@datagrok/sequence-translator 0.0.8 → 1.0.0

package/src/package.ts

@@ -6,13 +6,19 @@ import * as OCL from 'openchemlib/full.js';
 import $ from 'cash-dom';
 import {defineAxolabsPattern} from './defineAxolabsPattern';
 import {saveSenseAntiSense} from './structures-works/save-sense-antisense';
-import {sequenceToSmiles} from './structures-works/from-monomers';
-import {convertSequence, undefinedInputSequence} from './structures-works/sequence-codes-tools';
+import {sequenceToSmiles, sequenceToMolV3000} from './structures-works/from-monomers';
+import {convertSequence, undefinedInputSequence, isValidSequence, getFormat} from
+  './structures-works/sequence-codes-tools';
+import {map, COL_NAMES, MODIFICATIONS} from './structures-works/map';
 import {SALTS_CSV} from './salts';
+import {USERS_CSV} from './users';
+import {ICDS} from './ICDs';
+import {SOURCES} from './sources';
+import {IDPS} from './IDPs';
 
 export const _package = new DG.Package();
 
-const defaultInput = 'AGGTCCTCTTGACTTAGGCC';
+const defaultInput = 'fAmCmGmAmCpsmU';
 const sequenceWasCopied = 'Copied';
 const tooltipSequence = 'Copy sequence';
 
@@ -24,35 +30,40 @@ export function sequenceTranslator(): void {
   windows.showToolbox = false;
   windows.showHelp = false;
 
-  function updateTableAndMolecule(sequence: string): void {
+  function updateTableAndMolecule(sequence: string, inputFormat: string, isSet: boolean): void {
     moleculeSvgDiv.innerHTML = '';
     outputTableDiv.innerHTML = '';
     const pi = DG.TaskBarProgressIndicator.create('Rendering table and molecule...');
     let errorsExist = false;
     try {
-      const outputSequenceObj = convertSequence(sequence);
+      sequence = sequence.replace(/\s/g, '');
+      const output = isValidSequence(sequence, null);
+      if (isSet)
+        output.synthesizer = [inputFormat];
+      inputFormatChoiceInput.value = output.synthesizer![0];
+      const outputSequenceObj = convertSequence(sequence, output);
       const tableRows = [];
 
       for (const key of Object.keys(outputSequenceObj).slice(1)) {
-        const indexOfFirstNotValidCharacter = ('indexOfFirstNotValidCharacter' in outputSequenceObj) ?
-          JSON.parse(outputSequenceObj.indexOfFirstNotValidCharacter!).indexOfFirstNotValidCharacter :
+        const indexOfFirstNotValidChar = ('indexOfFirstNotValidChar' in outputSequenceObj) ?
+          JSON.parse(outputSequenceObj.indexOfFirstNotValidChar!).indexOfFirstNotValidChar :
           -1;
-        if ('indexOfFirstNotValidCharacter' in outputSequenceObj) {
-          const indexOfFirstNotValidCharacter = ('indexOfFirstNotValidCharacter' in outputSequenceObj) ?
-            JSON.parse(outputSequenceObj.indexOfFirstNotValidCharacter!).indexOfFirstNotValidCharacter :
+        if ('indexOfFirstNotValidChar' in outputSequenceObj) {
+          const indexOfFirstNotValidChar = ('indexOfFirstNotValidChar' in outputSequenceObj) ?
+            JSON.parse(outputSequenceObj.indexOfFirstNotValidChar!).indexOfFirstNotValidChar :
             -1;
-          if (indexOfFirstNotValidCharacter != -1)
+          if (indexOfFirstNotValidChar != -1)
             errorsExist = true;
         }
 
         tableRows.push({
           'key': key,
-          'value': ('indexOfFirstNotValidCharacter' in outputSequenceObj) ?
+          'value': ('indexOfFirstNotValidChar' in outputSequenceObj) ?
             ui.divH([
-              ui.divText(sequence.slice(0, indexOfFirstNotValidCharacter), {style: {color: 'grey'}}),
+              ui.divText(sequence.slice(0, indexOfFirstNotValidChar), {style: {color: 'grey'}}),
               ui.tooltip.bind(
-                ui.divText(sequence.slice(indexOfFirstNotValidCharacter), {style: {color: 'red'}}),
-                'Expected format: ' + JSON.parse(outputSequenceObj.indexOfFirstNotValidCharacter!).expectedSynthesizer +
+                ui.divText(sequence.slice(indexOfFirstNotValidChar), {style: {color: 'red'}}),
+                'Expected format: ' + JSON.parse(outputSequenceObj.indexOfFirstNotValidChar!).synthesizer +
                 '. See tables with valid codes on the right',
               ),
             ]) : //@ts-ignore
@@ -62,48 +73,44 @@ export function sequenceTranslator(): void {
       }
 
       if (errorsExist) {
-        const expectedSynthesizer = JSON.parse(outputSequenceObj.indexOfFirstNotValidCharacter!)
-          .expectedSynthesizer.slice(0, -6);
+        const synthesizer = JSON.parse(outputSequenceObj.indexOfFirstNotValidChar!).synthesizer.slice(0, -6);
         asoGapmersGrid.onCellPrepare(function(gc) {
-          gc.style.backColor = (gc.gridColumn.name == expectedSynthesizer) ? 0xFFF00000 : 0xFFFFFFFF;
+          gc.style.backColor = (gc.gridColumn.name == synthesizer) ? 0xFFF00000 : 0xFFFFFFFF;
         });
         omeAndFluoroGrid.onCellPrepare(function(gc) {
-          gc.style.backColor = (gc.gridColumn.name == expectedSynthesizer) ? 0xFFF00000 : 0xFFFFFFFF;
+          gc.style.backColor = (gc.gridColumn.name == synthesizer) ? 0xFFF00000 : 0xFFFFFFFF;
         });
         switchInput.enabled = true;
       } else {
-        asoGapmersGrid.onCellPrepare(function(gc) {
-          gc.style.backColor = 0xFFFFFFFF;
-        });
-        omeAndFluoroGrid.onCellPrepare(function(gc) {
-          gc.style.backColor = 0xFFFFFFFF;
-        });
+        asoGapmersGrid.onCellPrepare(function(gc) {gc.style.backColor = 0xFFFFFFFF;});
+        omeAndFluoroGrid.onCellPrepare(function(gc) {gc.style.backColor = 0xFFFFFFFF;});
       }
 
       outputTableDiv.append(
         ui.div([
           DG.HtmlTable.create(tableRows, (item: { key: string; value: string; }) =>
             [item.key, item.value], ['Code', 'Sequence']).root,
-        ], 'table'),
+        ]),
       );
-      semTypeOfInputSequence.textContent = 'Detected input type: ' + outputSequenceObj.type;
 
       if (outputSequenceObj.type != undefinedInputSequence && outputSequenceObj.Error != undefinedInputSequence) {
         const canvas = ui.canvas(300, 170);
         canvas.addEventListener('click', () => {
           const canv = ui.canvas($(window).width(), $(window).height());
-          const smiles = sequenceToSmiles(inputSequenceField.value.replace(/\s/g, ''));
+          const mol = sequenceToMolV3000(inputSequenceField.value.replace(/\s/g, ''), false, true,
+          output.synthesizer![0]);
           // @ts-ignore
-          OCL.StructureView.drawMolecule(canv, OCL.Molecule.fromSmiles(smiles), {suppressChiralText: true});
+          OCL.StructureView.drawMolecule(canv, OCL.Molecule.fromMolfile(mol), {suppressChiralText: true});
           ui.dialog('Molecule: ' + inputSequenceField.value)
             .add(canv)
             .showModal(true);
         });
         $(canvas).on('mouseover', () => $(canvas).css('cursor', 'zoom-in'));
         $(canvas).on('mouseout', () => $(canvas).css('cursor', 'default'));
-        const smiles = sequenceToSmiles(inputSequenceField.value.replace(/\s/g, ''));
+        const mol = sequenceToMolV3000(inputSequenceField.value.replace(/\s/g, ''), false, true,
+        output.synthesizer![0]);
         // @ts-ignore
-        OCL.StructureView.drawMolecule(canvas, OCL.Molecule.fromSmiles(smiles), {suppressChiralText: true});
+        OCL.StructureView.drawMolecule(canvas, OCL.Molecule.fromMolfile(mol), {suppressChiralText: true});
         moleculeSvgDiv.append(canvas);
       } else
         moleculeSvgDiv.innerHTML = '';
@@ -112,10 +119,14 @@ export function sequenceTranslator(): void {
     }
   }
 
-  const semTypeOfInputSequence = ui.divText('');
+  const inputFormatChoiceInput = ui.choiceInput(
+    'Input format: ', 'Janssen GCRS Codes', Object.keys(map), (format: string) => {
+      updateTableAndMolecule(inputSequenceField.value.replace(/\s/g, ''), format, true);
+    });
   const moleculeSvgDiv = ui.block([]);
-  const outputTableDiv = ui.div([], 'table');
-  const inputSequenceField = ui.textInput('', defaultInput, (sequence: string) => updateTableAndMolecule(sequence));
+  const outputTableDiv = ui.div([]);
+  const inputSequenceField = ui.textInput('', defaultInput, (sequence: string) => updateTableAndMolecule(sequence,
+    inputFormatChoiceInput.value!, false));
 
   const asoDf = DG.DataFrame.fromObjects([
     {'Name': '2\'MOE-5Me-rU', 'BioSpring': '5', 'Janssen GCRS': 'moeT'},
@@ -154,12 +165,11 @@ export function sequenceTranslator(): void {
   );
 
   const overhangModificationsGrid = DG.Viewer.grid(
-    DG.DataFrame.fromObjects([
-      {'Name': '(invabasic)'},
-      {'Name': '(GalNAc-2-JNJ)'},
+    DG.DataFrame.fromColumns([
+      DG.Column.fromStrings('Name', Object.keys(MODIFICATIONS)),
     ])!, {showRowHeader: false, showCellTooltip: false},
   );
-  updateTableAndMolecule(defaultInput);
+  updateTableAndMolecule(defaultInput, inputFormatChoiceInput.value!, true);
 
   const appMainDescription = ui.info([
     ui.divText('How to convert one sequence:', {style: {'font-weight': 'bolder'}}),
@@ -190,8 +200,8 @@ export function sequenceTranslator(): void {
               ui.div([
                 inputSequenceField.root,
               ], 'input-base'),
-            ], 'sequenceInput'),
-            semTypeOfInputSequence,
+            ], 'inputSequence'),
+            ui.div([inputFormatChoiceInput], {style: {padding: '5px 0'}}),
             ui.block([
               ui.h1('Output'),
               outputTableDiv,
@@ -216,15 +226,16 @@ export function sequenceTranslator(): void {
 
   const topPanel = [
     ui.iconFA('download', () => {
-      const smiles = sequenceToSmiles(inputSequenceField.value.replace(/\s/g, ''));
-      const result = `${OCL.Molecule.fromSmiles(smiles).toMolfile()}\n`;
+      const result = sequenceToMolV3000(inputSequenceField.value.replace(/\s/g, ''), false, false,
+        inputFormatChoiceInput.value!);
       const element = document.createElement('a');
       element.setAttribute('href', 'data:text/plain;charset=utf-8,' + encodeURIComponent(result));
       element.setAttribute('download', inputSequenceField.value.replace(/\s/g, '') + '.mol');
       element.click();
     }, 'Save .mol file'),
     ui.iconFA('copy', () => {
-      navigator.clipboard.writeText(sequenceToSmiles(inputSequenceField.value.replace(/\s/g, '')))
+      navigator.clipboard.writeText(
+        sequenceToSmiles(inputSequenceField.value.replace(/\s/g, ''), false, inputFormatChoiceInput.value!))
         .then(() => grok.shell.info(sequenceWasCopied));
     }, 'Copy SMILES'),
     switchInput.root,
@@ -233,38 +244,29 @@ export function sequenceTranslator(): void {
   tabControl.onTabChanged.subscribe((_) =>
     v.setRibbonPanels([(tabControl.currentPane.name == 'MAIN') ? topPanel : []]));
   v.setRibbonPanels([topPanel]);
-
-  $('.sequence')
-    .children().css('padding', '5px 0');
-  $('.sequenceInput .input-base')
-    .css('margin', '0');
-  $('.sequenceInput textarea')
-    .css('resize', 'none')
-    .css('min-height', '50px')
-    .css('width', '100%')
-    .attr('spellcheck', 'false');
-  $('.sequenceInput select')
-    .css('width', '100%');
 }
 
 async function saveTableAsSdFile(table: DG.DataFrame) {
   if (!table.columns.contains('Compound Name')) {
     grok.shell.warning(
-      'File saved without columns \'Compound Name\', \'Compound Components\', \'Cpd MW\', \'Salt mass\', \'Batch MW\'');
+      'File saved without columns \'' +
+      [COL_NAMES.COMPOUND_NAME, COL_NAMES.COMPOUND_COMMENTS, COL_NAMES.CPD_MW,
+        COL_NAMES.SALT_MASS, COL_NAMES.BATCH_MW].join('\', \''),
+    );
   }
-  const structureColumn = table.columns.byName('Sequence');
+  const structureColumn = table.col(COL_NAMES.SEQUENCE)!;
+  const typeColumn = table.col(COL_NAMES.TYPE)!;
   let result = '';
   for (let i = 0; i < table.rowCount; i++) {
-    try {
-      const smiles = sequenceToSmiles(structureColumn.get(i));
-      const mol = OCL.Molecule.fromSmiles(smiles);
-      result += `\n${mol.toMolfile()}\n`;
-      for (const col of table.columns)
+    const format = getFormat(structureColumn.get(i));
+    result += (typeColumn.get(i) == 'SS') ?
+      sequenceToMolV3000(structureColumn.get(i), false, true, format!) + '\n' + `>  <Sequence>\nSense Strand\n\n` :
+      sequenceToMolV3000(structureColumn.get(i), true, true, format!) + '\n' + `>  <Sequence>\nAnti Sense\n\n`;
+    for (const col of table.columns) {
+      if (col.name != COL_NAMES.SEQUENCE)
         result += `>  <${col.name}>\n${col.get(i)}\n\n`;
-      result += '$$$$';
-    } catch (error) {
-      console.error(error);
     }
+    result += '$$$$\n\n';
   }
   const element = document.createElement('a');
   element.setAttribute('href', 'data:text/plain;charset=utf-8,' + encodeURIComponent(result));
@@ -272,83 +274,115 @@ async function saveTableAsSdFile(table: DG.DataFrame) {
   element.click();
 }
 
+const weightsObj: {[code: string]: number} = {};
+for (const synthesizer of Object.keys(map)) {
+  for (const technology of Object.keys(map[synthesizer])) {
+    for (const code of Object.keys(map[synthesizer][technology]))
+      weightsObj[code] = map[synthesizer][technology][code].weight;
+  }
+}
+for (const [key, value] of Object.entries(MODIFICATIONS))
+  weightsObj[key] = value.molecularWeight;
+
+function sortByStringLengthInDescendingOrder(array: string[]): string[] {
+  return array.sort(function(a, b) {return b.length - a.length;});
+}
+
+function stringifyItems(items: string[]): string {
+  return '["' + items.join('", "') + '"]';
+}
+
+function molecularWeight(sequence: string, weightsObj: {[index: string]: number}): number {
+  const codes = sortByStringLengthInDescendingOrder(Object.keys(weightsObj)).concat(Object.keys(MODIFICATIONS));
+  let weight = 0;
+  let i = 0;
+  while (i < sequence.length) {
+    const matchedCode = codes.find((s) => s == sequence.slice(i, i + s.length))!;
+    weight += weightsObj[sequence.slice(i, i + matchedCode.length)];
+    i += matchedCode!.length;
+  }
+  return weight - 61.97;
+}
+
 //tags: autostart
 export function autostartOligoSdFileSubscription() {
   grok.events.onViewAdded.subscribe((v: any) => {
-    if (v.type == 'TableView' && v.dataFrame.columns.contains('Type'))
+    if (v.type == 'TableView' && v.dataFrame.columns.contains(COL_NAMES.TYPE))
       oligoSdFile(v.dataFrame);
   });
 }
 
 export function oligoSdFile(table: DG.DataFrame) {
   const saltsDf = DG.DataFrame.fromCsv(SALTS_CSV);
+  const usersDf = DG.DataFrame.fromCsv(USERS_CSV);
+  const sourcesDf = DG.DataFrame.fromCsv(SOURCES);
+  const icdsDf = DG.DataFrame.fromCsv(ICDS);
+  const idpsDf = DG.DataFrame.fromCsv(IDPS);
+
   function addColumns(t: DG.DataFrame, saltsDf: DG.DataFrame) {
-    if (t.columns.contains('Compound Name'))
+    if (t.columns.contains(COL_NAMES.COMPOUND_NAME))
       return grok.shell.error('Columns already exist!');
 
-    table.col('Source')?.init('Johnson and Johnson Pharma');
-    table.col('ICD')?.init('No Contract');
-
-    const sequence = t.col('Sequence')!;
-    const salt = t.col('Salt')!;
-    const equivalents = t.col('Equivalents')!;
+    const sequence = t.col(COL_NAMES.SEQUENCE)!;
+    const salt = t.col(COL_NAMES.SALT)!;
+    const equivalents = t.col(COL_NAMES.EQUIVALENTS)!;
 
-    t.columns.addNewString('Compound Name').init((i: number) => sequence.get(i));
-    t.columns.addNewString('Compound Comments').init((i: number) => (i > 0 && i % 2 == 0) ?
+    t.columns.addNewString(COL_NAMES.COMPOUND_NAME).init((i: number) => sequence.get(i));
+    t.columns.addNewString(COL_NAMES.COMPOUND_COMMENTS).init((i: number) => (i > 0 && i % 2 == 0) ?
       sequence.getString(i) + '; duplex of SS: ' + sequence.getString(i - 2) + ' and AS: ' + sequence.getString(i - 1) :
       sequence.getString(i),
     );
-    const chargeCol = saltsDf.col('CHARGE')!.toList();
-    const saltNames = saltsDf.col('DISPLAY')!.toList();
-    const molWeight = saltsDf.col('MOLWEIGHT')!.toList();
-    t.columns.addNewFloat('Cpd MW').init((i: number) => ((i + 1) % 3 == 0) ? DG.FLOAT_NULL : molWeight[i]);
-    t.columns.addNewFloat('Salt mass').init((i: number) => {
-      const v = chargeCol[saltNames.indexOf(salt.get(i))];
-      const n = (v == null) ? 0 : chargeCol[saltNames.indexOf(salt.get(i))];
-      return n * equivalents.get(i);
+    const molWeightCol = saltsDf.col('MOLWEIGHT')!;
+    const saltNamesList = saltsDf.col('DISPLAY')!.toList();
+    t.columns.addNewFloat(COL_NAMES.CPD_MW)
+      .init((i: number) => molecularWeight(sequence.get(i), weightsObj));
+    t.columns.addNewFloat(COL_NAMES.SALT_MASS).init((i: number) => {
+      const saltRowIndex = saltNamesList.indexOf(salt.get(i));
+      const mw = molWeightCol.get(saltRowIndex);
+      return mw * equivalents.get(i);
     });
-    t.columns.addNewCalculated('Batch MW', '${Cpd MW} + ${Salt mass}', DG.COLUMN_TYPE.FLOAT, false);
+    t.columns.addNewCalculated(COL_NAMES.BATCH_MW,
+      '${' + COL_NAMES.CPD_MW + '} + ${' + COL_NAMES.SALT_MASS + '}', DG.COLUMN_TYPE.FLOAT, false,
+    );
 
     addColumnsPressed = true;
     return newDf = t;
   }
 
-  const columnsOrder = ['Chemistry', 'Number', 'Type', 'Chemistry Name', 'Internal compound ID',
-    'IDP', 'Sequence', 'Compound Name', 'Compound Comments', 'Salt', 'Equivalents', 'Purity', 'Cpd MW', 'Salt mass',
-    'Batch MW', 'Source', 'ICD', 'Owner'];
   let newDf: DG.DataFrame;
   let addColumnsPressed = false;
 
   const d = ui.div([
     ui.icons.edit(() => {
       d.innerHTML = '';
+      if (table.col(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);
-          grok.shell.tableView(table.name).grid.columns.setOrder(columnsOrder);
-        }, 'Add columns: Compound Name, Compound Components, Cpd MW, Salt mass, Batch MW', ''),
+        ui.link('Add Columns', () => {
+          addColumns(table, saltsDf);
+          grok.shell.tableView(table.name).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('\', \''), ''),
         ui.button('Save SD file', () => saveTableAsSdFile(addColumnsPressed ? newDf : table)),
       );
-      const view = grok.shell.getTableView(table.name);
-      const typeCol = view.grid.col('Type')!;
-      const saltCol = view.grid.col('Salt')!;
-      saltCol.cellType = 'html';
-      typeCol.cellType = 'html';
-      view.grid.onCellPrepare(function(gc: DG.GridCell) {
-        if (gc.isTableCell) {
-          if (gc.gridColumn.name == 'Type')
-            gc.style.element = ui.choiceInput('', gc.cell.value, ['AS', 'SS', 'Duplex']).root;
-          else if (gc.gridColumn.name == 'Salt') {
-            gc.style.element = ui.choiceInput('', gc.cell.value, saltsDf.columns.byIndex(1).toList(), () => {
-              view.dataFrame.col('Salt')!.set(gc.gridRow, '');
-            }).root;
-          }
-        }
-      });
 
-      table.onDataChanged.subscribe((_) => {
-        if (table.currentCol.name == 'IDP' && typeof table.currentCell.value != 'number')
-          grok.shell.error('Value should be numeric');
+      const view = grok.shell.getTableView(table.name)!;
+
+      view.table!.col(COL_NAMES.TYPE)!.setTag(DG.TAGS.CHOICES, '["AS", "SS", "Duplex"]');
+      view.table!.col(COL_NAMES.OWNER)!.setTag(DG.TAGS.CHOICES, stringifyItems(usersDf.columns.byIndex(0).toList()));
+      view.table!.col(COL_NAMES.SALT)!.setTag(DG.TAGS.CHOICES, stringifyItems(saltsDf.columns.byIndex(0).toList()));
+      view.table!.col(COL_NAMES.SOURCE)!.setTag(DG.TAGS.CHOICES, stringifyItems(sourcesDf.columns.byIndex(0).toList()));
+      view.table!.col(COL_NAMES.ICD)!.setTag(DG.TAGS.CHOICES, stringifyItems(icdsDf.columns.byIndex(0).toList()));
+      view.table!.col(COL_NAMES.IDP)!.setTag(DG.TAGS.CHOICES, stringifyItems(idpsDf.columns.byIndex(0).toList()));
+
+      grok.events.onContextMenu.subscribe((args) => {
+        if ([COL_NAMES.TYPE, COL_NAMES.OWNER, COL_NAMES.SALT, COL_NAMES.SOURCE, COL_NAMES.ICD, COL_NAMES.IDP]
+          .includes(args.args.context.table.currentCol.name)) {
+          args.args.menu.item('Fill Column With Value', () => {
+            const v = args.args.context.table.currentCell.value;
+            args.args.context.table.currentCell.column.init(v);
+          });
+        }
       });
     }),
   ]);

package/src/salts.ts

@@ -1,2 +1,2 @@
-export const SALTS_CSV = `CHARGE,DISPLAY,MOLWEIGHT
-  ,no Data Added,100`;
+export const SALTS_CSV = `DISPLAY,MOLWEIGHT
+no Data Added,100`;

package/src/sources.ts

@@ -0,0 +1,3 @@
+export const SOURCES = `DISPLAY
+NO DATA
+`;

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

@@ -1,11 +1,13 @@
 import {map, stadardPhosphateLinkSmiles, SYNTHESIZERS, TECHNOLOGIES, MODIFICATIONS} from './map';
 import {isValidSequence} from './sequence-codes-tools';
+import {getNucleotidesMol} from './mol-transformations';
 
-export function sequenceToSmiles(sequence: string, inverted: boolean = false): string {
-  const obj = getObjectWithCodesAndSmiles(sequence);
+export function sequenceToMolV3000(sequence: string, inverted: boolean = false, oclRender: boolean = false,
+  format: string): string {
+  const obj = getObjectWithCodesAndSmiles(sequence, format);
   let codes = sortByStringLengthInDescendingOrder(Object.keys(obj));
   let i = 0;
-  let smiles = '';
+  const smilesCodes:string[] = [];
   const codesList = [];
   const links = ['s', 'ps', '*'];
   const includesStandardLinkAlready = ['e', 'h', /*'g',*/ 'f', 'i', 'l', 'k', 'j'];
@@ -18,15 +20,45 @@ export function sequenceToSmiles(sequence: string, inverted: boolean = false): s
   }
   for (let i = 0; i < codesList.length; i++) {
     if (dropdowns.includes(codesList[i])) {
-      if (i == codesList.length -1 || (i < codesList.length - 1 && links.includes(codesList[i + 1]))) {
-        smiles += (i >= codesList.length / 2) ?
-          MODIFICATIONS[codesList[i]].right:
-          MODIFICATIONS[codesList[i]].left;
-      } else if (i < codesList.length - 1) {
-        smiles += (i >= codesList.length / 2) ?
-          MODIFICATIONS[codesList[i]].right + stadardPhosphateLinkSmiles:
-          MODIFICATIONS[codesList[i]].left + stadardPhosphateLinkSmiles;
+      smilesCodes.push((i >= codesList.length / 2) ?
+        MODIFICATIONS[codesList[i]].right : MODIFICATIONS[codesList[i]].left);
+      smilesCodes.push(stadardPhosphateLinkSmiles);
+    } else {
+      if (links.includes(codesList[i]) ||
+        includesStandardLinkAlready.includes(codesList[i]) ||
+        (i < codesList.length - 1 && links.includes(codesList[i + 1]))
+      )
+        smilesCodes.push(obj[codesList[i]]);
+      else {
+        smilesCodes.push(obj[codesList[i]]);
+        smilesCodes.push(stadardPhosphateLinkSmiles);
       }
+    }
+  }
+
+  return getNucleotidesMol(smilesCodes, oclRender);
+}
+
+export function sequenceToSmiles(sequence: string, inverted: boolean = false, format: string): string {
+  const obj = getObjectWithCodesAndSmiles(sequence, format);
+  let codes = sortByStringLengthInDescendingOrder(Object.keys(obj));
+  let i = 0;
+  let smiles = '';
+  const codesList = [];
+  const links = ['s', 'ps', '*'];
+  const includesStandardLinkAlready = ['e', 'h', /*'g',*/ 'f', 'i', 'l', 'k', 'j'];
+  const dropdowns = Object.keys(MODIFICATIONS);
+  codes = codes.concat(dropdowns);
+  while (i < sequence.length) {
+    const code = codes.find((s: string) => s == sequence.slice(i, i + s.length))!;
+    i += code.length;
+    inverted ? codesList.unshift(code) : codesList.push(code);
+  }
+  for (let i = 0; i < codesList.length; i++) {
+    if (dropdowns.includes(codesList[i])) {
+      smiles += (i >= codesList.length / 2) ?
+        MODIFICATIONS[codesList[i]].right + stadardPhosphateLinkSmiles:
+        MODIFICATIONS[codesList[i]].left + stadardPhosphateLinkSmiles;
     } else {
       if (links.includes(codesList[i]) ||
         includesStandardLinkAlready.includes(codesList[i]) ||
@@ -51,19 +83,26 @@ export function sequenceToSmiles(sequence: string, inverted: boolean = false): s
     smiles.slice(0, smiles.length - stadardPhosphateLinkSmiles.length + 1);
 }
 
-function getObjectWithCodesAndSmiles(sequence: string) {
+function getObjectWithCodesAndSmiles(sequence: string, format: string) {
   const obj: { [code: string]: string } = {};
-  for (const synthesizer of Object.keys(map)) {
-    for (const technology of Object.keys(map[synthesizer])) {
-      for (const code of Object.keys(map[synthesizer][technology]))
-        obj[code] = map[synthesizer][technology][code].SMILES;
+  if (format == null) {
+    for (const synthesizer of Object.keys(map)) {
+      for (const technology of Object.keys(map[synthesizer])) {
+        for (const code of Object.keys(map[synthesizer][technology]))
+          obj[code] = map[synthesizer][technology][code].SMILES;
+      }
+    }
+  } else {
+    for (const technology of Object.keys(map[format])) {
+      for (const code of Object.keys(map[format][technology]))
+        obj[code] = map[format][technology][code].SMILES;
     }
   }
   // TODO: create object based from synthesizer type to avoid key(codes) duplicates
-  const output = isValidSequence(sequence);
-  if (output.expectedSynthesizer == SYNTHESIZERS.MERMADE_12)
+  const output = isValidSequence(sequence, format);
+  if (output.synthesizer!.includes(SYNTHESIZERS.MERMADE_12))
     obj['g'] = map[SYNTHESIZERS.MERMADE_12][TECHNOLOGIES.SI_RNA]['g'].SMILES;
-  else if (output.expectedSynthesizer == SYNTHESIZERS.AXOLABS)
+  else if (output.synthesizer!.includes(SYNTHESIZERS.AXOLABS))
     obj['g'] = map[SYNTHESIZERS.AXOLABS][TECHNOLOGIES.SI_RNA]['g'].SMILES;
   return obj;
 }

package/src/structures-works/map.ts

@@ -11,14 +11,36 @@ export const TECHNOLOGIES = {
   ASO_GAPMERS: 'For ASO Gapmers',
   SI_RNA: 'For 2\'-OMe and 2\'-F modified siRNA',
 };
+export const COL_NAMES = {
+  CHEMISTRY: 'Chemistry',
+  NUMBER: 'Number',
+  TYPE: 'Type',
+  CHEMISTRY_NAME: 'Chemistry Name',
+  INTERNAL_COMPOUND_ID: 'Internal compound ID',
+  IDP: 'IDP',
+  SEQUENCE: 'Sequence',
+  COMPOUND_NAME: 'Compound Name',
+  COMPOUND_COMMENTS: 'Compound Comments',
+  SALT: 'Salt',
+  EQUIVALENTS: 'Equivalents',
+  PURITY: 'Purity',
+  CPD_MW: 'Cpd MW',
+  SALT_MASS: 'Salt mass',
+  BATCH_MW: 'Batch MW',
+  SOURCE: 'Source',
+  ICD: 'ICD',
+  OWNER: 'Owner',
+};
 // interface CODES {
 // }
-export const MODIFICATIONS: {[index: string]: {left: string, right: string}} = {
+export const MODIFICATIONS: {[index: string]: {molecularWeight: number, left: string, right: string}} = {
   '(invabasic)': {
+    molecularWeight: 118.13,
     left: 'O[C@@H]1C[C@@H]O[C@H]1CO',
     right: 'O[C@@H]1C[C@@H]O[C@H]1CO',
   },
   '(GalNAc-2-JNJ)': {
+    molecularWeight: 1273.3,
     left: 'C(COCCC(=O)NCCCNC(=O)CCCCOC2OC(CO)C(O)C(O)C2NC(=O)C)' +
     '(COCCC(=O)NCCCNC(=O)CCCCOC2OC(CO)C(O)C(O)C2NC(=O)C)' +
     '(COCCC(=O)NCCCNC(=O)CCCCOC2OC(CO)C(O)C(O)C2NC(=O)C)NC(=O)CCCC(=O)NCC(O)CO',
@@ -49,7 +71,7 @@ export const map: {[synthesizer: string]:
             'name': 'Guanine',
             'weight': 329.21,
             'normalized': 'dG',
-            'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C)[C@@H]1O',
+            'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C[C@@H]1O',
           },
           'C': {
             'name': 'Cytosine',
@@ -75,7 +97,7 @@ export const map: {[synthesizer: string]:
             'name': 'Guanine',
             'weight': 329.21,
             'normalized': 'dG',
-            'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C)[C@@H]1O',
+            'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C[C@@H]1O',
           },
           'C': {
             'name': 'Cytosine',
@@ -139,7 +161,7 @@ export const map: {[synthesizer: string]:
             'name': 'Guanine',
             'weight': 329.21,
             'normalized': 'dG',
-            'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C)[C@@H]1O',
+            'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C[C@@H]1O',
           },
           'T': {
             'name': 'Tyrosine',
@@ -341,13 +363,13 @@ export const map: {[synthesizer: string]:
             'name': 'Guanine',
             'weight': 329.21,
             'normalized': 'dG',
-            'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C)[C@@H]1O',
+            'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C[C@@H]1O',
           },
           'dG': {
             'name': 'Guanine',
             'weight': 329.21,
             'normalized': 'dG',
-            'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C)[C@@H]1O',
+            'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C[C@@H]1O',
           },
           'T': {
             'name': 'Tyrosine',