@datagrok/bio 1.7.11 → 1.7.12

package/package.json

@@ -2,7 +2,7 @@
   "name": "@datagrok/bio",
   "beta": false,
   "friendlyName": "Bio",
-  "version": "1.7.11",
+  "version": "1.7.12",
   "description": "Bio is a [package](https://datagrok.ai/help/develop/develop#packages) for the [Datagrok](https://datagrok.ai) platform",
   "repository": {
     "type": "git",
@@ -13,7 +13,7 @@
     "@biowasm/aioli": ">=2.4.0",
     "@datagrok-libraries/bio": "^2.8.5",
     "@datagrok-libraries/utils": "^1.0.0",
-    "@datagrok-libraries/ml": "^2.0.10",
+    "@datagrok-libraries/ml": "^3.0.0",
     "cash-dom": "latest",
     "datagrok-api": "^1.4.12",
     "dayjs": "latest",

package/src/const.ts

@@ -23,3 +23,8 @@ export const CAP_GROUP_NAME = 'capGroupName';
 export const RGROUP_LABEL = 'label';
 export const MONOMER_SYMBOL = 'symbol';
 export const SDF_MONOMER_NAME = 'MonomerName';
+
+// range of hex nubers used in PepSea library to endode monomers
+export const MONOMER_ENCODE_MIN = 0x100;
+export const MONOMER_ENCODE_MAX = 0x40A;
+

package/src/package.ts

@@ -16,7 +16,7 @@ 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';
 import {sequenceGetSimilarities, drawTooltip} from './utils/sequence-activity-cliffs';
-import {createJsonMonomerLibFromSdf, getMolfilesFromSeq, HELM_CORE_LIB_FILENAME} from './utils/utils';
+import {createJsonMonomerLibFromSdf, encodeMonomers, getMolfilesFromSeq, HELM_CORE_LIB_FILENAME} from './utils/utils';
 import {getMacroMol} from './utils/atomic-works';
 import {MacromoleculeSequenceCellRenderer} from './utils/cell-renderer';
 import {convert} from './utils/convert';
@@ -112,7 +112,9 @@ export async function activityCliffs(df: DG.DataFrame, macroMolecule: DG.Column,
   similarity: number, methodName: string): Promise<void> {
   if (!checkInputColumn(macroMolecule, 'Activity Cliffs'))
     return;
-
+  const encodedCol = encodeMonomers(macroMolecule);
+  if (!encodedCol)
+    return;
   const axesNames = getEmbeddingColsNames(df);
   const options = {
     'SPE': {cycles: 2000, lambda: 1.0, dlambda: 0.0005},
@@ -121,6 +123,7 @@ export async function activityCliffs(df: DG.DataFrame, macroMolecule: DG.Column,
   await getActivityCliffs(
     df,
     macroMolecule,
+    encodedCol,
     axesNames,
     'Activity cliffs',
     activities,
@@ -146,10 +149,12 @@ export async function sequenceSpaceTopMenu(table: DG.DataFrame, macroMolecule: D
   similarityMetric: string = 'Levenshtein', plotEmbeddings: boolean): Promise<void> {
   if (!checkInputColumn(macroMolecule, 'Activity Cliffs'))
     return;
-
+  const encodedCol = encodeMonomers(macroMolecule);
+  if (!encodedCol)
+    return;
   const embedColsNames = getEmbeddingColsNames(table);
   const chemSpaceParams = {
-    seqCol: macroMolecule,
+    seqCol: encodedCol,
     methodName: methodName,
     similarityMetric: similarityMetric,
     embedAxesNames: embedColsNames

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

@@ -7,6 +7,7 @@ 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';
+import { encodeMonomers } from '../utils/utils';
 
 
 category('activityCliffs', async () => {
@@ -31,9 +32,11 @@ category('activityCliffs', async () => {
     const options = {
       'SPE': {cycles: 2000, lambda: 1.0, dlambda: 0.0005},
     };
+    const encodedCol = encodeMonomers(actCliffsDf.col('MSA')!) as DG.Column;
     const scatterPlot = await getActivityCliffs(
       actCliffsDf,
       actCliffsDf.col('MSA')!,
+      encodedCol,
       axesNames,
       'Activity cliffs',
       actCliffsDf.col('Activity')!,

package/src/utils/utils.ts

@@ -2,7 +2,7 @@ import * as DG from 'datagrok-api/dg';
 import {WebLogo, SplitterFunc} from '@datagrok-libraries/bio/src/viewers/web-logo';
 import * as grok from 'datagrok-api/grok';
 import {
-  CAP_GROUP_NAME, CAP_GROUP_SMILES, jsonSdfMonomerLibDict, MONOMER_SYMBOL,
+  CAP_GROUP_NAME, CAP_GROUP_SMILES, jsonSdfMonomerLibDict, MONOMER_ENCODE_MAX, MONOMER_ENCODE_MIN, MONOMER_SYMBOL,
   RGROUP_ALTER_ID, RGROUP_FIELD, RGROUP_LABEL, SDF_MONOMER_NAME
 } from '../const';
 
@@ -11,6 +11,33 @@ export const HELM_CORE_LIB_MONOMER_SYMBOL = 'symbol';
 export const HELM_CORE_LIB_MOLFILE = 'molfile';
 export const HELM_CORE_FIELDS = ['symbol', 'molfile', 'rgroups', 'name'];
 
+
+export function encodeMonomers(col: DG.Column): DG.Column | null {
+  let encodeSymbol = MONOMER_ENCODE_MIN;
+  const monomerSymbolDict:  { [key: string]: number }= {};
+  const units = col.tags[DG.TAGS.UNITS];
+  const sep = col.getTag('separator');
+  const splitterFunc: SplitterFunc = WebLogo.getSplitter(units, sep);
+  const encodedStringArray = [];
+  for (let i = 0; i < col.length; ++i) {
+    let encodedMonomerStr = '';
+    const monomers = splitterFunc(col.get(i));
+    monomers.forEach(m => {
+      if(!monomerSymbolDict[m]) {
+        if(encodeSymbol > MONOMER_ENCODE_MAX) {
+          grok.shell.error(`Not enougth symbols to encode monomers`);
+          return null;
+        }
+        monomerSymbolDict[m] = encodeSymbol;
+        encodeSymbol++;
+      }
+      encodedMonomerStr += String.fromCodePoint(monomerSymbolDict[m]);
+    })
+    encodedStringArray.push(encodedMonomerStr);
+  }
+  return DG.Column.fromStrings('encodedMolecules', encodedStringArray);
+}
+
 export function getMolfilesFromSeq(col: DG.Column, monomersLibObject: any[]): any[][] | null {
   const units = col.tags[DG.TAGS.UNITS];
   const sep = col.getTag('separator');
@@ -79,4 +106,4 @@ export function createJsonMonomerLibFromSdf(table: DG.DataFrame): any {
     resultLib.push(monomer);
   }
   return resultLib;
-}
+}

package/{test-Bio-34f75e5127b8-f542cbde.html → test-Bio-34f75e5127b8-6fa72ec4.html}

@@ -1,4 +1,4 @@
-<html><head><meta charset="utf-8"/><title>Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=34f75e5127b8. Commit f542cbde.</title><style type="text/css">html,
+<html><head><meta charset="utf-8"/><title>Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=34f75e5127b8. Commit 6fa72ec4.</title><style type="text/css">html,
 body {
   font-family: Arial, Helvetica, sans-serif;
   font-size: 1rem;
@@ -229,7 +229,8 @@ 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 f542cbde.</h1></header><div id="metadata-container"><div id="timestamp">Started: 2022-07-20 17:49:40</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">209.758s</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">199.086s</div></div><div class="failureMessages"> <pre class="failureMsg">Error: Test result : Bio.MSA.is_correct : TypeError: Cannot read properties of undefined (reading 'split')
+</style></head><body><div id="jesthtml-content"><header><h1 id="title">Bio Test Report. Datagrok version datagrok/datagrok:latest SHA=34f75e5127b8. Commit 6fa72ec4.</h1></header><div id="metadata-container"><div id="timestamp">Started: 2022-07-22 13:03:45</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">213.603s</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">199.146s</div></div><div class="failureMessages"> <pre class="failureMsg">Error: Test result : Bio.MSA.is_correct : TypeError: Cannot read properties of undefined (reading 'split')
+Test result : Bio.activityCliffs.activityCliffsOpen : Error: Expected "105 cliffs", got "2362 cliffs"
 
     at /home/runner/work/public/public/packages/Bio/src/__jest__/remote.test.ts:67:20
     at Generator.next (&lt;anonymous&gt;)
@@ -310,7 +311,6 @@ Test result : Bio.detectors.samplesTestUnichemSourcesNegativeSrcUrl : OK
 Test result : Bio.detectors.samplesTestUnichemSourcesNegativeBaseIdUrl : OK
 Test result : Bio.MSA.test_table.is_not_empty : OK
 Test result : Bio.sequenceSpace.sequenceSpaceOpens : OK
-Test result : Bio.activityCliffs.activityCliffsOpen : OK
 Test result : Bio.splitters.helm1 : OK
 Test result : Bio.splitters.helm2 : OK
 Test result : Bio.splitters.helm3-multichar : OK