@datagrok/sequence-translator 1.0.9 → 1.0.11

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@datagrok/sequence-translator",
   "friendlyName": "Sequence Translator",
-  "version": "1.0.9",
+  "version": "1.0.11",
   "author": {
     "name": "Vadym Kovadlo",
     "email": "vkovadlo@datagrok.ai"
@@ -13,9 +13,9 @@
     "directory": "packages/SequenceTranslator"
   },
   "dependencies": {
-    "@datagrok-libraries/utils": "^1.9.2",
+    "@datagrok-libraries/utils": "^1.11.1",
     "@types/react": "^18.0.15",
-    "datagrok-api": "^1.6.0",
+    "datagrok-api": "^1.7.2",
     "datagrok-tools": "^4.1.2",
     "npm": "^8.11.0",
     "openchemlib": "6.0.1",

package/src/autostart/registration.ts

@@ -1,11 +1,12 @@
 import * as grok from 'datagrok-api/grok';
 import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
-import {siRnaAxolabsToGcrs, gcrsToNucleotides, asoGapmersBioSpringToGcrs, gcrsToMermade12,
-} from '../structures-works/converters';
+import {siRnaBioSpringToGcrs, siRnaAxolabsToGcrs, gcrsToNucleotides, asoGapmersBioSpringToGcrs, gcrsToMermade12,
+  siRnaNucleotidesToGcrs} from '../structures-works/converters';
 import {map, COL_NAMES, MODIFICATIONS} from '../structures-works/map';
 import {isValidSequence} from '../structures-works/sequence-codes-tools';
 import {sequenceToMolV3000} from '../structures-works/from-monomers';
+import {linkV3000} from '../structures-works/mol-transformations';
 
 import {SALTS_CSV} from '../salts';
 import {USERS_CSV} from '../users';
@@ -54,6 +55,10 @@ function molecularWeight(sequence: string, weightsObj: {[index: string]: number}
   return weight - 61.97;
 }
 
+function parseStrandsFromDuplexCell(s: string): string[] {
+  return s.slice(3).split('\r\nAS ');
+}
+
 async function saveTableAsSdFile(table: DG.DataFrame) {
   if (!table.columns.contains('Compound Name')) {
     grok.shell.warning(
@@ -67,9 +72,23 @@ async function saveTableAsSdFile(table: DG.DataFrame) {
   let result = '';
   for (let i = 0; i < table.rowCount; i++) {
     const format = 'Janssen GCRS Codes'; //getFormat(structureColumn.get(i))!;
-    result += (typeColumn.get(i) == 'SS') ?
-      sequenceToMolV3000(structureColumn.get(i), false, true, format) + '\n' + `> <Sequence>\nSense Strand\n\n` :
-      sequenceToMolV3000(structureColumn.get(i), true, true, format) + '\n' + `> <Sequence>\nAnti Sense\n\n`;
+    if (typeColumn.get(i) == 'Duplex') {
+      const array = parseStrandsFromDuplexCell(structureColumn.get(i));
+      const as = sequenceToMolV3000(array[1], true, true, format) +
+      '\n' + `> <Sequence>\nAnti Sense\n\n`;
+      const ss = sequenceToMolV3000(array[0], false, true, format) +
+      '\n' + `> <Sequence>\nSense Strand\n\n`;
+      result += linkV3000([ss, as], true, true) + '\n\n';
+    } else if (typeColumn.get(i) == 'SS') {
+      const molSS = sequenceToMolV3000(structureColumn.get(i), false, true, format) +
+      '\n' + `> <Sequence>\nSense Strand\n\n`;
+      result += molSS;
+    } else if (typeColumn.get(i) == 'AS') {
+      const molAS = sequenceToMolV3000(structureColumn.get(i), true, true, format) +
+        '\n' + `> <Sequence>\nAnti Sense\n\n`;
+      result += molAS;
+    }
+
     for (const col of table.columns) {
       if (col.name != COL_NAMES.SEQUENCE)
         result += `> <${col.name}>\n${col.get(i)}\n\n`;
@@ -90,6 +109,13 @@ export function autostartOligoSdFileSubscription() {
       grok.events.onContextMenu.subscribe((args) => {
         const seqCol = args.args.context.table.currentCol; // /^[fsACGUacgu]{6,}$/
         if (DG.Detector.sampleCategories(seqCol,
+          (s) => /(\(invabasic\)|\(GalNAc-2-JNJ\)|A|U|G|C){6,}$/.test(s))) {
+          args.args.menu.item('Convert raw nucleotides to GCRS', () => {
+            args.args.context.table.columns.addNewString(seqCol.name + ' to GCRS').init((i: number) => {
+              return siRnaNucleotidesToGcrs(seqCol.get(i));
+            });
+          });
+        } else if (DG.Detector.sampleCategories(seqCol,
           (s) => /(\(invabasic\)|\(GalNAc-2-JNJ\)|f|s|A|C|G|U|a|c|g|u){6,}$/.test(s))) {
           args.args.menu.item('Convert Axolabs to GCRS', () => {
             args.args.context.table.columns.addNewString(seqCol.name + ' to GCRS').init((i: number) => {
@@ -121,7 +147,7 @@ export function autostartOligoSdFileSubscription() {
           (s) => /(\(invabasic\)|\(GalNAc-2-JNJ\)|\*|1|2|3|4|5|6|7|8){6,}$/.test(s))) {
           args.args.menu.item('Convert Biospring to GCRS', () => {
             args.args.context.table.columns.addNewString(seqCol.name + ' to GCRS').init((i: number) => {
-              return siRnaAxolabsToGcrs(seqCol.get(i));
+              return siRnaBioSpringToGcrs(seqCol.get(i));
             });
           });
         }
@@ -141,6 +167,7 @@ export function oligoSdFile(table: DG.DataFrame) {
   const saltCol = table.getCol(COL_NAMES.SALT);
   const equivalentsCol = table.getCol(COL_NAMES.EQUIVALENTS);
   const typeColumn = table.getCol(COL_NAMES.TYPE);
+  const chemistryNameCol = table.getCol(COL_NAMES.CHEMISTRY_NAME);
 
   const molWeightCol = saltsDf.getCol('MOLWEIGHT');
   const saltNamesList = saltsDf.getCol('DISPLAY').toList();
@@ -154,12 +181,17 @@ export function oligoSdFile(table: DG.DataFrame) {
         t.rows.removeAt(i, 1, false);
     }
 
-    t.columns.addNewString(COL_NAMES.COMPOUND_NAME).init((i: number) => sequenceCol.get(i));
+    t.columns.addNewString(COL_NAMES.COMPOUND_NAME).init((i: number) => {
+      return (typeColumn.get(i) == 'Duplex') ? chemistryNameCol.get(i) : sequenceCol.get(i);
+    });
 
-    t.columns.addNewString(COL_NAMES.COMPOUND_COMMENTS).init((i: number) => (i > 2 && typeColumn.get(i) == 'Duplex') ?
-      sequenceCol.get(i) + '; duplex of SS: ' + sequenceCol.get(i - 2) + ' and AS: ' + sequenceCol.get(i - 1) :
-      sequenceCol.get(i),
-    );
+    t.columns.addNewString(COL_NAMES.COMPOUND_COMMENTS).init((i: number) => {
+      if (typeColumn.get(i) == 'Duplex') {
+        const arr = parseStrandsFromDuplexCell(sequenceCol.get(i));
+        return chemistryNameCol.get(i) + '; duplex of SS: ' + arr[0] + ' and AS: ' + arr[1];
+      }
+      return sequenceCol.get(i);
+    });
 
     const weightsObj: {[code: string]: number} = {};
     for (const synthesizer of Object.keys(map)) {
@@ -172,6 +204,15 @@ export function oligoSdFile(table: DG.DataFrame) {
       weightsObj[key] = value.molecularWeight;
 
     t.columns.addNewFloat(COL_NAMES.CPD_MW).init((i: number) => {
+      if (typeColumn.get(i) == 'Duplex') {
+        const arr = parseStrandsFromDuplexCell(sequenceCol.get(i));
+        return (
+          isValidSequence(arr[0], null).indexOfFirstNotValidChar == -1 &&
+          isValidSequence(arr[1], null).indexOfFirstNotValidChar == -1
+        ) ?
+          molecularWeight(arr[0], weightsObj) + molecularWeight(arr[1], weightsObj) :
+          DG.FLOAT_NULL;
+      }
       return (isValidSequence(sequenceCol.get(i), null).indexOfFirstNotValidChar == -1) ?
         molecularWeight(sequenceCol.get(i), weightsObj) :
         DG.FLOAT_NULL;

package/src/axolabs/constants.ts

@@ -1,5 +1,5 @@
 const rnaColor = 'rgb(255,230,153)';
-const invAbasicColor = 'rgb(255,230,153)';
+const invAbasicColor = 'rgb(203,119,211)';
 export const axolabsMap:
   {[index: string]: {fullName: string, symbols: [string, string, string, string], color: string}} =
 {

package/src/axolabs/define-pattern.ts

@@ -703,6 +703,7 @@ export function defineAxolabsPattern() {
       grok.shell.v = grok.shell.getTableView(tables.value!.name);
       grok.shell.info(((createAsStrand.value) ? 'Columns were' : 'Column was') +
       ' added to table \'' + tables.value!.name + '\'');
+      updateOutputExamples();
     }
   });
 

package/src/axolabs/draw-svg.ts

@@ -38,8 +38,11 @@ function getTextWidth(text: string, font: number): number {
 function getTextInsideCircle(
   bases: string[], index: number, nucleotideCounter: number,
   numberOfNucleotides: number, enumerateModifications: string[]): string {
-  return (bases[index].slice(-3) == '(o)') || !enumerateModifications.includes(bases[index]) ? '' :
-    ['A', 'G', 'C', 'U', 'T'].includes(bases[index]) ? bases[index] : String(numberOfNucleotides - nucleotideCounter);
+  return ((bases[index].slice(-3) == '(o)') || !enumerateModifications.includes(bases[index])) ?
+    '' :
+    (['A', 'G', 'C', 'U', 'T'].includes(bases[index])) ?
+      bases[index] :
+      '';//String(numberOfNucleotides - nucleotideCounter);
 }
 
 function getFontColorVisibleOnBackground(rgbString: string): string {
@@ -157,6 +160,7 @@ export function drawAxolabsPattern(
     Math.max(xOfSsRightModifications, xOfAsRightModifications) +
       widthOfLeftModification + baseDiameter * (Math.max(ssRightOverhangs, asRightOverhangs));
   const yOfTitle = baseRadius;
+  const yOfNumbers = 2 * baseRadius;
   const yOfSsTexts = 4 * baseRadius;
   const yOfAsTexts = 7 * baseRadius;
   const yOfComment = asExists ? 11 * baseRadius : 8.5 * baseRadius;
@@ -188,14 +192,15 @@ export function drawAxolabsPattern(
   }
   let nucleotideCounter = numberOfSsNucleotides;
   for (let i = ssBases.length - 1; i > -1; i--) {
+    const xOfNumbers = getXOfBaseCircles(i, ssRightOverhangs) +
+      getShiftToAlignNumberInsideCircle(ssBases, ssBases.length - i, numberOfSsNucleotides - nucleotideCounter);
     if (ssBases[i].slice(-3) != '(o)')
       nucleotideCounter--;
     image.append(
+      svg.text(String(numberOfSsNucleotides - nucleotideCounter), xOfNumbers, yOfNumbers, legendFontSize, fontColor),
       svg.circle(getXOfBaseCircles(i, ssRightOverhangs), yOfSsCircles, baseRadius, getBaseColor(ssBases[i])),
       svg.text(getTextInsideCircle(ssBases, i, nucleotideCounter, numberOfSsNucleotides, enumerateModifications),
-        getXOfBaseCircles(i, ssRightOverhangs) +
-        getShiftToAlignNumberInsideCircle(ssBases, ssBases.length - i, numberOfSsNucleotides - nucleotideCounter),
-        yOfSsTexts, baseFontSize, getFontColorVisibleOnBackground(axolabsMap[ssBases[i]]['color'])),
+        xOfNumbers, yOfSsTexts, baseFontSize, getFontColorVisibleOnBackground(axolabsMap[ssBases[i]]['color'])),
       ssPtoStatuses[i] ?
         svg.star(getXOfBaseCircles(i, ssRightOverhangs) + baseRadius, yOfSsTexts + psLinkageRadius, psLinkageColor) :
         '',

package/src/main/main-view.ts

@@ -19,8 +19,7 @@ export function mainView() {
     try {
       sequence = sequence.replace(/\s/g, '');
       const output = isValidSequence(sequence, null);
-      output.synthesizer = [inputFormat];
-      // inputFormatChoiceInput.value = output.synthesizer![0];
+      inputFormatChoiceInput.value = output.synthesizer![0];
       const outputSequenceObj = convertSequence(sequence, output);
       const tableRows = [];
 

package/src/package-test.ts

@@ -1,13 +1,16 @@
 import * as DG from 'datagrok-api/dg';
-import {runTests, tests} from '@datagrok-libraries/utils/src/test';
+import {runTests, tests, TestContext} from '@datagrok-libraries/utils/src/test';
 import './tests/smiles-tests';
 
 export const _package = new DG.Package();
 export {tests};
 
 //name: test
+//input: string category {optional: true}
+//input: string test {optional: true}
+//input: object testContext {optional: true}
 //output: dataframe result
-export async function test(): Promise<DG.DataFrame> {
-  const data = await runTests();
+export async function test(category: string, test: string, testContext: TestContext): Promise<DG.DataFrame> {
+  const data = await runTests({category, test, testContext});
   return DG.DataFrame.fromObjects(data)!;
 }

package/src/structures-works/converters.ts

@@ -96,9 +96,10 @@ export function asoGapmersBioSpringToGcrs(nucleotides: string): string {
 //output: string result {semType: BioSpring / Gapmers}
 export function asoGapmersGcrsToBioSpring(nucleotides: 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',
     'moeT': '5', 'moeA': '6', 'moe5mC': '7', 'moeG': '8', 'moeU': '5', '5mC': '9', 'nps': '*', 'ps': '*', 'U': 'T',
   };
-  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|moeT|moeA|moe5mC|moeG|moeU|5mC|nps|ps|U)/g,
+  return nucleotides.replace(/(\(invabasic\)|\(GalNAc-2-JNJ\)|fU|fA|fC|fG|mU|mA|mC|mG|moeT|moeA|moe5mC|moeG|moeU|5mC|nps|ps|U)/g,
     function(x: string) {return obj[x];});
 }