@datagrok/sequence-translator 0.0.1 → 0.0.5

package/src/package.ts

@@ -2,321 +2,527 @@
 import * as grok from 'datagrok-api/grok';
 import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
-import $ from "cash-dom";
+import * as OCL from 'openchemlib/full.js';
+import $ from 'cash-dom';
+import {defineAxolabsPattern} from './defineAxolabsPattern';
+import {saveSenseAntiSense} from './save-sense-antisense';
+import {map, stadardPhosphateLinkSmiles, SYNTHESIZERS, TECHNOLOGIES, MODIFICATIONS} from './map';
+
+export const _package = new DG.Package();
+
+const defaultInput = 'AGGTCCTCTTGACTTAGGCC';
+const undefinedInputSequence = 'Type of input sequence is undefined';
+const noTranslationTableAvailable = 'No translation table available';
+const sequenceWasCopied = 'Copied';
+const tooltipSequence = 'Copy sequence';
+
+function getAllCodesOfSynthesizer(synthesizer: string): string[] {
+  let codes: string[] = [];
+  for (const technology of Object.keys(map[synthesizer]))
+    codes = codes.concat(Object.keys(map[synthesizer][technology]));
+  return codes.concat(Object.keys(MODIFICATIONS));
+}
 
-import {defineAxolabsPattern} from "./defineAxolabsPattern";
+function getListOfPossibleSynthesizersByFirstMatchedCode(sequence: string): string[] {
+  const synthesizers: string[] = [];
+  Object.keys(map).forEach((synthesizer: string) => {
+    const codes = getAllCodesOfSynthesizer(synthesizer);
+    //TODO: get first non-dropdown code when there are two modifications
+    let start = 0;
+    for (let i = 0; i < sequence.length; i++) {
+      if (sequence[i] == ')') {
+        start = i + 1;
+        break;
+      }
+    }
+    if (codes.some((s: string) => s == sequence.slice(start, start + s.length)))
+      synthesizers.push(synthesizer);
+  });
+  return synthesizers;
+}
 
-export let _package = new DG.Package();
+function getListOfPossibleTechnologiesByFirstMatchedCode(sequence: string, synthesizer: string): string[] {
+  const technologies: string[] = [];
+  Object.keys(map[synthesizer]).forEach((technology: string) => {
+    const codes = Object.keys(map[synthesizer][technology]).concat(Object.keys(MODIFICATIONS));
+    if (codes.some((s) => s == sequence.slice(0, s.length)))
+      technologies.push(technology);
+  });
+  return technologies;
+}
 
-const undefinedInputSequence: string = "Type of input sequence is undefined";
-const smallNumberOfCharacters: string = "Length of input sequence should be at least 10 characters";
-const defaultNucleotidesInput: string = "AGGTCCTCTTGACTTAGGCC";
-const noTranslationTableAvailable: string = "No translation table available";
-const sequenceWasCopied: string = 'Copied!';
-const tooltipSequence: string = 'Copy sequence';
+export function isValidSequence(sequence: string): {
+  indexOfFirstNotValidCharacter: number,
+  expectedSynthesizer: string | null,
+  expectedTechnology: string | null
+} {
+  const possibleSynthesizers = getListOfPossibleSynthesizersByFirstMatchedCode(sequence);
+  if (possibleSynthesizers.length == 0)
+    return {indexOfFirstNotValidCharacter: 0, expectedSynthesizer: null, expectedTechnology: null};
+
+  let outputIndices = Array(possibleSynthesizers.length).fill(0);
+
+  const firstUniqueCharacters = ['r', 'd'];
+  const nucleotides = ['A', 'U', 'T', 'C', 'G'];
+
+  possibleSynthesizers.forEach((synthesizer, synthesizerIndex) => {
+    const codes = getAllCodesOfSynthesizer(synthesizer);
+    while (outputIndices[synthesizerIndex] < sequence.length) {
+      const matchedCode = codes
+        .find((c) => c == sequence.slice(outputIndices[synthesizerIndex], outputIndices[synthesizerIndex] + c.length));
+
+      if (matchedCode == null)
+        break;
+
+      if ( // for mistake pattern 'rAA'
+        outputIndices[synthesizerIndex] > 1 &&
+        nucleotides.includes(sequence[outputIndices[synthesizerIndex]]) &&
+        firstUniqueCharacters.includes(sequence[outputIndices[synthesizerIndex] - 2])
+      ) break;
+
+      if ( // for mistake pattern 'ArA'
+        firstUniqueCharacters.includes(sequence[outputIndices[synthesizerIndex] + 1]) &&
+        nucleotides.includes(sequence[outputIndices[synthesizerIndex]])
+      ) {
+        outputIndices[synthesizerIndex]++;
+        break;
+      }
 
-//name: Sequence Translator
-//tags: app
-export function sequenceTranslator(): void {
+      outputIndices[synthesizerIndex] += matchedCode.length;
+    }
+  });
 
-  let windows = grok.shell.windows;
-  windows.showProperties = false;
-  windows.showToolbox = false;
-  windows.showHelp = false;
+  const indexOfExpectedSythesizer = Math.max.apply(Math, outputIndices);
+  const indexOfFirstNotValidCharacter = (indexOfExpectedSythesizer == sequence.length) ? -1 : indexOfExpectedSythesizer;
+  const expectedSynthesizer = possibleSynthesizers[outputIndices.indexOf(indexOfExpectedSythesizer)];
+  if (indexOfFirstNotValidCharacter != -1)
+    return {
+      indexOfFirstNotValidCharacter: indexOfFirstNotValidCharacter,
+      expectedSynthesizer: expectedSynthesizer,
+      expectedTechnology: null
+    };
 
-  let appMainDescription = ui.info(
-    [
-      ui.divText('\n How to convert one sequence:',{style:{'font-weight':'bolder'}}),
-      ui.divText("Paste sequence into the text field below"),
-      ui.divText('\n How to convert many sequences:',{style:{'font-weight':'bolder'}}),
-      ui.divText("1. Drag & drop an Excel or CSV file with sequences into Datagrok. The platform will automatically detect columns with sequences"),
-      ui.divText('2. Right-click on the column header, then see the \'Convert\' menu'),
-      ui.divText("This will add the result column to the right of the table"),
-    ], 'Convert oligonucleotide sequences between Nucleotides, BioSpring, Axolabs, and GCRS representations.'
-  );
+  let possibleTechnologies = getListOfPossibleTechnologiesByFirstMatchedCode(sequence, expectedSynthesizer);
+  if (possibleTechnologies.length == 0)
+    return { indexOfFirstNotValidCharacter: 0, expectedSynthesizer: null, expectedTechnology: null };
 
-  let inputSequenceField = ui.textInput("", defaultNucleotidesInput, async (seq: string) => {
-    moleculeSvg.innerHTML = "";
-    let outputSequencesObj = convertSequence(seq);
+  outputIndices = Array(possibleTechnologies.length).fill(0);
 
-    let tableRows = [];
-    for (let key of Object.keys(outputSequencesObj).slice(1)) {
-      // @ts-ignore
-      tableRows.push({'key': key, 'value': ui.link(outputSequencesObj[key], () => navigator.clipboard.writeText(outputSequencesObj[key]).then(() => grok.shell.info(sequenceWasCopied)), tooltipSequence, '')})
-    }
+  possibleTechnologies.forEach((technology: string, technologyIndex: number) => {
+    let codes = Object.keys(map[expectedSynthesizer][technology]);
+    while (outputIndices[technologyIndex] < sequence.length) {
 
-    outputTableDiv.innerHTML = "";
+      let matchedCode = codes
+        .find((c) => c == sequence.slice(outputIndices[technologyIndex], outputIndices[technologyIndex] + c.length));
 
-    outputTableDiv.append(
-      ui.div([
-        DG.HtmlTable.create(
-          tableRows,
-          (item: {key: string; value: string;}) => [item.key, item.value],
-          ['Code', 'Sequence']
-        ).root
-      ], 'table')
-    );
-    grok.shell.v
-    semTypeOfInputSequence.textContent = 'Detected input type: ' + outputSequencesObj.type;
-
-    if (!(outputSequencesObj.type == undefinedInputSequence || outputSequencesObj.type == smallNumberOfCharacters)) {
-      let pi = DG.TaskBarProgressIndicator.create('Rendering molecule...');
-      try {
-        let flavor: string = (outputSequencesObj.Nucleotides.includes('U')) ? "RNA_both_caps" : "DNA_both_caps";
-        let mol = grok.chem.svgMol(<string> await nucleotidesToSmiles(outputSequencesObj.Nucleotides, flavor), 900, 300);
-        moleculeSvg.append(mol);
-      } finally {
-        pi.close();
+      if (matchedCode == null)
+        break;
+
+      if ( // for mistake pattern 'rAA'
+        outputIndices[technologyIndex] > 1 &&
+        nucleotides.includes(sequence[outputIndices[technologyIndex]]) &&
+        firstUniqueCharacters.includes(sequence[outputIndices[technologyIndex] - 2])
+      ) break;
+
+      if (  // for mistake pattern 'ArA'
+        firstUniqueCharacters.includes(sequence[outputIndices[technologyIndex] + 1]) &&
+        nucleotides.includes(sequence[outputIndices[technologyIndex]])
+      ) {
+        outputIndices[technologyIndex]++;
+        break;
       }
+
+      outputIndices[technologyIndex] += matchedCode.length;
     }
   });
-  let semTypeOfInputSequence = ui.divText('Detected input type: DNA Nucleotides Code');
-
-  let outputTableDiv = ui.div([
-    DG.HtmlTable.create([
-      {key: 'Nucleotides', value: ui.link(defaultNucleotidesInput, () => navigator.clipboard.writeText(defaultNucleotidesInput).then(() => grok.shell.info(sequenceWasCopied)), tooltipSequence, '')},
-      {key: 'BioSpring', value: ui.link(asoGapmersNucleotidesToBioSpring(defaultNucleotidesInput), () => navigator.clipboard.writeText(asoGapmersNucleotidesToBioSpring(defaultNucleotidesInput)).then(() => grok.shell.info(sequenceWasCopied)), tooltipSequence, '')},
-      {key: 'Axolabs', value: ui.link(noTranslationTableAvailable, () => navigator.clipboard.writeText(defaultNucleotidesInput).then(() => grok.shell.info(sequenceWasCopied)), tooltipSequence, '')},
-      {key: 'GCRS', value: ui.link(asoGapmersNucleotidesToGcrs(defaultNucleotidesInput), () => navigator.clipboard.writeText(asoGapmersNucleotidesToGcrs(defaultNucleotidesInput)).then(() => grok.shell.info(sequenceWasCopied)), tooltipSequence, '')}
-    ], (item: {key: string; value: string;}) => [item.key, item.value], ['Code', 'Sequence']).root
-  ], 'table');
-
-  let accordionWithCmoCodes = ui.accordion();
-  accordionWithCmoCodes.addPane('CMO Codes', () =>
-    ui.divH([
-      DG.HtmlTable.create(
-        [
-          {name: "2'MOE-5Me-rU", bioSpring: '5', gcrs: 'moeT'},
-          {name: "2'MOE-rA", bioSpring: '6', gcrs: 'moeA'},
-          {name: "2'MOE-5Me-rC", bioSpring: '7', gcrs: 'moe5mC'},
-          {name: "2'MOE-rG", bioSpring: '8', gcrs: 'moeG'},
-          {name: "5-Methyl-dC", bioSpring: '9', gcrs: '5mC'},
-          {name: "ps linkage", bioSpring: '*', gcrs: 'ps'},
-          {name: "dA", bioSpring: 'A', gcrs: 'A'},
-          {name: "dC", bioSpring: 'C', gcrs: 'C'},
-          {name: "dT", bioSpring: 'T', gcrs: 'T'},
-          {name: "dG", bioSpring: 'G', gcrs: 'G'}
-        ],
-        (item: {name: string; bioSpring: string; gcrs: string}) => [item.name, item.bioSpring, item.gcrs],
-        ['For ASO Gapmers', 'BioSpring', 'GCRS']
-      ).root,
-      ui.div([], {style: {width: '50px'}}),
-      DG.HtmlTable.create(
-        [
-          {name: "2'-fluoro-U", axolabs: '1', bioSpring: 'Uf', gcrs: 'fU'},
-          {name: "2'-fluoro-A", axolabs: '2', bioSpring: 'Af', gcrs: 'fA'},
-          {name: "2'-fluoro-C", axolabs: '3', bioSpring: 'Cf', gcrs: 'fC'},
-          {name: "2'-fluoro-G", axolabs: '4', bioSpring: 'Gf', gcrs: 'fG'},
-          {name: "OMe-rU", axolabs: '5', bioSpring: 'u', gcrs: 'mU'},
-          {name: "OMe-rA", axolabs: '6', bioSpring: 'a', gcrs: 'mA'},
-          {name: "OMe-rC", axolabs: '7', bioSpring: 'c', gcrs: 'mC'},
-          {name: "OMe-rG", axolabs: '8', bioSpring: 'g', gcrs: 'mG'},
-          {name: "ps linkage", axolabs: '*', bioSpring: 's', gcrs: 'ps'}
-        ],
-        (item: {name: string; axolabs: string, bioSpring: string; gcrs: string}) => [item.name, item.bioSpring, item.axolabs, item.gcrs],
-        ["For 2\'-OMe and 2\'-F modified siRNA", 'BioSpring', 'Axolabs', 'GCRS']
-      ).root
-    ]), false
-  );
 
-  let moleculeSvg = ui.block([
-    grok.chem.svgMol('Cc1cn([C@H]2C[C@H](OP(=O)(O)OC[C@H]3O[C@@H](n4ccc(N)nc4=O)C[C@@H]3OP(=O)(O)OC[C@H]3O[C@@H](n' +
-      '4cc(C)c(=O)[nH]c4=O)C[C@@H]3OP(=O)(O)OC[C@H]3O[C@@H](n4cc(C)c(=O)[nH]c4=O)C[C@@H]3OP(=O)(O)OC[C@H]3O[C@@H](n4cnc5' +
-      'c(=O)[nH]c(N)nc54)C[C@@H]3OP(=O)(O)OC[C@H]3O[C@@H](n4cnc5c(N)ncnc54)C[C@@H]3OP(=O)(O)OC[C@H]3O[C@@H](n4ccc(N)nc4=O)' +
-      'C[C@@H]3OP(=O)(O)OC[C@H]3O[C@@H](n4cc(C)c(=O)[nH]c4=O)C[C@@H]3OP(=O)(O)OC[C@H]3O[C@@H](n4cc(C)c(=O)[nH]c4=O)C[C@@H]3OP(=O)(O)' +
-      'OC[C@H]3O[C@@H](n4cnc5c(N)ncnc54)C[C@@H]3OP(=O)(O)OC[C@H]3O[C@@H](n4cnc5c(=O)[nH]c(N)nc54)C[C@@H]3OP(=O)(O)OC[C@H]' +
-      '3O[C@@H](n4cnc5c(=O)[nH]c(N)nc54)C[C@@H]3OP(=O)(O)OC[C@H]3O[C@@H](n4ccc(N)nc4=O)C[C@@H]3OP(=O)(O)OC[C@H]3O[C@@H]' +
-      '(n4ccc(N)nc4=O)C[C@@H]3OP(=O)(O)O)[C@@H](COP(=O)(O)O[C@H]3C[C@H](n4ccc(N)nc4=O)O[C@@H]3COP(=O)(O)O[C@H]3C[C@H]' +
-      '(n4ccc(N)nc4=O)O[C@@H]3COP(=O)(O)O[C@H]3C[C@H](n4cc(C)c(=O)[nH]c4=O)O[C@@H]3COP(=O)(O)O[C@H]3C[C@H](n4cnc5c(=O)' +
-      '[nH]c(N)nc54)O[C@@H]3COP(=O)(O)O[C@H]3C[C@H](n4cnc5c(=O)[nH]c(N)nc54)O[C@@H]3COP(=O)(O)O[C@H]3C[C@H](n4cnc5c(N)' +
-      'ncnc54)O[C@@H]3COP(=O)(O)O)O2)c(=O)[nH]c1=O', 900, 300
-    )
-  ]);
+  const indexOfExpectedTechnology = Math.max.apply(Math, outputIndices);
+  const expectedTechnology = possibleTechnologies[outputIndices.indexOf(indexOfExpectedTechnology)];
 
-  let tab = ui.tabControl({
-    'MAIN': ui.div([
-      appMainDescription,
-      ui.panel([
-        ui.div([
-          ui.h1('Input sequence'),
-          ui.div([
-            inputSequenceField.root
-          ],'input-base')
-        ], 'sequenceInput'),
-        semTypeOfInputSequence,
-        ui.block([
-          ui.h1('Output'),
-          ui.h1('Output'),
-          outputTableDiv
-        ]),
-        accordionWithCmoCodes.root,
-        moleculeSvg,
-        ui.button('SAVE SD FILE', async() => {
-          let outputSequenceObj = convertSequence(inputSequenceField.value);
-          let flavor: string = outputSequenceObj.Nucleotides.includes('U') ? "RNA_both_caps" : "DNA_both_caps";
-          let smiles = await nucleotidesToSmiles(outputSequenceObj.Nucleotides, flavor);
-          smiles = smiles.replace(/@/g, '');  // Remove StereoChemistry on the Nucleic acid chain and remove the Chiral label
-          //@ts-ignore
-          let mol = new OCL.Molecule.fromSmiles(smiles);
-          let result = `${mol.toMolfile()}\n` + '$$$$';
-          var element = document.createElement('a');
-          element.setAttribute('href', 'data:text/plain;charset=utf-8,' + encodeURIComponent(result));
-          element.setAttribute('download', outputSequenceObj.Nucleotides + '.sdf');
-          element.click();
-        })
-      ], 'sequence')!
-    ]),
-    'AXOLABS': _defineAxolabsPattern()
-  }).root;
-  tab.style.height = '100%';
-  tab.style.width = '100%';
-
-  let v = grok.shell.newView('Sequence Translator', [
-     tab
-  ]);
-  v.box = true;
+  return {
+    indexOfFirstNotValidCharacter: indexOfFirstNotValidCharacter,
+    expectedSynthesizer: expectedSynthesizer,
+    expectedTechnology: expectedTechnology
+  };
+}
 
-  $('.sequence')
-    .children().css('padding','5px 0');
-  $('.sequenceInput .input-base').css('margin','0');
-  $('.sequenceInput textarea')
-    .css('resize','none')
-    .css('min-height','50px')
-    .css('width','100%');
-  $('.sequenceInput select')
-    .css('width','100%');
+function sortByStringLengthInDescendingOrder(array: string[]): string[] {
+  return array.sort(function(a: string, b: string) { return b.length - a.length; });
 }
 
-export async function nucleotidesToSmiles(nucleotides: string, flavor: string) {
-  return await grok.functions.call('SequenceTranslator:convertFastaToSmiles', {
-    'sequence_in_fasta_format': nucleotides,
-    'flavor': flavor
-  });
+function getObjectWithCodesAndSmiles(sequence: string) {
+  const obj: { [code: string]: string } = {};
+  for (const synthesizer of Object.keys(map))
+    for (const technology of Object.keys(map[synthesizer]))
+      for (let code of Object.keys(map[synthesizer][technology]))
+        obj[code] = map[synthesizer][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)
+    obj['g'] = map[SYNTHESIZERS.MERMADE_12][TECHNOLOGIES.SI_RNA]['g'].SMILES;
+  else if (output.expectedSynthesizer == SYNTHESIZERS.AXOLABS)
+    obj['g'] = map[SYNTHESIZERS.AXOLABS][TECHNOLOGIES.SI_RNA]['g'].SMILES;
+  return obj;
 }
 
-export function isDnaNucleotidesCode(sequence: string): boolean {return /^[ATGC]{10,}$/.test(sequence);}
+export function sequenceToSmiles(sequence: string, inverted: boolean = false): string {
+  const obj = getObjectWithCodesAndSmiles(sequence);
+  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])) {
+      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;
+      }
+    } else {
+      if (links.includes(codesList[i]) ||
+        includesStandardLinkAlready.includes(codesList[i]) ||
+        (i < codesList.length - 1 && links.includes(codesList[i + 1]))
+      )
+        smiles += obj[codesList[i]];
+      else
+        smiles += obj[codesList[i]] + stadardPhosphateLinkSmiles;
+    }
+  }
+  smiles = smiles.replace(/OO/g, 'O');
+  return (
+    (
+      links.includes(codesList[codesList.length - 1]) &&
+      codesList.length > 1 &&
+      !includesStandardLinkAlready.includes(codesList[codesList.length - 2])
+    ) ||
+    dropdowns.includes(codesList[codesList.length - 1]) ||
+    includesStandardLinkAlready.includes(codesList[codesList.length - 1])
+  ) ?
+    smiles :
+    smiles.slice(0, smiles.length - stadardPhosphateLinkSmiles.length + 1);
+}
+
+//name: Sequence Translator
+//tags: app
+export function sequenceTranslator(): void {
+  const windows = grok.shell.windows;
+  windows.showProperties = false;
+  windows.showToolbox = false;
+  windows.showHelp = false;
+
+  function updateTableAndMolecule(sequence: string): void {
+    moleculeSvgDiv.innerHTML = '';
+    outputTableDiv.innerHTML = '';
+    const pi = DG.TaskBarProgressIndicator.create('Rendering table and molecule...');
+    let errorsExist = false;
+    try {
+      const outputSequenceObj = convertSequence(sequence);
+      const tableRows = [];
+
+      for (const key of Object.keys(outputSequenceObj).slice(1)) {
+        let indexOfFirstNotValidCharacter = ('indexOfFirstNotValidCharacter' in outputSequenceObj) ?
+          JSON.parse(outputSequenceObj.indexOfFirstNotValidCharacter!).indexOfFirstNotValidCharacter :
+          -1;
+        if ('indexOfFirstNotValidCharacter' in outputSequenceObj) {
+          let indexOfFirstNotValidCharacter = ('indexOfFirstNotValidCharacter' in outputSequenceObj) ?
+            JSON.parse(outputSequenceObj.indexOfFirstNotValidCharacter!).indexOfFirstNotValidCharacter :
+            -1;
+          if (indexOfFirstNotValidCharacter != -1)
+            errorsExist = true;
+        }
+
+        tableRows.push({
+          'key': key,
+          'value': ('indexOfFirstNotValidCharacter' in outputSequenceObj) ?
+            ui.divH([
+              ui.divText(sequence.slice(0, indexOfFirstNotValidCharacter), {style: {color: 'grey'}}),
+              ui.tooltip.bind(
+                ui.divText(sequence.slice(indexOfFirstNotValidCharacter), {style: {color: 'red'}}),
+                'Expected format: ' + JSON.parse(outputSequenceObj.indexOfFirstNotValidCharacter!).expectedSynthesizer + '. See tables with valid codes on the right'
+              ),
+            ]) : //@ts-ignore
+            ui.link(outputSequenceObj[key], () => navigator.clipboard.writeText(outputSequenceObj[key]).then(() => grok.shell.info(sequenceWasCopied)), tooltipSequence, '')
+        });
+      }
+
+      if (errorsExist) {
+        const expectedSynthesizer = JSON.parse(outputSequenceObj.indexOfFirstNotValidCharacter!).expectedSynthesizer.slice(0, -6);
+        asoGapmersGrid.onCellPrepare(function (gc) {
+          gc.style.backColor = (gc.gridColumn.name == expectedSynthesizer) ? 0xFFF00000 : 0xFFFFFFFF;
+        });
+        omeAndFluoroGrid.onCellPrepare(function (gc) {
+          gc.style.backColor = (gc.gridColumn.name == expectedSynthesizer) ? 0xFFF00000 : 0xFFFFFFFF;
+        });
+        switchInput.enabled = true;
+      } else {
+        asoGapmersGrid.onCellPrepare(function (gc) {
+          gc.style.backColor = 0xFFFFFFFF;
+        });
+        omeAndFluoroGrid.onCellPrepare(function (gc) {
+          gc.style.backColor = 0xFFFFFFFF;
+        });
+      }
 
-export function isRnaNucleotidesCode(sequence: string): boolean {return /^[AUGC]{10,}$/.test(sequence);}
+      outputTableDiv.append(
+        ui.div([
+          DG.HtmlTable.create(tableRows, (item: { key: string; value: string; }) => [item.key, item.value], ['Code', 'Sequence']).root
+        ], 'table')
+      );
+      semTypeOfInputSequence.textContent = 'Detected input type: ' + outputSequenceObj.type;
+
+      if (outputSequenceObj.type != undefinedInputSequence && outputSequenceObj.Error != undefinedInputSequence) {
+        let canvas = ui.canvas(300, 170);
+        canvas.addEventListener("click", () => {
+          let canv = ui.canvas($(window).width(), $(window).height());
+          const smiles = sequenceToSmiles(inputSequenceField.value.replace(/\s/g, ''));
+          // @ts-ignore
+          OCL.StructureView.drawMolecule(canv, OCL.Molecule.fromSmiles(smiles), { suppressChiralText: true });
+          ui.dialog('Molecule')
+            .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, ''));
+        // @ts-ignore
+        OCL.StructureView.drawMolecule(canvas, OCL.Molecule.fromSmiles(smiles), { suppressChiralText: true });
+        moleculeSvgDiv.append(canvas);
+      } else
+        moleculeSvgDiv.innerHTML = '';
+    } finally {
+      pi.close();
+    }
+  }
+
+  const semTypeOfInputSequence = ui.divText('');
+  const moleculeSvgDiv = ui.block([]);
+  const outputTableDiv = ui.div([], 'table');
+  const inputSequenceField = ui.textInput('', defaultInput, (sequence: string) => updateTableAndMolecule(sequence));
+
+  const asoDf = DG.DataFrame.fromObjects([
+    { Name: "2'MOE-5Me-rU", BioSpring: "5", "Janssen GCRS": "moeT" },
+    { Name: "2'MOE-rA", BioSpring: "6", "Janssen GCRS": "moeA" },
+    { Name: "2'MOE-5Me-rC", BioSpring: "7", "Janssen GCRS": "moe5mC" },
+    { Name: "2'MOE-rG", BioSpring: "8", "Janssen GCRS": "moeG" },
+    { Name: "5-Methyl-dC", BioSpring: "9", "Janssen GCRS": "5mC" },
+    { Name: "ps linkage", BioSpring: "*", "Janssen GCRS": "ps" },
+    { Name: "dA", BioSpring: "A", "Janssen GCRS": "A, dA" },
+    { Name: "dC", BioSpring: "C", "Janssen GCRS": "C, dC" },
+    { Name: "dG", BioSpring: "G", "Janssen GCRS": "G, dG" },
+    { Name: "dT", BioSpring: "T", "Janssen GCRS": "T, dT" },
+    { Name: "rA", BioSpring: "", "Janssen GCRS": "rA" },
+    { Name: "rC", BioSpring: "", "Janssen GCRS": "rC" },
+    { Name: "rG", BioSpring: "", "Janssen GCRS": "rG" },
+    { Name: "rU", BioSpring: "", "Janssen GCRS": "rU" }
+  ])!;
+  const asoGapmersGrid = DG.Viewer.grid(
+    asoDf, { showRowHeader: false, showCellTooltip: false }
+  );
 
-export function isAbiCode(sequence: string): boolean {return /^[5678ATGC]{10,}$/.test(sequence);}
+  asoDf.onCurrentCellChanged.subscribe((_) => {
+    navigator.clipboard.writeText(asoDf.currentCell.value).then(() => grok.shell.info('Copied'))
+  });
 
-export function isAsoGapmerBioSpringCode(sequence: string): boolean {return /^[*56789ATGC]{30,}$/.test(sequence);}
+  let omeAndFluoroGrid = DG.Viewer.grid(
+    DG.DataFrame.fromObjects([
+      { Name: "2'-fluoro-U", BioSpring: "1", Axolabs: "Uf", "Janssen GCRS": "fU" },
+      { Name: "2'-fluoro-A", BioSpring: "2", Axolabs: "Af", "Janssen GCRS": "fA" },
+      { Name: "2'-fluoro-C", BioSpring: "3", Axolabs: "Cf", "Janssen GCRS": "fC" },
+      { Name: "2'-fluoro-G", BioSpring: "4", Axolabs: "Gf", "Janssen GCRS": "fG" },
+      { Name: "2'OMe-rU", BioSpring: "5", Axolabs: "u", "Janssen GCRS": "mU" },
+      { Name: "2'OMe-rA", BioSpring: "6", Axolabs: "a", "Janssen GCRS": "mA" },
+      { Name: "2'OMe-rC", BioSpring: "7", Axolabs: "c", "Janssen GCRS": "mC" },
+      { Name: "2'OMe-rG", BioSpring: "8", Axolabs: "g", "Janssen GCRS": "mG" },
+      { Name: "ps linkage", BioSpring: "*", Axolabs: "s", "Janssen GCRS": "ps" }
+    ])!, { showRowHeader: false, showCellTooltip: false }
+  );
 
-export function isAsoGapmerGcrsCode(sequence: string): boolean {return /^(?=.*moe)(?=.*5mC)(?=.*ps){30,}/.test(sequence);}
+  const overhangModificationsGrid = DG.Viewer.grid(
+    DG.DataFrame.fromObjects([
+      { Name: "(invabasic)" },
+      { Name: "(GalNAc-2-JNJ)" }
+    ])!, { showRowHeader: false, showCellTooltip: false }
+  );
+  updateTableAndMolecule(defaultInput);
 
-export function isSiRnaBioSpringCode(sequence: string): boolean {return /^[*1-8]{30,}$/.test(sequence);}
+  const appMainDescription = ui.info([
+      ui.divText('How to convert one sequence:',{style:{'font-weight':'bolder'}}),
+      ui.divText('Paste sequence into the text field below'),
+      ui.divText('\n How to convert many sequences:',{style:{'font-weight':'bolder'}}),
+      ui.divText('1. Drag & drop an Excel or CSV file with sequences into Datagrok. The platform will automatically detect columns with sequences'),
+      ui.divText('2. Right-click on the column header, then see the \'Convert\' menu'),
+      ui.divText('This will add the result column to the right of the table'),
+    ], 'Convert oligonucleotide sequences between Nucleotides, BioSpring, Axolabs, Mermade 12 and GCRS representations.'
+  );
 
-export function isSiRnaAxolabsCode(sequence: string): boolean {return /^[fsACGUacgu]{20,}$/.test(sequence);}
+  const codesTablesDiv = ui.splitV([
+    ui.box(ui.h2('ASO Gapmers'), { style: {maxHeight: '40px'} }),
+    asoGapmersGrid.root,
+    ui.box(ui.h2("2'-OMe and 2'-F siRNA"), { style: {maxHeight: '40px'} }),
+    omeAndFluoroGrid.root,
+    ui.box(ui.h2('Overhang modifications'), { style: {maxHeight: '40px'} }),
+    overhangModificationsGrid.root
+  ], { style: { maxWidth: '350px' } });
+
+  const tabControl = ui.tabControl({
+    'MAIN': ui.box(
+      ui.splitH([
+        ui.splitV([
+          ui.panel([
+            appMainDescription,
+            ui.div([
+              ui.h1('Input sequence'),
+              ui.div([
+                inputSequenceField.root,
+              ], 'input-base'),
+            ], 'sequenceInput'),
+            semTypeOfInputSequence,
+            ui.block([
+              ui.h1('Output'),
+              outputTableDiv,
+            ]),
+            moleculeSvgDiv,
+          ], 'sequence'),
+        ]),
+        codesTablesDiv,
+      ], {style: {height: '100%', width: '100%'}}),
+    ),
+    'AXOLABS': defineAxolabsPattern(),
+    'SDF': saveSenseAntiSense(),
+  });
 
-export function isSiRnaGcrsCode(sequence: string): boolean {return (sequence.slice(0, 3) == 'moe' && /^[fmpsACGU]{30,}$/.test(sequence));}
+  let v = grok.shell.newView('Sequence Translator', [tabControl]);
+  v.box = true;
 
-export function isGcrsCode(sequence: string): boolean {return /^[fmpsACGU]{30,}$/.test(sequence);}
+  const switchInput = ui.switchInput('Codes', true, (v: boolean) => (v) ?
+    $(codesTablesDiv).show() :
+    $(codesTablesDiv).hide()
+  );
 
-export function isOP100Code(sequence: string): boolean {return /^[acgu*]{10,}$/.test(sequence);}
+  const topPanel = [
+    ui.iconFA('download', () => {
+      const smiles = sequenceToSmiles(inputSequenceField.value.replace(/\s/g, ''));
+      const result = `${OCL.Molecule.fromSmiles(smiles).toMolfile()}\n`;
+      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, '')))
+        .then(() => grok.shell.info(sequenceWasCopied));
+    }, 'Copy SMILES'),
+    switchInput.root,
+  ];
+
+  tabControl.onTabChanged.subscribe((_) =>
+    v.setRibbonPanels([(tabControl.currentPane.name == 'MAIN') ? topPanel : []]));
+  v.setRibbonPanels([topPanel]);
 
-export function isMM12Code(sequence: string): boolean {return /^[IiJjKkLlEeFfGgHhQq]{10,}$/.test(sequence);}
+  $('.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%');
+}
 
-function convertSequence(seq: string) {
-  seq = seq.replace(/\s/g, '');
-  if (seq.length < 10)
+function convertSequence(text: string) {
+  text = text.replace(/\s/g, '');
+  let seq = text;
+  let output = isValidSequence(seq);
+  if (output.indexOfFirstNotValidCharacter != -1)
     return {
-      type: smallNumberOfCharacters,
-      Nucleotides: smallNumberOfCharacters,
-      BioSpring: smallNumberOfCharacters,
-      Axolabs: smallNumberOfCharacters,
-      GCRS: smallNumberOfCharacters
+      // type: '',
+      indexOfFirstNotValidCharacter: JSON.stringify(output),
+      Error: undefinedInputSequence
     };
-  if (isDnaNucleotidesCode(seq))
+  if (output.expectedSynthesizer == SYNTHESIZERS.RAW_NUCLEOTIDES && output.expectedTechnology == TECHNOLOGIES.DNA)
     return {
-      type: "DNA Nucleotides Code",
+      type: SYNTHESIZERS.RAW_NUCLEOTIDES + ' ' +  TECHNOLOGIES.DNA,
       Nucleotides: seq,
       BioSpring: asoGapmersNucleotidesToBioSpring(seq),
-      Axolabs: noTranslationTableAvailable,
       GCRS: asoGapmersNucleotidesToGcrs(seq)
     };
-  if (isAbiCode(seq))
+  if (output.expectedSynthesizer == SYNTHESIZERS.BIOSPRING && output.expectedTechnology == TECHNOLOGIES.ASO_GAPMERS)
     return {
-      type: "ABI Code",
-      Nucleotides: noTranslationTableAvailable,
-      GCRS: noTranslationTableAvailable,
-      MM12: noTranslationTableAvailable,
-      OP100: noTranslationTableAvailable,
-      ABI: seq
-    };
-  if (isAsoGapmerBioSpringCode(seq))
-    return {
-      type: "ASO Gapmers / BioSpring Code",
+      type: SYNTHESIZERS.BIOSPRING + ' ' +  TECHNOLOGIES.ASO_GAPMERS,
       Nucleotides: asoGapmersBioSpringToNucleotides(seq),
       BioSpring: seq,
-      Axolabs: noTranslationTableAvailable,
       GCRS: asoGapmersBioSpringToGcrs(seq)
     };
-  if (isAsoGapmerGcrsCode(seq))
+  if (output.expectedSynthesizer == SYNTHESIZERS.GCRS && output.expectedTechnology == TECHNOLOGIES.ASO_GAPMERS)
     return {
-      type: "ASO Gapmers / GCRS Code",
+      type: SYNTHESIZERS.GCRS + ' ' +  TECHNOLOGIES.ASO_GAPMERS,
       Nucleotides: asoGapmersGcrsToNucleotides(seq),
       BioSpring: asoGapmersGcrsToBioSpring(seq),
-      Axolabs: noTranslationTableAvailable,
+      Mermade12: gcrsToMermade12(seq),
       GCRS: seq
     };
-  if (isRnaNucleotidesCode(seq))
+  if (output.expectedSynthesizer == SYNTHESIZERS.RAW_NUCLEOTIDES && output.expectedTechnology == TECHNOLOGIES.RNA)
     return {
-      type: "RNA Nucleotides Code",
+      type: SYNTHESIZERS.RAW_NUCLEOTIDES + ' ' +  TECHNOLOGIES.RNA,
       Nucleotides: seq,
       BioSpring: siRnaNucleotideToBioSpringSenseStrand(seq),
       Axolabs: siRnaNucleotideToAxolabsSenseStrand(seq),
       GCRS: siRnaNucleotidesToGcrs(seq)
     };
-  if (isSiRnaBioSpringCode(seq))
+  if (output.expectedSynthesizer == SYNTHESIZERS.BIOSPRING && output.expectedTechnology == TECHNOLOGIES.SI_RNA)
     return {
-      type: "siRNA / bioSpring Code",
+      type: SYNTHESIZERS.BIOSPRING + ' ' + TECHNOLOGIES.SI_RNA,
       Nucleotides: siRnaBioSpringToNucleotides(seq),
       BioSpring: seq,
       Axolabs: siRnaBioSpringToAxolabs(seq),
       GCRS: siRnaBioSpringToGcrs(seq)
     };
-  if (isSiRnaAxolabsCode(seq))
+  if (output.expectedSynthesizer == SYNTHESIZERS.AXOLABS && output.expectedTechnology == TECHNOLOGIES.SI_RNA)
     return {
-      type: "siRNA / Axolabs Code",
+      type: SYNTHESIZERS.AXOLABS + ' ' + TECHNOLOGIES.SI_RNA,
       Nucleotides: siRnaAxolabsToNucleotides(seq),
       BioSpring: siRnaAxolabsToBioSpring(seq),
       Axolabs: seq,
       GCRS: siRnaAxolabsToGcrs(seq)
     };
-  if (isSiRnaGcrsCode(seq))
+  if (output.expectedSynthesizer == SYNTHESIZERS.GCRS && output.expectedTechnology == TECHNOLOGIES.SI_RNA)
     return {
-      type: "siRNA / GCRS Code",
+      type: SYNTHESIZERS.GCRS + ' ' + TECHNOLOGIES.SI_RNA,
       Nucleotides: siRnaGcrsToNucleotides(seq),
       BioSpring: siRnaGcrsToBioSpring(seq),
       Axolabs: siRnaGcrsToAxolabs(seq),
+      MM12: gcrsToMermade12(seq),
       GCRS: seq
     };
-  if (isGcrsCode(seq))
+  if (output.expectedSynthesizer == SYNTHESIZERS.GCRS)
     return {
-      type: "GCRS Code",
+      type: SYNTHESIZERS.GCRS,
       Nucleotides: gcrsToNucleotides(seq),
       GCRS: seq,
-      MM12: gcrsToMM12(seq),
-      OP100: gcrsToOP100(seq),
-      ABI: gcrsToABI(seq)
+      Mermade12: gcrsToMermade12(seq)
     }
-  if (isMM12Code(seq))
-    return {
-      type: "MM12 Code",
-      Nucleotides: noTranslationTableAvailable,
-      GCRS: noTranslationTableAvailable,
-      MM12: seq,
-      OP100: noTranslationTableAvailable,
-      ABI: noTranslationTableAvailable
-    };
-  if (isOP100Code(seq))
+  if (output.expectedSynthesizer == SYNTHESIZERS.MERMADE_12)
     return {
-      type: "OP100 Code",
+      type: SYNTHESIZERS.MERMADE_12,
       Nucleotides: noTranslationTableAvailable,
       GCRS: noTranslationTableAvailable,
-      MM12: noTranslationTableAvailable,
-      OP100: seq,
-      ABI: noTranslationTableAvailable
+      Mermade12: seq
     };
   return {
     type: undefinedInputSequence,
@@ -327,49 +533,49 @@ function convertSequence(seq: string) {
 //name: asoGapmersNucleotidesToBioSpring
 //input: string nucleotides {semType: DNA nucleotides}
 //output: string result {semType: BioSpring / Gapmers}
-export function asoGapmersNucleotidesToBioSpring(nucleotides: string) {
+export function asoGapmersNucleotidesToBioSpring(nucleotides: string): string {
   let count: number = -1;
-  const objForEdges: {[index: string]: string} = {"T": "5*", "A": "6*", "C": "7*", "G": "8*"};
-  const objForCenter: {[index: string]: string} = {"C": "9*", "A": "A*", "T": "T*", "G": "G*"};
-  return nucleotides.replace(/[ATCG]/g, function (x: string) {
+  const objForEdges: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'T': '5*', 'A': '6*', 'C': '7*', 'G': '8*'};
+  const objForCenter: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'T': 'T*', 'A': 'A*', 'C': '9*', 'G': 'G*'};
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|A|T|C|G)/g, function (x: string) {
     count++;
     return (count > 4 && count < 15) ? objForCenter[x] : objForEdges[x];
-  }).slice(0, 2 * count + 1);
+  }).slice(0, (nucleotides.endsWith('(invabasic)') || nucleotides.endsWith('(GalNAc-2-JNJ)')) ? nucleotides.length : 2 * count + 1);
 }
 
 //name: asoGapmersNucleotidesToGcrs
 //input: string nucleotides {semType: DNA nucleotides}
 //output: string result {semType: GCRS / Gapmers}
-export function asoGapmersNucleotidesToGcrs(nucleotides: string) {
+export function asoGapmersNucleotidesToGcrs(nucleotides: string): string {
   let count: number = -1;
-  const objForEdges: {[index: string]: string} = {"T": "moeUnps", "A": "moeAnps", "C": "moe5mCnps", "G": "moeGnps"};
-  const objForCenter: {[index: string]: string} = {"C": "5mCps", "A": "Aps", "T": "Tps", "G": "Gps"};
-  return nucleotides.replace(/[ATCG]/g, function (x: string) {
+  const objForEdges: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'T': 'moeUnps', 'A': 'moeAnps', 'C': 'moe5mCnps', 'G': 'moeGnps'};
+  const objForCenter: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'C': '5mCps', 'A': 'Aps', 'T': 'Tps', 'G': 'Gps'};
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|A|T|C|G)/g, function (x: string) {
     count++;
     if (count < 5) return (count == 4) ? objForEdges[x].slice(0, -3) + 'ps' : objForEdges[x];
     if (count < 15) return (count == 14) ? objForCenter[x].slice(0, -2) + 'nps' : objForCenter[x];
     return objForEdges[x];
-  }).slice(0, -3);
+  }).slice(0, (nucleotides.endsWith('(invabasic)') || nucleotides.endsWith('(GalNAc-2-JNJ)')) ? nucleotides.length : -3);
 }
 
 //name: asoGapmersBioSpringToNucleotides
 //input: string nucleotides {semType: BioSpring / Gapmers}
 //output: string result {semType: DNA nucleotides}
-export function asoGapmersBioSpringToNucleotides(nucleotides: string) {
-  const obj: {[index: string]: string} = {"*": "", "5": "T", "6": "A", "7": "C", "8": "G", "9": "C"};
-  return nucleotides.replace(/[*56789]/g, function (x: string) {return obj[x];});
+export function asoGapmersBioSpringToNucleotides(nucleotides: string): string {
+  const obj: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', '*': '', '5': 'T', '6': 'A', '7': 'C', '8': 'G', '9': 'C'};
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|\*|5|6|7|8|9)/g, function (x: string) {return obj[x];});
 }
 
 //name: asoGapmersBioSpringToGcrs
 //input: string nucleotides {semType: BioSpring / Gapmers}
 //output: string result {semType: GCRS / Gapmers}
-export function asoGapmersBioSpringToGcrs(nucleotides: string) {
+export function asoGapmersBioSpringToGcrs(nucleotides: string): string {
   let count: number = -1;
-  const obj: {[index: string]: string} = {
-    "5*": "moeUnps", "6*": "moeAnps", "7*": "moe5mCnps", "8*": "moeGnps", "9*": "5mCps", "A*": "Aps", "T*": "Tps",
-    "G*": "Gps", "C*": "Cps", "5": "moeU", "6": "moeA", "7": "moe5mC", "8": "moeG"
+  const obj: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)',
+    '5*': 'moeUnps', '6*': 'moeAnps', '7*': 'moe5mCnps', '8*': 'moeGnps', '9*': '5mCps', 'A*': 'Aps', 'T*': 'Tps',
+    'G*': 'Gps', 'C*': 'Cps', '5': 'moeU', '6': 'moeA', '7': 'moe5mC', '8': 'moeG'
   };
-  return nucleotides.replace(/(5\*|6\*|7\*|8\*|9\*|A\*|T\*|G\*|C\*|5|6|7|8)/g, function (x: string) {
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|5\*|6\*|7\*|8\*|9\*|A\*|T\*|G\*|C\*|5|6|7|8)/g, function (x: string) {
     count++;
     return (count == 4) ? obj[x].slice(0, -3) + 'ps' : (count == 14) ? obj[x].slice(0, -2) + 'nps' : obj[x];
   });
@@ -378,103 +584,103 @@ export function asoGapmersBioSpringToGcrs(nucleotides: string) {
 //name: asoGapmersGcrsToBioSpring
 //input: string nucleotides {semType: GCRS / Gapmers}
 //output: string result {semType: BioSpring / Gapmers}
-export function asoGapmersGcrsToBioSpring(nucleotides: string) {
-  const obj: {[index: string]: string} = {
-    "moeT": "5", "moeA": "6", "moe5mC": "7", "moeG": "8", "moeU": "5", "5mC": "9", "nps": "*", "ps": "*", "U": "T"
+export function asoGapmersGcrsToBioSpring(nucleotides: string): string {
+  const obj: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)',
+    'moeT': '5', 'moeA': '6', 'moe5mC': '7', 'moeG': '8', 'moeU': '5', '5mC': '9', 'nps': '*', 'ps': '*', 'U': 'T'
   };
-  return nucleotides.replace(/(moeT|moeA|moe5mC|moeG|moeU|5mC|nps|ps|U)/g, function (x: string) {return obj[x];});
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|moeT|moeA|moe5mC|moeG|moeU|5mC|nps|ps|U)/g, function (x: string) {return obj[x];});
 }
 
 //name: asoGapmersGcrsToNucleotides
 //input: string nucleotides {semType: GCRS / Gapmers}
 //output: string result {semType: DNA nucleotides}
 export function asoGapmersGcrsToNucleotides(nucleotides: string) {
-  const obj: {[index: string]: string} = {"moe": "", "5m": "", "n": "", "ps": "", "U": "T"};
-  return nucleotides.replace(/(moe|5m|n|ps|U)/g, function (x: string) {return obj[x];});
+  const obj: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'moe': '', '5m': '', 'n': '', 'ps': '', 'U': 'T'};
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|moe|5m|n|ps|U)/g, function (x: string) {return obj[x];});
 }
 
 //name: siRnaBioSpringToNucleotides
 //input: string nucleotides {semType: BioSpring / siRNA}
 //output: string result {semType: RNA nucleotides}
 export function siRnaBioSpringToNucleotides(nucleotides: string) {
-  const obj: {[index: string]: string} = {"1": "U", "2": "A", "3": "C", "4": "G", "5": "U", "6": "A", "7": "C", "8": "G", "*": ""};
-  return nucleotides.replace(/[12345678*]/g, function (x: string) {return obj[x];});
+  const obj: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', '1': 'U', '2': 'A', '3': 'C', '4': 'G', '5': 'U', '6': 'A', '7': 'C', '8': 'G', '*': ''};
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|1|2|3|4|5|6|7|8|\*)/g, function (x: string) {return obj[x];});
 }
 
 //name: siRnaBioSpringToAxolabs
 //input: string nucleotides {semType: BioSpring / siRNA}
 //output: string result {semType: Axolabs / siRNA}
 export function siRnaBioSpringToAxolabs(nucleotides: string) {
-  const obj: {[index: string]: string} = {"1": "Uf", "2": "Af", "3": "Cf", "4": "Gf", "5": "u", "6": "a", "7": "c", "8": "g", "*": "s"};
-  return nucleotides.replace(/[12345678*]/g, function (x: string) {return obj[x];});
+  const obj: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', '1': 'Uf', '2': 'Af', '3': 'Cf', '4': 'Gf', '5': 'u', '6': 'a', '7': 'c', '8': 'g', '*': 's'};
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|1|2|3|4|5|6|7|8|\*)/g, function (x: string) {return obj[x];});
 }
 
 //name: siRnaBioSpringToGcrs
 //input: string nucleotides {semType: BioSpring / siRNA}
 //output: string result {semType: GCRS}
 export function siRnaBioSpringToGcrs(nucleotides: string) {
-  const obj: {[index: string]: string} = {"1": "fU", "2": "fA", "3": "fC", "4": "fG", "5": "mU", "6": "mA", "7": "mC", "8": "mG", "*": "ps"};
-  return nucleotides.replace(/[12345678*]/g, function (x: string) {return obj[x];});
+  const obj: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', '1': 'fU', '2': 'fA', '3': 'fC', '4': 'fG', '5': 'mU', '6': 'mA', '7': 'mC', '8': 'mG', '*': 'ps'};
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|1|2|3|4|5|6|7|8|\*)/g, function (x: string) {return obj[x];});
 }
 
 //name: siRnaAxolabsToGcrs
 //input: string nucleotides {semType: Axolabs / siRNA}
 //output: string result {semType: GCRS}
 export function siRnaAxolabsToGcrs(nucleotides: string) {
-  const obj: {[index: string]: string} = {
-    "Uf": "fU", "Af": "fA", "Cf": "fC", "Gf": "fG", "u": "mU", "a": "mA", "c": "mC", "g": "mG", "s": "ps"
+  const obj: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)',
+    'Uf': 'fU', 'Af': 'fA', 'Cf': 'fC', 'Gf': 'fG', 'u': 'mU', 'a': 'mA', 'c': 'mC', 'g': 'mG', 's': 'ps'
   };
-  return nucleotides.replace(/(Uf|Af|Cf|Gf|u|a|c|g|s)/g, function (x: string) {return obj[x];});
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|Uf|Af|Cf|Gf|u|a|c|g|s)/g, function (x: string) {return obj[x];});
 }
 
 //name: siRnaAxolabsToBioSpring
 //input: string nucleotides {semType: Axolabs / siRNA}
 //output: string result {semType: BioSpring / siRNA}
 export function siRnaAxolabsToBioSpring(nucleotides: string) {
-  const obj: {[index: string]: string} = {
-    "Uf": "1", "Af": "2", "Cf": "3", "Gf": "4", "u": "5", "a": "6", "c": "7", "g": "8", "s": "*"
+  const obj: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)',
+    'Uf': '1', 'Af': '2', 'Cf': '3', 'Gf': '4', 'u': '5', 'a': '6', 'c': '7', 'g': '8', 's': '*'
   };
-  return nucleotides.replace(/(Uf|Af|Cf|Gf|u|a|c|g|s)/g, function (x: string) {return obj[x];});
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|Uf|Af|Cf|Gf|u|a|c|g|s)/g, function (x: string) {return obj[x];});
 }
 
 //name: siRnaAxolabsToNucleotides
 //input: string nucleotides {semType: Axolabs / siRNA}
 //output: string result {semType: RNA nucleotides}
 export function siRnaAxolabsToNucleotides(nucleotides: string) {
-  const obj: {[index: string]: string} = {
-    "Uf": "U", "Af": "A", "Cf": "C", "Gf": "G", "u": "U", "a": "A", "c": "C", "g": "G", "s": ""
+  const obj: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)',
+    'Uf': 'U', 'Af': 'A', 'Cf': 'C', 'Gf': 'G', 'u': 'U', 'a': 'A', 'c': 'C', 'g': 'G', 's': ''
   };
-  return nucleotides.replace(/(Uf|Af|Cf|Gf|u|a|c|g|s)/g, function (x: string) {return obj[x];});
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|Uf|Af|Cf|Gf|u|a|c|g|s)/g, function (x: string) {return obj[x];});
 }
 
 //name: siRnaGcrsToNucleotides
 //input: string nucleotides {semType: GCRS}
 //output: string result {semType: RNA nucleotides}
 export function siRnaGcrsToNucleotides(nucleotides: string) {
-  const obj: {[index: string]: string} = {
-    "fU": "U", "fA": "A", "fC": "C", "fG": "G", "mU": "U", "mA": "A", "mC": "C", "mG": "G", "ps": "", "s": ""
+  const obj: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)',
+    'fU': 'U', 'fA': 'A', 'fC': 'C', 'fG': 'G', 'mU': 'U', 'mA': 'A', 'mC': 'C', 'mG': 'G', 'ps': ''
   };
-  return nucleotides.replace(/(fU|fA|fC|fG|mU|mA|mC|mG|ps|s)/g, function (x: string) {return obj[x];});
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|fU|fA|fC|fG|mU|mA|mC|mG|ps)/g, function (x: string) {return obj[x];});
 }
 
 //name: siRnaGcrsToBioSpring
 //input: string nucleotides {semType: GCRS}
 //output: string result {semType: BioSpring / siRNA}
 export function siRnaGcrsToBioSpring(nucleotides: string) {
-  const obj: {[index: string]: string} = {
-    "fU": "1", "fA": "2", "fC": "3", "fG": "4", "mU": "5", "mA": "6", "mC": "7", "mG": "8", "ps": "*"
+  const obj: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)',
+    'fU': '1', 'fA': '2', 'fC': '3', 'fG': '4', 'mU': '5', 'mA': '6', 'mC': '7', 'mG': '8', 'ps': '*'
   };
-  return nucleotides.replace(/(fU|fA|fC|fG|mU|mA|mC|mG|ps)/g, function (x: string) {return obj[x];});
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|fU|fA|fC|fG|mU|mA|mC|mG|ps)/g, function (x: string) {return obj[x];});
 }
 
 //name: siRnaGcrsToAxolabs
 //input: string nucleotides {semType: GCRS}
 //output: string result {semType: Axolabs / siRNA}
 export function siRnaGcrsToAxolabs(nucleotides: string) {
-  const obj: {[index: string]: string} = {
-    "fU": "Uf", "fA": "Af", "fC": "Cf", "fG": "Gf", "mU": "u", "mA": "a", "mC": "c", "mG": "g", "ps": "s"
+  const obj: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)',
+    'fU': 'Uf', 'fA': 'Af', 'fC': 'Cf', 'fG': 'Gf', 'mU': 'u', 'mA': 'a', 'mC': 'c', 'mG': 'g', 'ps': 's'
   };
-  return nucleotides.replace(/(fU|fA|fC|fG|mU|mA|mC|mG|ps)/g, function (x: string) {return obj[x];});
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|fU|fA|fC|fG|mU|mA|mC|mG|ps)/g, function (x: string) {return obj[x];});
 }
 
 //name: siRnaNucleotideToBioSpringSenseStrand
@@ -482,11 +688,11 @@ export function siRnaGcrsToAxolabs(nucleotides: string) {
 //output: string result {semType: BioSpring / siRNA}
 export function siRnaNucleotideToBioSpringSenseStrand(nucleotides: string) {
   let count: number = -1;
-  const objForLeftEdge: {[index: string]: string} = {"A": "6*", "U": "5*", "G": "8*", "C": "7*"};
-  const objForRightEdge: {[index: string]: string} = {"A": "*6", "U": "*5", "G": "*8", "C": "*7"};
-  const objForOddIndices: {[index: string]: string} = {"A": "6", "U": "5", "G": "8", "C": "7"};
-  const objForEvenIndices: {[index: string]: string} = {"A": "2", "U": "1", "G": "4", "C": "3"};
-  return nucleotides.replace(/[AUGC]/g, function (x: string) {
+  const objForLeftEdge: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'A': '6*', 'U': '5*', 'G': '8*', 'C': '7*'};
+  const objForRightEdge: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'A': '*6', 'U': '*5', 'G': '*8', 'C': '*7'};
+  const objForOddIndices: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'A': '6', 'U': '5', 'G': '8', 'C': '7'};
+  const objForEvenIndices: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'A': '2', 'U': '1', 'G': '4', 'C': '3'};
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|A|U|G|C)/g, function (x: string) {
     count++;
     if (count < 2) return objForLeftEdge[x];
     if (count > nucleotides.length - 3) return objForRightEdge[x];
@@ -499,11 +705,11 @@ export function siRnaNucleotideToBioSpringSenseStrand(nucleotides: string) {
 //output: string result {semType: GCRS}
 export function siRnaNucleotidesToGcrs(nucleotides: string) {
   let count: number = -1;
-  const objForLeftEdge: {[index: string]: string} = {"A": "mAps", "U": "mUps", "G": "mGps", "C": "mCps"};
-  const objForRightEdge: {[index: string]: string} = {"A": "psmA", "U": "psmU", "G": "psmG", "C": "psmC"};
-  const objForEvenIndices: {[index: string]: string} = {"A": "fA", "U": "fU", "G": "fG", "C": "fC"};
-  const objForOddIndices: {[index: string]: string} = {"A": "mA", "U": "mU", "G": "mG", "C": "mC"};
-  return nucleotides.replace(/[AUGC]/g, function (x: string) {
+  const objForLeftEdge: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'A': 'mAps', 'U': 'mUps', 'G': 'mGps', 'C': 'mCps'};
+  const objForRightEdge: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'A': 'psmA', 'U': 'psmU', 'G': 'psmG', 'C': 'psmC'};
+  const objForEvenIndices: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'A': 'fA', 'U': 'fU', 'G': 'fG', 'C': 'fC'};
+  const objForOddIndices: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'A': 'mA', 'U': 'mU', 'G': 'mG', 'C': 'mC'};
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|A|U|G|C)/g, function (x: string) {
     count++;
     if (count < 2) return objForLeftEdge[x];
     if (count > nucleotides.length - 3) return objForRightEdge[x];
@@ -516,10 +722,10 @@ export function siRnaNucleotidesToGcrs(nucleotides: string) {
 //output: string result {semType: Axolabs}
 export function siRnaNucleotideToAxolabsSenseStrand(nucleotides: string) {
   let count: number = -1;
-  const objForLeftEdge: {[index: string]: string} = {"A": "as", "U": "us", "G": "gs", "C": "cs"};
-  const objForSomeIndices: {[index: string]: string} = {"A": "Af", "U": "Uf", "G": "Gf", "C": "Cf"};
-  const obj: {[index: string]: string} = {"A": "a", "U": "u", "G": "g", "C": "c"};
-  return nucleotides.replace(/[AUGC]/g, function (x: string) {
+  const objForLeftEdge: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'A': 'as', 'U': 'us', 'G': 'gs', 'C': 'cs'};
+  const objForSomeIndices: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'A': 'Af', 'U': 'Uf', 'G': 'Gf', 'C': 'Cf'};
+  const obj: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'A': 'a', 'U': 'u', 'G': 'g', 'C': 'c'};
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|A|U|G|C)/g, function (x: string) {
     count++;
     if (count < 2) return objForLeftEdge[x];
     if (count == 6 || (count > 7 && count < 11)) return objForSomeIndices[x]
@@ -533,11 +739,11 @@ export function siRnaNucleotideToAxolabsSenseStrand(nucleotides: string) {
 //output: string result {semType: Axolabs}
 export function siRnaNucleotideToAxolabsAntisenseStrand(nucleotides: string) {
   let count: number = -1;
-  const objForSmallLinkages: {[index: string]: string} = {"A": "as", "U": "us", "G": "gs", "C": "cs"};
-  const objForBigLinkages: {[index: string]: string} = {"A": "Afs", "U": "Ufs", "G": "Gfs", "C": "Cfs"};
-  const objForSomeIndices: {[index: string]: string} = {"A": "Af", "U": "Uf", "G": "Gf", "C": "Cf"};
-  const obj: {[index: string]: string} = {"A": "a", "U": "u", "G": "g", "C": "c"};
-  return nucleotides.replace(/[AUGC]/g, function (x: string) {
+  const objForSmallLinkages: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'A': 'as', 'U': 'us', 'G': 'gs', 'C': 'cs'};
+  const objForBigLinkages: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'A': 'Afs', 'U': 'Ufs', 'G': 'Gfs', 'C': 'Cfs'};
+  const objForSomeIndices: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'A': 'Af', 'U': 'Uf', 'G': 'Gf', 'C': 'Cf'};
+  const obj: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)', 'A': 'a', 'U': 'u', 'G': 'g', 'C': 'c'};
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|A|U|G|C)/g, function (x: string) {
     count++;
     if (count > 19 && count < 22) return objForSmallLinkages[x];
     if (count == 0) return 'us';
@@ -550,69 +756,141 @@ export function siRnaNucleotideToAxolabsAntisenseStrand(nucleotides: string) {
 //input: string nucleotides {semType: GCRS}
 //output: string result {semType: RNA nucleotides}
 export function gcrsToNucleotides(nucleotides: string) {
-  const obj: {[index: string]: string} = {
-    "mAps": "A", "mUps": "U", "mGps": "G", "mCps": "C", "fAps": "A", "fUps": "U", "fGps": "G", "fCps": "C",
-    "fU": "U", "fA": "A", "fC": "C", "fG": "G", "mU": "U", "mA": "A", "mC": "C", "mG": "G"
+  const obj: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)',
+    'mAps': 'A', 'mUps': 'U', 'mGps': 'G', 'mCps': 'C', 'fAps': 'A', 'fUps': 'U', 'fGps': 'G', 'fCps': 'C',
+    'fU': 'U', 'fA': 'A', 'fC': 'C', 'fG': 'G', 'mU': 'U', 'mA': 'A', 'mC': 'C', 'mG': 'G'
   };
-  return nucleotides.replace(/(mAps|mUps|mGps|mCps|fAps|fUps|fGps|fCps|fU|fA|fC|fG|mU|mA|mC|mG)/g, function (x: string) {return obj[x];});
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|mAps|mUps|mGps|mCps|fAps|fUps|fGps|fCps|fU|fA|fC|fG|mU|mA|mC|mG)/g, function (x: string) {return obj[x];});
 }
 
-//name: gcrsToOP100
+//name: gcrsToMermade12
 //input: string nucleotides {semType: GCRS}
-//output: string result {semType: OP100}
-export function gcrsToOP100(nucleotides: string) {
-  let count: number = -1;
-  const objForEvenIndicesAtLeftEdge: {[index: string]: string} = {
-    "mAps": "a", "mUps": "u", "mGps": "g", "mCps": "c", "fAps": "a", "fUps": "u", "fGps": "g", "fCps": "c"
-  };
-  const objForOddIndicesAtLeftEdge: {[index: string]: string} = {
-    "mAps": "a*", "mUps": "u*", "mGps": "g*", "mCps": "c*", "fAps": "a*", "fUps": "u*", "fGps": "g*", "fCps": "c*"
-  };
-  // const objForEvenIndicesAtRightEdge: {[index: string]: string} = {
-  //   "fU": "u*", "fA": "a*", "fC": "c*", "fG": "g*", "mU": "u*", "mA": "a*", "mC": "c*", "mG": "g*"
-  // };
-  const objForOddIndicesAtRightEdge: {[index: string]: string} = {
-    "mAps": "a", "mUps": "u", "mGps": "g", "mCps": "c", "fAps": "a", "fUps": "u", "fGps": "g", "fCps": "c"
-  };
-  const objForEvenIndicesAtCenter: {[index: string]: string} = {
-    "fU": "u*", "fA": "a*", "fC": "c*", "fG": "g*", "mU": "u*", "mA": "a*", "mC": "c*", "mG": "g*"
+//output: string result {semType: Mermade 12 / siRNA}
+export function gcrsToMermade12(nucleotides: string) {
+  const obj: {[index: string]: string} = {'(invabasic)': '(invabasic)', '(GalNAc-2-JNJ)': '(GalNAc-2-JNJ)',
+    'mAps': 'e', 'mUps': 'h', 'mGps': 'g', 'mCps': 'f', 'fAps': 'i', 'fUps': 'l', 'fGps': 'k', 'fCps': 'j', 'fU': 'L',
+    'fA': 'I', 'fC': 'J', 'fG': 'K', 'mU': 'H', 'mA': 'E', 'mC': 'F', 'mG': 'G'
   };
-  const objForOddIndicesAtCenter: {[index: string]: string} = {
-    "fU": "u", "fA": "a", "fC": "c", "fG": "g", "mU": "u", "mA": "a", "mC": "c", "mG": "g"
-  };
-  return nucleotides.replace(/(mAps|mUps|mGps|mCps|fAps|fUps|fGps|fCps|fU|fA|fC|fG|mU|mA|mC|mG)/g, function (x: string) {
-    count++;
-    if (count < 3) return (count % 2 == 0) ? objForEvenIndicesAtLeftEdge[x] : objForOddIndicesAtLeftEdge[x];
-    if (count == 19) return objForOddIndicesAtRightEdge[x];
-    return (count % 2 == 1) ? objForEvenIndicesAtCenter[x] : objForOddIndicesAtCenter[x];
-  });
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|mAps|mUps|mGps|mCps|fAps|fUps|fGps|fCps|fU|fA|fC|fG|mU|mA|mC|mG)/g, function (x: string) {return obj[x]});
 }
 
-//name: gcrsToMM12
-//input: string nucleotides {semType: GCRS}
-//output: string result {semType: MM12}
-export function gcrsToMM12(nucleotides: string) {
-  const obj: {[index: string]: string} = {
-    "mAps": "e", "mUps": "h", "mGps": "g", "mCps": "f", "fAps": "i", "fUps": "l", "fGps": "k", "fCps": "j", "fU": "L",
-    "fA": "I", "fC": "J", "fG": "K", "mU": "H", "mA": "E", "mC": "F", "mG": "G"
-  };
-  return nucleotides.replace(/(mAps|mUps|mGps|mCps|fAps|fUps|fGps|fCps|fU|fA|fC|fG|mU|mA|mC|mG)/g, function (x: string) {return obj[x]});
+async function saveTableAsSdFile(table: DG.DataFrame) {
+  if (!table.columns.contains('Compound Name'))
+    grok.shell.warning("File was saved without columns 'Compound Name', 'Compound Components', 'Cpd MW', 'Salt mass', 'Batch MW'!");
+  let structureColumn = table.columns.byName('Sequence');
+  let result = '';
+  for (let i = 0; i < table.rowCount; i++) {
+    try {
+      let smiles = sequenceToSmiles(structureColumn.get(i));
+      //@ts-ignore
+      let mol = new OCL.Molecule.fromSmiles(smiles);
+      result += `\n${mol.toMolfile()}\n`;
+      for (let col of table.columns)
+        result += `>  <${col.name}>\n${col.get(i)}\n\n`;
+      result += '$$$$';
+    }
+    catch (error) {
+      console.error(error);
+    }
+  }
+  let element = document.createElement('a');
+  element.setAttribute('href', 'data:text/plain;charset=utf-8,' + encodeURIComponent(result));
+  element.setAttribute('download', table.name + '.sdf');
+  element.click();
 }
 
-//name: gcrsToABI
-//input: string nucleotides {semType: GCRS}
-//output: string result {semType: ABI}
-export function gcrsToABI(nucleotides: string) {
-  let count: number = -1;
-  const objForEdges: {[index: string]: string} = {"moeA": "5", "(5m)moeC": "6", "moeG": "7", "moeT": "8"};
-  const objForCenter: {[index: string]: string} = {"A": "A", "T": "T", "(5m)C": "C", "G": "G"};
-  return nucleotides.replace(/(moeA|\(5m\)moeC|moeG|moeT|A|T|\(5m\)C|G)/g, function (x: string) {
-    count++;
-    return (5 < count || count < 15) ? objForCenter[x] : objForEdges[x];
+function parseNumber(saltName: string) {
+  let i = saltName.length;
+  while (saltName.length > -1 && saltName[i] != '(')
+    i--;
+  return parseInt(saltName.slice(i + 2));
+}
+
+//tags: autostart
+export function autostartOligoSdFileSubscription() {
+  grok.events.onViewAdded.subscribe((v: any) => {
+    if (v.type == 'TableView' && v.dataFrame.columns.contains('Type'))
+      oligoSdFile(v.dataFrame);
   });
 }
 
-//name: defineAxolabsPattern
-export function _defineAxolabsPattern() {
-  return defineAxolabsPattern();
-}
+let weightsObj: {[code: string]: number} = {};
+for (let synthesizer of Object.keys(map))
+  for (let technology of Object.keys(map[synthesizer]))
+    for (let code of Object.keys(map[synthesizer][technology]))
+      weightsObj[code] = map[synthesizer][technology][code].weight;
+
+function molecularWeight(sequence: string): number {
+  const codes = sortByStringLengthInDescendingOrder(Object.keys(weightsObj));
+  let weight = 0, i = 0;
+  while (i < sequence.length) {
+    let 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;
+}
+
+export function oligoSdFile(table: DG.DataFrame) {
+
+  function addColumns(t: DG.DataFrame) {
+    if (t.columns.contains('Compound Name'))
+      return grok.shell.error('Columns already exist!');
+
+    table.col('Source')?.init('Johnson and Johnson Pharma');
+    table.col('ICD')?.init('No Contract');
+
+    let sequence = t.col('Sequence')!;
+    let salt = t.col('Salt')!;
+    let equivalents = t.col('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) ?
+      sequence.getString(i) + '; duplex of SS: ' + sequence.getString(i - 2) + ' and AS: ' + sequence.getString(i - 1) :
+      sequence.getString(i)
+    );
+    t.columns.addNewFloat('Cpd MW').init((i: number) => ((i + 1) % 3 == 0) ? DG.FLOAT_NULL : molecularWeight(sequence.get(i)));
+    t.columns.addNewFloat('Salt mass').init((i: number) => parseNumber(salt.get(i)) * equivalents.get(i));
+    t.columns.addNewCalculated('Batch MW', '${Cpd MW} + ${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;
+
+  let d = ui.div([
+    ui.icons.edit(() => {
+      d.innerHTML = '';
+      d.append(
+        ui.link('Add Columns', async () => {
+          await addColumns(table);
+          grok.shell.tableView(table.name).grid.columns.setOrder(columnsOrder);
+        }, 'Add columns: Compound Name, Compound Components, Cpd MW, Salt mass, Batch MW', ''),
+        ui.button('Save SD file', () => saveTableAsSdFile(addColumnsPressed ? newDf : table))
+      );
+      let view = grok.shell.getTableView(table.name);
+      let typeCol = view.grid.col('Type')!;
+      let 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, ['Sodium (+1)', 'Sodium (+2)']).root;
+        }
+      });
+
+      table.onDataChanged.subscribe((_) => {
+        if (table.currentCol.name == 'IDP' && typeof table.currentCell.value != 'number')
+          grok.shell.error('Value should be numeric');
+      });
+    })
+  ]);
+  grok.shell.v.setRibbonPanels([[d]]);
+}