# ViroGym: Realistic Large-Scale Benchmarks for Evaluating Viral Proteins

arXiv: https://arxiv.org/abs/2603.06740 · HTML: https://mlsanity.com/paper/2603.06740/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 79 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 2 of 2)

- [ProGen2: Exploring the Boundaries of Protein Language Models](https://mlsanity.com/paper/2206.13517/) (2022)
- [Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval](https://mlsanity.com/paper/2205.13760/) (2022)

## Built on by (most cited first, 2 of 2)

- [A General Harness for Protein Foundation Model Fitness Prediction](https://mlsanity.com/paper/2609.34654/) (2026)
- [DRYLAB-Bench: Benchmarking the Biosecurity Risk of Agentic LLM Mutation Design](https://mlsanity.com/paper/2610.13116/) (2026)

## Abstract (arXiv)

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.