Skip to main content
Fig. 4 | BMC Bioinformatics

Fig. 4

From: CASTELO: clustered atom subtypes aided lead optimization—a combined machine learning and molecular modeling method

Fig. 4

T-SNE projection of the CVAE latent representations. The top row uses a color map based on the simulation time. The middle and bottom rows use colors to distinguish clustering results respectively of our AI-enhanced model and of the RMSD. Here we depict the encoded representations generated by the CVAE model with \(f=32\) filters and \(d=5\) latent dimensions. The calculated cosine similarity values are 0.975, 0.871, 0.785, 0.960 and 0.882 between AI-enhanced cluster sizes and RMSD cluster sizes for five sweeteners from left to right, respectively

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us