Deep Evolutionary Learning for Molecular Design

In this paper, a prototypical deep evolutionary learning (DEL) process is proposed to integrate deep generative model and multi-objective evolutionary computation for molecular design. Our approach enables (1) evolutionary operations in the latent space of the generative model, rather than the structural space, to generate promising novel molecular structures for the next evolutionary generation, and (2) generative model fine-tuning using newly generated high-quality samples. Thus, DEL implements a data-model co-evolution concept which improves both sample population and generative model learning. Experiments on public datasets indicate that the sample population obtained by DEL exhibits improvement on property distributions, and dominates samples generated by other baseline molecular optimization algorithms. Furthermore, comparisons with a range of deep generative models show that DEL is beneficial for improving sample populations.

Automated summary

This paper proposes a prototypical deep evolutionary learning (DEL) process that integrates deep generative model and multi-objective evolutionary computation for molecular design. DEL enables evolutionary operations in the latent space of the generative model, generates promising novel molecular structures, and improves the generative model learning through fine-tuning. Experimental results show that DEL achieves improvement in property distributions and outperforms other baseline molecular optimization algorithms in generating samples. Additionally, comparisons with various deep generative models demonstrate the benefits of DEL in improving sample populations.