@datagrok/bio 2.11.18 → 2.11.20

package/package.json

@@ -5,7 +5,7 @@
     "name": "Leonid Stolbov",
     "email": "lstolbov@datagrok.ai"
   },
-  "version": "2.11.18",
+  "version": "2.11.20",
   "description": "Bioinformatics support (import/export of sequences, conversion, visualization, analysis). [See more](https://github.com/datagrok-ai/public/blob/master/packages/Bio/README.md) for details.",
   "repository": {
     "type": "git",
@@ -30,18 +30,11 @@
       "propertyType": "string",
       "defaultValue": ".",
       "nullable": false
-    },
-    {
-      "name": "Debug",
-      "propertyType": "string_list",
-      "choices": ["detectors", "WebLogo"],
-      "defaultValue": [],
-      "nullable": false
     }
   ],
   "dependencies": {
     "@biowasm/aioli": "^3.1.0",
-    "@datagrok-libraries/bio": "^5.39.13",
+    "@datagrok-libraries/bio": "^5.39.14",
     "@datagrok-libraries/chem-meta": "^1.2.1",
     "@datagrok-libraries/ml": "^6.3.67",
     "@datagrok-libraries/tutorials": "^1.3.11",

package/src/analysis/sequence-space.ts

@@ -5,7 +5,7 @@ import {ISequenceSpaceParams} from '@datagrok-libraries/ml/src/viewers/activity-
 import {invalidateMols, MONOMERIC_COL_TAGS} from '../substructure-search/substructure-search';
 import {mmDistanceFunctionArgs} from '@datagrok-libraries/ml/src/macromolecule-distance-functions/types';
 import {UnitsHandler} from '@datagrok-libraries/bio/src/utils/units-handler';
-import {calculateMonomerSimilarity} from '@datagrok-libraries/bio/src/monomer-works/monomer-utils';
+import {getMonomerSubstitutionMatrix} from '@datagrok-libraries/bio/src/monomer-works/monomer-utils';
 import * as grok from 'datagrok-api/grok';
 import {MmDistanceFunctionsNames} from '@datagrok-libraries/ml/src/macromolecule-distance-functions';
 
@@ -56,7 +56,7 @@ export async function sequenceSpaceByFingerprints(spaceParams: ISequenceSpacePar
 }
 
 export async function getEncodedSeqSpaceCol(
-  seqCol: DG.Column, similarityMetric: BitArrayMetrics | MmDistanceFunctionsNames
+  seqCol: DG.Column, similarityMetric: BitArrayMetrics | MmDistanceFunctionsNames, fingerprintType: string = 'Morgan'
 ): Promise<{seqList:string[], options: {[_:string]: any}}> {
 // encodes sequences using utf charachters to also support multichar and non fasta sequences
   const ncUH = UnitsHandler.getOrCreate(seqCol);
@@ -85,7 +85,7 @@ export async function getEncodedSeqSpaceCol(
   let options = {};
   if (similarityMetric === MmDistanceFunctionsNames.MONOMER_CHEMICAL_DISTANCE) {
     const monomers = Array.from(charCodeMap.keys());
-    const monomerRes = await calculateMonomerSimilarity(monomers);
+    const monomerRes = await getMonomerSubstitutionMatrix(monomers, fingerprintType);
     // the susbstitution matrix contains similarity, but we need distances
     monomerRes.scoringMatrix.forEach((row, i) => {
       row.forEach((val, j) => {
@@ -101,7 +101,7 @@ export async function getEncodedSeqSpaceCol(
       alphabetIndexes: monomerHashToMatrixMap} satisfies mmDistanceFunctionArgs;
   } else if (similarityMetric === MmDistanceFunctionsNames.NEEDLEMANN_WUNSCH) {
     const monomers = Array.from(charCodeMap.keys());
-    const monomerRes = await calculateMonomerSimilarity(monomers);
+    const monomerRes = await getMonomerSubstitutionMatrix(monomers, fingerprintType);
     // the susbstitution matrix contains similarity, but we need distances
     // monomerRes.scoringMatrix.forEach((row, i) => {
     //   row.forEach((val, j) => {

package/src/package.ts

@@ -500,11 +500,13 @@ export async function activityCliffs(df: DG.DataFrame, macroMolecule: DG.Column<
 //input: string metric
 //input: double gapOpen = 1 {caption: Gap open penalty; default: 1; optional: true}
 //input: double gapExtend = 0.6 {caption: Gap extension penalty; default: 0.6; optional: true}
+// eslint-disable-next-line max-len
+//input: string fingerprintType = Morgan {caption: Fingerprint type; choices: ['Morgan', 'RDKit', 'Pattern']; default: Morgan; optional: true}
 //output: object result
 export async function macromoleculePreprocessingFunction(
-  col: DG.Column, metric: MmDistanceFunctionsNames, gapOpen: number = 1, gapExtend: number = 0.6
-): Promise<PreprocessFunctionReturnType> {
-  const {seqList, options} = await getEncodedSeqSpaceCol(col, metric);
+  col: DG.Column, metric: MmDistanceFunctionsNames, gapOpen: number = 1, gapExtend: number = 0.6,
+  fingerprintType = 'Morgan'): Promise<PreprocessFunctionReturnType> {
+  const {seqList, options} = await getEncodedSeqSpaceCol(col, metric, fingerprintType);
   return {entries: seqList, options: {...options, gapOpen, gapExtend}};
 }