计算机科学
杠杆(统计)
排名(信息检索)
水准点(测量)
机器学习
工作流程
数据挖掘
蛋白质工程
选择(遗传算法)
选型
人工智能
热稳定性
蛋白质功能
计算生物学
财产(哲学)
功能(生物学)
秩(图论)
蛋白质功能预测
学习排名
蛋白质-蛋白质相互作用
蛋白质设计
实验数据
蛋白质测序
训练集
集合预报
蛋白质法
计算模型
混合模型
特征选择
作者
David Harding-Larsen,Brianna M. Lax,Martina Escorial García,Catarina Mendonça,Felipe Mejía,Ditte Hededam Welner,Stanislav Mazurenko
出处
期刊:
[Cold Spring Harbor Laboratory]
日期:2026-02-10
被引量:1
标识
DOI:10.64898/2026.02.08.704628
摘要
Abstract Machine learning has repeatedly shown the ability to accelerate protein engineering, but many approaches demand large amounts of robust, high-quality training data as well as substantial computational expertise. While large pre-trained models can function as zero-shot proxies for predicting variant effects, selecting the best model for a given protein property is often non-trivial. Here, we introduce Protein Ranking using Informed Zero-shot Modelling (PRIZM), a two-phase workflow that first uses a high-quality low-N dataset to identify the most suitable pre-trained zero-shot model for a target protein property and then applies that model to rank and prioritize an in silico variant library for experimental testing. Across diverse benchmark datasets spanning multiple protein properties, PRIZM reliably separated low- from high-performing models using datasets of ∼20 labelled variants. We further demonstrate PRIZM in enzyme engineering case studies targeting sucrose synthase thermostability and glycosyltransferase activity, where PRIZM-guided selection identified improved variants, including gains of ∼3°C in apparent melting temperature and ∼20% higher relative activity. PRIZM provides an accessible, data-efficient route to leverage foundation models for protein design while requiring minimal experimental data.
科研通智能强力驱动
Strongly Powered by AbleSci AI