Efficient Evolutionary Search Over Chemical Space with Large Language Models
Georgia Institute of Technology · University of Toronto / Vector Institute · Department of Chemistry, Vector Institute, University of Toronto · Massachusetts Institute of Technology · Harvard University · University of Wuppertal · Tsinghua University · University of California, Los Angeles · Cornell University · University of Toronto · Vector Institute
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
Molecular discovery, when formulated as an optimization problem, presents significant computational challenges because optimization objectives can be non-differentiable. Evolutionary Algorithms (EAs), often used to optimize black-box objectives in molecular discovery, traverse chemical space by performing random mutations and crossovers, leading to a large number of expensive objective evaluations. In this work, we ameliorate this shortcoming by incorporating chemistry-aware Large Language Models (LLMs) into EAs. Namely, we redesign crossover and mutation operations in EAs using LLMs trained on large corpora of chemical information. We perform extensive empirical studies on both commercial and open-source models on multiple tasks involving property optimization, molecular rediscovery, and structure-based drug design, demonstrating that the joint usage of LLMs with EAs yields superior performance over all baseline models across single- and multi-objective settings. We demonstrate that our algorithm improves both the quality of the final solution and convergence speed, thereby reducing the number of required objective evaluations.