@datagrok/sequence-translator 1.0.13 → 1.0.14

package/src/structures-works/const.ts

@@ -0,0 +1,18 @@
+export const MODIFICATIONS: {[index: string]: {molecularWeight: number, left: string, right: string}} = {
+  '(invabasic)': {
+    molecularWeight: 118.13,
+    left: 'O[C@@H]1C[C@@H]O[C@H]1CO',
+    right: 'O[C@@H]1C[C@@H]O[C@H]1CO',
+  },
+  '(GalNAc-2-JNJ)': {
+    molecularWeight: 1273.3,
+    left: 'C(COCCC(=O)NCCCNC(=O)CCCCOC2OC(CO)C(O)C(O)C2NC(=O)C)' +
+    '(COCCC(=O)NCCCNC(=O)CCCCOC2OC(CO)C(O)C(O)C2NC(=O)C)' +
+    '(COCCC(=O)NCCCNC(=O)CCCCOC2OC(CO)C(O)C(O)C2NC(=O)C)NC(=O)CCCC(=O)NCC(O)CO',
+    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 standardPhosphateLinkSmiles = 'OP(=O)(O)O';

package/src/structures-works/converters.ts

@@ -1,6 +1,6 @@
 import {lcmsToGcrs} from './map';
 import * as DG from 'datagrok-api/dg';
-import {delimiter} from './map';
+import {DELIMITER} from './map';
 //name: gcrsToLcms
 //input: string nucleotides {semType: GCRS}
 //output: string result {semType: LCMS}
@@ -10,14 +10,14 @@ export function gcrsToLcms(sequence: string): string {
   const arr2 = df.getCol('LCMS').toList();
   const obj: {[i: string]: string} = {};
   arr1.forEach((element, index) => obj[element] = arr2[index]);
-  obj[delimiter] = delimiter;
+  obj[DELIMITER] = DELIMITER;
   // for (let i = 0; i < arr1.length; i++) {
   //   arr1[i] = arr1[i].replace('(', '\\(');
   //   arr1[i] = arr1[i].replace(')', '\\)');
   // }
   // const regExp = new RegExp('(' + arr1.join('|') + ')', 'g');
   // let r1 = sequence.replace(regExp, function(code) {return obj[code];});
-  const codes = arr1.concat(delimiter).sort(function(a, b) {return b.length - a.length;});
+  const codes = arr1.concat(DELIMITER).sort(function(a, b) {return b.length - a.length;});
   let i = 0;
   let r1 = '';
   while (i < sequence.length) {

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

@@ -1,44 +1,104 @@
-import {map, stadardPhosphateLinkSmiles, SYNTHESIZERS, TECHNOLOGIES, MODIFICATIONS, delimiter} from './map';
+// import {map, SYNTHESIZERS, TECHNOLOGIES, MODIFICATIONS, DELIMITER} from './map';
+import {map, SYNTHESIZERS, TECHNOLOGIES, DELIMITER} from './map';
 import {isValidSequence} from './sequence-codes-tools';
-import {getNucleotidesMol} from './mol-transformations';
 import {sortByStringLengthInDescendingOrder} from '../helpers';
+import {getMonomerWorks} from '../package';
+import {getNucleotidesMol} from './mol-transformations';
 
-export function sequenceToMolV3000(sequence: string, inverted: boolean = false, oclRender: boolean = false,
-  format: string): string {
-  const obj = getObjectWithCodesAndSmiles(sequence, format);
-  let codes = sortByStringLengthInDescendingOrder(Object.keys(obj));
+import {standardPhosphateLinkSmiles, MODIFICATIONS} from './const';
+import {getMonomerLib} from '../package';
+// todo: remove
+// const NAME = 'name';
+const CODES = 'codes';
+// const SMILES = 'smiles';
+const MOL = 'molfile';
+
+export function sequenceToMolV3000(
+  sequence: string, inverted: boolean = false, oclRender: boolean = false,
+  format: string,
+): string {
+  const monomerNameFromCode = getCodeToNameMap(sequence, format);
+  let codes = sortByStringLengthInDescendingOrder(Object.keys(monomerNameFromCode));
   let i = 0;
-  const smilesCodes:string[] = [];
   const codesList = [];
   const links = ['s', 'ps', '*'];
   const includesStandardLinkAlready = ['e', 'h', /*'g',*/ 'f', 'i', 'l', 'k', 'j'];
   const dropdowns = Object.keys(MODIFICATIONS);
-  codes = codes.concat(dropdowns).concat(delimiter);
+  codes = codes.concat(dropdowns).concat(DELIMITER);
   while (i < sequence.length) {
-    const code = codes.find((s: string) => s == sequence.slice(i, i + s.length))!;
+    const code = codes.find((s: string) => s === sequence.slice(i, i + s.length))!;
     i += code.length;
     inverted ? codesList.unshift(code) : codesList.push(code);
   }
+
+  const monomers: string[] = [];
+
   for (let i = 0; i < codesList.length; i++) {
-    if (dropdowns.includes(codesList[i])) {
-      smilesCodes.push((i >= codesList.length / 2) ?
-        MODIFICATIONS[codesList[i]].right : MODIFICATIONS[codesList[i]].left);
-      if (!(i < codesList.length - 1 && links.includes(codesList[i + 1])))
-        smilesCodes.push(stadardPhosphateLinkSmiles);
-    } else {
-      if (links.includes(codesList[i]) ||
-        includesStandardLinkAlready.includes(codesList[i]) ||
-        (i < codesList.length - 1 && links.includes(codesList[i + 1]))
-      )
-        smilesCodes.push(obj[codesList[i]]);
-      else {
-        smilesCodes.push(obj[codesList[i]]);
-        smilesCodes.push(stadardPhosphateLinkSmiles);
-      }
+    if (links.includes(codesList[i]) ||
+      includesStandardLinkAlready.includes(codesList[i]) ||
+      (i < codesList.length - 1 && links.includes(codesList[i + 1]))
+    ) {
+      let aa = monomerNameFromCode[codesList[i]];
+      if(aa !== undefined)
+        monomers.push(aa);
+      else
+        monomers.push(codesList[i]);
+    }
+    else {
+      let aa = monomerNameFromCode[codesList[i]];
+      if(aa !== undefined)
+      monomers.push(aa);
+    else
+      monomers.push(codesList[i]);
+      monomers.push('p linkage');
+    }
+  }
+
+  const lib = getMonomerLib();
+  const mols: string [] = [];
+  for(let i = 0; i < monomers.length; i++) {
+    const mnmr = lib?.getMonomer('RNA', monomers[i]);
+    mols.push(mnmr?.molfile!);
+  }
+
+
+  return getNucleotidesMol(mols);
+  //return getMonomerWorks()?.getAtomicLevel(monomers, 'RNA')!;
+}
+
+export function sequenceToMolV3000_new(
+  sequence: string, inverted: boolean = false, oclRender: boolean = false,
+  format: string,
+): string {
+  const monomerNameFromCode = getCodeToNameMap(sequence, format);
+  let codes = sortByStringLengthInDescendingOrder(Object.keys(monomerNameFromCode));
+  let i = 0;
+  const codesList = [];
+  const links = ['s', 'ps', '*'];
+  const includesStandardLinkAlready = ['e', 'h', /*'g',*/ 'f', 'i', 'l', 'k', 'j'];
+  const dropdowns = Object.keys(MODIFICATIONS);
+  codes = codes.concat(dropdowns).concat(DELIMITER);
+  while (i < sequence.length) {
+    const code = codes.find((s: string) => s === sequence.slice(i, i + s.length))!;
+    i += code.length;
+    inverted ? codesList.unshift(code) : codesList.push(code);
+  }
+
+  const monomers: string[] = [];
+
+  for (let i = 0; i < codesList.length; i++) {
+    if (links.includes(codesList[i]) ||
+      includesStandardLinkAlready.includes(codesList[i]) ||
+      (i < codesList.length - 1 && links.includes(codesList[i + 1]))
+    )
+      monomers.push(monomerNameFromCode[codesList[i]]);
+    else {
+      monomers.push(monomerNameFromCode[codesList[i]]);
+      monomers.push('p linkage');
     }
   }
 
-  return getNucleotidesMol(smilesCodes);
+  return getMonomerWorks()?.getAtomicLevel(monomers, 'RNA')!;
 }
 
 export function sequenceToSmiles(sequence: string, inverted: boolean = false, format: string): string {
@@ -50,7 +110,7 @@ export function sequenceToSmiles(sequence: string, inverted: boolean = false, fo
   const links = ['s', 'ps', '*'];
   const includesStandardLinkAlready = ['e', 'h', /*'g',*/ 'f', 'i', 'l', 'k', 'j'];
   const dropdowns = Object.keys(MODIFICATIONS);
-  codes = codes.concat(dropdowns).concat(delimiter);
+  codes = codes.concat(dropdowns).concat(DELIMITER);
   while (i < sequence.length) {
     const code = codes.find((s: string) => s == sequence.slice(i, i + s.length))!;
     i += code.length;
@@ -59,8 +119,8 @@ export function sequenceToSmiles(sequence: string, inverted: boolean = false, fo
   for (let i = 0; i < codesList.length; i++) {
     if (dropdowns.includes(codesList[i])) {
       smiles += (i >= codesList.length / 2) ?
-        MODIFICATIONS[codesList[i]].right + stadardPhosphateLinkSmiles:
-        MODIFICATIONS[codesList[i]].left + stadardPhosphateLinkSmiles;
+        MODIFICATIONS[codesList[i]].right + standardPhosphateLinkSmiles :
+        MODIFICATIONS[codesList[i]].left + standardPhosphateLinkSmiles;
     } else {
       if (links.includes(codesList[i]) ||
         includesStandardLinkAlready.includes(codesList[i]) ||
@@ -68,7 +128,7 @@ export function sequenceToSmiles(sequence: string, inverted: boolean = false, fo
       )
         smiles += obj[codesList[i]];
       else
-        smiles += obj[codesList[i]] + stadardPhosphateLinkSmiles;
+        smiles += obj[codesList[i]] + standardPhosphateLinkSmiles;
     }
   }
   smiles = smiles.replace(/OO/g, 'O');
@@ -82,7 +142,34 @@ export function sequenceToSmiles(sequence: string, inverted: boolean = false, fo
     includesStandardLinkAlready.includes(codesList[codesList.length - 1])
   ) ?
     smiles :
-    smiles.slice(0, smiles.length - stadardPhosphateLinkSmiles.length + 1);
+    smiles.slice(0, smiles.length - standardPhosphateLinkSmiles.length + 1);
+}
+
+function getCodeToNameMap(sequence: string, format: string) {
+  const obj: { [code: string]: string } = {};
+  const NAME = 'name';
+  if (format == null) {
+    for (const synthesizer of Object.keys(map)) {
+      for (const technology of Object.keys(map[synthesizer])) {
+        for (const code of Object.keys(map[synthesizer][technology]))
+          obj[code] = map[synthesizer][technology][code][NAME]!;
+      }
+    }
+  } else {
+    for (const technology of Object.keys(map[format])) {
+      for (const code of Object.keys(map[format][technology]))
+        obj[code] = map[format][technology][code][NAME]!;
+      // obj[code] = map[format][technology][code].SMILES;
+    }
+  }
+  obj[DELIMITER] = '';
+  // TODO: create object based from synthesizer type to avoid key(codes) duplicates
+  const output = isValidSequence(sequence, format);
+  if (output.synthesizer!.includes(SYNTHESIZERS.MERMADE_12))
+    obj['g'] = map[SYNTHESIZERS.MERMADE_12][TECHNOLOGIES.SI_RNA]['g'][NAME]!;
+  else if (output.synthesizer!.includes(SYNTHESIZERS.AXOLABS))
+    obj['g'] = map[SYNTHESIZERS.AXOLABS][TECHNOLOGIES.SI_RNA]['g'][NAME]!;
+  return obj;
 }
 
 function getObjectWithCodesAndSmiles(sequence: string, format: string) {
@@ -100,7 +187,7 @@ function getObjectWithCodesAndSmiles(sequence: string, format: string) {
         obj[code] = map[format][technology][code].SMILES;
     }
   }
-  obj[delimiter] = '';
+  obj[DELIMITER] = '';
   // TODO: create object based from synthesizer type to avoid key(codes) duplicates
   const output = isValidSequence(sequence, format);
   if (output.synthesizer!.includes(SYNTHESIZERS.MERMADE_12))
@@ -109,3 +196,72 @@ function getObjectWithCodesAndSmiles(sequence: string, format: string) {
     obj['g'] = map[SYNTHESIZERS.AXOLABS][TECHNOLOGIES.SI_RNA]['g'].SMILES;
   return obj;
 }
+
+function getObjectWithCodesAndMolsFromFile(sequence: string, format: string, libFileContent: string) {
+  const obj: { [code: string]: string } = {};
+  // todo: type
+  const lib: any[] = JSON.parse(libFileContent); //consider using library
+
+  for (const item of lib) {
+    for (const synthesizer of Object.keys(item[CODES])) {
+      if (synthesizer === format) {
+        for (const technology of Object.keys(item[CODES][synthesizer])) {
+          const codes = item[CODES][synthesizer][technology];
+          let mol: string = item[MOL];
+          // todo: find another solution
+          mol = mol.replace(/ R /g, ' O ');
+
+          for (const code of codes)
+            obj[code] = mol;
+        }
+      }
+    }
+  }
+
+  obj[DELIMITER] = '';
+  // TODO: create object based on synthesizer type to avoid key(codes) duplicates
+  const output = isValidSequence(sequence, format);
+  if (output.synthesizer!.includes(SYNTHESIZERS.MERMADE_12)) {
+    // todo: remove as quickfix, optimize access to 'g'
+    for (const item of lib) {
+      for (const synthesizer of Object.keys(item[CODES])) {
+        for (const technology of Object.keys(item[CODES][synthesizer])) {
+          const codes = item[CODES][synthesizer][technology];
+          for (const code of codes) {
+            const condition =
+              (code === 'g') &&
+              (synthesizer === SYNTHESIZERS.MERMADE_12) &&
+              (technology === TECHNOLOGIES.SI_RNA);
+            if (condition) {
+              let mol: string = item[MOL];
+              // todo: find another solution
+              mol = mol.replace(/ R /g, ' O ');
+              obj[code] = mol;
+            }
+          }
+        }
+      }
+    }
+  } else if (output.synthesizer!.includes(SYNTHESIZERS.AXOLABS)) {
+    for (const item of lib) {
+      for (const synthesizer of Object.keys(item[CODES])) {
+        for (const technology of Object.keys(item[CODES][synthesizer])) {
+          const codes = item[CODES][synthesizer][technology];
+          for (const code of codes) {
+            const condition =
+              (code === 'g') &&
+              (synthesizer === SYNTHESIZERS.AXOLABS) &&
+              (technology === TECHNOLOGIES.SI_RNA);
+            if (condition) {
+              let mol: string = item[MOL];
+              // todo: find another solution
+              mol = mol.replace(/ R /g, ' O ');
+              obj[code] = mol;
+            }
+          }
+        }
+      }
+    }
+  }
+  return obj;
+}

package/src/structures-works/map.ts

@@ -2,7 +2,8 @@ import * as DG from 'datagrok-api/dg';
 import {getAllCodesOfSynthesizer} from './sequence-codes-tools';
 import {differenceOfTwoArrays} from '../helpers';
 
-export const delimiter = ';';
+export const DELIMITER = ';';
+export const NUCLEOTIDES = ['A', 'G', 'C', 'U', 'T'];
 export const SYNTHESIZERS = {
   RAW_NUCLEOTIDES: 'Raw Nucleotides',
   BIOSPRING: 'BioSpring Codes',
@@ -46,7 +47,7 @@ export const map: {[synthesizer: string]:
             'SMILES': 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)C[C@@H]1O',
           },
           'T': {
-            'name': 'Tyrosine',
+            'name': 'Thymine',
             'weight': 304.2,
             'normalized': 'dT',
             'SMILES': 'OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))C[C@@H]1O',
@@ -148,7 +149,7 @@ export const map: {[synthesizer: string]:
             'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C[C@@H]1O',
           },
           'T': {
-            'name': 'Tyrosine',
+            'name': 'Thymine',
             'weight': 304.2,
             'normalized': 'dT',
             'SMILES': 'OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))C[C@@H]1O',
@@ -362,13 +363,13 @@ export const map: {[synthesizer: string]:
             'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C[C@@H]1O',
           },
           'T': {
-            'name': 'Tyrosine',
+            'name': 'Thymine',
             'weight': 304.2,
             'normalized': 'dT',
             'SMILES': 'OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))C[C@@H]1O',
           },
           'dT': {
-            'name': 'Tyrosine',
+            'name': 'Thymine',
             'weight': 304.2,
             'normalized': 'dT',
             'SMILES': 'OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))C[C@@H]1O',
@@ -550,8 +551,6 @@ export const map: {[synthesizer: string]:
           },
         },
       },
-      // 'LCMS': {
-      //   'For 2\'-OMe and 2\'-F modified siRNA': {
     };
 
 export const lcmsToGcrs = `LCMS, GCRS