@datagrok/sequence-translator 0.0.8 → 1.0.0

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

@@ -1,3 +1,6 @@
+// import * as grok from 'datagrok-api/grok';
+// import * as ui from 'datagrok-api/ui';
+// import * as DG from 'datagrok-api/dg';
 import {map, SYNTHESIZERS, TECHNOLOGIES, MODIFICATIONS} from './map';
 import {asoGapmersNucleotidesToBioSpring, asoGapmersNucleotidesToGcrs,
   asoGapmersBioSpringToNucleotides, asoGapmersBioSpringToGcrs, asoGapmersGcrsToNucleotides,
@@ -10,98 +13,196 @@ import {asoGapmersNucleotidesToBioSpring, asoGapmersNucleotidesToGcrs,
 const noTranslationTableAvailable = 'No translation table available';
 export const undefinedInputSequence = 'Type of input sequence is undefined';
 
-export function isValidSequence(sequence: string): {
-  indexOfFirstNotValidCharacter: number,
-  expectedSynthesizer: string | null,
-  expectedTechnology: string | null
-} {
+export function getFormat(sequence: string): string | null {
   const possibleSynthesizers = getListOfPossibleSynthesizersByFirstMatchedCode(sequence);
+
+  if (possibleSynthesizers.length == 0)
+    return null;
+
+  let outputIndex = 0;
+
+  const firstUniqueCharacters = ['r', 'd'];
+  const nucleotides = ['A', 'U', 'T', 'C', 'G'];
+
+  possibleSynthesizers.forEach((synthesizer) => {
+    const codes = getAllCodesOfSynthesizer(synthesizer);
+    while (outputIndex < sequence.length) {
+      const matchedCode = codes.find((c) => c == sequence.slice(outputIndex, outputIndex + c.length));
+
+      if (matchedCode == null)
+        break;
+
+      if ( // for mistake pattern 'rAA'
+        outputIndex > 1 &&
+        nucleotides.includes(sequence[outputIndex]) &&
+        firstUniqueCharacters.includes(sequence[outputIndex - 2])
+      ) break;
+
+      if ( // for mistake pattern 'ArA'
+        firstUniqueCharacters.includes(sequence[outputIndex + 1]) &&
+        nucleotides.includes(sequence[outputIndex])
+      ) {
+        outputIndex++;
+        break;
+      }
+
+      outputIndex += matchedCode.length;
+    }
+  });
+
+  const indexOfFirstNotValidChar = (outputIndex == sequence.length) ? -1 : outputIndex;
+  if (indexOfFirstNotValidChar != -1)
+    return possibleSynthesizers[0];
+
+  const possibleTechnologies = getListOfPossibleTechnologiesByFirstMatchedCode(sequence, possibleSynthesizers[0]);
+
+  if (possibleTechnologies.length == 0)
+    return null;
+
+  outputIndex = 0;
+
+  possibleTechnologies.forEach((technology: string) => {
+    const codes = Object.keys(map[possibleSynthesizers[0]][technology]);
+    while (outputIndex < sequence.length) {
+      const matchedCode = codes.find((c) => c == sequence.slice(outputIndex, outputIndex + c.length));
+
+      if (matchedCode == null)
+        break;
+
+      if ( // for mistake pattern 'rAA'
+        outputIndex > 1 &&
+        nucleotides.includes(sequence[outputIndex]) &&
+        firstUniqueCharacters.includes(sequence[outputIndex - 2])
+      ) break;
+
+      if ( // for mistake pattern 'ArA'
+        firstUniqueCharacters.includes(sequence[outputIndex + 1]) &&
+        nucleotides.includes(sequence[outputIndex])
+      ) {
+        outputIndex++;
+        break;
+      }
+
+      outputIndex += matchedCode.length;
+    }
+  });
+
+  return possibleSynthesizers[0];
+}
+
+export function isValidSequence(sequence: string, format: string | null): {
+  indexOfFirstNotValidChar: number,
+  synthesizer: string[] | null,
+  technology: string[] | null
+} {
+  const possibleSynthesizers = format == null ?
+    getListOfPossibleSynthesizersByFirstMatchedCode(sequence) :
+    [format];
+
+  // if (possibleSynthesizers.length > 1) {
+  //   const synthesizer = ui.choiceInput('Choose synthesizer from list: ', possibleSynthesizers[0],
+  //  possibleSynthesizers);
+  //   ui.dialog('Choose Synthesizer')
+  //     .add(ui.panel([synthesizer.root], {style: {fontWeight: 'bold'}}))
+  //     .onOK(() => possibleSynthesizers = [synthesizer.value])
+  //     .onCancel(() => {
+  //       possibleSynthesizers = [possibleSynthesizers[0]];
+  //       grok.shell.warning('Input sequence is expected to be in format ' + possibleSynthesizers[0]);
+  //     })
+  //     .show();
+  // } else if (possibleSynthesizers.length == 0)
   if (possibleSynthesizers.length == 0)
-    return {indexOfFirstNotValidCharacter: 0, expectedSynthesizer: null, expectedTechnology: null};
+    return {indexOfFirstNotValidChar: 0, synthesizer: null, technology: null};
 
-  let outputIndices = Array(possibleSynthesizers.length).fill(0);
+  let outputIndex = 0;
 
   const firstUniqueCharacters = ['r', 'd'];
   const nucleotides = ['A', 'U', 'T', 'C', 'G'];
 
-  possibleSynthesizers.forEach((synthesizer, synthesizerIndex) => {
+  possibleSynthesizers.forEach((synthesizer) => {
     const codes = getAllCodesOfSynthesizer(synthesizer);
-    while (outputIndices[synthesizerIndex] < sequence.length) {
-      const matchedCode = codes
-        .find((c) => c == sequence.slice(outputIndices[synthesizerIndex], outputIndices[synthesizerIndex] + c.length));
+    while (outputIndex < sequence.length) {
+      const matchedCode = codes.find((c) => c == sequence.slice(outputIndex, outputIndex + 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])
+        outputIndex > 1 &&
+        nucleotides.includes(sequence[outputIndex]) &&
+        firstUniqueCharacters.includes(sequence[outputIndex - 2])
       ) break;
 
       if ( // for mistake pattern 'ArA'
-        firstUniqueCharacters.includes(sequence[outputIndices[synthesizerIndex] + 1]) &&
-        nucleotides.includes(sequence[outputIndices[synthesizerIndex]])
+        firstUniqueCharacters.includes(sequence[outputIndex + 1]) &&
+        nucleotides.includes(sequence[outputIndex])
       ) {
-        outputIndices[synthesizerIndex]++;
+        outputIndex++;
         break;
       }
 
-      outputIndices[synthesizerIndex] += matchedCode.length;
+      outputIndex += matchedCode.length;
     }
   });
 
-  const indexOfExpectedSythesizer = Math.max(...outputIndices);
-  const indexOfFirstNotValidCharacter = (indexOfExpectedSythesizer == sequence.length) ? -1 : indexOfExpectedSythesizer;
-  const expectedSynthesizer = possibleSynthesizers[outputIndices.indexOf(indexOfExpectedSythesizer)];
-  if (indexOfFirstNotValidCharacter != -1) {
+  const indexOfFirstNotValidChar = (outputIndex == sequence.length) ? -1 : outputIndex;
+  if (indexOfFirstNotValidChar != -1) {
     return {
-      indexOfFirstNotValidCharacter: indexOfFirstNotValidCharacter,
-      expectedSynthesizer: expectedSynthesizer,
-      expectedTechnology: null,
+      indexOfFirstNotValidChar: indexOfFirstNotValidChar,
+      synthesizer: possibleSynthesizers,
+      technology: null,
     };
   }
 
-  const possibleTechnologies = getListOfPossibleTechnologiesByFirstMatchedCode(sequence, expectedSynthesizer);
+  const possibleTechnologies = getListOfPossibleTechnologiesByFirstMatchedCode(sequence, possibleSynthesizers[0]);
+
+  // if (possibleTechnologies.length > 1) {
+  //   const technology = ui.choiceInput('Choose technology from list: ', possibleTechnologies[0],
+  // possibleTechnologies);
+  //   ui.dialog('Choose Technology')
+  //     .add(ui.panel([technology.root], {style: {fontWeight: 'bold'}}))
+  //     .onOK(() => possibleTechnologies = [technology.value])
+  //     .onCancel(() => {
+  //       possibleTechnologies = [possibleTechnologies[0]];
+  //       grok.shell.warning('Input sequence is expected to be in format ' + possibleTechnologies[0]);
+  //     })
+  //     .show();
+  // } else if (possibleTechnologies.length == 0)
   if (possibleTechnologies.length == 0)
-    return {indexOfFirstNotValidCharacter: 0, expectedSynthesizer: null, expectedTechnology: null};
+    return {indexOfFirstNotValidChar: 0, synthesizer: null, technology: null};
 
-  outputIndices = Array(possibleTechnologies.length).fill(0);
+  outputIndex = 0;
 
-  possibleTechnologies.forEach((technology: string, technologyIndex: number) => {
-    const codes = Object.keys(map[expectedSynthesizer][technology]);
-    while (outputIndices[technologyIndex] < sequence.length) {
-      const matchedCode = codes
-        .find((c) => c == sequence.slice(outputIndices[technologyIndex], outputIndices[technologyIndex] + c.length));
+  possibleTechnologies.forEach((technology: string) => {
+    const codes = Object.keys(map[possibleSynthesizers[0]][technology]);
+    while (outputIndex < sequence.length) {
+      const matchedCode = codes.find((c) => c == sequence.slice(outputIndex, outputIndex + 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])
+        outputIndex > 1 &&
+        nucleotides.includes(sequence[outputIndex]) &&
+        firstUniqueCharacters.includes(sequence[outputIndex - 2])
       ) break;
 
       if ( // for mistake pattern 'ArA'
-        firstUniqueCharacters.includes(sequence[outputIndices[technologyIndex] + 1]) &&
-        nucleotides.includes(sequence[outputIndices[technologyIndex]])
+        firstUniqueCharacters.includes(sequence[outputIndex + 1]) &&
+        nucleotides.includes(sequence[outputIndex])
       ) {
-        outputIndices[technologyIndex]++;
+        outputIndex++;
         break;
       }
 
-      outputIndices[technologyIndex] += matchedCode.length;
+      outputIndex += matchedCode.length;
     }
   });
 
-  const indexOfExpectedTechnology = Math.max(...outputIndices);
-  const expectedTechnology = possibleTechnologies[outputIndices.indexOf(indexOfExpectedTechnology)];
-
   return {
-    indexOfFirstNotValidCharacter: indexOfFirstNotValidCharacter,
-    expectedSynthesizer: expectedSynthesizer,
-    expectedTechnology: expectedTechnology,
+    indexOfFirstNotValidChar: indexOfFirstNotValidChar,
+    synthesizer: possibleSynthesizers,
+    technology: [possibleTechnologies[outputIndex]],
   };
 }
 
@@ -140,93 +241,91 @@ function getListOfPossibleTechnologiesByFirstMatchedCode(sequence: string, synth
   return technologies;
 }
 
-export function convertSequence(text: string) {
-  text = text.replace(/\s/g, '');
-  const seq = text;
-  const output = isValidSequence(seq);
-  if (output.indexOfFirstNotValidCharacter != -1) {
+export function convertSequence(sequence: string, output: {
+  indexOfFirstNotValidChar: number, synthesizer: string[] | null, technology: string[] | null}) {
+  if (output.indexOfFirstNotValidChar != -1) {
     return {
       // type: '',
-      indexOfFirstNotValidCharacter: JSON.stringify(output),
+      indexOfFirstNotValidChar: JSON.stringify(output),
       Error: undefinedInputSequence,
     };
   }
-  if (output.expectedSynthesizer == SYNTHESIZERS.RAW_NUCLEOTIDES && output.expectedTechnology == TECHNOLOGIES.DNA) {
+  if (output.synthesizer!.includes(SYNTHESIZERS.RAW_NUCLEOTIDES)) {//&& output.technology!.includes(TECHNOLOGIES.DNA)) {
     return {
-      type: SYNTHESIZERS.RAW_NUCLEOTIDES + ' ' + TECHNOLOGIES.DNA,
-      Nucleotides: seq,
-      BioSpring: asoGapmersNucleotidesToBioSpring(seq),
-      GCRS: asoGapmersNucleotidesToGcrs(seq),
+      type: SYNTHESIZERS.RAW_NUCLEOTIDES, // + ' ' + TECHNOLOGIES.DNA,
+      Nucleotides: sequence,
+      BioSpring: asoGapmersNucleotidesToBioSpring(sequence),
+      GCRS: asoGapmersNucleotidesToGcrs(sequence),
     };
   }
-  if (output.expectedSynthesizer == SYNTHESIZERS.BIOSPRING && output.expectedTechnology == TECHNOLOGIES.ASO_GAPMERS) {
+  if (output.synthesizer!.includes(SYNTHESIZERS.BIOSPRING) && output.technology!.includes(TECHNOLOGIES.ASO_GAPMERS)) {
     return {
       type: SYNTHESIZERS.BIOSPRING + ' ' + TECHNOLOGIES.ASO_GAPMERS,
-      Nucleotides: asoGapmersBioSpringToNucleotides(seq),
-      BioSpring: seq,
-      GCRS: asoGapmersBioSpringToGcrs(seq),
+      Nucleotides: asoGapmersBioSpringToNucleotides(sequence),
+      BioSpring: sequence,
+      GCRS: asoGapmersBioSpringToGcrs(sequence),
     };
   }
-  if (output.expectedSynthesizer == SYNTHESIZERS.GCRS && output.expectedTechnology == TECHNOLOGIES.ASO_GAPMERS) {
+  if (output.synthesizer!.includes(SYNTHESIZERS.GCRS) && output.technology!.includes(TECHNOLOGIES.ASO_GAPMERS)) {
     return {
       type: SYNTHESIZERS.GCRS + ' ' + TECHNOLOGIES.ASO_GAPMERS,
-      Nucleotides: asoGapmersGcrsToNucleotides(seq),
-      BioSpring: asoGapmersGcrsToBioSpring(seq),
-      Mermade12: gcrsToMermade12(seq),
-      GCRS: seq,
+      Nucleotides: asoGapmersGcrsToNucleotides(sequence),
+      BioSpring: asoGapmersGcrsToBioSpring(sequence),
+      Mermade12: gcrsToMermade12(sequence),
+      GCRS: sequence,
     };
   }
-  if (output.expectedSynthesizer == SYNTHESIZERS.RAW_NUCLEOTIDES && output.expectedTechnology == TECHNOLOGIES.RNA) {
+  if (output.synthesizer!.includes(SYNTHESIZERS.RAW_NUCLEOTIDES) && output.technology!.includes(TECHNOLOGIES.RNA)) {
     return {
       type: SYNTHESIZERS.RAW_NUCLEOTIDES + ' ' + TECHNOLOGIES.RNA,
-      Nucleotides: seq,
-      BioSpring: siRnaNucleotideToBioSpringSenseStrand(seq),
-      Axolabs: siRnaNucleotideToAxolabsSenseStrand(seq),
-      GCRS: siRnaNucleotidesToGcrs(seq),
+      Nucleotides: sequence,
+      BioSpring: siRnaNucleotideToBioSpringSenseStrand(sequence),
+      Axolabs: siRnaNucleotideToAxolabsSenseStrand(sequence),
+      GCRS: siRnaNucleotidesToGcrs(sequence),
     };
   }
-  if (output.expectedSynthesizer == SYNTHESIZERS.BIOSPRING && output.expectedTechnology == TECHNOLOGIES.SI_RNA) {
+  if (output.synthesizer!.includes(SYNTHESIZERS.BIOSPRING) && output.technology!.includes(TECHNOLOGIES.SI_RNA)) {
     return {
       type: SYNTHESIZERS.BIOSPRING + ' ' + TECHNOLOGIES.SI_RNA,
-      Nucleotides: siRnaBioSpringToNucleotides(seq),
-      BioSpring: seq,
-      Axolabs: siRnaBioSpringToAxolabs(seq),
-      GCRS: siRnaBioSpringToGcrs(seq),
+      Nucleotides: siRnaBioSpringToNucleotides(sequence),
+      BioSpring: sequence,
+      Axolabs: siRnaBioSpringToAxolabs(sequence),
+      GCRS: siRnaBioSpringToGcrs(sequence),
     };
   }
-  if (output.expectedSynthesizer == SYNTHESIZERS.AXOLABS && output.expectedTechnology == TECHNOLOGIES.SI_RNA) {
+  if (output.synthesizer!.includes(SYNTHESIZERS.AXOLABS)) {
     return {
       type: SYNTHESIZERS.AXOLABS + ' ' + TECHNOLOGIES.SI_RNA,
-      Nucleotides: siRnaAxolabsToNucleotides(seq),
-      BioSpring: siRnaAxolabsToBioSpring(seq),
-      Axolabs: seq,
-      GCRS: siRnaAxolabsToGcrs(seq),
+      Nucleotides: siRnaAxolabsToNucleotides(sequence),
+      BioSpring: siRnaAxolabsToBioSpring(sequence),
+      Axolabs: sequence,
+      GCRS: siRnaAxolabsToGcrs(sequence),
     };
   }
-  if (output.expectedSynthesizer == SYNTHESIZERS.GCRS && output.expectedTechnology == TECHNOLOGIES.SI_RNA) {
+  if (output.synthesizer!.includes(SYNTHESIZERS.GCRS) && output.technology!.includes(TECHNOLOGIES.SI_RNA)) {
     return {
       type: SYNTHESIZERS.GCRS + ' ' + TECHNOLOGIES.SI_RNA,
-      Nucleotides: siRnaGcrsToNucleotides(seq),
-      BioSpring: siRnaGcrsToBioSpring(seq),
-      Axolabs: siRnaGcrsToAxolabs(seq),
-      MM12: gcrsToMermade12(seq),
-      GCRS: seq,
+      Nucleotides: siRnaGcrsToNucleotides(sequence),
+      BioSpring: siRnaGcrsToBioSpring(sequence),
+      Axolabs: siRnaGcrsToAxolabs(sequence),
+      MM12: gcrsToMermade12(sequence),
+      GCRS: sequence,
     };
   }
-  if (output.expectedSynthesizer == SYNTHESIZERS.GCRS) {
+  if (output.synthesizer!.includes(SYNTHESIZERS.GCRS)) {
     return {
       type: SYNTHESIZERS.GCRS,
-      Nucleotides: gcrsToNucleotides(seq),
-      GCRS: seq,
-      Mermade12: gcrsToMermade12(seq),
+      Nucleotides: gcrsToNucleotides(sequence),
+      GCRS: sequence,
+      Mermade12: gcrsToMermade12(sequence),
     };
   }
-  if (output.expectedSynthesizer == SYNTHESIZERS.MERMADE_12) {
+  if (output.synthesizer!.includes(SYNTHESIZERS.MERMADE_12)) {
     return {
       type: SYNTHESIZERS.MERMADE_12,
       Nucleotides: noTranslationTableAvailable,
       GCRS: noTranslationTableAvailable,
-      Mermade12: seq,
+      Mermade12: sequence,
     };
   }
   return {

package/src/tests/smiles-tests.ts

@@ -1,5 +1,6 @@
 import {category, expect, test} from '@datagrok-libraries/utils/src/test';
 import {sequenceToSmiles} from '../structures-works/from-monomers';
+import {SYNTHESIZERS} from '../structures-works/map';
 
 category('sequence-translator', () => {
   test('AGGTCCTCTTGACTTAGGCC', async () => {
@@ -23,7 +24,7 @@ category('sequence-translator', () => {
     '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);
+    expect(sequenceToSmiles('AGGTCCTCTTGACTTAGGCC', false, SYNTHESIZERS.RAW_NUCLEOTIDES), expected);
   });
 
   test('invabasic/galnac1', async () => {
@@ -34,7 +35,7 @@ category('sequence-translator', () => {
     '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)';
-    expect(sequenceToSmiles('(invabasic)sgg(invabasic)(GalNAc-2-JNJ)'), expected);
+    expect(sequenceToSmiles('(invabasic)sgg(invabasic)(GalNAc-2-JNJ)', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('invabasic/galnac2', async () => {
@@ -45,7 +46,7 @@ category('sequence-translator', () => {
     '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)';
-    expect(sequenceToSmiles('(invabasic)sgsg(invabasic)(GalNAc-2-JNJ)'), expected);
+    expect(sequenceToSmiles('(invabasic)sgsg(invabasic)(GalNAc-2-JNJ)', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('invabasic/galnac3', async () => {
@@ -56,7 +57,7 @@ category('sequence-translator', () => {
     '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)';
-    expect(sequenceToSmiles('(invabasic)sggs(invabasic)(GalNAc-2-JNJ)'), expected);
+    expect(sequenceToSmiles('(invabasic)sggs(invabasic)(GalNAc-2-JNJ)', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('invabasic/galnac4', async () => {
@@ -67,7 +68,7 @@ category('sequence-translator', () => {
     '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)';
-    expect(sequenceToSmiles('(invabasic)sgg(invabasic)s(GalNAc-2-JNJ)'), expected);
+    expect(sequenceToSmiles('(invabasic)sgg(invabasic)s(GalNAc-2-JNJ)', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('usCfCfUfGfAf', async () => {
@@ -77,7 +78,7 @@ category('sequence-translator', () => {
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](F)[C@@H]1OP(=O)(O)' +
     'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](F)[C@@H]1OP(=O)(O)' +
     'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](F)[C@@H]1O';
-    expect(sequenceToSmiles('usCfCfUfGfAf'), expected);
+    expect(sequenceToSmiles('usCfCfUfGfAf', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('usAfsusgsgsg', async () => {
@@ -87,7 +88,7 @@ category('sequence-translator', () => {
     'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OC)[C@@H]1OP(=O)(S)' +
     'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OC)[C@@H]1OP(=O)(S)' +
     'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OC)[C@@H]1O';
-    expect(sequenceToSmiles('usAfsusgsgsg'), expected);
+    expect(sequenceToSmiles('usAfsusgsgsg', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('UfUfUfsCfsuacg', async () => {
@@ -99,7 +100,7 @@ category('sequence-translator', () => {
     'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OC)[C@@H]1OP(=O)(O)' +
     'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[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]1O';
-    expect(sequenceToSmiles('UfUfUfsCfsuacg'), expected);
+    expect(sequenceToSmiles('UfUfUfsCfsuacg', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('susususauasu', async () => {
@@ -110,7 +111,7 @@ category('sequence-translator', () => {
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1OP(=O)(O)' +
     'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OC)[C@@H]1OP(=O)(S)' +
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1O';
-    expect(sequenceToSmiles('susususauasu'), expected);
+    expect(sequenceToSmiles('susususauasu', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('CfGfCfsGfsCf', async () => {
@@ -119,7 +120,7 @@ category('sequence-translator', () => {
     'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](F)[C@@H]1OP(=O)(S)' +
     'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](F)[C@@H]1OP(=O)(S)' +
     'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](F)[C@@H]1O';
-    expect(sequenceToSmiles('CfGfCfsGfsCf'), expected);
+    expect(sequenceToSmiles('CfGfCfsGfsCf', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('acacacsacsac', async () => {
@@ -133,7 +134,7 @@ category('sequence-translator', () => {
     'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](OC)[C@@H]1OP(=O)(S)' +
     'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OC)[C@@H]1OP(=O)(O)' +
     'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](OC)[C@@H]1O';
-    expect(sequenceToSmiles('acacacsacsac'), expected);
+    expect(sequenceToSmiles('acacacsacsac', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('cccgggusug', async () => {
@@ -147,7 +148,7 @@ category('sequence-translator', () => {
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1OP(=O)(S)' +
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[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]1O';
-    expect(sequenceToSmiles('cccgggusug'), expected);
+    expect(sequenceToSmiles('cccgggusug', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('UfAfCfGfGfCfAfUf', async () => {
@@ -160,7 +161,7 @@ category('sequence-translator', () => {
     'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](F)[C@@H]1OP(=O)(O)' +
     'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](F)[C@@H]1OP(=O)(O)' +
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](F)[C@@H]1O';
-    expect(sequenceToSmiles('UfAfCfGfGfCfAfUf'), expected);
+    expect(sequenceToSmiles('UfAfCfGfGfCfAfUf', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('(invabasic)sucuCfuUf', async () => {
@@ -172,7 +173,7 @@ category('sequence-translator', () => {
     'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](F)[C@@H]1OP(=O)(O)' +
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1OP(=O)(O)' +
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](F)[C@@H]1O';
-    expect(sequenceToSmiles('(invabasic)sucuCfuUf'), expected);
+    expect(sequenceToSmiles('(invabasic)sucuCfuUf', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('(invabasic)sAfgcugUf', async () => {
@@ -184,7 +185,7 @@ category('sequence-translator', () => {
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[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(=O)NC2(=O))[C@H](F)[C@@H]1O';
-    expect(sequenceToSmiles('(invabasic)sAfgcugUf'), expected);
+    expect(sequenceToSmiles('(invabasic)sAfgcugUf', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('(invabasic)cuCfuUfsc', async () => {
@@ -196,7 +197,7 @@ category('sequence-translator', () => {
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1OP(=O)(O)' +
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](F)[C@@H]1OP(=O)(S)' +
     'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](OC)[C@@H]1O';
-    expect(sequenceToSmiles('(invabasic)cuCfuUfsc'), expected);
+    expect(sequenceToSmiles('(invabasic)cuCfuUfsc', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('(invabasic)scususu(GalNAc-2-JNJ)', async () => {
@@ -209,7 +210,7 @@ category('sequence-translator', () => {
     '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)';
-    expect(sequenceToSmiles('(invabasic)scususu(GalNAc-2-JNJ)'), expected);
+    expect(sequenceToSmiles('(invabasic)scususu(GalNAc-2-JNJ)', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('(invabasic)usAfsucuCfuUfAfgcugUfgCfacususu', async () => {
@@ -236,7 +237,7 @@ category('sequence-translator', () => {
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1OP(=O)(S)' +
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1OP(=O)(S)' +
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1O';
-    expect(sequenceToSmiles('(invabasic)usAfsucuCfuUfAfgcugUfgCfacususu'), expected);
+    expect(sequenceToSmiles('(invabasic)usAfsucuCfuUfAfgcugUfgCfacususu', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('(invabasic)asacgGfuGfCfAfacucuauuca', async () => {
@@ -261,7 +262,7 @@ category('sequence-translator', () => {
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1OP(=O)(O)' +
     'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](OC)[C@@H]1OP(=O)(O)' +
     'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OC)[C@@H]1O';
-    expect(sequenceToSmiles('(invabasic)asacgGfuGfCfAfacucuauuca'), expected);
+    expect(sequenceToSmiles('(invabasic)asacgGfuGfCfAfacucuauuca', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('(invabasic)scsgguGfcAfAfCfucuauucuga', async () => {
@@ -286,7 +287,7 @@ category('sequence-translator', () => {
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[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](N2C3N=CN=C(N)C=3N=C2)[C@H](OC)[C@@H]1O';
-    expect(sequenceToSmiles('(invabasic)scsgguGfcAfAfCfucuauucuga'), expected);
+    expect(sequenceToSmiles('(invabasic)scsgguGfcAfAfCfucuauucuga', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('(invabasic)scsaacUfcUfAfUfucuggacuua', async () => {
@@ -311,7 +312,7 @@ category('sequence-translator', () => {
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1OP(=O)(O)' +
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1OP(=O)(O)' +
     'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OC)[C@@H]1O';
-    expect(sequenceToSmiles('(invabasic)scsaacUfcUfAfUfucuggacuua'), expected);
+    expect(sequenceToSmiles('(invabasic)scsaacUfcUfAfUfucuggacuua', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('(invabasic)sasacuCfuAfUfUfcuggacuuua', async () => {
@@ -336,7 +337,7 @@ category('sequence-translator', () => {
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1OP(=O)(O)' +
     'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1OP(=O)(O)' +
     'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OC)[C@@H]1O';
-    expect(sequenceToSmiles('(invabasic)sasacuCfuAfUfUfcuggacuuua'), expected);
+    expect(sequenceToSmiles('(invabasic)sasacuCfuAfUfUfcuggacuuua', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('(invabasic)usAfscug(invabasic)(GalNAc-2-JNJ)', async () => {
@@ -350,7 +351,7 @@ category('sequence-translator', () => {
     '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)';
-    expect(sequenceToSmiles('(invabasic)usAfscug(invabasic)(GalNAc-2-JNJ)'), expected);
+    expect(sequenceToSmiles('(invabasic)usAfscug(invabasic)(GalNAc-2-JNJ)', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('(invabasic)sasuaaCfcUf(GalNAc-2-JNJ)', async () => {
@@ -365,7 +366,7 @@ category('sequence-translator', () => {
     '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)';
-    expect(sequenceToSmiles('(invabasic)sasuaaCfcUf(GalNAc-2-JNJ)'), expected);
+    expect(sequenceToSmiles('(invabasic)sasuaaCfcUf(GalNAc-2-JNJ)', false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('(invabasic)sasuaaCfcUfCfUfuguaguuaua(GalNAc-2-JNJ)', async () => {
@@ -392,7 +393,8 @@ category('sequence-translator', () => {
     '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)';
-    expect(sequenceToSmiles('(invabasic)sasuaaCfcUfCfUfuguaguuaua(GalNAc-2-JNJ)'), expected);
+    expect(sequenceToSmiles('(invabasic)sasuaaCfcUfCfUfuguaguuaua(GalNAc-2-JNJ)', false, SYNTHESIZERS.AXOLABS),
+      expected);
   });
 
   test('(invabasic)scsaucacguUfGfCfagccgucuua(invabasic)(GalNAc-2-JNJ)', async () => {
@@ -422,7 +424,8 @@ category('sequence-translator', () => {
     '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)';
-    expect(sequenceToSmiles('(invabasic)scsaucacguUfGfCfagccgucuua(invabasic)(GalNAc-2-JNJ)'), expected);
+    expect(sequenceToSmiles('(invabasic)scsaucacguUfGfCfagccgucuua(invabasic)(GalNAc-2-JNJ)',
+      false, SYNTHESIZERS.AXOLABS), expected);
   });
 
   test('(invabasic)susguuUfgCfCfUfacaucuacua(GalNAc-2-JNJ)', async () => {
@@ -449,6 +452,7 @@ category('sequence-translator', () => {
     '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)';
-    expect(sequenceToSmiles('(invabasic)susguuUfgCfCfUfacaucuacua(GalNAc-2-JNJ)'), expected);
+    expect(sequenceToSmiles('(invabasic)susguuUfgCfCfUfacaucuacua(GalNAc-2-JNJ)', false, SYNTHESIZERS.AXOLABS),
+      expected);
   });
 });

package/src/users.ts

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