Utilizing random Forest QSAR models with optimized parameters for target identification and its application to target-fishing server

Table 2 Performance comparison between different ratios of the number of ligands for positive-oversampling

Ratio (inactive/active)	1	10	20	30	40
Overall ROC AUC	0.961	0.956	0.956	0.955	0.955
Top 1 recall	0.549	0.549	0.549	0.549	0.549
Top 4 recall	0.823	0.822	0.822	0.822	0.822
Top 8 recall	0.857	0.856	0.855	0.855	0.855
Top 11 recall	0.868	0.866	0.865	0.865	0.865

ISSN: 1471-2105