@datagrok/bio 2.15.0 → 2.15.2

package/package.json

@@ -5,7 +5,7 @@
     "name": "Aleksandr Tanas",
     "email": "atanas@datagrok.ai"
   },
-  "version": "2.15.0",
+  "version": "2.15.2",
   "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",
@@ -37,12 +37,12 @@
   ],
   "dependencies": {
     "@biowasm/aioli": "^3.1.0",
-    "@datagrok-libraries/bio": "^5.42.14",
+    "@datagrok-libraries/bio": "^5.43.0",
     "@datagrok-libraries/chem-meta": "^1.2.5",
     "@datagrok-libraries/math": "^1.2.0",
-    "@datagrok-libraries/ml": "^6.7.0",
+    "@datagrok-libraries/ml": "^6.7.1",
     "@datagrok-libraries/tutorials": "^1.4.0",
-    "@datagrok-libraries/utils": "^4.3.0",
+    "@datagrok-libraries/utils": "^4.3.3",
     "@webgpu/types": "^0.1.40",
     "ajv": "^8.12.0",
     "ajv-errors": "^3.0.0",
@@ -83,12 +83,12 @@
     "link-bio": "npm link @datagrok-libraries/bio",
     "link-ml": "npm link @datagrok-libraries/ml",
     "link-utils": "npm link @datagrok-libraries/utils",
-    "link-all": "npm link @datagrok-libraries/chem-meta datagrok-api @datagrok-libraries/utils @datagrok-libraries/math @datagrok-libraries/ml @datagrok-libraries/bio @datagrok-libraries/tutorials",
+    "link-all": "npm link @datagrok-libraries/chem-meta datagrok-api @datagrok-libraries/math @datagrok-libraries/utils @datagrok-libraries/ml @datagrok-libraries/bio @datagrok-libraries/tutorials",
     "debug-sequences1": "webpack && grok publish",
     "release-sequences1": "webpack && grok publish --release",
     "build-sequences1": "webpack",
     "build": "webpack",
-    "build-all": "npm --prefix ./../../libraries/chem-meta run build && npm --prefix ./../../js-api run build && npm --prefix ./../../libraries/utils run build && npm --prefix ./../../libraries/math run build && npm --prefix ./../../libraries/ml run build && npm --prefix ./../../libraries/bio run build && npm --prefix ./../../libraries/tutorials run build && npm run build",
+    "build-all": "npm --prefix ./../../libraries/chem-meta run build && npm --prefix ./../../js-api run build && npm --prefix ./../../libraries/math run build && npm --prefix ./../../libraries/utils run build && npm --prefix ./../../libraries/ml run build && npm --prefix ./../../libraries/bio run build && npm --prefix ./../../libraries/tutorials run build && npm run build",
     "debug-sequences1-local": "webpack && grok publish local",
     "release-sequences1-local": "webpack && grok publish local --release",
     "debug-sequences1-dev": "webpack && grok publish dev",
@@ -153,4 +153,4 @@
       }
     }
   }
-}
+}

package/src/tests/detectors-benchmark-tests.ts

@@ -52,17 +52,17 @@ category('detectorsBenchmark', () => {
     maxET: number, notation: NOTATION, alphabet: ALPHABET, length: number, count: number, separator?: string,
   ): Promise<number> {
     return await benchmark<DG.FuncCall, DG.Column>(maxET,
-      async (): Promise<DG.FuncCall> => {
+      /* prepare */ async (): Promise<DG.FuncCall> => {
         const col: DG.Column = generate(notation, [...getAlphabet(alphabet)], length, count, separator);
         const funcCall: DG.FuncCall = detectFunc.prepare({col: col});
         // warm-up Bio
-        await testDetector(funcCall);
+        testDetector(funcCall);
         return funcCall;
       },
-      async (funcCall: DG.FuncCall): Promise<DG.Column> => {
+      /* test */ (funcCall: DG.FuncCall): DG.Column => { // sync call for stability
         return testDetector(funcCall);
       },
-      (col: DG.Column) => {
+      /* check */ (col: DG.Column) => {
         checkDetectorRes(col, {
           semType: DG.SEMTYPE.MACROMOLECULE,
           notation: notation,
@@ -115,9 +115,8 @@ category('detectorsBenchmark', () => {
 
   type TgtType = { semType: string, notation: NOTATION, alphabet: ALPHABET, separator?: string };
 
-  async function testDetector(funcCall: DG.FuncCall): Promise<DG.Column> {
-    //const semType: string = await grok.functions.call('Bio:detectMacromolecule', {col: col});
-    await funcCall.call();
+  function testDetector(funcCall: DG.FuncCall): DG.Column {
+    funcCall.callSync();
     const semType = funcCall.getOutputParamValue() as string;
 
     const col: DG.Column = funcCall.inputs.col as unknown as DG.Column;
@@ -137,34 +136,21 @@ category('detectorsBenchmark', () => {
 
 //Returns ET [ms] of test()
 async function benchmark<TData, TRes>(
-  maxET: number, prepare: () => Promise<TData>, test: (data: TData) => Promise<TRes>, check: (res: TRes) => void,
+  maxET: number, prepare: () => Promise<TData>, test: (data: TData) => TRes, check: (res: TRes) => void,
 ): Promise<number> {
   const data: TData = await prepare();
 
-  const tryCount = 60;
-  const maxOutCount = 3; // 95%
-  let outCount: number = 0;
-  let outResET: number = 0;
-  const resEtList: number[] = new Array<number>(tryCount);
-  let resET: number = 0;
-  for (let tryI = 0; tryI < 20; ++tryI) {
-    const t1: number = Date.now();
-    // console.profile();
-    const res: TRes = await test(data);
-    //console.profileEnd();
-    const t2: number = Date.now();
-
-    resET = resEtList[tryI] = t2 - t1;
-    if (resET > maxET) {
-      outCount++;
-      outResET = Math.max(outResET, resET);
-    }
+  const t1: number = Date.now();
+  // console.profile();
+  const res: TRes = test(data); // sync call for stability
+  //console.profileEnd();
+  const t2: number = Date.now();
 
-    check(res);
-  }
+  check(res);
 
-  if (outCount > maxOutCount) {
-    const errMsg = `ET ${outResET} ms is more than max allowed ${maxET} ms. ET: ${JSON.stringify(resEtList)}`;
+  const resET = t2 - t1;
+  if (resET > maxET) {
+    const errMsg = `ET ${resET} ms is more than max allowed ${maxET} ms.`;
     console.error(errMsg);
     throw new Error(errMsg);
   } else

package/src/tests/monomer-libraries-tests.ts

@@ -3,11 +3,11 @@ import * as DG from 'datagrok-api/dg';
 import * as ui from 'datagrok-api/ui';
 
 import {test, after, before, category, expect} from '@datagrok-libraries/utils/src/test';
-
 import {getMonomerLibHelper, IMonomerLibHelper} from '@datagrok-libraries/bio/src/monomer-works/monomer-utils';
 import {
   getUserLibSettings, setUserLibSettings, setUserLibSettingsForTests
 } from '@datagrok-libraries/bio/src/monomer-works/lib-settings';
+import {expectMonomerLib} from '@datagrok-libraries/bio/src/tests/monomer-lib-tests';
 
 
 category('monomerLibraries', () => {
@@ -41,9 +41,7 @@ category('monomerLibraries', () => {
     // Currently default monomer lib set is of all files at LIB_PATH (at least HELMCoreLibrary.json)
     const currentMonomerLib = monomerLibHelper.getMonomerLib();
     // HELMCoreLibrary.json checks
-    expect(currentMonomerLib.getPolymerTypes().length, 2);
-    expect(currentMonomerLib.getMonomerSymbolsByType('PEPTIDE').length, 324);
-    expect(currentMonomerLib.getMonomerSymbolsByType('RNA').length, 383);
+    expectMonomerLib(currentMonomerLib);
   });
 
   test('empty', async () => {

package/src/tests/pepsea-tests.ts

@@ -63,5 +63,5 @@ category('PepSeA', () => {
       logger.error(errMsg, undefined, errStack);
     }
     expect(logger.errorList[0].message, pepseaErrorError);
-  });
+  },{skipReason: 'GROK-16699'});
 });

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

@@ -907,6 +907,13 @@ function capSmiles(smiles: string, rgroups: RGroup[]) {
 }
 
 function monomerFromDfRow(dfRow: DG.Row): Monomer {
+  // hacky way for now, but meta object for now only supports key value pairs and not nested objects
+  const metaJSON = JSON.parse(dfRow.get(MONOMER_DF_COLUMN_NAMES.META) ?? '{}');
+  for (const key in metaJSON) {
+    if (typeof metaJSON[key] === 'object')
+      metaJSON[key] = JSON.stringify(metaJSON[key]);
+  }
+
   return {
     symbol: dfRow.get(MONOMER_DF_COLUMN_NAMES.SYMBOL),
     name: dfRow.get(MONOMER_DF_COLUMN_NAMES.NAME),
@@ -917,7 +924,7 @@ function monomerFromDfRow(dfRow: DG.Row): Monomer {
     naturalAnalog: dfRow.get(MONOMER_DF_COLUMN_NAMES.NATURAL_ANALOG),
     id: dfRow.get(MONOMER_DF_COLUMN_NAMES.ID),
     rgroups: JSON.parse(dfRow.get(MONOMER_DF_COLUMN_NAMES.R_GROUPS) ?? '[]'),
-    meta: JSON.parse(dfRow.get(MONOMER_DF_COLUMN_NAMES.META) ?? '{}'),
+    meta: metaJSON,
     author: dfRow.get(MONOMER_DF_COLUMN_NAMES.AUTHOR),
     createDate: dfRow.get(MONOMER_DF_COLUMN_NAMES.CREATE_DATE),
   };

package/src/utils/pepsea.ts

@@ -7,6 +7,7 @@ import {Subject} from 'rxjs';
 
 import {testEvent} from '@datagrok-libraries/utils/src/test';
 import {NOTATION, TAGS as bioTAGS, ALIGNMENT, ALPHABET} from '@datagrok-libraries/bio/src/utils/macromolecule';
+import { fetchWrapper } from '@datagrok-libraries/utils/src/fetch-utils';
 import {ILogger} from '@datagrok-libraries/bio/src/utils/logger';
 
 import {checkForSingleSeqClusters} from './multiple-sequence-alignment';
@@ -79,7 +80,7 @@ export async function runPepsea(srcCol: DG.Column<string>, unUsedName: string,
 
   const alignedSequences: string[] = new Array(peptideCount);
   for (const body of bodies) { // getting aligned sequences for each cluster
-    const alignedObject = await requestAlignedObjects(pepseaContainer.id, body, method, gapOpen, gapExtend, logger);
+    const alignedObject = await fetchWrapper(() => requestAlignedObjects(pepseaContainer.id, body, method, gapOpen, gapExtend, logger));
     const alignments = alignedObject.Alignment;
 
     for (const alignment of alignments) { // filling alignedSequencesCol