跳到正文
arXiv cs.AI· Yichen Zhou, Jonathan Golob, Amir Mohammad Karimi Mamaghan, Stefan Bauer, Patrick Schwab·· 4 小时前AI 评分36

ViroGym:评估病毒蛋白的大规模真实基准

ViroGym: Realistic Large-Scale Benchmarks for Evaluating Viral Proteins

AI 导读

研究者推出 ViroGym 基准,系统评估蛋白质语言模型在病毒蛋白上的零样本突变效应预测能力,涵盖 79 个 DMS 实验(552,065 条突变序列、7 种表型读出)、21 个流感中和任务及 SARS-CoV-2 真实疫情预测任务。结果显示 ProGen2 系列在全部三类任务中表现最强,DMS 与中和任务表现可可靠预测模型在真实世界突变出现时的泛化能力。数据与代码已在 GitHub 公开。

正文 · 原文

View PDF HTML (experimental)

Abstract: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 this https URL
Subjects: Quantitative Methods (q-bio.QM); Artificial Intelligence (cs.AI)
Cite as: arXiv:2603.06740 [q-bio.QM]
  (or arXiv:2603.06740v3 [q-bio.QM] for this version)
  https://doi.org/10.48550/arXiv.2603.06740

arXiv-issued DOI via DataCite

Submission history

From: Yichen Zhou [view email]
[v1] Fri, 6 Mar 2026 08:38:43 UTC (4,693 KB)
[v2] Tue, 19 May 2026 11:09:15 UTC (4,248 KB)
[v3] Fri, 13 Nov 2026 13:45:07 UTC (4,270 KB)

来源:arXiv cs.AI · arxiv.org