期刊
ACS CATALYSIS
卷 13, 期 21, 页码 13863-13895出版社
AMER CHEMICAL SOC
DOI: 10.1021/acscatal.3c02743
关键词
activity; artificial intelligence; biocatalysis; deep learning; protein design
Recent progress has been made in engineering biocatalysts using machine learning methods. These methods utilize experimental and simulation data to discover and annotate enzymes, as well as suggest beneficial mutations. The field is expanding to cover various aspects of protein engineering, but there are still challenges to overcome. This Perspective provides an overview of ongoing trends, highlights case studies, and discusses limitations of machine learning-based methods.
Recent progress in engineering highly promising biocatalysts has increasingly involved machine learning methods. These methods leverage existing experimental and simulation data to aid in the discovery and annotation of promising enzymes, as well as in suggesting beneficial mutations for improving known targets. The field of machine learning for protein engineering is gathering steam, driven by recent success stories and notable progress in other areas. It already encompasses ambitious tasks such as understanding and predicting protein structure and function, catalytic efficiency, enantioselectivity, protein dynamics, stability, solubility, aggregation, and more. Nonetheless, the field is still evolving, with many challenges to overcome and questions to address. In this Perspective, we provide an overview of ongoing trends in this domain, highlight recent case studies, and examine the current limitations of machine learning-based methods. We emphasize the crucial importance of thorough experimental validation of emerging models before their use for rational protein design. We present our opinions on the fundamental problems and outline the potential directions for future research.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据