@datagrok/bio 2.0.26 → 2.0.28

package/files/tests/filter_FASTA.csv

@@ -0,0 +1,14 @@
+fasta
+MDYKETLLMPKTDFPMRGGLPNKEPQIQEKW
+MIEVFLFGIVLGLIPITLAGLFVTAYLQYRRGDQLDL
+MMELVLKTIIGPIVVGVVLRIVDKWLNKDK
+MDRTDEVSNHTHDKPTLTWFEEIFEEYHSPFHN
+MKSTKEEIQTIKTLLKDSRTAKYHKRLQIVL
+MHAILRYFIRRLFYHIFYKIYSLISKKHQSLPSDVRQF
+MSNFHNEHVMQFYRNNLKTKGVFGRQ
+MPNSEPASLLELFNSIATQGELVRSLKAGNASK
+IRVVGRYLIEVWKAAGMDMDKVLFLWSSDEI
+
+
+
+

package/files/tests/filter_HELM.csv

@@ -0,0 +1,5 @@
+HELM string
+"PEPTIDE1{D.E.F.G}|PEPTIDE2{C.E}$PEPTIDE1,PEPTIDE2,2:R3-1:R1$$$V2.0"
+"PEPTIDE1{L.M.P.Q.R.S.T}$PEPTIDE1,PEPTIDE1,7:R2-1:R1$$$"
+"PEPTIDE1{N.P.F.V.L.P.[dV]}$PEPTIDE1,PEPTIDE1,7:R2-1:R1$$$"
+"PEPTIDE1{A.R.C.A.A.K.T.C.D.A}$PEPTIDE1,PEPTIDE1,8:R3-3:R3$$$"

package/files/tests/filter_MSA.csv

@@ -0,0 +1,9 @@
+MSA,Activity
+meI/hHis/Aca/N/T/dE/Thr_PO3H2/Aca/D-Tyr_Et/Tyr_ab-dehydroMe/dV/E/N/D-Orn/D-aThr//Phe_4Me,5.307510973968128
+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,5.723876853431544
+Lys_Boc/hHis/Aca/Cys_SEt/T/dK/Thr_PO3H2/Aca/Tyr_PO3H2/D-Chg/dV/Thr_PO3H2/N/D-Orn/D-aThr//Phe_4Me,5.185811246022437
+meI/hHis/Aca/Cys_SEt/T/dK/Thr_PO3H2/Aca/Tyr_PO3H2/D-Chg/dV/Thr_PO3H2/N/D-Orn/D-aThr//Phe_4Me,6.223502390804369
+meI/hHis/Aca/N/T/dK/Thr_PO3H2/Aca/D-Tyr_Et/Tyr_ab-dehydroMe/dV/Chg/N/D-Orn/D-aThr//Phe_4Me,3.8459123763832412
+meI/hHis/Aca/N/T/dK/Thr_PO3H2/Aca/D-Tyr_Et/Tyr_Bn/dV/E/N/dV///Phe_4Me,3.27920438824657
+meI/hHis/Aca/N/T/dK/Thr_PO3H2/Aca/D-Tyr_Et/Aze/dV/E/N/dV///Phe_4Me,2.105852152992568
+meI/hHis/Aca/N/T/dK/Thr_PO3H2/Aca/D-Tyr_Et/meQ/dV/E/N/dV///Phe_4Me,1.803695001649272

package/package.json

@@ -5,7 +5,7 @@
     "name": "Leonid Stolbov",
     "email": "lstolbov@datagrok.ai"
   },
-  "version": "2.0.26",
+  "version": "2.0.28",
   "description": "Bio is a [package](https://datagrok.ai/help/develop/develop#packages) for the [Datagrok](https://datagrok.ai) platform",
   "repository": {
     "type": "git",
@@ -14,7 +14,7 @@
   },
   "dependencies": {
     "@biowasm/aioli": "^3.1.0",
-    "@datagrok-libraries/bio": "^5.4.1",
+    "@datagrok-libraries/bio": "^5.7.0",
     "@datagrok-libraries/chem-meta": "1.0.1",
     "@datagrok-libraries/ml": "^6.2.0",
     "@datagrok-libraries/utils": "^1.11.1",
@@ -47,7 +47,8 @@
     "webpack-cli": "^4.6.0"
   },
   "grokDependencies": {
-    "@datagrok/chem": "1.3.16"
+    "@datagrok/chem": "1.3.16",
+    "@datagrok/helm": "latest"
   },
   "scripts": {
     "link-api": "npm link datagrok-api",

package/scripts/admet-run.py

@@ -0,0 +1,27 @@
+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+"""
+Created on Mon Feb 19 17:30:46 2018
+
+@author: cbdd
+"""
+from sklearn.externals import joblib
+import numpy as np
+import pandas as pd
+import os
+
+###################################### Load model ##########
+# current_path = os.path.split(os.path.realpath(__file__))[0]
+cf = joblib.load('CYP3A4-substrate.pkl')
+
+###################################### Load descriptors ##########
+fingerprint_content = pd.read_csv('des.csv').ix[:, 1:]
+des_list = np.array(fingerprint_content)
+
+###################################### Prediction ##########
+y_predict_label = cf.predict(des_list)
+y_predict_proba = cf.predict_proba(des_list)
+print('#' * 10 + 'Results labels' + '#' * 10)
+print(y_predict_label)
+print('#' * 10 + 'Results probabilities' + '#' * 10)
+print(y_predict_proba)

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

@@ -8,7 +8,6 @@ import {getMonomericMols} from '../calculations/monomerLevelMols';
 import * as C from '../utils/constants';
 import {createDifferenceCanvas, createDifferencesWithPositions} from './sequence-activity-cliffs';
 import {updateDivInnerHTML} from '../utils/ui-utils';
-import {TableView} from 'datagrok-api/dg';
 import {Subject} from 'rxjs';
 
 export class SequenceSimilarityViewer extends SequenceSearchBaseViewer {
@@ -70,7 +69,7 @@ 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 TableView).grid.root.addEventListener('click', (event: MouseEvent) => {
+        (grok.shell.v as DG.TableView).grid.root.addEventListener('click', (event: MouseEvent) => {
           this.gridSelect = false;
         });
         updateDivInnerHTML(this.root, grid.root);

package/src/package-test.ts

@@ -16,6 +16,7 @@ import './tests/bio-tests';
 import './tests/WebLogo-positions-test';
 import './tests/checkInputColumn-tests';
 import './tests/similarity-diversity-tests';
+import './tests/substructure-filter-tests';
 
 export const _package = new DG.Package();
 export {tests};

package/src/package.ts

@@ -19,7 +19,6 @@ import {getMacroMol} from './utils/atomic-works';
 import {MacromoleculeSequenceCellRenderer} from './utils/cell-renderer';
 import {convert} from './utils/convert';
 import {getMacroMolColumnPropertyPanel, representationsWidget} from './widgets/representations';
-import {UnitsHandler, ALIGNMENT} from '@datagrok-libraries/bio/src/utils/units-handler';
 import {TAGS} from '@datagrok-libraries/bio/src/utils/macromolecule';
 import {ALPHABET, NOTATION} from '@datagrok-libraries/bio/src/utils/macromolecule'
 import {_toAtomicLevel} from '@datagrok-libraries/bio/src/utils/to-atomic-level';

package/src/substructure-search/substructure-search.ts

@@ -5,12 +5,11 @@ import * as bio from '@datagrok-libraries/bio';
 
 import * as C from '../utils/constants';
 import {getMonomericMols} from '../calculations/monomerLevelMols';
-import {BitSet} from 'datagrok-api/dg';
 import {updateDivInnerHTML} from '../utils/ui-utils';
 
 export const MONOMER_MOLS_COL = 'monomeric-mols';
 
-const enum MONOMERIC_COL_TAGS{
+const enum MONOMERIC_COL_TAGS {
   MONOMERIC_MOLS = 'monomeric-mols',
   LAST_INVALIDATED_VERSION = 'last-invalidated-version',
   MONOMERS_DICT = 'monomers-dict'
@@ -64,7 +63,7 @@ export function substructureSearchDialog(col: DG.Column): void {
       const colExists = col.dataFrame.columns.names()
         .filter((it) => it.toLocaleLowerCase() === matchesColName.toLocaleLowerCase()).length > 0;
       if (!colExists) {
-        let matches: BitSet;
+        let matches: DG.BitSet;
         if (units === bio.NOTATION.HELM)
           matches = await helmSubstructureSearch(substructure, col);
         else
@@ -92,13 +91,13 @@ function prepareSubstructureRegex(substructure: string, separator: string) {
   const endsWithSep = substructure.charAt(substructure.length - 1) === separator;
   const substrWithoutSep = substructure.replace(new RegExp(`^${char}|${char}$`, 'g'), '');
   const re = startsWithSep ? endsWithSep ? `${char}${substrWithoutSep}${char}` :
-    `${char}${substrWithoutSep}${char}|${char}${substrWithoutSep}$` :
+      `${char}${substrWithoutSep}${char}|${char}${substrWithoutSep}$` :
     endsWithSep ? `^${substrWithoutSep}${char}|${char}${substrWithoutSep}${char}` :
       `^${substrWithoutSep}${char}|${char}${substrWithoutSep}${char}|${char}${substrWithoutSep}$`;
   return re;
 }
 
-export async function helmSubstructureSearch(substructure: string, col: DG.Column): Promise<BitSet> {
+export async function helmSubstructureSearch(substructure: string, col: DG.Column): Promise<DG.BitSet> {
   if (col.version !== col.temp[MONOMERIC_COL_TAGS.LAST_INVALIDATED_VERSION])
     await invalidateHelmMols(col);
   const substructureCol = DG.Column.string('helm', 1).init((i) => substructure);

package/src/tests/checkInputColumn-tests.ts

@@ -7,8 +7,6 @@ import * as bio from '@datagrok-libraries/bio';
 import {after, before, category, test, expect, expectArray} from '@datagrok-libraries/utils/src/test';
 
 import {checkInputColumn, multipleSequenceAlignmentAny} from '../package';
-import {UNITS} from 'datagrok-api/dg';
-import {ALPHABET, NOTATION} from '@datagrok-libraries/bio/src/utils/macromolecule';
 
 category('checkInputColumn', () => {
   const csv = `seq
@@ -41,7 +39,7 @@ seq4`;
     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, NOTATION.HELM);
+    col.setTag(DG.TAGS.UNITS, bio.NOTATION.HELM);
     col.setTag(bio.TAGS.alphabetSize, '11');
     col.setTag(bio.TAGS.alphabetIsMultichar, 'true');
 
@@ -56,7 +54,7 @@ seq4`;
     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, NOTATION.FASTA);
+    col.setTag(DG.TAGS.UNITS, bio.NOTATION.FASTA);
     col.setTag(bio.TAGS.alphabet, 'UN');
     col.setTag(bio.TAGS.alphabetSize, '11');
     col.setTag(bio.TAGS.alphabetIsMultichar, 'true');

package/src/tests/detectors-test.ts

@@ -6,8 +6,6 @@ import * as bio from '@datagrok-libraries/bio';
 import {after, before, category, test, expect, expectObject} from '@datagrok-libraries/utils/src/test';
 
 import {importFasta} from '../package';
-import {UnitsHandler, ALIGNMENT} from '@datagrok-libraries/bio/src/utils/units-handler';
-import {NOTATION, ALPHABET} from '@datagrok-libraries/bio/src/utils/macromolecule';
 
 type DfReaderFunc = () => Promise<DG.DataFrame>;
 
@@ -201,49 +199,49 @@ MWRSWY-CKHP
   test('NegativeSmiles', async () => { await _testNeg(readCsv('csvDfSmiles', csvDfSmiles), 'col1'); });
 
   test('Dna1', async () => {
-    await _testPos(readCsv('csvDfDna1', csvDfDna1), 'seq', NOTATION.FASTA, ALIGNMENT.SEQ, ALPHABET.DNA, 4, false);
+    await _testPos(readCsv('csvDfDna1', csvDfDna1), 'seq', bio.NOTATION.FASTA, bio.ALIGNMENT.SEQ, bio.ALPHABET.DNA, 4, false);
   });
   test('Rna1', async () => {
-    await _testPos(readCsv('csvDfRna1', csvDfRna1), 'seq', NOTATION.FASTA, ALIGNMENT.SEQ, ALPHABET.RNA, 4, false);
+    await _testPos(readCsv('csvDfRna1', csvDfRna1), 'seq', bio.NOTATION.FASTA, bio.ALIGNMENT.SEQ, bio.ALPHABET.RNA, 4, false);
   });
   test('AA1', async () => {
-    await _testPos(readCsv('csvDfPt1', csvDfPt1), 'seq', NOTATION.FASTA, ALIGNMENT.SEQ, ALPHABET.PT, 20, false);
+    await _testPos(readCsv('csvDfPt1', csvDfPt1), 'seq', bio.NOTATION.FASTA, bio.ALIGNMENT.SEQ, bio.ALPHABET.PT, 20, false);
   });
   test('MsaDna1', async () => {
-    await _testPos(readCsv('csvDfMsaDna1', csvDfMsaDna1), 'seq', NOTATION.FASTA, ALIGNMENT.SEQ_MSA, ALPHABET.DNA, 4, false);
+    await _testPos(readCsv('csvDfMsaDna1', csvDfMsaDna1), 'seq', bio.NOTATION.FASTA, bio.ALIGNMENT.SEQ_MSA, bio.ALPHABET.DNA, 4, false);
   });
 
   test('MsaAA1', async () => {
-    await _testPos(readCsv('csvDfMsaPt1', csvDfMsaPt1), 'seq', NOTATION.FASTA,
-      ALIGNMENT.SEQ_MSA, ALPHABET.PT, 20, false);
+    await _testPos(readCsv('csvDfMsaPt1', csvDfMsaPt1), 'seq', bio.NOTATION.FASTA,
+      bio.ALIGNMENT.SEQ_MSA, bio.ALPHABET.PT, 20, false);
   });
 
   test('SepDna', async () => {
-    await _testPos(readCsv('csvDfSepDna', csvDfSepDna), 'seq', NOTATION.SEPARATOR, ALIGNMENT.SEQ, ALPHABET.DNA, 4, false, '*');
+    await _testPos(readCsv('csvDfSepDna', csvDfSepDna), 'seq', bio.NOTATION.SEPARATOR, bio.ALIGNMENT.SEQ, bio.ALPHABET.DNA, 4, false, '*');
   });
   test('SepRna', async () => {
-    await _testPos(readCsv('csvDfSepRna', csvDfSepRna), 'seq', NOTATION.SEPARATOR, ALIGNMENT.SEQ, ALPHABET.RNA, 4, false, '*');
+    await _testPos(readCsv('csvDfSepRna', csvDfSepRna), 'seq', bio.NOTATION.SEPARATOR, bio.ALIGNMENT.SEQ, bio.ALPHABET.RNA, 4, false, '*');
   });
   test('SepPt', async () => {
     await _testPos(readCsv('csvDfSepPt', csvDfSepPt), 'seq',
-      NOTATION.SEPARATOR, ALIGNMENT.SEQ, ALPHABET.PT, 20, false, '-');
+      bio.NOTATION.SEPARATOR, bio.ALIGNMENT.SEQ, bio.ALPHABET.PT, 20, false, '-');
   });
   test('SepUn1', async () => {
     await _testPos(readCsv('csvDfSepUn1', csvDfSepUn1), 'seq',
-      NOTATION.SEPARATOR, ALIGNMENT.SEQ, ALPHABET.UN, 8, true, '-');
+      bio.NOTATION.SEPARATOR, bio.ALIGNMENT.SEQ, bio.ALPHABET.UN, 8, true, '-');
   });
   test('SepUn2', async () => {
     await _testPos(readCsv('csvDfSepUn2', csvDfSepUn2), 'seq',
-      NOTATION.SEPARATOR, ALIGNMENT.SEQ, ALPHABET.UN, 9, true, '/');
+      bio.NOTATION.SEPARATOR, bio.ALIGNMENT.SEQ, bio.ALPHABET.UN, 9, true, '/');
   });
 
   test('SepMsaN1', async () => {
     await _testPos(readCsv('csvDfSepMsaDna1', csvDfSepMsaDna1), 'seq',
-      NOTATION.SEPARATOR, ALIGNMENT.SEQ_MSA, ALPHABET.DNA, 4, false, '-');
+      bio.NOTATION.SEPARATOR, bio.ALIGNMENT.SEQ_MSA, bio.ALPHABET.DNA, 4, false, '-');
   });
 
   test('SamplesFastaCsvPt', async () => {
-    await _testPos(readSamples(Samples.fastaCsv), 'sequence', NOTATION.FASTA, ALIGNMENT.SEQ, ALPHABET.PT, 20, false);
+    await _testPos(readSamples(Samples.fastaCsv), 'sequence', bio.NOTATION.FASTA, bio.ALIGNMENT.SEQ, bio.ALPHABET.PT, 20, false);
   });
   test('SamplesFastaCsvNegativeEntry', async () => {
     await _testNeg(readSamples(Samples.fastaCsv), 'Entry');
@@ -257,7 +255,7 @@ MWRSWY-CKHP
 
   test('SamplesFastaFastaPt', async () => {
     await _testPos(readSamples(Samples.fastaFasta, readFileFasta),
-      'sequence', NOTATION.FASTA, ALIGNMENT.SEQ, ALPHABET.PT, 20, false);
+      'sequence', bio.NOTATION.FASTA, bio.ALIGNMENT.SEQ, bio.ALPHABET.PT, 20, false);
   });
 
   // peptidesComplex contains monomers with spaces in AlignedSequence columns, which are forbidden
@@ -276,7 +274,7 @@ MWRSWY-CKHP
 
   test('samplesMsaComplexUn', async () => {
     await _testPos(readSamples(Samples.msaComplex), 'MSA',
-      NOTATION.SEPARATOR, ALIGNMENT.SEQ_MSA, ALPHABET.UN, 161, true, '/');
+      bio.NOTATION.SEPARATOR, bio.ALIGNMENT.SEQ_MSA, bio.ALPHABET.UN, 161, true, '/');
   });
   test('samplesMsaComplexNegativeActivity', async () => {
     await _testNeg(readSamples(Samples.msaComplex), 'Activity');
@@ -291,7 +289,7 @@ MWRSWY-CKHP
   });
 
   test('samplesHelmCsvHELM', async () => {
-    await _testPos(readSamples(Samples.helmCsv), 'HELM', NOTATION.HELM, null, null, 160, true, null);
+    await _testPos(readSamples(Samples.helmCsv), 'HELM', bio.NOTATION.HELM, null, null, 160, true, null);
   });
 
   test('samplesHelmCsvNegativeActivity', async () => {
@@ -307,7 +305,7 @@ MWRSWY-CKHP
     await _testNeg(readSamples(Samples.testHelmCsv), 'Test type');
   });
   test('samplesTestHelmPositiveHelmString', async () => {
-    await _testPos(readSamples(Samples.testHelmCsv), 'HELM string', NOTATION.HELM, null, null, 9, true, null);
+    await _testPos(readSamples(Samples.testHelmCsv), 'HELM string', bio.NOTATION.HELM, null, null, 9, true, null);
   });
   test('samplesTestHelmNegativeValid', async () => {
     await _testNeg(readSamples(Samples.testHelmCsv), 'Valid?');
@@ -339,7 +337,7 @@ MWRSWY-CKHP
   });
 
   test('samplesFastaPtPosSequence', async () => {
-    await _testPos(readSamples(Samples.fastaPtCsv), 'sequence', NOTATION.FASTA, ALIGNMENT.SEQ, ALPHABET.PT, 20, false);
+    await _testPos(readSamples(Samples.fastaPtCsv), 'sequence', bio.NOTATION.FASTA, bio.ALIGNMENT.SEQ, bio.ALPHABET.PT, 20, false);
   });
 
   test('samplesTestCerealNegativeCerealName', async () => {
@@ -414,7 +412,7 @@ export async function _testPos(
   if (separator)
     expect(col.getTag(bio.TAGS.separator), separator);
 
-  const uh = new UnitsHandler(col);
+  const uh = new bio.UnitsHandler(col);
   expect(uh.getAlphabetSize(), alphabetSize);
   expect(uh.getAlphabetIsMultichar(), alphabetIsMultichar);
   if (!uh.isHelm()) {

package/src/tests/renderers-test.ts

@@ -6,8 +6,6 @@ import {after, before, category, delay, expect, test} from '@datagrok-libraries/
 
 import {importFasta, multipleSequenceAlignmentAny} from '../package';
 import {convertDo} from '../utils/convert';
-import {ALPHABET, NOTATION} from '@datagrok-libraries/bio/src/utils/macromolecule';
-import {UnitsHandler, ALIGNMENT} from '@datagrok-libraries/bio/src/utils/units-handler';
 import {SEM_TYPES, TAGS} from '../utils/constants';
 import {generateLongSequence, generateManySequences, performanceTest} from './test-sequnces-generators';
 
@@ -105,7 +103,7 @@ category('renderers', () => {
   async function _rendererMacromoleculeDifference() {
     const seqDiffCol: DG.Column = DG.Column.fromStrings('SequencesDiff',
       ['meI/hHis/Aca/N/T/dK/Thr_PO3H2/Aca#D-Tyr_Et/Tyr_ab-dehydroMe/meN/E/N/dV']);
-    seqDiffCol.tags[DG.TAGS.UNITS] = NOTATION.SEPARATOR;
+    seqDiffCol.tags[DG.TAGS.UNITS] = bio.NOTATION.SEPARATOR;
     seqDiffCol.tags[TAGS.SEPARATOR] = '/';
     seqDiffCol.semType = SEM_TYPES.MACROMOLECULE_DIFFERENCE;
     const df = DG.DataFrame.fromColumns([seqDiffCol]);
@@ -141,7 +139,7 @@ category('renderers', () => {
       `cell.renderer="${srcSeqCol!.getTag(DG.TAGS.CELL_RENDERER)}"`);
     expect(srcSeqCol.semType, DG.SEMTYPE.MACROMOLECULE);
     expect(srcSeqCol.getTag(DG.TAGS.UNITS), bio.NOTATION.FASTA);
-    expect(srcSeqCol.getTag(bio.TAGS.aligned), ALIGNMENT.SEQ);
+    expect(srcSeqCol.getTag(bio.TAGS.aligned), bio.ALIGNMENT.SEQ);
     expect(srcSeqCol.getTag(bio.TAGS.alphabet), bio.ALPHABET.PT);
     expect(srcSeqCol.getTag(DG.TAGS.CELL_RENDERER), 'sequence');
 
@@ -150,7 +148,7 @@ category('renderers', () => {
 
     expect(msaSeqCol.semType, DG.SEMTYPE.MACROMOLECULE);
     expect(msaSeqCol.getTag(DG.TAGS.UNITS), bio.NOTATION.FASTA);
-    expect(msaSeqCol.getTag(bio.TAGS.aligned), ALIGNMENT.SEQ_MSA);
+    expect(msaSeqCol.getTag(bio.TAGS.aligned), bio.ALIGNMENT.SEQ_MSA);
     expect(msaSeqCol.getTag(bio.TAGS.alphabet), bio.ALPHABET.PT);
     expect(msaSeqCol.getTag(DG.TAGS.CELL_RENDERER), 'sequence');
 
@@ -192,7 +190,7 @@ category('renderers', () => {
     /**/
     const seqDiffCol: DG.Column = DG.Column.fromStrings('SequencesDiff',
       ['meI/hHis/Aca/N/T/dK/Thr_PO3H2/Aca#D-Tyr_Et/Tyr_ab-dehydroMe/meN/E/N/dV']);
-    seqDiffCol.tags[DG.TAGS.UNITS] = NOTATION.SEPARATOR;
+    seqDiffCol.tags[DG.TAGS.UNITS] = bio.NOTATION.SEPARATOR;
     seqDiffCol.tags[TAGS.SEPARATOR] = '/';
     seqDiffCol.semType = SEM_TYPES.MACROMOLECULE_DIFFERENCE;
     const df = DG.DataFrame.fromColumns([seqDiffCol]);
@@ -213,7 +211,7 @@ category('renderers', () => {
   async function _setRendererManually() {
     const seqDiffCol: DG.Column = DG.Column.fromStrings('SequencesDiff',
       ['meI/hHis/Aca/N/T/dK/Thr_PO3H2/Aca#D-Tyr_Et/Tyr_ab-dehydroMe/meN/E/N/dV']);
-    seqDiffCol.tags[DG.TAGS.UNITS] = NOTATION.SEPARATOR;
+    seqDiffCol.tags[DG.TAGS.UNITS] = bio.NOTATION.SEPARATOR;
     seqDiffCol.tags[TAGS.SEPARATOR] = '/';
     seqDiffCol.semType = SEM_TYPES.MACROMOLECULE;
     const tgtCellRenderer = 'MacromoleculeDifference';

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

@@ -0,0 +1,61 @@
+import {after, before, category, test, expect, delay} from '@datagrok-libraries/utils/src/test';
+import * as DG from 'datagrok-api/dg';
+import * as grok from 'datagrok-api/grok';
+import {readDataframe} from './utils';
+import {BioSubstructureFilter, HelmFilter, SeparatorFilter} from '../widgets/bio-substructure-filter';
+
+
+category('substructureFilters', async () => {
+  test('fasta', async () => {
+    const fasta = await readDataframe('tests/filter_FASTA.csv');
+    const filter = new BioSubstructureFilter();
+    await grok.data.detectSemanticTypes(fasta);
+    filter.attach(fasta);
+    filter.bioFilter!.substructure = 'MD';
+    await delay(100);
+    expect(filter.dataFrame!.filter.trueCount, 3);
+    expect(filter.dataFrame!.filter.get(0), true);
+    expect(filter.dataFrame!.filter.get(3), true);
+    expect(filter.dataFrame!.filter.get(8), true);
+    expect(filter.dataFrame!.filter.get(1), false);
+  });
+
+  test('separator', async () => {
+    const msa = await readDataframe('tests/filter_MSA.csv');
+    const filter = new BioSubstructureFilter();
+    await grok.data.detectSemanticTypes(msa);
+    filter.attach(msa);
+    filter.bioFilter!.substructure = 'meI';
+    await delay(100);
+    expect(filter.dataFrame!.filter.trueCount, 7);
+    expect(filter.dataFrame!.filter.get(2), false);
+    filter.bioFilter!.substructure = '/meI';
+    await delay(100);
+    expect(filter.dataFrame!.filter.trueCount, 0);
+    filter.bioFilter!.substructure = 'meI-hHis';
+    (filter.bioFilter! as SeparatorFilter).separatorInput.value = '-';
+    await delay(100);
+    expect(filter.dataFrame!.filter.trueCount, 7);
+    expect(filter.dataFrame!.filter.get(2), false);
+  });
+
+  test('helm', async () => {
+    const helm = await readDataframe('tests/filter_HELM.csv');
+    const helmTableView = grok.shell.addTableView(helm);
+    const filter = new BioSubstructureFilter();
+    await grok.data.detectSemanticTypes(helm);
+    filter.attach(helm);
+    (filter.bioFilter! as HelmFilter).helmSubstructure = 'PEPTIDE1{C}$$$$V2.0';
+    filter.bioFilter!.onChanged.next();
+    await delay(1000);
+    expect(filter.dataFrame!.filter.trueCount, 2);
+    expect(filter.dataFrame!.filter.get(0), true);
+    expect(filter.dataFrame!.filter.get(3), true);
+    (filter.bioFilter! as HelmFilter).helmSubstructure = 'PEPTIDE1{A.C}$$$$V2.0';
+    filter.bioFilter!.onChanged.next();
+    await delay(100);
+    expect(filter.dataFrame!.filter.trueCount, 1);
+    expect(filter.dataFrame!.filter.get(3), true);
+    helmTableView.close();
+  });
+});

package/src/tests/test-sequnces-generators.ts

@@ -1,9 +1,8 @@
-import * as DG from 'datagrok-api/dg';
 import * as grok from 'datagrok-api/grok';
-import {DataFrame} from 'datagrok-api/dg';
+import * as ui from 'datagrok-api/ui';
+import * as DG from 'datagrok-api/dg';
+import * as bio from '@datagrok-libraries/bio';
 
-import {ALIGNMENT, UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
-import {NOTATION, ALPHABET, TAGS} from '@datagrok-libraries/bio/src/utils/macromolecule';
 
 export function generateManySequences(): DG.Column[] {
   let columns: DG.Column[] = [];
@@ -22,10 +21,10 @@ export function generateLongSequence(): DG.Column[] {
 
 export function setTagsMacromolecule(col: DG.Column) {
   col.semType = DG.SEMTYPE.MACROMOLECULE;
-  col.setTag(DG.TAGS.UNITS, NOTATION.SEPARATOR);
-  col.setTag(TAGS.aligned, ALIGNMENT.SEQ_MSA);
-  col.setTag(TAGS.alphabet, ALPHABET.UN);
-  col.setTag(TAGS.separator, '/');
+  col.setTag(DG.TAGS.UNITS, bio.NOTATION.SEPARATOR);
+  col.setTag(bio.TAGS.aligned, bio.ALIGNMENT.SEQ_MSA);
+  col.setTag(bio.TAGS.alphabet, bio.ALPHABET.UN);
+  col.setTag(bio.TAGS.separator, '/');
   return col;
 }
 

package/src/utils/cell-renderer.ts

@@ -3,7 +3,6 @@ import * as DG from 'datagrok-api/dg';
 import * as ui from 'datagrok-api/ui';
 
 import {printLeftOrCentered, DrawStyle} from '@datagrok-libraries/bio/src/utils/cell-renderer';
-import {ALIGNMENT} from '@datagrok-libraries/bio/src/utils/units-handler';
 import * as bio from '@datagrok-libraries/bio';
 import * as C from './constants';
 
@@ -47,7 +46,7 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
   }
 
   onMouseMove(gridCell: DG.GridCell, e: MouseEvent): void {
-    if (gridCell.cell.column.getTag(bio.TAGS.aligned) !== ALIGNMENT.SEQ_MSA)
+    if (gridCell.cell.column.getTag(bio.TAGS.aligned) !== bio.ALIGNMENT.SEQ_MSA)
       return;
 
     const maxLengthWordsSum = gridCell.cell.column.temp['bio-sum-maxLengthWords'];

package/src/widgets/bio-substructure-filter.ts

@@ -158,7 +158,7 @@ class FastaFilter extends BioFilterBase {
   }
 }
 
-class SeparatorFilter extends FastaFilter {
+export class SeparatorFilter extends FastaFilter {
   separatorInput: DG.InputBase<string> = ui.stringInput('', '', () => {
     this.onChanged.next();
   }, {placeholder: 'Separator'});
@@ -192,7 +192,7 @@ class SeparatorFilter extends FastaFilter {
   }
 }
 
-class HelmFilter extends BioFilterBase {
+export class HelmFilter extends BioFilterBase {
   helmEditor: any;
   _filterPanel = ui.div('', {style: {cursor: 'pointer'}});
   helmSubstructure = '';