Skip to main content

Table 3 Performance of OptNCMiner with the few-shot learning dataset

From: OptNCMiner: a deep learning approach for the discovery of natural compounds modulating disease-specific multi-targets

Target protein Recall AUROC Accuracy Count
Beta 2 adrenergic receptor 0.488 0.400 0.450 5
Estrogen receptor a 0.585 1.000 0.764 5
Isocitrate dehydrogenase 0.488 0.600 0.536 5
Mammalian target of rapamycin complex 1 0.537 0.889 0.663 9
Kappa opioid receptor 0.659 1.000 0.806 5
Peroxisome proliferator-activated receptor gamma 0.610 1.000 0.778 5
Cellular tumor antigen p53 0.537 0.857 0.664 7
Weighted average 0.555 0.829 0.665 41