@datagrok/sequence-translator 1.0.6 → 1.0.8

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@datagrok/sequence-translator",
   "friendlyName": "Sequence Translator",
-  "version": "1.0.6",
+  "version": "1.0.8",
   "author": {
     "name": "Vadym Kovadlo",
     "email": "vkovadlo@datagrok.ai"
@@ -13,7 +13,7 @@
     "directory": "packages/SequenceTranslator"
   },
   "dependencies": {
-    "@datagrok-libraries/utils": "^0.1.0",
+    "@datagrok-libraries/utils": "^1.9.2",
     "@types/react": "^18.0.15",
     "datagrok-api": "^1.6.0",
     "datagrok-tools": "^4.1.2",

package/src/__jest__/remote.test.ts

@@ -42,19 +42,20 @@ it('TEST', async () => {
   let r = await page.evaluate((targetPackage):Promise<object> => {
     return new Promise<object>((resolve, reject) => {
       (<any>window).grok.functions.eval(targetPackage + ':test()').then((df: any) => {
-        let cStatus = df.columns.byName('success');
-        let cMessage = df.columns.byName('result');
-        let cCat = df.columns.byName('category');
-        let cName = df.columns.byName('name');
+        const cStatus = df.columns.byName('success');
+        const cMessage = df.columns.byName('result');
+        const cCat = df.columns.byName('category');
+        const cName = df.columns.byName('name');
+        const cTime = df.columns.byName('ms');
         let failed = false;
         let passReport = '';
         let failReport = '';
         for (let i = 0; i < df.rowCount; i++) {
           if (cStatus.get(i)) {
-            passReport += `Test result : Success : ${targetPackage}.${cCat.get(i)}.${cName.get(i)} : ${cMessage.get(i)}\n`;
+            passReport += `Test result : Success : ${cTime.get(i)} : ${targetPackage}.${cCat.get(i)}.${cName.get(i)} : ${cMessage.get(i)}\n`;
           } else {
             failed = true;
-            failReport += `Test result : Failed : ${targetPackage}.${cCat.get(i)}.${cName.get(i)} : ${cMessage.get(i)}\n`;
+            failReport += `Test result : Failed : ${cTime.get(i)} : ${targetPackage}.${cCat.get(i)}.${cName.get(i)} : ${cMessage.get(i)}\n`;
           }
         }
         resolve({failReport, passReport, failed});

package/src/__jest__/test-node.ts

@@ -75,7 +75,7 @@ export async function getBrowserPage(puppeteer: any): Promise<{browser: any, pag
   }, token);
   await page.goto(url);
   try {
-    await page.waitForSelector('.grok-preloader', { timeout: 1800000 });
+//    await page.waitForSelector('.grok-preloader', { timeout: 1800000 });
     await page.waitForFunction(() => document.querySelector('.grok-preloader') == null, {timeout: 3600000});
   } catch (error) {
     throw error;

package/src/autostart/registration.ts

@@ -4,7 +4,7 @@ import * as DG from 'datagrok-api/dg';
 import {siRnaAxolabsToGcrs, gcrsToNucleotides, asoGapmersBioSpringToGcrs, gcrsToMermade12,
 } from '../structures-works/converters';
 import {map, COL_NAMES, MODIFICATIONS} from '../structures-works/map';
-import {getFormat, isValidSequence} from '../structures-works/sequence-codes-tools';
+import {isValidSequence} from '../structures-works/sequence-codes-tools';
 import {sequenceToMolV3000} from '../structures-works/from-monomers';
 
 import {SALTS_CSV} from '../salts';
@@ -22,6 +22,26 @@ function stringify(items: string[]): string {
   return '["' + items.join('", "') + '"]';
 }
 
+function saltMass(saltNames: string[], molWeightCol: DG.Column, equivalentsCol: DG.Column, i: number,
+  saltCol: DG.Column) {
+  const saltRowIndex = saltNames.indexOf(saltCol.get(i));
+  return (
+    saltRowIndex == -1 || molWeightCol.get(saltRowIndex) == DG.FLOAT_NULL || equivalentsCol.get(i) == DG.INT_NULL) ?
+    DG.FLOAT_NULL :
+    molWeightCol.get(saltRowIndex) * equivalentsCol.get(i);
+}
+
+function saltMolWeigth(saltNamesList: string[], saltCol: DG.Column, molWeightCol: DG.Column, i: number) {
+  const saltRowIndex = saltNamesList.indexOf(saltCol.get(i));
+  return (saltRowIndex == -1) ? DG.FLOAT_NULL : molWeightCol.get(saltRowIndex);
+}
+
+function batchMolWeight(compoundMolWeightCol: DG.Column, saltMassCol: DG.Column, i: number) {
+  return (compoundMolWeightCol.getString(i) == '' || saltMassCol.getString(i) == '') ?
+    DG.FLOAT_NULL :
+    compoundMolWeightCol.get(i) + saltMassCol.get(i);
+}
+
 function molecularWeight(sequence: string, weightsObj: {[index: string]: number}): number {
   const codes = sortByStringLengthInDescendingOrder(Object.keys(weightsObj)).concat(Object.keys(MODIFICATIONS));
   let weight = 0;
@@ -48,13 +68,13 @@ async function saveTableAsSdFile(table: DG.DataFrame) {
   for (let i = 0; i < table.rowCount; i++) {
     const format = 'Janssen GCRS Codes'; //getFormat(structureColumn.get(i))!;
     result += (typeColumn.get(i) == 'SS') ?
-      sequenceToMolV3000(structureColumn.get(i), false, true, format) + '\n' + `>  <Sequence>\nSense Strand\n\n` :
-      sequenceToMolV3000(structureColumn.get(i), true, true, format) + '\n' + `>  <Sequence>\nAnti Sense\n\n`;
+      sequenceToMolV3000(structureColumn.get(i), false, true, format) + '\n' + `> <Sequence>\nSense Strand\n\n` :
+      sequenceToMolV3000(structureColumn.get(i), true, true, format) + '\n' + `> <Sequence>\nAnti Sense\n\n`;
     for (const col of table.columns) {
       if (col.name != COL_NAMES.SEQUENCE)
-        result += `>  <${col.name}>\n${col.get(i)}\n\n`;
+        result += `> <${col.name}>\n${col.get(i)}\n\n`;
     }
-    result += '$$$$\n\n';
+    result += '$$$$\n';
   }
   const element = document.createElement('a');
   element.setAttribute('href', 'data:text/plain;charset=utf-8,' + encodeURIComponent(result));
@@ -117,22 +137,30 @@ export function oligoSdFile(table: DG.DataFrame) {
   const icdsDf = DG.DataFrame.fromCsv(ICDS);
   const idpsDf = DG.DataFrame.fromCsv(IDPS);
 
-  async function addColumns(t: DG.DataFrame, saltsDf: DG.DataFrame) {
+  const sequenceCol = table.getCol(COL_NAMES.SEQUENCE);
+  const saltCol = table.getCol(COL_NAMES.SALT);
+  const equivalentsCol = table.getCol(COL_NAMES.EQUIVALENTS);
+  const typeColumn = table.getCol(COL_NAMES.TYPE);
+
+  const molWeightCol = saltsDf.getCol('MOLWEIGHT');
+  const saltNamesList = saltsDf.getCol('DISPLAY').toList();
+
+  function addColumns(t: DG.DataFrame) {
     if (t.columns.contains(COL_NAMES.COMPOUND_NAME))
       return grok.shell.error('Columns already exist');
 
-    const sequenceCol = t.getCol(COL_NAMES.SEQUENCE);
-    const saltCol = t.getCol(COL_NAMES.SALT);
-    const equivalentsCol = t.getCol(COL_NAMES.EQUIVALENTS);
+    for (let i = t.rowCount - 1; i > -1; i--) {
+      if (sequenceCol.get(i) == '')
+        t.rows.removeAt(i, 1, false);
+    }
 
     t.columns.addNewString(COL_NAMES.COMPOUND_NAME).init((i: number) => sequenceCol.get(i));
 
-    t.columns.addNewString(COL_NAMES.COMPOUND_COMMENTS).init((i: number) => (i > 0 && i % 2 == 0) ?
+    t.columns.addNewString(COL_NAMES.COMPOUND_COMMENTS).init((i: number) => (i > 2 && typeColumn.get(i) == 'Duplex') ?
       sequenceCol.get(i) + '; duplex of SS: ' + sequenceCol.get(i - 2) + ' and AS: ' + sequenceCol.get(i - 1) :
       sequenceCol.get(i),
     );
-    const molWeightCol = saltsDf.getCol('MOLWEIGHT');
-    const saltNamesList = saltsDf.getCol('DISPLAY').toList();
+
     const weightsObj: {[code: string]: number} = {};
     for (const synthesizer of Object.keys(map)) {
       for (const technology of Object.keys(map[synthesizer])) {
@@ -149,16 +177,14 @@ export function oligoSdFile(table: DG.DataFrame) {
         DG.FLOAT_NULL;
     });
 
-    t.columns.addNewFloat(COL_NAMES.SALT_MASS).init((i: number) => {
-      const saltRowIndex = saltNamesList.indexOf(saltCol.get(i));
-      return (saltRowIndex == -1) ?
-        DG.FLOAT_NULL :
-        molWeightCol.get(saltRowIndex) * equivalentsCol.get(i);
-    });
+    t.columns.addNewFloat(COL_NAMES.SALT_MASS).init((i: number) =>
+      saltMass(saltNamesList, molWeightCol, equivalentsCol, i, saltCol));
 
-    await t.columns.addNewCalculated(COL_NAMES.BATCH_MW,
-      '${' + COL_NAMES.CPD_MW + '} + ${' + COL_NAMES.SALT_MASS + '}', DG.COLUMN_TYPE.FLOAT, false,
-    );
+    t.columns.addNewFloat(COL_NAMES.SALT_MOL_WEIGHT).init((i: number) =>
+      saltMolWeigth(saltNamesList, saltCol, molWeightCol, i));
+
+    t.columns.addNewFloat(COL_NAMES.BATCH_MW).init((i: number) =>
+      batchMolWeight(t.getCol(COL_NAMES.CPD_MW), t.getCol(COL_NAMES.SALT_MASS), i));
 
     addColumnsPressed = true;
     return newDf = t;
@@ -173,8 +199,8 @@ export function oligoSdFile(table: DG.DataFrame) {
       if (table.getCol(COL_NAMES.IDP).type != DG.COLUMN_TYPE.STRING)
         table.changeColumnType(COL_NAMES.IDP, DG.COLUMN_TYPE.STRING);
       d.append(
-        ui.link('Add Columns', async () => {
-          await addColumns(table, saltsDf);
+        ui.link('Add Columns', () => {
+          addColumns(table);
           view.grid.columns.setOrder(Object.values(COL_NAMES));
         }, 'Add columns: \'' + [COL_NAMES.COMPOUND_NAME, COL_NAMES.COMPOUND_COMMENTS, COL_NAMES.CPD_MW,
           COL_NAMES.SALT_MASS, COL_NAMES.BATCH_MW].join('\', \''), '',
@@ -197,9 +223,26 @@ export function oligoSdFile(table: DG.DataFrame) {
           args.args.menu.item('Fill Column With Value', () => {
             const v = args.args.context.table.currentCell.value;
             args.args.context.table.currentCell.column.init(v);
+            for (let i = 0; i < view.dataFrame.rowCount; i++)
+              updateCalculatedColumns(view.dataFrame, i);
           });
         }
       });
+
+      view.dataFrame.onDataChanged.subscribe(() => {
+        const colName = view.dataFrame.currentCol.name;
+        if ([COL_NAMES.SALT, COL_NAMES.EQUIVALENTS, COL_NAMES.SALT_MOL_WEIGHT].includes(colName))
+          updateCalculatedColumns(view.dataFrame, view.dataFrame.currentRowIdx);
+      });
+
+      function updateCalculatedColumns(t: DG.DataFrame, i: number): void {
+        const smValue = saltMass(saltNamesList, molWeightCol, equivalentsCol, i, saltCol);
+        t.getCol(COL_NAMES.SALT_MASS).set(i, smValue, false);
+        const smwValue = saltMolWeigth(saltNamesList, saltCol, molWeightCol, i);
+        t.getCol(COL_NAMES.SALT_MOL_WEIGHT).set(i, smwValue, false);
+        const bmw = batchMolWeight(t.getCol(COL_NAMES.CPD_MW), t.getCol(COL_NAMES.SALT_MASS), i);
+        t.getCol(COL_NAMES.BATCH_MW).set(i, bmw, false);
+      }
     }),
   ]);
   grok.shell.v.setRibbonPanels([[d]]);

package/src/axolabs/define-pattern.ts

@@ -361,6 +361,11 @@ export function defineAxolabsPattern() {
         })
         .show();
     }
+    if (col.get(0) != ssLength.value) {
+      const d = ui.dialog('Length was updated by value to from imported file');
+      d.add(ui.divText('Latest modifications may not take effect during translation'))
+        .onOK(() => grok.shell.info('Lengths changed')).show();
+    }
     return allLengthsAreTheSame;
   }
 
@@ -513,7 +518,9 @@ export function defineAxolabsPattern() {
   let asPtoLinkages = Array(defaultSequenceLength).fill(ui.boolInput('', defaultPto));
 
   const ssLength = ui.intInput('SS Length', defaultSequenceLength, () => updateUiForNewSequenceLength());
+  ssLength.setTooltip('Length of sense strand, including overhangs');
   const asLength = ui.intInput('AS Length', defaultSequenceLength, () => updateUiForNewSequenceLength());
+  asLength.setTooltip('Length of sense strand, including overhangs');
   const asLengthDiv = ui.div([asLength.root]);
 
   function validateSsColumn(colName: string): void {
@@ -605,7 +612,9 @@ export function defineAxolabsPattern() {
   });
 
   const firstSsPto = ui.boolInput('First SS PTO', fullyPto.value!, () => updateSvgScheme());
+  firstSsPto.setTooltip('ps linkage before first nucleotide of sense strand');
   const firstAsPto = ui.boolInput('First AS PTO', fullyPto.value!, () => updateSvgScheme());
+  firstAsPto.setTooltip('ps linkage before first nucleotide of antisense strand');
   firstAsPtoDiv.append(firstAsPto.root);
 
   const createAsStrand = ui.boolInput('Create AS Strand', true, (v: boolean) => {
@@ -617,6 +626,7 @@ export function defineAxolabsPattern() {
     firstAsPtoDiv.hidden = (!v);
     updateSvgScheme();
   });
+  createAsStrand.setTooltip('Create antisense strand sections on SVG and table to the right');
 
   const saveAs = ui.textInput('Save As', 'Pattern Name', () => updateSvgScheme());
   saveAs.setTooltip('Name Of New Pattern');

package/src/main/main-view.ts

@@ -4,7 +4,6 @@ import * as DG from 'datagrok-api/dg';
 import {convertSequence, undefinedInputSequence, isValidSequence} from '../structures-works/sequence-codes-tools';
 import {map, MODIFICATIONS} from '../structures-works/map';
 import {sequenceToSmiles, sequenceToMolV3000} from '../structures-works/from-monomers';
-
 import $ from 'cash-dom';
 
 const defaultInput = 'fAmCmGmAmCpsmU';
@@ -12,7 +11,7 @@ const sequenceWasCopied = 'Copied';
 const tooltipSequence = 'Copy sequence';
 
 export function mainView() {
-  function updateTableAndMolecule(sequence: string, inputFormat: string, isSet: boolean): void {
+  function updateTableAndMolecule(sequence: string, inputFormat: string): void {
     moleculeSvgDiv.innerHTML = '';
     outputTableDiv.innerHTML = '';
     const pi = DG.TaskBarProgressIndicator.create('Rendering table and molecule...');
@@ -20,9 +19,8 @@ export function mainView() {
     try {
       sequence = sequence.replace(/\s/g, '');
       const output = isValidSequence(sequence, null);
-      if (isSet)
-        output.synthesizer = [inputFormat];
-      inputFormatChoiceInput.value = output.synthesizer![0];
+      output.synthesizer = [inputFormat];
+      // inputFormatChoiceInput.value = output.synthesizer![0];
       const outputSequenceObj = convertSequence(sequence, output);
       const tableRows = [];
 
@@ -101,14 +99,15 @@ export function mainView() {
     }
   }
 
-  const inputFormatChoiceInput = ui.choiceInput(
-    'Input format: ', 'Janssen GCRS Codes', Object.keys(map), (format: string) => {
-      updateTableAndMolecule(inputSequenceField.value.replace(/\s/g, ''), format, true);
-    });
+  const inputFormatChoiceInput = ui.choiceInput('Input format: ', 'Janssen GCRS Codes', Object.keys(map));
+  inputFormatChoiceInput.onInput((format: string) => {
+    updateTableAndMolecule(inputSequenceField.value.replace(/\s/g, ''), format);
+  });
   const moleculeSvgDiv = ui.block([]);
   const outputTableDiv = ui.div([]);
-  const inputSequenceField = ui.textInput('', defaultInput, (sequence: string) => updateTableAndMolecule(sequence,
-      inputFormatChoiceInput.value!, false));
+  const inputSequenceField = ui.textInput('', defaultInput, (sequence: string) => {
+    updateTableAndMolecule(sequence, inputFormatChoiceInput.value!);
+  });
 
   const asoDf = DG.DataFrame.fromObjects([
     {'Name': '2\'MOE-5Me-rU', 'BioSpring': '5', 'Janssen GCRS': 'moeT'},
@@ -151,7 +150,7 @@ export function mainView() {
         DG.Column.fromStrings('Name', Object.keys(MODIFICATIONS)),
       ])!, {showRowHeader: false, showCellTooltip: false},
   );
-  updateTableAndMolecule(defaultInput, inputFormatChoiceInput.value!, true);
+  updateTableAndMolecule(defaultInput, inputFormatChoiceInput.value!);
 
   const codesTablesDiv = ui.splitV([
     ui.box(ui.h2('ASO Gapmers'), {style: {maxHeight: '40px'}}),

package/src/structures-works/converters.ts

@@ -1,6 +1,6 @@
 import {lcmsToGcrs} from './map';
 import * as DG from 'datagrok-api/dg';
-
+import {delimiter} from './map';
 //name: gcrsToLcms
 //input: string nucleotides {semType: GCRS}
 //output: string result {semType: LCMS}
@@ -10,12 +10,21 @@ export function gcrsToLcms(sequence: string): string {
   const arr2 = df.getCol('LCMS').toList();
   const obj: {[i: string]: string} = {};
   arr1.forEach((element, index) => obj[element] = arr2[index]);
-  for (let i = 0; i < arr1.length; i++) {
-    arr1[i] = arr1[i].replace('(', '\\(');
-    arr1[i] = arr1[i].replace(')', '\\)');
+  obj[delimiter] = delimiter;
+  // for (let i = 0; i < arr1.length; i++) {
+  //   arr1[i] = arr1[i].replace('(', '\\(');
+  //   arr1[i] = arr1[i].replace(')', '\\)');
+  // }
+  // const regExp = new RegExp('(' + arr1.join('|') + ')', 'g');
+  // let r1 = sequence.replace(regExp, function(code) {return obj[code];});
+  const codes = arr1.concat(delimiter).sort(function(a, b) {return b.length - a.length;});
+  let i = 0;
+  let r1 = '';
+  while (i < sequence.length) {
+    const matchedCode = codes.find((c) => c == sequence.slice(i, i + c.length));
+    r1 += obj[sequence.slice(i, i + matchedCode.length)];
+    i += matchedCode.length;
   }
-  const regExp = new RegExp('(' + arr1.join('|') + ')', 'g');
-  let r1 = sequence.replace(regExp, function(code) {return obj[code];});
   while (r1.indexOf('//') != -1)
     r1 = r1.replace('//', '/');
   return r1;

package/src/structures-works/from-monomers.ts

@@ -22,7 +22,8 @@ export function sequenceToMolV3000(sequence: string, inverted: boolean = false,
     if (dropdowns.includes(codesList[i])) {
       smilesCodes.push((i >= codesList.length / 2) ?
         MODIFICATIONS[codesList[i]].right : MODIFICATIONS[codesList[i]].left);
-      smilesCodes.push(stadardPhosphateLinkSmiles);
+      if (!(i < codesList.length - 1 && links.includes(codesList[i + 1])))
+        smilesCodes.push(stadardPhosphateLinkSmiles);
     } else {
       if (links.includes(codesList[i]) ||
         includesStandardLinkAlready.includes(codesList[i]) ||

package/src/structures-works/map.ts

@@ -30,6 +30,7 @@ export const COL_NAMES = {
   EQUIVALENTS: 'Equivalents',
   PURITY: 'Purity',
   CPD_MW: 'Cpd MW',
+  SALT_MOL_WEIGHT: 'Salt MW',
   SALT_MASS: 'Salt mass',
   BATCH_MW: 'Batch MW',
   SOURCE: 'Source',

package/src/structures-works/mol-transformations.ts

@@ -56,7 +56,7 @@ M  V30 BEGIN ATOM
 M  V30 1 O 1.0934 -2.1636 0 0
 M  V30 2 C 1.8365 -1.4945 0 0 CFG=2
 M  V30 3 C 2.8147 -1.7024 0 0
-M  V30 4 C 3.3147 -0.8364 0 0 VAL=3
+M  V30 4 C 3.3147 -0.8364 0 0
 M  V30 5 O 2.6455 -0.0932 0 0
 M  V30 6 C 1.732 -0.5 0 0 CFG=1
 M  V30 7 C 0.866 0 0 0
@@ -250,7 +250,7 @@ export function linkV3000(molBlocks: string[], twoChains: boolean = false, useCh
     macroMolBlock = macroMolBlock.replace(/ CFG=\d/g, ' ');
 
   macroMolBlock += 'M  V30 END CTAB\n';
-  macroMolBlock += 'M  END\n';
+  macroMolBlock += 'M  END';
 
   return macroMolBlock;
 }

package/src/structures-works/save-sense-antisense.ts

@@ -10,13 +10,13 @@ export function saveSdf(as: string, ss: string, oneEntity: boolean, useChirality
   const molAS = sequenceToMolV3000(as, invertAS, false, formatAs!);
   let result: string;
   if (oneEntity)
-    result = linkV3000([molSS, molAS], true, useChirality) + '\n\n$$$$\n';
+    result = linkV3000([molSS, molAS], true, useChirality) + '\n$$$$\n';
   else {
     result =
     molSS + '\n' +
-    `>  <Sequence>\nSense Strand\n\n$$$$\n` +
+    `> <Sequence>\nSense Strand\n$$$$\n` +
     molAS + '\n' +
-    `>  <Sequence>\nAnti Sense\n\n$$$$\n`;
+    `> <Sequence>\nAnti Sense\n$$$$\n`;
   }
 
   const element = document.createElement('a');

package/src/structures-works/sequence-codes-tools.ts

@@ -170,8 +170,8 @@ export function isValidSequence(sequence: string, format: string | null): {
   //     })
   //     .show();
   // } else if (possibleTechnologies.length == 0)
-  if (possibleTechnologies.length == 0)
-    return {indexOfFirstNotValidChar: 0, synthesizer: [possibleSynthesizers[3]], technology: null};
+  // if (possibleTechnologies.length == 0)
+  //   return {indexOfFirstNotValidChar: 0, synthesizer: [possibleSynthesizers[3]], technology: null};
 
   outputIndex = 0;