@datagrok/bio 2.23.2 → 2.25.0

package/src/utils/seq-helper/seq-handler.ts

@@ -6,11 +6,11 @@ import wu from 'wu';
 
 /* eslint-disable max-len */
 import {ALIGNMENT, ALPHABET, candidateAlphabets, getSplitterWithSeparator, NOTATION, positionSeparator, splitterAsFasta, splitterAsHelm, TAGS} from '@datagrok-libraries/bio/src/utils/macromolecule/index';
-import {INotationProvider, ISeqConnection, ISeqSplitted, SeqColStats, SplitterFunc,} from '@datagrok-libraries/bio/src/utils/macromolecule/types';
+import {CandidateType, INotationProvider, ISeqConnection, ISeqSplitted, SeqColStats, SplitterFunc,} from '@datagrok-libraries/bio/src/utils/macromolecule/types';
 import {detectAlphabet, detectHelmAlphabet, splitterAsFastaSimple, StringListSeqSplitted} from '@datagrok-libraries/bio/src/utils/macromolecule/utils';
 import {mmDistanceFunctions, MmDistanceFunctionsNames} from '@datagrok-libraries/ml/src/macromolecule-distance-functions';
 import {mmDistanceFunctionType} from '@datagrok-libraries/ml/src/macromolecule-distance-functions/types';
-import {getMonomerLibHelper, IMonomerLibHelper} from '@datagrok-libraries/bio/src/monomer-works/monomer-utils';
+import {getMonomerLibHelper, IMonomerLibHelper} from '@datagrok-libraries/bio/src/types/monomer-library';
 import {HELM_POLYMER_TYPE, HELM_WRAPPERS_REGEXP, PHOSPHATE_SYMBOL} from '@datagrok-libraries/bio/src/utils/const';
 import {GAP_SYMBOL, GapOriginals} from '@datagrok-libraries/bio/src/utils/macromolecule/consts';
 import {CellRendererBackBase, GridCellRendererTemp} from '@datagrok-libraries/bio/src/utils/cell-renderer-back-base';
@@ -132,7 +132,7 @@ export class SeqHandler implements ISeqHandler {
       for (const seq of values) {
         const mSeq = !!seq ? splitter(seq) : [];
 
-        if (firstLength === null)
+        if (firstLength == null)
           firstLength = mSeq.length;
         else if (mSeq.length !== firstLength)
           sameLength = false;
@@ -182,13 +182,13 @@ export class SeqHandler implements ISeqHandler {
         throw new Error('Alphabet is empty and not annotated.');
 
       let aligned = uh.column.getTag(TAGS.aligned);
-      if (aligned === null) {
+      if (aligned == null) {
         aligned = uh.stats.sameLength ? ALIGNMENT.SEQ_MSA : ALIGNMENT.SEQ;
         uh.column.setTag(TAGS.aligned, aligned);
       }
 
       let alphabet = uh.column.getTag(TAGS.alphabet);
-      if (alphabet === null) {
+      if (alphabet == null) {
         alphabet = detectAlphabet(uh.stats.freq, candidateAlphabets);
         uh.column.setTag(TAGS.alphabet, alphabet);
       }
@@ -200,8 +200,21 @@ export class SeqHandler implements ISeqHandler {
       }
     } else if (units === NOTATION.HELM) {
       let alphabet = uh.column.getTag(TAGS.alphabet);
-      if (alphabet === null) {
-        alphabet = detectHelmAlphabet(uh.stats.freq, candidateAlphabets, uh.defaultGapOriginal);
+      if (alphabet == null) {
+        // const cats = uh.column.categories;
+        // const splitter = uh.getSplitter();
+        // const samples = Array.from(new Set(
+        //   wu.count(0).take(Math.min(100, cats.length)).map((_) => Math.floor(Math.random() * cats.length)).toArray())
+        // ).map((catIndex) => cats[catIndex]).filter((s) => (s?.length ?? 0) > 0).map((s) => splitter(s));
+        // // splitted helm has info about polymer types
+        // const polymerTypes = new Set<HELM_POLYMER_TYPE>();
+        // for (const ss of samples) {
+        //   ss.graphInfo?.polymerTypes
+        // }
+        // increase the detection threshold for candidate alphabets
+        const modifiedCandidateAlphabets = candidateAlphabets.map((ca) => new CandidateType(ca.name, ca.alphabet, 0.9));
+
+        alphabet = detectHelmAlphabet(uh.stats.freq, modifiedCandidateAlphabets, uh.defaultGapOriginal);
         uh.column.setTag(TAGS.alphabet, alphabet);
       }
     }
@@ -219,7 +232,7 @@ export class SeqHandler implements ISeqHandler {
 
   public get separator(): string | undefined {
     const separator: string | undefined = this.column.getTag(TAGS.separator) ?? undefined;
-    if (this.notation === NOTATION.SEPARATOR && separator === undefined)
+    if (this.notation === NOTATION.SEPARATOR && separator == undefined)
       throw new Error(`Separator is mandatory  for column '${this.column.name}' of notation '${this.notation}'.`);
     return separator;
   }
@@ -314,7 +327,7 @@ export class SeqHandler implements ISeqHandler {
       const seq = this.column.get(rowIdx);
       return this.getSplitter(limit)(seq);
     } else {
-      if (this.column.version !== this.columnVersion || this._splitted === null) {
+      if (this.column.version !== this.columnVersion || this._splitted == null) {
         this.columnVersion = this.column.version;
         this._splitted = new Array<WeakRef<ISeqSplitted>>(this.column.length);
       }
@@ -395,7 +408,7 @@ export class SeqHandler implements ISeqHandler {
   }
 
   public get stats(): SeqColStats {
-    if (this._stats === null) {
+    if (this._stats == null) {
       const freq: { [m: string]: number } = {};
       let sameLength = true;
       let firstLength = null;
@@ -422,7 +435,7 @@ export class SeqHandler implements ISeqHandler {
 
   private _maxLength: number | null = null;
   public get maxLength(): number {
-    if (this._maxLength === null) {
+    if (this._maxLength == null) {
       this._maxLength = this.column.length === 0 ? 0 :
         wu.count(0).take(this.column.length).map((rowIdx) => this.getSplitted(rowIdx).length).reduce((a, b) => a > b ? a : b, 0);
     }
@@ -431,7 +444,7 @@ export class SeqHandler implements ISeqHandler {
 
   private _posList: string[] | null = null;
   public get posList(): string[] {
-    if (this._posList === null) {
+    if (this._posList == null) {
       const posListTxt = this.column.getTag(TAGS.positionNames);
       this._posList = posListTxt ? posListTxt.split(positionSeparator).map((p) => p.trim()) :
         wu.count(1).take(this.maxLength).map((pos) => pos.toString()).toArray();
@@ -606,7 +619,7 @@ export class SeqHandler implements ISeqHandler {
   }
 
   get splitter(): SplitterFunc {
-    if (this._splitter === null)
+    if (this._splitter == null)
       this._splitter = this.getSplitter();
     return this._splitter;
   }

package/src/utils/seq-helper/seq-helper.ts

@@ -6,12 +6,11 @@ import wu from 'wu';
 
 import {ISeqHelper, ToAtomicLevelRes} from '@datagrok-libraries/bio/src/utils/seq-helper';
 import {RDModule, RDMol} from '@datagrok-libraries/chem-meta/src/rdkit-api';
-import {IMonomerLibHelper} from '@datagrok-libraries/bio/src/monomer-works/monomer-utils';
 import {getHelmHelper, IHelmHelper} from '@datagrok-libraries/bio/src/helm/helm-helper';
 import {MolfileWithMap} from '@datagrok-libraries/bio/src/monomer-works/types';
 import {getMolColName} from '@datagrok-libraries/bio/src/monomer-works/utils';
 import {ChemTags} from '@datagrok-libraries/chem-meta/src/consts';
-import {IMonomerLibBase} from '@datagrok-libraries/bio/src/types/index';
+import {IMonomerLibBase, IMonomerLibHelper} from '@datagrok-libraries/bio/src/types/monomer-library';
 
 import {HelmToMolfileConverter} from '../helm-to-molfile/converter';
 import {ISeqHandler} from '@datagrok-libraries/bio/src/utils/macromolecule/seq-handler';

package/src/utils/sequence-to-mol.ts

@@ -3,7 +3,7 @@ import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
 
 import {_toAtomicLevel} from '@datagrok-libraries/bio/src/monomer-works/to-atomic-level';
-import {IMonomerLib} from '@datagrok-libraries/bio/src/types';
+import {IMonomerLib} from '@datagrok-libraries/bio/src/types/monomer-library';
 import {NOTATION} from '@datagrok-libraries/bio/src/utils/macromolecule';
 import {getSeqHelper, ISeqHelper, ToAtomicLevelRes} from '@datagrok-libraries/bio/src/utils/seq-helper';
 import {RDModule} from '@datagrok-libraries/chem-meta/src/rdkit-api';

package/src/utils/ui-utils.ts

@@ -3,7 +3,7 @@ import * as DG from 'datagrok-api/dg';
 
 export function getMacromoleculeColumns(): DG.Column<string>[] {
   const columns = grok.shell.t.columns.bySemTypeAll(DG.SEMTYPE.MACROMOLECULE);
-  if (columns === null) {
+  if (columns == null) {
     grok.shell.error('Current table does not contain macromolecules');
     return [];
   }

package/src/viewers/web-logo-viewer.ts

@@ -25,7 +25,7 @@ import {ISeqSplitted} from '@datagrok-libraries/bio/src/utils/macromolecule/type
 import {testEvent} from '@datagrok-libraries/utils/src/test';
 import {PromiseSyncer} from '@datagrok-libraries/bio/src/utils/syncer';
 import {GAP_SYMBOL} from '@datagrok-libraries/bio/src/utils/macromolecule/consts';
-import {IMonomerLibBase} from '@datagrok-libraries/bio/src/types/index';
+import {IMonomerLibBase} from '@datagrok-libraries/bio/src/types/monomer-library';
 import {HelmType} from '@datagrok-libraries/bio/src/helm/types';
 import {undefinedColor} from '@datagrok-libraries/bio/src/utils/cell-renderer-monomer-placer';
 
@@ -34,6 +34,7 @@ import {AggFunc, getAgg} from '../utils/agg';
 import {_package, PackageFunctions} from '../package';
 import {numbersWithinMaxDiff} from './utils';
 import {buildCompositionTable} from '@datagrok-libraries/bio/src/utils/composition-table';
+import {helmTypeToPolymerType} from '@datagrok-libraries/bio/src/monomer-works/monomer-works';
 
 declare global {
   interface HTMLCanvasElement {
@@ -212,14 +213,24 @@ export class PositionInfo {
   ) {
     for (const [monomer, pmInfo] of Object.entries(this._freqs)) {
       if (monomer !== GAP_SYMBOL) {
-        const monomerTxt = monomerToShort(monomer, maxMonomerLetters);
+        // to handle explicit smiles based monomers in monomer lib
+        let monomerDisplayValue = monomer;
+
         const b = pmInfo.bounds!;
         const left = b.left;
 
         let color: string = undefinedColor;
-        if (monomerLib)
-          color = monomerLib.getMonomerTextColor(biotype, monomer)!;
-
+        if (monomerLib) {
+          try {
+            color = monomerLib.getMonomerTextColor(biotype, monomer)!;
+            const m = monomerLib.getMonomer(helmTypeToPolymerType(biotype), monomer);
+            if (m && m.symbol !== monomer) // for explicit smiles based monomers
+              monomerDisplayValue = m.symbol;
+          } catch (e) {
+            errorToConsole(e);
+          }
+        }
+        const monomerTxt = monomerToShort(monomerDisplayValue, maxMonomerLetters);
         g.resetTransform();
         g.strokeStyle = 'lightgray';
         g.lineWidth = 1;
@@ -949,7 +960,7 @@ export class WebLogoViewer extends DG.JsViewer implements IWebLogoViewer {
       return [null, null, null];
 
     const monomer: string | undefined = pi.getMonomerAt(calculatedX, p.y);
-    if (monomer === undefined)
+    if (monomer == undefined)
       return [pi, null, null];
 
     return [pi, monomer, pi.getFreq(monomer)];
@@ -1262,7 +1273,7 @@ export class WebLogoViewer extends DG.JsViewer implements IWebLogoViewer {
       const [pi, monomer] = this.getMonomer(cursorP, dpr);
       const positionLabelHeight = this.showPositionLabels ? POSITION_LABELS_HEIGHT * dpr : 0;
 
-      if (pi !== null && monomer === null && 0 <= cursorP.y && cursorP.y <= positionLabelHeight) {
+      if (pi !== null && monomer == null && 0 <= cursorP.y && cursorP.y <= positionLabelHeight) {
         // Position tooltip
 
         const tooltipRows = [ui.divText(`Position ${pi.label}`)];
@@ -1373,8 +1384,8 @@ function renderPositionLabels(g: CanvasRenderingContext2D,
       const pos = positions[jPos];
       const tm = g.measureText(pos.name);
       const textHeight = tm.actualBoundingBoxDescent - tm.actualBoundingBoxAscent;
-      maxPosNameWidth = maxPosNameWidth === null ? tm.width : Math.max(maxPosNameWidth, tm.width);
-      maxPosNameHeight = maxPosNameHeight === null ? textHeight : Math.max(maxPosNameHeight, textHeight);
+      maxPosNameWidth = maxPosNameWidth == null ? tm.width : Math.max(maxPosNameWidth, tm.width);
+      maxPosNameHeight = maxPosNameHeight == null ? textHeight : Math.max(maxPosNameHeight, textHeight);
     }
     const hScale = maxPosNameWidth! < (positionWidth * dpr - 2) ? 1 : (positionWidth * dpr - 2) / maxPosNameWidth!;
 

package/src/widgets/composition-analysis-widget.ts

@@ -6,7 +6,7 @@ import wu from 'wu';
 
 import {TAGS as bioTAGS, ALPHABET} from '@datagrok-libraries/bio/src/utils/macromolecule';
 import {GAP_SYMBOL} from '@datagrok-libraries/bio/src/utils/macromolecule/consts';
-import {IMonomerLibBase} from '@datagrok-libraries/bio/src/types';
+import {IMonomerLibBase} from '@datagrok-libraries/bio/src/types/monomer-library';
 import {HelmType} from '@datagrok-libraries/bio/src/helm/types';
 import {HelmTypes, PolymerTypes} from '@datagrok-libraries/bio/src/helm/consts';
 

package/src/widgets/sequence-scrolling-widget.ts

@@ -10,11 +10,10 @@ import {ConservationTrack, MSAHeaderTrack, MSAScrollingHeader, WebLogoTrack} fro
 import {MonomerPlacer} from '@datagrok-libraries/bio/src/utils/cell-renderer-monomer-placer';
 import {ALPHABET, TAGS as bioTAGS} from '@datagrok-libraries/bio/src/utils/macromolecule';
 import {_package} from '../package';
-import {getMonomerLibHelper} from '@datagrok-libraries/bio/src/monomer-works/monomer-utils';
 import {ISeqHandler} from '@datagrok-libraries/bio/src/utils/macromolecule/seq-handler';
 import * as RxJs from 'rxjs';
 import {filter} from 'rxjs/operators';
-import {IMonomerLib} from '@datagrok-libraries/bio/src/types';
+import {IMonomerLib, getMonomerLibHelper} from '@datagrok-libraries/bio/src/types/monomer-library';
 import wu from 'wu';
 
 // ============================================================================