@datagrok/bio 1.7.2 → 1.7.3

package/package.json

@@ -2,7 +2,7 @@
   "name": "@datagrok/bio",
   "beta": false,
   "friendlyName": "Bio",
-  "version": "1.7.2",
+  "version": "1.7.3",
   "description": "Bio is a [package](https://datagrok.ai/help/develop/develop#packages) for the [Datagrok](https://datagrok.ai) platform",
   "repository": {
     "type": "git",
@@ -11,7 +11,7 @@
   },
   "dependencies": {
     "@biowasm/aioli": ">=2.4.0",
-    "@datagrok-libraries/bio": "^2.5.0",
+    "@datagrok-libraries/bio": "2.8.1",
     "@datagrok-libraries/utils": "^1.0.0",
     "@datagrok-libraries/ml": "^2.0.10",
     "cash-dom": "latest",
@@ -60,10 +60,7 @@
   ],
   "sources": [
     "css/helm.css",
-    "https://ajax.googleapis.com/ajax/libs/dojo/1.10.4/dojo/dojo.js",
-    "helm/JSDraw/Scilligence.JSDraw2.Lite.js",
-    "helm/JSDraw/Scilligence.JSDraw2.Resources.js",
-    "helm/JSDraw/Pistoia.HELM-uncompressed.js"
+    "https://ajax.googleapis.com/ajax/libs/dojo/1.10.4/dojo/dojo.js"
   ],
   "category": "Bioinformatics"
 }

package/src/package-test.ts

@@ -8,7 +8,7 @@ import './tests/detectors-test';
 import './tests/msa-tests';
 import './tests/sequence-space-test';
 import './tests/activity-cliffs-tests';
-import './tests/splitter-test';
+import './tests/splitters-test';
 import './tests/renderer-test';
 import './tests/convert-test';
 

package/src/package.ts

@@ -11,7 +11,6 @@ import {runKalign, testMSAEnoughMemory} from './utils/multiple-sequence-alignmen
 import {SequenceAlignment, Aligned} from './seq_align';
 import {Nucleotides} from '@datagrok-libraries/bio/src/nucleotides';
 import {Aminoacids} from '@datagrok-libraries/bio/src/aminoacids';
-import {convert} from './utils/convert';
 import {getEmbeddingColsNames, sequenceSpace} from './utils/sequence-space';
 import {AvailableMetrics} from '@datagrok-libraries/ml/src/typed-metrics';
 import {getActivityCliffs} from '@datagrok-libraries/ml/src/viewers/activity-cliffs';
@@ -19,10 +18,8 @@ import {sequenceGetSimilarities, drawTooltip} from './utils/sequence-activity-cl
 import {getMolfilesFromSeq, HELM_CORE_LIB_FILENAME} from './utils/utils';
 import {getMacroMol} from './utils/atomic-works';
 import {MacromoleculeSequenceCellRenderer} from './utils/cell-renderer';
-import {Column} from 'datagrok-api/dg';
-import {SEM_TYPES} from './utils/constants';
-import { delay } from '@datagrok-libraries/utils/src/test';
-import { TableView } from 'datagrok-api/dg';
+import {delay} from '@datagrok-libraries/utils/src/test';
+import {convert} from './utils/convert';
 
 //tags: init
 export async function initBio(): Promise<void> {
@@ -175,21 +172,22 @@ export async function toAtomicLevel(df: DG.DataFrame, macroMolecule: DG.Column):
   if (!checkInputColumn(macroMolecule, 'To Atomic Level'))
     return;
 
-  let currentView: TableView;
-  for (let view of grok.shell.tableViews) {
-    if (df.name === view.name) {
+  let currentView: DG.TableView;
+  for (const view of grok.shell.tableViews) {
+    if (df.name === view.name)
       currentView = view;
-    }
   }
-  const file = await _package.files.readAsText('tests/sar-small.csv');
-  const df2 = DG.DataFrame.fromCsv(file);
-  const v = grok.shell.addTableView(df2);
-  setTimeout(()=> {
+
+  // Some hack to activate Chem Molecule rendering
+  const file2 = await _package.files.readAsText('tests/sar-small.csv');
+  const df2 = DG.DataFrame.fromCsv(file2);
+  const v2 = grok.shell.addTableView(df2);
+  setTimeout(() => {
     grok.shell.closeTable(df2);
-    v.close();
+    v2.close();
     grok.shell.v = currentView;
   }, 100);
-  
+
   const monomersLibFile = await _package.files.readAsText(HELM_CORE_LIB_FILENAME);
   const monomersLibObject: any[] = JSON.parse(monomersLibFile);
   const atomicCodes = getMolfilesFromSeq(macroMolecule, monomersLibObject);
@@ -199,7 +197,6 @@ export async function toAtomicLevel(df: DG.DataFrame, macroMolecule: DG.Column):
   col.semType = DG.SEMTYPE.MOLECULE;
   col.tags[DG.TAGS.UNITS] = 'molblock';
   df.columns.add(col, true);
-
 }
 
 

package/src/tests/WebLogo-test.ts

@@ -61,6 +61,24 @@ XZJ{}2
   test('testPickupPaletteX', async () => { await _testPickupPaletteX(csvDfX); });
 });
 
+category('WebLogo.monomerToText', () => {
+  test('longMonomerSingle', async () => {
+    await expect(WebLogo.monomerToText('S'), 'S');
+  });
+  test('longMonomerShort', async () => {
+    await expect(WebLogo.monomerToText('Short'), 'Short');
+  });
+  test('longMonomerLong56', async () => {
+    await expect(WebLogo.monomerToText('Long56'), 'Long5…');
+  });
+  test('longMonomerComplexFirstPartShort', async () => {
+    await expect(WebLogo.monomerToText('Long-long'), 'Long…');
+  });
+  test('longMonomerComplexFirstPartLong56', async () => {
+    await expect(WebLogo.monomerToText('Long56-long'), 'Long5…');
+  });
+});
+
 
 export async function _testGetStats(csvDfN1: string) {
   const dfN1: DG.DataFrame = DG.DataFrame.fromCsv(csvDfN1);

package/src/tests/activity-cliffs-tests.ts

@@ -1,7 +1,9 @@
 import {after, before, category, expect, expectFloat, test} from '@datagrok-libraries/utils/src/test';
+
 import * as DG from 'datagrok-api/dg';
-import {createTableView, readDataframe} from './utils';
-import {_package} from '../package-test';
+import * as grok from 'datagrok-api/grok';
+
+import {readDataframe} from './utils';
 import {getEmbeddingColsNames, sequenceSpace} from '../utils/sequence-space';
 import {drawTooltip, sequenceGetSimilarities} from '../utils/sequence-activity-cliffs';
 import {getActivityCliffs} from '@datagrok-libraries/ml/src/viewers/activity-cliffs';
@@ -12,8 +14,15 @@ category('activityCliffs', async () => {
   let actCliffsDf: DG.DataFrame;
 
   before(async () => {
-    actCliffsTableView = await createTableView('sample_MSA.csv');
-    actCliffsDf = await readDataframe('sample_MSA.csv');
+    actCliffsDf = await readDataframe('samples/sample_MSA.csv');
+    actCliffsTableView = grok.shell.addTableView(actCliffsDf);
+
+    actCliffsDf = actCliffsTableView.dataFrame;
+  });
+
+  after(async () => {
+    grok.shell.closeTable(actCliffsDf);
+    actCliffsTableView.close();
   });
 
   test('activityCliffsOpen', async () => {
@@ -41,10 +50,6 @@ category('activityCliffs', async () => {
 
     const cliffsLink = (Array.from(scatterPlot.root.children) as Element[])
       .filter((it) => it.className === 'ui-btn ui-btn-ok');
-    expect((cliffsLink[0] as HTMLElement).innerText, '101 cliffs');
-  });
-
-  after(async () => {
-    actCliffsTableView.close();
+    expect((cliffsLink[0] as HTMLElement).innerText, '105 cliffs');
   });
 });

package/src/tests/convert-test.ts

@@ -4,7 +4,7 @@ import * as grok from 'datagrok-api/grok';
 import * as DG from 'datagrok-api/dg';
 
 import {ConverterFunc, DfReaderFunc} from './types';
-import {NOTATION, NotationConverter} from '../utils/notation-converter';
+import {NOTATION, NotationConverter} from '@datagrok-libraries/bio/src/utils/notation-converter';
 
 // import {mmSemType} from '../const';
 // import {importFasta} from '../package';

package/src/tests/detectors-test.ts

@@ -102,6 +102,7 @@ MWRSWY-CKHP
 
   const enum Samples {
     peptidesComplex = 'peptidesComplex',
+    peptidesSimple = 'peptidesSimple',
     fastaCsv = 'fastaCsv',
     fastaFasta = 'fastaFasta',
     fastaPtCsv = 'fastaPtCsv',
@@ -115,15 +116,16 @@ MWRSWY-CKHP
   }
 
   const samples: { [key: string]: string } = {
-    'peptidesComplex': 'System:AppData/Bio/tests/peptides_complex_msa.csv',
     'fastaCsv': 'System:AppData/Bio/samples/sample_FASTA.csv',
     'fastaFasta': 'System:AppData/Bio/samples/sample_FASTA.fasta',
     'fastaPtCsv': 'System:AppData/Bio/samples/sample_FASTA_PT.csv',
     'msaComplex': 'System:AppData/Bio/samples/sample_MSA.csv',
     'helmCsv': 'System:AppData/Bio/samples/sample_HELM.csv',
+    'peptidesComplex': 'System:AppData/Bio/tests/peptides_complex_msa.csv',
+    'peptidesSimple': 'System:AppData/Bio/tests/peptides_simple_msa.csv',
     'testDemogCsv': 'System:AppData/Bio/tests/testDemog.csv',
     'testHelmCsv': 'System:AppData/Bio/tests/testHelm.csv',
-    'testIdCsv': 'System:AppData/Bio/tests/id.csv',
+    'testIdCsv': 'System:AppData/Bio/tests/testId.csv',
     'testSmilesCsv': 'System:AppData/Bio/tests/testSmiles.csv',
     'testSmiles2Csv': 'System:AppData/Bio/tests/testSmiles2.csv',
   };
@@ -228,6 +230,10 @@ MWRSWY-CKHP
     await _testPos(readSamples(Samples.fastaFasta, readFileFasta), 'sequence', 'fasta:SEQ:PT');
   });
 
+  // peptidesComplex contains monomers with spaces in AlignedSequence columns, which are forbidden
+  // test('samplesPeptidesComplexPositiveAlignedSequence', async () => {
+  //   await _testPos(readSamples(Samples.peptidesComplex), 'AlignedSequence', 'separator:SEQ:UN', '-');
+  // });
   test('samplesPeptidesComplexNegativeID', async () => {
     await _testNeg(readSamples(Samples.peptidesComplex), 'ID');
   });

package/src/tests/renderer-test.ts

@@ -7,12 +7,15 @@ import {importFasta, multipleSequenceAlignmentAny} from '../package';
 
 category('renderers', () => {
   let tvList: DG.TableView[];
+  let dfList: DG.DataFrame[];
 
   before(async () => {
     tvList = [];
+    dfList = [];
   });
 
   after(async () => {
+    dfList.forEach((df: DG.DataFrame) => { grok.shell.closeTable(df); });
     tvList.forEach((tv: DG.TableView) => tv.close());
   });
 
@@ -23,6 +26,7 @@ category('renderers', () => {
   async function _testAfterMsa() {
     const fastaTxt: string = await grok.dapi.files.readAsText('System:AppData/Bio/samples/sample_FASTA.fasta');
     const df: DG.DataFrame = importFasta(fastaTxt)[0];
+    // await grok.data.detectSemanticTypes(df);
 
     const srcSeqCol: DG.Column | null = df.col('sequence');
     expect(srcSeqCol !== null, true);
@@ -31,14 +35,15 @@ category('renderers', () => {
     const tv: DG.TableView = grok.shell.addTableView(df);
     console.log('Bio: tests/renderers/afterMsa, table view');
 
-    await grok.data.detectSemanticTypes(df);
+    // await grok.data.detectSemanticTypes(df);
     console.log('Bio: tests/renderers/afterMsa, detectSemanticTypes');
 
-    console.log('Bio: tests/renderers/afterMsa, src before test semType' +
+    console.log('Bio: tests/renderers/afterMsa, src before test ' +
       `semType="${srcSeqCol!.semType}", units="${srcSeqCol!.getTag(DG.TAGS.UNITS)}", ` +
       `cell.renderer="${srcSeqCol!.getTag('cell.renderer')}"`);
     expect(srcSeqCol!.semType, DG.SEMTYPE.MACROMOLECULE);
     expect(srcSeqCol!.getTag(DG.TAGS.UNITS), 'fasta:SEQ:PT');
+    // TODO: Find the way to check renderer for columns
     expect(srcSeqCol!.getTag('cell.renderer'), 'Macromolecule');
     console.log('Bio: tests/renderers/afterMsa, src semType tested');
 
@@ -53,6 +58,7 @@ category('renderers', () => {
     expect(msaSeqCol!.getTag('cell.renderer'), 'Macromolecule');
     console.log('Bio: tests/renderers/afterMsa, msa semType tested');
 
+    dfList.push(df);
     tvList.push(tv);
   }
 });

package/src/tests/sequence-space-test.ts

@@ -1,16 +1,20 @@
-import {before, category, test, expect} from '@datagrok-libraries/utils/src/test';
+import {after, before, category, test, expect} from '@datagrok-libraries/utils/src/test';
 import * as DG from 'datagrok-api/dg';
 import {sequenceSpace} from '../utils/sequence-space';
 import {readDataframe} from './utils';
-//import * as grok from 'datagrok-api/grok';
+import * as grok from 'datagrok-api/grok';
 
 category('sequenceSpace', async () => {
   let testFastaDf: DG.DataFrame;
 
   before(async () => {
-    testFastaDf = await readDataframe('sample_FASTA.csv');
+    testFastaDf = await readDataframe('samples/sample_FASTA.csv');
+    // await grok.data.detectSemanticTypes(testFastaDf);
   });
 
+  after(async () => {
+    grok.shell.closeTable(testFastaDf);
+  });
 
   test('sequenceSpaceOpens', async () => {
     const sequenceSpaceParams = {

package/src/tests/splitters-test.ts

@@ -0,0 +1,35 @@
+import {after, before, category, test, expect, expectArray} 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 {WebLogo, SplitterFunc} from '@datagrok-libraries/bio/src/viewers/web-logo';
+
+category('splitters', () => {
+  const helm1 = '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}$$$';
+
+  const helm2 = 'PEPTIDE1{meI.hHis.Hcy.Q.T.W.Q.Phe_4NH2.D-Tyr_Et.Tyr_ab-dehydroMe.dV.E.N.N.meK}$$$';
+
+  const data: { [key: string]: [string, string[]] } = {
+    helm1: [
+      '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}$$$',
+      ['meI', 'hHis', 'Aca', 'N', 'T', 'dE', 'Thr_PO3H2', 'Aca', 'D-Tyr_Et',
+        'Tyr_ab-dehydroMe', 'dV', 'E', 'N', 'D-Orn', 'D-aThr', 'Phe_4Me']
+    ],
+    helm2: [
+      'PEPTIDE1{meI.hHis.Aca.N.T.dK.Thr_PO3H2.Aca.D-Tyr_Et.D-Dap.dV.E.N.pnG.Phe_4Me}$$$',
+      ['meI', 'hHis', 'Aca', 'N', 'T', 'dK', 'Thr_PO3H2', 'Aca',
+        'D-Tyr_Et', 'D-Dap', 'dV', 'E', 'N', 'pnG', 'Phe_4Me']
+    ],
+  };
+
+  test('helm1', async () => { await _testHelmSplitter(data.helm1[0], data.helm1[1]); });
+  test('helm2', async () => { await _testHelmSplitter(data.helm2[0], data.helm2[1]); });
+});
+
+export async function _testHelmSplitter(src: string, tgt: string[]) {
+  const res: string[] = WebLogo.splitterAsHelm(src);
+  console.debug(`Bio: tests: splitters: src=${JSON.stringify(src)}, res=${JSON.stringify(res)} .`);
+  expectArray(res, tgt);
+}
+

package/src/utils/cell-renderer.ts

@@ -68,9 +68,9 @@ function printLeftOrCentered(
   g.textAlign = 'start';
   const colorPart = s.substring(0);
   let grayPart = separator;
-  if (last) {
+  if (last)
     grayPart = '';
-  }
+
   const textSize = g.measureText(colorPart + grayPart);
   const indent = 5;
 
@@ -98,8 +98,11 @@ function printLeftOrCentered(
 
 export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
   get name(): string { return 'macromoleculeSequence'; }
+
   get cellType(): string { return C.SEM_TYPES.Macro_Molecule; }
+
   get defaultHeight(): number { return 30; }
+
   get defaultWidth(): number { return 230; }
 
   /**
@@ -166,10 +169,10 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
         color = palette.get(amino);
         g.fillStyle = undefinedColor;
         let last = false;
-        if (index === subParts.length - 1) {
+        if (index === subParts.length - 1)
           last = true;
-        }
-        x1 = printLeftOrCentered(x1, y, w, h, g, amino, color, 0, true, 1.0,  separator, last);
+
+        x1 = printLeftOrCentered(x1, y, w, h, g, amino, color, 0, true, 1.0, separator, last);
       });
 
       g.restore();

package/src/utils/convert.ts

@@ -1,6 +1,6 @@
 import * as DG from 'datagrok-api/dg';
 import * as ui from 'datagrok-api/ui';
-import {NotationConverter, NOTATION} from './notation-converter';
+import {NotationConverter, NOTATION} from '@datagrok-libraries/bio/src/utils/notation-converter';
 
 /**
  * Converts notations of a Macromolecule column

package/{test-Bio-34f75e5127b8-ac96da52.html → test-Bio-34f75e5127b8-303cfb72.html}

@@ -1,4 +1,4 @@
-<html><head><meta charset="utf-8"/><title>Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=34f75e5127b8. Commit ac96da52.</title><style type="text/css">html,
+<html><head><meta charset="utf-8"/><title>Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=34f75e5127b8. Commit 303cfb72.</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=34f75e5127b8. Commit ac96da52.</h1></header><div id="metadata-container"><div id="timestamp">Started: 2022-07-13 09:24:48</div><div id="summary"><div id="suite-summary"><div class="summary-total">Suites (1)</div><div class="summary-passed summary-empty">0 passed</div><div class="summary-failed">1 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 summary-empty">0 passed</div><div class="summary-failed">1 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">110.354s</div></div><div class="suite-tests"><div class="test-result failed"><div class="test-info"><div class="test-suitename"> </div><div class="test-title">TEST</div><div class="test-status">failed</div><div class="test-duration">100.001s</div></div><div class="failureMessages"> <pre class="failureMsg">Error: thrown: "Exceeded timeout of 100000 ms for a test.
+</style></head><body><div id="jesthtml-content"><header><h1 id="title">Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=34f75e5127b8. Commit 303cfb72.</h1></header><div id="metadata-container"><div id="timestamp">Started: 2022-07-13 14:53:02</div><div id="summary"><div id="suite-summary"><div class="summary-total">Suites (1)</div><div class="summary-passed summary-empty">0 passed</div><div class="summary-failed">1 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 summary-empty">0 passed</div><div class="summary-failed">1 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">110.084s</div></div><div class="suite-tests"><div class="test-result failed"><div class="test-info"><div class="test-suitename"> </div><div class="test-title">TEST</div><div class="test-status">failed</div><div class="test-duration">100.002s</div></div><div class="failureMessages"> <pre class="failureMsg">Error: thrown: "Exceeded timeout of 100000 ms for a test.
 Use jest.setTimeout(newTimeout) to increase the timeout value, if this is a long-running test."
     at Object.&lt;anonymous&gt; (/home/runner/work/public/public/packages/Bio/src/__jest__/remote.test.ts:22:1)
     at Runtime._execModule (/home/runner/work/public/public/packages/Bio/node_modules/jest-runtime/build/index.js:1646:24)

package/src/tests/splitter-test.ts

@@ -1,22 +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 {WebLogo, SplitterFunc} from '@datagrok-libraries/bio/src/viewers/web-logo';
-
-category('splitter', () => {
-  const helm1 = '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}$$$';
-  const helm2 = 'PEPTIDE1{meI.hHis.Hcy.Q.T.W.Q.Phe_4NH2.D-Tyr_Et.Tyr_ab-dehydroMe.dV.E.N.N.meK}$$$';
-
-  test('helm1', async () => { await _testHelmSplitter(helm1); });
-  test('helm2', async () => { await _testHelmSplitter(helm2); });
-});
-
-export async function _testHelmSplitter(txt: string) {
-  // const splitter: SplitterFunc = WebLogo.getSplitterAsHelm();
-  //
-  // const mList: string[] = splitter(txt);
-  // expect(mList.length, 12);
-}
-