@datagrok/bio 2.10.23 → 2.10.25

package/files/samples/HELM-non-linear.csv

@@ -0,0 +1,8 @@
+HELM
+"PEPTIDE1{[meI].[hHis].[Aca].N.T.[dE].[Thr_PO3H2].[Aca].[D-Tyr_Et].[Tyr_ab-dehydroMe].[dV].E.N.[D-Orn].[D-aThr].[Phe_4Me]}$PEPTIDE1,PEPTIDE1,16:R2-1:R1$$$V2.0"
+PEPTIDE1{meI.hHis.Aca.Cys_SEt.T.dK.Thr_PO3H2.Aca.Tyr_PO3H2.D-Chg.dV.Phe_ab-dehydro.N.D-Orn.D-aThr.Phe_4Me}$$$$
+"PEPTIDE1{C.A.C.A.C.A.C.A}|PEPTIDE2{C.A.C.A.C.A.C.A}|PEPTIDE3{C.A.C.A.C.A.C.A}|PEPTIDE4{C.A.C.A.C.A.C.A}$PEPTIDE1,PEPTIDE2,3:R3-8:R2|PEPTIDE3,PEPTIDE4,3:R3-8:R2|PEPTIDE1,PEPTIDE3,5:R3-5:R3$$$V2.0"
+"PEPTIDE1{C.A.C.A.C.A.C.A.C.A.C.A}|PEPTIDE2{C.A.C.A.C.A.C.A.C.A.C.A}$PEPTIDE2,PEPTIDE1,1:R1-3:R3|PEPTIDE2,PEPTIDE2,1:R3-12:R2$$$V2.0"
+RNA1{d(A)p.d(G)p.d(C)p.d(T)p.d(A)p.d(G)p.d(C)p.d(T)p}$$$$V2.0
+RNA1{d(A)p.d(G)p.d(C)p.d(T)p.d(A)p.d(G)p.d(C)p.d(T)p}|RNA2{d(G)p.d(G)p.d(G)p.d(G)p.d(A)p.d(G)p.d(C)p.d(T)p}$$$$V2.0
+"RNA1{d(A)p.d(G)p.d(C)p.d(T)p.d(A)p.d(G)p.d(C)p.d(T)p}$RNA1,RNA1,24:R2-1:R1$$$V2.0"

package/package.json

@@ -5,7 +5,7 @@
     "name": "Leonid Stolbov",
     "email": "lstolbov@datagrok.ai"
   },
-  "version": "2.10.23",
+  "version": "2.10.25",
   "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": "^5.38.12",
+    "@datagrok-libraries/bio": "^5.38.13",
     "@datagrok-libraries/chem-meta": "^1.0.1",
     "@datagrok-libraries/ml": "^6.3.49",
     "@datagrok-libraries/tutorials": "^1.3.6",

package/src/demo/bio03-atomic-level.ts

@@ -35,7 +35,7 @@ export async function demoBio03UI(): Promise<void> {
       })
       .step('To atomic level', async () => {
         const seqCol = df.getCol(seqColName);
-        await toAtomicLevel(df, seqCol);
+        await toAtomicLevel(df, seqCol, false);
       }, {
         description: 'Get atomic level structures of Macromolecules.',
         delay: 2000,

package/src/package.ts

@@ -60,7 +60,7 @@ import {SplitToMonomersFunctionEditor} from './function-edtiors/split-to-monomer
 import {splitToMonomersUI} from './utils/split-to-monomers';
 import {MonomerCellRenderer} from './utils/monomer-cell-renderer';
 import {BioPackage, BioPackageProperties} from './package-types';
-import {RDModule} from '@datagrok-libraries/chem-meta/src/rdkit-api';
+import {RDMol} from '@datagrok-libraries/chem-meta/src/rdkit-api';
 import {PackageSettingsEditorWidget} from './widgets/package-settings-editor-widget';
 import {getCompositionAnalysisWidget} from './widgets/composition-analysis-widget';
 import {MacromoleculeColumnWidget} from './utils/macromolecule-column-widget';
@@ -69,9 +69,11 @@ import {_getEnumeratorWidget, _setPeptideColumn} from './utils/enumerator-tools'
 import {getRegionDo} from './utils/get-region';
 import {GetRegionApp} from './apps/get-region-app';
 import {GetRegionFuncEditor} from './utils/get-region-func-editor';
+import {HelmToMolfileConverter} from './utils/helm-to-molfile';
 import {DIMENSIONALITY_REDUCER_TERMINATE_EVENT}
   from '@datagrok-libraries/ml/src/workers/dimensionality-reducing-worker-creator';
 import {Options} from '@datagrok-libraries/utils/src/type-declarations';
+import { sequenceToMolfile } from './utils/sequence-to-mol';
 
 export const _package = new BioPackage();
 
@@ -620,22 +622,11 @@ export async function sequenceSpaceTopMenu(
 //description: Converts sequences to molblocks
 //input: dataframe df [Input data table]
 //input: column macroMolecule {semType: Macromolecule}
-export async function toAtomicLevel(df: DG.DataFrame, macroMolecule: DG.Column): Promise<void> {
-  if (DG.Func.find({package: 'Chem', name: 'getRdKitModule'}).length === 0) {
-    grok.shell.warning('Transformation to atomic level requires package "Chem" installed.');
-    return;
-  }
-  if (!checkInputColumnUI(macroMolecule, 'To Atomic Level'))
-    return;
-  const monomerLib: IMonomerLib = (await getMonomerLibHelper()).getBioLib();
-  const atomicLevelRes = await _toAtomicLevel(df, macroMolecule, monomerLib);
-  if (atomicLevelRes.col !== null) {
-    df.columns.add(atomicLevelRes.col, true);
-    await grok.data.detectSemanticTypes(df);
-  }
-
-  if (atomicLevelRes.warnings && atomicLevelRes.warnings.length > 0)
-    grok.shell.warning(ui.list(atomicLevelRes.warnings));
+//input: bool nonlinear=false { description: Slower mode for cycling/branching HELM structures }
+export async function toAtomicLevel(df: DG.DataFrame, macroMolecule: DG.Column, nonlinear: boolean): Promise<void> {
+  const pi = DG.TaskBarProgressIndicator.create('Converting to atomic level ...');
+  sequenceToMolfile(df, macroMolecule, nonlinear);
+  pi.close();
 }
 
 //top-menu: Bio | Analyze | MSA...
@@ -1059,6 +1050,7 @@ 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

@@ -32,7 +32,7 @@ ATC-G-TTGC--
     const wlViewer: WebLogoViewer = (await df.plot.fromType('WebLogo')) as WebLogoViewer;
     await testEvent(wlViewer.onLayoutCalculated, () => {}, () => {
       tv.dockManager.dock(wlViewer.root, DG.DOCK_TYPE.DOWN);
-    }, 200);
+    }, 300);
     const positions: PI[] = wlViewer['positions'];
 
     const resAllDf1: PI[] = [
@@ -84,7 +84,7 @@ ATC-G-TTGC--
       {'shrinkEmptyTail': true})) as WebLogoViewer;
     await testEvent(wlViewer.onLayoutCalculated, () => {}, () => {
       tv.dockManager.dock(wlViewer.root, DG.DOCK_TYPE.DOWN);
-    }, 200);
+    }, 500);
     const positions: PI[] = wlViewer['positions'];
 
     const resAllDf1: PI[] = [
@@ -122,7 +122,7 @@ ATC-G-TTGC--
       {'skipEmptyPositions': true})) as WebLogoViewer;
     await testEvent(wlViewer.onLayoutCalculated, () => {}, () => {
       tv.dockManager.dock(wlViewer.root, DG.DOCK_TYPE.DOWN);
-    }, 200);
+    }, 300);
     const resPosList: PI[] = wlViewer['positions'];
 
     const tgtPosList: PI[] = [
@@ -158,7 +158,7 @@ ATC-G-TTGC--
     })) as WebLogoViewer;
     await testEvent(wlViewer.onLayoutCalculated, () => {}, () => {
       tv.dockManager.dock(wlViewer.root, DG.DOCK_TYPE.DOWN);
-    }, 200);
+    }, 300);
     const resPosList: PI[] = wlViewer['positions'];
     const tgtPosList: PI[] = [
       new PI(2, '3', {'C': new PMI(5)}),
@@ -179,6 +179,24 @@ ATC-G-TTGC--
     const countAt1 = countForMonomerAtPosition(df, uh, df.filter, 'G', atPI1);
     expect(countAt1, 5);
   });
+
+  test('empty', async () => {
+    const df: DG.DataFrame = DG.DataFrame.fromColumns([(() => {
+      const col = DG.Column.fromStrings('seq', []);
+      col.setTag(DG.TAGS.SEMTYPE, DG.SEMTYPE.MACROMOLECULE);
+      col.setTag(DG.TAGS.UNITS, NOTATION.FASTA);
+      col.setTag(bioTAGS.alphabet, ALPHABET.DNA);
+      return col;
+    })()]);
+
+    const tv: DG.TableView = grok.shell.addTableView(df);
+
+    const wlViewer: WebLogoViewer = (await df.plot.fromType('WebLogo')) as WebLogoViewer;
+    await testEvent(wlViewer.onLayoutCalculated, () => {}, () => {
+      tv.dockManager.dock(wlViewer.root, DG.DOCK_TYPE.DOWN);
+    }, 300);
+    const resPosList: PI[] = wlViewer['positions'];
+  });
 });
 
 function expectPositionInfo(actualPos: PI, expectedPos: PI): void {

package/src/tests/to-atomic-level-tests.ts

@@ -64,7 +64,7 @@ category('toAtomicLevel', async () => {
 
   async function getTestResult(source: DG.DataFrame, target: DG.DataFrame): Promise<void> {
     const inputCol = source.getCol(inputColName);
-    await toAtomicLevel(source, inputCol);
+    await toAtomicLevel(source, inputCol, false);
     const obtainedCol = source.getCol(outputColName);
     const expectedCol = target.getCol(outputColName);
     const obtainedArray = [...obtainedCol.values()];