@datagrok/bio 2.13.8 → 2.14.2

package/files/monomer-sets/monomer-set-PEPTIDE.json

@@ -0,0 +1,93 @@
+{
+  "$schema": "../schemas/monomer-set-schema.json",
+  "description": "Amino-acids types",
+  "placeholders": {
+    "AA:aliphatic": {
+      "description": "Aliphatic amino acids",
+      "monomerType": "Backbone",
+      "polymerType": "PEPTIDE",
+      "set": [
+        {
+          "source": "HELMCoreLibrary.json",
+          "symbol": "G",
+          "notes": "Glycine"
+        },
+        {
+          "source": "HELMCoreLibrary.json",
+          "symbol": "A",
+          "notes": "Alanine"
+        },
+        {
+          "source": "HELMCoreLibrary.json",
+          "symbol": "V",
+          "notes": "Valine"
+        },
+        {
+          "source": "HELMCoreLibrary.json",
+          "symbol": "L",
+          "notes": "Leucine"
+        },
+        {
+          "source": "HELMCoreLibrary.json",
+          "symbol": "I",
+          "notes": "Isoleucine"
+        }
+      ]
+    },
+    "AA:neutral": {
+      "description": "Neutral amino acids",
+      "monomerType": "Backbone",
+      "polymerType": "PEPTIDE",
+      "set": [
+        {
+          "source": "HELMCoreLibrary.json",
+          "symbol": "N",
+          "notes": "Asparagine"
+        },
+        {
+          "source": "HELMCoreLibrary.json",
+          "symbol": "Q",
+          "notes": "Glutamine"
+        }
+      ]
+    },
+    "AA:acidic": {
+      "description": "acidic amino acids",
+      "monomerType": "Backbone",
+      "polymerType": "PEPTIDE",
+      "set": [
+        {
+          "source": "HELMCoreLibrary.json",
+          "symbol": "D",
+          "notes": "Aspartic Acid"
+        },
+        {
+          "source": "HELMCoreLibrary.json",
+          "symbol": "E",
+          "notes": "Glutamic Acid"
+        }
+      ]
+    },
+    "AA:basic": {
+      "description": "basic amino acids",
+      "polymerType": "PEPTIDE",
+      "set": [
+        {
+          "source": "HELMCoreLibrary.json",
+          "symbol": "H",
+          "notes": "Histidine"
+        },
+        {
+          "source": "HELMCoreLibrary.json",
+          "symbol": "K",
+          "notes": "Lysine"
+        },
+        {
+          "source": "HELMCoreLibrary.json",
+          "symbol": "R",
+          "notes": "Arginine"
+        }
+      ]
+    }
+  }
+}

package/files/monomer-sets/monomer-set-RNA.json

@@ -0,0 +1,29 @@
+{
+  "$schema": "../schemas/monomer-set-schema.json",
+  "description": "RNA sugar types",
+  "placeholders": {
+    "r:pentose": {
+      "description": "Five-carbon sugars in ribonucleic acids backbone",
+      "monomerType": "Backbone",
+      "polymerType": "RNA",
+      "set": [
+        {
+          "source": "HELMCoreLibrary.json",
+          "symbol": "r",
+          "notes": "ribose"
+        },
+        {
+          "source": "HELMCoreLibrary.json",
+          "symbol": "d",
+          "notes": "deoxyribose"
+        }
+      ]
+    },
+    "r:hexose": {
+      "description": "Six-carbon sugars in ribonucleic acids backbone",
+      "monomerType": "Backbone",
+      "polymerType": "RNA",
+      "set": []
+    }
+  }
+}

package/files/schemas/monomer-set-schema.json

@@ -0,0 +1,48 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "description": "Monomer Sets JSON Schema v1 for combinatorial libraries",
+  "type": "object",
+  "properties": {
+    "description": {
+      "type": "string"
+    },
+    "placeholders": {
+      "type": "object",
+      "additionalProperties": {
+        "type": "object",
+        "properties": {
+          "description": {
+            "type": "string"
+          },
+          "monomerType": {
+            "enum": ["Backbone", "Branch", "Terminal"]
+          },
+          "polymerType": {
+            "enum": ["PEPTIDE", "RNA"]
+          },
+          "set": {
+            "type": "array",
+            "items": {
+              "type": "object",
+              "description": "Link to a monomer of a monomer library",
+              "required": ["source", "symbol"],
+              "properties": {
+                "source": {
+                  "type": "string",
+                  "description": "Monomer library name, path."
+                },
+                "symbol": {
+                  "type": "string",
+                  "description": "Monomer symbol from the library"
+                },
+                "notes": {
+                  "type": "string"
+                }
+              }
+            }
+          }
+        }
+      }
+    }
+  }
+}

package/package.json

@@ -5,7 +5,7 @@
     "name": "Aleksandr Tanas",
     "email": "atanas@datagrok.ai"
   },
-  "version": "2.13.8",
+  "version": "2.14.2",
   "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",
@@ -37,10 +37,10 @@
   ],
   "dependencies": {
     "@biowasm/aioli": "^3.1.0",
-    "@datagrok-libraries/bio": "^5.42.6",
+    "@datagrok-libraries/bio": "^5.42.9",
     "@datagrok-libraries/chem-meta": "^1.2.5",
     "@datagrok-libraries/math": "^1.1.12",
-    "@datagrok-libraries/ml": "^6.6.17",
+    "@datagrok-libraries/ml": "^6.6.19",
     "@datagrok-libraries/tutorials": "^1.3.13",
     "@datagrok-libraries/utils": "^4.2.22",
     "@webgpu/types": "^0.1.40",
@@ -58,8 +58,8 @@
     "wu": "latest"
   },
   "devDependencies": {
-    "@datagrok-libraries/helm-web-editor": "^1.1.6",
-    "@datagrok-libraries/js-draw-lite": "^0.0.4",
+    "@datagrok-libraries/helm-web-editor": "^1.1.8",
+    "@datagrok-libraries/js-draw-lite": "^0.0.6",
     "@datagrok/chem": "^1.9.2",
     "@datagrok/dendrogram": "^1.2.29",
     "@datagrok/helm": "^2.2.1",

package/src/analysis/sequence-similarity-viewer.ts

@@ -30,12 +30,14 @@ export class SequenceSimilarityViewer extends SequenceSearchBaseViewer {
   mmDistanceMatrix: Float32Array;
   knn?: KnnResult;
   kPrevNeighbors: number = 0;
+  demo?: boolean;
 
-  constructor() {
+  constructor(demo?: boolean) {
     super('similarity');
     this.cutoff = this.float('cutoff', 0.01, {min: 0, max: 1});
     this.hotSearch = this.bool('hotSearch', true);
     this.similarColumnLabel = this.string('similarColumnLabel', null);
+    this.demo = demo;
   }
 
   init(): void {
@@ -70,7 +72,8 @@ export class SequenceSimilarityViewer extends SequenceSearchBaseViewer {
         const targetMolRow = this.idxs?.getRawData().findIndex((it) => it == this.targetMoleculeIdx);
         const targetScoreCell = grid.cell('score', targetMolRow!);
         targetScoreCell.cell.value = null;
-        (grok.shell.v as DG.TableView).grid.root.addEventListener('click', (_event: MouseEvent) => {
+        const view = this.demo ? (grok.shell.view('Browse')! as DG.BrowseView)!.preview! as DG.TableView : grok.shell.v as DG.TableView;
+        view.grid.root.addEventListener('click', (_event: MouseEvent) => {
           this.gridSelect = false;
         });
         updateDivInnerHTML(this.root, grid.root);

package/src/demo/bio01-similarity-diversity.ts

@@ -37,10 +37,11 @@ export async function demoBio01UI() {
         delay: 2000,
       })
       .step('Find the most similar sequences to the current one', async () => {
-        const simViewer = await df.plot.fromType('Sequence Similarity Search', {
+        const simViewer = new SequenceSimilarityViewer(true);
+        view.addViewer(simViewer, {
           moleculeColumnName: 'sequence',
           similarColumnLabel: 'Similar to current',
-        }) as SequenceSimilarityViewer;
+        });
         view.dockManager.dock(simViewer, DG.DOCK_TYPE.RIGHT, null, 'Similarity search', 0.35);
       }, {
         description: `Add 'Sequence Similarity Search' viewer.`,

package/src/demo/bio01b-hierarchical-clustering-and-activity-cliffs.ts

@@ -53,7 +53,7 @@ export async function demoBio01bUI() {
         const seqEncodingFunc = DG.Func.find({name: 'macromoleculePreprocessingFunction', package: 'Bio'})[0];
         activityCliffsViewer = (await activityCliffs(
           df, df.getCol('Sequence'), df.getCol('Activity'),
-          80, dimRedMethod, MmDistanceFunctionsNames.LEVENSHTEIN, seqEncodingFunc, {})) as DG.ScatterPlotViewer;
+          80, dimRedMethod, MmDistanceFunctionsNames.LEVENSHTEIN, seqEncodingFunc, {}, true)) as DG.ScatterPlotViewer;
         view.dockManager.dock(activityCliffsViewer, DG.DOCK_TYPE.RIGHT, null, 'Activity Cliffs', 0.35);
 
         // Show grid viewer with the cliffs

package/src/package.ts

@@ -11,7 +11,7 @@ import {MmDistanceFunctionsNames} from '@datagrok-libraries/ml/src/macromolecule
 import {BitArrayMetrics, KnownMetrics} from '@datagrok-libraries/ml/src/typed-metrics';
 import {NOTATION, TAGS as bioTAGS} from '@datagrok-libraries/bio/src/utils/macromolecule';
 import {SeqHandler, SeqTemps} from '@datagrok-libraries/bio/src/utils/seq-handler';
-import {IMonomerLib} from '@datagrok-libraries/bio/src/types';
+import {IMonomerLib, IMonomerSet} from '@datagrok-libraries/bio/src/types';
 import {SeqPalette} from '@datagrok-libraries/bio/src/seq-palettes';
 import {FastaFileHandler} from '@datagrok-libraries/bio/src/utils/fasta-handler';
 import {_toAtomicLevel} from '@datagrok-libraries/bio/src/monomer-works/to-atomic-level';
@@ -78,9 +78,9 @@ import {CyclizedNotationProvider} from './utils/cyclized';
 import {getMolColumnFromHelm} from './utils/helm-to-molfile/utils';
 import {PackageSettingsEditorWidget} from './widgets/package-settings-editor-widget';
 import {getUserLibSettings, setUserLibSettings} from '@datagrok-libraries/bio/src/monomer-works/lib-settings';
-import { calculateScoresWithEmptyValues } from './utils/calculate-scores';
+import {calculateScoresWithEmptyValues} from './utils/calculate-scores';
 
-export const _package = new BioPackage();
+export const _package = new BioPackage(/*{debug: true}/**/);
 
 // /** Avoid reassigning {@link monomerLib} because consumers subscribe to {@link IMonomerLib.onChanged} event */
 // let monomerLib: MonomerLib | null = null;
@@ -107,6 +107,7 @@ export class SeqPaletteCustom implements SeqPalette {
 }
 
 let monomerLib: IMonomerLib | null = null;
+let monomerSets: IMonomerSet | null = null;
 
 //tags: init
 export async function initBio() {
@@ -123,8 +124,9 @@ export async function initBio() {
         libSettings.explicit = [];
         await setUserLibSettings(libSettings);
       }
-      await monomerLibManager.loadLibraries();
-      monomerLib = monomerLibManager.getBioLib();
+      await Promise.all([monomerLibManager.loadMonomerLib(), monomerLibManager.loadMonomerSets()]);
+      monomerLib = monomerLibManager.getMonomerLib();
+      monomerSets = monomerLibManager.getMonomerSets();
     })(),
     (async () => {
       const pkgProps = await _package.getProperties();
@@ -438,12 +440,13 @@ export async function getRegionTopMenu(
 //input: string similarityMetric { choices:["Hamming", "Levenshtein", "Monomer chemical distance"] }
 //input: func preprocessingFunction
 //input: object options {optional: true}
+//input: bool demo {optional: true}
 //output: viewer result
 //editor: Bio:SeqActivityCliffsEditor
 export async function activityCliffs(table: DG.DataFrame, molecules: DG.Column<string>, activities: DG.Column,
   similarity: number, methodName: DimReductionMethods,
   similarityMetric: MmDistanceFunctionsNames | BitArrayMetrics, preprocessingFunction: DG.Func,
-  options?: (IUMAPOptions | ITSNEOptions) & Options): Promise<DG.Viewer | undefined> {
+  options?: (IUMAPOptions | ITSNEOptions) & Options, demo?: boolean): Promise<DG.Viewer | undefined> {
   if (!checkInputColumnUI(molecules, 'Activity Cliffs'))
     return;
   const axesNames = getEmbeddingColsNames(table);
@@ -473,6 +476,8 @@ export async function activityCliffs(table: DG.DataFrame, molecules: DG.Column<s
       createTooltipElement,
       createPropPanelElement,
       createLinesGrid,
+      undefined,
+      demo
     );
     return sp;
   };
@@ -595,7 +600,7 @@ export async function sequenceSpaceTopMenu(table: DG.DataFrame, molecules: DG.Co
 export async function toAtomicLevel(table: DG.DataFrame, seqCol: DG.Column, nonlinear: boolean): Promise<void> {
   const pi = DG.TaskBarProgressIndicator.create('Converting to atomic level ...');
   try {
-    const monomerLib = (await getMonomerLibHelper()).getBioLib();
+    const monomerLib = (await getMonomerLibHelper()).getMonomerLib();
     await sequenceToMolfile(table, seqCol, nonlinear, monomerLib);
   } finally {
     pi.close();

package/src/tests/activity-cliffs-tests.ts

@@ -36,7 +36,7 @@ category('activityCliffs', async () => {
 
     // Test 'helm' requires default monomer library loaded
     await setUserLibSettingsForTests();
-    await monomerLibHelper.loadLibraries(true); // load default libraries
+    await monomerLibHelper.loadMonomerLib(true); // load default libraries
 
     viewList = [];
     dfList = [];
@@ -48,7 +48,7 @@ category('activityCliffs', async () => {
 
     // UserDataStorage.put() replaces existing data
     await setUserLibSettings(userLibSettings);
-    await monomerLibHelper.loadLibraries(true); // load user settings libraries
+    await monomerLibHelper.loadMonomerLib(true); // load user settings libraries
   });
 
   test('activityCliffsOpens', async () => {

package/src/tests/detectors-tests.ts

@@ -99,6 +99,13 @@ C1CCCCC1
 CCCCCC`,
       neg: ['col1'],
     },
+    'negSmilesWithSquareBrackets': {
+      csv: `col1
+Cl.c1ccc2nc3ccccc3cc2c1
+Oc1cccc2cc3ccccc3cc12
+[SeH]c1ccc2ccccc2c1`,
+      neg: ['col1'],
+    },
     'negFastaUnSingleChar': {
       csv: `col1
 Alanine
@@ -247,7 +254,7 @@ MWRSWY-CKHPMWRSWY-CKHP`;
     peptidesComplex = 'peptidesComplex',
     peptidesSimple = 'peptidesSimple',
     fastaCsv = 'fastaCsv',
-    fastaFasta = 'fastaFasta',
+    // fastaFasta = 'fastaFasta',
     fastaPtCsv = 'fastaPtCsv',
     msaComplex = 'msaComplex',
     helmCsv = 'helmCsv',
@@ -268,7 +275,7 @@ MWRSWY-CKHPMWRSWY-CKHP`;
   }
 
   const samples: { [key: string]: string } = {
-    [Samples.fastaFasta]: 'System:AppData/Bio/samples/FASTA.fasta',
+    // [Samples.fastaFasta]: 'System:AppData/Bio/samples/FASTA.fasta',
     [Samples.fastaPtCsv]: 'System:AppData/Bio/samples/FASTA_PT.csv',
     [Samples.msaComplex]: 'System:AppData/Bio/samples/MSA.csv',
     [Samples.fastaCsv]: 'System:AppData/Bio/samples/FASTA.csv',
@@ -408,11 +415,11 @@ MWRSWY-CKHPMWRSWY-CKHP`;
     });
   });
 
-  test('samplesFastaFasta', async () => {
-    await _testDf(readSamples(Samples.fastaFasta), {
-      'sequence': new PosCol(NOTATION.FASTA, ALIGNMENT.SEQ, ALPHABET.PT, 20, false),
-    });
-  });
+  // test('samplesFastaFasta', async () => {
+  //   await _testDf(readSamples(Samples.fastaFasta), {
+  //     'sequence': new PosCol(NOTATION.FASTA, ALIGNMENT.SEQ, ALPHABET.PT, 20, false),
+  //   });
+  // });
 
   // peptidesComplex contains monomers with spaces in AlignedSequence columns, which are forbidden
   // test('samplesPeptidesComplexPositiveAlignedSequence', async () => {

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

@@ -27,19 +27,19 @@ category('monomerLibraries', () => {
   test('default', async () => {
     // Clear settings to test default
     await setUserLibSettings({exclude: [], explicit: []});
-    await monomerLibHelper.loadLibraries(true); // test defaultLib
+    await monomerLibHelper.loadMonomerLib(true); // test defaultLib
 
     // Currently default monomer lib set is of all files at LIB_PATH (at least HELMCoreLibrary.json)
-    const currentMonomerLib = monomerLibHelper.getBioLib();
+    const currentMonomerLib = monomerLibHelper.getMonomerLib();
     expect(currentMonomerLib.getPolymerTypes().length > 0, true);
   });
 
   test('forTests', async () => {
     await setUserLibSettingsForTests();
-    await monomerLibHelper.loadLibraries(true); // test defaultLib
+    await monomerLibHelper.loadMonomerLib(true); // test defaultLib
 
     // Currently default monomer lib set is of all files at LIB_PATH (at least HELMCoreLibrary.json)
-    const currentMonomerLib = monomerLibHelper.getBioLib();
+    const currentMonomerLib = monomerLibHelper.getMonomerLib();
     // HELMCoreLibrary.json checks
     expect(currentMonomerLib.getPolymerTypes().length, 2);
     expect(currentMonomerLib.getMonomerSymbolsByType('PEPTIDE').length, 322);
@@ -59,8 +59,8 @@ category('monomerLibraries', () => {
     libSettings.explicit = [];
     await setUserLibSettings(libSettings);
 
-    await monomerLibHelper.loadLibraries(true);
-    const currentMonomerLib = monomerLibHelper.getBioLib();
+    await monomerLibHelper.loadMonomerLib(true);
+    const currentMonomerLib = monomerLibHelper.getMonomerLib();
     const polymerTypes = currentMonomerLib.getPolymerTypes();
     expect(polymerTypes.length === 0, true);
   });

package/src/tests/renderers-monomer-placer-tests.ts

@@ -26,12 +26,12 @@ category('renderers: monomerPlacer', () => {
 
     await setUserLibSettingsForTests();
     await libHelper.awaitLoaded();
-    await libHelper.loadLibraries(true);
+    await libHelper.loadMonomerLib(true);
   });
 
   after(async () => {
     await setUserLibSettings(libSettings);
-    await libHelper.loadLibraries(true);
+    await libHelper.loadMonomerLib(true);
   });
 
   const tests = {

package/src/tests/scoring.ts

@@ -42,13 +42,13 @@ PEPTIDE1{[1Nal].[1Nal].[1Nal].[1Nal].[1Nal].[1Nal].[1Nal].[1Nal].[1Nal].[1Nal].[
     userLibSettings = await getUserLibSettings();
 
     await setUserLibSettingsForTests();
-    await monomerLibHelper.loadLibraries(true); // load default libraries
+    await monomerLibHelper.loadMonomerLib(true); // load default libraries
   });
 
   after(async () => {
     // UserDataStorage.put() replaces existing data
     await setUserLibSettings(userLibSettings);
-    await monomerLibHelper.loadLibraries(true); // load user settings libraries
+    await monomerLibHelper.loadMonomerLib(true); // load user settings libraries
   });
 
   test('Identity', async () => {

package/src/tests/substructure-filters-tests.ts

@@ -37,13 +37,13 @@ category('bio-substructure-filters', async () => {
 
     // Test 'helm' requires default monomer library loaded
     await setUserLibSettingsForTests();
-    await monomerLibHelper.loadLibraries(true); // load default libraries
+    await monomerLibHelper.loadMonomerLib(true); // load default libraries
   });
 
   after(async () => {
     // UserDataStorage.put() replaces existing data
     await setUserLibSettings(userLibSettings);
-    await monomerLibHelper.loadLibraries(true); // load user settings libraries
+    await monomerLibHelper.loadMonomerLib(true); // load user settings libraries
   });
 
   test('fasta', async () => {

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

@@ -64,7 +64,7 @@ category('toAtomicLevel', async () => {
     userLibSettings = await getUserLibSettings();
     // Clear settings to test default
     await setUserLibSettingsForTests();
-    await monomerLibHelper.loadLibraries(true);
+    await monomerLibHelper.loadMonomerLib(true);
 
     for (const [testName, testData] of Object.entries(TestsData)) {
       const inputPath = testData.inPath;
@@ -77,7 +77,7 @@ category('toAtomicLevel', async () => {
 
   after(async () => {
     await setUserLibSettings(userLibSettings);
-    await monomerLibHelper.loadLibraries(true);
+    await monomerLibHelper.loadMonomerLib(true);
   });
 
   async function getTestResult(source: DG.DataFrame, target: DG.DataFrame): Promise<void> {
@@ -217,7 +217,7 @@ async function _testToAtomicLevel(
   df: DG.DataFrame, seqColName: string = 'seq', monomerLibHelper: IMonomerLibHelper
 ): Promise<DG.Column | null> {
   const seqCol: DG.Column<string> = df.getCol(seqColName);
-  const monomerLib: IMonomerLib = monomerLibHelper.getBioLib();
+  const monomerLib: IMonomerLib = monomerLibHelper.getMonomerLib();
   const res = await _toAtomicLevel(df, seqCol, monomerLib);
   if (res.warnings.length > 0)
     _package.logger.warning(`_toAtomicLevel() warnings ${res.warnings.join('\n')}`);

package/src/utils/helm-to-molfile/converter/converter.ts

@@ -84,7 +84,7 @@ export class HelmToMolfileConverter {
   private async convertToMolfileV3KColumn(): Promise<DG.Column<string>> {
     const polymerGraphColumn: DG.Column<string> = await this.getPolymerGraphColumn();
     const rdKitModule = await grok.functions.call('Chem:getRdKitModule');
-    const monomerLib: IMonomerLib = (await getMonomerLibHelper()).getBioLib();
+    const monomerLib: IMonomerLib = (await getMonomerLibHelper()).getMonomerLib();
     const molfileList = polymerGraphColumn.toList().map(
       (pseudoMolfile: string, idx: number) => {
         const helm = this.helmColumn.get(idx);