@datagrok/bio 1.7.11 → 1.7.14

package/package.json

@@ -2,7 +2,7 @@
   "name": "@datagrok/bio",
   "beta": false,
   "friendlyName": "Bio",
-  "version": "1.7.11",
+  "version": "1.7.14",
   "description": "Bio is a [package](https://datagrok.ai/help/develop/develop#packages) for the [Datagrok](https://datagrok.ai) platform",
   "repository": {
     "type": "git",
@@ -11,25 +11,25 @@
   },
   "dependencies": {
     "@biowasm/aioli": ">=2.4.0",
-    "@datagrok-libraries/bio": "^2.8.5",
-    "@datagrok-libraries/utils": "^1.0.0",
-    "@datagrok-libraries/ml": "^2.0.10",
+    "@datagrok-libraries/bio": "^2.8.6",
+    "@datagrok-libraries/ml": "^3.0.0",
+    "@datagrok-libraries/utils": "^1.4.0",
     "cash-dom": "latest",
-    "datagrok-api": "^1.4.12",
-    "dayjs": "latest",
+    "datagrok-api": "^1.5.1",
+    "dayjs": "^1.11.4",
+    "openchemlib": "6.0.1",
     "rxjs": "^6.5.5",
     "ts-loader": "^9.2.5",
-    "typescript": "^4.4.2",
-    "openchemlib": "6.0.1"
+    "typescript": "^4.4.2"
   },
   "devDependencies": {
     "@types/jest": "^27.0.0",
     "@typescript-eslint/eslint-plugin": "latest",
     "@typescript-eslint/parser": "latest",
-    "eslint": "latest",
+    "eslint": "^8.20.0",
     "eslint-config-google": "latest",
     "jest": "^27.0.0",
-    "jest-html-reporter": "^3.5.0",
+    "jest-html-reporter": "^3.6.0",
     "puppeteer": "^13.7.0",
     "ts-jest": "^27.0.0",
     "webpack": "latest",
@@ -40,16 +40,16 @@
     "link-bio": "npm link @datagrok-libraries/bio",
     "link-ml": "npm link @datagrok-libraries/ml",
     "link-all": "npm link datagrok-api @datagrok-libraries/utils @datagrok-libraries/bio @datagrok-libraries/ml",
-    "debug-sequences1": "grok publish --rebuild",
-    "release-sequences1": "grok publish --rebuild --release",
+    "debug-sequences1": "grok publish",
+    "release-sequences1": "grok publish --release",
     "build-sequences1": "webpack",
     "debug-local": "grok publish local",
     "release-local": "grok publish local --release",
     "build": "webpack",
-    "debug-sequences1-public": "grok publish public --rebuild",
-    "release-sequences1-public": "grok publish public --rebuild --release",
-    "debug-sequences1-local": "grok publish local --rebuild",
-    "release-sequences1-local": "grok publish local --rebuild --release",
+    "debug-sequences1-public": "grok publish public",
+    "release-sequences1-public": "grok publish public --release",
+    "debug-sequences1-local": "grok publish local",
+    "release-sequences1-local": "grok publish local --release",
     "lint": "eslint \"./src/**/*.ts\"",
     "lint-fix": "eslint \"./src/**/*.ts\" --fix",
     "test": "jest",

package/scripts/embed.py

@@ -0,0 +1,13 @@
+#name: Embed
+#language: python
+#input: string molecule
+#output: string sdf
+
+from rdkit.Chem import AllChem
+from rdkit import Chem
+mol = AllChem.MolFromMolBlock(molecule) if ("M  END" in molecule) else AllChem.MolFromSmiles(molecule)
+
+AllChem.EmbedMolecule(mol, AllChem.ETKDG())
+#AllChem.UFFOptimizeMolecule(mol)
+#mol = Chem.RemoveHs(mol)
+sdf = Chem.MolToMolBlock(mol)

package/src/const.ts

@@ -23,3 +23,8 @@ export const CAP_GROUP_NAME = 'capGroupName';
 export const RGROUP_LABEL = 'label';
 export const MONOMER_SYMBOL = 'symbol';
 export const SDF_MONOMER_NAME = 'MonomerName';
+
+// range of hex nubers used in PepSea library to endode monomers
+export const MONOMER_ENCODE_MIN = 0x100;
+export const MONOMER_ENCODE_MAX = 0x40A;
+

package/src/package.ts

@@ -16,11 +16,12 @@ import {getEmbeddingColsNames, sequenceSpace} from './utils/sequence-space';
 import {AvailableMetrics} from '@datagrok-libraries/ml/src/typed-metrics';
 import {getActivityCliffs} from '@datagrok-libraries/ml/src/viewers/activity-cliffs';
 import {sequenceGetSimilarities, drawTooltip} from './utils/sequence-activity-cliffs';
-import {createJsonMonomerLibFromSdf, getMolfilesFromSeq, HELM_CORE_LIB_FILENAME} from './utils/utils';
+import {createJsonMonomerLibFromSdf, encodeMonomers, getMolfilesFromSeq, HELM_CORE_LIB_FILENAME} from './utils/utils';
 import {getMacroMol} from './utils/atomic-works';
 import {MacromoleculeSequenceCellRenderer} from './utils/cell-renderer';
 import {convert} from './utils/convert';
 import {lru} from './utils/cell-renderer';
+import {representationsWidget} from './widgets/representations';
 
 //tags: init
 export async function initBio(): Promise<void> {
@@ -37,7 +38,6 @@ export function Lru() {
   return lru;
 }
 
-
 //name: macromoleculeSequenceCellRenderer
 //tags: cellRenderer
 //meta.cellType: Macromolecule
@@ -112,7 +112,9 @@ export async function activityCliffs(df: DG.DataFrame, macroMolecule: DG.Column,
   similarity: number, methodName: string): Promise<void> {
   if (!checkInputColumn(macroMolecule, 'Activity Cliffs'))
     return;
-
+  const encodedCol = encodeMonomers(macroMolecule);
+  if (!encodedCol)
+    return;
   const axesNames = getEmbeddingColsNames(df);
   const options = {
     'SPE': {cycles: 2000, lambda: 1.0, dlambda: 0.0005},
@@ -121,6 +123,7 @@ export async function activityCliffs(df: DG.DataFrame, macroMolecule: DG.Column,
   await getActivityCliffs(
     df,
     macroMolecule,
+    encodedCol,
     axesNames,
     'Activity cliffs',
     activities,
@@ -146,10 +149,12 @@ export async function sequenceSpaceTopMenu(table: DG.DataFrame, macroMolecule: D
   similarityMetric: string = 'Levenshtein', plotEmbeddings: boolean): Promise<void> {
   if (!checkInputColumn(macroMolecule, 'Activity Cliffs'))
     return;
-
+  const encodedCol = encodeMonomers(macroMolecule);
+  if (!encodedCol)
+    return;
   const embedColsNames = getEmbeddingColsNames(table);
   const chemSpaceParams = {
-    seqCol: macroMolecule,
+    seqCol: encodedCol,
     methodName: methodName,
     similarityMetric: similarityMetric,
     embedAxesNames: embedColsNames
@@ -275,6 +280,17 @@ function parseMacromolecule(
   return seqArray.join('');
 }
 
+//name: Representations
+//tags: panel, widgets
+//input: cell macroMolecule {semType: Macromolecule}
+//output: widget result
+export async function peptideMolecule(macroMolecule: DG.Cell): Promise<DG.Widget> {
+  const monomersLibFile = await _package.files.readAsText(HELM_CORE_LIB_FILENAME);
+  const monomersLibObject: any[] = JSON.parse(monomersLibFile);
+  
+  return representationsWidget(macroMolecule, monomersLibObject);
+}
+
 //name: importFasta
 //description: Opens FASTA file
 //tags: file-handler

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

@@ -7,6 +7,7 @@ import {readDataframe} from './utils';
 import {getEmbeddingColsNames, sequenceSpace} from '../utils/sequence-space';
 import {drawTooltip, sequenceGetSimilarities} from '../utils/sequence-activity-cliffs';
 import {getActivityCliffs} from '@datagrok-libraries/ml/src/viewers/activity-cliffs';
+import { encodeMonomers } from '../utils/utils';
 
 
 category('activityCliffs', async () => {
@@ -31,9 +32,11 @@ category('activityCliffs', async () => {
     const options = {
       'SPE': {cycles: 2000, lambda: 1.0, dlambda: 0.0005},
     };
+    const encodedCol = encodeMonomers(actCliffsDf.col('MSA')!) as DG.Column;
     const scatterPlot = await getActivityCliffs(
       actCliffsDf,
       actCliffsDf.col('MSA')!,
+      encodedCol,
       axesNames,
       'Activity cliffs',
       actCliffsDf.col('Activity')!,

package/src/tests/convert-test.ts

@@ -4,7 +4,8 @@ import * as grok from 'datagrok-api/grok';
 import * as DG from 'datagrok-api/dg';
 
 import {ConverterFunc} from './types';
-import {NOTATION, NotationConverter} from '@datagrok-libraries/bio/src/utils/notation-converter';
+import {NotationConverter} from '@datagrok-libraries/bio/src/utils/notation-converter';
+import {NOTATION} from '@datagrok-libraries/bio/src/utils/units-handler';
 
 // import {mmSemType} from '../const';
 // import {importFasta} from '../package';

package/src/tests/detectors-test.ts

@@ -14,6 +14,13 @@ category('detectors', () => {
 2
 3`;
 
+  const csvDfEmpty: string = `id,col1
+1,
+2,
+3,
+4,
+5,`;
+
   const csvDf2: string = `col1
 4
 5
@@ -179,6 +186,7 @@ MWRSWY-CKHP
     };
   };
 
+  test('NegativeEmpty', async () => {await _testNeg(readCsv('csvDfEmpty', csvDfEmpty), 'col1'); });
   test('Negative1', async () => { await _testNeg(readCsv('csvDf1', csvDf1), 'col1'); });
   test('Negative2', async () => { await _testNeg(readCsv('csvDf2', csvDf2), 'col1'); });
   test('Negative3', async () => { await _testNeg(readCsv('csvDf3', csvDf3), 'col1'); });

package/src/tests/renderers-test.ts

@@ -5,7 +5,7 @@ import * as DG from 'datagrok-api/dg';
 import {importFasta, multipleSequenceAlignmentAny} from '../package';
 import {readDataframe} from './utils';
 import {convertDo} from '../utils/convert';
-import {NOTATION} from '@datagrok-libraries/bio/src/utils/notation-converter';
+import {NOTATION} from '@datagrok-libraries/bio/src/utils/units-handler';
 
 category('renderers', () => {
   let tvList: DG.TableView[];

package/src/utils/convert.ts

@@ -4,7 +4,8 @@ import * as grok from 'datagrok-api/grok';
 import $ from 'cash-dom';
 
 import {Subscription} from 'rxjs';
-import {NotationConverter, NOTATION} from '@datagrok-libraries/bio/src/utils/notation-converter';
+import {NotationConverter} from '@datagrok-libraries/bio/src/utils/notation-converter';
+import {NOTATION} from '@datagrok-libraries/bio/src/utils/units-handler';
 
 
 let convertDialog: DG.Dialog | null = null;
@@ -17,7 +18,7 @@ let convertDialogSubs: Subscription[] = [];
  */
 export function convert(col: DG.Column): void {
   const converter = new NotationConverter(col);
-  const current: NOTATION = converter.sourceNotation;
+  const currentNotation: NOTATION = converter.notation;
   //TODO: read all notations
   const notations = [
     NOTATION.FASTA,
@@ -25,7 +26,7 @@ export function convert(col: DG.Column): void {
     NOTATION.HELM
   ];
   const separatorArray = ['-', '.', '/'];
-  const filteredNotations = notations.filter((e) => e !== current);
+  const filteredNotations = notations.filter((e) => e !== currentNotation);
   const targetNotationInput = ui.choiceInput('Convert to', filteredNotations[0], filteredNotations);
 
   const separatorInput = ui.choiceInput('Separator', separatorArray[0], separatorArray);
@@ -48,7 +49,7 @@ export function convert(col: DG.Column): void {
   if (convertDialog == null) {
     convertDialog = ui.dialog('Convert sequence notation')
       .add(ui.div([
-        ui.h1('Current notation: ' + current),
+        ui.h1('Current notation: ' + currentNotation),
         targetNotationInput.root,
         separatorInput.root
       ]))

package/src/utils/utils.ts

@@ -2,7 +2,7 @@ import * as DG from 'datagrok-api/dg';
 import {WebLogo, SplitterFunc} from '@datagrok-libraries/bio/src/viewers/web-logo';
 import * as grok from 'datagrok-api/grok';
 import {
-  CAP_GROUP_NAME, CAP_GROUP_SMILES, jsonSdfMonomerLibDict, MONOMER_SYMBOL,
+  CAP_GROUP_NAME, CAP_GROUP_SMILES, jsonSdfMonomerLibDict, MONOMER_ENCODE_MAX, MONOMER_ENCODE_MIN, MONOMER_SYMBOL,
   RGROUP_ALTER_ID, RGROUP_FIELD, RGROUP_LABEL, SDF_MONOMER_NAME
 } from '../const';
 
@@ -11,6 +11,33 @@ export const HELM_CORE_LIB_MONOMER_SYMBOL = 'symbol';
 export const HELM_CORE_LIB_MOLFILE = 'molfile';
 export const HELM_CORE_FIELDS = ['symbol', 'molfile', 'rgroups', 'name'];
 
+
+export function encodeMonomers(col: DG.Column): DG.Column | null {
+  let encodeSymbol = MONOMER_ENCODE_MIN;
+  const monomerSymbolDict:  { [key: string]: number }= {};
+  const units = col.tags[DG.TAGS.UNITS];
+  const sep = col.getTag('separator');
+  const splitterFunc: SplitterFunc = WebLogo.getSplitter(units, sep);
+  const encodedStringArray = [];
+  for (let i = 0; i < col.length; ++i) {
+    let encodedMonomerStr = '';
+    const monomers = splitterFunc(col.get(i));
+    monomers.forEach(m => {
+      if(!monomerSymbolDict[m]) {
+        if(encodeSymbol > MONOMER_ENCODE_MAX) {
+          grok.shell.error(`Not enougth symbols to encode monomers`);
+          return null;
+        }
+        monomerSymbolDict[m] = encodeSymbol;
+        encodeSymbol++;
+      }
+      encodedMonomerStr += String.fromCodePoint(monomerSymbolDict[m]);
+    })
+    encodedStringArray.push(encodedMonomerStr);
+  }
+  return DG.Column.fromStrings('encodedMolecules', encodedStringArray);
+}
+
 export function getMolfilesFromSeq(col: DG.Column, monomersLibObject: any[]): any[][] | null {
   const units = col.tags[DG.TAGS.UNITS];
   const sep = col.getTag('separator');
@@ -18,7 +45,8 @@ export function getMolfilesFromSeq(col: DG.Column, monomersLibObject: any[]): an
   const monomersDict = createMomomersMolDict(monomersLibObject);
   const molFiles = [];
   for (let i = 0; i < col.length; ++i) {
-    const monomers = splitterFunc(col.get(i));
+    const macroMolecule = col.get(i);
+    const monomers = splitterFunc(macroMolecule);
     const molFilesForSeq = [];
     for (let j = 0; j < monomers.length; ++j) {
       if (monomers[j]) {
@@ -34,6 +62,28 @@ export function getMolfilesFromSeq(col: DG.Column, monomersLibObject: any[]): an
   return molFiles;
 }
 
+export function getMolfilesFromSingleSeq(cell: DG.Cell, monomersLibObject: any[]): any[][] | null {
+  const units = cell.column.tags[DG.TAGS.UNITS];
+  const sep = cell.column!.getTag('separator');
+  const splitterFunc: SplitterFunc = WebLogo.getSplitter(units, sep);
+  const monomersDict = createMomomersMolDict(monomersLibObject);
+  const molFiles = [];
+  const macroMolecule = cell.value;
+  const monomers = splitterFunc(macroMolecule);
+  const molFilesForSeq = [];
+  for (let j = 0; j < monomers.length; ++j) {
+    if (monomers[j]) {
+      if (!monomersDict[monomers[j]]) {
+        grok.shell.warning(`Monomer ${monomers[j]} is missing in HELM library. Structure cannot be created`);
+        return null;
+      }
+      molFilesForSeq.push(JSON.parse(JSON.stringify(monomersDict[monomers[j]])));
+    }
+  }
+  molFiles.push(molFilesForSeq);
+  return molFiles;
+}
+
 export function createMomomersMolDict(lib: any[]): { [key: string]: string | any } {
   const dict: { [key: string]: string | any } = {};
   lib.forEach((it) => {
@@ -79,4 +129,4 @@ export function createJsonMonomerLibFromSdf(table: DG.DataFrame): any {
     resultLib.push(monomer);
   }
   return resultLib;
-}
+}

package/src/widgets/representations.ts

@@ -0,0 +1,54 @@
+import * as grok from 'datagrok-api/grok';
+import * as ui from 'datagrok-api/ui';
+import * as DG from 'datagrok-api/dg';
+import {getMolfilesFromSingleSeq, HELM_CORE_LIB_FILENAME} from '../utils/utils';
+import {getMacroMol} from '../utils/atomic-works';
+
+/**
+ * 3D representation widget of macromolecule.
+ *
+ * @export
+ * @param {DG.Cell} macroMolecule macromolecule cell.
+ * @return {Promise<DG.Widget>} Widget.
+ */
+export async function representationsWidget(macroMolecule: DG.Cell, monomersLibObject: any[]): Promise<DG.Widget> {
+  const pi = DG.TaskBarProgressIndicator.create('Creating 3D view');
+
+  let widgetHost;
+  let molBlock3D = '';
+  try {
+    try {
+      const atomicCodes = getMolfilesFromSingleSeq(macroMolecule, monomersLibObject);
+      const result = await getMacroMol(atomicCodes!);
+      const molBlock2D = result[0];
+      molBlock3D = (await grok.functions.call('Bio:Embed', {molBlock2D})) as string;
+    } catch (e) {
+      console.warn(e);
+    }
+
+    try {
+      molBlock3D = molBlock3D.replaceAll('\\n', '\n');
+      const stringBlob = new Blob([molBlock3D], {type: 'text/plain'});
+      const nglHost = ui.div([], {classes: 'd4-ngl-viewer', id: 'ngl-3d-host'});
+
+      //@ts-ignore
+      const stage = new NGL.Stage(nglHost, {backgroundColor: 'white'});
+      //@ts-ignore
+      stage.loadFile(stringBlob, {ext: 'sdf'}).then(function(comp: NGL.StructureComponent) {
+        stage.setSize(300, 300);
+        comp.addRepresentation('ball+stick');
+        comp.autoView();
+      });
+      const sketch = grok.chem.svgMol(molBlock3D);
+      const panel = ui.divH([sketch]);
+
+      widgetHost = ui.div([panel, nglHost]);
+    } catch (e) {
+      widgetHost = ui.divText('Couldn\'t get peptide structure');
+    }
+  } catch (e) {
+    widgetHost = ui.divText('Couldn\'t get peptide structure');
+  }
+  pi.close();
+  return new DG.Widget(widgetHost);
+}

package/{test-Bio-34f75e5127b8-f542cbde.html → test-Bio-34f75e5127b8-92b3a565.html}

@@ -1,4 +1,4 @@
-<html><head><meta charset="utf-8"/><title>Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=34f75e5127b8. Commit f542cbde.</title><style type="text/css">html,
+<html><head><meta charset="utf-8"/><title>Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=34f75e5127b8. Commit 92b3a565.</title><style type="text/css">html,
 body {
   font-family: Arial, Helvetica, sans-serif;
   font-size: 1rem;
@@ -229,7 +229,8 @@ header {
   font-size: 1rem;
   padding: 0 0.5rem;
 }
-</style></head><body><div id="jesthtml-content"><header><h1 id="title">Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=34f75e5127b8. Commit f542cbde.</h1></header><div id="metadata-container"><div id="timestamp">Started: 2022-07-20 17:49:40</div><div id="summary"><div id="suite-summary"><div class="summary-total">Suites (1)</div><div class="summary-passed summary-empty">0 passed</div><div class="summary-failed">1 failed</div><div class="summary-pending summary-empty">0 pending</div></div><div id="test-summary"><div class="summary-total">Tests (1)</div><div class="summary-passed summary-empty">0 passed</div><div class="summary-failed">1 failed</div><div class="summary-pending summary-empty">0 pending</div></div></div></div><div id="suite-1" class="suite-container"><div class="suite-info"><div class="suite-path">/home/runner/work/public/public/packages/Bio/src/__jest__/remote.test.ts</div><div class="suite-time warn">209.758s</div></div><div class="suite-tests"><div class="test-result failed"><div class="test-info"><div class="test-suitename"> </div><div class="test-title">TEST</div><div class="test-status">failed</div><div class="test-duration">199.086s</div></div><div class="failureMessages"> <pre class="failureMsg">Error: Test result : Bio.MSA.is_correct : TypeError: Cannot read properties of undefined (reading 'split')
+</style></head><body><div id="jesthtml-content"><header><h1 id="title">Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=34f75e5127b8. Commit 92b3a565.</h1></header><div id="metadata-container"><div id="timestamp">Started: 2022-07-27 15:30:45</div><div id="summary"><div id="suite-summary"><div class="summary-total">Suites (1)</div><div class="summary-passed summary-empty">0 passed</div><div class="summary-failed">1 failed</div><div class="summary-pending summary-empty">0 pending</div></div><div id="test-summary"><div class="summary-total">Tests (1)</div><div class="summary-passed summary-empty">0 passed</div><div class="summary-failed">1 failed</div><div class="summary-pending summary-empty">0 pending</div></div></div></div><div id="suite-1" class="suite-container"><div class="suite-info"><div class="suite-path">/home/runner/work/public/public/packages/Bio/src/__jest__/remote.test.ts</div><div class="suite-time warn">209.012s</div></div><div class="suite-tests"><div class="test-result failed"><div class="test-info"><div class="test-suitename"> </div><div class="test-title">TEST</div><div class="test-status">failed</div><div class="test-duration">198.977s</div></div><div class="failureMessages"> <pre class="failureMsg">Error: Test result : Bio.MSA.is_correct : TypeError: Cannot read properties of undefined (reading 'split')
+Test result : Bio.activityCliffs.activityCliffsOpen : Error: Expected "105 cliffs", got "2362 cliffs"
 
     at /home/runner/work/public/public/packages/Bio/src/__jest__/remote.test.ts:67:20
     at Generator.next (&lt;anonymous&gt;)
@@ -262,6 +263,7 @@ Test result : Bio.WebLogo.monomerToText.longMonomerComplexFirstPartShort : OK
 Test result : Bio.WebLogo.monomerToText.longMonomerComplexFirstPartLong56 : OK
 Test result : Bio.Palettes.testPaletteN : OK
 Test result : Bio.Palettes.testPaletteAA : OK
+Test result : Bio.detectors.NegativeEmpty : OK
 Test result : Bio.detectors.Negative1 : OK
 Test result : Bio.detectors.Negative2 : OK
 Test result : Bio.detectors.Negative3 : OK
@@ -310,7 +312,6 @@ Test result : Bio.detectors.samplesTestUnichemSourcesNegativeSrcUrl : OK
 Test result : Bio.detectors.samplesTestUnichemSourcesNegativeBaseIdUrl : OK
 Test result : Bio.MSA.test_table.is_not_empty : OK
 Test result : Bio.sequenceSpace.sequenceSpaceOpens : OK
-Test result : Bio.activityCliffs.activityCliffsOpen : OK
 Test result : Bio.splitters.helm1 : OK
 Test result : Bio.splitters.helm2 : OK
 Test result : Bio.splitters.helm3-multichar : OK