Skip to main content
Fig. 3 | Journal of Cheminformatics

Fig. 3

From: Exploration and augmentation of pharmacological space via adversarial auto-encoder model for facilitating kinase-centric drug development

Fig. 3

a Loss plot of PCM-AAE. b Performance comparison between non-balanced model (NB) and reconstructed model with augmented data from generators trained by PCM-AAE. Statistical significance of the difference between the performance of NB and PCM-AAE was determined by paired t-test. ns: p > 0.05; *p < 0.05; **p < 0.01; ***p < 0.001; ****p < 0.0001

Back to article page