Large language models design sequencedefined macromolecules via evolutionary optimization  

作　　者：Wesley F.Reinhart Antonia Statt 

机构地区：[1]Department of Materials Science and Engineering,Pennsylvania State University,University Park,16802 PA,USA [2]Institute for Computational and Data Sciences,Pennsylvania State University,University Park,16802 PA,USA [3]Department of Materials Science and Engineering,Grainger College of Engineering,University of Illinois Urbana-Champaign,Champaign,61801 IL,USA

出　　处：《npj Computational Materials》2024年第1期446-453,共8页计算材料学(英文)

基　　金：supported by the National Science Foundation under Grant No.DMR-2401663 and DMR-2401664.

摘　　要：We demonstrate the ability of a large language model to perform evolutionary optimization for materials discovery.Anthropic’s Claude 3.5 model outperforms an active learning scheme with handcrafted surrogate models and an evolutionary algorithm in selecting monomer sequences to produce targeted morphologies in macromolecular self-assembly.Utilizing pre-trained language models can potentially reduce the need for hyperparameter tuning while offering new capabilities such as self-reflection.The model performs this task effectively with orwithout context about the task itself,but domain-specific context sometimes results in faster convergence to good solutions.Furthermore,when this context is withheld,the model infers an approximate notion of the task(e.g.,calling it a protein folding problem).This work provides evidence of Claude 3.5’s ability to act as an evolutionary optimizer,a recently discovered emergent behavior of large language models,and demonstrates a practical use case in the study and design of soft materials.

关 键 词：offering EVOLUTIONARY FASTER 

分 类 号：H31[语言文字—英语]