@datagrok/bio 1.5.3 → 1.5.4

package/files/samples/sar-small.csv

@@ -0,0 +1,201 @@
+smiles
+O=C1CN=C(c2ccccc2N1)C3CCCCC3
+CN1C(=O)CN=C(c2ccccc12)C3CCCCC3
+CCCCN1C(=O)CN=C(c2ccccc12)C3CCCCC3
+CC(C)CCN1C(=O)CN=C(c2ccccc12)C3CCCCC3
+O=C1CN=C(c2ccccc2N1CC3CCCCC3)C4CCCCC4
+O=C1CN=C(c2cc(Cl)ccc2N1)C3CCCCC3
+CN1C(=O)CN=C(c2cc(Cl)ccc12)C3CCCCC3
+CCCCN1C(=O)CN=C(c2cc(Cl)ccc12)C3CCCCC3
+CC(C)CCN1C(=O)CN=C(c2cc(Cl)ccc12)C3CCCCC3
+O=C1CN=C(c2cc(Cl)ccc2N1CC3CCCCC3)C4CCCCC4
+N#Cc1ccc2NC(=O)CN=C(c2c1)C3CCCCC3
+CN1C(=O)CN=C(c2cc(C#N)ccc12)C3CCCCC3
+CCCCN1C(=O)CN=C(c2cc(C#N)ccc12)C3CCCCC3
+CC(C)CCN1C(=O)CN=C(c2cc(C#N)ccc12)C3CCCCC3
+N#Cc1ccc2c(c1)C(=NCC(=O)N2CC3CCCCC3)C4CCCCC4
+CN(C)c1ccc2NC(=O)CN=C(c2c1)C3CCCCC3
+CN(C)c1ccc2c(c1)C(=NCC(=O)N2C)C3CCCCC3
+CCCCN1C(=O)CN=C(c2cc(ccc12)N(C)C)C3CCCCC3
+CC(C)CCN1C(=O)CN=C(c2cc(ccc12)N(C)C)C3CCCCC3
+CN(C)c1ccc2c(c1)C(=NCC(=O)N2CC3CCCCC3)C4CCCCC4
+O=C1CN=C(c2cc(F)ccc2N1)C3CCCCC3
+CN1C(=O)CN=C(c2cc(F)ccc12)C3CCCCC3
+CCCCN1C(=O)CN=C(c2cc(F)ccc12)C3CCCCC3
+CC(C)CCN1C(=O)CN=C(c2cc(F)ccc12)C3CCCCC3
+O=C1CN=C(c2cc(F)ccc2N1CC3CCCCC3)C4CCCCC4
+O=C1CN=C(c2cc(Br)ccc2N1)C3CCCCC3
+CN1C(=O)CN=C(c2cc(Br)ccc12)C3CCCCC3
+CCCCN1C(=O)CN=C(c2cc(Br)ccc12)C3CCCCC3
+CC(C)CCN1C(=O)CN=C(c2cc(Br)ccc12)C3CCCCC3
+O=C1CN=C(c2cc(Br)ccc2N1CC3CCCCC3)C4CCCCC4
+O=C1CN=C(c2cc(I)ccc2N1)C3CCCCC3
+CN1C(=O)CN=C(c2cc(I)ccc12)C3CCCCC3
+CCCCN1C(=O)CN=C(c2cc(I)ccc12)C3CCCCC3
+CC(C)CCN1C(=O)CN=C(c2cc(I)ccc12)C3CCCCC3
+O=C1CN=C(c2cc(I)ccc2N1CC3CCCCC3)C4CCCCC4
+NC(=O)c1ccc2NC(=O)CN=C(c2c1)C3CCCCC3
+CN1C(=O)CN=C(c2cc(ccc12)C(N)=O)C3CCCCC3
+CCCCN1C(=O)CN=C(c2cc(ccc12)C(N)=O)C3CCCCC3
+CC(C)CCN1C(=O)CN=C(c2cc(ccc12)C(N)=O)C3CCCCC3
+NC(=O)c1ccc2c(c1)C(=NCC(=O)N2CC3CCCCC3)C4CCCCC4
+O=C1CN=C(c2cc(ccc2N1)[N+](=O)[O-])C3CCCCC3
+CN1C(=O)CN=C(c2cc(ccc12)[N+](=O)[O-])C3CCCCC3
+CCCCN1C(=O)CN=C(c2cc(ccc12)[N+](=O)[O-])C3CCCCC3
+CC(C)CCN1C(=O)CN=C(c2cc(ccc12)[N+](=O)[O-])C3CCCCC3
+O=C1CN=C(c2cc(ccc2N1CC3CCCCC3)[N+](=O)[O-])C4CCCCC4
+O=C1CN=C(c2ccccc2)c3ccccc3N1
+CN1C(=O)CN=C(c2ccccc2)c3ccccc13
+CCCCN1C(=O)CN=C(c2ccccc2)c3ccccc13
+CC(C)CCN1C(=O)CN=C(c2ccccc2)c3ccccc13
+O=C1CN=C(c2ccccc2)c3ccccc3N1CC4CCCCC4
+O=C1CN=C(c2ccccc2)c3cc(Cl)ccc3N1
+CN1C(=O)CN=C(c2ccccc2)c3cc(Cl)ccc13
+CCCCN1C(=O)CN=C(c2ccccc2)c3cc(Cl)ccc13
+CC(C)CCN1C(=O)CN=C(c2ccccc2)c3cc(Cl)ccc13
+O=C1CN=C(c2ccccc2)c3cc(Cl)ccc3N1CC4CCCCC4
+N#Cc1ccc2NC(=O)CN=C(c3ccccc3)c2c1
+CN1C(=O)CN=C(c2ccccc2)c3cc(C#N)ccc13
+CCCCN1C(=O)CN=C(c2ccccc2)c3cc(C#N)ccc13
+CC(C)CCN1C(=O)CN=C(c2ccccc2)c3cc(C#N)ccc13
+N#Cc1ccc2c(c1)C(=NCC(=O)N2CC3CCCCC3)c4ccccc4
+CN(C)c1ccc2NC(=O)CN=C(c3ccccc3)c2c1
+CN(C)c1ccc2c(c1)C(=NCC(=O)N2C)c3ccccc3
+CCCCN1C(=O)CN=C(c2ccccc2)c3cc(ccc13)N(C)C
+CC(C)CCN1C(=O)CN=C(c2ccccc2)c3cc(ccc13)N(C)C
+CN(C)c1ccc2c(c1)C(=NCC(=O)N2CC3CCCCC3)c4ccccc4
+O=C1CN=C(c2ccccc2)c3cc(F)ccc3N1
+CN1C(=O)CN=C(c2ccccc2)c3cc(F)ccc13
+CCCCN1C(=O)CN=C(c2ccccc2)c3cc(F)ccc13
+CC(C)CCN1C(=O)CN=C(c2ccccc2)c3cc(F)ccc13
+O=C1CN=C(c2ccccc2)c3cc(F)ccc3N1CC4CCCCC4
+O=C1CN=C(c2ccccc2)c3cc(Br)ccc3N1
+CN1C(=O)CN=C(c2ccccc2)c3cc(Br)ccc13
+CCCCN1C(=O)CN=C(c2ccccc2)c3cc(Br)ccc13
+CC(C)CCN1C(=O)CN=C(c2ccccc2)c3cc(Br)ccc13
+O=C1CN=C(c2ccccc2)c3cc(Br)ccc3N1CC4CCCCC4
+O=C1CN=C(c2ccccc2)c3cc(I)ccc3N1
+CN1C(=O)CN=C(c2ccccc2)c3cc(I)ccc13
+CCCCN1C(=O)CN=C(c2ccccc2)c3cc(I)ccc13
+CC(C)CCN1C(=O)CN=C(c2ccccc2)c3cc(I)ccc13
+O=C1CN=C(c2ccccc2)c3cc(I)ccc3N1CC4CCCCC4
+NC(=O)c1ccc2NC(=O)CN=C(c3ccccc3)c2c1
+CN1C(=O)CN=C(c2ccccc2)c3cc(ccc13)C(N)=O
+CCCCN1C(=O)CN=C(c2ccccc2)c3cc(ccc13)C(N)=O
+CC(C)CCN1C(=O)CN=C(c2ccccc2)c3cc(ccc13)C(N)=O
+NC(=O)c1ccc2c(c1)C(=NCC(=O)N2CC3CCCCC3)c4ccccc4
+O=C1CN=C(c2ccccc2)c3cc(ccc3N1)[N+](=O)[O-]
+CN1C(=O)CN=C(c2ccccc2)c3cc(ccc13)[N+](=O)[O-]
+CCCCN1C(=O)CN=C(c2ccccc2)c3cc(ccc13)[N+](=O)[O-]
+CC(C)CCN1C(=O)CN=C(c2ccccc2)c3cc(ccc13)[N+](=O)[O-]
+O=C1CN=C(c2ccccc2)c3cc(ccc3N1CC4CCCCC4)[N+](=O)[O-]
+COc1ccc(cc1)C2=NCC(=O)Nc3ccccc23
+COc1ccc(cc1)C2=NCC(=O)N(C)c3ccccc23
+CCCCN1C(=O)CN=C(c2ccc(cc2)OC)c3ccccc13
+COc1ccc(cc1)C2=NCC(=O)N(CCC(C)C)c3ccccc23
+COc1ccc(cc1)C2=NCC(=O)N(CC3CCCCC3)c4ccccc24
+COc1ccc(cc1)C2=NCC(=O)Nc3ccc(Cl)cc23
+COc1ccc(cc1)C2=NCC(=O)N(C)c3ccc(Cl)cc23
+CCCCN1C(=O)CN=C(c2ccc(cc2)OC)c3cc(Cl)ccc13
+COc1ccc(cc1)C2=NCC(=O)N(CCC(C)C)c3ccc(Cl)cc23
+COc1ccc(cc1)C2=NCC(=O)N(CC3CCCCC3)c4ccc(Cl)cc24
+COc1ccc(cc1)C2=NCC(=O)Nc3ccc(C#N)cc23
+COc1ccc(cc1)C2=NCC(=O)N(C)c3ccc(C#N)cc23
+CCCCN1C(=O)CN=C(c2ccc(cc2)OC)c3cc(C#N)ccc13
+COc1ccc(cc1)C2=NCC(=O)N(CCC(C)C)c3ccc(C#N)cc23
+COc1ccc(cc1)C2=NCC(=O)N(CC3CCCCC3)c4ccc(C#N)cc24
+COc1ccc(cc1)C2=NCC(=O)Nc3ccc(cc23)N(C)C
+COc1ccc(cc1)C2=NCC(=O)N(C)c3ccc(cc23)N(C)C
+CCCCN1C(=O)CN=C(c2ccc(cc2)OC)c3cc(ccc13)N(C)C
+COc1ccc(cc1)C2=NCC(=O)N(CCC(C)C)c3ccc(cc23)N(C)C
+COc1ccc(cc1)C2=NCC(=O)N(CC3CCCCC3)c4ccc(cc24)N(C)C
+COc1ccc(cc1)C2=NCC(=O)Nc3ccc(F)cc23
+COc1ccc(cc1)C2=NCC(=O)N(C)c3ccc(F)cc23
+CCCCN1C(=O)CN=C(c2ccc(cc2)OC)c3cc(F)ccc13
+COc1ccc(cc1)C2=NCC(=O)N(CCC(C)C)c3ccc(F)cc23
+COc1ccc(cc1)C2=NCC(=O)N(CC3CCCCC3)c4ccc(F)cc24
+COc1ccc(cc1)C2=NCC(=O)Nc3ccc(Br)cc23
+COc1ccc(cc1)C2=NCC(=O)N(C)c3ccc(Br)cc23
+CCCCN1C(=O)CN=C(c2ccc(cc2)OC)c3cc(Br)ccc13
+COc1ccc(cc1)C2=NCC(=O)N(CCC(C)C)c3ccc(Br)cc23
+COc1ccc(cc1)C2=NCC(=O)N(CC3CCCCC3)c4ccc(Br)cc24
+COc1ccc(cc1)C2=NCC(=O)Nc3ccc(I)cc23
+COc1ccc(cc1)C2=NCC(=O)N(C)c3ccc(I)cc23
+CCCCN1C(=O)CN=C(c2ccc(cc2)OC)c3cc(I)ccc13
+COc1ccc(cc1)C2=NCC(=O)N(CCC(C)C)c3ccc(I)cc23
+COc1ccc(cc1)C2=NCC(=O)N(CC3CCCCC3)c4ccc(I)cc24
+COc1ccc(cc1)C2=NCC(=O)Nc3ccc(cc23)C(N)=O
+COc1ccc(cc1)C2=NCC(=O)N(C)c3ccc(cc23)C(N)=O
+CCCCN1C(=O)CN=C(c2ccc(cc2)OC)c3cc(ccc13)C(N)=O
+COc1ccc(cc1)C2=NCC(=O)N(CCC(C)C)c3ccc(cc23)C(N)=O
+COc1ccc(cc1)C2=NCC(=O)N(CC3CCCCC3)c4ccc(cc24)C(N)=O
+COc1ccc(cc1)C2=NCC(=O)Nc3ccc(cc23)[N+](=O)[O-]
+COc1ccc(cc1)C2=NCC(=O)N(C)c3ccc(cc23)[N+](=O)[O-]
+CCCCN1C(=O)CN=C(c2ccc(cc2)OC)c3cc(ccc13)[N+](=O)[O-]
+COc1ccc(cc1)C2=NCC(=O)N(CCC(C)C)c3ccc(cc23)[N+](=O)[O-]
+COc1ccc(cc1)C2=NCC(=O)N(CC3CCCCC3)c4ccc(cc24)[N+](=O)[O-]
+CC1N=C(c2ccccc2NC1=O)C3CCCCC3
+CC1N=C(c2ccccc2N(C)C1=O)C3CCCCC3
+CCCCN1C(=O)C(C)N=C(c2ccccc12)C3CCCCC3
+CC(C)CCN1C(=O)C(C)N=C(c2ccccc12)C3CCCCC3
+CC1N=C(c2ccccc2N(CC3CCCCC3)C1=O)C4CCCCC4
+CC1N=C(c2cc(Cl)ccc2NC1=O)C3CCCCC3
+CC1N=C(c2cc(Cl)ccc2N(C)C1=O)C3CCCCC3
+CCCCN1C(=O)C(C)N=C(c2cc(Cl)ccc12)C3CCCCC3
+CC(C)CCN1C(=O)C(C)N=C(c2cc(Cl)ccc12)C3CCCCC3
+CC1N=C(c2cc(Cl)ccc2N(CC3CCCCC3)C1=O)C4CCCCC4
+CC1N=C(c2cc(C#N)ccc2NC1=O)C3CCCCC3
+CC1N=C(c2cc(C#N)ccc2N(C)C1=O)C3CCCCC3
+CCCCN1C(=O)C(C)N=C(c2cc(C#N)ccc12)C3CCCCC3
+CC(C)CCN1C(=O)C(C)N=C(c2cc(C#N)ccc12)C3CCCCC3
+CC1N=C(c2cc(C#N)ccc2N(CC3CCCCC3)C1=O)C4CCCCC4
+CC1N=C(c2cc(ccc2NC1=O)N(C)C)C3CCCCC3
+CC1N=C(c2cc(ccc2N(C)C1=O)N(C)C)C3CCCCC3
+CCCCN1C(=O)C(C)N=C(c2cc(ccc12)N(C)C)C3CCCCC3
+CC(C)CCN1C(=O)C(C)N=C(c2cc(ccc12)N(C)C)C3CCCCC3
+CC1N=C(c2cc(ccc2N(CC3CCCCC3)C1=O)N(C)C)C4CCCCC4
+CC1N=C(c2cc(F)ccc2NC1=O)C3CCCCC3
+CC1N=C(c2cc(F)ccc2N(C)C1=O)C3CCCCC3
+CCCCN1C(=O)C(C)N=C(c2cc(F)ccc12)C3CCCCC3
+CC(C)CCN1C(=O)C(C)N=C(c2cc(F)ccc12)C3CCCCC3
+CC1N=C(c2cc(F)ccc2N(CC3CCCCC3)C1=O)C4CCCCC4
+CC1N=C(c2cc(Br)ccc2NC1=O)C3CCCCC3
+CC1N=C(c2cc(Br)ccc2N(C)C1=O)C3CCCCC3
+CCCCN1C(=O)C(C)N=C(c2cc(Br)ccc12)C3CCCCC3
+CC(C)CCN1C(=O)C(C)N=C(c2cc(Br)ccc12)C3CCCCC3
+CC1N=C(c2cc(Br)ccc2N(CC3CCCCC3)C1=O)C4CCCCC4
+CC1N=C(c2cc(I)ccc2NC1=O)C3CCCCC3
+CC1N=C(c2cc(I)ccc2N(C)C1=O)C3CCCCC3
+CCCCN1C(=O)C(C)N=C(c2cc(I)ccc12)C3CCCCC3
+CC(C)CCN1C(=O)C(C)N=C(c2cc(I)ccc12)C3CCCCC3
+CC1N=C(c2cc(I)ccc2N(CC3CCCCC3)C1=O)C4CCCCC4
+CC1N=C(c2cc(ccc2NC1=O)C(N)=O)C3CCCCC3
+CC1N=C(c2cc(ccc2N(C)C1=O)C(N)=O)C3CCCCC3
+CCCCN1C(=O)C(C)N=C(c2cc(ccc12)C(N)=O)C3CCCCC3
+CC(C)CCN1C(=O)C(C)N=C(c2cc(ccc12)C(N)=O)C3CCCCC3
+CC1N=C(c2cc(ccc2N(CC3CCCCC3)C1=O)C(N)=O)C4CCCCC4
+CC1N=C(c2cc(ccc2NC1=O)[N+](=O)[O-])C3CCCCC3
+CC1N=C(c2cc(ccc2N(C)C1=O)[N+](=O)[O-])C3CCCCC3
+CCCCN1C(=O)C(C)N=C(c2cc(ccc12)[N+](=O)[O-])C3CCCCC3
+CC(C)CCN1C(=O)C(C)N=C(c2cc(ccc12)[N+](=O)[O-])C3CCCCC3
+CC1N=C(c2cc(ccc2N(CC3CCCCC3)C1=O)[N+](=O)[O-])C4CCCCC4
+CC1N=C(c2ccccc2)c3ccccc3NC1=O
+CC1N=C(c2ccccc2)c3ccccc3N(C)C1=O
+CCCCN1C(=O)C(C)N=C(c2ccccc2)c3ccccc13
+CC(C)CCN1C(=O)C(C)N=C(c2ccccc2)c3ccccc13
+CC1N=C(c2ccccc2)c3ccccc3N(CC4CCCCC4)C1=O
+CC1N=C(c2ccccc2)c3cc(Cl)ccc3NC1=O
+CC1N=C(c2ccccc2)c3cc(Cl)ccc3N(C)C1=O
+CCCCN1C(=O)C(C)N=C(c2ccccc2)c3cc(Cl)ccc13
+CC(C)CCN1C(=O)C(C)N=C(c2ccccc2)c3cc(Cl)ccc13
+CC1N=C(c2ccccc2)c3cc(Cl)ccc3N(CC4CCCCC4)C1=O
+CC1N=C(c2ccccc2)c3cc(C#N)ccc3NC1=O
+CC1N=C(c2ccccc2)c3cc(C#N)ccc3N(C)C1=O
+CCCCN1C(=O)C(C)N=C(c2ccccc2)c3cc(C#N)ccc13
+CC(C)CCN1C(=O)C(C)N=C(c2ccccc2)c3cc(C#N)ccc13
+CC1N=C(c2ccccc2)c3cc(C#N)ccc3N(CC4CCCCC4)C1=O
+CC1N=C(c2ccccc2)c3cc(ccc3NC1=O)N(C)C
+CC1N=C(c2ccccc2)c3cc(ccc3N(C)C1=O)N(C)C
+CCCCN1C(=O)C(C)N=C(c2ccccc2)c3cc(ccc13)N(C)C
+CC(C)CCN1C(=O)C(C)N=C(c2ccccc2)c3cc(ccc13)N(C)C
+CC1N=C(c2ccccc2)c3cc(ccc3N(CC4CCCCC4)C1=O)N(C)C

package/package.json

@@ -2,7 +2,7 @@
   "name": "@datagrok/bio",
   "beta": false,
   "friendlyName": "Bio",
-  "version": "1.5.3",
+  "version": "1.5.4",
   "description": "Bio is a [package](https://datagrok.ai/help/develop/develop#packages) for the [Datagrok](https://datagrok.ai) platform",
   "repository": {
     "type": "git",

package/src/const.ts

@@ -2,4 +2,3 @@ import * as ui from 'datagrok-api/ui';
 import * as grok from 'datagrok-api/grok';
 import * as DG from 'datagrok-api/dg';
 
-export const mmSemType = 'Macromolecule';

package/src/package.ts

@@ -5,7 +5,6 @@ import * as DG from 'datagrok-api/dg';
 
 export const _package = new DG.Package();
 
-import {mmSemType} from './const';
 import {WebLogo, SeqColStats} from '@datagrok-libraries/bio/src/viewers/web-logo';
 import {VdRegionsViewer} from './viewers/vd-regions-viewer';
 import {runKalign, testMSAEnoughMemory} from './utils/multiple-sequence-alignment';
@@ -120,20 +119,23 @@ export async function multipleSequenceAlignmentAny(table: DG.DataFrame, col: DG.
 //top-menu: Bio | Composition Analysis
 //output: viewer result
 export async function compositionAnalysis(): Promise<void> {
-  const col = grok.shell.t.columns.bySemType('Macromolecule');//DG.SEMTYPE.MACROMOLECULE);
-  if (col === null) {
+  // Higher priority for columns with MSA data to show with WebLogo.
+  const tv = grok.shell.tv;
+  const df = tv.dataFrame;
+  const semTypeColList = df.columns.bySemTypeAll(DG.SEMTYPE.MACROMOLECULE);
+  let col: DG.Column | undefined = semTypeColList.find((col) => {
+    const units = col.getTag(DG.TAGS.UNITS);
+    return units ? units.indexOf('MSA') !== -1 : false;
+  });
+  if (!col)
+    col = semTypeColList[0];
+
+  if (!col) {
     grok.shell.error('Current table does not contain sequences');
     return;
   }
 
-  const wl = await col.dataFrame.plot.fromType('WebLogo', {});
-
-  for (const v of grok.shell.views) {
-    if (v instanceof DG.TableView && (v as DG.TableView).dataFrame.name === col.dataFrame.name) {
-      (v as DG.TableView).dockManager.dock(wl.root, 'down');
-      break;
-    }
-  }
+  tv.addViewer('WebLogo', {sequenceColumnName: col.name});
 }
 
 // helper function for importFasta
@@ -182,7 +184,7 @@ export function importFasta(fileContent: string): DG.DataFrame [] {
     (c) => WebLogo.getAlphabetSimilarity(stats.freq, c[1]));
   const maxCos = Math.max(...alphabetCandidatesSim);
   const alphabet = maxCos > 0.65 ? alphabetCandidates[alphabetCandidatesSim.indexOf(maxCos)][0] : 'UN';
-  sequenceCol.semType = mmSemType;
+  sequenceCol.semType = DG.SEMTYPE.MACROMOLECULE;
   const units: string = `fasta:${seqType}:${alphabet}`;
   sequenceCol.setTag(DG.TAGS.UNITS, units);
 

package/src/tests/convert-test.ts

@@ -0,0 +1,31 @@
+import {after, before, category, test, expect, expectObject} from '@datagrok-libraries/utils/src/test';
+
+import * as grok from 'datagrok-api/grok';
+import * as ui from 'datagrok-api/ui';
+import * as DG from 'datagrok-api/dg';
+
+// import {mmSemType} from '../const';
+// import {importFasta} from '../package';
+
+category('converters', () => {
+//   test('a', async () => {await _a();});
+//   test('b', async () => {await _b();});
+  test('testFastaToSeparator', async () => { await _testFastaToSeparator(); });
+  test('testSeparatorToFasta', async () => { await _testSeparatorToFasta(); });
+});
+
+// export async function _a() {
+//   expect(1, 1);
+// }
+// 
+// export async function _b() {
+//   expect(1, 2);
+// }
+
+export async function _testFastaToSeparator() {
+  expect(1, 1);
+}
+
+export async function _testSeparatorToFasta() {
+  expect(1, 2);
+}

package/src/tests/detectors-test.ts

@@ -4,7 +4,6 @@ import * as grok from 'datagrok-api/grok';
 import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
 
-import {mmSemType} from '../const';
 import {importFasta} from '../package';
 
 type DfReaderFunc = () => Promise<DG.DataFrame>;
@@ -94,6 +93,7 @@ MWRSWY-CKHP
     fastaCsv = 'FastaCsv',
     msaComplex = 'MsaComplex',
     idCsv = 'IdCsv',
+    sarSmallCsv = 'SarSmallCsv',
   }
 
   const samples: { [key: string]: string } = {
@@ -101,6 +101,7 @@ MWRSWY-CKHP
     'FastaCsv': 'System:AppData/Bio/samples/sample_FASTA.csv',
     'MsaComplex': 'System:AppData/Bio/samples/sample_MSA.csv',
     'IdCsv': 'System:AppData/Bio/samples/id.csv',
+    'SarSmallCsv': 'System:AppData/Bio/samples/sar-small.csv',
   };
 
   const _samplesDfs: { [key: string]: Promise<DG.DataFrame> } = {};
@@ -189,20 +190,24 @@ MWRSWY-CKHP
   test('samplesIdCsvNegativeID', async () => {
     await _testNeg(readSamplesCsv(Samples.idCsv), 'ID');
   });
+
+  test('samplesSarSmallCsvNegativeSmiles', async () => {
+    await _testNeg(readSamplesCsv(Samples.sarSmallCsv), 'smiles');
+  });
 });
 
 export async function _testNeg(readDf: DfReaderFunc, colName: string) {
   const df: DG.DataFrame = await readDf();
 
   const col: DG.Column = df.col(colName)!;
-  expect(col.semType === mmSemType, false);
+  expect(col.semType === DG.SEMTYPE.MACROMOLECULE, false);
 }
 
 export async function _testPos(readDf: DfReaderFunc, colName: string, units: string, separator: string) {
   const df: DG.DataFrame = await readDf();
 
   const col: DG.Column = df.col(colName)!;
-  expect(col.semType === mmSemType, true);
+  expect(col.semType === DG.SEMTYPE.MACROMOLECULE, true);
   expect(col.getTag(DG.TAGS.UNITS), units);
   if (separator)
     expect(col.getTag('separator'), separator);
@@ -213,7 +218,7 @@ export async function _testN1(csvDfN1: string) {
   await grok.data.detectSemanticTypes(dfN1);
 
   const col: DG.Column = dfN1.col('seq')!;
-  expect(col.semType, mmSemType);
+  expect(col.semType, DG.SEMTYPE.MACROMOLECULE);
   expect(col.getTag(DG.TAGS.UNITS), 'fasta:SEQ:NT');
 }
 
@@ -222,7 +227,7 @@ export async function _testAA1(csvDfAA1: string) {
   await grok.data.detectSemanticTypes(dfAA1);
 
   const col: DG.Column = dfAA1.col('seq')!;
-  expect(col.semType, mmSemType);
+  expect(col.semType, DG.SEMTYPE.MACROMOLECULE);
   expect(col.getTag(DG.TAGS.UNITS), 'fasta:SEQ:PT');
 }
 
@@ -231,7 +236,7 @@ export async function _testMsaN1(csvDfMsaN1: string) {
   await grok.data.detectSemanticTypes(dfMsaN1);
 
   const col: DG.Column = dfMsaN1.col('seq')!;
-  expect(col.semType, mmSemType);
+  expect(col.semType, DG.SEMTYPE.MACROMOLECULE);
   expect(col.getTag(DG.TAGS.UNITS), 'fasta:SEQ.MSA:NT');
 }
 
@@ -240,7 +245,7 @@ export async function _testMsaAA1(csvDfMsaAA1: string) {
   await grok.data.detectSemanticTypes(dfMsaAA1);
 
   const col: DG.Column = dfMsaAA1.col('seq')!;
-  expect(col.semType, mmSemType);
+  expect(col.semType, DG.SEMTYPE.MACROMOLECULE);
   expect(col.getTag(DG.TAGS.UNITS), 'fasta:SEQ.MSA:PT');
 }
 
@@ -249,7 +254,7 @@ export async function _testSepNt(csv: string, separator: string) {
   await grok.data.detectSemanticTypes(df);
 
   const col: DG.Column = df.col('seq')!;
-  expect(col.semType, mmSemType);
+  expect(col.semType, DG.SEMTYPE.MACROMOLECULE);
   expect(col.getTag(DG.TAGS.UNITS), 'separator:SEQ:NT');
   expect(col.getTag('separator'), separator);
 }
@@ -259,7 +264,7 @@ export async function _testSepPt(csv: string, separator: string) {
   await grok.data.detectSemanticTypes(df);
 
   const col: DG.Column = df.col('seq')!;
-  expect(col.semType, mmSemType);
+  expect(col.semType, DG.SEMTYPE.MACROMOLECULE);
   expect(col.getTag(DG.TAGS.UNITS), 'separator:SEQ:PT');
   expect(col.getTag('separator'), separator);
 }
@@ -269,7 +274,7 @@ export async function _testSepUn(csv: string, separator: string) {
   await grok.data.detectSemanticTypes(df);
 
   const col: DG.Column = df.col('seq')!;
-  expect(col.semType, mmSemType);
+  expect(col.semType, DG.SEMTYPE.MACROMOLECULE);
   expect(col.getTag(DG.TAGS.UNITS), 'separator:SEQ:UN');
   expect(col.getTag('separator'), separator);
 }
@@ -279,7 +284,7 @@ export async function _testSepMsaN1(csvDfSepMsaN1: string) {
   await grok.data.detectSemanticTypes(dfSepMsaN1);
 
   const col: DG.Column = dfSepMsaN1.col('seq')!;
-  expect(col.semType, mmSemType);
+  expect(col.semType, DG.SEMTYPE.MACROMOLECULE);
   expect(col.getTag(DG.TAGS.UNITS), 'separator:SEQ.MSA:NT');
 }
 
@@ -289,7 +294,7 @@ export async function _testSamplesFastaCsvPt() {
   await grok.data.detectSemanticTypes(df);
 
   const col: DG.Column = df.col('sequence')!;
-  expect(col.semType, mmSemType);
+  expect(col.semType, DG.SEMTYPE.MACROMOLECULE);
   expect(col.getTag(DG.TAGS.UNITS), 'fasta:SEQ:PT');
   expect(col.getTag('separator'), null);
 }
@@ -299,7 +304,7 @@ export async function _testSamplesFastaFastaPt() {
   const df: DG.DataFrame = importFasta(fasta)[0];
 
   const col: DG.Column = df.col('sequence')!;
-  expect(col.semType, mmSemType);
+  expect(col.semType, DG.SEMTYPE.MACROMOLECULE);
   expect(col.getTag(DG.TAGS.UNITS), 'fasta:SEQ:PT');
   expect(col.getTag('separator'), null);
 }
@@ -310,7 +315,7 @@ export async function _testSamplesPeptidesComplexUn() {
   await grok.data.detectSemanticTypes(df);
 
   const col: DG.Column = df.col('AlignedSequence')!;
-  expect(col.semType, mmSemType);
+  expect(col.semType, DG.SEMTYPE.MACROMOLECULE);
   expect(col.getTag(DG.TAGS.UNITS), 'separator:SEQ.MSA:UN');
   expect(col.getTag('separator'), '-');
 }

package/src/utils/convert.ts

@@ -1,11 +1,21 @@
 import * as DG from 'datagrok-api/dg';
 import * as ui from 'datagrok-api/ui';
+import {NotationConverter} from './notation-converter';
 
+/**
+ * Converts notations of a Macromolecule column
+ *
+ * @param {DG.column} col Column with 'Macromolecule' semantic type
+ */
 export function convert(col: DG.Column): void {
   const current = col.tags[DG.TAGS.UNITS];
   //TODO: read all notations
-  const notations = ['fasta:SEQ:NT', 'fasta:SEQ:PT', 'fasta:SEQ.MSA:NT', 'fasta:SEQ.MSA:PT', 'HELM'];
-  const choices = ui.choiceInput('convert to', '', notations.filter((e) => e !== current));
+  const units = [
+    'fasta',
+    'separator',
+    'HELM'
+  ];
+  const choices = ui.choiceInput('convert to', '', units.filter((e) => e !== current));
 
   ui.dialog('Convert sequence')
     .add(
@@ -17,7 +27,9 @@ export function convert(col: DG.Column): void {
     )
     .onOK(() => {
       //TODO: create new converted column
-      //col.dataFrame.columns.add();
+      const converter = new NotationConverter(col, choices.value!);
+      const newColumn = converter.convert();
+      col.dataFrame.columns.add(newColumn);
     })
     .show();
 }

package/src/utils/multiple-sequence-alignment.ts

@@ -29,12 +29,12 @@ function _fastaToStrings(fasta: string): string[] {
 /**
  * Runs Aioli environment with kalign tool.
  *
- * @param {DG.Column} col Column with sequences.
+ * @param {DG.Column} srcCol Column with sequences.
  * @param {boolean} isAligned Whether the column is aligned.
  * @return {Promise<DG.Column>} Aligned sequences.
  */
-export async function runKalign(col: DG.Column, isAligned = false) : Promise<DG.Column> {
-  let sequences = col.toList();
+export async function runKalign(srcCol: DG.Column, isAligned = false): Promise<DG.Column> {
+  let sequences = srcCol.toList();
 
   if (isAligned)
     sequences = sequences.map((v: string, _) => AlignedSequenceEncoder.clean(v).replace(/\-/g, ''));
@@ -55,15 +55,20 @@ export async function runKalign(col: DG.Column, isAligned = false) : Promise<DG.
   console.warn(output);
 
   const aligned = _fastaToStrings(buf).slice(0, sequences.length);
-  const alignedCol = DG.Column.fromStrings(`msa(${col.name})`, aligned);
-  alignedCol.setTag(DG.TAGS.UNITS, '');
-  alignedCol.semType = C.SEM_TYPES.Macro_Molecule;
-  return alignedCol;
+  const tgtCol = DG.Column.fromStrings(`msa(${srcCol.name})`, aligned);
+
+  // units
+  const srcUnits = srcCol.getTag(DG.TAGS.UNITS);
+  const tgtUnits = srcUnits.split(':').map((p, i) => i == 1 ? p + '.MSA' : p).join(':');
+
+  tgtCol.setTag(DG.TAGS.UNITS, tgtUnits);
+  tgtCol.semType = C.SEM_TYPES.Macro_Molecule;
+  return tgtCol;
 }
 
 export async function testMSAEnoughMemory(col: DG.Column): Promise<void> {
   const sequencesCount = col.length;
-  const delta = sequencesCount/100;
+  const delta = sequencesCount / 100;
 
   for (let i = delta; i < sequencesCount; i += delta) {
     try {

package/src/utils/notation-converter.ts

@@ -0,0 +1,131 @@
+import * as DG from 'datagrok-api/dg';
+
+// export const enum NOTATION {
+//   // these values can be changed to "user-friendly" ones later on
+//   FASTA = 'fasta',
+//   SEPARATOR = 'separator',
+//   HELM = 'helm'
+// }
+
+export class NotationConverter {
+  private _sourceColumn: DG.Column; // the column to be converted
+  private _currentUnits: string; // units of the form fasta:SEQ:NT, etc.
+  private _sourceNotation: string; // current notation (without :SEQ:NT, etc.)
+  private _targetNotation: string;
+
+  private get sourceColumn(): DG.Column { return this._sourceColumn; }
+  private get currentUnits(): string { return this._currentUnits; }
+  private get sourceNotation(): string { return this._sourceNotation; }
+  private get targetNotation(): string { return this._targetNotation; }
+
+  // these values can be changed to "user-friendly" ones later on
+  private _fasta = 'fasta';
+  private _separator = 'separator';
+  private _helm = 'helm';
+
+  public isFasta(): boolean { return this.sourceNotation == this._fasta; }
+  public isSeparator(): boolean { return this.sourceNotation == this._separator; }
+  public isHelm(): boolean { return this.sourceNotation == this._helm; }
+
+  private determineSourceNotation() : string {
+    if (this.currentUnits.toLowerCase().startsWith('fasta'))
+      return 'fasta';
+    else if (this.currentUnits.toLowerCase().startsWith('separator'))
+      return 'separator';
+    else
+      // TODO: handle possible exceptions
+      return 'HELM';
+  }
+
+  private convertFastaToSeparator(): DG.Column {
+    // TODO: implementation
+    const len = this.sourceColumn.length;
+    const newColName = 'converted';
+    const newColumn = DG.Column.fromList('string', newColName, new Array(len).fill('fasta2sep'));
+    newColumn.semType = 'Macromolecule';
+    return newColumn;
+  }
+
+  private convertFastaToHelm(): DG.Column {
+    // TODO: implementation
+    const len = this.sourceColumn.length;
+    const newColName = 'converted';
+    const newColumn = DG.Column.fromList('string', newColName, new Array(len).fill('fasta2helm'));
+    newColumn.semType = 'Macromolecule';
+    return newColumn;
+  }
+
+  private convertSeparatorToFasta(): DG.Column {
+    // TODO: implementation
+    const len = this.sourceColumn.length;
+    const newColName = 'converted';
+    const newColumn = DG.Column.fromList('string', newColName, new Array(len).fill('sep2fasta'));
+    newColumn.semType = 'Macromolecule';
+    return newColumn;
+  }
+
+  private convertSeparatorToHelm(): DG.Column {
+    // TODO: implementation
+    const len = this.sourceColumn.length;
+    const newColName = 'converted';
+    const newColumn = DG.Column.fromList('string', newColName, new Array(len).fill('sep2helm'));
+    newColumn.semType = 'Macromolecule';
+    return newColumn;
+  }
+
+  private convertHelmToFasta(): DG.Column {
+    // TODO: implementation
+    const len = this.sourceColumn.length;
+    const newColName = 'converted';
+    const newColumn = DG.Column.fromList('string', newColName, new Array(len).fill('helm2fasta'));
+    newColumn.semType = 'Macromolecule';
+    return newColumn;
+  }
+
+  private convertHelmToSeparator(): DG.Column {
+    // TODO: implementation
+    const len = this.sourceColumn.length;
+    const newColName = 'converted';
+    const newColumn = DG.Column.fromList('string', newColName, new Array(len).fill('helm2sep'));
+    newColumn.semType = 'Macromolecule';
+    return newColumn;
+  }
+
+  // TODO: write the bodies of converter methods
+  public convert() : DG.Column {
+    if (
+      this.sourceNotation == this._fasta &&
+      this.targetNotation == this._separator
+    )
+      return this.convertFastaToSeparator();
+    else if (
+      this.sourceNotation == this._fasta &&
+      this.targetNotation == this._helm
+    )
+      return this.convertFastaToHelm();
+    else if (
+      this.sourceNotation == this._separator &&
+      this.targetNotation == this._fasta
+    )
+      return this.convertSeparatorToFasta();
+    else if (
+      this.sourceNotation == this._separator &&
+      this.targetNotation == this._helm
+    )
+      return this.convertSeparatorToHelm();
+    else if (
+      this.sourceNotation == this._helm &&
+      this.targetNotation == this._fasta
+    )
+      return this.convertHelmToFasta();
+    else
+      return this.convertHelmToSeparator();
+  }
+
+  public constructor(col: DG.Column, target: string) {
+    this._sourceColumn = col;
+    this._currentUnits = this._sourceColumn.tags[DG.TAGS.UNITS];
+    this._sourceNotation = this.determineSourceNotation();
+    this._targetNotation = target;
+  }
+}

package/src/utils/sequence-space.ts

@@ -18,9 +18,9 @@ export async function sequenceSpace(spaceParams: ISequenceSpaceParams): Promise<
     const sepFinal = sep ? sep === '.' ? '\\\.' : sep : '-';
     const regex = new RegExp(sepFinal, 'g');
     if (Object.keys(AvailableMetrics['String']).includes(spaceParams.similarityMetric))
-      preparedData = spaceParams.seqCol.toList().map((v) => v.replace(regex, '')) as string[];
+      preparedData = spaceParams.seqCol.toList().map((v: string) => v.replace(regex, '')) as string[];
     else
-      preparedData = spaceParams.seqCol.toList().map((v) => v.replace(regex, '')) as string[];
+      preparedData = spaceParams.seqCol.toList().map((v: string) => v.replace(regex, '')) as string[];
   } else {
     preparedData = spaceParams.seqCol.toList();
   }
@@ -31,13 +31,13 @@ export async function sequenceSpace(spaceParams: ISequenceSpaceParams): Promise<
     spaceParams.similarityMetric as StringMetrics | BitArrayMetrics,
     spaceParams.options);
   const cols: DG.Column[] = spaceParams.embedAxesNames.map(
-    (name, index) => DG.Column.fromFloat32Array(name, sequenceSpaceResult.embedding[index]));
+    (name: string, index: number) => DG.Column.fromFloat32Array(name, sequenceSpaceResult.embedding[index]));
   return {distance: sequenceSpaceResult.distance, coordinates: new DG.ColumnList(cols)};
 }
 
 
 export function getEmbeddingColsNames(df: DG.DataFrame) {
   const axes = ['Embed_X', 'Embed_Y'];
-  const colNameInd = df.columns.names().filter((it) => it.includes(axes[0])).length + 1;
+  const colNameInd = df.columns.names().filter((it: string) => it.includes(axes[0])).length + 1;
   return axes.map((it) => `${it}_${colNameInd}`);
 }