@datagrok/bio 1.5.10 → 1.6.0

package/files/samples/sample_FASTA.csv

@@ -63,4 +63,3 @@ UPI0001614A89,37,A0A0A8VBX4; A0A0H3NXY0; A0A0G2N6K7.1 (obsolete); A0A0M1V224.1 (
 UPI000169E485,35,A0A153KQI0.1 (obsolete); A0A1J0NK41.1 (obsolete); A0A1V2DF85.1 (obsolete); K7QCB5.1 (obsolete),MHERFLRENRRSPSRVGGAIDAMPAGCGGMVVIGM,-1.5044359483896845
 UPI000169FCE1,39,A0A656IDX3; A0A6C7A0R4; C0Q053; E8XEF8; G5LRF0; G5NFQ1; M7RCS7; A0A021WPB8.1 (obsolete); A0A068IN21.1 (obsolete); A0A068PK03.1 (obsolete); A0A077YJZ3.1 (obsolete); A0A078P440.1 (obsolete); A0A078PGS7.1 (obsolete); A0A080YVC6.1 (obsolete); A0A098GTT7.1 (obsolete); A0A0A8SUG6.1 (obsolete); A0A0B7QMT4.1 (obsolete); A0A0B7QXI3.1 (obsolete); A0A0B7QYQ1.1 (obsolete); A0A0B7RM41.1 (obsolete); A0A0B7RSH2.1 (obsolete); A0A0B7RYE2.1 (obsolete); A0A0B7SSM9.1 (obsolete); A0A0B7STM0.1 (obsolete); A0A0B7T296.1 (obsolete); A0A0B7TX24.1 (obsolete); A0A0B7U1H7.1 (obsolete); A0A0B7U264.1 (obsolete); A0A0B7UC41.1 (obsolete); A0A0B7UME8.1 (obsolete); A0A0B7V6B1.1 (obsolete); A0A0B7VLT0.1 (obsolete); A0A0B7VRU2.1 (obsolete); A0A0B7W472.1 (obsolete); A0A0B7W5J9.1 (obsolete); A0A0B7WUQ0.1 (obsolete); A0A0B8K7B9.1 (obsolete); A0A0C5TXP2.1 (obsolete); A0A0E1Q441.1 (obsolete); A0A0E2MH47.1 (obsolete); A0A0F6DRT0.1 (obsolete); A0A0G2LKZ8.1 (obsolete); A0A0G2NQ03.1 (obsolete); A0A0H3RKU6.1 (obsolete); A0A0N2BI82.1 (obsolete); A0A0N2BNW2.1 (obsolete); A0A0S2WD32.1 (obsolete); A0A1M3ZBY0.1 (obsolete); A0A1M3ZIA1.1 (obsolete); A0A1M4A4L9.1 (obsolete); A0A1M4A739.1 (obsolete); A0A1W2L8M5.1 (obsolete); A0A221AY29.1 (obsolete); A0A486X7G3.1 (obsolete); A0A518UNK4.1 (obsolete); A0A5E4DW86.1 (obsolete); B5C6Q5.1 (obsolete); B5FPF5.1 (obsolete); B5MIR4.1 (obsolete); B5N1F1.1 (obsolete); E7V3X0.1 (obsolete); E8NPX9.1 (obsolete); F2FBP0.1 (obsolete); F2FSL8.1 (obsolete); G5MZY4.1 (obsolete); G7T2W4.1 (obsolete); J1I084.1 (obsolete); J1IMV6.1 (obsolete); J1J8I1.1 (obsolete); J1KGX6.1 (obsolete); J1L3A6.1 (obsolete); J1L833.1 (obsolete); J1LPB8.1 (obsolete); J1NKU7.1 (obsolete); J1PPY6.1 (obsolete); J1S5B6.1 (obsolete); J1VRL7.1 (obsolete); J1WIA4.1 (obsolete); J1WZQ3.1 (obsolete); J2AWK9.1 (obsolete); J2B6K2.1 (obsolete); J2DH55.1 (obsolete); J2DI78.1 (obsolete); J2ENS4.1 (obsolete); J2FR89.1 (obsolete); J2HHJ4.1 (obsolete); J2I9P0.1 (obsolete); K8S348.1 (obsolete); K8S5C1.1 (obsolete); K8S896.1 (obsolete); K8T7U3.1 (obsolete); K8TAY6.1 (obsolete); K8TJL1.1 (obsolete); K8UBJ3.1 (obsolete); K8ULX9.1 (obsolete); K8V3L9.1 (obsolete); K8VAJ8.1 (obsolete); K8VPG1.1 (obsolete); L5W4S4.1 (obsolete); L5WC19.1 (obsolete); L5WHP1.1 (obsolete); L5WP78.1 (obsolete); L5X276.1 (obsolete); L5XDS4.1 (obsolete); L5YA20.1 (obsolete); L5YPV3.1 (obsolete); L5YVT4.1 (obsolete); L5ZH95.1 (obsolete); L5ZKS5.1 (obsolete); L6A2S2.1 (obsolete); L6A7R6.1 (obsolete); L6APT2.1 (obsolete); L6B959.1 (obsolete); L6BV30.1 (obsolete); L6C2V7.1 (obsolete); L6CB61.1 (obsolete); L6CX95.1 (obsolete); L6D2R2.1 (obsolete); L6DYK1.1 (obsolete); L6E2G1.1 (obsolete); L6ECX2.1 (obsolete); L6F2X8.1 (obsolete); L6FBL9.1 (obsolete); L6FXC0.1 (obsolete); L6GAQ7.1 (obsolete); L6GDF3.1 (obsolete); L6GQ18.1 (obsolete); L6GUK0.1 (obsolete); L6HEM7.1 (obsolete); L6HZ42.1 (obsolete); L6IJA8.1 (obsolete); L6IKQ8.1 (obsolete); L6JAX7.1 (obsolete); L6JQW5.1 (obsolete); L6JTZ9.1 (obsolete); L6KHV2.1 (obsolete); L6KJ96.1 (obsolete); L6KPE7.1 (obsolete); L6LIS9.1 (obsolete); L6LRL1.1 (obsolete); L6M479.1 (obsolete); L6MJ49.1 (obsolete); L6MRV4.1 (obsolete); L6N4S1.1 (obsolete); L6NJT7.1 (obsolete); L6NQD7.1 (obsolete); L6NYY9.1 (obsolete); L6PTJ6.1 (obsolete); L6Q5G9.1 (obsolete); L6QG28.1 (obsolete); L6RD28.1 (obsolete); L6RT68.1 (obsolete); L6S8W2.1 (obsolete); L6SG06.1 (obsolete); L6ST86.1 (obsolete); L6TMF4.1 (obsolete); L6TTR9.1 (obsolete); L6U0S5.1 (obsolete); L6UCM0.1 (obsolete); L6UY97.1 (obsolete); L6V2H8.1 (obsolete); L6VEW0.1 (obsolete); L6VGW5.1 (obsolete); L6VM83.1 (obsolete); L6W988.1 (obsolete); L6WWB6.1 (obsolete); L6WY56.1 (obsolete); L6X469.1 (obsolete); L6Y0M1.1 (obsolete); L6YE57.1 (obsolete); L6YI25.1 (obsolete); L6Z0U5.1 (obsolete); L6ZMA5.1 (obsolete); L6ZXN5.1 (obsolete); L9Q2Z1.1 (obsolete); L9Q651.1 (obsolete); L9QWK6.1 (obsolete); L9RTY2.1 (obsolete); L9RZ23.1 (obsolete); L9RZV7.1 (obsolete); L9SPL8.1 (obsolete); L9SUR8.1 (obsolete); L9T0I1.1 (obsolete); L9T3F0.1 (obsolete); M9XM34.1 (obsolete); R7RAX9.1 (obsolete); S4HPD6.1 (obsolete); S4IA20.1 (obsolete); S4IYB2.1 (obsolete); S4JUW3.1 (obsolete); S4KAX3.1 (obsolete); S4KSA9.1 (obsolete); S4KVH5.1 (obsolete); S4LU50.1 (obsolete); S5HC55.1 (obsolete); S5IK76.1 (obsolete); S5V9L5.1 (obsolete); T1YEZ9.1 (obsolete); T2PZY7.1 (obsolete); T2QEG8.1 (obsolete); U1J3E4.1 (obsolete); U1RUM6.1 (obsolete); U3SIJ4.1 (obsolete); U6QI94.1 (obsolete); U6QL14.1 (obsolete); U6VL57.1 (obsolete); U6W0G5.1 (obsolete); U6WAX9.1 (obsolete); U6X5N2.1 (obsolete); U6XU02.1 (obsolete); U6XUE1.1 (obsolete); U6Z0B9.1 (obsolete); V0GUR1.1 (obsolete); V0JCU6.1 (obsolete); V1FK33.1 (obsolete); V1G2K9.1 (obsolete); V1GCR6.1 (obsolete); V1IGN7.1 (obsolete); V1IMQ3.1 (obsolete); V1JBW5.1 (obsolete); V1K0S1.1 (obsolete); V1KS42.1 (obsolete); V1LZZ7.1 (obsolete); V1NPU7.1 (obsolete); V1NX60.1 (obsolete); V1Q9V0.1 (obsolete); V1QHX1.1 (obsolete); V1RCP8.1 (obsolete); V1YX44.1 (obsolete); V2CQS1.1 (obsolete); V2D2U7.1 (obsolete); V2DLF9.1 (obsolete); V2F5F1.1 (obsolete); V2F5Q4.1 (obsolete); V2MGV5.1 (obsolete); V2NI96.1 (obsolete); V2NYL4.1 (obsolete); V2PHB9.1 (obsolete); V5KNP2.1 (obsolete); V5ZLN4.1 (obsolete); V7RZQ1.1 (obsolete); V7WUI4.1 (obsolete); V7X4V6.1 (obsolete); V8M2J1.1 (obsolete); V8ML76.1 (obsolete); X4RML9.1 (obsolete); X5NKI0.1 (obsolete),MFFTQNLWVERQQLIKPFILNVNIIYLKNIIIFFIIGGY,-1.194574836126887
 UPI00016B0142,38,NA,MRDTQCHSADFPVYPNVLAVGVRRALWPLPAQDANRTQ,0.44996359010503817
-UPI000173114C,30,B2L4W4,PADDMPTXRNGPSTTNDSDDFVDPWTVQTG,1.3068624916447211

package/files/samples/sample_FASTA.fasta

@@ -190,7 +190,4 @@ MFFTQNLWVERQQLIKPFILNVNIIYLKNIIIFFIIGGY
 >UPI00016B0142:38
 MRDTQCHSADFPVYPNVLAVGVRRALWPLPAQDANRTQ
 
->UPI000173114C:30
-PADDMPTXRNGPSTTNDSDDFVDPWTVQTG
-
 

package/package.json

@@ -2,7 +2,7 @@
   "name": "@datagrok/bio",
   "beta": false,
   "friendlyName": "Bio",
-  "version": "1.5.10",
+  "version": "1.6.0",
   "description": "Bio is a [package](https://datagrok.ai/help/develop/develop#packages) for the [Datagrok](https://datagrok.ai) platform",
   "repository": {
     "type": "git",
@@ -11,7 +11,7 @@
   },
   "dependencies": {
     "@biowasm/aioli": ">=2.4.0",
-    "@datagrok-libraries/bio": "^2.4.2",
+    "@datagrok-libraries/bio": "^2.5.0",
     "@datagrok-libraries/utils": "^1.0.0",
     "@datagrok-libraries/ml": "^2.0.9",
     "cash-dom": "latest",

package/src/package-test.ts

@@ -10,6 +10,7 @@ import './tests/sequence-space-test';
 import './tests/activity-cliffs-tests';
 import './tests/splitter-test';
 import './tests/renderer-test';
+import './tests/convert-test';
 
 export const _package = new DG.Package();
 export {tests};

package/src/package.ts

@@ -19,6 +19,8 @@ import {sequenceGetSimilarities, drawTooltip} from './utils/sequence-activity-cl
 import {getMolfilesFromSeq, HELM_CORE_LIB_FILENAME} from './utils/utils';
 import {getMacroMol} from './utils/atomic-works';
 import {MacromoleculeSequenceCellRenderer} from './utils/cell-renderer';
+import {Column} from 'datagrok-api/dg';
+import {SEM_TYPES} from './utils/constants';
 
 //tags: init
 export async function initBio(): Promise<void> {
@@ -38,6 +40,29 @@ export function macromoleculeSequenceCellRenderer(): MacromoleculeSequenceCellRe
   return new MacromoleculeSequenceCellRenderer();
 }
 
+function checkInputColumn(col: DG.Column, name: string,
+  allowedNotations: string[] = [], allowedAlphabets: string[] = []): boolean {
+  const units: string = col.getTag(DG.TAGS.UNITS);
+  if (col.semType !== DG.SEMTYPE.MACROMOLECULE) {
+    grok.shell.warning(name + ' analysis is allowed for Macromolecules semantic type');
+    return false;
+  } else if (
+    (allowedAlphabets.length > 0 &&
+      !allowedAlphabets.some((a) => units.toUpperCase().endsWith(a.toUpperCase()))) ||
+    (allowedNotations.length > 0 &&
+      !allowedNotations.some((n) => units.toUpperCase().startsWith(n.toUpperCase())))
+  ) {
+    const notationAdd = allowedNotations.length == 0 ? 'any notation' :
+      (`notation${allowedNotations.length > 1 ? 's' : ''} ${allowedNotations.map((n) => `"${n}"`).join(', ')} `);
+    const alphabetAdd = allowedNotations.length == 0 ? 'any alphabet' :
+      (`alphabet${allowedAlphabets.length > 1 ? 's' : ''} ${allowedAlphabets.map((a) => `"${a}"`).join(', ')}.`);
+
+    grok.shell.warning(name + ' analysis is allowed for Macromolecules with ' + notationAdd + ' and ' + alphabetAdd);
+    return false;
+  }
+
+  return true;
+}
 
 //name: sequenceAlignment
 //input: string alignType {choices: ['Local alignment', 'Global alignment']}
@@ -73,20 +98,23 @@ export function vdRegionViewer() {
 //name: Sequence Activity Cliffs
 //description: detect activity cliffs
 //input: dataframe table [Input data table]
-//input: column sequence {semType: Macromolecule}
+//input: column macroMolecule {semType: Macromolecule}
 //input: column activities
 //input: double similarity = 80 [Similarity cutoff]
 //input: string methodName { choices:["UMAP", "t-SNE", "SPE"] }
-export async function activityCliffs(df: DG.DataFrame, sequence: DG.Column, activities: DG.Column,
+export async function activityCliffs(df: DG.DataFrame, macroMolecule: DG.Column, activities: DG.Column,
   similarity: number, methodName: string): Promise<void> {
+  if (!checkInputColumn(macroMolecule, 'Activity Cliffs'))
+    return;
+
   const axesNames = getEmbeddingColsNames(df);
   const options = {
     'SPE': {cycles: 2000, lambda: 1.0, dlambda: 0.0005},
   };
-  const units = sequence!.tags[DG.TAGS.UNITS];
+  const units = macroMolecule!.tags[DG.TAGS.UNITS];
   await getActivityCliffs(
     df,
-    sequence,
+    macroMolecule,
     axesNames,
     'Activity cliffs',
     activities,
@@ -110,6 +138,9 @@ export async function activityCliffs(df: DG.DataFrame, sequence: DG.Column, acti
 //input: bool plotEmbeddings = true
 export async function sequenceSpaceTopMenu(table: DG.DataFrame, macroMolecule: DG.Column, methodName: string,
   similarityMetric: string = 'Levenshtein', plotEmbeddings: boolean): Promise<void> {
+  if (!checkInputColumn(macroMolecule, 'Activity Cliffs'))
+    return;
+
   const embedColsNames = getEmbeddingColsNames(table);
   const chemSpaceParams = {
     seqCol: macroMolecule,
@@ -133,16 +164,18 @@ export async function sequenceSpaceTopMenu(table: DG.DataFrame, macroMolecule: D
 //name: To Atomic Level
 //description: returns molfiles for each monomer from HELM library
 //input: dataframe df [Input data table]
-//input: column sequence {semType: Macromolecule}
-export async function toAtomicLevel(df: DG.DataFrame, sequence: DG.Column): Promise<void> {
-  if (DG.Func.find({package: 'Chem', name: 'getRdKitModule'})) {
+//input: column macroMolecule {semType: Macromolecule}
+export async function toAtomicLevel(df: DG.DataFrame, macroMolecule: DG.Column): Promise<void> {
+  if (DG.Func.find({package: 'Chem', name: 'getRdKitModule'}).length === 0) {
     grok.shell.warning('Transformation to atomic level requires package "Chem" installed.');
     return;
   }
+  if (!checkInputColumn(macroMolecule, 'To Atomic Level'))
+    return;
 
   const monomersLibFile = await _package.files.readAsText(HELM_CORE_LIB_FILENAME);
   const monomersLibObject: any[] = JSON.parse(monomersLibFile);
-  const atomicCodes = getMolfilesFromSeq(sequence, monomersLibObject);
+  const atomicCodes = getMolfilesFromSeq(macroMolecule, monomersLibObject);
   const result = await getMacroMol(atomicCodes!);
 
   const col = DG.Column.fromStrings('regenerated', result);
@@ -158,21 +191,8 @@ export async function toAtomicLevel(df: DG.DataFrame, sequence: DG.Column): Prom
 //input: column sequence { semType: Macromolecule }
 //output: column result
 export async function multipleSequenceAlignmentAny(table: DG.DataFrame, col: DG.Column): Promise<DG.Column | null> {
-  if (col.semType != DG.SEMTYPE.MACROMOLECULE) {
-    grok.shell.warning(`MSA analysis is allowed for semantic type "${DG.SEMTYPE.MACROMOLECULE}" data only.`);
-    return null;
-  }
-  const units: string = col.getTag(DG.TAGS.UNITS);
-  const allowedAlphabets = ['DNA', 'RNA', 'PT'];
-  const allowedNotations = ['fasta'];
-  if (!allowedAlphabets.some((a) => units.toUpperCase().endsWith(a.toUpperCase())) ||
-    !allowedNotations.some((n) => units.toUpperCase().startsWith(n.toUpperCase()))) {
-    grok.shell.warning('MSA analysis is allowed for ' +
-      `notation${allowedNotations.length > 1 ? 's' : ''} ${allowedNotations.map((n) => `"${n}"`).join(', ')} ` +
-      'and ' +
-      `alphabet${allowedAlphabets.length > 1 ? 's' : ''} ${allowedAlphabets.map((a) => `"${a}"`).join(', ')}.`);
+  if (!checkInputColumn(col, 'MSA', ['fasta'], ['DNA', 'RNA', 'PT']))
     return null;
-  }
 
   const msaCol = await runKalign(col, false);
   table.columns.add(msaCol);
@@ -199,6 +219,9 @@ export async function compositionAnalysis(): Promise<void> {
     return;
   }
 
+  if (!checkInputColumn(col, 'Composition'))
+    return;
+
   const allowedNotations: string[] = ['fasta', 'separator'];
   const units = col.getTag(DG.TAGS.UNITS);
   if (!allowedNotations.some((n) => units.toUpperCase().startsWith(n.toUpperCase()))) {
@@ -224,7 +247,7 @@ function parseMacromolecule(
 //name: importFasta
 //description: Opens FASTA file
 //tags: file-handler
-//meta.ext: fasta, fna, ffn, faa, frn, fa
+//meta.ext: fasta, fna, ffn, faa, frn, fa, fst
 //input: string fileContent
 //output: list tables
 export function importFasta(fileContent: string): DG.DataFrame [] {
@@ -244,13 +267,34 @@ export function importFasta(fileContent: string): DG.DataFrame [] {
   const descriptionsArrayCol = DG.Column.fromStrings('description', descriptionsArray);
   const sequenceCol = DG.Column.fromStrings('sequence', sequencesArray);
   sequenceCol.semType = 'Macromolecule';
-
   const stats: SeqColStats = WebLogo.getStats(sequenceCol, 5, WebLogo.splitterAsFasta);
   const seqType = stats.sameLength ? 'SEQ.MSA' : 'SEQ';
+
+  const PeptideFastaAlphabet = new Set([
+    'G', 'L', 'Y', 'S', 'E', 'Q', 'D', 'N', 'F', 'A',
+    'K', 'R', 'H', 'C', 'V', 'P', 'W', 'I', 'M', 'T',
+  ]);
+
+  const DnaFastaAlphabet = new Set(['A', 'C', 'G', 'T']);
+
+  const RnaFastaAlphabet = new Set(['A', 'C', 'G', 'U']);
+
+  //const SmilesRawAlphabet = new Set([
+  //  'O', 'C', 'c', 'N', 'S', 'F', '(', ')',
+  //  '1', '2', '3', '4', '5', '6', '7',
+  //  '+', '-', '@', '[', ']', '/', '\\', '#', '=']);
+
   const alphabetCandidates: [string, Set<string>][] = [
-    ['NT', new Set(Object.keys(Nucleotides.Names))],
-    ['PT', new Set(Object.keys(Aminoacids.Names))],
+    ['PT', PeptideFastaAlphabet],
+    ['DNA', DnaFastaAlphabet],
+    ['RNA', RnaFastaAlphabet],
   ];
+
+  //const alphabetCandidates: [string, Set<string>][] = [
+  //  ['NT', new Set(Object.keys(Nucleotides.Names))],
+  //  ['PT', new Set(Object.keys(Aminoacids.Names))],
+  //];
+
   // Calculate likelihoods for alphabet_candidates
   const alphabetCandidatesSim: number[] = alphabetCandidates.map(
     (c) => WebLogo.getAlphabetSimilarity(stats.freq, c[1]));

package/src/tests/convert-test.ts

@@ -44,7 +44,7 @@ PEPTIDE1{M.K.P.S.E.Y.V}$$$
 ACGTC
 CAGTGT
 TTCAAC
-    `,
+`,
     separatorDna: `seq
 A/C/G/T/C
 C/A/G/T/G/T
@@ -59,7 +59,7 @@ DNA1{D(T)P.D(T)P.D(C)P.D(A)P.D(A)P.D(C)P}$$$
 ACGUC
 CAGUGU
 UUCAAC
-    `,
+`,
     separatorRna: `seq
 A*C*G*U*C
 C*A*G*U*G*U
@@ -90,10 +90,10 @@ RNA1{R(U)P.R(U)P.R(C)P.R(A)P.R(A)P.R(C)P}$$$
     return _csvDfs[key];
   };
 
-  function converter(tgtNotation: NOTATION, separator: string | null = null): ConverterFunc {
+  function converter(tgtNotation: NOTATION, tgtSeparator: string | null = null): ConverterFunc {
     return function(srcCol: DG.Column): DG.Column {
       const converter = new NotationConverter(srcCol);
-      const resCol = converter.convert(NOTATION.SEPARATOR, separator);
+      const resCol = converter.convert(tgtNotation, tgtSeparator);
       return resCol;
     };
   };
@@ -127,7 +127,7 @@ RNA1{R(U)P.R(U)P.R(C)P.R(A)P.R(A)P.R(C)P}$$$
     await _testConvert(Samples.fastaDna, converter(NOTATION.HELM), Samples.helmDna);
   });
   test('testFastaRnaToHelm', async () => {
-    await _testConvert(Samples.fastaDna, converter(NOTATION.HELM), Samples.helmRna);
+    await _testConvert(Samples.fastaRna, converter(NOTATION.HELM), Samples.helmRna);
   });
 
   test('testSeparatorPtToFasta', async () => {
@@ -136,15 +136,15 @@ RNA1{R(U)P.R(U)P.R(C)P.R(A)P.R(A)P.R(C)P}$$$
   test('testSeparatorDnaToFasta', async () => {
     await _testConvert(Samples.separatorDna, converter(NOTATION.FASTA), Samples.fastaDna);
   });
-  test('testSeparatorDnaToFasta', async () => {
+  test('testSeparatorRnaToFasta', async () => {
     await _testConvert(Samples.separatorRna, converter(NOTATION.FASTA), Samples.fastaRna);
   });
 
   test('testSeparatorPtToHelm', async () => {
-    await _testConvert(Samples.separatorRna, converter(NOTATION.HELM), Samples.helmPt);
+    await _testConvert(Samples.separatorPt, converter(NOTATION.HELM), Samples.helmPt);
   });
   test('testSeparatorDnaToHelm', async () => {
-    await _testConvert(Samples.separatorRna, converter(NOTATION.HELM), Samples.helmDna);
+    await _testConvert(Samples.separatorDna, converter(NOTATION.HELM), Samples.helmDna);
   });
   test('testSeparatorRnaToHelm', async () => {
     await _testConvert(Samples.separatorRna, converter(NOTATION.HELM), Samples.helmRna);

package/src/utils/cell-renderer.ts

@@ -1,6 +1,4 @@
 import * as C from "./constants";
-import {getSeparator} from "./misc";
-import {ChemPalette} from "./chem-palette";
 import * as DG from 'datagrok-api/dg';
 import {AminoacidsPalettes} from "@datagrok-libraries/bio/src/aminoacids";
 import {NucleotidesPalettes} from "@datagrok-libraries/bio/src/nucleotides";
@@ -10,6 +8,7 @@ import {SeqPalette} from "@datagrok-libraries/bio/src/seq-palettes";
 import * as ui from 'datagrok-api/ui';
 
 const lru = new DG.LruCache<any, any>();
+const undefinedColor =  'rgb(100,100,100)';
 
 function getPalleteByType(paletteType: string): SeqPalette  {
   switch (paletteType) {
@@ -48,7 +47,7 @@ export function processSequence(subParts: string[]): [string[], boolean] {
  * @param {number} h Height.
  * @param {CanvasRenderingContext2D} g Canvas rendering context.
  * @param {string} s String to print.
- * @param {string} [color=ChemPalette.undefinedColor] String color.
+ * @param {string} [color=undefinedColor] String color.
  * @param {number} [pivot=0] Pirvot.
  * @param {boolean} [left=false] Is left aligned.
  * @param {boolean} [hideMod=false] Hide amino acid redidue modifications.
@@ -57,12 +56,15 @@ export function processSequence(subParts: string[]): [string[], boolean] {
  */
 function printLeftOrCentered(
     x: number, y: number, w: number, h: number,
-    g: CanvasRenderingContext2D, s: string, color = ChemPalette.undefinedColor,
+    g: CanvasRenderingContext2D, s: string, color = undefinedColor,
     pivot: number = 0, left = false, hideMod = false, transparencyRate: number = 1.0,
-    separator: string = ''): number {
+    separator: string = '', last:boolean = false): number {
   g.textAlign = 'start';
   let colorPart = s.substring(0);
   let grayPart = separator;
+  if (last) {
+    grayPart = '';
+  }
   const textSize = g.measureText(colorPart + grayPart);
   const indent = 5;
 
@@ -87,44 +89,6 @@ function printLeftOrCentered(
     return x + dx + colorTextSize.width;
   }
 }
-function renderSequense(
-      g: CanvasRenderingContext2D, x: number, y: number, w: number, h: number, gridCell: DG.GridCell,
-      cellStyle: DG.GridCellStyle,
-): void {
-    const grid = gridCell.grid;
-    const cell = gridCell.cell;
-    const [type, subtype, paletteType] =  gridCell.cell.column.getTag(DG.TAGS.UNITS).split(":");
-    w = grid ? Math.min(grid.canvas.width - x, w) : g.canvas.width - x;
-    g.save();
-    g.beginPath();
-    g.rect(x, y, w, h);
-    g.clip();
-    g.font = '12px monospace';
-    g.textBaseline = 'top';
-    const s: string = cell.value ?? '';
-
-  //TODO: can this be replaced/merged with splitSequence?
-  const units = gridCell.cell.column.getTag(DG.TAGS.UNITS);
-
-  const palette = getPalleteByType(paletteType);
-
-  const separator = gridCell.cell.column.getTag('separator') ?? '';
-  const splitterFunc: SplitterFunc = WebLogo.getSplitter(units, gridCell.cell.column.getTag('separator') );// splitter,
-
-  const subParts:string[] =  splitterFunc(cell.value);
-
-  const textSize = g.measureText(subParts.join(''));
-  let x1 = Math.max(x, x + (w - textSize.width) / 2);
-
-  subParts.forEach((amino, index) => {
-    let [color, outerAmino,, pivot] = ChemPalette.getColorAAPivot(amino);
-    color = palette.get(amino);
-    g.fillStyle = ChemPalette.undefinedColor;
-    x1 = printLeftOrCentered(x1, y, w, h, g, amino, color, pivot, true, false, 1.0, separator);
-  });
-
-  g.restore();
-}
 
 export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
 
@@ -196,13 +160,16 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
       // console.log(subParts);
 
       const textSize = g.measureText(subParts.join(''));
-      let x1 = Math.max(x, x + (w - textSize.width) / 2);
-
+      let x1 = x;
+      let color = undefinedColor;
       subParts.forEach((amino, index) => {
-        let [color, outerAmino,, pivot] = ChemPalette.getColorAAPivot(amino);
         color = palette.get(amino);
-        g.fillStyle = ChemPalette.undefinedColor;
-        x1 = printLeftOrCentered(x1, y, w, h, g, amino, color, pivot, true, false, 1.0, separator);
+        g.fillStyle = undefinedColor;
+        let last = false;
+        if (index === subParts.length - 1) {
+          last = true;
+        }
+        x1 = printLeftOrCentered(x1, y, w, h, g, amino, color, 0, true, false, 1.0, separator, last);
       });
 
       g.restore();

package/src/utils/convert.ts

@@ -16,26 +16,22 @@ export function convert(col: DG.Column): void {
     NOTATION.SEPARATOR,
     NOTATION.HELM
   ];
-  const filtered = notations.filter((e) => e !== current);
-  const targetNotationInput = ui.choiceInput('Convert to', filtered[0], filtered);
+  const separatorArray = ['-', '.', '/'];
+  const filteredNotations = notations.filter((e) => e !== current);
+  const targetNotationInput = ui.choiceInput('Convert to', filteredNotations[0], filteredNotations);
 
-  const separatorInput = ui.choiceInput('separator', '-', ['-', '.', '/']);
+  const separatorInput = ui.choiceInput('Choose separator', separatorArray[0], separatorArray);
 
-  ui.dialog('Convert sequence')
+  ui.dialog('Convert sequence notation')
     .add(ui.div([
-      ui.h1('current notation'),
-      ui.div(current),
-      targetNotationInput.root
-    ]))
-    .add(ui.div([
-      ui.h1('Separator'),
-      separatorInput,
-
+      ui.h1('Current notation: ' + current),
+      targetNotationInput.root,
+      // TODO: conditional separator input
+      separatorInput.root
     ]))
     .onOK(() => {
       //TODO: create new converted column
-      //const targetNotation: NOTATION = strToEnum<NOTATION>(NOTATION, targetNotationInput.value)!;
-      const targetNotation: NOTATION = targetNotationInput.value as NOTATION;
+      const targetNotation = targetNotationInput.value as NOTATION;
       const separator = separatorInput.value!;
       const newColumn = converter.convert(targetNotation, separator);
       col.dataFrame.columns.add(newColumn);