@datagrok/bio 2.16.2 → 2.16.4

package/files/tests/placer_MSA.csv

@@ -0,0 +1,5 @@
+MSA,Activity
+meI/hHis/Aca/N/T/dE/Thr_PO3H2/Aca//Phe_4Me,5.307510973968128
+meI/hHis/Aca/Cys_SEt/T/dK/Thr_PO3H2/Aca//Phe_4Me,5.723876853431544
+Lys_Boc/hHis/Aca/Cys_SEt/T/dK/Thr_PO3H2/Aca//Phe_4Me,5.185811246022437
+meI/hHis/Aca/Cys_SEt/T/dK/Thr_PO3H2///Phe_4Me,6.223502390804369

package/package.json

@@ -5,7 +5,7 @@
     "name": "Aleksandr Tanas",
     "email": "atanas@datagrok.ai"
   },
-  "version": "2.16.2",
+  "version": "2.16.4",
   "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",
@@ -37,9 +37,9 @@
   ],
   "dependencies": {
     "@biowasm/aioli": "^3.1.0",
-    "@datagrok-libraries/bio": "^5.45.2",
+    "@datagrok-libraries/bio": "^5.45.3",
     "@datagrok-libraries/chem-meta": "^1.2.7",
-    "@datagrok-libraries/math": "^1.2.1",
+    "@datagrok-libraries/math": "^1.2.2",
     "@datagrok-libraries/ml": "^6.7.4",
     "@datagrok-libraries/tutorials": "^1.4.3",
     "@datagrok-libraries/utils": "^4.3.6",
@@ -68,7 +68,7 @@
     "@typescript-eslint/eslint-plugin": "^8.8.1",
     "@typescript-eslint/parser": "^8.8.1",
     "datagrok-tools": "latest",
-    "eslint": "^9.12.0",
+    "eslint": "^8.57.1",
     "eslint-config-google": "^0.14.0",
     "eslint-plugin-rxjs": "^5.0.3",
     "source-map-loader": "^5.0.0",

package/src/global.d.ts

@@ -0,0 +1,13 @@
+import * as grokNamespace from 'datagrok-api/grok';
+import * as uiNamespace from 'datagrok-api/ui';
+import * as DGNamespace from 'datagrok-api/dg';
+import * as rxjsNamespace from 'rxjs';
+import $Namespace from 'cash-dom';
+
+declare global {
+    const grok: typeof grokNamespace;
+    const ui: typeof uiNamespace;
+    const DG: typeof DGNamespace;
+    const rjxs: typeof rxjsNamespace;
+    const $: typeof $Namespace;
+}

package/src/package.ts

@@ -26,6 +26,7 @@ import {getUserLibSettings, setUserLibSettings} from '@datagrok-libraries/bio/sr
 import {ISeqHelper} from '@datagrok-libraries/bio/src/utils/seq-helper';
 import {RDModule} from '@datagrok-libraries/chem-meta/src/rdkit-api';
 import {getRdKitModule} from '@datagrok-libraries/bio/src/chem/rdkit-module';
+import {ISeqHandler} from '@datagrok-libraries/bio/src/utils/macromolecule/seq-handler';
 
 import {getMacromoleculeColumns} from './utils/ui-utils';
 import {MacromoleculeDifferenceCellRenderer, MacromoleculeSequenceCellRenderer,} from './utils/cell-renderer';
@@ -69,7 +70,6 @@ import {getMolColumnFromHelm} from './utils/helm-to-molfile/utils';
 import {MonomerManager} from './utils/monomer-lib/monomer-manager/monomer-manager';
 import {calculateScoresWithEmptyValues} from './utils/calculate-scores';
 import {SeqHelper} from './utils/seq-helper/seq-helper';
-import {ISeqHandler} from '@datagrok-libraries/bio/src/utils/macromolecule/seq-handler';
 
 export const _package = new BioPackage(/*{debug: true}/**/);
 

package/src/tests/helm-tests.ts

@@ -12,58 +12,75 @@ category('helm', () => {
     'single-linear': {
       src: {helm: 'PEPTIDE1{R.F.Y.[GGaz].T.[meI]}$$$$'},
       tgt: {
-        simplePolymers: [6],
+        simplePolymers: [6], connections: [],
         bondedRGroups: [1, 2, 2, 2, 2, 1],
       }
     },
     'single-cyclized-C-2-2': {
-      src: {helm: 'PEPTIDE1{R.F.C.Y.G.H.[GGaz].C.T.[meI]}$PEPTIDE1,PEPTIDE1,3:R3-8,R3$$$'},
+      src: {helm: 'PEPTIDE1{R.F.C.Y.G.H.[GGaz].C.T.[meI]}$PEPTIDE1,PEPTIDE1,3:R3-8:R3$$$'},
       tgt: {
-        simplePolymers: [10],
+        simplePolymers: [10], connections: [[['PEPTIDE1', 3, 'R3'], ['PEPTIDE1', 8, 'R3']]],
         bondedRGroups: [1, 2, 3, 2, 2, 2, 2, 3, 2, 1],
       }
     },
     'single-cyclized-C-1-1': {
-      src: {helm: 'PEPTIDE1{F.C.Y.G.H.[GGaz].C.[meI]}$PEPTIDE1,PEPTIDE1,2:R3-7,R3$$$'},
+      src: {helm: 'PEPTIDE1{F.C.Y.G.H.[GGaz].C.[meI]}$PEPTIDE1,PEPTIDE1,2:R3-7:R3$$$'},
       tgt: {
-        simplePolymers: [8],
+        simplePolymers: [8], connections: [[['PEPTIDE1', 2, 'R3'], ['PEPTIDE1', 7, 'R3']]],
         bondedRGroups: [1, 3, 2, 2, 2, 1, 3, 1],
       }
     },
     'single-cyclized-C-0-0': {
-      src: {helm: 'PEPTIDE1{C.Y.G.H.[GGaz].C}$PEPTIDE1,PEPTIDE1,2:R3-7,R3$$$'},
+      src: {helm: 'PEPTIDE1{C.Y.G.H.[GGaz].C}$PEPTIDE1,PEPTIDE1,1:R3-6:R3$$$'},
       tgt: {
-        simplePolymers: [6],
+        simplePolymers: [6], connections: [[['PEPTIDE1', 1, 'R3'], ['PEPTIDE1', 6, 'R3']]],
         bondedRGroups: [2, 2, 2, 2, 2, 2],
       }
     },
-    'two-separated-1': {
+    'two-separated-5-1': {
       src: {helm: 'PEPTIDE1{R.F.Y.[GGaz].T}|PEPTIDE2{[meI]}$$$$'},
       tgt: {
-        simplePolymers: [5, 1],
-        bondedRGroups: [1, 2, 2, 2, 1, 1],
+        simplePolymers: [5, 1], connections: [],
+        bondedRGroups: [1, 2, 2, 2, 1, 0],
       }
     },
-    'two-separated-2': {
+    'two-separated-1-5': {
+      src: {helm: 'PEPTIDE1{[meI]}|PEPTIDE2{R.F.Y.[GGaz].T}$$$$'},
+      tgt: {
+        simplePolymers: [1, 5], connections: [],
+        bondedRGroups: [0, 1, 2, 2, 2, 1],
+      }
+    },
+    'two-separated-4-2': {
       src: {helm: 'PEPTIDE1{R.F.Y.[GGaz]}|PEPTIDE2{T.[meI]}$$$$'},
       tgt: {
-        simplePolymers: [4, 2],
+        simplePolymers: [4, 2], connections: [],
         bondedRGroups: [1, 2, 2, 1, 1, 1],
       }
     },
     'two-connected-1': {
-      src: {helm: 'PEPTIDE1{R.F.Y.[GGaz].T}|PEPTIDE2{[meI]}$PEPTIDE1,PEPTIDE2,5:R2-1,R1$$$'},
+      src: {helm: 'PEPTIDE1{R.F.Y.[GGaz].T}|PEPTIDE2{[meI]}$PEPTIDE1,PEPTIDE2,5:R2-1:R1$$$'},
       tgt: {
-        simplePolymers: [5, 1],
+        simplePolymers: [5, 1], connections: [[['PEPTIDE1', 5, 'R2'], ['PEPTIDE2', 1, 'R1']]],
         bondedRGroups: [1, 2, 2, 2, 2, 1],
       }
     },
     'two-connected-2': {
-      src: {helm: 'PEPTIDE1{R.F.Y.[GGaz]}|PEPTIDE2{T.[meI]}$PEPTIDE1,PEPTIDE2,4:R2-1,R1$$$'},
+      src: {helm: 'PEPTIDE1{R.F.Y.[GGaz]}|PEPTIDE2{T.[meI]}$PEPTIDE1,PEPTIDE2,4:R2-1:R1$$$'},
       tgt: {
-        simplePolymers: [4, 2],
+        simplePolymers: [4, 2], connections: [[['PEPTIDE1', 4, 'R2'], ['PEPTIDE2', 1, 'R1']]],
         bondedRGroups: [1, 2, 2, 2, 2, 1],
       }
+    },
+    'two-cyclized-1-9': {
+      src: {helm: 'PEPTIDE1{[meI]}|PEPTIDE2{R.F.[GGaz].T.G.H.F.Y.P}$PEPTIDE2,PEPTIDE2,3:R3-9:R2|PEPTIDE2,PEPTIDE1,3:R4-1:R1$$$V2.0'},
+      tgt: {
+        simplePolymers: [1, 9],
+        connections: [
+          [['PEPTIDE2', 3, 'R3'], ['PEPTIDE2', 9, 'R2']],
+          [['PEPTIDE2', 3, 'R4'], ['PEPTIDE1', 1, 'R1']]],
+        bondedRGroups: [1, 1, 2, 4, 2, 2, 2, 2, 2, 1],
+      }
     }
   };
 
@@ -74,12 +91,21 @@ category('helm', () => {
       const simplePolymers = resHelm.simplePolymers
         .map((sp) => sp.monomers.length);
       const totalMonomerCount = simplePolymers.reduce((a, b) => a + b, 0);
-      expect(simplePolymers, tgt.simplePolymers);
+      expectArray(simplePolymers, tgt.simplePolymers);
+
+      const connections = resHelm.connectionList.getConnectionData()
+        .map((cdi) => {
+          return [
+            [cdi[0].polymerId, cdi[0].bond.monomerIdx + 1, `R${cdi[0].bond.rGroupId}`],
+            [cdi[1].polymerId, cdi[1].bond.monomerIdx + 1, `R${cdi[1].bond.rGroupId}`]];
+        });
+
+      expectArray(connections, tgt.connections);
 
-      const bondedRGroups = wu.count(0).take(resHelm.bondedRGroupsMap.size)
-        .map((i) => resHelm.bondedRGroupsMap.get(i)!.length).toArray();
+      const bondedRGroups = wu.count(0).take(resHelm.bondedRGroupsMap.length)
+        .map((i) => resHelm.bondedRGroupsMap[i].length).toArray();
       expect(totalMonomerCount, bondedRGroups.length);
       // expectArray(bondedRGroups, tgt.bondedRGroups);
-    }, {skipReason: 'new tests'});
+    });
   }
 });

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

@@ -4,10 +4,9 @@ import * as ui from 'datagrok-api/ui';
 
 import wu from 'wu';
 
-import {after, before, category, expect, test} from '@datagrok-libraries/utils/src/test';
+import {after, before, category, expect, expectArray, test} from '@datagrok-libraries/utils/src/test';
 import {MonomerPlacer, hitBounds} from '@datagrok-libraries/bio/src/utils/cell-renderer-monomer-placer';
 import {monomerToShort} from '@datagrok-libraries/bio/src/utils/macromolecule';
-import {getSeqHelper, ISeqHelper} from '@datagrok-libraries/bio/src/utils/seq-helper';
 import {getMonomerLibHelper, IMonomerLibHelper} from '@datagrok-libraries/bio/src/monomer-works/monomer-utils';
 import {
   getUserLibSettings, setUserLibSettings
@@ -164,4 +163,60 @@ id3,QHIRE--LT
       expect(res, testData.tgt);
     });
   }
+
+  const lengthsTests = {
+    mono1: {
+      src: {
+        csv: 'seq' + '\n' +
+          'm1/m2/m3/m4/m5/m6/m7/m8/m9' + '\n' +
+          'n1/m2/n3/m4/n5/m6/n7/m8/n9' + '\n' +
+          'm1/n2/m3/n4/m5/n6/m7/n8/m9' + '\n',
+      },
+      tgt: {
+        lengths: [5, 31, 57, 83, 109, 135, 161, 187, 213, 239],
+      }
+    },
+    monoWithGaps: {
+      src: {
+        csv: 'seq' + '\n' +
+          'm1/m2/m3/m4/m5/m6//m8/m9' + '\n' +
+          'n1/m2/n3/m4/n5/m6//m8/n9' + '\n' +
+          'm1/n2/m3/n4/m5/n6/m7/n8/m9' + '\n',
+      },
+      tgt: {
+        lengths: [5, 31, 57, 83, 109, 135, 161, 187, 213, 239],
+      }
+    },
+    monoWithGapColumn: {
+      src: {
+        csv: 'seq' + '\n' +
+          'm1/m2/m3/m4/m5/m6//m8/m9' + '\n' +
+          'n1/m2/n3/m4/n5/m6//m8/n9' + '\n' +
+          'm1/n2/m3/n4/m5///n8/m9' + '\n',
+      },
+      tgt: {lengths: [5, 31, 57, 83, 109, 135, 161, 180, 206, 232],}
+    },
+  };
+
+  for (const [testName, testData] of Object.entries(lengthsTests)) {
+    test(`getCellMonomerLengths-${testName}`, async () => {
+      const df: DG.DataFrame = DG.DataFrame.fromCsv(testData.src.csv);
+      await grok.data.detectSemanticTypes(df);
+      const seqCol = df.getCol('seq');
+
+      const monLengthLimit: number = 3;
+      const charWidth: number = 7;
+      const sepWidth: number = 12;
+      const colTemp = new MonomerPlacer(null, seqCol, _package.logger, monLengthLimit, () => {
+        return {
+          monomerCharWidth: charWidth,
+          separatorWidth: sepWidth,
+          monomerToShort: monomerToShort,
+        };
+      });
+      await colTemp.init();
+      const resLengths = colTemp.getCellMonomerLengths(0, 1000)[1];
+      expectArray(resLengths, testData.tgt.lengths);
+    });
+  }
 });

package/src/utils/helm-to-molfile/converter/connection-list.ts

@@ -4,12 +4,12 @@ import {Bond} from './types';
 
 export class ConnectionList {
   constructor(connectionList: string) {
-    const splitted = connectionList.split(HELM_ITEM_SEPARATOR);
+    const splitted = connectionList.split(HELM_ITEM_SEPARATOR).filter((ci) => ci);
     splitted.forEach((connectionItem: string) => this.validateConnectionItem(connectionItem));
     this.connectionItems = splitted;
   }
 
-  private connectionItems: string[];
+  public connectionItems: string[];
 
   private validateConnectionItem(connectionItem: string): void {
     const allowedType = `(${HELM_POLYMER_TYPE.PEPTIDE}|${HELM_POLYMER_TYPE.RNA})`;
@@ -18,10 +18,10 @@ export class ConnectionList {
       throw new Error(`Cannot parse connection item from ${connectionItem}`);
   }
 
-  getConnectionData(): {polymerId: string, bond: Bond}[][] {
-    const result: {polymerId: string, bond: Bond}[][] = [];
+  getConnectionData(): { polymerId: string, bond: Bond }[][] {
+    const result: { polymerId: string, bond: Bond }[][] = [];
     this.connectionItems.forEach((connectionItem: string) => {
-      const pair: {polymerId: string, bond: Bond}[] = [];
+      const pair: { polymerId: string, bond: Bond }[] = [];
       const splitted = connectionItem.split(',');
       splitted[2].split('-').forEach((item, idx) => {
         const polymerId = splitted[idx];

package/src/utils/helm-to-molfile/converter/helm.ts

@@ -10,8 +10,7 @@ export class Helm {
     const simplePolymers = helmSections[0].split(HELM_ITEM_SEPARATOR);
     this.simplePolymers = simplePolymers
       .map((item) => new SimplePolymer(item));
-    if (helmSections[1] !== '')
-      this.connectionList = new ConnectionList(helmSections[1]);
+    this.connectionList = new ConnectionList(helmSections[1]);
     this.bondData = this.getBondData();
 
     this.bondedRGroupsMap = this.getBondedRGroupsMap();
@@ -22,25 +21,25 @@ export class Helm {
   readonly bondData: Bond[][];
 
   public readonly simplePolymers: SimplePolymer[];
-  public readonly connectionList?: ConnectionList;
+  public readonly connectionList: ConnectionList;
 
   /** Maps global monomer index to r-group ids (starting from 1) participating
    * in connection */
-  readonly bondedRGroupsMap: Map<number, number[]>;
+  readonly bondedRGroupsMap: number[][];
 
-  private getBondedRGroupsMap(): Map<number, number[]> {
-    const bondedRGroupsMap = new Map<number, number[]>();
+  private getBondedRGroupsMap(): number[][] {
+    const monomerCount = this.simplePolymers.map((sp) => sp.monomers.length)
+      .reduce((a, b) => a + b, 0);
+    const bondedRGroupsList: number[][] = Array.from({length: monomerCount}, () => []);
     this.bondData.forEach((bond) => {
       bond.forEach((bondPart) => {
         const monomerIdx = bondPart.monomerIdx;
         const rGroupId = bondPart.rGroupId;
-        if (!bondedRGroupsMap.get(monomerIdx))
-          bondedRGroupsMap.set(monomerIdx, []);
-        bondedRGroupsMap.get(monomerIdx)!.push(rGroupId);
+        bondedRGroupsList[monomerIdx].push(rGroupId);
       });
     });
 
-    return bondedRGroupsMap;
+    return bondedRGroupsList;
   }
 
   toString() {
@@ -93,19 +92,17 @@ export class Helm {
       this.shiftBondMonomerIds(shift, bondData);
       result.push(...bondData);
     });
-    if (this.connectionList) {
-      const connectionData = this.connectionList.getConnectionData();
-      connectionData.forEach((connection) => {
-        const data: Bond[] = [];
-        connection.forEach((connectionItem) => {
-          const shift = shifts[connectionItem.polymerId];
-          const bond = connectionItem.bond;
-          bond.monomerIdx += shift;
-          data.push(bond);
-        });
-        result.push(data);
+    const connectionData = this.connectionList.getConnectionData();
+    connectionData.forEach((connection) => {
+      const data: Bond[] = [];
+      connection.forEach((connectionItem) => {
+        const shift = shifts[connectionItem.polymerId];
+        const bond = connectionItem.bond;
+        bond.monomerIdx += shift;
+        data.push(bond);
       });
-    }
+      result.push(data);
+    });
     return result;
   }
 }

package/src/utils/helm-to-molfile/converter/monomer-wrapper.ts

@@ -28,8 +28,7 @@ export class MonomerWrapper {
     this.molfileWrapper = MolfileWrapperFactory.getInstance(molfile, monomerSymbol);
     this.capGroupElements = this.getCapGroupElements(libraryMonomerObject);
 
-    if (helm.bondedRGroupsMap.has(monomerIdx))
-      this.removeRGroups(helm.bondedRGroupsMap.get(monomerIdx)!);
+    this.removeRGroups(helm.bondedRGroupsMap[monomerIdx]!);
     this.capRemainingRGroups();
 
     this.shiftCoordinates(shift);

package/src/utils/monomer-lib/library-file-manager/file-manager.ts

@@ -264,7 +264,7 @@ export class MonomerLibFileManager implements IMonomerLibFileManager {
     this.logger.debug(`${logPrefix}, start`);
 
     const libPaths = await grok.dapi.files.list(LIB_PATH)
-      .then((l) => l.map((fi) => fi.fullPath));
+      .then((l) => l.filter((f) => f.isFile).map((fi) => fi.fullPath));
 
     const checkForUi = false;
     const existingLibPaths: string[] = [];

package/src/utils/monomer-lib/monomer-lib-base.ts

@@ -161,12 +161,12 @@ export class MonomerLibBase implements IMonomerLibBase {
   getTooltip(biotype: HelmType, monomerSymbol: string): HTMLElement {
     const polymerType = helmTypeToPolymerType(biotype);
     const res = ui.div([], {classes: 'ui-form ui-tooltip'});
+    const wem = this.getWebEditorMonomer(biotype, monomerSymbol)!;
     const monomer = this.getMonomer(polymerType, monomerSymbol);
     if (monomer) {
       // Symbol & Name
       const symbol = monomer[REQ.SYMBOL];
       const _name = monomer[REQ.NAME];
-      const wem = this.getWebEditorMonomer(biotype, monomerSymbol)!;
 
       const htmlColor = wem.backgroundcolor;
       res.append(ui.divH([

package/src/viewers/web-logo-viewer.ts

@@ -548,6 +548,7 @@ export class WebLogoViewer extends DG.JsViewer implements IWebLogoViewer {
         style: {
           display: 'flex',
           flexDirection: 'row',
+          flexGrow: 0,
           /** For alignContent to have an effect */ flexWrap: 'wrap',
           /* backgroundColor: '#EEFFEE' */
         }