@datagrok/bio 2.11.6 → 2.11.7

package/package.json

@@ -5,7 +5,7 @@
     "name": "Leonid Stolbov",
     "email": "lstolbov@datagrok.ai"
   },
-  "version": "2.11.6",
+  "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/tests/units-handler-splitted-tests.ts

@@ -6,12 +6,25 @@ import {GapSymbols, UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-
 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
 ACGTCACGTC
@@ -19,6 +32,7 @@ CAGTGTCAGTGT
 TTCAACTTCAAC`
       },
       tgt: {
+        notation: NOTATION.FASTA,
         splitted: [
           'ACGTCACGTC',
           'CAGTGTCAGTGT',
@@ -26,7 +40,7 @@ TTCAACTTCAAC`
         ]
       }
     },
-    fastaMsa: {
+    [Tests.fastaMsa]: {
       src: {
         csv: `seq
 AC-GT-CTAC-GT-CT
@@ -34,6 +48,7 @@ CAC-T-GTCAC-T-GT
 ACCGTACTACCGTACT`,
       },
       tgt: {
+        notation: NOTATION.FASTA,
         splitted: [
           //@formatter:off
           'AC-GT-CTAC-GT-CT',
@@ -43,7 +58,7 @@ ACCGTACTACCGTACT`,
         ]
       }
     },
-    separator: {
+    [Tests.separator]: {
       src: {
         csv: `seq
 abc-dfgg-abc1-cfr3-rty-wert-abc-dfgg-abc1-cfr3-rty-wert
@@ -51,6 +66,8 @@ 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', 'abc', 'dfgg', 'abc1', 'cfr3', 'rty', 'wert'],
           ['rut12', 'her2', 'rty', 'wert', 'abc', 'abc1', 'dfgg', 'rut12', 'her2', 'rty', 'wert', 'abc'],
@@ -59,22 +76,31 @@ rut12-rty-her2-abc-cfr3-wert-rut12-rut12-rty-her2-abc-cfr3`,
       }
     },
 
-    separatorMsa: {
+    [Tests.separatorMsa]: {
       src: {
         csv: `seq
-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`
+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', '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'],
+          ['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.Thr_PO3H2.Aca.D-Tyr_Et}$$$$
@@ -83,6 +109,7 @@ PEPTIDE1{Lys_Boc.hHis.Aca.Cys_SEt.T.dK.Thr_PO3H2.Aca.dK.Thr_PO3H2.Aca}$$$$
 PEPTIDE1{meI.hHis.Aca.Cys_SEt.T.dK.Thr_PO3H2.T.dK.Thr_PO3H2}$$$$`
       },
       tgt: {
+        notation: NOTATION.HELM,
         splitted: [
           ['meI', 'hHis', 'Aca', 'N', 'T', 'dE', 'Thr_PO3H2', 'Aca', 'D-Tyr_Et', 'Thr_PO3H2', 'Aca', 'D-Tyr_Et'],
           ['meI', 'hHis', 'Aca', 'Cys_SEt', 'T', 'dK', 'Thr_PO3H2', 'Aca', 'dK', 'Thr_PO3H2', 'Aca'],
@@ -103,8 +130,11 @@ PEPTIDE1{meI.hHis.Aca.Cys_SEt.T.dK.Thr_PO3H2.T.dK.Thr_PO3H2}$$$$`
       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);
   }
 });