@datagrok/sequence-translator 1.0.13 → 1.0.15

package/package.json

@@ -1,10 +1,10 @@
 {
   "name": "@datagrok/sequence-translator",
   "friendlyName": "Sequence Translator",
-  "version": "1.0.13",
+  "version": "1.0.15",
   "author": {
-    "name": "Vadym Kovadlo",
-    "email": "vkovadlo@datagrok.ai"
+    "name": "Alexey Choposky",
+    "email": "achopovsky@datagrok.ai"
   },
   "description": "SequenceTranslator is a [package](https://datagrok.ai/help/develop/develop#packages) for the [Datagrok](https://datagrok.ai) platform, used to translate [oligonucleotide](https://en.wikipedia.org/wiki/Oligonucleotide) sequences between [different representations](https://github.com/datagrok-ai/public/tree/master/packages/SequenceTranslator#sequence-representations).",
   "repository": {
@@ -13,8 +13,9 @@
     "directory": "packages/SequenceTranslator"
   },
   "dependencies": {
-    "@datagrok-libraries/utils": "^1.15.5",
+    "@datagrok-libraries/utils": "^1.17.2",
     "@types/react": "^18.0.15",
+    "@datagrok-libraries/bio": "^5.11.1",
     "datagrok-api": "^1.7.2",
     "datagrok-tools": "^4.1.2",
     "npm": "^8.11.0",
@@ -23,24 +24,6 @@
     "ts-loader": "^9.3.1",
     "typescript": "^4.7.4"
   },
-  "scripts": {
-    "link-api": "npm link datagrok-api",
-    "debug-sequencetranslator": "grok publish",
-    "release-sequencetranslator": "grok publish localhost --release",
-    "build-sequencetranslator": "webpack",
-    "build": "webpack",
-    "debug-sequencetranslator-public": "grok publish public",
-    "release-sequencetranslator-public": "grok publish public --release",
-    "debug-sequencetranslator-local": "grok publish local",
-    "release-sequencetranslator-local": "grok publish local --release",
-    "test": "jest",
-    "test-dev": "set HOST=dev && jest",
-    "test-local": "set HOST=localhost && jest"
-  },
-  "sources": [
-    "css/style.css",
-    "vendors/openchemlib-full.js"
-  ],
   "devDependencies": {
     "@types/jest": "^27.0.0",
     "@types/jquery": "^3.5.14",
@@ -60,5 +43,27 @@
     "@types/node-fetch": "^2.6.2",
     "node-fetch": "^2.6.7"
   },
+  "grokDependencies": {
+    "@datagrok/chem": "1.3.32"
+  },
+  "scripts": {
+    "link-api": "npm link datagrok-api",
+    "link-all": "npm link datagrok-api @datagrok-libraries/utils @datagrok-libraries/bio",
+    "debug-sequencetranslator": "grok publish",
+    "release-sequencetranslator": "grok publish localhost --release",
+    "build-sequencetranslator": "webpack",
+    "build": "webpack",
+    "debug-sequencetranslator-public": "grok publish public",
+    "release-sequencetranslator-public": "grok publish public --release",
+    "debug-sequencetranslator-local": "grok publish local",
+    "release-sequencetranslator-local": "grok publish local --release",
+    "test": "jest",
+    "test-dev": "set HOST=dev && jest",
+    "test-local": "set HOST=localhost && jest"
+  },
+  "sources": [
+    "css/style.css",
+    "vendors/openchemlib-full.js"
+  ],
   "category": "Bioinformatics"
 }

package/scripts/build-monomer-lib.py

@@ -0,0 +1,178 @@
+from io import TextIOWrapper
+
+from rdkit import Chem
+
+import orjson
+
+import click
+
+from click_default_group import DefaultGroup
+from rdkit.Chem.rdchem import Mol
+
+
+def molAddCollection(mol: Mol, name: str, title: str = None) -> str:
+    """
+    Get and postprocess (atom's CFG, title, e.t.c.) molblock
+    :param mol:    Mol molecule structure / object
+    :param name:   Monomer name to add to molblock title
+    :param title:  title to replace in Chem.MolToMolBlock() string output
+    :return:       molblock string
+    """
+    res: str = Chem.MolToMolBlock(mol, forceV3000=True)  # MolToMolFile
+
+    mb_line_list: list[str] = res.split('\n')
+    if title:
+        mb_line_list[1] = title
+
+    if name and name not in mb_line_list[1]:
+        mb_line_list[1] += '|' + name
+
+    end_bond_idx: int = mb_line_list.index('M  V30 END BOND')
+    chirality = [atom.GetChiralTag() for atom in mol.GetAtoms()]
+    begin_atom_idx = mb_line_list.index('M  V30 BEGIN ATOM')
+    end_atom_idx = mb_line_list.index('M  V30 END ATOM')
+    for atom_idx in range(1, end_atom_idx - begin_atom_idx):
+        line_idx = begin_atom_idx + atom_idx
+        atom_ch = chirality[atom_idx - 1]
+        if atom_ch != Chem.rdchem.CHI_UNSPECIFIED:
+            mb_line_list[line_idx] += " CFG={0}".format(int(atom_ch))
+
+    steabs: list[int] = [i + 1 for (i, ch) in enumerate(chirality) if ch != Chem.rdchem.CHI_UNSPECIFIED]
+    if len(steabs) > 0:
+        steabs_str: str = "M  V30 MDLV30/STEABS ATOMS=({count} {list})" \
+            .format(count=len(steabs), list=' '.join([str(idx) for idx in steabs]))
+
+        mb_line_list = mb_line_list[:(end_bond_idx + 1)] + \
+                       ["M  V30 BEGIN COLLECTION", steabs_str, "M  V30 END COLLECTION"] + \
+                       mb_line_list[(end_bond_idx + 1):]
+
+    return '\n'.join(mb_line_list)
+
+
+def molfile2molfile(src_mol: str, name: str) -> str:
+    mol: Mol = Chem.MolFromMolBlock(src_mol)
+    src_mf_lines = src_mol.split('\n')
+    title = src_mf_lines[1]
+    return molAddCollection(mol, name, title=title)
+
+
+def smiles2molfile(smiles: str, name: str) -> str:
+    mol: Mol = Chem.MolFromSmiles(smiles)
+    return molAddCollection(mol, name)
+
+
+CodesType = dict[str, dict[str, list[str]]]
+
+
+class Monomer:
+    def __init__(self,
+                 symbol: str, name: str, molfile: str, smiles: str,
+                 codes: CodesType):
+        self.monomerType = 'Backbone'
+        self.smiles = smiles
+        self.name = name
+        self.author = 'SequenceTranslator'
+        self.molfile = molfile2molfile(molfile, name) if molfile else smiles2molfile(smiles, name)
+        self.naturalAnalog = ''
+        self.rgroups = [
+            {
+                "capGroupSmiles": "O[*:1]",
+                "alternateId": "R1-OH",
+                "capGroupName": "OH",
+                "label": "R1"
+            },
+            {
+                "capGroupSmiles": "O[*:2]",
+                "alternateId": "R2-OH",
+                "capGroupName": "OH",
+                "label": "R2"
+            }]
+        self.createDate = None
+        self.id = 0
+        self.polymerType = 'RNA'
+        self.symbol = symbol
+        self.codes: CodesType = codes
+
+    @staticmethod
+    def from_json(src_json: {}):
+        obj = Monomer(src_json['symbol'], src_json['name'],
+                      src_json['molfile'], src_json['smiles'],
+                      src_json['codes'])
+        return obj
+
+    def to_json(self):
+        return {
+            'monomerType': self.monomerType,
+            'smiles': self.smiles,
+            'name': self.name,
+            'author': self.author,
+            'molfile': self.molfile,
+            'naturalAnalog': self.naturalAnalog,
+            'rgroups': self.rgroups,
+            'createDate': self.createDate,
+            'id': self.id,
+            'polymerType': self.polymerType,
+            'symbol': self.symbol,
+            'codes': self.codes,
+        }
+
+
+def codes2monomers(codes_json: {}) -> dict[str, Monomer]:
+    monomers_res: dict[str, Monomer] = {}
+    for (codes_src, src_dict) in codes_json.items():
+        for (codes_type, monomers_dict) in src_dict.items():
+            for (codes_code, monomer_json) in monomers_dict.items():
+                monomer_name = monomer_json['name']
+                if monomer_name not in monomers_res:
+                    symbol = monomer_json['name']
+                    name = monomer_json['name']
+                    smiles = monomer_json['SMILES']
+                    monomers_res[monomer_name] = Monomer(symbol, name, None, smiles, {})
+                codes = monomers_res[monomer_name].codes
+                if codes_src not in codes:
+                    codes[codes_src] = {}
+                if codes_type not in codes[codes_src]:
+                    codes[codes_src][codes_type] = [];
+                codes[codes_src][codes_type].append(codes_code)
+    return monomers_res
+
+
+@click.group(cls=DefaultGroup, default='main')
+def cli():
+    pass
+
+
+@cli.command()
+@click.pass_context
+@click.option('--initial', 'initial_f',
+              help='Initial monomers source file.',
+              type=click.File('r', 'utf-8'))
+@click.option('--lib', 'lib_f',
+              help='Output library (HELM format) file.',
+              type=click.File('wb', 'utf-8'))
+@click.option('--add', 'add_f_list', multiple=True,
+              help='Additional libraries to build.',
+              type=click.File('r', 'utf-8'))
+def main(ctx, initial_f: TextIOWrapper, lib_f: TextIOWrapper, add_f_list: list[TextIOWrapper]):
+    initial_json_str = initial_f.read()
+
+    initial_json = orjson.loads(initial_json_str)
+
+    monomers: dict[str, Monomer] = codes2monomers(initial_json)
+
+    for add_f in add_f_list:
+        add_json_str = add_f.read()
+        add_json = orjson.loads(add_json_str)
+        for add_m in add_json:
+            m = Monomer.from_json(add_m)
+            monomers[m.name] = m
+
+    add_json = [m.to_json() for m in monomers.values()]
+
+    lib_json_txt = orjson.dumps(add_json, option=orjson.OPT_INDENT_2)
+    lib_f.write(lib_json_txt)
+    k = 11
+
+
+if __name__ == '__main__':
+    cli()

package/setup-unlink-clean.cmd

@@ -0,0 +1,14 @@
+set package_dir=%cd%
+
+set dirs=^
+\..\..\js-api\ ^
+\..\..\libraries\utils\ ^
+\..\..\libraries\bio\ ^
+\
+
+call npm uninstall -g datagrok-api @datagrok-libraries/utils @datagrok-libraries/bio
+
+for %%p in (%dirs%) do cd %package_dir%\%%p & rmdir /s /q node_modules
+for %%p in (%dirs%) do cd %package_dir%\%%p & rmdir /s /q dist
+
+rem for %%p in (%dirs%) do cd %package_dir%\%%p & del "package-lock.json"

package/setup.cmd

@@ -1,11 +1,14 @@
-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
+call setup-unlink-clean.cmd
+
+set package_dir=%cd%
+
+set dirs=^
+\..\..\js-api\ ^
+\..\..\libraries\utils\ ^
+\..\..\libraries\bio\ ^
+\
+
+for %%p in (%dirs%) do cd %package_dir%\%%p & call npm install
+for %%p in (%dirs%) do cd %package_dir%\%%p & call npm link
+for %%p in (%dirs%) do cd %package_dir%\%%p & call npm run link-all
+for %%p in (%dirs%) do cd %package_dir%\%%p & call npm run build

package/setup.sh

@@ -0,0 +1,37 @@
+#!/bin/bash
+
+./setup-unlink-clean.sh
+
+GREEN='\e[0;32m'
+NO_COLOR='\e[0m'
+
+package_dir=$(pwd)
+
+dirs=(
+  "../../js-api/"
+  "../../libraries/utils/"
+  "../../libraries/bio/"
+)
+
+for dir in ${dirs[@]}; do
+  cd $package_dir
+  cd $dir 
+  echo -e $GREEN npm install in $(pwd) $NO_COLOR
+  npm install 
+  echo -e $GREEN npm link in $(pwd) $NO_COLOR
+  npm link
+done
+
+for dir in ${dirs[@]}; do
+  cd $package_dir
+  cd $dir 
+  if [ $dir != "../../js-api/" ]; then
+    echo -e $GREEN npm link-all in $(pwd) $NO_COLOR
+    npm run link-all
+  fi
+  echo -e $GREEN npm run build in$(pwd) $NO_COLOR
+  npm run build || exit
+done
+
+cd $package_dir
+npm run link-all

package/src/autostart/constants.ts

@@ -6,6 +6,18 @@ export const SEQUENCE_TYPES = {
   DIMER: 'Dimer',
 };
 
+export const CELL_STRUCTURE = {
+  DUPLEX: {
+    BEFORE_SS: 'SS ',
+    BEFORE_AS: '\r\nAS ',
+  },
+  TRIPLEX_OR_DIMER: {
+    BEFORE_SS: 'SS ',
+    BEFORE_AS1: '\r\nAS1 ',
+    BEFORE_AS2: '\r\nAS2 ',
+  },
+};
+
 export const COL_NAMES = {
   CHEMISTRY: 'Chemistry',
   NUMBER: 'Number',

package/src/autostart/registration.ts

@@ -4,7 +4,7 @@ import * as DG from 'datagrok-api/dg';
 import {siRnaBioSpringToGcrs, siRnaAxolabsToGcrs, gcrsToNucleotides, asoGapmersBioSpringToGcrs, gcrsToMermade12,
   siRnaNucleotidesToGcrs} from '../structures-works/converters';
 import {weightsObj, SYNTHESIZERS} from '../structures-works/map';
-import {SEQUENCE_TYPES, COL_NAMES, GENERATED_COL_NAMES} from './constants';
+import {SEQUENCE_TYPES, COL_NAMES, GENERATED_COL_NAMES, CELL_STRUCTURE} from './constants';
 import {saltMass, saltMolWeigth, molecularWeight, batchMolWeight} from './calculations';
 import {isValidSequence} from '../structures-works/sequence-codes-tools';
 import {sequenceToMolV3000} from '../structures-works/from-monomers';
@@ -19,13 +19,18 @@ import {IDPS} from './IDPs';
 
 
 function parseStrandsFromDuplexCell(s: string): {SS: string, AS: string} {
-  const arr = s.slice(3).split('\r\nAS ');
+  const arr = s
+    .slice(CELL_STRUCTURE.DUPLEX.BEFORE_SS.length)
+    .split(CELL_STRUCTURE.DUPLEX.BEFORE_AS);
   return {SS: arr[0], AS: arr[1]};
 }
 
 function parseStrandsFromTriplexOrDimerCell(s: string): {SS: string, AS1: string, AS2: string} {
-  const arr1 = s.slice(3).split('\r\nAS1 ');
-  const arr2 = arr1[1].split('\r\nAS2 ');
+  const arr1 = s
+    .slice(CELL_STRUCTURE.TRIPLEX_OR_DIMER.BEFORE_SS.length)
+    .split(CELL_STRUCTURE.TRIPLEX_OR_DIMER.BEFORE_AS1);
+  const arr2 = arr1[1]
+    .split(CELL_STRUCTURE.TRIPLEX_OR_DIMER.BEFORE_AS2);
   return {SS: arr1[0], AS1: arr2[0], AS2: arr2[1]};
 }
 
@@ -249,6 +254,15 @@ export function oligoSdFile(table: DG.DataFrame) {
         if ([COL_NAMES.SALT, COL_NAMES.EQUIVALENTS, COL_NAMES.SALT_MOL_WEIGHT].includes(colName))
           updateCalculatedColumns(view.dataFrame, view.dataFrame.currentRowIdx);
       });
+
+      function updateCalculatedColumns(t: DG.DataFrame, i: number): void {
+        const smValue = saltMass(saltNamesList, molWeightCol, equivalentsCol, i, saltCol);
+        t.getCol(COL_NAMES.SALT_MASS).set(i, smValue, false);
+        const smwValue = saltMolWeigth(saltNamesList, saltCol, molWeightCol, i);
+        t.getCol(COL_NAMES.SALT_MOL_WEIGHT).set(i, smwValue, false);
+        const bmw = batchMolWeight(t.getCol(COL_NAMES.COMPOUND_MOL_WEIGHT), t.getCol(COL_NAMES.SALT_MASS), i);
+        t.getCol(COL_NAMES.BATCH_MOL_WEIGHT).set(i, bmw, false);
+      }
     }),
   ]);
   grok.shell.v.setRibbonPanels([[d]]);

package/src/axolabs/constants.ts

@@ -1,12 +1,12 @@
-const rnaColor = 'rgb(255,230,153)';
-const invAbasicColor = 'rgb(203,119,211)';
-export const axolabsMap:
+const RNA_COLOR = 'rgb(255,230,153)';
+const INVABASIC_COLOR = 'rgb(203,119,211)';
+export const AXOLABS_MAP:
   {[index: string]: {fullName: string, symbols: [string, string, string, string], color: string}} =
 {
   'RNA': {
     fullName: 'RNA nucleotides',
     symbols: ['A', 'C', 'G', 'U'],
-    color: rnaColor,
+    color: RNA_COLOR,
   },
   'DNA': {
     fullName: 'DNA nucleotides',
@@ -44,24 +44,24 @@ export const axolabsMap:
     color: 'rgb(255,192,0)',
   },
   'A': {
-    fullName: 'Adenine',
+    fullName: 'Adenosine',
     symbols: ['a', 'a', 'a', 'a'],
-    color: rnaColor,
+    color: RNA_COLOR,
   },
   'C': {
-    fullName: 'Cytosine',
+    fullName: 'Cytidine',
     symbols: ['c', 'c', 'c', 'c'],
-    color: rnaColor,
+    color: RNA_COLOR,
   },
   'G': {
-    fullName: 'Guanine',
+    fullName: 'Guanosine',
     symbols: ['g', 'g', 'g', 'g'],
-    color: rnaColor,
+    color: RNA_COLOR,
   },
   'U': {
-    fullName: 'Uracil',
+    fullName: 'Uridine',
     symbols: ['u', 'u', 'u', 'u'],
-    color: rnaColor,
+    color: RNA_COLOR,
   },
   'X-New': {
     fullName: '',
@@ -81,7 +81,7 @@ export const axolabsMap:
   'InvAbasic': {
     fullName: 'Inverted abasic capped',
     symbols: ['(invabasic)', '(invabasic)', '(invabasic)', '(invabasic)'],
-    color: invAbasicColor,
+    color: INVABASIC_COLOR,
   },
   "5\"-vinylps": {
     fullName: '5\'-vinylphosphonate-2\'-OMe-uridine',
@@ -91,7 +91,7 @@ export const axolabsMap:
   'InvAbasic(o)': {
     fullName: 'Inverted abasic capped (overhang)',
     symbols: ['(invabasic)', '(invabasic)', '(invabasic)', '(invabasic)'],
-    color: invAbasicColor,
+    color: INVABASIC_COLOR,
   },
   "2\"-OMe-U(o)": {
     fullName: 'Nucleotide Uridine with 2\'O-Methyl protection (overhang)',

package/src/axolabs/define-pattern.ts

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