@datagrok/bio 1.10.2 → 1.11.0

package/package.json

@@ -5,7 +5,7 @@
     "name": "Leonid Stolbov",
     "email": "lstolbov@datagrok.ai"
   },
-  "version": "1.10.2",
+  "version": "1.11.0",
   "description": "Bio is a [package](https://datagrok.ai/help/develop/develop#packages) for the [Datagrok](https://datagrok.ai) platform",
   "repository": {
     "type": "git",
@@ -14,12 +14,12 @@
   },
   "dependencies": {
     "@biowasm/aioli": ">=2.4.0",
-    "@datagrok-libraries/bio": "^4.1.0",
+    "@datagrok-libraries/bio": "^4.2.0",
     "@datagrok-libraries/chem-meta": "1.0.0",
     "@datagrok-libraries/ml": "^4.0.0",
     "@datagrok-libraries/utils": "^1.6.2",
     "cash-dom": "latest",
-    "datagrok-api": "^1.5.5",
+    "datagrok-api": "^1.6.6",
     "dayjs": "^1.11.4",
     "openchemlib": "6.0.1",
     "rxjs": "^6.5.5",
@@ -69,11 +69,7 @@
     "Developers"
   ],
   "sources": [
-    "css/helm.css",
-    "https://ajax.googleapis.com/ajax/libs/dojo/1.10.4/dojo/dojo.js",
-    "helm/JSDraw/Scilligence.JSDraw2.Lite.js",
-    "helm/JSDraw/Scilligence.JSDraw2.Resources.js",
-    "helm/JSDraw/Pistoia.HELM-uncompressed.js"
+    "css/helm.css"
   ],
   "category": "Bioinformatics"
 }

package/src/package-test.ts

@@ -13,6 +13,7 @@ import './tests/renderers-test';
 import './tests/convert-test';
 import './tests/fasta-handler-test';
 import './tests/WebLogo-positions-test';
+import './tests/checkInputColumn-tests'
 
 export const _package = new DG.Package();
 export {tests};

package/src/package.ts

@@ -30,6 +30,9 @@ import {
   performanceTest
 } from './tests/test-sequnces-generators';
 
+import {splitAlignedSequences} from '@datagrok-libraries/bio/src/utils/splitter';
+import * as C from './utils/constants';
+
 //tags: init
 export async function initBio() {
 }
@@ -63,29 +66,50 @@ export function separatorSequenceCellRenderer(): MacromoleculeSequenceCellRender
   return new MacromoleculeSequenceCellRenderer();
 }
 
-function checkInputColumn(col: DG.Column, name: string,
-  allowedNotations: string[] = [], allowedAlphabets: string[] = []): boolean {
-  const notation: string = col.getTag(DG.TAGS.UNITS);
-  const alphabet: string = col.getTag('alphabet');
+function checkInputColumnUi(
+  col: DG.Column, name: string, allowedNotations: string[] = [], allowedAlphabets: string[] = []
+): boolean {
+  const [res, msg]: [boolean, string] = checkInputColumn(col, name, allowedNotations, allowedAlphabets);
+  if (!res)
+    grok.shell.warning(msg);
+  return res;
+}
+
+export function checkInputColumn(
+  col: DG.Column, name: string, allowedNotations: string[] = [], allowedAlphabets: string[] = []
+): [boolean, string] {
+  let res: boolean = true;
+  let msg: string = '';
+
+  const uh = new UnitsHandler(col);
   if (col.semType !== DG.SEMTYPE.MACROMOLECULE) {
     grok.shell.warning(name + ' analysis is allowed for Macromolecules semantic type');
-    return false;
-  } else if (
-    (allowedAlphabets.length > 0 &&
-      !allowedAlphabets.some((a) => alphabet.toUpperCase() == (a.toUpperCase()))) ||
-    (allowedNotations.length > 0 &&
-      !allowedNotations.some((n) => notation.toUpperCase() == (n.toUpperCase())))
-  ) {
-    const notationAdd = allowedNotations.length == 0 ? 'any notation' :
-      (`notation${allowedNotations.length > 1 ? 's' : ''} ${allowedNotations.map((n) => `"${n}"`).join(', ')} `);
-    const alphabetAdd = allowedNotations.length == 0 ? 'any alphabet' :
-      (`alphabet${allowedAlphabets.length > 1 ? 's' : ''} ${allowedAlphabets.map((a) => `"${a}"`).join(', ')}.`);
-
-    grok.shell.warning(name + ' analysis is allowed for Macromolecules with ' + notationAdd + ' and ' + alphabetAdd);
-    return false;
+    res = false;
+  } else {
+    const notation: string = uh.notation;
+    if (allowedNotations.length > 0 &&
+      !allowedNotations.some((n) => notation.toUpperCase() == (n.toUpperCase()))
+    ) {
+      const notationAdd = allowedNotations.length == 0 ? 'any notation' :
+        (`notation${allowedNotations.length > 1 ? 's' : ''} ${allowedNotations.map((n) => `"${n}"`).join(', ')} `);
+      msg = `${name} + ' analysis is allowed for Macromolecules with notation ${notationAdd}.`;
+      res = false;
+    } else if (!uh.isHelm()) {
+      // alphabet is not specified for 'helm' notation
+      const alphabet: string = uh.alphabet;
+      if (
+        allowedAlphabets.length > 0 &&
+        !allowedAlphabets.some((a) => alphabet.toUpperCase() == (a.toUpperCase()))
+      ) {
+        const alphabetAdd = allowedAlphabets.length == 0 ? 'any alphabet' :
+          (`alphabet${allowedAlphabets.length > 1 ? 's' : ''} ${allowedAlphabets.map((a) => `"${a}"`).join(', ')}.`);
+        msg = `${name} + ' analysis is allowed for Macromolecules with alphabet ${alphabetAdd}.`;
+        res = false;
+      }
+    }
   }
 
-  return true;
+  return [res, msg];
 }
 
 //name: sequenceAlignment
@@ -128,7 +152,7 @@ export function vdRegionViewer() {
 //input: string methodName { choices:["UMAP", "t-SNE", "SPE"] }
 export async function activityCliffs(df: DG.DataFrame, macroMolecule: DG.Column, activities: DG.Column,
   similarity: number, methodName: string): Promise<DG.Viewer | undefined> {
-  if (!checkInputColumn(macroMolecule, 'Activity Cliffs'))
+  if (!checkInputColumnUi(macroMolecule, 'Activity Cliffs'))
     return;
   const encodedCol = encodeMonomers(macroMolecule);
   if (!encodedCol)
@@ -171,7 +195,7 @@ export async function activityCliffs(df: DG.DataFrame, macroMolecule: DG.Column,
 //input: bool plotEmbeddings = true
 export async function sequenceSpaceTopMenu(table: DG.DataFrame, macroMolecule: DG.Column, methodName: string,
   similarityMetric: string = 'Levenshtein', plotEmbeddings: boolean): Promise<DG.Viewer | undefined> {
-  if (!checkInputColumn(macroMolecule, 'Activity Cliffs'))
+  if (!checkInputColumnUi(macroMolecule, 'Activity Cliffs'))
     return;
   const encodedCol = encodeMonomers(macroMolecule);
   if (!encodedCol)
@@ -213,7 +237,7 @@ export async function toAtomicLevel(df: DG.DataFrame, macroMolecule: DG.Column):
     grok.shell.warning('Transformation to atomic level requires package "Chem" installed.');
     return;
   }
-  if (!checkInputColumn(macroMolecule, 'To Atomic Level'))
+  if (!checkInputColumnUi(macroMolecule, 'To Atomic Level'))
     return;
 
   const monomersLibFile = await _package.files.readAsText(HELM_CORE_LIB_FILENAME);
@@ -232,10 +256,12 @@ export async function toAtomicLevel(df: DG.DataFrame, macroMolecule: DG.Column):
 //top-menu: Bio | MSA...
 //name: MSA
 //input: dataframe table
-//input: column sequence { semType: Macromolecule }
+//input: column sequence { semType: Macromolecule, units: ['fasta'], alphabet: ['DNA', 'RNA', 'PT'] }
 //output: column result
 export async function multipleSequenceAlignmentAny(table: DG.DataFrame, col: DG.Column): Promise<DG.Column | null> {
-  if (!checkInputColumn(col, 'MSA', ['fasta'], ['DNA', 'RNA', 'PT']))
+  const func: DG.Func = DG.Func.find({package: 'Bio', name: 'multipleSequenceAlignmentAny'})[0];
+
+  if (!checkInputColumnUi(col, 'MSA', ['fasta'], ['DNA', 'RNA', 'PT']))
     return null;
 
   const unUsedName = table.columns.getUnusedName(`msa(${col.name})`);
@@ -276,7 +302,7 @@ export async function compositionAnalysis(): Promise<void> {
   });
 
   const handler = async (col: DG.Column) => {
-    if (!checkInputColumn(col, 'Composition'))
+    if (!checkInputColumnUi(col, 'Composition'))
       return;
 
     const wlViewer = tv.addViewer('WebLogo', {sequenceColumnName: col.name});
@@ -391,11 +417,11 @@ export async function testDetectMacromolecule(path: string): Promise<DG.DataFram
           //console.warn(`file: ${fileInfo.path}, column: ${col.name}, ` +
           //  `semType: ${semType}, units: ${col.getTag(DG.TAGS.UNITS)}`);
           // console.warn('file: "' + fileInfo.path + '", semType: "' + semType + '", ' +
-          //   'units: "' + col.getTag('units') + '"');
+          //   'units: "' + col.getTag(DG.TAGS.UNITS) + '"');
 
           res.push({
             file: fileInfo.path, result: 'detected', column: col.name,
-            message: `units: ${col.getTag('units')}`
+            message: `units: ${col.getTag(DG.TAGS.UNITS)}`
           });
         }
       }
@@ -418,3 +444,19 @@ export async function testDetectMacromolecule(path: string): Promise<DG.DataFram
   return resDf;
 }
 
+//name: Bio | Split to monomers
+//tags: panel, bio
+//input: column col {semType: Macromolecule}
+export function splitToMonomers(col: DG.Column<string>): void {
+  if (!col.getTag(UnitsHandler.TAGS.aligned).includes(C.MSA))
+    return grok.shell.error('Splitting is applicable only for aligned sequences');
+
+  const tempDf = splitAlignedSequences(col);
+  const originalDf = col.dataFrame;
+  for (const tempCol of tempDf.columns) {
+    const newCol = originalDf.columns.add(tempCol);
+    newCol.semType = C.SEM_TYPES.MONOMER;
+    // newCol.setTag(DG.TAGS.CELL_RENDERER, C.SEM_TYPES.MONOMER);
+    newCol.setTag(C.TAGS.ALPHABET, col.getTag(C.TAGS.ALPHABET));
+  }
+}

package/src/tests/WebLogo-positions-test.ts

@@ -5,6 +5,7 @@ import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
 import {PositionInfo, PositionMonomerInfo, WebLogo} from '@datagrok-libraries/bio/src/viewers/web-logo';
 import {Column} from 'datagrok-api/dg';
+import {ALPHABET, NOTATION, UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
 
 category('WebLogo-positions', () => {
   let tvList: DG.TableView[];
@@ -35,9 +36,9 @@ ATC-G-TTGC--
     const tv: DG.TableView = grok.shell.addTableView(df);
 
     const seqCol: DG.Column = df.getCol('seq');
-    seqCol.semType = 'Macromolecule';
-    seqCol.setTag('units', 'fasta');
-    seqCol.setTag('alphabet', 'DNA');
+    seqCol.semType = DG.SEMTYPE.MACROMOLECULE;
+    seqCol.setTag(DG.TAGS.UNITS, NOTATION.FASTA);
+    seqCol.setTag(UnitsHandler.TAGS.alphabet, ALPHABET.DNA);
 
     const wlViewer: WebLogo = await df.plot.fromType('WebLogo') as unknown as WebLogo;
     tv.dockManager.dock(wlViewer.root, DG.DOCK_TYPE.DOWN);
@@ -84,9 +85,9 @@ ATC-G-TTGC--
     const tv: DG.TableView = grok.shell.addTableView(df);
 
     const seqCol: DG.Column = df.getCol('seq');
-    seqCol.semType = 'Macromolecule';
-    seqCol.setTag('units', 'fasta');
-    seqCol.setTag('alphabet', 'DNA');
+    seqCol.semType = DG.SEMTYPE.MACROMOLECULE;
+    seqCol.setTag(DG.TAGS.UNITS, NOTATION.FASTA);
+    seqCol.setTag(UnitsHandler.TAGS.alphabet, ALPHABET.DNA);
 
     df.filter.init((i) => {
       return i > 2;
@@ -129,9 +130,9 @@ ATC-G-TTGC--
     const tv: DG.TableView = grok.shell.addTableView(df);
 
     const seqCol: DG.Column = df.getCol('seq');
-    seqCol.semType = 'Macromolecule';
-    seqCol.setTag('units', 'fasta');
-    seqCol.setTag('alphabet', 'DNA');
+    seqCol.semType = DG.SEMTYPE.MACROMOLECULE;
+    seqCol.setTag(DG.TAGS.UNITS, NOTATION.FASTA);
+    seqCol.setTag(UnitsHandler.TAGS.alphabet, ALPHABET.DNA);
 
     const wlViewer: WebLogo = await df.plot.fromType('WebLogo', {'skipEmptyPositions': true}) as unknown as WebLogo;
     tv.dockManager.dock(wlViewer.root, DG.DOCK_TYPE.DOWN);

package/src/tests/checkInputColumn-tests.ts

@@ -0,0 +1,69 @@
+import {after, before, category, test, expect, expectArray} from '@datagrok-libraries/utils/src/test';
+
+import * as grok from 'datagrok-api/grok';
+import * as ui from 'datagrok-api/ui';
+import * as DG from 'datagrok-api/dg';
+
+import {checkInputColumn} from '../package';
+import {UNITS} from 'datagrok-api/dg';
+import {ALPHABET, UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
+
+
+category('checkInputColumn', () => {
+
+  const csv = `seq
+seq1,
+seq2,
+seq3,
+seq4`;
+
+  category('MSA', () => {
+
+    test('testMsaPos', async () => {
+      const func: DG.Func = DG.Func.find({package: 'Bio', name: 'multipleSequenceAlignmentAny'})[0];
+      const funcInputColumnProperty: DG.Property = func.inputs.find((i) => i.name == 'sequence')!;
+
+      let k = 11;
+
+      const df: DG.DataFrame = DG.DataFrame.fromCsv(csv);
+      const col: DG.Column = df.getCol('seq');
+      col.semType = DG.SEMTYPE.MACROMOLECULE;
+      col.setTag(DG.TAGS.UNITS, 'fasta');
+      col.setTag(UnitsHandler.TAGS.alphabet, ALPHABET.DNA);
+
+      const [res, msg]: [boolean, string] = checkInputColumn(
+        col, 'Test', ['fasta',], ['DNA', 'RNA', 'PT']);
+
+      expect(res, true);
+    });
+
+    test('testMsaNegHelm', async () => {
+      const df: DG.DataFrame = DG.DataFrame.fromCsv(csv);
+      const col: DG.Column = df.getCol('seq');
+      col.semType = DG.SEMTYPE.MACROMOLECULE;
+      col.setTag(DG.TAGS.UNITS, 'helm');
+      col.setTag(UnitsHandler.TAGS.alphabetSize, '11');
+      col.setTag(UnitsHandler.TAGS.alphabetIsMultichar, 'true');
+
+      const [res, msg]: [boolean, string] = checkInputColumn(
+        col, 'Test', ['fasta',], ['DNA', 'RNA', 'PT']);
+
+      expect(res, false);
+    });
+
+    test('testMsaNegUN', async () => {
+      const df: DG.DataFrame = DG.DataFrame.fromCsv(csv);
+      const col: DG.Column = df.getCol('seq');
+      col.semType = DG.SEMTYPE.MACROMOLECULE;
+      col.setTag(DG.TAGS.UNITS, 'fasta');
+      col.setTag(UnitsHandler.TAGS.alphabet, 'UN');
+      col.setTag(UnitsHandler.TAGS.alphabetSize, '11');
+      col.setTag(UnitsHandler.TAGS.alphabetIsMultichar, 'true');
+
+      const [res, msg]: [boolean, string] = checkInputColumn(
+        col, 'Test', ['fasta',], ['DNA', 'RNA', 'PT']);
+
+      expect(res, false);
+    });
+  });
+});

package/src/tests/detectors-test.ts

@@ -400,10 +400,10 @@ export async function _testPos(
 
   expect(col.semType === DG.SEMTYPE.MACROMOLECULE, true);
   expect(col.getTag(DG.TAGS.UNITS), units);
-  expect(col.getTag('aligned'), aligned);
-  expect(col.getTag('alphabet'), alphabet);
+  expect(col.getTag(UnitsHandler.TAGS.aligned), aligned);
+  expect(col.getTag(UnitsHandler.TAGS.alphabet), alphabet);
   if (separator)
-    expect(col.getTag('separator'), separator);
+    expect(col.getTag(UnitsHandler.TAGS.separator), separator);
 
   const uh = new UnitsHandler(col);
   expect(uh.getAlphabetSize(), alphabetSize);

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/units-handler';
+import {ALPHABET, NOTATION, UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
 
 category('renderers', () => {
   let tvList: DG.TableView[];
@@ -42,21 +42,21 @@ category('renderers', () => {
 
     console.log('Bio: tests/renderers/afterMsa, src before test ' +
       `semType="${srcSeqCol!.semType}", units="${srcSeqCol!.getTag(DG.TAGS.UNITS)}", ` +
-      `cell.renderer="${srcSeqCol!.getTag('cell.renderer')}"`);
+      `cell.renderer="${srcSeqCol!.getTag(DG.TAGS.CELL_RENDERER)}"`);
     expect(srcSeqCol!.semType, DG.SEMTYPE.MACROMOLECULE);
-    expect(srcSeqCol!.getTag(DG.TAGS.UNITS), 'fasta');
-    expect(srcSeqCol!.getTag('aligned'), 'SEQ');
-    expect(srcSeqCol!.getTag('alphabet'), 'PT');
-    expect(srcSeqCol!.getTag('cell.renderer'), 'sequence');
+    expect(srcSeqCol!.getTag(DG.TAGS.UNITS), NOTATION.FASTA);
+    expect(srcSeqCol!.getTag(UnitsHandler.TAGS.aligned), 'SEQ');
+    expect(srcSeqCol!.getTag(UnitsHandler.TAGS.alphabet), ALPHABET.PT);
+    expect(srcSeqCol!.getTag(DG.TAGS.CELL_RENDERER), 'sequence');
 
     const msaSeqCol: DG.Column | null = await multipleSequenceAlignmentAny(df, srcSeqCol!);
     tv.grid.invalidate();
-    
+
     expect(msaSeqCol!.semType, DG.SEMTYPE.MACROMOLECULE);
-    expect(msaSeqCol!.getTag(DG.TAGS.UNITS), 'fasta');
-    expect(msaSeqCol!.getTag('aligned'), 'SEQ.MSA');
-    expect(msaSeqCol!.getTag('alphabet'), 'PT');
-    expect(msaSeqCol!.getTag('cell.renderer'), 'sequence');
+    expect(msaSeqCol!.getTag(DG.TAGS.UNITS), NOTATION.FASTA);
+    expect(msaSeqCol!.getTag(UnitsHandler.TAGS.aligned), 'SEQ.MSA');
+    expect(msaSeqCol!.getTag(UnitsHandler.TAGS.alphabet), ALPHABET.PT);
+    expect(msaSeqCol!.getTag(DG.TAGS.CELL_RENDERER), 'sequence');
 
     dfList.push(df);
     tvList.push(tv);
@@ -70,7 +70,7 @@ category('renderers', () => {
 
     const srcCol: DG.Column = df.col('sequence')!;
     const tgtCol: DG.Column = await convertDo(srcCol, NOTATION.SEPARATOR, '/');
-    expect(tgtCol.getTag('cell.renderer'), 'sequence');
+    expect(tgtCol.getTag(DG.TAGS.CELL_RENDERER), 'sequence');
 
     tvList.push(tv);
     dfList.push(df);

package/src/tests/splitters-test.ts

@@ -4,6 +4,8 @@ import * as grok from 'datagrok-api/grok';
 import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
 import {WebLogo, SplitterFunc} from '@datagrok-libraries/bio/src/viewers/web-logo';
+import {splitToMonomers, _package} from '../package';
+import * as C from '../utils/constants';
 
 category('splitters', () => {
   const helm1 = '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}$$$';
@@ -51,6 +53,19 @@ category('splitters', () => {
   test('testHelm1', async () => { await _testHelmSplitter(data.testHelm1[0], data.testHelm1[1]); });
   test('testHelm2', async () => { await _testHelmSplitter(data.testHelm2[0], data.testHelm2[1]); });
   test('testHelm3', async () => { await _testHelmSplitter(data.testHelm3[0], data.testHelm3[1]); });
+
+  test('splitToMonomers', async () => {
+    const df: DG.DataFrame = await grok.dapi.files.readCsv('System:AppData/Bio/samples/sample_MSA.csv');
+
+    const seqCol = df.getCol('MSA');
+    const semType = await grok.functions.call('Bio:detectMacromolecule', {col: seqCol});
+    if (semType)
+      seqCol.semType = semType;
+    seqCol.setTag(C.TAGS.ALIGNED, C.MSA);
+
+    splitToMonomers(seqCol);
+    expect(df.columns.names().includes('17'), true);
+  });
 });
 
 export async function _testHelmSplitter(src: string, tgt: string[]) {

package/src/utils/cell-renderer.ts

@@ -7,6 +7,7 @@ import {SplitterFunc, WebLogo} from '@datagrok-libraries/bio/src/viewers/web-log
 import {SeqPalette} from '@datagrok-libraries/bio/src/seq-palettes';
 import * as ui from 'datagrok-api/ui';
 import {printLeftOrCentered, DrawStyle} from '@datagrok-libraries/bio/src/utils/cell-renderer';
+import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
 
 const undefinedColor = 'rgb(100,100,100)';
 const monomerToShortFunction: (amino: string, maxLengthOfMonomer: number) => string = WebLogo.monomerToShort;
@@ -57,7 +58,7 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
   get defaultWidth(): number { return 230; }
 
   onMouseMove(gridCell: DG.GridCell, e: MouseEvent): void {
-    if (gridCell.cell.column.getTag('aligned') !== 'SEQ.MSA') {
+    if (gridCell.cell.column.getTag(UnitsHandler.TAGS.aligned) !== 'SEQ.MSA') {
       return;
     }
     const maxLengthWordsSum = gridCell.cell.column.temp['bio-sum-maxLengthWords'];

package/src/utils/constants.ts

@@ -9,17 +9,13 @@ export enum COLUMNS_NAMES {
   MEAN_DIFFERENCE = 'Mean difference',
 }
 
-export enum CATEGORIES {
-  OTHER = 'Other',
-  ALL = 'All',
-}
-
 export enum TAGS {
   AAR = 'AAR',
   POSITION = 'Pos',
   SEPARATOR = 'separator',
   SELECTION = 'selection',
   ALPHABET = 'alphabet',
+  ALIGNED = 'aligned',
 }
 
 export enum SEM_TYPES {
@@ -30,6 +26,8 @@ export enum SEM_TYPES {
   MACROMOLECULE = 'Macromolecule',
 }
 
+export const MSA = 'MSA';
+
 export const STATS = 'stats';
 
 export const EMBEDDING_STATUS = 'embeddingStatus';

package/src/utils/convert.ts

@@ -42,7 +42,7 @@ export function convert(col: DG.Column): void {
   // set correct visibility on init
   toggleSeparator();
 
-  targetNotationInput.onChanged( () => {
+  targetNotationInput.onChanged(() => {
     toggleSeparator();
   });
 

package/src/utils/multiple-sequence-alignment.ts

@@ -9,6 +9,7 @@ import {FastaFileHandler} from '@datagrok-libraries/bio/src/utils/fasta-handler'
 import Aioli from '@biowasm/aioli';
 
 import {AlignedSequenceEncoder} from '@datagrok-libraries/bio/src/sequence-encoder';
+import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
 
 /**
  * Converts array of sequences into simple fasta string.
@@ -58,14 +59,14 @@ export async function runKalign(srcCol: DG.Column, isAligned = false, unUsedName
   // units
   const srcUnits = srcCol.getTag(DG.TAGS.UNITS);
   //aligned
-  const srcAligned = srcCol.getTag('aligned');
+  const srcAligned = srcCol.getTag(UnitsHandler.TAGS.aligned);
   const tgtAligned = srcAligned + '.MSA';
   //alphabet
-  const srcAlphabet = srcCol.getTag('alphabet');
+  const srcAlphabet = srcCol.getTag(UnitsHandler.TAGS.alphabet);
 
   tgtCol.setTag(DG.TAGS.UNITS, srcUnits);
-  tgtCol.setTag('aligned', tgtAligned);
-  tgtCol.setTag('alphabet', srcAlphabet);
+  tgtCol.setTag(UnitsHandler.TAGS.aligned, tgtAligned);
+  tgtCol.setTag(UnitsHandler.TAGS.alphabet, srcAlphabet);
   tgtCol.semType = DG.SEMTYPE.MACROMOLECULE;
   return tgtCol;
 }

package/src/utils/sequence-space.ts

@@ -16,7 +16,7 @@ export async function sequenceSpace(spaceParams: ISequenceSpaceParams): Promise<
 // code deprecated since seqCol is encoded
 /*    let preparedData: any;
   if (!(spaceParams.seqCol!.tags[DG.TAGS.UNITS] === 'HELM')) {
-    const sep = spaceParams.seqCol.getTag('separator');
+    const sep = spaceParams.seqCol.getTag(UnitsHandler.TAGS.separator);
     const sepFinal = sep ? sep === '.' ? '\\\.' : sep : '-';
     const regex = new RegExp(sepFinal, 'g');
     if (Object.keys(AvailableMetrics['String']).includes(spaceParams.similarityMetric))

package/src/utils/utils.ts

@@ -5,6 +5,7 @@ import {
   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';
+import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
 
 export const HELM_CORE_LIB_FILENAME = '/samples/HELMCoreLibrary.json';
 export const HELM_CORE_LIB_MONOMER_SYMBOL = 'symbol';
@@ -16,7 +17,7 @@ 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 sep = col.getTag(UnitsHandler.TAGS.separator);
   const splitterFunc: SplitterFunc = WebLogo.getSplitter(units, sep);
   const encodedStringArray = [];
   for (let i = 0; i < col.length; ++i) {
@@ -25,7 +26,7 @@ export function encodeMonomers(col: DG.Column): DG.Column | null {
     monomers.forEach((m) => {
       if (!monomerSymbolDict[m]) {
         if (encodeSymbol > MONOMER_ENCODE_MAX) {
-          grok.shell.error(`Not enougth symbols to encode monomers`);
+          grok.shell.error(`Not enough symbols to encode monomers`);
           return null;
         }
         monomerSymbolDict[m] = encodeSymbol;

package/{test-Bio-eb4783c07294-0aa1538b.html → test-Bio-eb4783c07294-8e35df79.html}

@@ -1,4 +1,4 @@
-<html><head><meta charset="utf-8"/><title>Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=eb4783c07294. Commit 0aa1538b.</title><style type="text/css">html,
+<html><head><meta charset="utf-8"/><title>Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=eb4783c07294. Commit 8e35df79.</title><style type="text/css">html,
 body {
   font-family: Arial, Helvetica, sans-serif;
   font-size: 1rem;
@@ -229,7 +229,7 @@ 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=eb4783c07294. Commit 0aa1538b.</h1></header><div id="metadata-container"><div id="timestamp">Started: 2022-09-02 13:13:34</div><div id="summary"><div id="suite-summary"><div class="summary-total">Suites (1)</div><div class="summary-passed">1 passed</div><div class="summary-failed summary-empty">0 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">1 passed</div><div class="summary-failed summary-empty">0 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">45.182s</div></div><div class="suite-tests"><div class="test-result passed"><div class="test-info"><div class="test-suitename"> </div><div class="test-title">TEST</div><div class="test-status">passed</div><div class="test-duration">30.315s</div></div></div></div><div class="suite-consolelog"><div class="suite-consolelog-header">Console Log</div><div class="suite-consolelog-item"><pre class="suite-consolelog-item-origin">    at Object.&lt;anonymous&gt; (/home/runner/work/public/public/packages/Bio/src/__jest__/test-node.ts:63:11)
+</style></head><body><div id="jesthtml-content"><header><h1 id="title">Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=eb4783c07294. Commit 8e35df79.</h1></header><div id="metadata-container"><div id="timestamp">Started: 2022-09-05 13:58:32</div><div id="summary"><div id="suite-summary"><div class="summary-total">Suites (1)</div><div class="summary-passed">1 passed</div><div class="summary-failed summary-empty">0 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">1 passed</div><div class="summary-failed summary-empty">0 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">47.737s</div></div><div class="suite-tests"><div class="test-result passed"><div class="test-info"><div class="test-suitename"> </div><div class="test-title">TEST</div><div class="test-status">passed</div><div class="test-duration">26.873s</div></div></div></div><div class="suite-consolelog"><div class="suite-consolelog-header">Console Log</div><div class="suite-consolelog-item"><pre class="suite-consolelog-item-origin">    at Object.&lt;anonymous&gt; (/home/runner/work/public/public/packages/Bio/src/__jest__/test-node.ts:63:11)
     at Generator.next (&lt;anonymous&gt;)
     at fulfilled (/home/runner/work/public/public/packages/Bio/src/__jest__/test-node.ts:28:58)
     at processTicksAndRejections (internal/process/task_queues.js:97:5)</pre><pre class="suite-consolelog-item-message">Using web root: http://localhost:8080</pre></div><div class="suite-consolelog-item"><pre class="suite-consolelog-item-origin">    at /home/runner/work/public/public/packages/Bio/src/__jest__/remote.test.ts:40:11
@@ -309,6 +309,9 @@ Test result : Success : Bio.detectors.samplesTestDmvOfficesNegativeCity : OK
 Test result : Success : Bio.detectors.samplesTestAlertCollectionNegativeSmarts : OK
 Test result : Success : Bio.MSA.isCorrect : OK
 Test result : Success : Bio.MSA.isCorrectLong : OK
+Test result : Success : Bio.MSA.testMsaPos : OK
+Test result : Success : Bio.MSA.testMsaNegHelm : OK
+Test result : Success : Bio.MSA.testMsaNegUN : OK
 Test result : Success : Bio.sequenceSpace.sequenceSpaceOpens : OK
 Test result : Success : Bio.sequenceSpace.sequenceSpaceOpensWithEmptyRows : OK
 Test result : Success : Bio.activityCliffs.activityCliffsOpen : OK
@@ -319,6 +322,7 @@ Test result : Success : Bio.splitters.helm3-multichar : OK
 Test result : Success : Bio.splitters.testHelm1 : OK
 Test result : Success : Bio.splitters.testHelm2 : OK
 Test result : Success : Bio.splitters.testHelm3 : OK
+Test result : Success : Bio.splitters.splitToMonomers : OK
 Test result : Success : Bio.renderers.afterMsa : OK
 Test result : Success : Bio.renderers.afterConvert : OK
 Test result : Success : Bio.converters.testFastaPtToSeparator : OK

package/src/utils/split-to-monomers.ts

@@ -1,8 +0,0 @@
-/* Do not change these import lines to match external modules in webpack configuration */
-import * as grok from 'datagrok-api/grok';
-import * as ui from 'datagrok-api/ui';
-import * as DG from 'datagrok-api/dg';
-
-export function splitToMonomers() {
-
-}