@datagrok/sequence-translator 1.0.12 → 1.0.14

package/src/autostart/registration.ts

@@ -3,90 +3,64 @@ import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
 import {siRnaBioSpringToGcrs, siRnaAxolabsToGcrs, gcrsToNucleotides, asoGapmersBioSpringToGcrs, gcrsToMermade12,
   siRnaNucleotidesToGcrs} from '../structures-works/converters';
-import {map, COL_NAMES, MODIFICATIONS} from '../structures-works/map';
+import {weightsObj, SYNTHESIZERS} from '../structures-works/map';
+import {SEQUENCE_TYPES, COL_NAMES, GENERATED_COL_NAMES, CELL_STRUCTURE} from './constants';
+import {saltMass, saltMolWeigth, molecularWeight, batchMolWeight} from './calculations';
 import {isValidSequence} from '../structures-works/sequence-codes-tools';
 import {sequenceToMolV3000} from '../structures-works/from-monomers';
-import {linkV3000} from '../structures-works/mol-transformations';
+import {linkStrandsV3000} from '../structures-works/mol-transformations';
+import {stringify, download, removeEmptyRows, differenceOfTwoArrays} from '../helpers';
 
-import {SALTS_CSV} from '../salts';
-import {USERS_CSV} from '../users';
-import {ICDS} from '../ICDs';
-import {SOURCES} from '../sources';
-import {IDPS} from '../IDPs';
+import {SALTS_CSV} from './salts';
+import {USERS_CSV} from './users';
+import {ICDS} from './ICDs';
+import {SOURCES} from './sources';
+import {IDPS} from './IDPs';
 
 
-function sortByStringLengthInDescendingOrder(array: string[]): string[] {
-  return array.sort(function(a, b) {return b.length - a.length;});
+function parseStrandsFromDuplexCell(s: string): {SS: string, AS: string} {
+  const arr = s
+    .slice(CELL_STRUCTURE.DUPLEX.BEFORE_SS.length)
+    .split(CELL_STRUCTURE.DUPLEX.BEFORE_AS);
+  return {SS: arr[0], AS: arr[1]};
 }
 
-function stringify(items: string[]): string {
-  return '["' + items.join('", "') + '"]';
+function parseStrandsFromTriplexOrDimerCell(s: string): {SS: string, AS1: string, AS2: string} {
+  const arr1 = s
+    .slice(CELL_STRUCTURE.TRIPLEX_OR_DIMER.BEFORE_SS.length)
+    .split(CELL_STRUCTURE.TRIPLEX_OR_DIMER.BEFORE_AS1);
+  const arr2 = arr1[1]
+    .split(CELL_STRUCTURE.TRIPLEX_OR_DIMER.BEFORE_AS2);
+  return {SS: arr1[0], AS1: arr2[0], AS2: arr2[1]};
 }
 
-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;
-  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;
+async function saveTableAsSdFile(table: DG.DataFrame) {
+  if (GENERATED_COL_NAMES.some((colName) => !table.columns.contains(colName))) {
+    const absentColNames = differenceOfTwoArrays(GENERATED_COL_NAMES, table.columns.names()).join(`', '`);
+    grok.shell.warning(`File saved without columns '${absentColNames}'`);
   }
-  return weight - 61.97;
-}
 
-function parseStrandsFromDuplexCell(s: string): string[] {
-  return s.slice(3).split('\r\nAS ');
-}
+  const sequenceCol = table.getCol(COL_NAMES.SEQUENCE);
+  const typeCol = table.getCol(COL_NAMES.TYPE);
 
-async function saveTableAsSdFile(table: DG.DataFrame) {
-  if (!table.columns.contains('Compound Name')) {
-    grok.shell.warning(
-      '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.getCol(COL_NAMES.SEQUENCE);
-  const typeColumn = table.getCol(COL_NAMES.TYPE);
   let result = '';
   for (let i = 0; i < table.rowCount; i++) {
-    const format = 'Janssen GCRS Codes'; //getFormat(structureColumn.get(i))!;
-    if (typeColumn.get(i) == 'Duplex') {
-      const array = parseStrandsFromDuplexCell(structureColumn.get(i));
-      const as = sequenceToMolV3000(array[1], true, true, format) +
-      '\n' + `> <Sequence>\nAnti Sense\n\n`;
-      const ss = sequenceToMolV3000(array[0], false, true, format) +
-      '\n' + `> <Sequence>\nSense Strand\n\n`;
-      result += linkV3000([ss, as], true, true) + '\n\n';
-    } else if (typeColumn.get(i) == 'SS') {
-      const molSS = sequenceToMolV3000(structureColumn.get(i), false, true, format) +
-      '\n' + `> <Sequence>\nSense Strand\n\n`;
-      result += molSS;
-    } else if (typeColumn.get(i) == 'AS') {
-      const molAS = sequenceToMolV3000(structureColumn.get(i), true, true, format) +
-        '\n' + `> <Sequence>\nAnti Sense\n\n`;
-      result += molAS;
+    const format = SYNTHESIZERS.GCRS; //getFormat(sequenceCol.get(i))!;
+    if (typeCol.get(i) == SEQUENCE_TYPES.SENSE_STRAND)
+      result += `${sequenceToMolV3000(sequenceCol.get(i), false, true, format)}\n> <Sequence>\nSense Strand\n\n`;
+    else if (typeCol.get(i) == SEQUENCE_TYPES.ANTISENSE_STRAND)
+      result += `${sequenceToMolV3000(sequenceCol.get(i), true, true, format)}\n> <Sequence>\nAnti Sense\n\n`;
+    else if (typeCol.get(i) == SEQUENCE_TYPES.DUPLEX) {
+      const obj = parseStrandsFromDuplexCell(sequenceCol.get(i));
+      const as = `${sequenceToMolV3000(obj.AS, true, true, format)}\n> <Sequence>\nAnti Sense\n\n`;
+      const ss = `${sequenceToMolV3000(obj.SS, false, true, format)}\n> <Sequence>\nSense Strand\n\n`;
+      result += `${linkStrandsV3000({senseStrands: [ss], antiStrands: [as]}, true)}\n\n`;
+    } else if ([SEQUENCE_TYPES.TRIPLEX, SEQUENCE_TYPES.DIMER].includes(typeCol.get(i))) {
+      const obj = parseStrandsFromTriplexOrDimerCell(sequenceCol.get(i));
+      const as1 = `${sequenceToMolV3000(obj.AS1, true, true, format)}\n> <Sequence>\nAnti Sense\n\n`;
+      const as2 = `${sequenceToMolV3000(obj.AS2, true, true, format)}\n> <Sequence>\nAnti Sense\n\n`;
+      const ss = `${sequenceToMolV3000(obj.SS, false, true, format)}\n> <Sequence>\nSense Strand\n\n`;
+      result += `${linkStrandsV3000({senseStrands: [ss], antiStrands: [as1, as2]}, true)}\n\n`;
     }
 
     for (const col of table.columns) {
@@ -95,17 +69,16 @@ async function saveTableAsSdFile(table: DG.DataFrame) {
     }
     result += '$$$$\n';
   }
-  const element = document.createElement('a');
-  element.setAttribute('href', 'data:text/plain;charset=utf-8,' + encodeURIComponent(result));
-  element.setAttribute('download', table.name + '.sdf');
-  element.click();
+  download(`${table.name}.sdf`, encodeURIComponent(result));
 }
 
 export function autostartOligoSdFileSubscription() {
   grok.events.onViewAdded.subscribe((v: any) => {
-    if (v.type == 'TableView') {
+    if (v.type == DG.VIEW_TYPE.TABLE_VIEW) {
       if (v.dataFrame.columns.contains(COL_NAMES.TYPE))
         oligoSdFile(v.dataFrame);
+
+      // Should be removed after fixing bug https://github.com/datagrok-ai/public/issues/808
       grok.events.onContextMenu.subscribe((args) => {
         const seqCol = args.args.context.table.currentCol; // /^[fsACGUacgu]{6,}$/
         if (DG.Detector.sampleCategories(seqCol,
@@ -166,56 +139,56 @@ export function oligoSdFile(table: 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 typeCol = table.getCol(COL_NAMES.TYPE);
   const chemistryNameCol = table.getCol(COL_NAMES.CHEMISTRY_NAME);
 
   const molWeightCol = saltsDf.getCol('MOLWEIGHT');
   const saltNamesList = saltsDf.getCol('DISPLAY').toList();
 
+  let newDf: DG.DataFrame;
+  let addColumnsPressed = false;
+
   function addColumns(t: DG.DataFrame) {
-    if (t.columns.contains(COL_NAMES.COMPOUND_NAME))
+    if (GENERATED_COL_NAMES.some((colName) => t.columns.contains(colName)))
       return grok.shell.error('Columns already exist');
 
-    for (let i = t.rowCount - 1; i > -1; i--) {
-      if (sequenceCol.get(i) == '')
-        t.rows.removeAt(i, 1, false);
-    }
+    t = removeEmptyRows(t, sequenceCol);
 
     t.columns.addNewString(COL_NAMES.COMPOUND_NAME).init((i: number) => {
-      return (typeColumn.get(i) == 'Duplex') ? chemistryNameCol.get(i) : sequenceCol.get(i);
+      return ([SEQUENCE_TYPES.DUPLEX, SEQUENCE_TYPES.DIMER, SEQUENCE_TYPES.TRIPLEX].includes(typeCol.get(i))) ?
+        chemistryNameCol.get(i) :
+        sequenceCol.get(i);
     });
 
     t.columns.addNewString(COL_NAMES.COMPOUND_COMMENTS).init((i: number) => {
-      if (typeColumn.get(i) == 'Duplex') {
-        const arr = parseStrandsFromDuplexCell(sequenceCol.get(i));
-        return chemistryNameCol.get(i) + '; duplex of SS: ' + arr[0] + ' and AS: ' + arr[1];
+      if ([SEQUENCE_TYPES.SENSE_STRAND, SEQUENCE_TYPES.ANTISENSE_STRAND].includes(typeCol.get(i)))
+        return sequenceCol.get(i);
+      else if (typeCol.get(i) == SEQUENCE_TYPES.DUPLEX) {
+        const obj = parseStrandsFromDuplexCell(sequenceCol.get(i));
+        return `${chemistryNameCol.get(i)}; duplex of SS: ${obj.SS} and AS: ${obj.AS}`;
+      } else if ([SEQUENCE_TYPES.DIMER, SEQUENCE_TYPES.TRIPLEX].includes(typeCol.get(i))) {
+        const obj = parseStrandsFromTriplexOrDimerCell(sequenceCol.get(i));
+        return `${chemistryNameCol.get(i)}; duplex of SS: ${obj.SS} and AS1: ${obj.AS1} and AS2: ${obj.AS2}`;
       }
-      return sequenceCol.get(i);
     });
 
-    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;
-
-    t.columns.addNewFloat(COL_NAMES.CPD_MW).init((i: number) => {
-      if (typeColumn.get(i) == 'Duplex') {
-        const arr = parseStrandsFromDuplexCell(sequenceCol.get(i));
-        return (
-          isValidSequence(arr[0], null).indexOfFirstNotValidChar == -1 &&
-          isValidSequence(arr[1], null).indexOfFirstNotValidChar == -1
-        ) ?
-          molecularWeight(arr[0], weightsObj) + molecularWeight(arr[1], weightsObj) :
+    t.columns.addNewFloat(COL_NAMES.COMPOUND_MOL_WEIGHT).init((i: number) => {
+      if ([SEQUENCE_TYPES.SENSE_STRAND, SEQUENCE_TYPES.ANTISENSE_STRAND].includes(typeCol.get(i))) {
+        return (isValidSequence(sequenceCol.get(i), null).indexOfFirstNotValidChar == -1) ?
+          molecularWeight(sequenceCol.get(i), weightsObj) :
+          DG.FLOAT_NULL;
+      } else if (typeCol.get(i) == SEQUENCE_TYPES.DUPLEX) {
+        const obj = parseStrandsFromDuplexCell(sequenceCol.get(i));
+        return (Object.values(obj).every((seq) => isValidSequence(seq, null).indexOfFirstNotValidChar == -1)) ?
+          molecularWeight(obj.SS, weightsObj) + molecularWeight(obj.AS, weightsObj) :
+          DG.FLOAT_NULL;
+      } else if ([SEQUENCE_TYPES.DIMER, SEQUENCE_TYPES.TRIPLEX].includes(typeCol.get(i))) {
+        const obj = parseStrandsFromTriplexOrDimerCell(sequenceCol.get(i));
+        return (Object.values(obj).every((seq) => isValidSequence(seq, null).indexOfFirstNotValidChar == -1)) ?
+          molecularWeight(obj.SS, weightsObj) + molecularWeight(obj.AS1, weightsObj) +
+          molecularWeight(obj.AS2, weightsObj) :
           DG.FLOAT_NULL;
       }
-      return (isValidSequence(sequenceCol.get(i), null).indexOfFirstNotValidChar == -1) ?
-        molecularWeight(sequenceCol.get(i), weightsObj) :
-        DG.FLOAT_NULL;
     });
 
     t.columns.addNewFloat(COL_NAMES.SALT_MASS).init((i: number) =>
@@ -224,15 +197,24 @@ export function oligoSdFile(table: DG.DataFrame) {
     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));
+    const compoundMolWeightCol = t.getCol(COL_NAMES.COMPOUND_MOL_WEIGHT);
+    const saltMassCol = t.getCol(COL_NAMES.SALT_MASS);
+    t.columns.addNewFloat(COL_NAMES.BATCH_MOL_WEIGHT).init((i: number) =>
+      batchMolWeight(compoundMolWeightCol, saltMassCol, i));
 
+    grok.shell.getTableView(table.name).grid.columns.setOrder(Object.values(COL_NAMES));
     addColumnsPressed = true;
     return newDf = t;
   }
 
-  let newDf: DG.DataFrame;
-  let addColumnsPressed = false;
+  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.COMPOUND_MOL_WEIGHT), t.getCol(COL_NAMES.SALT_MASS), i);
+    t.getCol(COL_NAMES.BATCH_MOL_WEIGHT).set(i, bmw, false);
+  }
 
   const d = ui.div([
     ui.icons.edit(() => {
@@ -240,18 +222,15 @@ 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', () => {
-          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('\', \''), '',
-        ),
-        ui.button('Save SD file', () => saveTableAsSdFile(addColumnsPressed ? newDf : table)),
+        ui.divH([
+          ui.icons.add(() => addColumns(table), `Add columns: '${GENERATED_COL_NAMES.join(`', '`)}'`),
+          ui.icons.save(() => saveTableAsSdFile(addColumnsPressed ? newDf : table), 'Save SD file'),
+        ]),
       );
 
       const view = grok.shell.getTableView(table.name);
-
-      view.dataFrame.getCol(COL_NAMES.TYPE).setTag(DG.TAGS.CHOICES, '["AS", "SS", "Duplex"]');
+      view.grid.setOptions({rowHeight: 45});
+      view.dataFrame.getCol(COL_NAMES.TYPE).setTag(DG.TAGS.CHOICES, stringify(Object.values(SEQUENCE_TYPES)));
       view.dataFrame.getCol(COL_NAMES.OWNER).setTag(DG.TAGS.CHOICES, stringify(usersDf.columns.byIndex(0).toList()));
       view.dataFrame.getCol(COL_NAMES.SALT).setTag(DG.TAGS.CHOICES, stringify(saltsDf.columns.byIndex(0).toList()));
       view.dataFrame.getCol(COL_NAMES.SOURCE).setTag(DG.TAGS.CHOICES, stringify(sourcesDf.columns.byIndex(0).toList()));
@@ -281,8 +260,8 @@ export function oligoSdFile(table: DG.DataFrame) {
         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);
+        const bmw = batchMolWeight(t.getCol(COL_NAMES.COMPOUND_MOL_WEIGHT), t.getCol(COL_NAMES.SALT_MASS), i);
+        t.getCol(COL_NAMES.BATCH_MOL_WEIGHT).set(i, bmw, false);
       }
     }),
   ]);

package/src/axolabs/constants.ts

@@ -1,12 +1,12 @@
-const rnaColor = 'rgb(255,230,153)';
-const invAbasicColor = 'rgb(203,119,211)';
-export const axolabsMap:
+const RNA_COLOR = 'rgb(255,230,153)';
+const INVABASIC_COLOR = 'rgb(203,119,211)';
+export const AXOLABS_MAP:
   {[index: string]: {fullName: string, symbols: [string, string, string, string], color: string}} =
 {
   'RNA': {
     fullName: 'RNA nucleotides',
     symbols: ['A', 'C', 'G', 'U'],
-    color: rnaColor,
+    color: RNA_COLOR,
   },
   'DNA': {
     fullName: 'DNA nucleotides',
@@ -46,22 +46,22 @@ export const axolabsMap:
   'A': {
     fullName: 'Adenine',
     symbols: ['a', 'a', 'a', 'a'],
-    color: rnaColor,
+    color: RNA_COLOR,
   },
   'C': {
     fullName: 'Cytosine',
     symbols: ['c', 'c', 'c', 'c'],
-    color: rnaColor,
+    color: RNA_COLOR,
   },
   'G': {
     fullName: 'Guanine',
     symbols: ['g', 'g', 'g', 'g'],
-    color: rnaColor,
+    color: RNA_COLOR,
   },
   'U': {
     fullName: 'Uracil',
     symbols: ['u', 'u', 'u', 'u'],
-    color: rnaColor,
+    color: RNA_COLOR,
   },
   'X-New': {
     fullName: '',
@@ -81,7 +81,7 @@ export const axolabsMap:
   'InvAbasic': {
     fullName: 'Inverted abasic capped',
     symbols: ['(invabasic)', '(invabasic)', '(invabasic)', '(invabasic)'],
-    color: invAbasicColor,
+    color: INVABASIC_COLOR,
   },
   "5\"-vinylps": {
     fullName: '5\'-vinylphosphonate-2\'-OMe-uridine',
@@ -91,7 +91,7 @@ export const axolabsMap:
   'InvAbasic(o)': {
     fullName: 'Inverted abasic capped (overhang)',
     symbols: ['(invabasic)', '(invabasic)', '(invabasic)', '(invabasic)'],
-    color: invAbasicColor,
+    color: INVABASIC_COLOR,
   },
   "2\"-OMe-U(o)": {
     fullName: 'Nucleotide Uridine with 2\'O-Methyl protection (overhang)',

package/src/axolabs/define-pattern.ts

@@ -6,9 +6,10 @@ import * as svg from 'save-svg-as-png';
 import $ from 'cash-dom';
 
 import {drawAxolabsPattern} from './draw-svg';
-import {axolabsMap} from './constants';
+import {AXOLABS_MAP} from './constants';
+import {isOverhang} from './helpers';
 
-const baseChoices: string[] = Object.keys(axolabsMap);
+const baseChoices: string[] = Object.keys(AXOLABS_MAP);
 const defaultBase: string = baseChoices[0];
 const defaultPto: boolean = true;
 const defaultSequenceLength: number = 23;
@@ -17,7 +18,7 @@ const userStorageKey: string = 'SequenceTranslator';
 const exampleMinWidth: string = '400px';
 
 function generateExample(sequenceLength: number, sequenceBasis: string): string {
-  const uniqueSymbols = axolabsMap[sequenceBasis].symbols.join('');
+  const uniqueSymbols = AXOLABS_MAP[sequenceBasis].symbols.join('');
   return uniqueSymbols.repeat(Math.floor(sequenceLength / 4)) + uniqueSymbols.slice(0, sequenceLength % 4);
 }
 
@@ -64,12 +65,12 @@ function translateSequence(
   let i: number = -1;
   let mainSequence = sequence.replace(/[AUGC]/g, function(x: string) {
     i++;
-    const indexOfSymbol = axolabsMap['RNA']['symbols'].indexOf(x);
-    let symbol = axolabsMap[bases[i].value]['symbols'][indexOfSymbol];
-    if (bases[i].value.slice(-3) == '(o)') {
-      if (i < sequence.length / 2 && bases[i + 1].value.slice(-3) != '(o)')
+    const indexOfSymbol = AXOLABS_MAP['RNA']['symbols'].indexOf(x);
+    let symbol = AXOLABS_MAP[bases[i].value]['symbols'][indexOfSymbol];
+    if (isOverhang(bases[i].value)) {
+      if (i < sequence.length / 2 && !isOverhang(bases[i + 1].value))
         symbol = symbol + x + 'f';
-      else if (i > sequence.length / 2 && bases[i - 1].value.slice(-3) != '(o)')
+      else if (i > sequence.length / 2 && !isOverhang(bases[i - 1].value))
         symbol = x + 'f' + symbol;
     }
     return (ptoLinkages[i].value) ? symbol + 's' : symbol;
@@ -150,12 +151,12 @@ export function defineAxolabsPattern() {
         updateSvgScheme();
         updateOutputExamples();
       });
-      if (asBases[i].value.slice(-3) != '(o)')
+      if (!isOverhang(asBases[i].value))
         nucleotideCounter++;
 
       asModificationItems.append(
         ui.divH([
-          ui.div([ui.label(asBases[i].value.slice(-3) == '(o)' ? '' : String(nucleotideCounter))],
+          ui.div([ui.label(isOverhang(asBases[i].value) ? '' : String(nucleotideCounter))],
             {style: {width: '20px'}})!,
           ui.block75([asBases[i]])!,
           ui.div([asPtoLinkages[i]])!,
@@ -196,12 +197,12 @@ export function defineAxolabsPattern() {
         updateSvgScheme();
         updateOutputExamples();
       });
-      if (ssBases[i].value.slice(-3) != '(o)')
+      if (!isOverhang(ssBases[i].value))
         nucleotideCounter++;
 
       ssModificationItems.append(
         ui.divH([
-          ui.div([ui.label(ssBases[i].value.slice(-3) == '(o)' ? '' : String(nucleotideCounter))],
+          ui.div([ui.label(isOverhang(ssBases[i].value) ? '' : String(nucleotideCounter))],
             {style: {width: '20px'}})!,
           ui.block75([ssBases[i]])!,
           ui.div([ssPtoLinkages[i]])!,