@datagrok/bio 2.4.46 → 2.4.48

package/package.json

@@ -5,7 +5,7 @@
     "name": "Leonid Stolbov",
     "email": "lstolbov@datagrok.ai"
   },
-  "version": "2.4.46",
+  "version": "2.4.48",
   "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.",
   "repository": {
     "type": "git",
@@ -22,7 +22,7 @@
   ],
   "dependencies": {
     "@biowasm/aioli": "^3.1.0",
-    "@datagrok-libraries/bio": "^5.32.4",
+    "@datagrok-libraries/bio": "^5.32.5",
     "@datagrok-libraries/chem-meta": "^1.0.1",
     "@datagrok-libraries/ml": "^6.3.39",
     "@datagrok-libraries/tutorials": "^1.3.2",

package/scripts/sequence_generator.py

@@ -16,6 +16,14 @@
 # input: double fasta_separator = '' [Separator for a FASTA notation]
 # output: dataframe sequences
 
+"""
+The most simple options set running from command line
+  python sequence_generator.py -c 4 -s 50 > output_file.tsv
+Basic options:
+  -с number of clusters
+  -s cluster size (number of sequences per cluster)
+"""
+
 import random
 import argparse
 import sys

package/src/package.ts

@@ -57,6 +57,7 @@ import {BioPackage, BioPackageProperties} from './package-types';
 import {RDModule} from '@datagrok-libraries/chem-meta/src/rdkit-api';
 import {ObjectPropertyBag} from 'datagrok-api/dg';
 import {PackageSettingsEditorWidget} from './widgets/package-settings-editor-widget';
+import {getCompositionAnalysisWidget} from './widgets/composition-analysis-widget';
 
 export const _package = new BioPackage();
 
@@ -218,6 +219,14 @@ export function macroMolColumnPropertyPanel(molColumn: DG.Column): DG.Widget {
   return getMacromoleculeColumnPropertyPanel(molColumn);
 }
 
+//name: Composition analysis
+//tags: panel, bio, widgets
+//input: semantic_value sequence { semType: Macromolecule }
+//output: widget result
+export function compositionAnalysisWidget(sequence: DG.SemanticValue): DG.Widget {
+  return getCompositionAnalysisWidget(sequence);
+}
+
 //name: separatorSequenceCellRenderer
 //tags: cellRenderer
 //meta.cellType: sequence
@@ -771,7 +780,7 @@ export async function webLogoLargeApp(): Promise<void> {
   const pi = DG.TaskBarProgressIndicator.create('WebLogo');
   try {
     const app = new WebLogoApp();
-    const df: DG.DataFrame = await _package.files.readCsv('data/sample_PT_10000.csv');
+    const df: DG.DataFrame = await _package.files.readCsv('data/sample_PT_100000x5.csv');
     await grok.data.detectSemanticTypes(df);
     await app.init(df, 'webLogoLargeApp');
   } finally {

package/src/tests/WebLogo-positions-test.ts

@@ -61,8 +61,8 @@ ATC-G-TTGC--
 
     for (let i = 0; i < positions.length; i++) {
       expect(positions[i].name, resAllDf1[i].name);
-      for (const key in positions[i].freq)
-        expect(positions[i].freq[key].count, resAllDf1[i].freq[key].count);
+      for (const m of positions[i].getMonomers())
+        expect(positions[i].getFreq(m).count, resAllDf1[i].getFreq(m).count);
     }
   }, {skipReason: 'GROK-13300'});
 
@@ -109,8 +109,8 @@ ATC-G-TTGC--
 
     for (let i = 0; i < positions.length; i++) {
       expect(positions[i].name, resAllDf1[i].name);
-      for (const key in positions[i].freq)
-        expect(positions[i].freq[key].count, resAllDf1[i].freq[key].count);
+      for (const m of positions[i].getMonomers())
+        expect(positions[i].getFreq(m).count, resAllDf1[i].getFreq(m).count);
     }
   }, {skipReason: 'GROK-13300'});
 
@@ -187,10 +187,10 @@ ATC-G-TTGC--
 
 function expectPositionInfo(actualPos: PI, expectedPos: PI): void {
   expect(actualPos.name, expectedPos.name);
-  expectArray(Object.keys(actualPos.freq), Object.keys(expectedPos.freq));
-  for (const key in actualPos.freq) {
+  expectArray(actualPos.getMonomers(), expectedPos.getMonomers());
+  for (const key of actualPos.getMonomers()) {
     //
-    expect(actualPos.freq[key].count, expectedPos.freq[key].count);
+    expect(actualPos.getFreq(key).count, expectedPos.getFreq(key).count);
   }
 }