Analysis of training and seed bias in small molecules generated with a conditional graph-based variational autoencoder -- Insights for practical AI-driven molecule generation
This work addresses bias issues in AI-driven molecule generation for computational chemists and drug discovery, but it is incremental as it builds on existing VAE methods.
The study analyzed how seed and training bias affect molecule generation using a conditional graph-based variational autoencoder, finding that the model effectively produced molecules with desired activities and favorable properties, as verified by independent classifiers.
The application of deep learning to generative molecule design has shown early promise for accelerating lead series development. However, questions remain concerning how factors like training, dataset, and seed bias impact the technology's utility to medicine and computational chemists. In this work, we analyze the impact of seed and training bias on the output of an activity-conditioned graph-based variational autoencoder (VAE). Leveraging a massive, labeled dataset corresponding to the dopamine D2 receptor, our graph-based generative model is shown to excel in producing desired conditioned activities and favorable unconditioned physical properties in generated molecules. We implement an activity swapping method that allows for the activation, deactivation, or retention of activity of molecular seeds, and we apply independent deep learning classifiers to verify the generative results. Overall, we uncover relationships between noise, molecular seeds, and training set selection across a range of latent-space sampling procedures, providing important insights for practical AI-driven molecule generation.