@datagrok/bio 2.11.3 → 2.11.6

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

@@ -1,10 +1,7 @@
 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';
@@ -17,31 +14,31 @@ category('UnitsHandler', () => {
     fasta: {
       src: {
         csv: `seq
-ACGTC
-CAGTGT
-TTCAAC`
+ACGTCACGTC
+CAGTGTCAGTGT
+TTCAACTTCAAC`
       },
       tgt: {
         splitted: [
-          'ACGTC',
-          'CAGTGT',
-          'TTCAAC',
+          'ACGTCACGTC',
+          'CAGTGTCAGTGT',
+          'TTCAACTTCAAC',
         ]
       }
     },
     fastaMsa: {
       src: {
         csv: `seq
-AC-GT-CT
-CAC-T-GT
-ACCGTACT`,
+AC-GT-CTAC-GT-CT
+CAC-T-GTCAC-T-GT
+ACCGTACTACCGTACT`,
       },
       tgt: {
         splitted: [
           //@formatter:off
-          'AC-GT-CT',
-          'CAC-T-GT',
-          'ACCGTACT',
+          'AC-GT-CTAC-GT-CT',
+          'CAC-T-GTCAC-T-GT',
+          'ACCGTACTACCGTACT',
           //@formatter:on
         ]
       }
@@ -49,15 +46,15 @@ ACCGTACT`,
     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: {
         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']
         ]
       }
     },
@@ -65,32 +62,32 @@ rut12-rty-her2-abc-cfr3-wert-rut12`,
     separatorMsa: {
       src: {
         csv: `seq
-abc-dfgg-abc1-cfr3-rty-wert
-rut12-her2-rty--abc1-dfgg
-rut12-rty-her2---wert`
+abc-dfgg-abc1-cfr3-rty-wert-abc-dfgg-abc1-cfr3-rty-wert
+rut12-her2-rty--abc1-dfgg-rut12-her2-rty--abc1-dfgg
+rut12-rty-her2---wert-rut12-rty-her2---wert`
       },
       tgt: {
         splitted: [
-          ['abc', 'dfgg', 'abc1', 'cfr3', 'rty', 'wert'],
-          ['rut12', 'her2', 'rty', sG, 'abc1', 'dfgg'],
-          ['rut12', 'rty', 'her2', sG, sG, 'wert'],
+          ['abc', 'dfgg', 'abc1', 'cfr3', 'rty', 'wert', 'abc', 'dfgg', 'abc1', 'cfr3', 'rty', 'wert'],
+          ['rut12', 'her2', 'rty', sG, 'abc1', 'dfgg', 'rut12', 'her2', 'rty', sG, 'abc1', 'dfgg'],
+          ['rut12', 'rty', 'her2', sG, sG, 'wert', 'rut12', 'rty', 'her2', sG, sG, 'wert'],
         ]
       }
     },
     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: {
         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'],
         ]
       }
     }

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}$$$$

package/src/utils/detect-macromolecule-probe.ts

@@ -0,0 +1,44 @@
+import * as grok from 'datagrok-api/grok';
+import * as ui from 'datagrok-api/ui';
+import * as DG from 'datagrok-api/dg';
+
+
+import {_package} from '../package';
+import {delay} from '@datagrok-libraries/utils/src/test';
+
+type IDetectorReport = { categoriesSample: any[], rejectReason: string };
+
+type IDetectorDebugStore = { last: IDetectorReport };
+
+export async function detectMacromoleculeProbeDo(
+  csv: string, colName: string | undefined, probeCount: number
+): Promise<void> {
+  const pi = DG.TaskBarProgressIndicator.create(`detectMacromolecule probe ...`);
+  try {
+    let progressLast = 0;
+    const store: IDetectorDebugStore = await grok.functions.call('Bio:detectMacromoleculeEnableStore');
+    let failCount: number = 0;
+    for (let i = 0; i < probeCount; ++i) {
+      const df: DG.DataFrame = DG.DataFrame.fromCsv(csv);
+      const seqCol = colName ? df.getCol(colName) : df.columns.byIndex(0);
+
+      const detectRes: string = await grok.functions.call('Bio:detectMacromolecule', {col: seqCol});
+      if (detectRes !== DG.SEMTYPE.MACROMOLECULE) {
+        ++failCount;
+        console.warn(`Reject reason: ${store.last.rejectReason}`);
+      }
+      const progress = i / probeCount;
+      if ((progress - progressLast) >= 0.1) {
+        progressLast = progress;
+        pi.update(100 * progress, `detectMacromolecule probe ${failCount}/${i}/${probeCount} ...`);
+        await delay(0);
+      }
+    }
+    if (failCount > 0)
+      grok.shell.warning(`detectMacromolecule failed ${failCount} / ${probeCount}`);
+    else
+      grok.shell.info(`detectMacromolecule success ${probeCount}`);
+  } finally {
+    pi.close();
+  }
+}

package/src/utils/monomer-lib.ts

@@ -8,9 +8,7 @@ import {IMonomerLib, Monomer} from '@datagrok-libraries/bio/src/types/index';
 import {MolfileHandler} from '@datagrok-libraries/chem-meta/src/parsing-utils/molfile-handler';
 import {
   createJsonMonomerLibFromSdf,
-  getJsonMonomerLibForEnumerator,
   IMonomerLibHelper,
-  isValidEnumeratorLib,
 } from '@datagrok-libraries/bio/src/monomer-works/monomer-utils';
 import {
   HELM_REQUIRED_FIELDS as REQ, HELM_OPTIONAL_FIELDS as OPT, HELM_POLYMER_TYPE
@@ -18,12 +16,8 @@ import {
 
 import {_package} from '../package';
 
-const _HELM_REQUIRED_FIELDS_ARRAY = [
-  REQ.SYMBOL, REQ.NAME, REQ.MOLFILE, REQ.AUTHOR, REQ.ID,
-  REQ.RGROUPS, REQ.SMILES, REQ.POLYMER_TYPE, REQ.MONOMER_TYPE, REQ.CREATE_DATE,
-] as const;
+import {PolyToolMonomerLibHandler} from '@datagrok-libraries/bio/src/utils/poly-tool/monomer-lib-handler';
 
-const _HELM_OPTIONAL_FIELDS_ARRAY = [OPT.NATURAL_ANALOG, OPT.META] as const;
 // -- Monomer libraries --
 export const LIB_STORAGE_NAME = 'Libraries';
 export const LIB_PATH = 'System:AppData/Bio/libraries/';
@@ -291,8 +285,9 @@ export class MonomerLibHelper implements IMonomerLibHelper {
       }
       const df = await fileSource.readCsv(fileName);
       const json = toJson(df);
-      if (isValidEnumeratorLib(json))
-        rawLibData = getJsonMonomerLibForEnumerator(json);
+      const polyToolMonomerLib = new PolyToolMonomerLibHandler(json);
+      if (polyToolMonomerLib.isValid())
+        rawLibData = polyToolMonomerLib.getJsonMonomerLib();
       else
         throw new Error('Invalid format of CSV monomer lib');
     } else {