@datagrok/helm 2.1.8 → 2.1.9

package/package.json

@@ -1,12 +1,12 @@
 {
   "name": "@datagrok/helm",
   "friendlyName": "Helm",
-  "version": "2.1.8",
+  "version": "2.1.9",
   "author": {
     "name": "Oleksandra Serhiienko",
     "email": "oserhiienko@datagrok.ai"
   },
-  "description": "Provides support for HELM notation (importing, detecting, rendering, conversion). [Learn more](https://github.com/datagrok-ai/public/blob/master/packages/Helm/README.md)",
+  "description": "Provides support for HELM notation (importing, detecting, rendering, conversion).",
   "dependencies": {
     "@datagrok-libraries/bio": "^5.22.1",
     "@datagrok-libraries/utils": "^1.19.1",

package/src/cell-renderer.ts

@@ -37,27 +37,27 @@ export class HelmCellRenderer extends DG.GridCellRenderer {
           } else if (argsX > maxLengthWordsSum[mid + 1]) {
             left = mid + 1;
           }
-          if (left == right) {
+          if (left == right)
             found = true;
-          }
         }
       }
       left = (argsX >= maxLengthWordsSum[left]) ? left + 1 : left;
       const monomers = findMonomers(gridCell.cell.value);
-      let s: string = gridCell.cell.value ?? '';
-      let subParts: string[] = parseHelm(s);
-      let allParts: string[] = getParts(subParts, s);
-      let tooltipMessage: HTMLElement[] = [];
+      const s: string = gridCell.cell.value ?? '';
+      const subParts: string[] = parseHelm(s);
+      const allParts: string[] = getParts(subParts, s);
+      const tooltipMessage: HTMLElement[] = [];
       for (let i = 0; i < allParts.length; ++i) {
-        if (monomers.has(allParts[i]))
+        if (monomers.has(allParts[i])) {
           tooltipMessage[i] = ui.divV([
             ui.divText(`Monomer ${allParts[i]} not found.`),
             ui.divText('Open the Context Panel, then expand Manage Libraries')
           ]);
+        }
       }
-      (((tooltipMessage[left]?.childNodes.length ?? 0) > 0))
-        ? ui.tooltip.show(ui.div(tooltipMessage[left]), e.x + 16, e.y + 16)
-        : ui.tooltip.hide();
+      (((tooltipMessage[left]?.childNodes.length ?? 0) > 0)) ?
+        ui.tooltip.show(ui.div(tooltipMessage[left]), e.x + 16, e.y + 16) :
+        ui.tooltip.hide();
     } catch (err: any) {
       const errMsg: string = errorToConsole(err);
       console.error('Helm: HelmCellRenderer.onMouseMove() error:\n' + errMsg);
@@ -71,8 +71,8 @@ export class HelmCellRenderer extends DG.GridCellRenderer {
     const undefinedColor = 'rgb(100,100,100)';
     const grayColor = '#808080';
     const monomers = findMonomers(gridCell.cell.value);
-    let s: string = gridCell.cell.value ?? '';
-    let subParts: string[] = parseHelm(s);
+    const s: string = gridCell.cell.value ?? '';
+    const subParts: string[] = parseHelm(s);
     if (monomers.size == 0 && grid) {
       const host = ui.div([], {style: {width: `${w}px`, height: `${h}px`}});
       host.setAttribute('dataformat', 'helm');
@@ -96,20 +96,20 @@ export class HelmCellRenderer extends DG.GridCellRenderer {
       g.font = '12px monospace';
       g.textBaseline = 'top';
       let x1 = x;
-      let maxLengthWords: any = {};
-      let maxLengthWordSum: any = {};
-      let allParts: string[] = getParts(subParts, s);
+      const maxLengthWords: any = {};
+      const maxLengthWordSum: any = {};
+      const allParts: string[] = getParts(subParts, s);
       for (let i = 0; i < allParts.length; ++i) {
         maxLengthWords[i] = allParts[i].length * 7;
-        let color = monomers.has(allParts[i]) ? 'red' : grayColor;
+        const color = monomers.has(allParts[i]) ? 'red' : grayColor;
         g.fillStyle = undefinedColor;
         x1 = printLeftOrCentered(x1, y, w, h, g, allParts[i], color, 0, true, 1.0);
       }
 
       maxLengthWordSum[0] = maxLengthWords[0];
-      for (let i = 1; i < allParts.length; i++) {
+      for (let i = 1; i < allParts.length; i++)
         maxLengthWordSum[i] = maxLengthWordSum[i - 1] + maxLengthWords[i];
-      }
+
       gridCell.cell.column.temp = {
         'helm-sum-maxLengthWords': maxLengthWordSum,
         'helm-maxLengthWords': maxLengthWords

package/src/tests/helm-tests.ts

@@ -1,4 +1,4 @@
-import {after, before, category, delay, expect, test} from '@datagrok-libraries/utils/src/test';
+import {after, before, category, delay, expect, expectArray, test} from '@datagrok-libraries/utils/src/test';
 //import {findMonomers, helmToFasta, helmToPeptide, helmToRNA, initHelm} from '../package';
 import {_package} from '../package-test';
 import {parseHelm} from '../utils';
@@ -18,7 +18,9 @@ category('Helm', () => {
   //   expect(await helmToRNA('RNA1{R(U)P.R(T)P.R(G)P.R(C)P.R(A)}$$$$'), 'UTGCA');
   //   expect(await helmToRNA('RNA1{P.R(U).P.R(T)}$$$$'), 'UT');
   //   // eslint-disable-next-line max-len
-  //   expect(await helmToRNA('RNA1{R(U)P.R(T)P}|RNA2{P.R(A)P.R(A)}$RNA1,RNA2,2:pair-6:pair|RNA1,RNA2,5:pair-3:pair$$$'), 'UT AA');
+  //   expect(
+  // await helmToRNA('RNA1{R(U)P.R(T)P}|RNA2{P.R(A)P.R(A)}$RNA1,RNA2,2:pair-6:pair|RNA1,RNA2,5:pair-3:pair$$$'), 'UT AA'
+  //   );
   // });
   //
   // test('helmToPeptide', async () => {
@@ -46,7 +48,32 @@ category('Helm', () => {
   //   expect(col.tags[DG.TAGS.UNITS], 'HELM');
   // });
 
-  test('parseHelm', async() => {
+  const complexMonomers = [
+    // tests parsing of complex monomemer in square brackets like [L-hArg(Et,Et)]
+    'PEPTIDE1{[L-hArg(Et,Et)].E.F.G}|PEPTIDE2{C.E}$PEPTIDE1,PEPTIDE2,2:R3-1:R1$$$V2.0',
+    // tests parsing of complex monomer and one as a side chain as well
+    'PEPTIDE1{[L-hArg(Et,Et)]([L-hArg(Et,Et)]).E.F.G}$$$$',
+    // tests parsing of complex monomer and one as a side chain as well
+    'RNA1{[dhp]([m1A])p.r(T)p.r(T)p.r(G)p}$$$$V2.0',
+    // tests complex monomer as side chain
+    'RNA1{r([mo6pur])p.r(T)p.r(T)p.r(G)p}$$$$V2.0',
+    // test complex monomer, side chain and linker
+    'RNA1{[afhna]([mo6pur])[36SS].r(T)p}$$$$V2.0'
+  ];
+
+  const complexMonomersExpected = [
+    ['L-hArg(Et,Et)', 'E', 'F', 'G', 'C', 'E'],
+    ['L-hArg(Et,Et)', 'L-hArg(Et,Et)', 'E', 'F', 'G'],
+    ['dhp', 'm1A', 'p', 'r', 'T', 'p', 'r', 'T', 'p', 'r', 'G', 'p'],
+    ['r', 'mo6pur', 'p', 'r', 'T', 'p', 'r', 'T', 'p', 'r', 'G', 'p'],
+    ['afhna', 'mo6pur', '36SS', 'r', 'T', 'p']
+  ];
+
+  const complexTestNames = [
+    'comples-monomer', 'complex-monomer+side-chain', 'complex-monomer+side-chain-RNA',
+    'complex-side-chain', 'complex+side-chain+linker'
+  ];
+  test('parseHelm', async () => {
     const expectedResults = [
       ['meI', 'hHis', 'Aca', 'N', 'T', 'dK', 'Thr_PO3H2', 'D-Tyr_Et', 'Aze', 'dV', 'E', 'Phe_4Me'],
       ['A', 'C', 'T', 'G', 'W', 'E', 'Q'],
@@ -55,14 +82,24 @@ category('Helm', () => {
     ];
     const helmStrings = [
       'PEPTIDE1{meI.hHis.Aca.N.T.dK.Thr_PO3H2.Aca.D-Tyr_Et.Aze.dV.E.N.dV.Phe_4Me}$$$',
+      // eslint-disable-next-line max-len
       'PEPTIDE1{A.C.T.G.C.T.W.G.T.W.E.C.W.C.Q.W}|PEPTIDE2{A.C.T.G.C.T.W.G.T.W.E.Q}$PEPTIDE1,PEPTIDE1,5:R3-14:R3|PEPTIDE2,PEPTIDE1,2:R3-12:R3$$$',
       'RNA1{R(U)P.R(T)P}|RNA2{P.R(A)P.R(A)}$RNA1,RNA2,2:pair-6:pair|RNA1,RNA2,5:pair-3:pair$$$',
       'PEPTIDE1{A.*.G.C}$$$$V2.0'
     ];
     for (let idx = 0; idx < helmStrings.length; ++idx) {
-      let monomerSet = new Set(parseHelm(helmStrings[idx]));
-      let monomerArray = Array.from(monomerSet);
+      const monomerSet = new Set(parseHelm(helmStrings[idx]));
+      const monomerArray = Array.from(monomerSet);
       expect(JSON.stringify(monomerArray), JSON.stringify(expectedResults[idx]));
     }
   });
+  complexMonomers.forEach((helm, i) => {
+    test(complexTestNames[i], async () => {
+      const monomersArray = parseHelm(helm);
+      monomersArray.sort();
+      const expected = complexMonomersExpected[i];
+      expected.sort();
+      expectArray(monomersArray, expected);
+    });
+  });
 });

package/src/utils.ts

@@ -1,12 +1,11 @@
 import * as DG from 'datagrok-api/dg';
-import { RGROUP_CAP_GROUP_NAME, RGROUP_CAP_GROUP_SMILES, jsonSdfMonomerLibDict, MONOMER_SYMBOL, RGROUP_ALTER_ID, RGROUPS, RGROUP_LABEL, SDF_MONOMER_NAME } from "./constants";
 
 export function getParts(subParts: string[], s: string): string[] {
-  let j = 0;
-  let allParts: string[] = [];
+  const j = 0;
+  const allParts: string[] = [];
   for (let k = 0; k < subParts.length; ++k) {
-    let indexOfMonomer = s.indexOf(subParts[k]);
-    let helmBeforeMonomer = s.slice(j, indexOfMonomer);
+    const indexOfMonomer = s.indexOf(subParts[k]);
+    const helmBeforeMonomer = s.slice(j, indexOfMonomer);
     allParts.push(helmBeforeMonomer);
     allParts.push(subParts[k]);
     s = s.substring(indexOfMonomer + subParts[k].length);
@@ -16,32 +15,44 @@ export function getParts(subParts: string[], s: string): string[] {
 }
 
 export function parseHelm(s: string) {
-  var sections = split(s, '$');
+  const sections = split(s, '$');
   s = sections[0];
-  var monomers = [];
+  const monomers = [];
   //@ts-ignore
   if (!scil.Utils.isNullOrEmpty(s)) {
-    var seqs = split(s, '|');
-    for (var i = 0; i < seqs.length; ++i) {
-      var e = detachAnnotation(seqs[i]);
+    const seqs = split(s, '|');
+    for (let i = 0; i < seqs.length; ++i) {
+      const e = detachAnnotation(seqs[i]);
       s = e.str;
 
-      var p = s.indexOf('{');
+      let p = s.indexOf('{');
 
       s = s.substring(p + 1);
       p = s.indexOf('}');
       s = s.substring(0, p);
 
-      var ss = split(s, '.');
-      for (var monomer of ss) {
-        if (monomer.includes('(') && monomer.includes(')')) {
-          var elements = monomer.replace(/[()]/g, '').split('');
-          for (var el of elements) {
-            monomers.push(el);
-          }
-        } else if (monomer.includes('[') && monomer.includes(']')) {
-          var element = monomer.match(/(?<=\[).*?(?=\])/g, '');
-          monomers.push(element[0]);
+      const ss = split(s, '.');
+      for (const monomer of ss) {
+        if (!monomer || monomer === '') continue;
+        if (monomer.startsWith('[') && monomer.includes(']')) {
+          const element = monomer.substring(1, monomer.indexOf(']'));
+          monomers.push(element);
+          const residue = monomer.substring(monomer.indexOf(']') + 1);
+          ss.push(residue);
+        } else if (monomer.includes('[') && monomer.endsWith(']')) {
+          const element = monomer.substring(monomer.lastIndexOf('[') + 1, monomer.length - 1);
+          monomers.push(element);
+          const residue = monomer.substring(0, monomer.lastIndexOf('['));
+          ss.push(residue);
+        } else if (monomer.includes('(') && monomer.includes(')')) {
+          // here we only want to split the string at first '(' and last ')'
+          // because entries like [L-hArg(Et,Et)]([L-hArg(Et,Et)]) where L-hArg(Et,Et) is a single monomer
+          const firstPiece = monomer.substring(0, monomer.indexOf('('));
+          const thirdPiece = monomer.substring(monomer.lastIndexOf(')') + 1);
+          const secondPiece = monomer.substring(firstPiece.length + 1, monomer.length - thirdPiece.length - 1);
+          const elements =[firstPiece, secondPiece, thirdPiece];
+          for (const el of elements)
+            ss.push(el);
         } else {
           monomers.push(monomer);
         }
@@ -50,32 +61,33 @@ export function parseHelm(s: string) {
   }
   return monomers;
 }
-
+/* this function returns names of monomers that are NOT in the monomer library */
 export function findMonomers(helmString: string) {
   //@ts-ignore
   const types = Object.keys(org.helm.webeditor.monomerTypeList());
   const monomers: any = [];
-  const monomer_names: any = [];
-  for (var i = 0; i < types.length; i++) {
+  const monomerNames: any = [];
+  for (let i = 0; i < types.length; i++) {
     //@ts-ignore
+    // eslint-disable-next-line new-cap
     monomers.push(new scil.helm.Monomers.getMonomerSet(types[i]));
-    Object.keys(monomers[i]).forEach(k => {
-      monomer_names.push(monomers[i][k].id);
+    Object.keys(monomers[i]).forEach((k) => {
+      monomerNames.push(monomers[i][k].id);
     });
   }
-  const split_string = parseHelm(helmString);
-  return new Set(split_string.filter(val => !monomer_names.includes(val)));
+  const splitString = parseHelm(helmString);
+  return new Set(splitString.filter((val) => !monomerNames.includes(val)));
 }
 
 function split(s: string, sep: string) {
-  var ret = [];
-  var frag = '';
-  var parentheses = 0;
-  var bracket = 0;
-  var braces = 0;
-  var quote = 0;
-  for (var i = 0; i < s.length; ++i) {
-    var c = s.substring(i, i + 1);
+  const ret = [];
+  let frag = '';
+  let parentheses = 0;
+  let bracket = 0;
+  let braces = 0;
+  let quote = 0;
+  for (let i = 0; i < s.length; ++i) {
+    let c = s.substring(i, i + 1);
     if (c == sep && bracket == 0 && parentheses == 0 && braces == 0 && quote == 0) {
       ret.push(frag);
       frag = '';
@@ -84,7 +96,7 @@ function split(s: string, sep: string) {
       if (quote > 0) {
         if (c == '\\' && i + 1 < s.length) {
           ++i;
-          var c2 = s.substring(i, i + 1);
+          const c2 = s.substring(i, i + 1);
           frag += c2;
           c += c2;
         }
@@ -92,18 +104,19 @@ function split(s: string, sep: string) {
       if (c == '\"') {
         if (!(i > 0 && s.substring(i - 1, i) == '\\'))
           quote = quote == 0 ? 1 : 0;
-      } else if (c == '[')
+      } else if (c == '[') {
         ++bracket;
-      else if (c == ']')
+      } else if (c == ']') {
         --bracket;
-      else if (c == '(')
+      } else if (c == '(') {
         ++parentheses;
-      else if (c == ')')
+      } else if (c == ')') {
         --parentheses;
-      else if (c == '{')
+      } else if (c == '{') {
         ++braces;
-      else if (c == '}')
+      } else if (c == '}') {
         --braces;
+      }
     }
   }
   ret.push(frag);
@@ -111,19 +124,19 @@ function split(s: string, sep: string) {
 }
 
 function detachAnnotation(s: string) {
-  var ret = _detachAppendix(s, '\"');
+  const ret = _detachAppendix(s, '\"');
   if (ret.tag != null)
     return ret;
 
-  var r = _detachAppendix(s, '\'');
+  const r = _detachAppendix(s, '\'');
   return {tag: ret.tag, repeat: r.tag, str: r.str};
 }
 
 function _detachAppendix(s: string, c: string) {
-  var tag = null;
+  let tag = null;
   //@ts-ignore
   if (scil.Utils.endswith(s, c)) {
-    var p = s.length - 1;
+    let p = s.length - 1;
     while (p > 0) {
       p = s.lastIndexOf(c, p - 1);
       if (p <= 0 || s.substring(p - 1, p) != '\\')

package/tsconfig.json

@@ -6,7 +6,7 @@
     // "incremental": true,                         /* Enable incremental compilation */
     "target": "es6",                                /* Specify ECMAScript target version: 'ES3' (default), 'ES5', 'ES2015', 'ES2016', 'ES2017', 'ES2018', 'ES2019', 'ES2020', or 'ESNEXT'. */
     "module": "es2020",                             /* Specify module code generation: 'none', 'commonjs', 'amd', 'system', 'umd', 'es2015', 'es2020', or 'ESNext'. */
-    "lib": ["es2020", "dom", "ES2021.String"],      /* Specify library files to be included in the compilation. */
+    "lib": ["ES2022", "dom"],      /* Specify library files to be included in the compilation. */
     "allowJs": true,                                /* Allow javascript files to be compiled. */
     // "checkJs": true,                             /* Report errors in .js files. */
     // "jsx": "preserve",                           /* Specify JSX code generation: 'preserve', 'react-native', 'react', 'react-jsx' or 'react-jsxdev'. */