@datagrok/bio 2.8.1 → 2.8.3

package/package.json

@@ -5,7 +5,7 @@
     "name": "Leonid Stolbov",
     "email": "lstolbov@datagrok.ai"
   },
-  "version": "2.8.1",
+  "version": "2.8.3",
   "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",
@@ -16,7 +16,7 @@
     {
       "name": "MaxMonomerLength",
       "propertyType": "int",
-      "defaultValue": 3,
+      "defaultValue": 4,
       "nullable": false
     },
     {
@@ -34,7 +34,7 @@
   ],
   "dependencies": {
     "@biowasm/aioli": "^3.1.0",
-    "@datagrok-libraries/bio": "^5.34.0",
+    "@datagrok-libraries/bio": "^5.34.1",
     "@datagrok-libraries/chem-meta": "^1.0.1",
     "@datagrok-libraries/ml": "^6.3.39",
     "@datagrok-libraries/tutorials": "^1.3.6",

package/scripts/sequence_generator.py

@@ -13,7 +13,7 @@
 # input: bool disable_cliffs = False [Disable generation of cliffs]
 # input: double cliff_probability = 0.01 [Probability to make activity cliff of a sequence]
 # input: double cliff_strength = 4.0 [Strength of cliff]
-# input: double fasta_separator = '' [Separator for a FASTA notation]
+# input: string fasta_separator = '' {nullable: true}
 # output: dataframe sequences
 
 """
@@ -54,6 +54,7 @@ alphabets: Dict[str, str] = {
     "PT": "A,C,D,E,F,G,H,I,K,L,M,N,P,Q,R,S,T,V,W,Y",
     "DNA": "A,T,G,C",
     "RNA": "A,U,G,C",
+    "PT_HELM": "A,C,D,E,F,G,H,I,K,L,M,N,P,Q,R,S,T,V,W,Y,dA,dC,dD,dE,dF,dH,dI,dK,dL,dM,dN,dP,dQ,dR,dS,dT,dV,dW,dY,meA,meD,meS,meT,meV,meY,meE,meG,meI,meK,meM,meN,meQ,meC,meR,meW,meF,meH,meL,Nle,Nva,Orn,Iva,aIle,gGlu,Hcy,Hse,Hyp,D-gGlu,D-Nle,D-hPhe,D-Hyp,D-Nva,D-Orn,Pyr,Phe_3Cl,Phe_4Cl,Phe_4NH2,Phg,Ser_tBu,Tyr_Bn,Tza,1Nal,Cha,Lys_Boc,aThr,D-2Nal,D-2Thi,D-aHyp,D-aIle,D-Phg,D-Ser_tBu,Cya,Lys_Me3,Pen,Phe_4Me,Ser_Bn,Tyr_tBu,2Nal,Thi,aHyp,Ala_tBu,hPhe,D-1Nal,D-aThr,D-Cha,D-Pen,D-Phe_4Cl,D-Ser_Bn,Wil,Oic_3aS-7aS,Pip,3Pal,4Pal,Abu,Apm,Chg,Dab,Dap,D-3Pal,D-aMeAbu,D-Chg,D-Cit,D-Dab,D-Pip,D-Tic,Aca,Tic,Aad,Cit,Aze,Ac5c,Aib,D-2Pal,D-Abu,D-Dap,Asu,D-Thz,D-Trp_For,D-Tyr_Et,Lys_Ac,Asp_OMe,Phe_ab-dehydro,Sta_3xi4xi,Tyr_ab-dehydroMe,App,Cap,Cys_SEt,Dsu,pnC,pnG,Pqa,Pro_4Me3OH,Met_O2,Phe_2Me,Phe_34diCl,Phe_4Br,Phe_4I,Phe_4Sdihydroorotamido,Pyl,Ser_PO3H2,Thr_PO3H2,Thz,Trp_Me,Tyr_26diMe,Tyr_3I,Tyr_3NO2,Tyr_Ph4OH,Tyr_SO3H,Val_3OH,xiIle,NMe2Abz,NMebAla,aMePhe,aMePro,aMeTyr_3OH,Bmt,Bmt_E,Cys_Bn,Gla,hHis,His_1Me,Gly_allyl,Gly_cPr,Asp_Ph2NH2,Azi,2Abz,3Abz,4Abz,Ac3c,Ac6c,bAla,D-Bmt,D-Bmt_E,D-hArg,D-Phe_4F,D-Trp_2Me,D-Tyr_Me,D-xiIle,Lys_iPr,Phe_ab-dehydro_3NO2,Sta_3S4S,Bux,Dpm,pnA,pnT,seC,Met_O,nTyr,Oic_3aR-7aS,Oic_3axi-7axi,Phe_2F,Phe_3F,Phe_4F,Phe_4NO2,Phe_bbdiMe,Trp_5OH,Trp_Ome,Tyr_35diI,Tyr_3OH,Tyr_Me,Tyr_PO3H2,xiHyp,xiThr,NMe4Abz,aMeTyr,Aoda,Bpa,Cys_Me,Dip,hArg,His_1Bn,His_3Me,Hyl_5xi,Bip,Abu_23dehydro,D-Dip,Dha,D-hArg_Et2,D-Met_S-O,D-His_1Bn,D-nTyr,D-Phe_4ureido",
 }
 
 
@@ -392,7 +393,9 @@ if not grok:
     helm_library_file = args.helm_library_file
     helm_connection_mode = args.helm_connection_mode
 
-if helm_library_file is None:
+helm_init = "helm_library_file" in globals() and helm_library_file is not None
+
+if not helm_init:
     alphabet: Alphabet = (
         alphabets[alphabet_key].split(",")
         if alphabet_key in alphabets
@@ -414,7 +417,7 @@ header, data = generate_sequences(
     cliff_probability,
     cliff_strength,
 )
-if helm_library_file is None:
+if not helm_init:
     data_formatted = convert_to_fasta(data, fasta_separator)
 else:
     data_formatted = convert_to_helm(data, helm_connection_mode)

package/src/demo/bio03-atomic-level.ts

@@ -7,7 +7,7 @@ import {DemoScript} from '@datagrok-libraries/tutorials/src/demo-script';
 import {delay} from '@datagrok-libraries/utils/src/test';
 
 export async function demoBio03UI(): Promise<void> {
-  const dataFn: string = 'samples/sample_HELM.csv';
+  const dataFn: string = 'samples/HELM.csv';
   const seqColName = 'HELM';
 
   let df: DG.DataFrame;

package/src/demo/bio05-helm-msa-sequence-space.ts

@@ -11,7 +11,7 @@ import {DemoScript} from '@datagrok-libraries/tutorials/src/demo-script';
 import {DimReductionMethods} from '@datagrok-libraries/ml/src/reduce-dimensionality';
 import {MmDistanceFunctionsNames} from '@datagrok-libraries/ml/src/macromolecule-distance-functions';
 
-const helmFn: string = 'samples/sample_HELM.csv';
+const helmFn: string = 'samples/HELM.csv';
 
 export async function demoBio05UI(): Promise<void> {
   let view: DG.TableView;

package/src/package.ts

@@ -167,7 +167,7 @@ export async function libraryPanel(_seqColumn: DG.Column): Promise<DG.Widget> {
 export function packageSettingsEditor(propList: DG.Property[]): DG.Widget {
   const widget = new PackageSettingsEditorWidget(propList);
   widget.init().then(); // Ignore promise returned
-  return widget;
+  return widget as DG.Widget;
 }
 
 // -- Cell renderers --
@@ -246,7 +246,7 @@ export function webLogoViewer() {
 //tags: viewer, panel
 //meta.icon: files/icons/vdregions-viewer.svg
 //output: viewer result
-export function vdRegionViewer() {
+export function vdRegionsViewer() {
   return new VdRegionsViewer();
 }
 

package/src/tests/bio-tests.ts

@@ -2,7 +2,7 @@ import * as grok from 'datagrok-api/grok';
 import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
 
-import {category, test, expect, expectObject} from '@datagrok-libraries/utils/src/test';
+import {category, test, expect, expectObject, expectArray} from '@datagrok-libraries/utils/src/test';
 import {
   getAlphabetSimilarity,
   monomerToShort,
@@ -83,13 +83,43 @@ category('WebLogo.monomerToShort', () => {
     expect(monomerToShort('Short', 5), 'Short');
   });
   test('longMonomerLong56', async () => {
-    expect(monomerToShort('Long56', 5), 'Long5…');
+    expect(monomerToShort('Long56', 6), 'Long56');
   });
   test('longMonomerComplexFirstPartShort', async () => {
     expect(monomerToShort('Long-long', 5), 'Long…');
   });
   test('longMonomerComplexFirstPartLong56', async () => {
-    expect(monomerToShort('Long56-long', 5), 'Long5…');
+    expect(monomerToShort('Long56-long', 6), 'Long5…');
+  });
+  test('monomerToShort', async () => {
+    const pairs = [
+      ['AbC', 'AbC'],
+      ['AbCd', 'Ab…'],
+      ['ABc', 'ABc'],
+      ['ABcd', 'AB…'],
+      ['A_b', 'A_b'],
+      ['A_bc', 'A…'],
+      ['Ab_c', 'Ab…'],
+      ['A1_b', 'A1…'],
+      ['Abc_d', 'Ab…'],
+      ['Abcd_e', 'Ab…'],
+      ['A-b', 'A-b'],
+      ['A-bc', 'A…'],
+      ['Ab-c', 'Ab…'],
+      ['A1-b', 'A1…'],
+      ['Abc-d', 'Ab…'],
+      ['Abcd-e', 'Ab…'],
+      ['A', 'A'],
+      ['Ab', 'Ab'],
+      ['Abc', 'Abc'],
+      ['Ab…', 'Ab…'],
+      ['Abcd', 'Ab…'],
+      ['Abcde', 'Ab…'],
+    ];
+    const src: string[] = pairs.map((p) => p[0]);
+    const tgt: string[] = pairs.map((p) => p[1]);
+    const res: string [] = src.map((m) => monomerToShort(m, 3));
+    expectArray(res, tgt);
   });
 });
 

package/src/tests/detectors-tests.ts

@@ -146,9 +146,9 @@ MWRSWY-CKHP`;
   const samples: { [key: string]: string } = {
     [Samples.fastaFasta]: 'System:AppData/Bio/data/sample_FASTA.fasta',
     [Samples.fastaPtCsv]: 'System:AppData/Bio/data/sample_FASTA_PT.csv',
-    [Samples.msaComplex]: 'System:AppData/Bio/samples/sample_MSA.csv',
-    [Samples.fastaCsv]: 'System:AppData/Bio/samples/sample_FASTA.csv',
-    [Samples.helmCsv]: 'System:AppData/Bio/samples/sample_HELM.csv',
+    [Samples.msaComplex]: 'System:AppData/Bio/samples/MSA.csv',
+    [Samples.fastaCsv]: 'System:AppData/Bio/samples/FASTA.csv',
+    [Samples.helmCsv]: 'System:AppData/Bio/samples/HELM.csv',
     [Samples.peptidesComplex]: 'System:AppData/Bio/tests/peptides_complex_msa.csv',
     [Samples.peptidesSimple]: 'System:AppData/Bio/tests/peptides_simple_msa.csv',
     [Samples.testDemogCsv]: 'System:AppData/Bio/tests/testDemog.csv',

package/src/tests/renderers-monomer-placer.ts

@@ -26,10 +26,10 @@ category('renderers: monomerPlacer', () => {
         {src: {row: 1, x: 5}, tgt: {pos: 0}},
         {src: {row: 1, x: 6}, tgt: {pos: 0}},
         {src: {row: 1, x: 26}, tgt: {pos: 1}},
-        {src: {row: 1, x: 170}, tgt: {pos: 6}},
-        {src: {row: 1, x: 208}, tgt: {pos: 7}},
-        {src: {row: 2, x: 170}, tgt: {pos: 5}},
-        {src: {row: 2, x: 175}, tgt: {pos: 5}},
+        {src: {row: 1, x: 160}, tgt: {pos: 6}},
+        {src: {row: 1, x: 185}, tgt: {pos: 7}},
+        {src: {row: 2, x: 140}, tgt: {pos: 5}},
+        {src: {row: 2, x: 145}, tgt: {pos: 5}},
       ]
     },
     splitterMsa: {
@@ -46,9 +46,9 @@ category('renderers: monomerPlacer', () => {
         {src: {row: 1, x: 1}, tgt: {pos: null}},
         {src: {row: 1, x: 26}, tgt: {pos: 0}},
         {src: {row: 1, x: 170}, tgt: {pos: 4}},
-        {src: {row: 1, x: 227}, tgt: {pos: 5}},
-        {src: {row: 2, x: 220}, tgt: {pos: 5}},
-        {src: {row: 2, x: 227}, tgt: {pos: 5}},
+        {src: {row: 1, x: 200}, tgt: {pos: 5}},
+        {src: {row: 2, x: 200}, tgt: {pos: 5}},
+        {src: {row: 2, x: 203}, tgt: {pos: 5}},
       ]
     },
     fastaMsa: {

package/src/tests/renderers-test.ts

@@ -52,7 +52,7 @@ category('renderers', () => {
   }, {skipReason: 'GROK-11212'});
 
   async function _rendererMacromoleculeFasta() {
-    const csv: string = await grok.dapi.files.readAsText('System:AppData/Bio/samples/sample_FASTA.csv');
+    const csv: string = await grok.dapi.files.readAsText('System:AppData/Bio/samples/FASTA.csv');
     const df: DG.DataFrame = DG.DataFrame.fromCsv(csv);
 
     const seqCol = df.getCol('Sequence');

package/src/tests/splitters-test.ts

@@ -79,7 +79,7 @@ category('splitters', async () => {
   test('testHelm3', async () => { await _testHelmSplitter(data.testHelm3[0], data.testHelm3[1]); });
 
   test('splitToMonomers', async () => {
-    const df: DG.DataFrame = await grok.dapi.files.readCsv('System:AppData/Bio/samples/sample_MSA.csv');
+    const df: DG.DataFrame = await grok.dapi.files.readCsv('System:AppData/Bio/samples/MSA.csv');
 
     const seqCol = df.getCol('MSA');
     const semType = await grok.functions.call('Bio:detectMacromolecule', {col: seqCol});

package/scripts/admet-requirements.txt

@@ -1,7 +0,0 @@
-numpy==1.16.6
-pandas==0.24.2
-python-dateutil==2.8.2
-pytz==2022.5
-scikit-learn==0.17.1
-scipy==1.2.3
-six==1.16.0

package/scripts/admet-run.py

@@ -1,27 +0,0 @@
-#!/usr/bin/env python2
-# -*- coding: utf-8 -*-
-"""
-Created on Mon Feb 19 17:30:46 2018
-
-@author: cbdd
-"""
-from sklearn.externals import joblib
-import numpy as np
-import pandas as pd
-import os
-
-###################################### Load model ##########
-# current_path = os.path.split(os.path.realpath(__file__))[0]
-cf = joblib.load('CYP3A4-substrate.pkl')
-
-###################################### Load descriptors ##########
-fingerprint_content = pd.read_csv('des.csv').ix[:, 1:]
-des_list = np.array(fingerprint_content)
-
-###################################### Prediction ##########
-y_predict_label = cf.predict(des_list)
-y_predict_proba = cf.predict_proba(des_list)
-print('#' * 10 + 'Results labels' + '#' * 10)
-print(y_predict_label)
-print('#' * 10 + 'Results probabilities' + '#' * 10)
-print(y_predict_proba)