@datagrok/peptides 1.23.13 → 1.23.14

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@datagrok/peptides",
   "friendlyName": "Peptides",
-  "version": "1.23.13",
+  "version": "1.23.14",
   "author": {
     "name": "Davit Rizhinashvili",
     "email": "drizhinashvili@datagrok.ai"
@@ -19,9 +19,9 @@
     "@datagrok-libraries/statistics": "^1.2.12",
     "@datagrok-libraries/tutorials": "^1.6.1",
     "@datagrok-libraries/utils": "^4.5.7",
-    "datagrok-api": "^1.23.0",
     "@webgpu/types": "^0.1.40",
     "cash-dom": "^8.1.5",
+    "datagrok-api": "^1.23.0",
     "file-loader": "^6.2.0",
     "rxjs": "^6.5.5",
     "uuid": "^10.0.0",
@@ -30,16 +30,17 @@
   "devDependencies": {
     "@datagrok-libraries/helm-web-editor": "^1.1.7",
     "@datagrok-libraries/js-draw-lite": "^0.0.5",
-    "@datagrok/eda": "^1.3.1",
     "@datagrok/bio": "^2.21.11",
     "@datagrok/chem": "^1.13.0",
     "@datagrok/dendrogram": "^1.2.33",
+    "@datagrok/eda": "^1.3.1",
     "@datagrok/helm": "^2.7.0",
     "@types/uuid": "^10.0.0",
     "@types/wu": "^2.1.44",
     "@typescript-eslint/eslint-plugin": "^8.8.1",
     "@typescript-eslint/parser": "^8.8.1",
     "css-loader": "^7.1.2",
+    "datagrok-tools": "^4.14.20",
     "eslint": "^8.57.1",
     "eslint-config-google": "^0.14.0",
     "style-loader": "^4.0.0",
@@ -59,7 +60,7 @@
     "debug-peptides": "grok publish",
     "release-peptides": "grok publish --release",
     "build-peptides": "webpack",
-    "build": "webpack",
+    "build": "grok api && grok check --soft && webpack",
     "debug-peptides-dev": "grok publish dev",
     "release-peptides-dev": "grok publish dev --release",
     "debug-peptides-public": "grok publish public",

package/src/package-api.ts

@@ -0,0 +1,77 @@
+/**
+This file is auto-generated by the grok api command.
+If you notice any changes, please push them to the repository.
+Do not edit this file manually.
+*/
+import * as grok from 'datagrok-api/grok';
+import * as DG from 'datagrok-api/dg';
+
+
+export namespace scripts {
+  export async function smiTo3D(smiles: string ): Promise<string> {
+    return await grok.functions.call('Peptides:SmiTo3D', { smiles });
+  }
+}
+
+export namespace funcs {
+  export async function initPeptides(): Promise<void> {
+    return await grok.functions.call('Peptides:InitPeptides', {});
+  }
+
+  export async function peptides(): Promise<DG.View> {
+    return await grok.functions.call('Peptides:Peptides', {});
+  }
+
+  export async function peptidesDialog(): Promise<void> {
+    return await grok.functions.call('Peptides:PeptidesDialog', {});
+  }
+
+  export async function testInitFunctionPeptides(v: any ): Promise<void> {
+    return await grok.functions.call('Peptides:TestInitFunctionPeptides', { v });
+  }
+
+  export async function peptidesPanel(col: DG.Column ): Promise<any> {
+    return await grok.functions.call('Peptides:PeptidesPanel', { col });
+  }
+
+  /**
+  Peptides Sequence Variability Map Viewer
+  */
+  export async function monomerPosition(): Promise<any> {
+    return await grok.functions.call('Peptides:MonomerPosition', {});
+  }
+
+  /**
+  Peptides Most Potent Residues Viewer
+  */
+  export async function mostPotentResidues(): Promise<any> {
+    return await grok.functions.call('Peptides:MostPotentResidues', {});
+  }
+
+  export async function logoSummaryTable(): Promise<any> {
+    return await grok.functions.call('Peptides:LogoSummaryTable', {});
+  }
+
+  export async function sequencePositionStatistics(): Promise<any> {
+    return await grok.functions.call('Peptides:SequencePositionStatistics', {});
+  }
+
+  export async function clusterMaxActivity(): Promise<any> {
+    return await grok.functions.call('Peptides:ClusterMaxActivity', {});
+  }
+
+  export async function manualAlignment(_monomer: string ): Promise<any> {
+    return await grok.functions.call('Peptides:ManualAlignment', { _monomer });
+  }
+
+  /**
+  Peptide SAR Analysis demo on peptide sequences in FASTA format
+  */
+  export async function macromoleculeSarFastaDemo(): Promise<void> {
+    return await grok.functions.call('Peptides:MacromoleculeSarFastaDemo', {});
+  }
+
+  export async function lstPiechartCellRenderer(): Promise<any> {
+    return await grok.functions.call('Peptides:LstPiechartCellRenderer', {});
+  }
+}

package/src/viewers/logo-summary.ts

@@ -55,6 +55,9 @@ export const enum LST_PROPERTIES {
   AGGREGATION = 'aggregation',
   ACTIVITY_SCALING = 'activityScaling',
   ACTIVITY = 'activity',
+
+  WEB_LOGO_AGGREGATION_COLUMN_NAME = 'webLogoAggregationColumnName',
+  WEB_LOGO_AGGREGATION_TYPE = 'webLogoAggregationType',
 }
 
 enum LST_CATEGORIES {
@@ -86,6 +89,11 @@ export class LogoSummaryTable extends DG.JsViewer implements ILogoSummaryTable {
   activityScaling: SCALING_METHODS;
   _scaledActivityColumn: DG.Column | null = null;
 
+  webLogoAggregationColumnName: string | null;
+  webLogoAggregationType: DG.AggregationType;
+
+  private _webLogoCacheGeneration: number = 0;
+
   /** Creates LogoSummaryTable properties. */
   constructor() {
     super();
@@ -122,6 +130,25 @@ export class LogoSummaryTable extends DG.JsViewer implements ILogoSummaryTable {
         category: LST_CATEGORIES.STYLE,
       });
 
+    const aggExcludeList = [DG.AGG.KEY, DG.AGG.PIVOT, DG.AGG.MISSING_VALUE_COUNT, DG.AGG.SKEW, DG.AGG.KURT,
+      DG.AGG.SELECTED_ROWS_COUNT];
+    const aggChoices = Object.values(DG.AGG).filter((agg) => !aggExcludeList.includes(agg));
+    this.webLogoAggregationType = this.string(LST_PROPERTIES.WEB_LOGO_AGGREGATION_TYPE, DG.AGG.TOTAL_COUNT, {
+      category: LST_CATEGORIES.STYLE,
+      choices: aggChoices,
+      description: 'Aggregation method for WebLogo position heights',
+    }) as DG.AggregationType;
+
+
+    this.webLogoAggregationColumnName = this.column(LST_PROPERTIES.WEB_LOGO_AGGREGATION_COLUMN_NAME, {
+      defaultValue: null,
+      category: LST_CATEGORIES.STYLE,
+      nullable: true,
+      columnTypeFilter: DG.TYPE.NUMERICAL,
+      description: `Column with values to aggregate for WebLogo position heights.
+    Used if aggregation type is not '${DG.AGG.TOTAL_COUNT}'.`,
+    });
+
     this.columns = this.columnList(LST_PROPERTIES.COLUMNS, [], {category: LST_CATEGORIES.AGGREGATION});
     this.aggregation = this.string(LST_PROPERTIES.AGGREGATION, DG.AGG.AVG,
       {
@@ -251,9 +278,7 @@ export class LogoSummaryTable extends DG.JsViewer implements ILogoSummaryTable {
    * @return - iterable over custom clusters columns.
    */
   get customClusters(): wu.WuIterable<DG.Column<boolean>> {
-    const query: {
-      [key: string]: string
-    } = {};
+    const query: {[key: string]: string} = {};
     query[C.TAGS.CUSTOM_CLUSTER] = '1';
     return wu(this.dataFrame.columns.byTags(query));
   }
@@ -293,10 +318,13 @@ export class LogoSummaryTable extends DG.JsViewer implements ILogoSummaryTable {
   onTableAttached(): void {
     super.onTableAttached();
     if (isApplicableDataframe(this.dataFrame)) {
+      const activityColName = wu(this.dataFrame.columns.numerical).next().value.name;
       this.getProperty(`${LST_PROPERTIES.SEQUENCE}${COLUMN_NAME}`)
         ?.set(this, this.dataFrame.columns.bySemType(DG.SEMTYPE.MACROMOLECULE)!.name);
       this.getProperty(`${LST_PROPERTIES.ACTIVITY}${COLUMN_NAME}`)
-        ?.set(this, wu(this.dataFrame.columns.numerical).next().value.name);
+        ?.set(this, activityColName);
+      this.getProperty(`${LST_PROPERTIES.WEB_LOGO_AGGREGATION_COLUMN_NAME}`)?.set(this, activityColName);
+
       this.getProperty(`${LST_PROPERTIES.CLUSTERS}${COLUMN_NAME}`)
         ?.set(this, wu(this.dataFrame.columns.categorical).next().value.name);
     } else {
@@ -376,7 +404,11 @@ export class LogoSummaryTable extends DG.JsViewer implements ILogoSummaryTable {
       doRender = true;
       break;
     case `${LST_PROPERTIES.ACTIVITY}${COLUMN_NAME}`:
+      this.webLogoAggregationColumnName = this.activityColumnName;
     case LST_PROPERTIES.ACTIVITY_SCALING:
+    case `${LST_PROPERTIES.WEB_LOGO_AGGREGATION_COLUMN_NAME}${COLUMN_NAME}`:
+    case LST_PROPERTIES.WEB_LOGO_AGGREGATION_TYPE:
+      this._webLogoCacheGeneration++; // Increment to invalidate cache
       this._scaledActivityColumn = null;
       this._viewerGrid = null;
       this._clusterStats = null;
@@ -402,9 +434,7 @@ export class LogoSummaryTable extends DG.JsViewer implements ILogoSummaryTable {
    * @param options.notify - flag that indicates if bitset changed event should fire.
    * @return - cluster selection.
    */
-  initClusterSelection(options: {
-    notify?: boolean
-  } = {}): type.Selection {
+  initClusterSelection(options: {notify?: boolean} = {}): type.Selection {
     options.notify ??= true;
 
     const newClusterSelection = {} as type.Selection;
@@ -438,7 +468,13 @@ export class LogoSummaryTable extends DG.JsViewer implements ILogoSummaryTable {
    */
   getNeededDfClone(): DG.DataFrame {
     // gather all needed columns. for string columns we need to remove 'dist(' and ')' from the name
-    const neededCols = [this.clustersColumnName, this.sequenceColumnName, this.activityColumnName, ...(this.getTotalViewerAggColumns() ?? []).map(([cn, _]) => cn), ...(this.getStringAggregatedColumns() ?? []).map((cn) => cn.substring(5, cn.length - 1))];
+    const neededCols = [this.clustersColumnName, this.sequenceColumnName, this.activityColumnName,
+      ...(this.getTotalViewerAggColumns() ?? []).map(([cn, _]) => cn),
+      ...(this.getStringAggregatedColumns() ?? []).map((cn) => cn.substring(5, cn.length - 1))];
+    if (this.webLogoAggregationColumnName)
+      neededCols.push(this.webLogoAggregationColumnName);
+
+
     const colsSet = Array.from(new Set(neededCols)).filter((colName) => this.dataFrame.columns.contains(colName));
     return this.dataFrame.clone(this.dataFrame.filter, colsSet);
   }
@@ -459,9 +495,7 @@ export class LogoSummaryTable extends DG.JsViewer implements ILogoSummaryTable {
     const filteredDfClustColData = filteredDfClustCol.getRawData();
     const filteredDfClustColCat = filteredDfClustCol.categories;
 
-    const query: {
-      [key: string]: string
-    } = {};
+    const query: {[key: string]: string} = {};
     query[C.TAGS.CUSTOM_CLUSTER] = '1';
     const customClustColList: DG.Column<boolean>[] = wu(filteredDfCols.byTags(query))
       .filter((c) => c.max > 0).toArray();
@@ -614,8 +648,8 @@ export class LogoSummaryTable extends DG.JsViewer implements ILogoSummaryTable {
     grid.columns.rowHeader!.visible = false;
     grid.props.rowHeight = 55;
 
-    const webLogoCache = new DG.LruCache<number, DG.Viewer & IWebLogoViewer>();
-    const webLogoPromiseCache = new Map<number, boolean>();// this map will keep the promises for weblogo creation
+    const webLogoCache = new DG.LruCache<string, DG.Viewer & IWebLogoViewer>();
+    const webLogoPromiseCache = new Map<string, boolean>(); // this map will keep promises for weblogo creation
 
     let invalidateTimeout: any = null;
 
@@ -655,14 +689,17 @@ export class LogoSummaryTable extends DG.JsViewer implements ILogoSummaryTable {
           CR.renderLogoSummaryCell(canvasContext, gridCell.cell.value, this.clusterSelection, bound);
           gridCellArgs.preventDefault();
         } else if (gridCell.tableColumn?.name === C.LST_COLUMN_NAMES.WEB_LOGO) {
+          const cacheKey = `${currentRowIdx}_${this.webLogoAggregationColumnName || 'count'}_${this.webLogoAggregationType}_${this._webLogoCacheGeneration}`;
+          const viewer = webLogoCache.get(cacheKey);
+
           // if current weblogo is being created, prevent the creation of another one
-          if (webLogoPromiseCache.get(currentRowIdx) === true) {
+
+          if (webLogoPromiseCache.get(cacheKey) === true) {
             gridCellArgs.preventDefault();
             return;
           }
           const positionWidth = Math.floor((gridCell.bounds.width - 2 - (4 * (maxSequenceLen - 1))) / maxSequenceLen);
 
-          const viewer = webLogoCache.get(currentRowIdx);
           if (viewer !== undefined) {
             const viewerProps = viewer.getProperties();
 
@@ -680,19 +717,30 @@ export class LogoSummaryTable extends DG.JsViewer implements ILogoSummaryTable {
             gridCell.element = viewer.root;
             gridCellArgs.preventDefault();
           } else {
-            const webLogoTable = this.createWebLogoDf(pepCol, clusterBitSet);
-            webLogoPromiseCache.set(currentRowIdx, true);
+            const columnsToInclude = [pepCol];
+            if (this.webLogoAggregationType !== DG.AGG.TOTAL_COUNT && this.webLogoAggregationColumnName) {
+              const aggCol = this.dataFrame.columns.byName(this.webLogoAggregationColumnName);
+              if (aggCol)
+                columnsToInclude.push(aggCol);
+            }
+            const webLogoTable = DG.DataFrame.fromColumns(columnsToInclude);
+            webLogoTable.filter.copyFrom(clusterBitSet);
+
+            webLogoPromiseCache.set(cacheKey, true);
             webLogoTable.plot
               .fromType('WebLogo', {
+                valueColumnName: this.webLogoAggregationColumnName,
+                valueAggrType: this.webLogoAggregationType,
                 positionHeight: this.webLogoMode,
                 horizontalAlignment: HorizontalAlignments.LEFT,
                 maxHeight: 1000,
                 minHeight: height,
                 positionWidth: positionWidth,
                 showPositionLabels: false,
-              }).then((v) => {
-                webLogoCache.set(currentRowIdx, v);
-                webLogoPromiseCache.delete(currentRowIdx);
+              })
+              .then((v) => {
+                webLogoCache.set(cacheKey, v);
+                webLogoPromiseCache.delete(cacheKey);
                 debouncedInvalidate();
               });
             gridCellArgs.preventDefault();
@@ -875,12 +923,8 @@ export class LogoSummaryTable extends DG.JsViewer implements ILogoSummaryTable {
     this.bitsets.push(currentSelection.clone());
 
     const newClusterName = this.dataFrame.columns.getUnusedName('New Cluster');
-    const aggregatedValues: {
-      [colName: string]: number
-    } = {};
-    const stringAggregatedValues: {
-      [colName: string]: string
-    } = {};
+    const aggregatedValues: {[colName: string]: number} = {};
+    const stringAggregatedValues: {[colName: string]: string} = {};
     const aggColsEntries = this.getTotalViewerAggColumns();
     const aggStringColNames = this.getStringAggregatedColumns();
     for (const [colName, aggFn] of aggColsEntries) {
@@ -1021,9 +1065,7 @@ export class LogoSummaryTable extends DG.JsViewer implements ILogoSummaryTable {
         filterDf: true,
         mask: mask,
       });
-    const resultMap: {
-      [key: string]: any
-    } = {...tableMap, ...aggregatedColMap};
+    const resultMap: {[key: string]: any} = {...tableMap, ...aggregatedColMap};
     const tooltip = getDistributionPanel(hist, resultMap);
 
     ui.tooltip.show(tooltip, x, y);
@@ -1032,10 +1074,9 @@ export class LogoSummaryTable extends DG.JsViewer implements ILogoSummaryTable {
   }
 
   /**
-   * Creates a dataframe for WebLogo viewer.
    * @param pepCol - column with peptides.
    * @param mask - bitset to filter dataframe with.
-   * @return - dataframe for WebLogo viewer.
+   * @deprecated The logic is now handled directly in createLogoSummaryTableGrid
    */
   createWebLogoDf(pepCol: DG.Column<string>, mask: DG.BitSet): DG.DataFrame {
     const newDf = DG.DataFrame.fromColumns([pepCol]);

package/src/widgets/peptides.ts

@@ -44,14 +44,8 @@ export function analyzePeptidesUI(df: DG.DataFrame, col?: DG.Column<string>): Di
       }));
       if (value.stats.missingValueCount !== 0)
         grok.shell.info('Sequences column contains missing values. They will be ignored during analysis');
-    }, filter: (col: DG.Column) => col.semType === DG.SEMTYPE.MACROMOLECULE});
+    }, filter: (col: DG.Column) => col.semType === DG.SEMTYPE.MACROMOLECULE, nullable: false});
     seqColInput.setTooltip('Macromolecule column in FASTA, HELM or separated format');
-  } else if (!(col.getTag(bioTAGS.aligned) === ALIGNMENT.SEQ_MSA) &&
-    col.getTag(DG.TAGS.UNITS) !== NOTATION.HELM) {
-    return {
-      host: ui.label('Peptides analysis only works with aligned sequences'),
-      callback: async (): Promise<boolean> => false,
-    };
   }
 
   let funcs = DG.Func.find({package: 'Bio', name: 'webLogoViewer'});
@@ -96,7 +90,7 @@ export function analyzePeptidesUI(df: DG.DataFrame, col?: DG.Column<string>): Di
     if (activityColumnChoice.value!.stats.missingValueCount !== 0)
       grok.shell.info('Activity column contains missing values. They will be ignored during analysis');
   };
-  const activityColumnChoice = ui.input.column('Activity', {table: df, value: defaultActivityColumn!,
+  const activityColumnChoice = ui.input.column('Activity', {table: df, value: defaultActivityColumn!, nullable: false,
     onValueChanged: activityScalingMethodState, filter: (col: DG.Column) => col.type === DG.TYPE.INT || col.type === DG.TYPE.FLOAT || col.type === DG.TYPE.QNUM});
   activityColumnChoice.setTooltip('Numerical activity column');
   const clustersColumnChoice = ui.input.column('Clusters', {table: df, onValueChanged: (value) => {
@@ -355,6 +349,15 @@ export async function startAnalysis(activityColumn: DG.Column<number>, peptidesC
     }
   }
 
+  const selectionGrid = model.df.plot.grid({
+    rowSource: DG.RowSet.Selected,
+    selectedRowsColor: DG.Color.fromHtml('#ffffff'),
+    title: 'Selection',
+  });
+
+  const logoViewerNode = (model?.findViewerNode(VIEWER_TYPE.LOGO_SUMMARY_TABLE));
+  if (logoViewerNode)
+    model.analysisView.dockManager.dock(selectionGrid, DG.DOCK_TYPE.DOWN, logoViewerNode, 'Selection', 0.4);
 
   progress.close();
   return model;