumeratorColumnChoice(df: DG.DataFrame, macroMolecule: DG
   await grok.data.detectSemanticTypes(df);
 }
 
-//name: PolyTool
-//input: column molColumn {semType: Macromolecule}
-//tags: panel, exclude-actions-panel
-//output: widget result
-export function getEnumeratorWidget(molColumn: DG.Column): DG.Widget {
-  return _getEnumeratorWidget(molColumn);
-}
-
-
 //top-menu: Bio | Convert | SDF to JSON Library...
 //name: SDF to JSON Library
 //input: dataframe table

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

@@ -55,7 +55,7 @@ ATC-G-TTGC--
     for (let i = 0; i < positions.length; i++) {
       expect(positions[i].name, resAllDf1[i].name);
       for (const m of positions[i].getMonomers())
-        expect(positions[i].getFreq(m).count, resAllDf1[i].getFreq(m).count);
+        expect(positions[i].getFreq(m).rowCount, resAllDf1[i].getFreq(m).rowCount);
     }
   });
 
@@ -104,7 +104,7 @@ ATC-G-TTGC--
     for (let i = 0; i < positions.length; i++) {
       expect(positions[i].name, resAllDf1[i].name);
       for (const m of positions[i].getMonomers())
-        expect(positions[i].getFreq(m).count, resAllDf1[i].getFreq(m).count);
+        expect(positions[i].getFreq(m).rowCount, resAllDf1[i].getFreq(m).rowCount);
     }
   });
 
@@ -204,7 +204,7 @@ function expectPositionInfo(actualPos: PI, expectedPos: PI): void {
   expectArray(actualPos.getMonomers(), expectedPos.getMonomers());
   for (const key of actualPos.getMonomers()) {
     //
-    expect(actualPos.getFreq(key).count, expectedPos.getFreq(key).count);
+    expect(actualPos.getFreq(key).rowCount, expectedPos.getFreq(key).rowCount);
   }
 }
 

package/src/utils/agg.ts

@@ -0,0 +1,29 @@
+import * as grok from 'datagrok-api/grok';
+import * as ui from 'datagrok-api/ui';
+import * as DG from 'datagrok-api/dg';
+
+export type AggValueListType = (number | null)[] | Float32Array | Int32Array;
+export type AggFunc = (valueList: AggValueListType) => number | null;
+
+export function getAgg(agg: DG.AggregationType): AggFunc {
+  let res: AggFunc;
+
+  function buildCol(valueList: AggValueListType): DG.Column<number> {
+    let resCol: DG.Column<number>;
+    const resColName = `agg`;
+    if (valueList instanceof Float32Array)
+      resCol = DG.Column.fromFloat32Array(resColName, valueList as Float32Array);
+    else if (valueList instanceof Int32Array)
+      resCol = DG.Column.fromInt32Array(resColName, valueList as Int32Array);
+    else
+      resCol = DG.Column.fromList(DG.COLUMN_TYPE.FLOAT, resColName, valueList as (number | null)[]);
+
+    return resCol;
+  }
+
+  return (valueList: AggValueListType): number | null => {
+    const aggCol = buildCol(valueList);
+    const res = aggCol.aggregate(agg);
+    return res;
+  };
+}

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

@@ -0,0 +1,16 @@
+export const enum HELM_WRAPPER {
+  LEFT = 'PEPTIDE1{',
+  RIGHT = '}$$$$',
+}
+export const ALL_MONOMERS = '<All>';
+
+export const enum TRANSFORMATION_TYPE {
+  CYCLIZATION = 'Cyclization',
+}
+
+export const enum CYCLIZATION_TYPE {
+  NO = 'N-O',
+  NCys = 'N-Cys',
+  R3 = 'R3-R3',
+}
+

package/src/utils/{enumerator-tools.ts → poly-tool/enumerator-tools.ts}

@@ -3,51 +3,15 @@ import * as grok from 'datagrok-api/grok';
 import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
 
-import {NOTATION, ALIGNMENT, ALPHABET} from '@datagrok-libraries/bio/src/utils/macromolecule';
+import {NOTATION} from '@datagrok-libraries/bio/src/utils/macromolecule';
 import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
 import {HELM_POLYMER_TYPE} from '@datagrok-libraries/bio/src/utils/const';
-import {MonomerLibHelper} from '../utils/monomer-lib';
-import {_package} from '../package';
+import {MonomerLibHelper} from '../../utils/monomer-lib';
+import {_package} from '../../package';
+import {addCommonTags} from './utils';
 import * as rxjs from 'rxjs';
-
-const LEFT_HELM_WRAPPER = 'PEPTIDE1{';
-const RIGHT_HELM_WRAPPER = '}$$$$';
-const ALL_MONOMERS = '<All>';
-
-type MetaData = {
-  leftTerminal: string,
-  rightTerminal: string,
-  transformationType: TRANSFORMATION_TYPE,
-  cyclizationType: CYCLIZATION_TYPE,
-}
-
-type ConnectionData = {
-  monomerPosition: number,
-  attachmentPoint: number,
-}
-
-const enum TRANSFORMATION_TYPE {
-  CYCLIZATION = 'Cyclization',
-}
-
-const enum CYCLIZATION_TYPE {
-  NO = 'N-O',
-  NCys = 'N-Cys',
-  R3 = 'R3-R3',
-}
-
-function addCommonTags(col: DG.Column):void {
-  col.setTag('quality', DG.SEMTYPE.MACROMOLECULE);
-  col.setTag('aligned', ALIGNMENT.SEQ);
-  col.setTag('alphabet', ALPHABET.PT);
-}
-
-export function _setPeptideColumn(col: DG.Column): void {
-  addCommonTags(col);
-  col.setTag('units', NOTATION.SEPARATOR);
-  col.setTag('separator', '-');
-  // col.setTag('cell.renderer', 'sequence');
-}
+import {HELM_WRAPPER, ALL_MONOMERS, CYCLIZATION_TYPE, TRANSFORMATION_TYPE} from './const';
+import {MetaData, ConnectionData} from './types';
 
 abstract class TransformationBase {
   constructor(helmColumn: DG.Column<string>, meta: MetaData) {
@@ -80,11 +44,11 @@ class TransformationNCys extends TransformationBase {
   }
 
   protected hasTerminals(helm: string): boolean {
-    if (! helm.includes(this.rightTerminal + RIGHT_HELM_WRAPPER))
+    if (! helm.includes(this.rightTerminal + HELM_WRAPPER.RIGHT))
       return false;
     if (this.leftTerminal === ALL_MONOMERS)
       return true;
-    return helm.includes(LEFT_HELM_WRAPPER + this.leftTerminal);
+    return helm.includes(HELM_WRAPPER.LEFT + this.leftTerminal);
   }
 
   protected getLinkedPositions(helm: string): [number, number] {
@@ -107,8 +71,8 @@ class TransformationNO extends TransformationBase {
   protected hasTerminals(helm: string): boolean {
     if (this.leftTerminal === ALL_MONOMERS || this.rightTerminal === ALL_MONOMERS)
       return true;
-    return helm.includes(LEFT_HELM_WRAPPER + this.leftTerminal) &&
-      helm.includes(this.rightTerminal + RIGHT_HELM_WRAPPER);
+    return helm.includes(HELM_WRAPPER.LEFT + this.leftTerminal) &&
+      helm.includes(this.rightTerminal + HELM_WRAPPER.RIGHT);
   }
 
   protected getLinkedPositions(helm: string): [number, number] {
@@ -136,7 +100,7 @@ class TransformationR3 extends TransformationBase {
   }
 
   protected getLinkedPositions(helm: string): [number, number] {
-    const seq = helm.replace(LEFT_HELM_WRAPPER, '').replace(RIGHT_HELM_WRAPPER, '');
+    const seq = helm.replace(HELM_WRAPPER.LEFT, '').replace(HELM_WRAPPER.RIGHT, '');
     const monomers = seq.split('.');
     const start = monomers.findIndex((el) => el === this.leftTerminal);
     const end = monomers.findIndex((el, idx) => el === this.rightTerminal && idx > start);
@@ -163,12 +127,12 @@ class PolymerTransformation {
 }
 
 function getNumberOfMonomers(helm: string): number {
-  const seq = helm.replace(LEFT_HELM_WRAPPER, '').replace(RIGHT_HELM_WRAPPER, '');
+  const seq = helm.replace(HELM_WRAPPER.LEFT, '').replace(HELM_WRAPPER.RIGHT, '');
   return seq.split('.').length;
 }
 
 function getHelmCycle(helm: string, source: ConnectionData, target: ConnectionData): string {
-  return helm.replace(RIGHT_HELM_WRAPPER,
+  return helm.replace(HELM_WRAPPER.RIGHT,
     `}$PEPTIDE1,PEPTIDE1,${
       source.monomerPosition
     }:R${
@@ -200,7 +164,7 @@ async function addTransformedColumn(
   await grok.data.detectSemanticTypes(df);
 }
 
-export function _getEnumeratorWidget(molColumn: DG.Column): DG.Widget {
+export function getPolyToolDialog(): DG.Dialog {
   function getMonomerList(cyclizationType: CYCLIZATION_TYPE): string[] {
     if (cyclizationType === cyclizationTypes[0]) {
       return [ALL_MONOMERS].concat(
@@ -280,16 +244,34 @@ export function _getEnumeratorWidget(molColumn: DG.Column): DG.Widget {
 
   updateMeta();
 
-  const btn = ui.bigButton('Run', async () =>
-    addTransformedColumn(molColumn, meta)
+  const targetColumns = grok.shell.t.columns.bySemTypeAll(DG.SEMTYPE.MACROMOLECULE);
+  if (!targetColumns)
+    throw new Error('No dataframe with maceomolecule columns open');
+
+
+  const targetColumnInput = ui.columnInput(
+    'Column', grok.shell.t, targetColumns[0], null,
+    {filter: (col: DG.Column) => col.semType === DG.SEMTYPE.MACROMOLECULE}
   );
 
   const div = ui.div([
+    targetColumnInput,
     transformationChoice,
     cyclizationTypeChoice,
     terminalControls,
-    btn
   ]);
 
-  return new DG.Widget(div);
+  const dialog = ui.dialog('Poly Tool')
+    .add(div)
+    .onOK(async () => {
+      const molCol = targetColumnInput.value;
+      if (!molCol) {
+        grok.shell.warning('No marcomolecule column chosen!');
+        return;
+      }
+      addTransformedColumn(molCol!, meta);
+    }
+    );
+
+  return dialog;
 }

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

@@ -0,0 +1,14 @@
+import {TRANSFORMATION_TYPE, CYCLIZATION_TYPE} from './const';
+
+export type MetaData = {
+  leftTerminal: string,
+  rightTerminal: string,
+  transformationType: TRANSFORMATION_TYPE,
+  cyclizationType: CYCLIZATION_TYPE,
+}
+
+export type ConnectionData = {
+  monomerPosition: number,
+  attachmentPoint: number,
+}
+

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

@@ -0,0 +1,20 @@
+/* Do not change these import lines to match external modules in webpack configuration */
+import * as grok from 'datagrok-api/grok';
+import * as ui from 'datagrok-api/ui';
+import * as DG from 'datagrok-api/dg';
+
+import {NOTATION, ALIGNMENT, ALPHABET} from '@datagrok-libraries/bio/src/utils/macromolecule';
+
+export function addCommonTags(col: DG.Column):void {
+  col.setTag('quality', DG.SEMTYPE.MACROMOLECULE);
+  col.setTag('aligned', ALIGNMENT.SEQ);
+  col.setTag('alphabet', ALPHABET.PT);
+}
+
+export function _setPeptideColumn(col: DG.Column): void {
+  addCommonTags(col);
+  col.setTag('units', NOTATION.SEPARATOR);
+  col.setTag('separator', '-');
+  // col.setTag('cell.renderer', 'sequence');
+}
+