1. Dual-Space Optimization: Improved Molecule Sequence Design by Latent Prompt Transformer
- Author
-
Kong, Deqian, Huang, Yuhao, Xie, Jianwen, Honig, Edouardo, Xu, Ming, Xue, Shuanghong, Lin, Pei, Zhou, Sanping, Zhong, Sheng, Zheng, Nanning, and Wu, Ying Nian
- Subjects
Computer Science - Machine Learning ,Quantitative Biology - Biomolecules - Abstract
Designing molecules with desirable properties, such as drug-likeliness and high binding affinities towards protein targets, is a challenging problem. In this paper, we propose the Dual-Space Optimization (DSO) method that integrates latent space sampling and data space selection to solve this problem. DSO iteratively updates a latent space generative model and a synthetic dataset in an optimization process that gradually shifts the generative model and the synthetic data towards regions of desired property values. Our generative model takes the form of a Latent Prompt Transformer (LPT) where the latent vector serves as the prompt of a causal transformer. Our extensive experiments demonstrate effectiveness of the proposed method, which sets new performance benchmarks across single-objective, multi-objective and constrained molecule design tasks.
- Published
- 2024