@datagrok/bio 2.11.5 → 2.11.7

package/package.json

@@ -5,7 +5,7 @@
     "name": "Leonid Stolbov",
     "email": "lstolbov@datagrok.ai"
   },
-  "version": "2.11.5",
+  "version": "2.11.7",
   "description": "Bioinformatics support (import/export of sequences, conversion, visualization, analysis). [See more](https://github.com/datagrok-ai/public/blob/master/packages/Bio/README.md) for details.",
   "repository": {
     "type": "git",
@@ -34,7 +34,7 @@
   ],
   "dependencies": {
     "@biowasm/aioli": "^3.1.0",
-    "@datagrok-libraries/bio": "^5.39.1",
+    "@datagrok-libraries/bio": "^5.39.2",
     "@datagrok-libraries/chem-meta": "^1.0.1",
     "@datagrok-libraries/ml": "^6.3.53",
     "@datagrok-libraries/tutorials": "^1.3.6",

package/src/package.ts

@@ -75,6 +75,7 @@ import {GetRegionApp} from './apps/get-region-app';
 import {GetRegionFuncEditor} from './utils/get-region-func-editor';
 import {sequenceToMolfile} from './utils/sequence-to-mol';
 import {errInfo} from './utils/err-info';
+import {detectMacromoleculeProbeDo} from './utils/detect-macromolecule-probe';
 
 import {SHOW_SCATTERPLOT_PROGRESS} from '@datagrok-libraries/ml/src/functionEditors/seq-space-base-editor';
 import {DIMENSIONALITY_REDUCER_TERMINATE_EVENT}
@@ -427,7 +428,6 @@ export async function activityCliffs(df: DG.DataFrame, macroMolecule: DG.Column<
     };
   }
 
-
   const runCliffs = async () => {
     const sp = await getActivityCliffs(
       df,
@@ -457,13 +457,13 @@ export async function activityCliffs(df: DG.DataFrame, macroMolecule: DG.Column<
     return;
   }
 
+  const pi = DG.TaskBarProgressIndicator.create(`Running sequence activity cliffs ...`);
   return new Promise<DG.Viewer | undefined>((resolve, reject) => {
     if (df.rowCount > fastRowCount && !options?.[BYPASS_LARGE_DATA_WARNING]) {
       ui.dialog().add(ui.divText(`Activity cliffs analysis might take several minutes.
     Do you want to continue?`))
         .onOK(async () => {
-          //const progressBar = DG.TaskBarProgressIndicator.create(`Running sequence activity cliffs ...`);
-          runCliffs().then((res) => resolve(res)).catch((err) => reject(err)).finally(() => {});
+          runCliffs().then((res) => resolve(res)).catch((err) => reject(err));
         })
         .onCancel(() => { resolve(undefined); })
         .show();
@@ -474,7 +474,7 @@ export async function activityCliffs(df: DG.DataFrame, macroMolecule: DG.Column<
     const [errMsg, errStack] = errInfo(err);
     _package.logger.error(errMsg, undefined, errStack);
     throw err;
-  });
+  }).finally(() => { pi.close(); });
 }
 
 //top-menu: Bio | Analyze | Sequence Space...
@@ -526,6 +526,7 @@ export async function sequenceSpaceTopMenu(
       const progress = (_nEpoch / epochsLength * 100);
       pg.update(progress, `Running sequence space ... ${progress.toFixed(0)}%`);
     }
+
     const embedColsNames = getEmbeddingColsNames(table);
     const withoutEmptyValues = DG.DataFrame.fromColumns([macroMolecule]).clone();
     const emptyValsIdxs = removeEmptyStringRows(withoutEmptyValues, macroMolecule);
@@ -1109,3 +1110,14 @@ export async function sdfToJsonLib(table: DG.DataFrame) {
   const jsonMonomerLibrary = JSON.stringify(_jsonMonomerLibrary);
   DG.Utils.download(`${table.name}.json`, jsonMonomerLibrary);
 }
+
+// -- Utils --
+
+//name: detectMacromoleculeProbe
+//input: file file
+//input: string colName = ''
+//input: int probeCount = 100
+export async function detectMacromoleculeProbe(file: DG.FileInfo, colName: string, probeCount: number): Promise<void> {
+  const csv: string = await file.readAsString();
+  await detectMacromoleculeProbeDo(csv, colName, probeCount);
+}

package/src/tests/converters-test.ts

@@ -41,79 +41,79 @@ category('converters', () => {
   }
 
   const _csvTxts: { [key: string]: string } = {
-    fastaPt: `seq
-FWPHEY
-YNRQWYV
-MKPSEYV`,
-    separatorPt: `seq
-F-W-P-H-E-Y
-Y-N-R-Q-W-Y-V
-M-K-P-S-E-Y-V`,
-    helmPt: `seq
-PEPTIDE1{F.W.P.H.E.Y}$$$$
-PEPTIDE1{Y.N.R.Q.W.Y.V}$$$$
-PEPTIDE1{M.K.P.S.E.Y.V}$$$$`,
-    fastaDna: `seq
-ACGTC
-CAGTGT
-TTCAAC`,
-    separatorDna: `seq
-A/C/G/T/C
-C/A/G/T/G/T
-T/T/C/A/A/C`,
-    helmDna: `seq
-RNA1{d(A)p.d(C)p.d(G)p.d(T)p.d(C)p}$$$$
-RNA1{d(C)p.d(A)p.d(G)p.d(T)p.d(G)p.d(T)p}$$$$
-RNA1{d(T)p.d(T)p.d(C)p.d(A)p.d(A)p.d(C)p}$$$$`,
-    fastaRna: `seq
-ACGUC
-CAGUGU
-UUCAAC`,
-    separatorRna: `seq
-A*C*G*U*C
-C*A*G*U*G*U
-U*U*C*A*A*C`,
-    helmRna: `seq
-RNA1{r(A)p.r(C)p.r(G)p.r(U)p.r(C)p}$$$$
-RNA1{r(C)p.r(A)p.r(G)p.r(U)p.r(G)p.r(U)p}$$$$
-RNA1{r(U)p.r(U)p.r(C)p.r(A)p.r(A)p.r(C)p}$$$$`,
-    fastaGaps: `seq
-FW-PH-EYY
-FYNRQWYV-
-FKP-Q-SEYV`,
-    separatorGaps: `seq
-F/W//P/H//E/Y/Y
-F/Y/N/R/Q/W/Y/V/
-F/K/P//Q//S/E/Y/V`,
-    helmGaps: `seq
-PEPTIDE1{F.W.*.P.H.*.E.Y.Y}$$$$
-PEPTIDE1{F.Y.N.R.Q.W.Y.V.*}$$$$
-PEPTIDE1{F.K.P.*.Q.*.S.E.Y.V}$$$$`,
+    [Samples.fastaPt]: `seq
+FWPHEYFWPHEY
+YNRQWYVYNRQWYV
+MKPSEYVMKPSEYV`,
+    [Samples.separatorPt]: `seq
+F-W-P-H-E-Y-F-W-P-H-E-Y
+Y-N-R-Q-W-Y-V-Y-N-R-Q-W-Y-V
+M-K-P-S-E-Y-V-M-K-P-S-E-Y-V`,
+    [Samples.helmPt]: `seq
+PEPTIDE1{F.W.P.H.E.Y.F.W.P.H.E.Y}$$$$
+PEPTIDE1{Y.N.R.Q.W.Y.V.Y.N.R.Q.W.Y.V}$$$$
+PEPTIDE1{M.K.P.S.E.Y.V.M.K.P.S.E.Y.V}$$$$`,
+    [Samples.fastaDna]: `seq
+ACGTCACGTC
+CAGTGTCAGTGT
+TTCAACTTCAAC`,
+    [Samples.separatorDna]: `seq
+A/C/G/T/C/A/C/G/T/C
+C/A/G/T/G/T/C/A/G/T/G/T
+T/T/C/A/A/C/T/T/C/A/A/C`,
+    [Samples.helmDna]: `seq
+RNA1{d(A)p.d(C)p.d(G)p.d(T)p.d(C)p.d(A)p.d(C)p.d(G)p.d(T)p.d(C)p}$$$$
+RNA1{d(C)p.d(A)p.d(G)p.d(T)p.d(G)p.d(T)p.d(C)p.d(A)p.d(G)p.d(T)p.d(G)p.d(T)p}$$$$
+RNA1{d(T)p.d(T)p.d(C)p.d(A)p.d(A)p.d(C)p.d(T)p.d(T)p.d(C)p.d(A)p.d(A)p.d(C)p}$$$$`,
+    [Samples.fastaRna]: `seq
+ACGUCACGUC
+CAGUGUCAGUGU
+UUCAACUUCAAC`,
+    [Samples.separatorRna]: `seq
+A*C*G*U*C*A*C*G*U*C
+C*A*G*U*G*U*C*A*G*U*G*U
+U*U*C*A*A*C*U*U*C*A*A*C`,
+    [Samples.helmRna]: `seq
+RNA1{r(A)p.r(C)p.r(G)p.r(U)p.r(C)p.r(A)p.r(C)p.r(G)p.r(U)p.r(C)p}$$$$
+RNA1{r(C)p.r(A)p.r(G)p.r(U)p.r(G)p.r(U)p.r(C)p.r(A)p.r(G)p.r(U)p.r(G)p.r(U)p}$$$$
+RNA1{r(U)p.r(U)p.r(C)p.r(A)p.r(A)p.r(C)p.r(U)p.r(U)p.r(C)p.r(A)p.r(A)p.r(C)p}$$$$`,
+    [Samples.fastaGaps]: `seq
+FW-PH-EYYFW-PH-EYY
+FYNRQWYV-FYNRQWYV-
+FKP-Q-SEYVFKP-Q-SEYV`,
+    [Samples.separatorGaps]: `seq
+F/W//P/H//E/Y/Y/F/W//P/H//E/Y/Y
+F/Y/N/R/Q/W/Y/V//F/Y/N/R/Q/W/Y/V/
+F/K/P//Q//S/E/Y/V/F/K/P//Q//S/E/Y/V`,
+    [Samples.helmGaps]: `seq
+PEPTIDE1{F.W.*.P.H.*.E.Y.Y.F.W.*.P.H.*.E.Y.Y}$$$$
+PEPTIDE1{F.Y.N.R.Q.W.Y.V.*.F.Y.N.R.Q.W.Y.V.*}$$$$
+PEPTIDE1{F.K.P.*.Q.*.S.E.Y.V.F.K.P.*.Q.*.S.E.Y.V}$$$$`,
 
-    fastaUn: `seq
-[meI][hHis][Aca]NT[dE][Thr_PO3H2][Aca]D
-[meI][hHis][Aca][Cys_SEt]T[dK][Thr_PO3H2][Aca][Tyr_PO3H2]
-[Lys_Boc][hHis][Aca][Cys_SEt]T[dK][Thr_PO3H2][Aca][Tyr_PO3H2]`,
-    separatorUn: `seq
-meI-hHis-Aca-N-T-dE-Thr_PO3H2-Aca-D
-meI-hHis-Aca-Cys_SEt-T-dK-Thr_PO3H2-Aca-Tyr_PO3H2
-Lys_Boc-hHis-Aca-Cys_SEt-T-dK-Thr_PO3H2-Aca-Tyr_PO3H2`,
-    helmUn: `seq
-PEPTIDE1{meI.hHis.Aca.N.T.dE.Thr_PO3H2.Aca.D}$$$$
-PEPTIDE1{meI.hHis.Aca.Cys_SEt.T.dK.Thr_PO3H2.Aca.Tyr_PO3H2}$$$$
-PEPTIDE1{Lys_Boc.hHis.Aca.Cys_SEt.T.dK.Thr_PO3H2.Aca.Tyr_PO3H2}$$$$`,
-    helmLoneDeoxyribose: `seq
-RNA1{d(A).d(C).d(G).d(T).d(C)}$$$$
-RNA1{d(C).d(A).d(G).d(T).d(G).d(T)p}$$$$
-RNA1{d(T).d(T).d(C).d(A).d(A).d(C)p}$$$$`,
-    helmLoneRibose: `seq
-RNA1{r(A).r(C).r(G).r(U).r(C)}$$$$
-RNA1{r(C).r(A).r(G).r(U).r(G).r(U)p}$$$$
-RNA1{r(U).r(U).r(C).r(A).r(A).r(C)p}$$$$`,
-    helmLonePhosphorus: `seq
-RNA1{p.p.r(A)p.r(C)p.r(G)p.r(U)p.r(C)p}$$$$
-RNA1{p.p.r(C)p.r(A)p.p.r(G)p.r(U)p.r(G)p.r(U)p}$$$$
-RNA1{p.r(U)p.r(U)p.r(C)p.r(A)p.r(A)p.r(C)p.p.p}$$$$`,
+    [Samples.fastaUn]: `seq
+[meI][hHis][Aca]NT[dE][Thr_PO3H2][Aca]D[meI][hHis][Aca]NT[dE][Thr_PO3H2][Aca]D
+[meI][hHis][Aca][Cys_SEt]T[dK][Thr_PO3H2][Aca][Tyr_PO3H2][meI][hHis][Aca][Cys_SEt]T[dK][Thr_PO3H2][Aca][Tyr_PO3H2]
+[Lys_Boc][hHis][Aca][Cys_SEt]T[dK][Thr_PO3H2][Aca][Tyr_PO3H2][Lys_Boc][hHis][Aca][Cys_SEt]T[dK][Thr_PO3H2][Aca]`,
+    [Samples.separatorUn]: `seq
+meI-hHis-Aca-N-T-dE-Thr_PO3H2-Aca-D-meI-hHis-Aca-N-T-dE-Thr_PO3H2-Aca-D
+meI-hHis-Aca-Cys_SEt-T-dK-Thr_PO3H2-Aca-Tyr_PO3H2-meI-hHis-Aca-Cys_SEt-T-dK-Thr_PO3H2-Aca-Tyr_PO3H2
+Lys_Boc-hHis-Aca-Cys_SEt-T-dK-Thr_PO3H2-Aca-Tyr_PO3H2-Lys_Boc-hHis-Aca-Cys_SEt-T-dK-Thr_PO3H2-Aca`,
+    [Samples.helmUn]: `seq
+PEPTIDE1{meI.hHis.Aca.N.T.dE.Thr_PO3H2.Aca.D.meI.hHis.Aca.N.T.dE.Thr_PO3H2.Aca.D}$$$$
+PEPTIDE1{meI.hHis.Aca.Cys_SEt.T.dK.Thr_PO3H2.Aca.Tyr_PO3H2.meI.hHis.Aca.Cys_SEt.T.dK.Thr_PO3H2.Aca.Tyr_PO3H2}$$$$
+PEPTIDE1{Lys_Boc.hHis.Aca.Cys_SEt.T.dK.Thr_PO3H2.Aca.Tyr_PO3H2.Lys_Boc.hHis.Aca.Cys_SEt.T.dK.Thr_PO3H2.Aca}$$$$`,
+    [Samples.helmLoneDeoxyribose]: `seq
+RNA1{d(A).d(C).d(G).d(T).d(C).d(A).d(C).d(G).d(T).d(C)}$$$$
+RNA1{d(C).d(A).d(G).d(T).d(G).d(T)p.d(C).d(A).d(G).d(T).d(G).d(T)p}$$$$
+RNA1{d(T).d(T).d(C).d(A).d(A).d(C)p.d(T).d(T).d(C).d(A).d(A).d(C)p}$$$$`,
+    [Samples.helmLoneRibose]: `seq
+RNA1{r(A).r(C).r(G).r(U).r(C).r(A).r(C).r(G).r(U).r(C)}$$$$
+RNA1{r(C).r(A).r(G).r(U).r(G).r(U)p.r(C).r(A).r(G).r(U).r(G).r(U)p}$$$$
+RNA1{r(U).r(U).r(C).r(A).r(A).r(C)p.r(U).r(U).r(C).r(A).r(A).r(C)p}$$$$`,
+    [Samples.helmLonePhosphorus]: `seq
+RNA1{p.p.r(A)p.r(C)p.r(G)p.r(U)p.r(C)p.r(A)p.r(C)p.r(G)p.r(U)p.r(C)p}$$$$
+RNA1{p.p.r(C)p.r(A)p.p.r(G)p.r(U)p.r(G)p.r(U)p.r(C)p.r(A)p.p.r(G)p.r(U)p.r(G)p.r(U)p}$$$$
+RNA1{p.r(U)p.r(U)p.r(C)p.r(A)p.r(A)p.r(C)p.r(U)p.r(U)p.r(C)p.r(A)p.r(A)p.r(C)p.p.p}$$$$`,
   };
 
   /** Also detects semantic types

package/src/tests/detectors-benchmark-tests.ts

@@ -39,11 +39,11 @@ category('detectorsBenchmark', () => {
   });
 
   test('separatorDnaShorts50Many1E6', async () => {
-    await detectMacromoleculeBenchmark(10, NOTATION.SEPARATOR, ALPHABET.DNA, 50, 1E6, '/');
+    await detectMacromoleculeBenchmark(20, NOTATION.SEPARATOR, ALPHABET.DNA, 50, 1E6, '/');
   });
 
   test('separatorDnaLong1e6Few50', async () => {
-    await detectMacromoleculeBenchmark(10, NOTATION.SEPARATOR, ALPHABET.DNA, 1E6, 50, '/');
+    await detectMacromoleculeBenchmark(20, NOTATION.SEPARATOR, ALPHABET.DNA, 1E6, 50, '/');
   });
 
   async function detectMacromoleculeBenchmark(

package/src/tests/detectors-tests.ts

@@ -71,63 +71,63 @@ CCCCN1C(=O)CN=C(c2cc(F)ccc12)C3CCCCC3
 C1CCCCC1
 CCCCCC`;
     [csvTests.fastaDna1]: string = `seq
-ACGTC
-CAGTGT
-TTCAAC`;
+ACGTCACGTC
+CAGTGTCAGTGT
+TTCAACTTCAAC`;
     [csvTests.fastaRna1]: string = `seq
-ACGUC
-CAGUGU
-UUCAAC`;
+ACGUCACGUC
+CAGUGUCAGUGU
+UUCAACUUCAAC`;
     /** Pure amino acids sequence */
     [csvTests.fastaPt1]: string = `seq
 FWPHEY
 YNRQWYV
 MKPSEYV`;
     [csvTests.fastaUn]: string = `seq
-[meI][hHis][Aca]NT[dE][Thr_PO3H2][Aca]D
-[meI][hHis][Aca][Cys_SEt]T[dK][Thr_PO3H2][Aca][Tyr_PO3H2]
-[Lys_Boc][hHis][Aca][Cys_SEt]T[dK][Thr_PO3H2][Aca][Tyr_PO3H2]`;
+[meI][hHis][Aca]NT[dE][Thr_PO3H2][Aca]DN
+[meI][hHis][Aca][Cys_SEt]T[dK][Thr_PO3H2][Aca][Tyr_PO3H2][Aca]
+[Lys_Boc][hHis][Aca][Cys_SEt]T[dK][Thr_PO3H2][Aca][Tyr_PO3H2][Aca]`;
     [csvTests.sepDna]: string = `seq
-A*C*G*T*C
-C*A*G*T*G*T
-T*T*C*A*A*C`;
+A*C*G*T*C*A*C*G*T*C
+C*A*G*T*G*T*C*A*G*T*G*T
+T*T*C*A*A*C*T*T*C*A*A*C`;
     [csvTests.sepRna]: string = `seq
-A*C*G*U*C
-C*A*G*U*G*U
-U*U*C*A*A*C`;
+A*C*G*U*C*A*C*G*U*C
+C*A*G*U*G*U*C*A*G*U*G*U
+U*U*C*A*A*C*U*U*C*A*A*C`;
     [csvTests.sepPt]: string = `seq
-F-W-P-H-E-Y
-Y-N-R-Q-W-Y-V
-M-K-P-S-E-Y-V`;
+F-W-P-H-E-Y-F-W-P-H-E-Y
+Y-N-R-Q-W-Y-V-Y-N-R-Q-W-Y-V
+M-K-P-S-E-Y-V-M-K-P-S-E-Y-V`;
     [csvTests.sepUn1]: string = `seq
-abc-dfgg-abc1-cfr3-rty-wert
-rut12-her2-rty-wert-abc-abc1-dfgg
-rut12-rty-her2-abc-cfr3-wert-rut12`;
+abc-dfgg-abc1-cfr3-rty-wert-cfr3-rty-wert
+rut12-her2-rty-wert-abc-abc1-dfgg-abc-abc1-dfgg
+rut12-rty-her2-abc-cfr3-wert-rut12-cfr3-wert-rut12`;
     [csvTests.sepUn2]: string = `seq
-abc/dfgg/abc1/cfr3/rty/wert
-rut12/her2/rty/wert//abc/abc1/dfgg
-rut12/rty/her2/abc/cfr3//wert/rut12`;
+abc/dfgg/abc1/cfr3/rty/wert/abc/dfgg/abc1/cfr3/rty/wert
+rut12/her2/rty/wert//abc/abc1/dfgg/rut12/her2/rty/wert//abc/abc1/dfgg
+rut12/rty/her2/abc/cfr3//wert/rut12/rut12/rty/her2/abc/cfr3//wert/rut12`;
     [csvTests.sepMsaDna1]: string = `seq
-A-C--G-T--C-T
-C-A-C--T--G-T
-A-C-C-G-T-A-C-T`;
+A-C--G-T--C-T-A-C--G-T--C-T
+C-A-C--T--G-T-C-A-C--T--G-T
+A-C-C-G-T-A-C-T-A-C-C-G-T-A-C-T`;
     [csvTests.sepMsaUnWEmpty]: string = `seq
-m1-M-m3-mon4-mon5-N-T-MON8-N9
-m1-mon2-m3-mon4-mon5-Num--MON8-N9
+m1-M-m3-mon4-mon5-N-T-MON8-N9-m1-M-m3-mon4-mon5-N-T-MON8-N9
+m1-mon2-m3-mon4-mon5-Num--MON8-N9-m1-mon2-m3-mon4-mon5-Num--MON8-N9
 
-mon1-M-mon3-mon4-mon5---MON8-N9`;
+mon1-M-mon3-mon4-mon5---MON8-N9-mon1-M-mon3-mon4-mon5---MON8-N9`;
     [csvTests.sepComplex]: string = `seq
 Ac(1)-F-K(AEEA-AEEA-R-Ac)-L-mF-V-Y-mNle-D-W-N-mF-C(1)-G-NH2
 Ac(1)-F-K(AEEA-ARRA-W-Ac)-L-mF-V-Y-mNle-D-W-N-mF-C(1)-G-NH2
 Ac(1)-F-K(AEEA-AEEA-Ac)-L-mF-V-Y-mNle-D-W-N-mF-C(1)-G-NH2`;
     [csvTests.fastaMsaDna1]: string = `seq
-AC-GT-CT
-CAC-T-GT
-ACCGTACT`;
+AC-GT-CTAC-GT-CT
+CAC-T-GTCAC-T-GT
+ACCGTACTACCGTACT`;
     [csvTests.fastaMsaPt1]: string = `seq
-FWR-WYV-KHP
-YNR-WYV-KHP
-MWRSWY-CKHP`;
+FWR-WYV-KHPFWR-WYV-KHP
+YNR-WYV-KHPYNR-WYV-KHP
+MWRSWY-CKHPMWRSWY-CKHP`;
   }();
 
   const enum Samples {

package/src/tests/detectors-weak-and-likely-tests.ts

@@ -28,35 +28,35 @@ category('detectors:weak-and-likely', () => {
 
   const csvData: { [name: string]: string } = {
     [csvTests.fastaDnaWeak1]: `id,colName
-1,TTTTT
-2,TTTTT
-3,TTTTT
-4,TTTTT`,
+1,TTTTTTTTTT
+2,TTTTTTTTTT
+3,TTTTTTTTTT
+4,TTTTTTTTTT`,
     [csvTests.fastaDnaWeak1LikelyName]: `id,seq
-1,TTTTT
-2,TTTTT
-3,TTTTT
-4,TTTTT`,
+1,TTTTTTT
+2,TTTTTTT
+3,TTTTTTT
+4,TTTTTTT`,
     [csvTests.fastaRnaWeak1]: `id,colName
-1,UUUUU
-2,UUUUU
-3,UUUUU
-4,UUUUU`,
+1,UUUUUUUUUU
+2,UUUUUUUUUU
+3,UUUUUUUUUU
+4,UUUUUUUUUU`,
     [csvTests.fastaRnaWeak1LikelyName]: `id,seq
-1,UUUUU
-2,UUUUU
-3,UUUUU
-4,UUUUU`,
+1,UUUUUUU
+2,UUUUUUU
+3,UUUUUUU
+4,UUUUUUU`,
     [csvTests.fastaPtWeak1]: `id,colName
-1,SLSLSPGK
-2,SLSLSPGK
-3,SLSLSPGK
-4,SLSLSPGK`,
+1,SLSLSPGKSLSLSPGK
+2,SLSLSPGKSLSLSPGK
+3,SLSLSPGKSLSLSPGK
+4,SLSLSPGKSLSLSPGK`,
     [csvTests.fastaPtWeak1LikelyName]: `id,seq
-1,SLSLSPGK
-2,SLSLSPGK
-3,SLSLSPGK
-4,SLSLSPGK`,
+1,SLSLSPGKSLSLSPGK
+2,SLSLSPGKSLSLSPGK
+3,SLSLSPGKSLSLSPGK
+4,SLSLSPGKSLSLSPGK`,
     [csvTests.fastaUn1]: `id,colName
 1,word
 2,other

package/src/tests/mm-distance-tests.ts

@@ -27,19 +27,20 @@ category('Distance', async () => {
   const prot6 = 'FWRRRRY';
 
   const protTable = `seq
-      FWRWYVKHP
-      YNRWYVKHP
-      MWRSWYCKHP`;
+FWRWYVKHPFWRWYVKHP
+YNRWYVKHPYNRWYVKHP
+MWRSWYCKHPMWRSWYCKHP`;
 
   const DNATable = `seq
-      ATAACG
-      ATCGA
-      ATCGA`;
+ATAACGATAACG
+ATCGAATCGA
+ATCGAATCGA`;
 
   const MSATable = `seq
-      ATAAC
-      ATCGA
-      ATCGA`;
+ATAACATAAC
+ATCGAATCGA
+ATCGAATCGA`;
+
   test('protein-distance-function', async () => {
     const uh = await _initMacromoleculeColumn(protTable);
     const distFunc = uh.getDistanceFunctionName();

package/src/tests/units-handler-splitted-tests.ts

@@ -1,96 +1,120 @@
 import * as grok from 'datagrok-api/grok';
-import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
 
-import wu from 'wu';
-
-import {category, test, expect, expectArray} from '@datagrok-libraries/utils/src/test';
+import {category, expect, expectArray, test} from '@datagrok-libraries/utils/src/test';
 import {GapSymbols, UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
 import {NOTATION} from '@datagrok-libraries/bio/src/utils/macromolecule';
 import {ISeqSplitted} from '@datagrok-libraries/bio/src/utils/macromolecule/types';
 
+enum Tests {
+  fasta = 'fasta',
+  fastaMsa = 'fastaMsa',
+  separator = 'separator',
+  separatorMsa = 'separatorMsa',
+  helm = 'helm',
+}
+
 category('UnitsHandler', () => {
   const fG = GapSymbols[NOTATION.FASTA];
   const hG = GapSymbols[NOTATION.HELM];
   const sG = GapSymbols[NOTATION.SEPARATOR];
-  const data: { [testName: string]: { src: { csv: string }, tgt: { splitted: (string[] | string)[] } } } = {
-    fasta: {
+  const data: {
+    [testName: string]: {
+      src: { csv: string },
+      tgt: { notation: NOTATION, separator?: string, splitted: (string[] | string)[] }
+    }
+  } = {
+    [Tests.fasta]: {
       src: {
         csv: `seq
-ACGTC
-CAGTGT
-TTCAAC`
+ACGTCACGTC
+CAGTGTCAGTGT
+TTCAACTTCAAC`
       },
       tgt: {
+        notation: NOTATION.FASTA,
         splitted: [
-          'ACGTC',
-          'CAGTGT',
-          'TTCAAC',
+          'ACGTCACGTC',
+          'CAGTGTCAGTGT',
+          'TTCAACTTCAAC',
         ]
       }
     },
-    fastaMsa: {
+    [Tests.fastaMsa]: {
       src: {
         csv: `seq
-AC-GT-CT
-CAC-T-GT
-ACCGTACT`,
+AC-GT-CTAC-GT-CT
+CAC-T-GTCAC-T-GT
+ACCGTACTACCGTACT`,
       },
       tgt: {
+        notation: NOTATION.FASTA,
         splitted: [
           //@formatter:off
-          'AC-GT-CT',
-          'CAC-T-GT',
-          'ACCGTACT',
+          'AC-GT-CTAC-GT-CT',
+          'CAC-T-GTCAC-T-GT',
+          'ACCGTACTACCGTACT',
           //@formatter:on
         ]
       }
     },
-    separator: {
+    [Tests.separator]: {
       src: {
         csv: `seq
-abc-dfgg-abc1-cfr3-rty-wert
-rut12-her2-rty-wert-abc-abc1-dfgg
-rut12-rty-her2-abc-cfr3-wert-rut12`,
+abc-dfgg-abc1-cfr3-rty-wert-abc-dfgg-abc1-cfr3-rty-wert
+rut12-her2-rty-wert-abc-abc1-dfgg-rut12-her2-rty-wert-abc
+rut12-rty-her2-abc-cfr3-wert-rut12-rut12-rty-her2-abc-cfr3`,
       },
       tgt: {
+        notation: NOTATION.SEPARATOR,
+        separator: '-',
         splitted: [
-          ['abc', 'dfgg', 'abc1', 'cfr3', 'rty', 'wert'],
-          ['rut12', 'her2', 'rty', 'wert', 'abc', 'abc1', 'dfgg'],
-          ['rut12', 'rty', 'her2', 'abc', 'cfr3', 'wert', 'rut12']
+          ['abc', 'dfgg', 'abc1', 'cfr3', 'rty', 'wert', 'abc', 'dfgg', 'abc1', 'cfr3', 'rty', 'wert'],
+          ['rut12', 'her2', 'rty', 'wert', 'abc', 'abc1', 'dfgg', 'rut12', 'her2', 'rty', 'wert', 'abc'],
+          ['rut12', 'rty', 'her2', 'abc', 'cfr3', 'wert', 'rut12', 'rut12', 'rty', 'her2', 'abc', 'cfr3']
         ]
       }
     },
 
-    separatorMsa: {
+    [Tests.separatorMsa]: {
       src: {
         csv: `seq
-abc-dfgg-abc1-cfr3-rty-wert
-rut12-her2-rty--abc1-dfgg
-rut12-rty-her2---wert`
+rut0-dfgg-abc1-cfr3-rty-wert-abc-dfgg-abc1-cfr3-rty-wert
+rut1-her2-rty--abc1-dfgg-rut12-her2-rty--abc1-dfgg
+rut2-rty-her2---wert-rut12-rty-her2---wert
+\"rut3-rty-her2-\"\"-\"\"-\"\"-\"\"-wert-rut12-rty-her2-\"\"-\"\"-\"\"-\"\"-wert\"
+\"\"\"-\"\"-rut4-her2-wert-rut12-rty-her2-wert\"
+\"rut5-rty-her2-wert-rut12-rty-her2-wert-\"\"-\"\"\"`
       },
       tgt: {
+        notation: NOTATION.SEPARATOR,
+        separator: '-',
         splitted: [
-          ['abc', 'dfgg', 'abc1', 'cfr3', 'rty', 'wert'],
-          ['rut12', 'her2', 'rty', sG, 'abc1', 'dfgg'],
-          ['rut12', 'rty', 'her2', sG, sG, 'wert'],
+          ['rut0', 'dfgg', 'abc1', 'cfr3', 'rty', 'wert', 'abc', 'dfgg', 'abc1', 'cfr3', 'rty', 'wert'],
+          ['rut1', 'her2', 'rty', sG, 'abc1', 'dfgg', 'rut12', 'her2', 'rty', sG, 'abc1', 'dfgg'],
+          ['rut2', 'rty', 'her2', sG, sG, 'wert', 'rut12', 'rty', 'her2', sG, sG, 'wert'],
+          ['rut3', 'rty', 'her2', sG, sG, 'wert', 'rut12', 'rty', 'her2', sG, sG, 'wert'],
+          [sG, 'rut4', 'her2', 'wert', 'rut12', 'rty', 'her2', 'wert'],
+          ['rut5', 'rty', 'her2', 'wert', 'rut12', 'rty', 'her2', 'wert', sG],
         ]
       }
     },
-    helm: {
+
+    [Tests.helm]: {
       src: {
         csv: `seq
-PEPTIDE1{meI.hHis.Aca.N.T.dE.Thr_PO3H2.Aca.D-Tyr_Et}$$$$
-PEPTIDE1{meI.hHis.Aca.Cys_SEt.T.dK.Thr_PO3H2.Aca}$$$$
-PEPTIDE1{Lys_Boc.hHis.Aca.Cys_SEt.T.dK.Thr_PO3H2.Aca}$$$$
-PEPTIDE1{meI.hHis.Aca.Cys_SEt.T.dK.Thr_PO3H2}$$$$`
+PEPTIDE1{meI.hHis.Aca.N.T.dE.Thr_PO3H2.Aca.D-Tyr_Et.Thr_PO3H2.Aca.D-Tyr_Et}$$$$
+PEPTIDE1{meI.hHis.Aca.Cys_SEt.T.dK.Thr_PO3H2.Aca.dK.Thr_PO3H2.Aca}$$$$
+PEPTIDE1{Lys_Boc.hHis.Aca.Cys_SEt.T.dK.Thr_PO3H2.Aca.dK.Thr_PO3H2.Aca}$$$$
+PEPTIDE1{meI.hHis.Aca.Cys_SEt.T.dK.Thr_PO3H2.T.dK.Thr_PO3H2}$$$$`
       },
       tgt: {
+        notation: NOTATION.HELM,
         splitted: [
-          ['meI', 'hHis', 'Aca', 'N', 'T', 'dE', 'Thr_PO3H2', 'Aca', 'D-Tyr_Et'],
-          ['meI', 'hHis', 'Aca', 'Cys_SEt', 'T', 'dK', 'Thr_PO3H2', 'Aca'],
-          ['Lys_Boc', 'hHis', 'Aca', 'Cys_SEt', 'T', 'dK', 'Thr_PO3H2', 'Aca'],
-          ['meI', 'hHis', 'Aca', 'Cys_SEt', 'T', 'dK', 'Thr_PO3H2'],
+          ['meI', 'hHis', 'Aca', 'N', 'T', 'dE', 'Thr_PO3H2', 'Aca', 'D-Tyr_Et', 'Thr_PO3H2', 'Aca', 'D-Tyr_Et'],
+          ['meI', 'hHis', 'Aca', 'Cys_SEt', 'T', 'dK', 'Thr_PO3H2', 'Aca', 'dK', 'Thr_PO3H2', 'Aca'],
+          ['Lys_Boc', 'hHis', 'Aca', 'Cys_SEt', 'T', 'dK', 'Thr_PO3H2', 'Aca', 'dK', 'Thr_PO3H2', 'Aca'],
+          ['meI', 'hHis', 'Aca', 'Cys_SEt', 'T', 'dK', 'Thr_PO3H2', 'T', 'dK', 'Thr_PO3H2'],
         ]
       }
     }
@@ -106,8 +130,11 @@ PEPTIDE1{meI.hHis.Aca.Cys_SEt.T.dK.Thr_PO3H2}$$$$`
       expect(col.semType, DG.SEMTYPE.MACROMOLECULE);
 
       const uh = UnitsHandler.getOrCreate(col);
+      expect(uh.notation, testData.tgt.notation);
+      expect(uh.separator === testData.tgt.separator, true);
+
       const resSplitted: ISeqSplitted[] = uh.splitted;
       expectArray(resSplitted, testData.tgt.splitted);
-    });
+    }, testName == Tests.separatorMsa ? {skipReason: '#2468 CSV row starting with the quote character'} : undefined);
   }
 });

package/src/tests/units-handler-tests.ts

@@ -7,19 +7,19 @@ import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
 import {ALPHABET, NOTATION, TAGS} from '@datagrok-libraries/bio/src/utils/macromolecule';
 
 const seqDna = `seq
-ACGTC
-CAGTGT
-TTCAAC`;
+ACGTCACGTC
+CAGTGTCAGTGT
+TTCAACTTCAAC`;
 
 const seqDnaMsa = `seq
-AC-GT-CT
-CAC-T-GT
-ACCGTACT`;
+AC-GT-CTAC-GT-CT
+CAC-T-GTCAC-T-GT
+ACCGTACTACCGTACT`;
 
 const seqUn = `seq
-abc-dfgg-abc1-cfr3-rty-wert
-rut12-her2-rty-wert-abc-abc1-dfgg
-rut12-rty-her2-abc-cfr3-wert-rut12`;
+abc-dfgg-abc1-cfr3-rty-wert-abc-dfgg-abc1-cfr3-rty-wert
+rut12-her2-rty-wert-abc-abc1-dfgg-rut12-her2-rty-wert-abc-abc1-dfgg
+rut12-rty-her2-abc-cfr3-wert-rut12-rut12-rty-her2-abc-cfr3-wert-rut12`;
 
 const seqHelm = `seq
 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}$$$$