SMILES-based deep generative scaffold decorator for de-novo drug design

Table 2 Results of the decoration for each of the non-dataset scaffolds

S	Generated		ChEMBL decoys			DRD2 decoys
S	Total	% act.	% act.	% diff	EOR	% act.	% diff	EOR
6	1864	78.3	49.5	28.9	1.6	66.6	11.7	1.2
7	15,724	45.4	1.0	44.4	44.2	10.6	34.8	4.3
8	2178	80.2	44.3	35.9	1.8	49.3	30.9	1.6
9	5362	85.4	3.1	82.3	27.9	7.0	78.4	12.2
10	1012	98.9	90.4	8.4	1.1	93.7	5.2	1.1

Total number of molecules sampled (Total); percent of generated molecules that are predicted as active (\(p_{active} \ge 0.5\)) by the APM (% act); For both the decoys decorated with ChEMBL fragments and DRD2 fragments from the training set: Percent of predicted active decoys (\(p_{active} \ge 0.5\)) (% act); difference between the generated predicted active percent and the predicted active percent of the decoys (% Diff); Enrichment Over Random (\(percent_{active} /percent_{decoy}\)) (EOR)

ISSN: 1758-2946