@datagrok/sequence-translator 0.0.3 → 0.0.4

package/detectors.js

@@ -1,29 +1,35 @@
 class SequenceTranslatorPackageDetectors extends DG.Package {
+  isDnaNucleotides(sequence) {return /^[ATGC]{6,}$/.test(sequence);}
+  isRnaNucleotides(sequence) {return /^[AUGC]{6,}$/.test(sequence);}
+  isAsoGapmerBioSpring(sequence) {return /^[*56789ATGC]{6,}$/.test(sequence);}
+  isAsoGapmerGcrs(sequence) {return /^(?=.*moe)(?=.*5mC)(?=.*ps){6,}/.test(sequence);}
+  isSiRnaBioSpring(sequence) {return /^[*1-8]{6,}$/.test(sequence);}
+  isSiRnaAxolabs(sequence) {return /^[fsACGUacgu]{6,}$/.test(sequence);}
+  isSiRnaGcrs(sequence) {return /^[fmpsACGU]{6,}$/.test(sequence);} // TODO: insert into detectNucleotides
+  isGcrs(sequence) {return /^[fmpsACGU]{6,}$/.test(sequence);}
+  isMermade12(sequence) {return /^[IiJjKkLlEeFfGgHhQq]{6,}$/.test(sequence);}
+
   //tags: semTypeDetector
   //input: column col
   //output: string semType
   detectNucleotides(col) {
     if (col.type === DG.TYPE.STRING) {
-      if (DG.Detector.sampleCategories(col, (s) => /^[ATGC]{10,}$/.test(s)))
+      if (DG.Detector.sampleCategories(col, (s) => isDnaNucleotides(s)))
         return 'DNA nucleotides';
-      if (DG.Detector.sampleCategories(col, (s) => /^[AUGC]{10,}$/.test(s)))
+      if (DG.Detector.sampleCategories(col, (s) => isRnaNucleotides(s)))
         return 'RNA nucleotides';
-      if (DG.Detector.sampleCategories(col, (s) => /^[5678ATGC]{10,}$/.test(s)))
-        return 'ABI';
-      if (DG.Detector.sampleCategories(col, (s) => /^[*56789ATGC]{30,}$/.test(s)))
+      if (DG.Detector.sampleCategories(col, (s) => isAsoGapmerBioSpring(s)))
         return 'BioSpring / Gapmers';
-      if (DG.Detector.sampleCategories(col, (s) => /^(?=.*moe)(?=.*5mC)(?=.*ps){30,}/.test(s)))
+      if (DG.Detector.sampleCategories(col, (s) => isAsoGapmerGcrs(s)))
         return 'GCRS / Gapmers';
-      if (DG.Detector.sampleCategories(col, (s) => /^[*1-8]{30,}$/.test(s)))
+      if (DG.Detector.sampleCategories(col, (s) => isSiRnaBioSpring(s)))
         return 'BioSpring / siRNA';
-      if (DG.Detector.sampleCategories(col, (s) => /^[fsACGUacgu]{20,}$/.test(s)))
-        return 'Axolabs / siRNA';
-      if (DG.Detector.sampleCategories(col, (s) => /^[fmpsACGU]{30,}$/.test(s)))
+      if (DG.Detector.sampleCategories(col, (s) => isSiRnaAxolabs(s)))
+        return 'Axolabs / siRNA';  
+      if (DG.Detector.sampleCategories(col, (s) => isGcrs(s)))
         return 'GCRS';
-      if (DG.Detector.sampleCategories(col, (s) => /^[acgu*]{10,}$/.test(s)))
-        return 'OP100';
-      if (DG.Detector.sampleCategories(col, (s) => /^[IiJjKkLlEeFfGgHhQq]{10,}$/.test(s)))
-        return 'MM12';
+      if (DG.Detector.sampleCategories(col, (s) => isMermade12(s)))
+        return 'Mermade 12 / siRNA';
     }
   }
 }

package/package.json

@@ -1,16 +1,18 @@
 {
   "name": "@datagrok/sequence-translator",
   "friendlyName": "SequenceTranslator",
-  "version": "0.0.3",
+  "version": "0.0.4",
   "description": "",
   "dependencies": {
+    "@datagrok-libraries/utils": "^0.0.23",
     "@types/react": "latest",
     "datagrok-api": ">0.94.10",
     "datagrok-tools": "^4.1.2",
     "npm": "^7.11.2",
     "save-svg-as-png": "^1.4.17",
     "ts-loader": "latest",
-    "typescript": "latest"
+    "typescript": "latest",
+    "openchemlib": "6.0.1"
   },
   "scripts": {
     "link-api": "npm link datagrok-api",
@@ -28,4 +30,4 @@
     "webpack": "^5.31.0",
     "webpack-cli": "^4.6.0"
   }
-}
+}

package/setup.cmd

@@ -0,0 +1,11 @@
+cd ../../js-api
+call npm install
+call npm link
+cd ../libraries/utils
+call npm install
+call npm link
+call npm link datagrok-api
+cd ../../packages/SequenceTranslator
+call npm install
+call npm link datagrok-api @datagrok-libraries/utils
+webpack

package/src/map.ts

@@ -1,7 +1,86 @@
-export const stadardPhosphateLinkSMILES = 'OP(=O)(O)O';
+export const SYNTHESIZERS = {
+  RAW_NUCLEOTIDES: "Raw Nucleotides",
+  BIOSPRING: "BioSpring Codes",
+  GCRS: "Janssen GCRS Codes",
+  AXOLABS: "Axolabs Codes",
+  MERMADE_12: "Mermade 12"
+};
+export const TECHNOLOGIES = {
+  DNA: "DNA",
+  RNA: "RNA",
+  ASO_GAPMERS: "For ASO Gapmers",
+  SI_RNA: "For 2'-OMe and 2'-F modified siRNA"
+};
+// interface CODES {
+// }
+export const MODIFICATIONS: {[index: string]: {left: string, right: string}} = {
+  "(invabasic)": {
+    left: "OC1CCOC1COP(=O)(S[H])O",
+    right: "OP(=O)(S[H])OCC1OCCC1O"
+  },
+  "(GalNAc-2-JNJ)": {
+    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",
+    right: "OCC(O)CNC(=O)CCCC(=O)NC(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)"
+  }
+};
+export const stadardPhosphateLinkSmiles = 'OP(=O)(O)O';
 export const map: {[synthesizer: string]: {[technology: string]: {[code: string]: {"name": string, "weight": number, "normalized": string, "SMILES": string}}}} = {
+  "Raw Nucleotides": {
+    "DNA": {
+      "A": {
+        "name": "Adenine",
+        "weight": 313.21,
+        "normalized": "dA",
+        "SMILES": "OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)C[C@@H]1O"
+      },
+      "T": {
+        "name": "Tyrosine",
+        "weight": 304.2,
+        "normalized": "dT",
+        "SMILES": "OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))C[C@@H]1O"
+      },
+      "G": {
+        "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"
+      },
+      "C": {
+        "name": "Cytosine",
+        "weight": 289.18,
+        "normalized": "dC",
+        "SMILES": "OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))C[C@@H]1O"
+      }
+    },
+    "RNA": {
+      "A": {
+        "name": "Adenine",
+        "weight": 313.21,
+        "normalized": "dA",
+        "SMILES": "OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)C[C@@H]1O"
+      },
+      "U": {
+        "name": "Uracil",
+        "weight": 306.17,
+        "normalized": "rU",
+        "SMILES": "OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](O)[C@@H]1O"
+      },
+      "G": {
+        "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"
+      },
+      "C": {
+        "name": "Cytosine",
+        "weight": 289.18,
+        "normalized": "dC",
+        "SMILES": "OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))C[C@@H]1O"
+      }
+    }
+  },
   "BioSpring Codes": {
-    "For ASO Gapmers": {
+    'For ASO Gapmers': {
       "5": {
         "name": "2'MOE-5Me-rU",
         "weight": 378.27,
@@ -36,7 +115,7 @@ export const map: {[synthesizer: string]: {[technology: string]: {[code: string]
         "name": "ps linkage",
         "weight": 16.07,
         "normalized": "",
-        "SMILES": "OP(=O)(O)S"
+        "SMILES": "OP(=O)(S)O"
       },
       "A": {
         "name": "Adenine",
@@ -116,7 +195,7 @@ export const map: {[synthesizer: string]: {[technology: string]: {[code: string]
         "name": "ps linkage",
         "weight": 16.07,
         "normalized": "",
-        "SMILES": "OP(=O)(O)S"
+        "SMILES": "OP(=O)(S)O"
       }
     }
   },
@@ -174,7 +253,7 @@ export const map: {[synthesizer: string]: {[technology: string]: {[code: string]
         "name": "ps linkage",
         "weight": 16.07,
         "normalized": "",
-        "SMILES": "OP(=O)(O)S"
+        "SMILES": "OP(=O)(S)O"
       }
     }
   },
@@ -226,7 +305,7 @@ export const map: {[synthesizer: string]: {[technology: string]: {[code: string]
         "name": "ps linkage",
         "weight": 16.07,
         "normalized": "",
-        "SMILES": "OP(=O)(O)S"
+        "SMILES": "OP(=O)(S)O"
       },
       "A": {
         "name": "Adenine",
@@ -351,5 +430,105 @@ export const map: {[synthesizer: string]: {[technology: string]: {[code: string]
         "SMILES": "OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OC)[C@@H]1O"
       }
     }
+  },
+  "Mermade 12": {
+    "For 2'-OMe and 2'-F modified siRNA": {
+      "e": {
+        "name": "2'OMe-rA-ps",
+        "weight": 359.31,
+        "normalized": "rA",
+        "SMILES": "OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OC)[C@@H]1OP(=O)(S)O"
+      },
+      "h": {
+        "name": "2'OMe-rU-ps",
+        "weight": 336.27,
+        "normalized": "rU",
+        "SMILES": "OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1OP(=O)(S)O"
+      },
+      "g": {
+        "name": "2'OMe-rG-ps",
+        "weight": 375.31,
+        "normalized": "rG",
+        "SMILES": "OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OC)[C@@H]1OP(=O)(S)O"
+      },
+      "f": {
+        "name": "2'OMe-rC-ps",
+        "weight": 335.28,
+        "normalized": "rC",
+        "SMILES": "OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](OC)[C@@H]1OP(=O)(S)O"
+      },
+      "i": {
+        "name": "2'-fluoro-A-ps",
+        "weight": 347.27,
+        "normalized": "rA",
+        "SMILES": "OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](F)[C@@H]1OP(=O)(S)O"
+      },
+      "l": {
+        "name": "2'-fluoro-U-ps",
+        "weight": 324.23,
+        "normalized": "rU",
+        "SMILES": "OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](F)[C@@H]1OP(=O)(S)O"
+      },
+      "k": {
+        "name": "2'-fluoro-G-ps",
+        "weight": 363.26,
+        "normalized": "rG",
+        "SMILES": "OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](F)[C@@H]1OP(=O)(S)O"
+      },
+      "j": {
+        "name": "2'-fluoro-C-ps",
+        "weight": 323.25,
+        "normalized": "rC",
+        "SMILES": "OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](F)[C@@H]1OP(=O)(S)O"
+      },
+      "L": {
+        "name": "2'-fluoro-U",
+        "weight": 308.16,
+        "normalized": "rU",
+        "SMILES": "OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](F)[C@@H]1O"
+      },
+      "I": {
+        "name": "2'-fluoro-A",
+        "weight": 331.2,
+        "normalized": "rA",
+        "SMILES": "OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](F)[C@@H]1O"
+      },
+      "J": {
+        "name": "2'-fluoro-C",
+        "weight": 307.18,
+        "normalized": "rC",
+        "SMILES": "OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](F)[C@@H]1O"
+      },
+      "K": {
+        "name": "2'-fluoro-G",
+        "weight": 347.19,
+        "normalized": "rG",
+        "SMILES": "OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](F)[C@@H]1O"
+      },
+      "H": {
+        "name": "2'OMe-rU",
+        "weight": 320.2,
+        "normalized": "rU",
+        "SMILES": "OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1O"
+      },
+      "E": {
+        "name": "2'OMe-rA",
+        "weight": 343.24,
+        "normalized": "rA",
+        "SMILES": "OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OC)[C@@H]1O"
+      },
+      "F": {
+        "name": "2'OMe-rC",
+        "weight": 319.21,
+        "normalized": "rC",
+        "SMILES": "OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](OC)[C@@H]1O"
+      },
+      "G": {
+        "name": "2'OMe-rG",
+        "weight": 359.24,
+        "normalized": "rG",
+        "SMILES": "OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OC)[C@@H]1O"
+      }
+    }
   }
 };

package/src/package-test.ts

@@ -0,0 +1,13 @@
+import * as DG from "datagrok-api/dg";
+import * as grok from "datagrok-api/grok";
+import {runTests} from "@datagrok-libraries/utils/src/test";
+import "./tests/smiles-tests";
+
+export let _package = new DG.Package();
+
+//name: test
+//output: dataframe result
+export async function test(): Promise<DG.DataFrame> {
+  let data = await runTests();
+  return DG.DataFrame.fromObjects(data)!;
+}

package/src/package.ts

@@ -5,20 +5,141 @@ import * as DG from 'datagrok-api/dg';
 import * as OCL from 'openchemlib/full.js';
 import $ from "cash-dom";
 import {defineAxolabsPattern} from "./defineAxolabsPattern";
-import {map, stadardPhosphateLinkSMILES} from "./map";
+import {map, stadardPhosphateLinkSmiles, SYNTHESIZERS, TECHNOLOGIES, MODIFICATIONS} from "./map";
 
 export let _package = new DG.Package();
 
 const defaultInput = "AGGTCCTCTTGACTTAGGCC";
-const minimalValidNumberOfCharacters = 6;
-const smallNumberOfCharacters = "Length of input sequence should be at least " + minimalValidNumberOfCharacters + " characters";
 const undefinedInputSequence = "Type of input sequence is undefined";
 const noTranslationTableAvailable = "No translation table available";
 const sequenceWasCopied = 'Copied';
 const tooltipSequence = 'Copy sequence';
 
-function sortByStringLengthInDescendingOrderToCheckForMatchWithLongerCodesFirst(array: string[]): string[] {
-  return array.sort(function(a, b) { return b.length - a.length; });
+function getAllCodesOfSynthesizer(synthesizer: string) {
+  let codes: string[] = [];
+  for (let technology of Object.keys(map[synthesizer]))
+    codes = codes.concat(Object.keys(map[synthesizer][technology]));
+  return codes.concat(Object.keys(MODIFICATIONS));
+}
+
+function getListOfPossibleSynthesizersByFirstMatchedCode(sequence: string): string[] {
+  let 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;
+}
+
+function getListOfPossibleTechnologiesByFirstMatchedCode(sequence: string, synthesizer: string): string[] {
+  let 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;
+}
+
+function isValidSequence(sequence: string) {
+  let possibleSynthesizers = getListOfPossibleSynthesizersByFirstMatchedCode(sequence);
+  if (possibleSynthesizers.length == 0)
+    return { indexOfFirstNotValidCharacter: 0, expectedType: null };
+
+  let outputIndices = Array(possibleSynthesizers.length).fill(0);
+
+  const firstUniqueCharacters = ['r', 'd'], nucleotides = ["A", "U", "T", "C", "G"];
+
+  possibleSynthesizers.forEach((synthesizer, synthesizerIndex) => {
+    let codes = getAllCodesOfSynthesizer(synthesizer);
+    while (outputIndices[synthesizerIndex] < sequence.length) {
+
+      let 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;
+      }
+
+      outputIndices[synthesizerIndex] += matchedCode.length;
+    }
+  });
+
+  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,
+      expectedType: expectedSynthesizer
+    };
+
+  let possibleTechnologies = getListOfPossibleTechnologiesByFirstMatchedCode(sequence, expectedSynthesizer);
+  if (possibleTechnologies.length == 0)
+    return { indexOfFirstNotValidCharacter: 0, expectedRepresentation: null };
+
+  outputIndices = Array(possibleTechnologies.length).fill(0);
+
+  possibleTechnologies.forEach((technology, technologyIndex) => {
+    let codes = Object.keys(map[expectedSynthesizer][technology]);
+    while (outputIndices[technologyIndex] < sequence.length) {
+
+      let matchedCode = codes
+        .find((c) => c == sequence.slice(outputIndices[technologyIndex], outputIndices[technologyIndex] + c.length));
+
+      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;
+    }
+  });
+
+  const indexOfExpectedTechnology = Math.max.apply(Math, outputIndices);
+  const expectedTechnology = possibleTechnologies[outputIndices.indexOf(indexOfExpectedTechnology)];
+
+  return {
+    indexOfFirstNotValidCharacter: indexOfFirstNotValidCharacter,
+    expectedType: expectedSynthesizer + ' ' + expectedTechnology
+  };
+}
+
+function sortByStringLengthInDescendingOrder(array: string[]): string[] {
+  return array.sort(function(a: string, b: string) { return b.length - a.length; });
 }
 
 function getObjectWithCodesAndSmiles() {
@@ -30,22 +151,48 @@ function getObjectWithCodesAndSmiles() {
   return obj;
 }
 
-function modifiedToSmiles(sequence: string) {
+export function sequenceToSmiles(sequence: string) {
   const obj = getObjectWithCodesAndSmiles();
-  const codes = sortByStringLengthInDescendingOrderToCheckForMatchWithLongerCodesFirst(Object.keys(obj));
-  let i = 0,  smiles = '', codesList = [];
+  let codes = sortByStringLengthInDescendingOrder(Object.keys(obj));
+  let i = 0, smiles = '', 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) {
-    let code = codes.find((s) => s == sequence.slice(i, i + s.length))!;
+    let code = codes.find((s: string) => s == sequence.slice(i, i + s.length))!;
     i += code.length;
     codesList.push(code);
   }
-  for (let i = 0; i < codesList.length; i++)
-    smiles += (links.includes(codesList[i]) || (i < codesList.length - 1 && links.includes(codesList[i+1]))) ?
-      obj[codesList[i]] :
-      obj[codesList[i]] + stadardPhosphateLinkSMILES;
-  smiles = smiles.replace(/OO/g, 'O').replace(/SO/g, 'S');
-  return codesList[codesList.length - 1] == 'ps' ? smiles : smiles.slice(0, smiles.length - stadardPhosphateLinkSMILES.length + 1);
+  for (let i = 0; i < codesList.length; i++) {
+    if (dropdowns.includes(codesList[i])) {
+      smiles += (i >= codesList.length / 2) ?
+        MODIFICATIONS[codesList[i]].right :
+        MODIFICATIONS[codesList[i]].left;
+    } else {
+      if (links.includes(codesList[i]) && i > 1 && !includesStandardLinkAlready.includes(codesList[i - 1]))
+        smiles = smiles.slice(0, smiles.length - stadardPhosphateLinkSmiles.length + 1);
+      else if (links.includes(codesList[i]) ||
+        includesStandardLinkAlready.includes(codesList[i]) ||
+        (i < codesList.length - 1 && (links.includes(codesList[i + 1]) || dropdowns.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
@@ -57,71 +204,60 @@ export function sequenceTranslator() {
   windows.showToolbox = false;
   windows.showHelp = false;
 
-  function updateTableAndSVG(sequence: string) {
+  function updateTableAndMolecule(sequence: string) {
     moleculeSvgDiv.innerHTML = "";
     outputTableDiv.innerHTML = "";
-    let outputSequenceObj = convertSequence(sequence);
-    let tableRows = [];
-    for (let key of Object.keys(outputSequenceObj).slice(1)) {
-      //@ts-ignore
-      tableRows.push({'key': key, 'value': ui.link(outputSequenceObj[key], () => navigator.clipboard.writeText(outputSequenceObj[key]).then(() => grok.shell.info(sequenceWasCopied)), tooltipSequence, '')})
-    }
-    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.type == smallNumberOfCharacters)) {
-      let pi = DG.TaskBarProgressIndicator.create('Rendering molecule...');
-      try {
-        let flavor: string = (outputSequenceObj.Nucleotides.includes('U')) ? "RNA_both_caps" : "DNA_both_caps";
-        (async () => {
-          let smiles = (/^[ATGCU]{6,}$/.test(inputSequenceField.value.replace(/\s/g, ''))) ? 
-            await nucleotidesToSmiles(outputSequenceObj.Nucleotides, flavor) :
-            modifiedToSmiles(inputSequenceField.value.replace(/\s/g, '')); 
-          smiles = smiles.replace(/@/g, ''); // Remove StereoChemistry on the Nucleic acid chain and remove the Chiral label
-          moleculeSvgDiv.append(grok.chem.svgMol(smiles, 900, 300));
-        })();
-      } finally {
-        pi.close();
+    let pi = DG.TaskBarProgressIndicator.create('Rendering table and molecule...');
+    try {
+      let outputSequenceObj = convertSequence(sequence);
+      let tableRows = [];
+      for (let key of Object.keys(outputSequenceObj).slice(1)) {
+        tableRows.push({
+          'key': key,
+          'value': ("indexOfFirstNotValidCharacter" in outputSequenceObj) ?
+            ui.divH([
+              ui.divText(sequence.slice(0, JSON.parse(outputSequenceObj.indexOfFirstNotValidCharacter!).indexOfFirstNotValidCharacter), {style: {color: "grey"}}),
+              ui.tooltip.bind(
+                ui.divText(sequence.slice(JSON.parse(outputSequenceObj.indexOfFirstNotValidCharacter!).indexOfFirstNotValidCharacter), {style: {color: "red"}}),
+                "Expected format: " + JSON.parse(outputSequenceObj.indexOfFirstNotValidCharacter!).expectedType + ". Press 'SHOW CODES' button to see tables with valid codes"
+              )
+            ]) : //@ts-ignore
+            ui.link(outputSequenceObj[key], () => navigator.clipboard.writeText(outputSequenceObj[key]).then(() => grok.shell.info(sequenceWasCopied)), tooltipSequence, '')
+        })
       }
+      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;
+
+      let width = $(window).width();
+      const canvas = ui.canvas(width, Math.round(width / 2));
+      let smiles = sequenceToSmiles(inputSequenceField.value.replace(/\s/g, ''));
+      // @ts-ignore
+      OCL.StructureView.drawMolecule(canvas, OCL.Molecule.fromSmiles(smiles), { suppressChiralText: true });
+      if (outputSequenceObj.type != undefinedInputSequence)
+        moleculeSvgDiv.append(canvas);
+    } finally {
+      pi.close();
     }
   }
 
-  const 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 inputSequenceField = ui.textInput("", defaultInput, (sequence: string) => updateTableAndSVG(sequence));
-  let outputSequenceObj = convertSequence(defaultInput);
-  let semTypeOfInputSequence = ui.divText('Detected input type: ' + outputSequenceObj.type);
-
-  let tableRows = [];
-  for (let key of Object.keys(outputSequenceObj).slice(1)) {
-    //@ts-ignore
-    tableRows.push({'key': key, 'value': ui.link(outputSequenceObj[key], () => navigator.clipboard.writeText(outputSequenceObj[key]).then(() => grok.shell.info(sequenceWasCopied)), tooltipSequence, '')})
-  }
+  let semTypeOfInputSequence = ui.divText('');
+  let moleculeSvgDiv = ui.block([]);
   let outputTableDiv = ui.div([], 'table');
-  outputTableDiv.append(
-    DG.HtmlTable.create(tableRows, (item: {key: string; value: string;}) => [item.key, item.value], ['Code', 'Sequence']).root
-  );
+  let inputSequenceField = ui.textInput("", defaultInput, (sequence: string) => updateTableAndMolecule(sequence));
+  updateTableAndMolecule(defaultInput);
 
-  let tables = ui.divV([]);
+  let tablesWithCodes = ui.divV([
+    DG.HtmlTable.create(Object.keys(MODIFICATIONS), (item: string) => [item], ['Overhang modification']).root,
+    ui.div([], {style: {height: '30px'}})
+  ]);
   for (let synthesizer of Object.keys(map)) {
     for (let technology of Object.keys(map[synthesizer])) {
       let tableRows = [];
       for (let [key, value] of Object.entries(map[synthesizer][technology]))
         tableRows.push({'name': value.name, 'code': key});
-      tables.append(
+      tablesWithCodes.append(
         DG.HtmlTable.create(
           tableRows,
           (item: {name: string; code: string;}) => [item['name'], item['code']],
@@ -131,29 +267,31 @@ export function sequenceTranslator() {
       );
     }
   }
-
-  let showCodesButton = ui.button('SHOW CODES', () => ui.dialog('Codes').add(tables).show());
-
-  let moleculeSvgDiv = ui.block([]);
-
-  let flavor: string = (defaultInput.includes('U')) ? "RNA_both_caps" : "DNA_both_caps";
-  (async () => moleculeSvgDiv.append(grok.chem.svgMol(<string> await nucleotidesToSmiles(defaultInput, flavor), 900, 300)))();
-
-  let saveMolFileButton = ui.bigButton('SAVE MOL FILE', async() => {
-    let outputSequenceObj = convertSequence(inputSequenceField.value);
-    flavor = outputSequenceObj.Nucleotides.includes('U') ? "RNA_both_caps" : "DNA_both_caps";
-    let smiles = (/^[ATGCU]{6,}$/.test(inputSequenceField.value.replace(/\s/g, ''))) ? 
-      await nucleotidesToSmiles(outputSequenceObj.Nucleotides, flavor) :
-      modifiedToSmiles(inputSequenceField.value.replace(/\s/g, '')); 
-    smiles = smiles.replace(/@/g, ''); // Remove StereoChemistry on the Nucleic acid chain and remove the Chiral label
-    let mol = OCL.Molecule.fromSmiles(smiles);
-    let result = `${mol.toMolfile()}\n`;// + '$$$$';
-    var element = document.createElement('a');
+  let showCodesButton = ui.button('SHOW CODES', () => ui.dialog('Codes').add(tablesWithCodes).show());
+  let copySmiles = ui.button(
+    'COPY SMILES',
+    () => navigator.clipboard.writeText(sequenceToSmiles(inputSequenceField.value.replace(/\s/g, '')))
+      .then(() => grok.shell.info(sequenceWasCopied))
+  );
+  let saveMolFileButton = ui.bigButton('SAVE MOL FILE', () => {
+    let smiles = sequenceToSmiles(inputSequenceField.value.replace(/\s/g, ''));
+    let result = `${OCL.Molecule.fromSmiles(smiles).toMolfile()}\n`;
+    let 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();
   });
 
+  const 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, Mermade 12 and GCRS representations.'
+  );
+
   let v = grok.shell.newView('Sequence Translator', [
     ui.tabControl({
       'MAIN': ui.div([
@@ -171,7 +309,7 @@ export function sequenceTranslator() {
             outputTableDiv
           ]),
           moleculeSvgDiv,
-          ui.divH([saveMolFileButton, showCodesButton])
+          ui.divH([saveMolFileButton, showCodesButton, copySmiles])
         ], 'sequence')
       ]),
       'AXOLABS': defineAxolabsPattern()
@@ -192,104 +330,83 @@ export function sequenceTranslator() {
     .css('width','100%');
 }
 
-export async function nucleotidesToSmiles(nucleotides: string, flavor: string) {
-  return await grok.functions.call('SequenceTranslator:convertFastaToSmiles', {
-    'sequence_in_fasta_format': nucleotides,
-    'flavor': flavor
-  });
-}
-
-export function isDnaNucleotidesCode(sequence: string) {return /^[ATGC]{6,}$/.test(sequence);}
-export function isRnaNucleotidesCode(sequence: string) {return /^[AUGC]{6,}$/.test(sequence);}
-export function isAsoGapmerBioSpringCode(sequence: string) {return /^[*56789ATGC]{6,}$/.test(sequence);}
-export function isAsoGapmerGcrsCode(sequence: string) {return /^(?=.*moe)(?=.*5mC)(?=.*ps){6,}/.test(sequence);}
-export function isSiRnaBioSpringCode(sequence: string) {return /^[*1-8]{6,}$/.test(sequence);}
-export function isSiRnaAxolabsCode(sequence: string) {return /^[fsACGUacgu]{6,}$/.test(sequence);}
-export function isSiRnaGcrsCode(sequence: string) {return /^[fmpsACGU]{6,}$/.test(sequence);}
-export function isGcrsCode(sequence: string) {return /^[fmpsACGU]{6,}$/.test(sequence);}
-export function isMM12Code(sequence: string) {return /^[IiJjKkLlEeFfGgHhQq]{6,}$/.test(sequence);}
-
-function convertSequence(seq: string) {
-  seq = seq.replace(/\s/g, '');
-  if (seq.length < minimalValidNumberOfCharacters)
+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
+      indexOfFirstNotValidCharacter: JSON.stringify(output),
+      Error: undefinedInputSequence
     };
-  if (isDnaNucleotidesCode(seq))
+  if (output.expectedType == SYNTHESIZERS.RAW_NUCLEOTIDES + ' ' + TECHNOLOGIES.DNA)
     return {
-      type: "DNA Nucleotides Code",
+      type: SYNTHESIZERS.RAW_NUCLEOTIDES + ' ' +  TECHNOLOGIES.DNA,
       Nucleotides: seq,
       BioSpring: asoGapmersNucleotidesToBioSpring(seq),
-      Axolabs: noTranslationTableAvailable,
       GCRS: asoGapmersNucleotidesToGcrs(seq)
     };
-  if (isAsoGapmerBioSpringCode(seq))
+  if (output.expectedType == SYNTHESIZERS.BIOSPRING + ' ' +  TECHNOLOGIES.ASO_GAPMERS)
     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.expectedType == SYNTHESIZERS.GCRS + ' ' +  TECHNOLOGIES.ASO_GAPMERS)
     return {
-      type: "ASO Gapmers / GCRS Code",
+      type: SYNTHESIZERS.GCRS + ' ' +  TECHNOLOGIES.ASO_GAPMERS,
       Nucleotides: asoGapmersGcrsToNucleotides(seq),
       BioSpring: asoGapmersGcrsToBioSpring(seq),
-      Axolabs: noTranslationTableAvailable,
-      MM12: gcrsToMM12(seq),
+      Mermade12: gcrsToMermade12(seq),
       GCRS: seq
     };
-  if (isRnaNucleotidesCode(seq))
+  if (output.expectedType == SYNTHESIZERS.RAW_NUCLEOTIDES + ' ' +  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.expectedType == SYNTHESIZERS.BIOSPRING + ' ' + 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.expectedType == SYNTHESIZERS.AXOLABS + ' ' + 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.expectedType == SYNTHESIZERS.GCRS + ' ' + TECHNOLOGIES.SI_RNA)
     return {
-      type: "siRNA / GCRS Code",
+      type: SYNTHESIZERS.GCRS + ' ' + TECHNOLOGIES.SI_RNA,
       Nucleotides: siRnaGcrsToNucleotides(seq),
       BioSpring: siRnaGcrsToBioSpring(seq),
       Axolabs: siRnaGcrsToAxolabs(seq),
-      MM12: gcrsToMM12(seq), 
+      MM12: gcrsToMermade12(seq),
       GCRS: seq
     };
-  if (isGcrsCode(seq))
+  if (output.expectedType == SYNTHESIZERS.GCRS)
     return {
-      type: "GCRS Code",
+      type: SYNTHESIZERS.GCRS,
       Nucleotides: gcrsToNucleotides(seq),
       GCRS: seq,
-      MM12: gcrsToMM12(seq)
+      Mermade12: gcrsToMermade12(seq)
     }
-  if (isMM12Code(seq))
+  if (output.expectedType == SYNTHESIZERS.MERMADE_12)
     return {
-      type: "MM12 Code",
+      type: SYNTHESIZERS.MERMADE_12,
       Nucleotides: noTranslationTableAvailable,
       GCRS: noTranslationTableAvailable,
-      MM12: seq
+      Mermade12: seq
     };
   return {
     type: undefinedInputSequence,
@@ -302,12 +419,12 @@ function convertSequence(seq: string) {
 //output: string result {semType: BioSpring / Gapmers}
 export function asoGapmersNucleotidesToBioSpring(nucleotides: 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
@@ -315,22 +432,22 @@ export function asoGapmersNucleotidesToBioSpring(nucleotides: string) {
 //output: string result {semType: GCRS / Gapmers}
 export function asoGapmersNucleotidesToGcrs(nucleotides: 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];});
+  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
@@ -338,11 +455,11 @@ export function asoGapmersBioSpringToNucleotides(nucleotides: string) {
 //output: string result {semType: GCRS / Gapmers}
 export function asoGapmersBioSpringToGcrs(nucleotides: string) {
   let count: number = -1;
-  const obj: {[index: string]: string} = {
+  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];
   });
@@ -352,102 +469,102 @@ export function asoGapmersBioSpringToGcrs(nucleotides: string) {
 //input: string nucleotides {semType: GCRS / Gapmers}
 //output: string result {semType: BioSpring / Gapmers}
 export function asoGapmersGcrsToBioSpring(nucleotides: string) {
-  const obj: {[index: 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} = {
+  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} = {
+  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} = {
+  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} = {
+  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)/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} = {
+  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} = {
+  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
@@ -455,11 +572,11 @@ 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];
@@ -472,11 +589,11 @@ 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];
@@ -489,10 +606,10 @@ 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]
@@ -506,11 +623,11 @@ 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';
@@ -523,48 +640,20 @@ 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} = {
+  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];});
-}
-
-//name: gcrsToOP100
-//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 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*"
-  };
-  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
+//name: gcrsToMermade12
 //input: string nucleotides {semType: GCRS}
-//output: string result {semType: MM12}
-export function gcrsToMM12(nucleotides: string) {
-  const obj: {[index: string]: string} = {
+//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"
   };
-  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]});
+}

package/src/tests/smiles-tests.ts

@@ -0,0 +1,13 @@
+import {category, expect, expectFloat, test, testExpectFinish} from "@datagrok-libraries/utils/src/test";
+import * as DG from "datagrok-api/dg";
+import * as grok from "datagrok-api/grok";
+import * as ui from "datagrok-api/ui";
+import {sequenceToSmiles} from '../package'
+
+category('sequence-translator', () => {
+
+  testExpectFinish('ts', async () => {
+    let expected = 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)C[C@@H]1OP(=O)(O)OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OC)[C@@H]1OP(=O)(O)OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OC)[C@@H]1OP(=O)(O)OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))C[C@@H]1OP(=O)(O)OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))C[C@@H]1OP(=O)(O)OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))C[C@@H]1OP(=O)(O)OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))C[C@@H]1OP(=O)(O)OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))C[C@@H]1OP(=O)(O)OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))C[C@@H]1OP(=O)(O)OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))C[C@@H]1OP(=O)(O)OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OC)[C@@H]1OP(=O)(O)OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)C[C@@H]1OP(=O)(O)OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))C[C@@H]1OP(=O)(O)OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))C[C@@H]1OP(=O)(O)OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))C[C@@H]1OP(=O)(O)OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)C[C@@H]1OP(=O)(O)OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OC)[C@@H]1OP(=O)(O)OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OC)[C@@H]1OP(=O)(O)OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))C[C@@H]1OP(=O)(O)OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))C[C@@H]1O';
+    expect(sequenceToSmiles('AGGTCCTCTTGACTTAGGCC'), expected);
+  });
+});

package/webpack.config.js

@@ -1,9 +1,15 @@
 const path = require('path');
+const packageName = path.parse(require('./package.json').name).name.toLowerCase().replace(/-/g, '');
 
 module.exports = {
   mode: 'development',
   entry: {
-    package: './src/package.ts'
+    package: ['./src/package.ts'],
+    test: {
+      filename: 'package-test.js',
+      library: {type: 'var', name: `${packageName}_test`},
+      import: './src/package-test.ts',
+    }
   },
   resolve: {
     extensions: ['.wasm', '.mjs', '.js', '.json', '.ts', '.tsx'],

package/scripts/convertFastaToSmiles

@@ -1,24 +0,0 @@
-#name: convertFastaToSmiles
-#description: Converts FASTA format to smiles
-#language: python
-#tags: demo, chem, rdkit, smiles
-#input: string sequence_in_fasta_format = AGGTCTTCATGACTTCGGCC {semType: nucleotides}
-#input: string flavor = DNA_no_cap {choices: ["Protein_L_amino_acids","Protein_D_amino_acids","RNA_no_cap","RNA_5_cap","RNA_3_cap","RNA_both_caps","DNA_no_cap","DNA_5_cap","DNA_3_cap","DNA_both_caps"]}
-#output: string smiles {semType: Molecule}
-
-from rdkit import Chem
-
-flavors = {
-    "Protein_L_amino_acids": 0,
-    "Protein_D_amino_acids": 1,
-    "RNA_no_cap": 2,
-    "RNA_5_cap": 3,
-    "RNA_3_cap": 4,
-    "RNA_both_caps": 5,
-    "DNA_no_cap": 6,
-    "DNA_5_cap": 7,
-    "DNA_3_cap": 8,
-    "DNA_both_caps": 9
-}
-
-smiles = Chem.MolToSmiles(Chem.MolFromFASTA(text=sequence_in_fasta_format, flavor=flavors[flavor]))

package/scripts/drawAxolabsPattern

@@ -1,50 +0,0 @@
-#name: drawAxolabsPattern
-#language: python
-#input: dataframe ss_df
-#input: dataframe as_df
-#input: string patternName
-#output: graphics pattern
-
-import matplotlib.pyplot as plt
-
-basis_color_dict = {
-    "RNA": 'k',  # black
-    "DNA": 'm',  # magenta
-    "2'-Fluoro": 'b',  # blue
-    "2'-O-Methyl": 'r',  # red
-    "2'-O-MOE": 'c',  # cyan
-    "Glycol nucleic acid": 'y',  # yellow
-    "LNA": 'aquamarine',
-    "Unlocked (UNA)": 'g'  # green
-}
-
-pattern = plt.figure()
-
-max_length = 2 * max(len(ss_df), len(as_df)) + 2.5
-
-for i in range(len(ss_df) - 1, -1, -1):
-    plt.gca().add_patch(plt.Circle(xy=(-2 * i, 3), radius=1, fc=basis_color_dict[ss_df['basis'][i]]))
-    if ss_df['pto'][i]:
-        plt.gca()._add_text(plt.Text(x=-2 * i - 1.25, y=3.25, text="*", color='r', fontsize=20))
-plt.gca()._add_text(plt.Text(x=-2 * len(ss_df) - 0.25, y=2.5, text="5'", fontsize=30))
-plt.gca()._add_text(plt.Text(x=-max_length, y=2.5, text='SS:', fontsize=30))
-plt.gca()._add_text(plt.Text(x=1, y=2.5, text="3'", fontsize=30))
-
-for i in range(len(as_df) - 1, -1, -1):
-    plt.gca().add_patch(plt.Circle(xy=(-2 * i, 0), radius=1, fc=basis_color_dict[as_df['basis'][i]]))
-    if as_df['pto'][i]:
-        plt.gca()._add_text(plt.Text(x=-2 * i - 1.25, y=-1.25, text="*", color='r', fontsize=20))
-plt.gca()._add_text(plt.Text(x=-2 * len(as_df) - 0.25, y=-0.5, text="3'", fontsize=30))
-plt.gca()._add_text(plt.Text(x=-max_length, y=-0.5, text='AS:', fontsize=30))
-plt.gca()._add_text(plt.Text(x=1, y=-0.5, text="5'", fontsize=30))
-
-scaler = -1
-for index, key in enumerate(basis_color_dict):
-    if key in as_df['basis'].unique() or key in ss_df['basis'].unique():
-        scaler += 1
-        plt.gca().add_patch(plt.Circle(xy=(-3 * scaler, -2), radius=0.5, fc=basis_color_dict[key]))
-        plt.gca()._add_text(plt.Text(x=-3 * scaler - 1, y=-4, text=key, fontsize=10))
-
-plt.axis('scaled')
-plt.axis('off')
-plt.title(patternName + ' for ' + str(len(ss_df)) + '/' + str(len(as_df)) + 'mer')