@datagrok/bio 1.7.2 → 1.7.5

package/files/samples/sample_SEPARATOR_PT.csv

@@ -0,0 +1,101 @@
+id,sequence
+1,M-F-I-T-M-F-C-M-F-W-L-F-I-F-I-L-M-M-L-I-F-F-M-E-A-M-I-K-P-M-L
+2,A-Q-M-T-M-F-C-I-M-F-F-L-M-L-M-F-I-I-M-I-M-F-M-I-L-E-A-M-K-K-M-L-N-A-I
+3,I-L-M-T-M-F-C-I-C-W-M-I-M-I-F-F-L-L-L-I-M-F-M-L-M-A-M-M-K-M-L-I-F-L
+4,F-Q-M-T-M-I-C-M-L-F-F-L-M-M-F-M-F-D-L-I-I-L-F-I-M-M-E-A-M-M-K-P-D-L-M-F-I
+5,L-L-M-T-M-F-C-F-F-M-M-L-L-M-F-F-M-F-M-I-M-F-M-Y-F-E-A-M-K-K-F-F-I-L-F
+6,A-M-M-T-M-F-C-F-M-L-I-M-M-F-I-L-L-F-I-D-I-I-M-E-A-M-L-K-L-D-N-F-I
+7,L-L-M-T-M-F-C-M-I-L-I-S-M-I-M-I-L-M-M-I-M-F-L-M-E-A-M-K-K-I-F-F-A-V
+8,L-I-M-T-M-F-C-M-L-I-L-I-F-M-L-M-D-F-M-I-I-M-I-F-F-E-A-M-F-K-M-L-F-L-M-F
+9,F-Q-M-T-M-F-C-L-M-I-F-M-W-I-F-M-M-M-M-I-L-D-I-F-I-E-A-M-I-K-F-I-N-L-F-M
+10,F-L-M-T-M-F-C-I-L-I-N-I-M-I-I-W-M-I-I-M-L-M-F-E-A-M-F-K-L-D-I-I-F
+11,F-F-M-T-M-F-C-M-M-I-F-L-L-L-I-M-I-I-I-M-I-M-D-M-I-M-E-A-M-K-K-M-M-D-I-I-I
+12,I-M-M-T-M-F-C-I-C-L-L-F-W-L-L-F-M-L-L-I-M-D-M-M-F-E-A-M-L-K-F-I-M-M-I
+13,M-Q-M-T-M-F-C-F-M-L-L-L-M-F-F-M-D-I-M-I-I-M-L-L-D-E-A-M-L-K-L-D-L-I-L
+14,L-Q-M-T-M-F-C-I-F-W-M-L-F-M-L-F-M-L-F-I-F-F-L-F-L-E-A-M-L-K-F-I-N-L-I
+15,I-I-M-T-M-F-C-M-I-M-I-I-S-I-F-F-I-I-M-I-M-L-F-I-F-E-A-M-I-K-L-D-I-I-A-M
+16,F-L-M-T-M-L-C-M-C-F-I-L-F-F-F-L-F-M-F-I-M-L-S-F-F-L-E-A-L-I-K-I-L-I-L-I
+17,F-Q-M-T-M-F-C-M-M-I-F-L-F-I-M-W-M-I-I-F-I-I-F-F-I-F-E-A-M-K-M-L-L-L-L
+18,M-F-M-T-M-F-C-M-C-I-M-F-W-I-F-D-I-I-I-I-I-L-F-L-I-E-A-M-L-K-L-F-F-I-I-V
+19,I-M-L-M-T-M-F-C-M-F-F-F-M-W-I-F-M-F-M-L-I-I-F-S-L-I-L-E-A-M-M-K-P-D-I-I-I
+20,A-F-L-T-M-F-C-F-M-W-L-L-M-L-M-F-L-F-L-I-M-I-I-I-D-E-A-M-I-K-L-F-F-L
+21,F-Q-M-T-M-F-C-F-L-L-M-S-F-L-M-I-I-M-I-F-I-L-M-F-F-D-E-A-M-F-K-I-L-N-F-I
+22,M-I-M-T-M-F-C-M-L-M-N-L-L-M-F-F-M-L-I-I-L-I-L-M-I-E-A-M-L-K-L-M-M-A-I
+23,M-I-M-T-M-F-C-M-I-I-L-M-F-H-M-M-M-F-L-I-F-I-L-Y-E-A-M-K-K-L-F-N-M-I-V
+24,L-F-T-M-F-C-M-C-W-M-I-M-I-F-W-I-I-I-L-M-I-M-I-F-L-A-M-K-K-P-M-F-L-F
+25,A-F-L-M-T-M-F-C-I-C-W-F-L-F-F-L-F-M-I-L-I-M-L-M-F-F-E-A-M-K-K-F-F-L-V
+26,L-L-M-T-M-F-C-M-C-M-N-M-M-M-F-M-L-I-M-M-I-L-M-S-Y-I-E-A-M-F-K-F-F-L-I
+27,L-Q-L-T-M-F-C-F-I-L-L-I-F-L-M-I-L-L-I-L-M-I-L-F-E-A-M-M-K-M-F-F-A-L
+28,I-Q-M-T-M-F-C-M-M-M-M-F-L-M-L-F-F-I-D-I-M-F-L-M-M-E-M-M-F-K-M-D-L-M-F-F
+29,M-M-T-M-F-C-I-W-I-F-M-M-I-L-D-M-M-F-F-I-I-M-I-I-A-M-M-M-F-L-L-I-I-V
+30,F-Q-M-T-M-F-C-M-M-L-F-M-F-I-L-W-D-I-F-I-M-I-S-M-L-E-A-M-M-K-L-D-I-I-M
+31,L-F-M-T-M-F-C-M-M-M-N-F-M-I-F-W-L-I-L-I-F-F-S-L-F-E-A-M-K-K-L-I-L-A-M
+32,A-F-M-T-M-F-C-M-F-L-W-F-I-L-H-L-W-I-F-F-I-M-M-L-I-M-I-E-A-M-I-K-I-D-I-A-V
+33,L-L-T-M-F-C-M-I-L-I-F-W-H-F-M-F-M-D-I-M-M-M-M-I-F-E-A-M-L-M-I-F-I-M-I
+34,I-M-M-T-M-F-C-F-C-F-L-I-F-H-M-M-I-F-D-I-M-I-S-M-I-E-A-M-K-K-I-I-M-L-L
+35,F-M-M-T-M-F-C-M-M-M-L-F-I-I-M-F-L-I-M-M-I-D-I-L-L-F-I-D-E-A-M-M-K-D-F-I-L
+36,I-M-M-T-M-F-C-M-I-I-L-F-M-F-M-F-M-M-I-I-I-M-L-F-F-M-L-E-A-M-F-K-M-M-F-F
+37,L-L-M-T-M-F-C-M-L-W-M-M-L-F-I-F-F-I-M-L-I-F-I-S-L-F-E-A-M-K-K-I-F-I-I-M
+38,F-I-M-T-M-F-C-M-M-L-L-L-F-F-F-I-I-L-D-I-M-L-M-F-I-E-A-M-K-K-L-L-L-L
+39,I-M-M-T-M-F-C-F-M-M-M-S-M-M-F-F-F-L-I-I-I-I-L-F-M-F-D-M-A-M-K-I-L-L-I
+40,M-F-M-T-M-F-C-M-F-I-L-I-L-L-L-W-I-I-D-I-M-F-M-L-D-E-A-M-K-K-P-D-F-L
+41,L-I-M-T-M-F-C-M-C-M-F-L-I-L-W-M-M-F-I-M-L-I-I-I-E-A-M-K-K-P-I-I-L-I
+42,A-F-M-T-M-F-C-F-M-M-M-F-M-H-F-M-L-I-F-I-F-M-I-F-M-E-A-M-K-K-F-F-L-F-L-M
+43,A-F-I-Q-M-T-M-L-C-M-C-M-L-L-M-F-F-L-D-I-F-I-I-I-I-F-L-D-E-A-M-M-K-P-L-M-L-L
+44,L-Q-M-T-M-F-C-M-F-M-I-I-L-F-D-M-I-M-M-M-M-M-E-A-M-L-K-I-M-I-F
+45,A-L-M-T-M-F-C-F-I-W-N-S-I-F-I-F-I-F-D-I-L-M-I-L-L-I-E-A-M-F-K-M-D-N-I-I
+46,L-M-M-T-M-F-C-L-M-L-F-S-W-L-M-W-L-M-I-I-F-I-I-M-M-I-L-E-A-M-L-K-P-L-F-A-F-V
+47,F-F-M-T-M-F-C-M-F-F-I-M-F-L-I-F-F-L-L-L-I-M-L-F-M-M-E-A-M-L-K-I-F-L
+48,L-M-M-M-T-M-F-C-I-F-M-L-L-F-F-F-F-M-F-I-M-M-M-F-D-E-A-M-F-K-M-D-M-I-L
+49,Q-I-T-M-F-C-I-F-F-M-F-I-I-M-W-L-F-F-F-L-F-F-L-F-E-A-M-L-K-M-I-M-A-L
+50,I-I-M-T-M-F-C-I-M-L-I-L-W-I-F-L-F-I-I-I-I-M-I-L-I-A-M-K-K-L-I-L-L-L
+51,I-L-M-T-M-F-C-M-M-L-I-I-F-F-F-M-L-F-F-I-L-I-I-L-D-F-F-F-E-A-M-L-K-I-D-M-M-I
+52,F-I-M-T-M-F-C-M-C-W-F-I-L-L-I-M-M-I-I-I-F-L-I-D-E-A-M-M-K-M-F-L-M-M
+53,F-I-M-T-M-F-C-M-L-L-M-F-S-L-M-F-F-M-M-M-I-L-I-F-Y-I-E-A-M-I-K-M-M-L-F-I
+54,I-Q-M-T-M-F-C-M-C-W-M-F-L-H-M-M-F-L-D-I-L-F-I-F-L-D-E-A-M-L-K-M-I-I-F-L
+55,F-M-M-T-M-F-C-M-L-I-L-M-M-H-L-F-F-F-I-I-M-D-M-I-E-A-M-L-K-M-D-M-L-V
+56,L-M-M-T-M-F-C-M-F-I-N-S-M-L-L-M-M-F-I-L-I-L-M-M-L-F-E-A-M-K-K-P-F-M-I-M
+57,M-L-M-T-M-F-C-L-I-M-N-F-F-M-F-L-M-F-M-I-M-M-M-E-A-M-F-K-M-L-M
+58,I-L-M-T-M-F-C-L-F-F-F-S-F-F-F-I-L-I-M-M-I-Y-I-E-A-M-L-K-I-M-M-I-L
+59,I-I-M-M-T-M-F-C-M-C-L-L-M-L-M-F-W-I-I-M-I-M-I-S-F-L-M-E-A-M-K-K-F-L-I-A-M
+60,I-F-M-T-M-F-C-M-M-F-N-S-F-L-I-F-W-I-I-L-M-F-F-L-L-I-L-E-A-M-M-K-P-L-N-L-V
+61,I-F-I-T-M-F-C-M-I-L-L-S-M-L-F-I-L-F-D-I-F-F-I-I-M-E-I-M-K-K-F-I-I-A-F
+62,I-M-M-T-M-F-C-F-C-M-I-M-F-M-F-I-L-F-L-I-L-F-L-D-E-A-M-M-K-M-L-I-L
+63,I-F-M-T-M-F-C-M-F-L-M-F-M-I-M-L-L-F-D-I-F-L-S-F-F-E-A-M-K-K-F-F-I-A-V
+64,I-Q-M-T-M-F-C-M-I-F-F-S-M-M-F-F-M-D-M-D-I-M-I-F-I-I-E-A-M-F-K-M-N-M-L-L
+65,L-F-M-T-M-F-C-M-F-L-L-M-F-I-L-F-F-I-I-M-D-F-Y-F-F-E-A-M-K-K-P-M-L-I-L-L
+66,A-M-M-T-M-F-C-M-L-L-M-M-F-H-M-L-D-F-I-F-D-F-F-M-E-A-M-K-K-M-M-M-L
+67,A-I-M-T-M-F-C-M-F-L-N-L-M-L-M-M-F-I-F-M-M-I-D-E-A-M-I-K-F-L-L-F-I
+68,M-F-M-T-M-F-C-M-F-I-I-F-L-I-I-M-M-D-L-I-I-M-I-I-M-L-E-A-M-I-F-I-L-I-L-L-L
+69,I-F-M-T-M-F-F-M-F-M-M-I-I-F-W-L-M-W-D-L-M-I-I-F-S-I-M-I-M-A-M-I-K-L-M-M-A-L
+70,I-L-M-T-M-F-C-M-M-L-F-L-L-F-F-F-L-I-I-I-I-F-S-M-M-E-A-M-M-K-P-D-I-M-M
+71,F-F-M-T-M-F-C-M-F-F-I-F-L-H-M-I-F-F-D-I-F-L-F-F-Y-L-E-A-M-M-K-P-M-F-F-I
+72,M-F-M-T-M-F-C-M-L-W-M-F-M-L-H-I-M-F-F-L-I-M-M-M-L-F-E-A-M-F-K-F-M-L-A-F
+73,A-I-M-T-M-F-C-M-M-I-M-M-I-M-L-F-F-L-L-I-L-M-F-L-I-E-A-M-F-K-F-I-F-F-M
+74,M-M-M-T-M-F-C-M-L-M-F-W-I-I-F-I-I-F-L-I-F-I-L-M-I-E-A-M-F-K-M-I-N-I-V
+75,L-L-M-T-M-F-C-M-L-I-M-L-I-M-L-W-L-M-D-I-M-M-M-L-I-E-A-M-K-K-P-L-M-F-F-L
+76,L-Q-I-T-M-F-I-M-M-W-I-L-L-F-M-I-F-I-F-I-L-F-F-E-A-M-M-K-F-M-L-F
+77,I-L-M-T-M-F-C-I-F-F-I-F-F-M-F-M-F-M-F-F-I-M-F-F-L-I-E-A-M-K-K-L-D-I-M-L
+78,M-L-M-T-M-L-C-M-M-M-F-S-L-L-I-F-I-F-L-D-I-I-I-F-I-L-E-A-M-L-K-F-M-M-I
+79,I-L-M-T-M-F-C-M-C-M-M-M-I-M-M-I-I-I-I-M-D-S-F-L-E-A-M-K-K-P-M-M-M-I
+80,Q-M-T-M-F-C-M-M-F-F-I-I-H-M-M-I-I-F-F-M-D-L-I-M-M-L-A-M-K-K-P-D-M-A-I
+81,L-L-M-T-M-I-C-I-L-F-F-M-F-M-F-L-M-M-L-I-I-M-F-L-Y-F-E-A-M-M-K-M-L-N-I-I
+82,M-M-M-M-F-C-M-F-I-F-F-I-H-F-M-L-I-L-I-M-L-I-Y-M-M-I-M-K-I-M-M-N-M-L
+83,A-L-M-T-M-F-C-M-F-I-F-F-M-L-M-M-M-I-I-I-F-F-F-F-E-A-M-M-K-M-F-I-F-V
+84,A-L-M-T-M-F-C-M-W-L-I-L-M-W-F-M-I-I-I-L-M-M-D-E-A-M-K-K-L-L-N-I-L
+85,L-I-I-M-T-M-F-C-M-M-L-L-L-I-I-M-M-F-L-I-F-I-F-L-L-E-A-M-I-K-F-L-L-F-L-L
+86,M-L-M-T-M-F-C-M-L-L-M-F-H-F-L-I-M-M-I-L-I-S-Y-F-E-A-M-K-K-L-I-F-M-L
+87,F-I-M-T-M-F-C-M-M-I-F-I-F-F-F-M-F-D-I-I-L-S-M-M-A-M-F-K-I-D-L-I-M
+88,F-M-T-M-F-C-M-M-W-L-S-L-F-F-M-F-L-I-L-F-F-I-F-I-E-A-M-F-K-L-M-N-F-V
+89,M-M-M-T-M-M-C-M-L-L-I-M-F-L-F-M-F-I-M-F-I-F-M-L-I-E-A-M-K-K-L-D-L-L-I
+90,A-F-M-T-M-F-C-F-M-F-I-S-W-M-M-I-I-F-M-L-I-M-F-I-L-F-E-A-M-M-K-M-F-F-F-L
+91,L-I-M-T-M-F-C-M-I-W-F-I-M-H-F-L-I-L-M-L-I-M-I-L-Y-L-E-A-M-F-K-P-L-I-F-F
+92,M-I-M-T-M-F-C-M-F-I-N-L-W-I-F-F-L-L-D-I-F-F-L-I-M-E-A-M-K-L-D-M-I-M
+93,L-L-M-T-M-F-C-M-F-I-I-M-L-F-F-L-F-M-F-L-I-M-F-F-I-D-E-A-M-F-K-P-L-F-I-M
+94,F-F-M-T-M-F-C-I-F-F-M-S-L-H-L-F-M-L-L-I-I-F-M-F-D-E-A-M-K-K-M-L-L-F-I
+95,I-F-F-T-M-F-L-I-F-L-L-F-I-M-M-M-I-D-M-I-I-F-I-L-L-E-A-M-K-K-P-M-F-I-I
+96,M-F-M-M-T-M-F-C-F-M-I-I-F-F-M-M-M-D-I-M-I-I-M-D-F-I-L-E-A-M-L-K-I-F-L-I-I-I
+97,I-I-M-T-M-F-C-M-I-I-N-M-L-F-F-D-L-L-I-I-I-L-L-E-A-M-L-K-F-D-M-F-F
+98,M-L-M-T-M-F-C-M-L-L-I-M-F-M-I-L-I-L-M-F-I-F-L-L-Y-D-E-A-M-K-K-M-L-M-L-I
+99,L-F-M-T-M-F-C-M-L-I-N-S-L-I-M-I-F-F-D-I-I-I-F-L-E-A-M-F-K-F-F-L-I-L-L
+100,F-L-M-T-M-F-C-M-M-M-F-S-M-M-M-M-F-I-I-F-M-L-L-I-E-A-M-L-K-I-F-N-A-L

package/package.json

@@ -2,7 +2,7 @@
   "name": "@datagrok/bio",
   "beta": false,
   "friendlyName": "Bio",
-  "version": "1.7.2",
+  "version": "1.7.5",
   "description": "Bio is a [package](https://datagrok.ai/help/develop/develop#packages) for the [Datagrok](https://datagrok.ai) platform",
   "repository": {
     "type": "git",
@@ -11,12 +11,13 @@
   },
   "dependencies": {
     "@biowasm/aioli": ">=2.4.0",
-    "@datagrok-libraries/bio": "^2.5.0",
+    "@datagrok-libraries/bio": "2.8.3",
     "@datagrok-libraries/utils": "^1.0.0",
     "@datagrok-libraries/ml": "^2.0.10",
     "cash-dom": "latest",
     "datagrok-api": "^1.4.12",
     "dayjs": "latest",
+    "rxjs": "^6.5.5",
     "ts-loader": "^9.2.5",
     "typescript": "^4.4.2",
     "openchemlib": "6.0.1"

package/src/const.ts

@@ -2,3 +2,24 @@ import * as ui from 'datagrok-api/ui';
 import * as grok from 'datagrok-api/grok';
 import * as DG from 'datagrok-api/dg';
 
+export const jsonSdfMonomerLibDict = {
+    "monomerType": null, 
+    "smiles": null, 
+    "name": "MonomerName", 
+    "author": null, 
+    "molfile": "molecule", 
+    "naturalAnalog": "MonomerNaturalAnalogCode", 
+    "rgroups": "MonomerCaps",
+    "createDate": null, 
+    "id": null, 
+    "polymerType": "MonomerType", 
+    "symbol": "MonomerCode"
+}
+
+export const RGROUP_FIELD = "rgroups";
+export const CAP_GROUP_SMILES = "capGroupSmiles";
+export const RGROUP_ALTER_ID = "alternateId";
+export const CAP_GROUP_NAME = "capGroupName";
+export const RGROUP_LABEL = "label";
+export const MONOMER_SYMBOL = "symbol";
+export const SDF_MONOMER_NAME = "MonomerName";

package/src/package-test.ts

@@ -8,8 +8,8 @@ import './tests/detectors-test';
 import './tests/msa-tests';
 import './tests/sequence-space-test';
 import './tests/activity-cliffs-tests';
-import './tests/splitter-test';
-import './tests/renderer-test';
+import './tests/splitters-test';
+import './tests/renderers-test';
 import './tests/convert-test';
 
 export const _package = new DG.Package();

package/src/package.ts

@@ -11,18 +11,14 @@ import {runKalign, testMSAEnoughMemory} from './utils/multiple-sequence-alignmen
 import {SequenceAlignment, Aligned} from './seq_align';
 import {Nucleotides} from '@datagrok-libraries/bio/src/nucleotides';
 import {Aminoacids} from '@datagrok-libraries/bio/src/aminoacids';
-import {convert} from './utils/convert';
 import {getEmbeddingColsNames, sequenceSpace} from './utils/sequence-space';
 import {AvailableMetrics} from '@datagrok-libraries/ml/src/typed-metrics';
 import {getActivityCliffs} from '@datagrok-libraries/ml/src/viewers/activity-cliffs';
 import {sequenceGetSimilarities, drawTooltip} from './utils/sequence-activity-cliffs';
-import {getMolfilesFromSeq, HELM_CORE_LIB_FILENAME} from './utils/utils';
+import {createJsonMonomerLibFromSdf, 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';
-import { delay } from '@datagrok-libraries/utils/src/test';
-import { TableView } from 'datagrok-api/dg';
+import {convert} from './utils/convert';
 
 //tags: init
 export async function initBio(): Promise<void> {
@@ -175,21 +171,22 @@ export async function toAtomicLevel(df: DG.DataFrame, macroMolecule: DG.Column):
   if (!checkInputColumn(macroMolecule, 'To Atomic Level'))
     return;
 
-  let currentView: TableView;
-  for (let view of grok.shell.tableViews) {
-    if (df.name === view.name) {
+  let currentView: DG.TableView;
+  for (const view of grok.shell.tableViews) {
+    if (df.name === view.name)
       currentView = view;
-    }
   }
-  const file = await _package.files.readAsText('tests/sar-small.csv');
-  const df2 = DG.DataFrame.fromCsv(file);
-  const v = grok.shell.addTableView(df2);
-  setTimeout(()=> {
+
+  // Some hack to activate Chem Molecule rendering
+  const file2 = await _package.files.readAsText('tests/sar-small.csv');
+  const df2 = DG.DataFrame.fromCsv(file2);
+  const v2 = grok.shell.addTableView(df2);
+  setTimeout(() => {
     grok.shell.closeTable(df2);
-    v.close();
+    v2.close();
     grok.shell.v = currentView;
   }, 100);
-  
+
   const monomersLibFile = await _package.files.readAsText(HELM_CORE_LIB_FILENAME);
   const monomersLibObject: any[] = JSON.parse(monomersLibFile);
   const atomicCodes = getMolfilesFromSeq(macroMolecule, monomersLibObject);
@@ -199,7 +196,6 @@ export async function toAtomicLevel(df: DG.DataFrame, macroMolecule: DG.Column):
   col.semType = DG.SEMTYPE.MOLECULE;
   col.tags[DG.TAGS.UNITS] = 'molblock';
   df.columns.add(col, true);
-
 }
 
 
@@ -248,7 +244,15 @@ export async function compositionAnalysis(): Promise<void> {
     return;
   }
 
-  tv.addViewer('WebLogo', {sequenceColumnName: col.name});
+  const wlViewer = tv.addViewer('WebLogo', {sequenceColumnName: col.name});
+  grok.shell.tv.dockManager.dock(wlViewer, DG.DOCK_TYPE.DOWN, null, 'Composition analysis', 0.25);
+}
+
+//top-menu: Bio | Sdf to Json lib...
+//name: sdfToJsonLib
+//input: dataframe table
+export async function sdfToJsonLib(table: DG.DataFrame) {
+  const jsonMonomerLibrary = createJsonMonomerLibFromSdf(table);   
 }
 
 // helper function for importFasta
@@ -328,7 +332,7 @@ export function importFasta(fileContent: string): DG.DataFrame [] {
   ])];
 }
 
-//name: Bio | Convert
+//name: Bio | Convert ...
 //friendly-name: Bio | Convert
 //tags: panel, bio
 //input: column col {semType: Macromolecule}

package/src/tests/WebLogo-test.ts

@@ -61,6 +61,24 @@ XZJ{}2
   test('testPickupPaletteX', async () => { await _testPickupPaletteX(csvDfX); });
 });
 
+category('WebLogo.monomerToText', () => {
+  test('longMonomerSingle', async () => {
+    await expect(WebLogo.monomerToText('S'), 'S');
+  });
+  test('longMonomerShort', async () => {
+    await expect(WebLogo.monomerToText('Short'), 'Short');
+  });
+  test('longMonomerLong56', async () => {
+    await expect(WebLogo.monomerToText('Long56'), 'Long5…');
+  });
+  test('longMonomerComplexFirstPartShort', async () => {
+    await expect(WebLogo.monomerToText('Long-long'), 'Long…');
+  });
+  test('longMonomerComplexFirstPartLong56', async () => {
+    await expect(WebLogo.monomerToText('Long56-long'), 'Long5…');
+  });
+});
+
 
 export async function _testGetStats(csvDfN1: string) {
   const dfN1: DG.DataFrame = DG.DataFrame.fromCsv(csvDfN1);

package/src/tests/activity-cliffs-tests.ts

@@ -1,7 +1,9 @@
 import {after, before, category, expect, expectFloat, test} from '@datagrok-libraries/utils/src/test';
+
 import * as DG from 'datagrok-api/dg';
-import {createTableView, readDataframe} from './utils';
-import {_package} from '../package-test';
+import * as grok from 'datagrok-api/grok';
+
+import {readDataframe} from './utils';
 import {getEmbeddingColsNames, sequenceSpace} from '../utils/sequence-space';
 import {drawTooltip, sequenceGetSimilarities} from '../utils/sequence-activity-cliffs';
 import {getActivityCliffs} from '@datagrok-libraries/ml/src/viewers/activity-cliffs';
@@ -12,8 +14,15 @@ category('activityCliffs', async () => {
   let actCliffsDf: DG.DataFrame;
 
   before(async () => {
-    actCliffsTableView = await createTableView('sample_MSA.csv');
-    actCliffsDf = await readDataframe('sample_MSA.csv');
+    actCliffsDf = await readDataframe('samples/sample_MSA.csv');
+    actCliffsTableView = grok.shell.addTableView(actCliffsDf);
+
+    actCliffsDf = actCliffsTableView.dataFrame;
+  });
+
+  after(async () => {
+    grok.shell.closeTable(actCliffsDf);
+    actCliffsTableView.close();
   });
 
   test('activityCliffsOpen', async () => {
@@ -41,10 +50,6 @@ category('activityCliffs', async () => {
 
     const cliffsLink = (Array.from(scatterPlot.root.children) as Element[])
       .filter((it) => it.className === 'ui-btn ui-btn-ok');
-    expect((cliffsLink[0] as HTMLElement).innerText, '101 cliffs');
-  });
-
-  after(async () => {
-    actCliffsTableView.close();
+    expect((cliffsLink[0] as HTMLElement).innerText, '105 cliffs');
   });
 });

package/src/tests/convert-test.ts

@@ -4,7 +4,7 @@ import * as grok from 'datagrok-api/grok';
 import * as DG from 'datagrok-api/dg';
 
 import {ConverterFunc, DfReaderFunc} from './types';
-import {NOTATION, NotationConverter} from '../utils/notation-converter';
+import {NOTATION, NotationConverter} from '@datagrok-libraries/bio/src/utils/notation-converter';
 
 // import {mmSemType} from '../const';
 // import {importFasta} from '../package';

package/src/tests/detectors-test.ts

@@ -102,6 +102,7 @@ MWRSWY-CKHP
 
   const enum Samples {
     peptidesComplex = 'peptidesComplex',
+    peptidesSimple = 'peptidesSimple',
     fastaCsv = 'fastaCsv',
     fastaFasta = 'fastaFasta',
     fastaPtCsv = 'fastaPtCsv',
@@ -115,15 +116,16 @@ MWRSWY-CKHP
   }
 
   const samples: { [key: string]: string } = {
-    'peptidesComplex': 'System:AppData/Bio/tests/peptides_complex_msa.csv',
     'fastaCsv': 'System:AppData/Bio/samples/sample_FASTA.csv',
     'fastaFasta': 'System:AppData/Bio/samples/sample_FASTA.fasta',
     'fastaPtCsv': 'System:AppData/Bio/samples/sample_FASTA_PT.csv',
     'msaComplex': 'System:AppData/Bio/samples/sample_MSA.csv',
     'helmCsv': 'System:AppData/Bio/samples/sample_HELM.csv',
+    'peptidesComplex': 'System:AppData/Bio/tests/peptides_complex_msa.csv',
+    'peptidesSimple': 'System:AppData/Bio/tests/peptides_simple_msa.csv',
     'testDemogCsv': 'System:AppData/Bio/tests/testDemog.csv',
     'testHelmCsv': 'System:AppData/Bio/tests/testHelm.csv',
-    'testIdCsv': 'System:AppData/Bio/tests/id.csv',
+    'testIdCsv': 'System:AppData/Bio/tests/testId.csv',
     'testSmilesCsv': 'System:AppData/Bio/tests/testSmiles.csv',
     'testSmiles2Csv': 'System:AppData/Bio/tests/testSmiles2.csv',
   };
@@ -228,6 +230,10 @@ MWRSWY-CKHP
     await _testPos(readSamples(Samples.fastaFasta, readFileFasta), 'sequence', 'fasta:SEQ:PT');
   });
 
+  // peptidesComplex contains monomers with spaces in AlignedSequence columns, which are forbidden
+  // test('samplesPeptidesComplexPositiveAlignedSequence', async () => {
+  //   await _testPos(readSamples(Samples.peptidesComplex), 'AlignedSequence', 'separator:SEQ:UN', '-');
+  // });
   test('samplesPeptidesComplexNegativeID', async () => {
     await _testNeg(readSamples(Samples.peptidesComplex), 'ID');
   });

package/src/tests/{renderer-test.ts → renderers-test.ts}

@@ -1,18 +1,23 @@
-import {after, before, category, test, expect, expectObject} from '@datagrok-libraries/utils/src/test';
+import {after, before, category, expect, test} 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 {importFasta, multipleSequenceAlignmentAny} from '../package';
+import {readDataframe} from './utils';
+import {convertDo} from '../utils/convert';
+import {NOTATION} from '@datagrok-libraries/bio/src/utils/notation-converter';
 
 category('renderers', () => {
   let tvList: DG.TableView[];
+  let dfList: DG.DataFrame[];
 
   before(async () => {
     tvList = [];
+    dfList = [];
   });
 
   after(async () => {
+    dfList.forEach((df: DG.DataFrame) => { grok.shell.closeTable(df); });
     tvList.forEach((tv: DG.TableView) => tv.close());
   });
 
@@ -20,39 +25,49 @@ category('renderers', () => {
     await _testAfterMsa();
   });
 
+  test('afterConvert', async () => {
+    await _testAfterConvert();
+  });
+
   async function _testAfterMsa() {
     const fastaTxt: string = await grok.dapi.files.readAsText('System:AppData/Bio/samples/sample_FASTA.fasta');
     const df: DG.DataFrame = importFasta(fastaTxt)[0];
-
-    const srcSeqCol: DG.Column | null = df.col('sequence');
-    expect(srcSeqCol !== null, true);
-    console.log('Bio: tests/renderers/afterMsa, src data loaded');
-
     const tv: DG.TableView = grok.shell.addTableView(df);
+    await grok.data.detectSemanticTypes(df);
     console.log('Bio: tests/renderers/afterMsa, table view');
 
-    await grok.data.detectSemanticTypes(df);
-    console.log('Bio: tests/renderers/afterMsa, detectSemanticTypes');
+    const srcSeqCol: DG.Column | null = df.col('sequence');
+    expect(srcSeqCol !== null, true);
 
-    console.log('Bio: tests/renderers/afterMsa, src before test semType' +
+    console.log('Bio: tests/renderers/afterMsa, src before test ' +
       `semType="${srcSeqCol!.semType}", units="${srcSeqCol!.getTag(DG.TAGS.UNITS)}", ` +
       `cell.renderer="${srcSeqCol!.getTag('cell.renderer')}"`);
     expect(srcSeqCol!.semType, DG.SEMTYPE.MACROMOLECULE);
     expect(srcSeqCol!.getTag(DG.TAGS.UNITS), 'fasta:SEQ:PT');
     expect(srcSeqCol!.getTag('cell.renderer'), 'Macromolecule');
-    console.log('Bio: tests/renderers/afterMsa, src semType tested');
 
     const msaSeqCol: DG.Column | null = await multipleSequenceAlignmentAny(df, srcSeqCol!);
-    console.log('Bio: tests/renderers/afterMsa, msaSeqCol created');
-
     tv.grid.invalidate();
-    console.log('Bio: tests/renderers/afterMsa, tv.grid invalidated');
 
     expect(msaSeqCol!.semType, DG.SEMTYPE.MACROMOLECULE);
     expect(msaSeqCol!.getTag(DG.TAGS.UNITS), 'fasta:SEQ.MSA:PT');
     expect(msaSeqCol!.getTag('cell.renderer'), 'Macromolecule');
-    console.log('Bio: tests/renderers/afterMsa, msa semType tested');
 
+    dfList.push(df);
     tvList.push(tv);
   }
+
+  async function _testAfterConvert() {
+    const csv: string = await grok.dapi.files.readAsText('System:AppData/Bio/samples/sample_FASTA_PT.csv');
+    const df: DG.DataFrame = DG.DataFrame.fromCsv(csv);
+    const tv: DG.TableView = grok.shell.addTableView(df);
+    await grok.data.detectSemanticTypes(df);
+
+    const srcCol: DG.Column = df.col('sequence')!;
+    const tgtCol: DG.Column = await convertDo(srcCol, NOTATION.SEPARATOR, '/');
+    expect(tgtCol.getTag('cell.renderer'), 'Macromolecule');
+
+    tvList.push(tv);
+    dfList.push(df);
+  };
 });

package/src/tests/sequence-space-test.ts

@@ -1,16 +1,20 @@
-import {before, category, test, expect} from '@datagrok-libraries/utils/src/test';
+import {after, before, category, test, expect} from '@datagrok-libraries/utils/src/test';
 import * as DG from 'datagrok-api/dg';
 import {sequenceSpace} from '../utils/sequence-space';
 import {readDataframe} from './utils';
-//import * as grok from 'datagrok-api/grok';
+import * as grok from 'datagrok-api/grok';
 
 category('sequenceSpace', async () => {
   let testFastaDf: DG.DataFrame;
 
   before(async () => {
-    testFastaDf = await readDataframe('sample_FASTA.csv');
+    testFastaDf = await readDataframe('samples/sample_FASTA.csv');
+    // await grok.data.detectSemanticTypes(testFastaDf);
   });
 
+  after(async () => {
+    grok.shell.closeTable(testFastaDf);
+  });
 
   test('sequenceSpaceOpens', async () => {
     const sequenceSpaceParams = {

package/src/tests/splitters-test.ts

@@ -0,0 +1,35 @@
+import {after, before, category, test, expect, expectArray} 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 {WebLogo, SplitterFunc} from '@datagrok-libraries/bio/src/viewers/web-logo';
+
+category('splitters', () => {
+  const helm1 = 'PEPTIDE1{meI.hHis.Aca.N.T.dE.Thr_PO3H2.Aca.D-Tyr_Et.Tyr_ab-dehydroMe.dV.E.N.D-Orn.D-aThr.Phe_4Me}$$$';
+
+  const helm2 = 'PEPTIDE1{meI.hHis.Hcy.Q.T.W.Q.Phe_4NH2.D-Tyr_Et.Tyr_ab-dehydroMe.dV.E.N.N.meK}$$$';
+
+  const data: { [key: string]: [string, string[]] } = {
+    helm1: [
+      'PEPTIDE1{meI.hHis.Aca.N.T.dE.Thr_PO3H2.Aca.D-Tyr_Et.Tyr_ab-dehydroMe.dV.E.N.D-Orn.D-aThr.Phe_4Me}$$$',
+      ['meI', 'hHis', 'Aca', 'N', 'T', 'dE', 'Thr_PO3H2', 'Aca', 'D-Tyr_Et',
+        'Tyr_ab-dehydroMe', 'dV', 'E', 'N', 'D-Orn', 'D-aThr', 'Phe_4Me']
+    ],
+    helm2: [
+      'PEPTIDE1{meI.hHis.Aca.N.T.dK.Thr_PO3H2.Aca.D-Tyr_Et.D-Dap.dV.E.N.pnG.Phe_4Me}$$$',
+      ['meI', 'hHis', 'Aca', 'N', 'T', 'dK', 'Thr_PO3H2', 'Aca',
+        'D-Tyr_Et', 'D-Dap', 'dV', 'E', 'N', 'pnG', 'Phe_4Me']
+    ],
+  };
+
+  test('helm1', async () => { await _testHelmSplitter(data.helm1[0], data.helm1[1]); });
+  test('helm2', async () => { await _testHelmSplitter(data.helm2[0], data.helm2[1]); });
+});
+
+export async function _testHelmSplitter(src: string, tgt: string[]) {
+  const res: string[] = WebLogo.splitterAsHelm(src);
+  console.debug(`Bio: tests: splitters: src=${JSON.stringify(src)}, res=${JSON.stringify(res)} .`);
+  expectArray(res, tgt);
+}
+

package/src/utils/cell-renderer.ts

@@ -9,6 +9,7 @@ import * as ui from 'datagrok-api/ui';
 
 const lru = new DG.LruCache<any, any>();
 const undefinedColor = 'rgb(100,100,100)';
+const grayColor = '#808080'
 
 function getPalleteByType(paletteType: string): SeqPalette {
   switch (paletteType) {
@@ -68,9 +69,9 @@ function printLeftOrCentered(
   g.textAlign = 'start';
   const colorPart = s.substring(0);
   let grayPart = separator;
-  if (last) {
+  if (last)
     grayPart = '';
-  }
+
   const textSize = g.measureText(colorPart + grayPart);
   const indent = 5;
 
@@ -81,7 +82,7 @@ function printLeftOrCentered(
     g.fillStyle = color;
     g.globalAlpha = transparencyRate;
     g.fillText(colorPart, x + dx1, y + dy);
-    g.fillStyle = '#808080';
+    g.fillStyle = grayColor;
     g.fillText(grayPart, x + dx2, y + dy);
   }
 
@@ -96,10 +97,29 @@ function printLeftOrCentered(
   }
 }
 
+function findMonomers(helmString: string) {
+  //@ts-ignore
+  const types = Object.keys(org.helm.webeditor.monomerTypeList());
+  const monomers: any = [];
+  const monomer_names: any = [];
+  for (var i = 0; i < types.length; i++) {
+    //@ts-ignore
+    monomers.push(new scil.helm.Monomers.getMonomerSet(types[i]));
+    Object.keys(monomers[i]).forEach(k => {
+      monomer_names.push(monomers[i][k].id);
+    });
+  }
+  const split_string = WebLogo.splitterAsHelm(helmString);
+  return new Set(split_string.filter(val => !monomer_names.includes(val)));
+}
+
 export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
   get name(): string { return 'macromoleculeSequence'; }
+
   get cellType(): string { return C.SEM_TYPES.Macro_Molecule; }
+
   get defaultHeight(): number { return 30; }
+
   get defaultWidth(): number { return 230; }
 
   /**
@@ -122,22 +142,47 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
     const cell = gridCell.cell;
     const tag = gridCell.cell.column.getTag(DG.TAGS.UNITS);
     if (tag === 'HELM') {
-      const host = ui.div([], {style: {width: `${w}px`, height: `${h}px`}});
-      host.setAttribute('dataformat', 'helm');
-      host.setAttribute('data', gridCell.cell.value);
-      gridCell.element = host;
-      //@ts-ignore
-      const canvas = new JSDraw2.Editor(host, {width: w, height: h, skin: 'w8', viewonly: true});
-      const formula = canvas.getFormula(true);
-      if (!formula) {
-        gridCell.element = ui.divText(gridCell.cell.value, {style: {color: 'red'}});
-      } else {
+      console.log(findMonomers(cell.value));
+      const monomers = findMonomers(cell.value);
+      if (monomers.size == 0) {
+        const host = ui.div([], {style: {width: `${w}px`, height: `${h}px`}});
+        host.setAttribute('dataformat', 'helm');
+        host.setAttribute('data', gridCell.cell.value);
         gridCell.element = host;
-        const molWeight = Math.round(canvas.getMolWeight() * 100) / 100;
-        const coef = Math.round(canvas.getExtinctionCoefficient(true) * 100) / 100;
-        const molfile = canvas.getMolfile();
-        const result = formula + ', ' + molWeight + ', ' + coef + ', ' + molfile;
-        lru.set(gridCell.cell.value, result);
+        //@ts-ignore
+        const canvas = new JSDraw2.Editor(host, {width: w, height: h, skin: 'w8', viewonly: true});
+        const formula = canvas.getFormula(true);
+        if (!formula) {
+          gridCell.element = ui.divText(gridCell.cell.value, {style: {color: 'red'}});
+        }
+        return;
+      }
+      if (monomers.size > 0) {
+        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';
+        let x1 = x;
+        const s: string = cell.value ?? '';
+        let subParts: string[] = WebLogo.splitterAsHelm(s);
+        let color = undefinedColor;
+        subParts.forEach((amino, index) => {
+          if (monomers.has(amino)) {
+            color = 'red';
+          } else {
+            color = grayColor;
+          }
+          g.fillStyle = undefinedColor;
+          let last = false;
+          if (index === subParts.length - 1)
+            last = true;
+          x1 = printLeftOrCentered(x1, y, w, h, g, amino, color, 0, true, 1.0, '/', last);
+        });
+        g.restore();
+        return;
       }
     } else {
       const [type, subtype, paletteType] = gridCell.cell.column.getTag(DG.TAGS.UNITS).split(':');
@@ -166,13 +211,15 @@ export class MacromoleculeSequenceCellRenderer extends DG.GridCellRenderer {
         color = palette.get(amino);
         g.fillStyle = undefinedColor;
         let last = false;
-        if (index === subParts.length - 1) {
+        if (index === subParts.length - 1)
           last = true;
-        }
-        x1 = printLeftOrCentered(x1, y, w, h, g, amino, color, 0, true, 1.0,  separator, last);
+
+        x1 = printLeftOrCentered(x1, y, w, h, g, amino, color, 0, true, 1.0, separator, last);
       });
 
       g.restore();
+      return;
+
     }
   }
 }