ViroGym: 用于评估病毒蛋白的现实大规模基准
ViroGym: Realistic Large-Scale Benchmarks for Evaluating Viral Proteins
AI总结:
本文提出ViroGym,一个用于评估蛋白质语言模型在病毒蛋白上的表现的综合基准,通过三个任务评估pLMs:79个深入突变扫描实验、21个流感中和任务以及SARS-CoV-2的现实世界预测任务,发现ProGen2家族在所有任务中表现最佳。
摘要:
蛋白质语言模型(pLMs)在零样本预测错义变异效应方面显示出强大潜力,但对病毒蛋白的系统性基准评估仍然有限,这在需要提前预测新兴突变的工具方面是一个关键缺口。本文介绍ViroGym,一个全面的基准,评估pLMs在三个任务上的表现:79个覆盖真核病毒的深入突变扫描(DMS)实验,包含7个表型读数,552,065个突变序列;21个流感中和任务;以及SARS-CoV-2的现实世界大流行预测任务。我们对已建立的pLMs在适应度景观、抗原多样性及大流行预测任务上进行了基准测试,并发现ProGen2家族在所有三个任务中均表现最佳。关键的是,DMS和中和性能可靠地识别出能够泛化到现实世界突变的模型,即使它们所揭示的突变集几乎不重叠,这表明互补的体外基准能够捕捉到现实突变预测所需进化的约束条件。
英文摘要:
Protein language models (pLMs) have shown strong potential for zero-shot prediction of missense variant effects, yet systematic benchmarking on viral proteins remains limited, a critical gap given the need for proactive tools that can anticipate emerging mutations ahead of experimental validation. Here we introduce ViroGym, a comprehensive benchmark evaluating pLMs across three tasks: 79 deep mutational scanning (DMS) assays covering eukaryotic viruses with 552,065 mutated sequences across 7 phenotypic readouts, 21 influenza neutralisation tasks, and a real-world pandemic prediction task for SARS-CoV-2. We benchmark well-established pLMs on fitness landscapes, antigenic diversity, and pandemic forecasting, and find that the ProGen2 family consistently achieves the strongest performance across all three tasks. Crucially, DMS and neutralisation performance reliably identifies models that generalise to real-world emergence, even though the mutation sets they surface barely overlap, revealing that complementary in vitro benchmarks capture the evolutionary constraints needed for real-world mutation forecasting. The data and code supporting this study are publicly available on GitHub at https://github.com/GSK-AI/viroGym
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。