@datagrok/bio - npm Package Compare versions

Comparing version 2.12.9 to 2.12.10

CHANGELOG.md

 # Bio changelog
 
+## 2.12.10 (2024-04-11)
+
+### Bug fixes
+
+* Bio: Fix detector for non-fasta seqs of the same length
+
 ## 2.12.9 (2024-04-10)
@@ -4,0 +10,0 @@

detectors.js

@@ -239,3 +239,5 @@ /**
 
-      if (statsAsChars.sameLength) { // MSA FASTA single character
+      if (statsAsChars.sameLength && !separator &&
+        !(['[', ']'].some((c) => c in statsAsChars.freq)) // not fasta ext notation
+      ) { // MSA FASTA single character
         const stats = this.getStats(categoriesSample, seqMinLength, splitter);
@@ -371,4 +373,4 @@ const alphabet = this.detectAlphabet(stats.freq, candidateAlphabets, '-', colNameLikely ? 0.20 : 0);
 
-    return (sepRate / expSepRate > 2.2 && mLengthVarN < 0.7) ||
-    (sepRate / expSepRate > 4) ? sep : null;
+    return (sepRate / expSepRate > 2.2 && mLengthVarN < 0.8) ||
+    (sepRate / expSepRate > 3.5) ? sep : null;
   }
@@ -375,0 +377,0 @@

package.json

@@ -8,3 +8,3 @@ {
   },
-  "version": "2.12.9",
+  "version": "2.12.10",
   "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.",
@@ -55,3 +55,4 @@ "repository": {
     "umap-js": "^1.3.3",
-    "wu": "latest"
+    "wu": "latest",
+    "@webgpu/types": "^0.1.40"
   },
@@ -111,2 +112,3 @@ "devDependencies": {
   "meta": {
+    "dartium": false,
     "menu": {
@@ -142,2 +144,2 @@ "Bio": {
   }
-}
+}

src/tests/detectors-tests.ts

@@ -24,9 +24,16 @@ import * as grok from 'datagrok-api/grok';
 
+
+class PosCol {
+  constructor(
+    public readonly units: string,
+    public readonly aligned: string | null,
+    public readonly alphabet: string | null,
+    public readonly alphabetSize: number,
+    public readonly alphabetIsMultichar?: boolean,
+    public readonly separator?: string,
+  ) { };
+}
+
 category('detectors', () => {
   const enum csvTests {
-    negEmpty = 'negEmpty',
-    neg1 = 'neg1',
-    neg2 = 'neg2',
-    neg3 = 'neg3',
-    negSmiles = 'negSmiles',
     fastaDna1 = 'csvFastaDna1',
@@ -46,6 +53,13 @@ fastaRna1 = 'fastaRna1',
     fastaMsaPt1 = 'fastaMsaPt1',
+    fastaMsaSameLength = 'fastaMsaSameLength',
+    fastaExtSameLength = 'fastaExtSameLength',
+    fastaMsaExtSameLength = 'fastaMsaExtSameLength',
+    sepSameLength = 'sepSameLength',
+    sepMsaSameLength = 'sepMsaSameLength',
+    helmSameLength = 'helmSameLength',
   }
 
-  const csvData = new class {
-    [csvTests.negEmpty]: string = `id,col1
+  const csvData2: { [testName: string]: { csv: string, neg?: string[], pos?: { [colName: string]: PosCol } } } = {
+    'negEmpty': {
+      csv: `id,col1
 1,
@@ -55,13 +69,22 @@ 2,
 4,
-5,`;
-    [csvTests.neg1]: string = `col1
+5,`,
+      neg: ['col1']
+    },
+    'negNum1': {
+      csv: `col1
 1
 2
-3`;
-    [csvTests.neg2]: string = `col1
+3`,
+      neg: ['col1'],
+    },
+    'negNum2': {
+      csv: `col1
 4
 5
 6
-7`;
-    [csvTests.neg3]: string = `col1
+7`,
+      neg: ['col1'],
+    },
+    'negNum3': {
+      csv: `col1
 8
@@ -71,7 +94,85 @@ 9
 11
-12`;
-    [csvTests.negSmiles]: string = `col1
+12`,
+      neg: ['col1'],
+    },
+
+    'negSmiles': {
+      csv: `col1
 CCCCN1C(=O)CN=C(c2cc(F)ccc12)C3CCCCC3
 C1CCCCC1
-CCCCCC`;
+CCCCCC`,
+      neg: ['col1'],
+    },
+
+    // Same length
+    'fastaMsaSameLength': {
+      csv: `seq
+FWPHEYFWPHEYYV
+YNRQWYVYNRQWYV
+MKPSEYVMKPSEYV`,
+      pos: {'seq': new PosCol(NOTATION.FASTA, ALIGNMENT.SEQ_MSA, ALPHABET.PT, 20, false, undefined)}
+    },
+    'fastaExtSameLength': {
+      csv: `seq
+FW[Ac]PHEYFWPH
+YN[Re]VYNRQWYV
+[Me]EYVMPS[Et]`,
+      pos: {'seq': new PosCol(NOTATION.FASTA, ALIGNMENT.SEQ, ALPHABET.UN, 16, true, undefined)},
+    },
+    'fastaMsaExtSameLength': {
+      csv: `seq
+FW[Ac]PHEY[Re]WPH
+YN[Re]VYNR[Ac]WYV
+[Me]EYVMPSFW[Me]H`,
+      pos: {'seq': new PosCol(NOTATION.FASTA, ALIGNMENT.SEQ_MSA, ALPHABET.UN, 14, true, undefined)},
+    },
+    'sepSameLength': {
+      csv: `seq
+Ac(1)-A-A-A-A-A-A-A-A-A-A-A-A-A-C(1)-G-NH2
+Ac(1)-A-A-A-A-A-A-A-A-A-A-A-A-A-C(1)-G-NH2
+Ac(1)-A-A-A-A-A-A-A-A-A-A-A-A-A-C(1)-G-NH2`, pos: {
+        'seq': new PosCol(NOTATION.SEPARATOR, ALIGNMENT.SEQ_MSA, ALPHABET.UN, 5, true, '-'),
+      }
+    },
+    'sepMsaSameLength': {
+      csv: `seq
+Ac(1)-A-A-A-A-A-A-A-A-A-A-A-A-A-C(1)-G-NH2
+Ac(1)-A-A(2)-A-A-A-C(2)-A-A-A-A-C(1)-G-NH2
+Ac(1)-A-A-A-A-A-A-A-A-A-A-A-A-A-C(1)-G-NH2`, pos: {
+        'seq': new PosCol(NOTATION.SEPARATOR, ALIGNMENT.SEQ, ALPHABET.UN, 5, true, '-'),
+      }
+    },
+    'helmSameLength': {
+      csv: `seq
+PEPTIDE1{Ac(1).A.A.A.A.A.A.A.A.A.A.A.A.A.C(1).G.NH2}$$$$
+PEPTIDE1{Ab(1).Y.V.K.H.P.F.W.R.W.Y.A.A.A.C(1).G.NH2}$$$$
+PEPTIDE1{Ad(1).S.W.Y.C.K.H.P.M.W.A.A.A.A.C(1)-G-NH2}$$$$`,
+      pos: {
+        'seq': new PosCol(NOTATION.HELM, null, null, 19, undefined, undefined)
+      }
+    },
+  };
+
+  const readCsv2: (key: keyof typeof csvData2) => DfReaderFunc = (key: keyof typeof csvData2) => {
+    return async () => {
+      const csv: string = csvData2[key].csv;
+      const df: DG.DataFrame = DG.DataFrame.fromCsv(csv);
+      await grok.data.detectSemanticTypes(df);
+      return df;
+    };
+  };
+
+  for (const [testName, testData] of Object.entries(csvData2)) {
+    test(`csvData2-${testName}`, async () => {
+      const reader = readCsv2(testName as csvTests);
+      for (const negColName of testData.neg ?? [])
+        await _testNeg(reader, negColName);
+      for (const [posColName, posCol] of Object.entries(testData.pos ?? {})) {
+        await _testPos(reader, posColName, posCol.units, posCol.aligned,
+          posCol.alphabet, posCol.alphabetSize, posCol.alphabetIsMultichar, posCol.separator);
+      }
+    });
+  }
+
+  const csvData = new class {
     [csvTests.fastaDna1]: string = `seq
@@ -215,3 +316,3 @@ ACGTCACGTC
 
-  const readCsv: (key: csvTests) => DfReaderFunc = (key: keyof typeof csvData) => {
+  const readCsv: (key: keyof typeof csvData) => DfReaderFunc = (key: keyof typeof csvData) => {
     return async () => {
@@ -226,8 +327,2 @@ // Always recreate test data frame from CSV for reproducible detector behavior in tests.
 
-
-  test('NegativeEmpty', async () => { await _testNeg(readCsv(csvTests.negEmpty), 'col1'); });
-  test('Negative1', async () => { await _testNeg(readCsv(csvTests.neg1), 'col1'); });
-  test('Negative2', async () => { await _testNeg(readCsv(csvTests.neg2), 'col1'); });
-  test('Negative3', async () => { await _testNeg(readCsv(csvTests.neg3), 'col1'); });
-  test('NegativeSmiles', async () => { await _testNeg(readCsv(csvTests.negSmiles), 'col1'); });
   test('NegativeStartEnd', async () => { await _testNegList(['START', 'END']); });
@@ -452,4 +547,4 @@ test('NegativeStartEndIntermediate', async () => { await _testNegList(['START', 'END', 'INTERMEDIATE']); });
 export async function _testPos(
-  readDf: DfReaderFunc, colName: string, units: string,
-  aligned: string | null, alphabet: string | null, alphabetSize: number, alphabetIsMultichar: boolean,
+  readDf: DfReaderFunc, colName: string, units: string, aligned: string | null,
+  alphabet: string | null, alphabetSize: number, alphabetIsMultichar?: boolean,
   separator: string | null = null,
@@ -480,12 +575,2 @@ ) {
 
-class PosCol {
-  constructor(
-    public readonly units: string,
-    public readonly aligned: string | null,
-    public readonly alphabet: string | null,
-    public readonly alphabetSize: number,
-    public readonly alphabetIsMultichar: boolean,
-    public readonly separator?: string,
-  ) { };
-}
 
@@ -492,0 +577,0 @@ export async function _testDf(readDf: DfReaderFunc, posCols: { [colName: string]: PosCol }): Promise<void> {

src/utils/helm-to-molfile.ts

@@ -93,3 +93,3 @@ /* Do not change these import lines to match external modules in webpack configuration */
   async getMolV3000ViaOCL(beautifiedMols: (RDMol | null)[], columnName: string) {
-    const beautifiedMolV2000 =  beautifiedMols.map((mol) => {
+    const beautifiedMolV2000 = beautifiedMols.map((mol) => {
       if (mol === null)
@@ -107,7 +107,7 @@ return '';
       molv3000Arr[i] = molV3000.replace('STERAC1', 'STEABS');
-      const progress = i/beautifiedMolV2000.length*100;
+      const progress = i / beautifiedMolV2000.length * 100;
       chiralityPb.update(progress, `${progress?.toFixed(2)}% of molecules completed`);
     }
     chiralityPb.close();
-    return DG.Column.fromStrings(columnName, molv3000Arr); 
+    return DG.Column.fromStrings(columnName, molv3000Arr);
   }
@@ -138,3 +138,3 @@
       return molBlock;
-    })); 
+    }));
   }
@@ -141,0 +141,0 @@

src/utils/poly-tool/transformation.ts

@@ -248,10 +248,10 @@ import * as grok from 'datagrok-api/grok';
   molCol.name = df.columns.getUnusedName('molfile(' + molColumn.name + ')');
+  molCol.semType = DG.SEMTYPE.MOLECULE;
 
   if (addHelm) {
     targetHelmCol.setTag('cell.renderer', 'helm');
+    targetHelmCol.semType = DG.SEMTYPE.MACROMOLECULE;
     df.columns.add(targetHelmCol);
   }
   df.columns.add(molCol, true);
-
-  await grok.data.detectSemanticTypes(df);
 }

tsconfig.json

@@ -66,3 +66,3 @@ {
     "emitDecoratorMetadata": true,                  /* Enables experimental support for emitting type metadata for decorators. */
-
+    "typeRoots": ["./node_modules/@webgpu/types", "./node_modules/@types"],
     /* Advanced Options */
@@ -69,0 +69,0 @@ "skipLibCheck": false,                          /* Skip type checking of declaration files. */

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

35407516

increased by0.02%

Lines of code

58909

increased by0.15%

Worsened metrics

Dependency count

20

increased by5.26%

Dependency changes

• + Added@webgpu/types@^0.1.40