Skip to main content
Fig. 3 | Journal of Cheminformatics

Fig. 3

From: Leveraging 3D chemical similarity, target and phenotypic data in the identification of drug-protein and drug-adverse effect associations

Fig. 3

a Performance of the 3D drug-target model (AUROCs) in the hold-out validations extracting 20 and 40 % of the initial data into test sets. b Performance of the 3D drug-target model (AUROCs) using 8 Anatomical Therapeutic Chemical (ATC) categories as test sets: ACE inhibitors (A), Angiotensin II antagonists (B), Benzodiazepines (C), Beta-blocking agents (D), Fluoroquinolones (E), Imidazole/triazole derivatives (F), Nucleosides/Nucleotides (G) and Sulfonamides/urea derivatives (H). c AUROC values for the individual drug-target models

Back to article page