@datagrok/bio 2.18.2 → 2.18.4

package/package.json

@@ -5,7 +5,7 @@
     "name": "Leonid Stolbov",
     "email": "lstolbov@datagrok.ai"
   },
-  "version": "2.18.2",
+  "version": "2.18.4",
   "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",
@@ -44,7 +44,7 @@
   ],
   "dependencies": {
     "@biowasm/aioli": "^3.1.0",
-    "@datagrok-libraries/bio": "^5.48.1",
+    "@datagrok-libraries/bio": "^5.49.1",
     "@datagrok-libraries/chem-meta": "^1.2.7",
     "@datagrok-libraries/math": "^1.2.4",
     "@datagrok-libraries/ml": "^6.7.6",

package/src/analysis/sequence-search-base-viewer.ts

@@ -70,7 +70,7 @@ export class SequenceSearchBaseViewer extends DG.JsViewer {
     this.render();
   }
 
-  /** For tests */ public computeRequested: boolean;
+  /** For tests */ public computeRequested: boolean = false;
   public renderPromise: Promise<void> = Promise.resolve();
 
   protected render(computeData = true): void {

package/src/package.ts

@@ -979,7 +979,8 @@ export async function manageLibrariesApp(): Promise<DG.View> {
 export async function manageLibrariesAppTreeBrowser(treeNode: DG.TreeViewGroup, browseView: DG.BrowseView) {
   const libraries = (await (await MonomerLibManager.getInstance()).getFileManager()).getValidLibraryPaths();
   libraries.forEach((libName) => {
-    const libNode = treeNode.item(libName);
+    const nodeName = libName.endsWith('.json') ? libName.substring(0, libName.length - 5) : libName;
+    const libNode = treeNode.item(nodeName);
     // eslint-disable-next-line rxjs/no-ignored-subscription, rxjs/no-async-subscribe
     libNode.onSelected.subscribe(async () => {
       const monomerManager = await MonomerManager.getNewInstance();

package/src/tests/seq-handler-get-region-tests.ts

@@ -1,3 +1,4 @@
+/* eslint-disable max-lines-per-function */
 import * as grok from 'datagrok-api/grok';
 import * as DG from 'datagrok-api/dg';
 
@@ -68,7 +69,7 @@ PEPTIDE1{N.T.[dE].[Thr_PO3H2]}$$$$
 PEPTIDE1{[Cys_SEt].T.[dK].[Thr_PO3H2]}$$$$
 PEPTIDE1{[Cys_SEt].T.*.*}$$$$`,
       units: NOTATION.HELM,
-      alphabet: null,
+      alphabet: ALPHABET.UN,
 
       positionNames: {tag: null, start: '4', end: '7'}
     }

package/src/utils/monomer-lib/monomer-manager/duplicate-monomer-manager.ts

@@ -97,6 +97,8 @@ export class DuplicateMonomerManager {
       DuplicateMonomerManager._instance = new DuplicateMonomerManager();
       await DuplicateMonomerManager._instance.refresh();
       const libManager = await MonomerLibManager.getInstance();
+      // reason: subscription happens only once, and is needed throught the lifetime of the app
+      // eslint-disable-next-line rxjs/no-async-subscribe, rxjs/no-ignored-subscription
       libManager.getMonomerLib().onChanged.subscribe(async () => await DuplicateMonomerManager._instance.refresh());
     }
     DuplicateMonomerManager._instance.refresh();

package/src/utils/monomer-lib/monomer-manager/monomer-manager.ts

@@ -1028,6 +1028,7 @@ function getCorrectedMolBlock(molBlock: string) {
   // 2. RGP field is present in the correct format
   // 3. R group labels are written as R# and not just R
   // 4. there is no ISO field in the molblock. if there is, it needs to be substituted with RGP field and thats it.
+  // 5. make sure that R groups have no metadata in the atomblocks
 
   const lines = molBlock.split('\n');
 
@@ -1055,7 +1056,7 @@ function getCorrectedMolBlock(molBlock: string) {
       rgroupLineNumbers[atomI - molStartIdx] = rgroupNum;
   }
 
-  const rgroupLineNums = Object.values(rgroupLineNumbers);
+  const rgroupLineNums = Object.keys(rgroupLineNumbers);
   // find and possibly add rgp field
 
   const rgpLineIdx = lines.findIndex((line) => line.startsWith('M') && line.includes('RGP'));
@@ -1066,6 +1067,23 @@ function getCorrectedMolBlock(molBlock: string) {
     const mEndIdx = lines.findIndex((line) => line.startsWith('M') && line.includes('END'));
     lines.splice(mEndIdx, 0, rgpLine);
   }
+
+  //make sure that R# lines do not have any metadata that can be interpreted as isotopes or anything else
+  //for example, following line could be interpreted as isotope with mass 2 in some cases
+  //"    3.9970    0.3462    0.0000 R#  0  0  0  0  0  1  0  0  0  0  2  0"
+  const rGroupActualLines = rgroupLineNums.filter((rLine) => !!Number.parseInt(rLine)).map((atomLine) => Number.parseInt(atomLine) + molStartIdx);
+  rGroupActualLines.forEach((lineIdx) => {
+    const splitLine = lines[lineIdx].split(' ');
+    const rIdx = splitLine.findIndex((s) => s === 'R#');
+    if (rIdx === -1)
+      return;
+    for (let i = rIdx + 1; i < splitLine.length; i++) {
+      if (!!splitLine[i] && splitLine[i].length == 1 && (Number.parseInt(splitLine[i]) ?? 0) > 0)
+        splitLine[i] = '0';
+    }
+    lines[lineIdx] = splitLine.join(' ');
+  });
+
   return lines.join('\n');
 }
 
@@ -1087,12 +1105,24 @@ function monomerFromDfRow(dfRow: DG.Row): Monomer {
     if (typeof metaJSON[key] === 'object')
       metaJSON[key] = JSON.stringify(metaJSON[key]);
   }
+  const smiles = dfRow.get(MONOMER_DF_COLUMN_NAMES.MONOMER);
+  if (!smiles)
+    throw new Error('Monomer SMILES is empty');
+  let molfile = '';
+
+  try {
+    molfile = grok.chem.convert(smiles, DG.chem.Notation.Smiles, DG.chem.Notation.MolBlock);
+    molfile = getCorrectedMolBlock(molfile);
+  } catch (e) {
+    grok.shell.error(`Error converting SMILES to molfile, \n ${smiles}`);
+    console.error(e);
+  }
 
   return {
     symbol: dfRow.get(MONOMER_DF_COLUMN_NAMES.SYMBOL),
     name: dfRow.get(MONOMER_DF_COLUMN_NAMES.NAME),
-    molfile: '',
-    smiles: dfRow.get(MONOMER_DF_COLUMN_NAMES.MONOMER),
+    molfile: molfile,
+    smiles: smiles,
     polymerType: dfRow.get(MONOMER_DF_COLUMN_NAMES.POLYMER_TYPE),
     monomerType: dfRow.get(MONOMER_DF_COLUMN_NAMES.MONOMER_TYPE),
     naturalAnalog: dfRow.get(MONOMER_DF_COLUMN_NAMES.NATURAL_ANALOG),

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

@@ -1,3 +1,5 @@
+/* eslint-disable max-lines */
+/* eslint-disable @typescript-eslint/no-unused-vars */
 import * as DG from 'datagrok-api/dg';
 
 import wu from 'wu';
@@ -5,7 +7,7 @@ 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, ISeqSplitted, SeqColStats, SplitterFunc,} from '@datagrok-libraries/bio/src/utils/macromolecule/types';
-import {detectAlphabet, splitterAsFastaSimple, StringListSeqSplitted} from '@datagrok-libraries/bio/src/utils/macromolecule/utils';
+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';
@@ -123,6 +125,12 @@ export class SeqHandler implements ISeqHandler {
         uh.column.setTag(TAGS.alphabetSize, alphabetSize.toString());
         uh.column.setTag(TAGS.alphabetIsMultichar, alphabetIsMultichar ? 'true' : 'false');
       }
+    } else if (units === NOTATION.HELM) {
+      let alphabet = uh.column.getTag(TAGS.alphabet);
+      if (alphabet === null) {
+        alphabet = detectHelmAlphabet(uh.stats.freq, candidateAlphabets, uh.defaultGapOriginal);
+        uh.column.setTag(TAGS.alphabet, alphabet);
+      }
     }
   }
 
@@ -539,6 +547,7 @@ export class SeqHandler implements ISeqHandler {
     // convert the peptides list to a set for faster lookup
     const peptidesSet = new Set(peptides);
     // get splitter for given separator and check if all monomers are in the lib
+    // eslint-disable-next-line @typescript-eslint/no-unused-vars
     const splitterFunc = getSplitterWithSeparator(this.separator!);
     // iterate over the columns, split them and check if all monomers are in the lib
     //TODO maybe add missing threshold so that if there are not too many missing monomers

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

@@ -87,7 +87,7 @@ export class SeqHelper implements ISeqHelper {
 
     //#endregion From HelmToMolfileConverter
 
-    const molHlList = molfilesV3K.map((item: MolfileWithMap) => getMolHighlight(item.monomers.values(), monomerLib));
+    //const molHlList = molfilesV3K.map((item: MolfileWithMap) => getMolHighlight(item.monomers.values(), monomerLib));
 
     const molCol = DG.Column.fromStrings(molColName, molList);
     molCol.semType = DG.SEMTYPE.MOLECULE;

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

@@ -26,7 +26,9 @@ export function getCompositionAnalysisWidget(
   const rowIdx = val.cell.rowIndex;
   const seqSS = sh.getSplitted(rowIdx);
   wu.count(0).take(seqSS.length).filter((posIdx) => !seqSS.isGap(posIdx)).forEach((posIdx) => {
-    const cm = seqSS.getCanonical(posIdx);
+    let cm = seqSS.getCanonical(posIdx);
+    if (biotype === HelmTypes.NUCLEOTIDE && sh.isHelm() && cm[1] === '(' && cm[cm.length - 2] === ')')
+      cm = cm.substring(2, cm.length - 2);
     const count = counts[cm] || 0;
     counts[cm] = count + 1;
   });