@datagrok/bio 1.2.1 → 1.4.0

package/src/utils/multiple-sequence-alignment.ts

@@ -0,0 +1,107 @@
+import * as DG from 'datagrok-api/dg';
+
+//@ts-ignore
+import Aioli from '@biowasm/aioli';
+
+import {AlignedSequenceEncoder} from '@datagrok-libraries/bio/src/sequence-encoder';
+import * as C from './constants';
+
+/**
+ * Converts array of sequences into simple fasta string.
+ *
+ * @param {string[]} sequences Input list of sequences.
+ * @return {string} Fasta-formatted string.
+ */
+function _stringsToFasta(sequences: string[]): string {
+  return sequences.reduce((a, v, i) => a + `>sample${i + 1}\n${v}\n`, '');
+}
+
+/**
+ * Extracts array of sequences from simple fasta string.
+ *
+ * @param {string} fasta Fasta-formatted string.
+ * @return {string[]} Output list of sequences.
+ */
+function _fastaToStrings(fasta: string): string[] {
+  return fasta.replace(/>sample\d+(\r\n|\r|\n)/g, '').split('\n');
+}
+
+/**
+ * Converts aligned sequence to semantic type format.
+ *
+ * @param {string} seq Source sequence.
+ * @return {string} Formatted sequence.
+ */
+function _castAligned(seq: string): string {
+  let delimited = '';
+
+  for (const char of seq)
+    delimited += char == '-' ? char : `-${char}`;
+
+  return delimited;
+}
+
+/**
+ * Formats a batch of sequences to correspond the semantic type.
+ *
+ * @param {string[]} alignment List of aligned sequences.
+ * @return {string[]} Formatted sequences.
+ */
+function _stringsToAligned(alignment: string[]): string[] {
+  const nItems = alignment.length;
+  const aligned = new Array<string>(nItems);
+
+  for (let i = 0; i < nItems; ++i)
+    aligned[i] = _castAligned(alignment[i]);
+
+  return aligned;
+}
+
+/**
+ * Runs Aioli environment with kalign tool.
+ *
+ * @param {DG.Column} col Column with sequences.
+ * @param {boolean} isAligned Whether the column is aligned.
+ * @return {Promise<DG.Column>} Aligned sequences.
+ */
+export async function runKalign(col: DG.Column, isAligned = false) : Promise<DG.Column> {
+  let sequences = col.toList();
+
+  if (isAligned)
+    sequences = sequences.map((v: string, _) => AlignedSequenceEncoder.clean(v).replace(/\-/g, ''));
+
+  const fasta = _stringsToFasta(sequences);
+  const CLI = await new Aioli({
+    tool: 'kalign',
+    version: '3.3.1',
+    reinit: true,
+  });
+
+  console.log(['fasta.length =', fasta.length]);
+
+  await CLI.fs.writeFile('input.fa', fasta);
+  const output = await CLI.exec('kalign input.fa -f fasta -o result.fasta');
+  const buf = await CLI.cat('result.fasta');
+
+  console.warn(output);
+
+  const aligned = _fastaToStrings(buf).slice(0, sequences.length);
+  const alignedCol = DG.Column.fromStrings(`msa(${col.name})`, _stringsToAligned(aligned));
+  alignedCol.setTag(DG.TAGS.UNITS, ''); 
+  alignedCol.semType = C.SEM_TYPES.Macro_Molecule;
+  return alignedCol;
+}
+
+export async function testMSAEnoughMemory(col: DG.Column): Promise<void> {
+  const sequencesCount = col.length;
+  const delta = sequencesCount/100;
+
+  for (let i = delta; i < sequencesCount; i += delta) {
+    try {
+      await runKalign(DG.Column.fromStrings(col.name, col.toList().slice(0, Math.round(i))));
+      console.log(`runKalign succeeded on ${i}`);
+    } catch (error) {
+      console.log(`runKalign failed on ${i} with '${error}'`);
+    }
+  }
+}

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);
-}

package/test-Bio-3109311545e4-270baeb2.html

@@ -1,245 +0,0 @@
-<html><head><meta charset="utf-8"/><title>Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=3109311545e4. Commit 270baeb2.</title><style type="text/css">html,
-body {
-  font-family: Arial, Helvetica, sans-serif;
-  font-size: 1rem;
-  margin: 0;
-  padding: 0;
-  color: #333;
-}
-body {
-  padding: 2rem 1rem;
-  font-size: 0.85rem;
-}
-#jesthtml-content {
-  margin: 0 auto;
-  max-width: 70rem;
-}
-header {
-  display: flex;
-  align-items: center;
-}
-#title {
-  margin: 0;
-  flex-grow: 1;
-}
-#logo {
-  height: 4rem;
-}
-#timestamp {
-  color: #777;
-  margin-top: 0.5rem;
-}
-
-/** SUMMARY */
-#summary {
-  color: #333;
-  margin: 2rem 0;
-  display: flex;
-  font-family: monospace;
-  font-size: 1rem;
-}
-#summary > div {
-  margin-right: 2rem;
-  background: #eee;
-  padding: 1rem;
-  min-width: 15rem;
-}
-#summary > div:last-child {
-  margin-right: 0;
-}
-@media only screen and (max-width: 720px) {
-  #summary {
-    flex-direction: column;
-  }
-  #summary > div {
-    margin-right: 0;
-    margin-top: 2rem;
-  }
-  #summary > div:first-child {
-    margin-top: 0;
-  }
-}
-
-.summary-total {
-  font-weight: bold;
-  margin-bottom: 0.5rem;
-}
-.summary-passed {
-  color: #4f8a10;
-  border-left: 0.4rem solid #4f8a10;
-  padding-left: 0.5rem;
-}
-.summary-failed,
-.summary-obsolete-snapshots {
-  color: #d8000c;
-  border-left: 0.4rem solid #d8000c;
-  padding-left: 0.5rem;
-}
-.summary-pending {
-  color: #9f6000;
-  border-left: 0.4rem solid #9f6000;
-  padding-left: 0.5rem;
-}
-.summary-empty {
-  color: #999;
-  border-left: 0.4rem solid #999;
-}
-
-.test-result {
-  padding: 1rem;
-  margin-bottom: 0.25rem;
-}
-.test-result:last-child {
-  border: 0;
-}
-.test-result.passed {
-  background-color: #dff2bf;
-  color: #4f8a10;
-}
-.test-result.failed {
-  background-color: #ffbaba;
-  color: #d8000c;
-}
-.test-result.pending {
-  background-color: #ffdf61;
-  color: #9f6000;
-}
-
-.test-info {
-  display: flex;
-  justify-content: space-between;
-}
-.test-suitename {
-  width: 20%;
-  text-align: left;
-  font-weight: bold;
-  word-break: break-word;
-}
-.test-title {
-  width: 40%;
-  text-align: left;
-  font-style: italic;
-}
-.test-status {
-  width: 20%;
-  text-align: right;
-}
-.test-duration {
-  width: 10%;
-  text-align: right;
-  font-size: 0.75rem;
-}
-
-.failureMessages {
-  padding: 0 1rem;
-  margin-top: 1rem;
-  border-top: 1px dashed #d8000c;
-}
-.failureMessages.suiteFailure {
-  border-top: none;
-}
-.failureMsg {
-  white-space: pre-wrap;
-  white-space: -moz-pre-wrap;
-  white-space: -pre-wrap;
-  white-space: -o-pre-wrap;
-  word-wrap: break-word;
-}
-
-.suite-container {
-  margin-bottom: 2rem;
-}
-.suite-info {
-  padding: 1rem;
-  background-color: #eee;
-  color: #777;
-  display: flex;
-  align-items: center;
-  margin-bottom: 0.25rem;
-}
-.suite-info .suite-path {
-  word-break: break-all;
-  flex-grow: 1;
-  font-family: monospace;
-  font-size: 1rem;
-}
-.suite-info .suite-time {
-  margin-left: 0.5rem;
-  padding: 0.2rem 0.3rem;
-  font-size: 0.75rem;
-}
-.suite-info .suite-time.warn {
-  background-color: #d8000c;
-  color: #fff;
-}
-
-/* CONSOLE LOGS */
-.suite-consolelog {
-  margin-bottom: 0.25rem;
-  padding: 1rem;
-  background-color: #efefef;
-}
-.suite-consolelog-header {
-  font-weight: bold;
-}
-.suite-consolelog-item {
-  padding: 0.5rem;
-}
-.suite-consolelog-item pre {
-  margin: 0.5rem 0;
-  white-space: pre-wrap;
-  white-space: -moz-pre-wrap;
-  white-space: -pre-wrap;
-  white-space: -o-pre-wrap;
-  word-wrap: break-word;
-}
-.suite-consolelog-item-origin {
-  color: #777;
-  font-weight: bold;
-}
-.suite-consolelog-item-message {
-  color: #000;
-  font-size: 1rem;
-  padding: 0 0.5rem;
-}
-
-/* OBSOLETE SNAPSHOTS */
-.suite-obsolete-snapshots {
-  margin-bottom: 0.25rem;
-  padding: 1rem;
-  background-color: #ffbaba;
-  color: #d8000c;
-}
-.suite-obsolete-snapshots-header {
-  font-weight: bold;
-}
-.suite-obsolete-snapshots-item {
-  padding: 0.5rem;
-}
-.suite-obsolete-snapshots-item pre {
-  margin: 0.5rem 0;
-  white-space: pre-wrap;
-  white-space: -moz-pre-wrap;
-  white-space: -pre-wrap;
-  white-space: -o-pre-wrap;
-  word-wrap: break-word;
-}
-.suite-obsolete-snapshots-item-message {
-  color: #000;
-  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 270baeb2.</h1></header><div id="metadata-container"><div id="timestamp">Started: 2022-06-23 09:29:26</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">17.389s</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">6.514s</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
-    at Generator.next (&lt;anonymous&gt;)
-    at /home/runner/work/public/public/packages/Bio/src/__jest__/remote.test.ts:34:71
-    at new Promise (&lt;anonymous&gt;)
-    at Object.&lt;anonymous&gt;.__awaiter (/home/runner/work/public/public/packages/Bio/src/__jest__/remote.test.ts:30:12)
-    at Object.&lt;anonymous&gt; (/home/runner/work/public/public/packages/Bio/src/__jest__/remote.test.ts:22:23)
-    at Promise.then.completed (/home/runner/work/public/public/packages/Bio/node_modules/jest-circus/build/utils.js:391:28)
-    at new Promise (&lt;anonymous&gt;)</pre><pre class="suite-consolelog-item-message">Testing Bio package</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:47:11
-    at Generator.next (&lt;anonymous&gt;)
-    at fulfilled (/home/runner/work/public/public/packages/Bio/src/__jest__/remote.test.ts:31:58)
-    at processTicksAndRejections (internal/process/task_queues.js:97:5)</pre><pre class="suite-consolelog-item-message"/></div></div></div></div></body></html>