@datagrok/bio 1.2.0 → 1.3.1

package/package.json

@@ -2,7 +2,7 @@
   "name": "@datagrok/bio",
   "beta": false,
   "friendlyName": "Bio",
-  "version": "1.2.0",
+  "version": "1.3.1",
   "description": "Bio is a [package](https://datagrok.ai/help/develop/develop#packages) for the [Datagrok](https://datagrok.ai) platform",
   "repository": {
     "type": "git",
@@ -10,10 +10,10 @@
     "directory": "packages/Bio"
   },
   "dependencies": {
-    "@datagrok-libraries/bio": "^2.1.0",
+    "@datagrok-libraries/bio": "^2.1.4",
     "@datagrok-libraries/utils": "^0.4.2",
     "cash-dom": "latest",
-    "datagrok-api": "^1.3.5",
+    "datagrok-api": "^1.4.10",
     "dayjs": "latest",
     "ts-loader": "^9.2.5",
     "typescript": "^4.4.2"

package/src/package-test.ts

@@ -2,17 +2,20 @@ import * as DG from 'datagrok-api/dg';
 
 import {runTests, tests} from '@datagrok-libraries/utils/src/test';
 
-import './tests/WebLogo.test';
+import './tests/WebLogo-test';
+import './tests/Palettes-test';
+import './tests/detectors-test';
 
 export const _packageTest = new DG.Package();
 export {tests};
 
+/** For the 'test' function argument names are fixed as 'category' and 'test' because of way it is called. */
 //name: test
 //input: string category {optional: true}
-//input: string t {optional: true}
+//input: string test {optional: true}
 //output: dataframe result
 //top-menu: Tools | Dev | JS API Tests
-export async function test(category: string, t: string): Promise<DG.DataFrame> {
-  const data = await runTests({category, test: t});
+export async function test(category: string, test: string): Promise<DG.DataFrame> {
+  const data = await runTests({category, test});
   return DG.DataFrame.fromObjects(data)!;
 }

package/src/package.ts

@@ -7,6 +7,7 @@ import {SequenceAlignment, Aligned} from './seq_align';
 export const _package = new DG.Package();
 
 import {WebLogo} from '@datagrok-libraries/bio/src/viewers/web-logo';
+import {VdRegionsViewer} from './viewers/vd-regions-viewer';
 
 //name: sequenceAlignment
 //input: string alignType {choices: ['Local alignment', 'Global alignment']}
@@ -29,3 +30,11 @@ export function sequenceAlignment(alignType: string, alignTable: string, gap: nu
 export function webLogoViewer() {
   return new WebLogo();
 }
+
+//name: VdRegions
+//description: V-Domain regions viewer
+//tags: viewer, panel
+//output: viewer result
+export function vdRegionViewer() {
+  return new VdRegionsViewer();
+}

package/src/tests/{Palettes.test.ts → Palettes-test.ts}

@@ -7,6 +7,6 @@ import * as DG from 'datagrok-api/dg';
 import {_testPaletteN, _testPaletteAA} from '@datagrok-libraries/bio/src/tests/palettes.test';
 
 category('Palettes', () => {
-  test('testPaletteN', async () => { _testPaletteN(); });
-  test('testPaletteAA', async () => { _testPaletteAA(); });
+  test('testPaletteN', async () => { await _testPaletteN(); });
+  test('testPaletteAA', async () => { await _testPaletteAA(); });
 });

package/src/tests/WebLogo-test.ts

@@ -0,0 +1,127 @@
+import {after, before, category, test, expect, expectObject} from '@datagrok-libraries/utils/src/test';
+
+import * as grok from 'datagrok-api/grok';
+import * as ui from 'datagrok-api/ui';
+import * as DG from 'datagrok-api/dg';
+
+import {Nucleotides, NucleotidesPalettes} from '@datagrok-libraries/bio/src/nucleotides';
+import {Aminoacids, AminoacidsPalettes} from '@datagrok-libraries/bio/src/aminoacids';
+import {WebLogo} from '@datagrok-libraries/bio/src/viewers/web-logo';
+import {SeqPalette} from '@datagrok-libraries/bio/src/seq-palettes';
+import {UnknownSeqPalette} from '@datagrok-libraries/bio/src/unknown';
+
+category('WebLogo', () => {
+  const csvDfN1: string = `seq
+ACGTCT
+CAGTGT
+TTCAAC
+`;
+
+  /** 2 - is an error monomer
+   * This sequence set should be classified as nucleotides sequences.
+   * Small error, not similar to amino acids.
+   */
+  const csvDfN1e: string = `seq
+ACGTAT
+CAGTTG
+TTCG2C
+`;
+
+  /** Pure amino acids sequence */
+  const csvDfAA1: string = `seq
+FWPHEYV
+YNRQWYV
+MKPSEYV
+`;
+
+  /** A - alanine, G - glycine, T -= threonine, C - cysteine, W - tryptophan
+   * This sequence set should be detected as amino acids more than nucleotides.
+   */
+  const csvDfAA2: string = `seq
+AGTCAT
+AGTCGC
+AGTCATW
+`;
+
+  /** This sequence set should be recognized as unknown. */
+  const csvDfX: string = `seq
+XZJ{}2
+5Z4733
+3Z6></
+675687
+`;
+
+  // anonymous functions specified in test() registering must return Promise<any>
+  test('testGetAlphabetSimilarity', async () => { await _testGetAlphabetSimilarity(); });
+
+  test('testPickupPaletteN1', async () => { await _testPickupPaletteN1(csvDfN1); });
+  test('testPickupPaletteN1e', async () => { await _testPickupPaletteN1e(csvDfN1e); });
+  test('testPickupPaletteAA1', async () => { await _testPickupPaletteAA1(csvDfAA1); });
+  test('testPickupPaletteX', async () => { await _testPickupPaletteX(csvDfX); });
+});
+
+
+export async function _testGetAlphabetFreqs(dfN1: DG.DataFrame) {
+  const seqCol: DG.Column = dfN1.col('seq')!;
+  const mFreq = WebLogo.getAlphabetFreqs(seqCol);
+
+  expectObject(mFreq, {
+    'A': 4,
+    'C': 5,
+    'G': 3,
+    'T': 6
+  });
+}
+
+export async function _testGetAlphabetSimilarity() {
+  const freq: { [m: string]: number } = {
+    'A': 2041,
+    'C': 3015,
+    'G': 3015,
+    'T': 2048,
+    '-': 1000
+  };
+  const alphabet: Set<string> = new Set(Object.keys(Nucleotides.Names));
+  const res = WebLogo.getAlphabetSimilarity(freq, alphabet);
+
+  expect(res > 0.6, true);
+}
+
+export async function _testPickupPaletteN1(csvDfN1: string) {
+  const df: DG.DataFrame = DG.DataFrame.fromCsv(csvDfN1);
+  const col: DG.Column = df.col('seq')!;
+  const cp = WebLogo.pickUpPalette(col);
+
+  expect(cp instanceof NucleotidesPalettes, true);
+}
+
+export async function _testPickupPaletteN1e(csvDfN1e: string) {
+  const df: DG.DataFrame = DG.DataFrame.fromCsv(csvDfN1e);
+  const col: DG.Column = df.col('seq')!;
+  const cp = WebLogo.pickUpPalette(col);
+
+  expect(cp instanceof NucleotidesPalettes, true);
+}
+
+export async function _testPickupPaletteAA1(csvDfAA1: string) {
+  const df: DG.DataFrame = DG.DataFrame.fromCsv(csvDfAA1);
+  const col: DG.Column = df.col('seq')!;
+  const cp = WebLogo.pickUpPalette(col);
+
+  expect(cp instanceof AminoacidsPalettes, true);
+}
+
+export async function _testPickupPaletteX(csvDfX: string) {
+  const df: DG.DataFrame = DG.DataFrame.fromCsv(csvDfX);
+  const col: DG.Column = df.col('seq')!;
+  const cp = WebLogo.pickUpPalette(col);
+
+  expect(cp instanceof UnknownSeqPalette, true);
+}
+
+export async function _testPickupPaletteAA2(dfAA2: DG.DataFrame) {
+  const seqCol: DG.Column = dfAA2.col('seq')!;
+  const cp = WebLogo.pickUpPalette(seqCol);
+
+  expect(cp instanceof AminoacidsPalettes, true);
+}

package/src/tests/detectors-test.ts

@@ -0,0 +1,166 @@
+import {after, before, category, test, expect, expectObject} from '@datagrok-libraries/utils/src/test';
+
+import * as grok from 'datagrok-api/grok';
+import * as ui from 'datagrok-api/ui';
+import * as DG from 'datagrok-api/dg';
+
+category('detectors', () => {
+  //   const csvDf1: string = `col1
+  // 1
+  // 2
+  // 3`;
+  //
+  //   const csvDf2: string = `col1
+  // 4
+  // 5
+  // 6
+  // 7`;
+  //
+  //   const csvDf3: string = `col1
+  // 8
+  // 9
+  // 10
+  // 11
+  // 12`;
+
+  const csvDfN1: string = `seq
+ACGTC
+CAGTGT
+TTCAAC
+`;
+
+  /** Pure amino acids sequence */
+  const csvDfAA1: string = `seq
+FWPHEY
+YNRQWYV
+MKPSEYV
+`;
+
+  const csvDfSepNt: string = `seq
+A*C*G*T*C
+C*A*G*T*G*T
+T*T*C*A*A*C
+`;
+
+  const csvDfSepPt: string = `seq
+F-W-P-H-E-Y
+Y-N-R-Q-W-Y-V
+M-K-P-S-E-Y-V
+`;
+
+  const csvDfSepUn1: string = `seq
+abc-dfgg-abc1-cfr3-rty-wert
+rut12-her2-rty-wert-abc-abc1-dfgg
+rut12-rty-her2-abc-cfr3-wert-rut12
+`;
+
+  const csvDfSepUn2: string = `seq
+abc/dfgg/abc1/cfr3/rty/wert
+rut12/her2/rty/wert//abc/abc1/dfgg
+rut12/rty/her2/abc/cfr3//wert/rut12
+`;
+
+  const csvDfSepMsaN1: string = `seq
+A-C--G-T--C-T
+C-A-C--T--G-T
+A-C-C-G-T-A-C-T
+`;
+
+  const csvDfMsaN1: string = `seq
+AC-GT-CT
+CAC-T-GT
+ACCGTACT
+`;
+
+  const csvDfMsaAA1: string = `seq
+FWR-WYV-KHP
+YNR-WYV-KHP
+MWRSWY-CKHP
+`;
+
+  // test('testDetectors1', async () => { await _testDetectors(csvDf1); });
+  // test('testDetectors2', async () => { await _testDetectors(csvDf2); });
+  // test('testDetectors3', async () => { await _testDetectors(csvDf3); });
+
+  test('testDetectorsN1', async () => { await _testDetectorsN1(csvDfN1); });
+  test('testDetectorsAA1', async () => { await _testDetectorsAA1(csvDfAA1); });
+  test('testDetectorsMsaN1', async () => { await _testDetectorsMsaN1(csvDfMsaN1); });
+  test('testDetectorsMsaAA1', async () => { await _testDetectorsMsaAA1(csvDfMsaAA1); });
+
+  test('testDetectorsSepUn1', async () => { await _testDetectorsSepUn1(csvDfSepUn1); });
+  test('testDetectorsSepUn2', async () => { await _testDetectorsSepUn2(csvDfSepUn2); });
+
+  test('testDetectorsSepMsaN1', async () => { await _testDetectorsSepMsaN1(csvDfSepMsaN1); });
+});
+
+// export async function _testDetectors(csvDf: string) {
+//   const df: DG.DataFrame = DG.DataFrame.fromCsv(csvDf);
+//   await grok.data.detectSemanticTypes(df);
+//
+//   const col1: DG.Column = df.col('col1')!;
+//   expect(col1.semType, null);
+//   expect(col1.getTag(DG.TAGS.UNITS), null);
+// }
+
+export async function _testDetectorsN1(csvDfN1: string) {
+  const dfN1: DG.DataFrame = DG.DataFrame.fromCsv(csvDfN1);
+  await grok.data.detectSemanticTypes(dfN1);
+
+  const col: DG.Column = dfN1.col('seq')!;
+  expect(col.semType, 'MACROMOLECULE');
+  expect(col.getTag(DG.TAGS.UNITS), 'fasta:SEQ:NT');
+}
+
+export async function _testDetectorsAA1(csvDfAA1: string) {
+  const dfAA1: DG.DataFrame = DG.DataFrame.fromCsv(csvDfAA1);
+  await grok.data.detectSemanticTypes(dfAA1);
+
+  const col: DG.Column = dfAA1.col('seq')!;
+  expect(col.semType, 'MACROMOLECULE');
+  expect(col.getTag(DG.TAGS.UNITS), 'fasta:SEQ:PT');
+}
+
+export async function _testDetectorsMsaN1(csvDfMsaN1: string) {
+  const dfMsaN1: DG.DataFrame = DG.DataFrame.fromCsv(csvDfMsaN1);
+  await grok.data.detectSemanticTypes(dfMsaN1);
+
+  const col: DG.Column = dfMsaN1.col('seq')!;
+  expect(col.semType, 'MACROMOLECULE');
+  expect(col.getTag(DG.TAGS.UNITS), 'fasta:SEQ.MSA:NT');
+}
+
+export async function _testDetectorsMsaAA1(csvDfMsaAA1: string) {
+  const dfMsaAA1: DG.DataFrame = DG.DataFrame.fromCsv(csvDfMsaAA1);
+  await grok.data.detectSemanticTypes(dfMsaAA1);
+
+  const col: DG.Column = dfMsaAA1.col('seq')!;
+  expect(col.semType, 'MACROMOLECULE');
+  expect(col.getTag(DG.TAGS.UNITS), 'fasta:SEQ.MSA:PT');
+}
+
+export async function _testDetectorsSepUn1(csvDfSepUn1: string) {
+  const dfSepUn1: DG.DataFrame = DG.DataFrame.fromCsv(csvDfSepUn1);
+  await grok.data.detectSemanticTypes(dfSepUn1);
+
+  const col: DG.Column = dfSepUn1.col('seq')!;
+  expect(col.semType, 'MACROMOLECULE');
+  expect(col.getTag(DG.TAGS.UNITS), 'separator:SEQ:UN');
+}
+
+export async function _testDetectorsSepUn2(csvDfSepUn2: string) {
+  const dfSepUn2: DG.DataFrame = DG.DataFrame.fromCsv(csvDfSepUn2);
+  await grok.data.detectSemanticTypes(dfSepUn2);
+
+  const col: DG.Column = dfSepUn2.col('seq')!;
+  expect(col.semType, 'MACROMOLECULE');
+  expect(col.getTag(DG.TAGS.UNITS), 'separator:SEQ:UN');
+}
+
+export async function _testDetectorsSepMsaN1(csvDfSepMsaN1: string) {
+  const dfSepMsaN1: DG.DataFrame = DG.DataFrame.fromCsv(csvDfSepMsaN1);
+  await grok.data.detectSemanticTypes(dfSepMsaN1);
+
+  const col: DG.Column = dfSepMsaN1.col('seq')!;
+  expect(col.semType, 'MACROMOLECULE');
+  expect(col.getTag(DG.TAGS.UNITS), 'separator:SEQ.MSA:NT');
+}

package/{test-Bio-3109311545e4-fcd6a7f5.html → test-Bio-69a4761f6044-51a4ab35.html}

@@ -1,4 +1,4 @@
-<html><head><meta charset="utf-8"/><title>Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=3109311545e4. Commit fcd6a7f5.</title><style type="text/css">html,
+<html><head><meta charset="utf-8"/><title>Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=69a4761f6044. Commit 51a4ab35.</title><style type="text/css">html,
 body {
   font-family: Arial, Helvetica, sans-serif;
   font-size: 1rem;
@@ -229,7 +229,7 @@ header {
   font-size: 1rem;
   padding: 0 0.5rem;
 }
-</style></head><body><div id="jesthtml-content"><header><h1 id="title">Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=3109311545e4. Commit fcd6a7f5.</h1></header><div id="metadata-container"><div id="timestamp">Started: 2022-06-23 09:07:04</div><div id="summary"><div id="suite-summary"><div class="summary-total">Suites (1)</div><div class="summary-passed">1 passed</div><div class="summary-failed summary-empty">0 failed</div><div class="summary-pending summary-empty">0 pending</div></div><div id="test-summary"><div class="summary-total">Tests (1)</div><div class="summary-passed">1 passed</div><div class="summary-failed summary-empty">0 failed</div><div class="summary-pending summary-empty">0 pending</div></div></div></div><div id="suite-1" class="suite-container"><div class="suite-info"><div class="suite-path">/home/runner/work/public/public/packages/Bio/src/__jest__/remote.test.ts</div><div class="suite-time warn">20.235s</div></div><div class="suite-tests"><div class="test-result passed"><div class="test-info"><div class="test-suitename"> </div><div class="test-title">TEST</div><div class="test-status">passed</div><div class="test-duration">6.845s</div></div></div></div><div class="suite-consolelog"><div class="suite-consolelog-header">Console Log</div><div class="suite-consolelog-item"><pre class="suite-consolelog-item-origin">    at Object.&lt;anonymous&gt; (/home/runner/work/public/public/packages/Bio/src/__jest__/test-node.ts:63:11)
+</style></head><body><div id="jesthtml-content"><header><h1 id="title">Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=69a4761f6044. Commit 51a4ab35.</h1></header><div id="metadata-container"><div id="timestamp">Started: 2022-07-01 14:55:40</div><div id="summary"><div id="suite-summary"><div class="summary-total">Suites (1)</div><div class="summary-passed">1 passed</div><div class="summary-failed summary-empty">0 failed</div><div class="summary-pending summary-empty">0 pending</div></div><div id="test-summary"><div class="summary-total">Tests (1)</div><div class="summary-passed">1 passed</div><div class="summary-failed summary-empty">0 failed</div><div class="summary-pending summary-empty">0 pending</div></div></div></div><div id="suite-1" class="suite-container"><div class="suite-info"><div class="suite-path">/home/runner/work/public/public/packages/Bio/src/__jest__/remote.test.ts</div><div class="suite-time warn">39.007s</div></div><div class="suite-tests"><div class="test-result passed"><div class="test-info"><div class="test-suitename"> </div><div class="test-title">TEST</div><div class="test-status">passed</div><div class="test-duration">28.74s</div></div></div></div><div class="suite-consolelog"><div class="suite-consolelog-header">Console Log</div><div class="suite-consolelog-item"><pre class="suite-consolelog-item-origin">    at Object.&lt;anonymous&gt; (/home/runner/work/public/public/packages/Bio/src/__jest__/test-node.ts:63:11)
     at Generator.next (&lt;anonymous&gt;)
     at fulfilled (/home/runner/work/public/public/packages/Bio/src/__jest__/test-node.ts:28:58)
     at processTicksAndRejections (internal/process/task_queues.js:97:5)</pre><pre class="suite-consolelog-item-message">Using web root: http://localhost:8080</pre></div><div class="suite-consolelog-item"><pre class="suite-consolelog-item-origin">    at /home/runner/work/public/public/packages/Bio/src/__jest__/remote.test.ts:24:11

package/src/tests/WebLogo.test.ts

@@ -1,132 +0,0 @@
-import {after, before, category, test, expect, expectObject} from '@datagrok-libraries/utils/src/test';
-
-import * as grok from 'datagrok-api/grok';
-import * as ui from 'datagrok-api/ui';
-import * as DG from 'datagrok-api/dg';
-
-import {Nucleotides, NucleotidesPalettes} from '@datagrok-libraries/bio/src/nucleotides';
-import {Aminoacids, AminoacidsPalettes} from '@datagrok-libraries/bio/src/aminoacids';
-import {WebLogo} from '@datagrok-libraries/bio/src/viewers/web-logo';
-import {SeqPalette} from '@datagrok-libraries/bio/src/seq-palettes';
-import {UnknownSeqPalette} from '@datagrok-libraries/bio/src/unknown';
-
-category('WebLogo', () => {
-  test('testGetAlphabetSimilarity', async () => { _testGetAlphabetSimilarity(); });
-
-  test('testPickupPaletteN1', async () => { _testPickupPaletteN1(); });
-  test('testPickupPaletteAA1', async () => { _testPickupPaletteAA1(); });
-
-  // dfAA2 is too similar to nucleotides
-  // test('testPickupPaletteAA2', async () => {
-  //   _testPickupPaletteAA2();
-  // });
-});
-
-const dfN1: DG.DataFrame = DG.DataFrame.fromCsv(
-  `seq
-ACGTCT
-CAGTGT
-TTCAAC
-`);
-
-/** 2 - is an error monomer
- * This sequence set should be classified as nucleotides sequences.
- * Small error, not similar to amino acids.
- */
-const dfN1e: DG.DataFrame = DG.DataFrame.fromCsv(
-  `seq
-ACGTAT
-CAGTTG
-TTCG2C
-`);
-
-/** Pure amino acids sequence */
-const dfAA1: DG.DataFrame = DG.DataFrame.fromCsv(
-  `seq
-FWPHEYV
-YNRQWYV
-MKPSEYV
-`);
-
-/** A - alanine, G - glycine, T -= threonine, C - cysteine, W - tryptophan
- * This sequence set should be detected as amino acids more than nucleotides.
- */
-const dfAA2: DG.DataFrame = DG.DataFrame.fromCsv(
-  `seq
-AGTCAT
-AGTCGC
-AGTCATW
-`);
-
-/** This sequence set should be recognized as unknown. */
-const dfX: DG.DataFrame = DG.DataFrame.fromCsv(
-  `seq
-XZJ{}2
-5Z4733
-3Z6></
-675687
-`);
-
-export function _testGetAlphabetFreqs() {
-  const seqCol: DG.Column = dfN1.col('seq')!;
-  const mFreq = WebLogo.getAlphabetFreqs(seqCol);
-
-  expectObject(mFreq, {
-    'A': 4,
-    'C': 5,
-    'G': 3,
-    'T': 6
-  });
-}
-
-export function _testGetAlphabetSimilarity() {
-  const freq: { [m: string]: number } = {
-    'A': 2041,
-    'C': 3015,
-    'G': 3015,
-    'T': 2048,
-    '-': 1000
-  };
-  const alphabet: Set<string> = new Set(Object.keys(Nucleotides.Names));
-  const res = WebLogo.getAlphabetSimilarity(freq, alphabet);
-
-  expect(res > 0.6, true);
-}
-
-export function _testPickupPaletteN1() {
-  const seqCol: DG.Column = dfN1.col('seq')!;
-  const cp = WebLogo.pickUpPalette(seqCol);
-
-  expect(cp instanceof NucleotidesPalettes, true);
-}
-
-export function _testPickupPaletteAA1() {
-  const seqCol: DG.Column = dfAA1.col('seq')!;
-  const cp = WebLogo.pickUpPalette(seqCol);
-
-  expect(cp instanceof AminoacidsPalettes, true);
-}
-
-export function _testPickupPaletteAA2() {
-  const seqCol: DG.Column = dfAA2.col('seq')!;
-  const cp = WebLogo.pickUpPalette(seqCol);
-
-  expect(cp instanceof AminoacidsPalettes, true);
-}
-
-export function _testPickupPaletteAll() {
-  const seqColN1: DG.Column = dfN1.col('seq')!;
-  const seqColAA1: DG.Column = dfAA1.col('seq')!;
-  const seqColAA2: DG.Column = dfAA2.col('seq')!;
-  const seqColX: DG.Column = dfX.col('seq')!;
-
-  const cpN1: SeqPalette = WebLogo.pickUpPalette(seqColN1);
-  const cpAA1: SeqPalette = WebLogo.pickUpPalette(seqColAA1);
-  const cpAA2: SeqPalette = WebLogo.pickUpPalette(seqColAA2);
-  const cpX: SeqPalette = WebLogo.pickUpPalette(seqColX);
-
-  expect(cpN1 instanceof NucleotidesPalettes, true);
-  expect(cpAA1 instanceof AminoacidsPalettes, true);
-  expect(cpAA2 instanceof AminoacidsPalettes, true);
-  expect(cpX instanceof UnknownSeqPalette, true);
-}