Multi-Objective Latent Space Optimization of Generative Molecular Design Models
This work addresses the challenge of efficiently designing molecules with multiple optimized properties for applications in drug discovery and materials science, representing an incremental advancement in generative molecular design.
The paper tackles the problem of improving generative molecular design models by proposing a multi-objective latent space optimization method, which uses iterative weighted retraining based on Pareto efficiency to enhance sampling efficiency for novel molecules with desired properties, resulting in significant performance improvements.
Molecular design based on generative models, such as variational autoencoders (VAEs), has become increasingly popular in recent years due to its efficiency for exploring high-dimensional molecular space to identify molecules with desired properties. While the efficacy of the initial model strongly depends on the training data, the sampling efficiency of the model for suggesting novel molecules with enhanced properties can be further enhanced via latent space optimization. In this paper, we propose a multi-objective latent space optimization (LSO) method that can significantly enhance the performance of generative molecular design (GMD). The proposed method adopts an iterative weighted retraining approach, where the respective weights of the molecules in the training data are determined by their Pareto efficiency. We demonstrate that our multi-objective GMD LSO method can significantly improve the performance of GMD for jointly optimizing multiple molecular properties.