Benchmarking open-source tools for in silico antiviral drug discovery

TL;DR

This paper benchmarks open-source computational tools for in silico antiviral drug discovery, introduces a curated viral protein-ligand dataset, and evaluates model performance for predicting antiviral binding affinities.

Contribution

It presents a comprehensive benchmarking of 15 tools, a new antiviral dataset, and insights into model performance improvements through fine-tuning.

Findings

Boltz-2 and DrugFormDTA ranked highest among ML models

GNINA performed best among docking tools

Fine-tuning DrugFormDTA improved correlation from 0.5 to 0.7

Abstract

Antivirals are uniquely positioned to be deployed quickly during a new outbreak, especially when repurposed from approved drugs. Yet there are no FDA-approved antivirals for the majority of viral families with pandemic potential. Here we lay out the case for investing in technologies and techniques for antiviral drug discovery and designing antiviral combinations. We present a survey of open source datasets and computational tools for in silico antiviral drug discovery, with a particular focus on the latest AI-based systems and docking tools. We then present our custom dataset of 43,005 viral protein-ligand binding measurements that we curated from BindingDB and other sources. Importantly, we found that 31% of viral protein binding data in BindingDB required polyprotein sequences to be carefully split before the data were suitable for training or testing ML models. Using our custom dataset we fine-tuned the DrugFormDTA binding affinity prediction model (Khokhlov et al. 2025). We then benchmarked 15 open-source binding affinity prediction tools on a custom test set of 853 antiviral compounds spread across 16 different protein targets from 10 virus species. Models tested include Boltz-2, GNINA, FlowDock, Interformer, AutoDock-GPU, and others. We found that Boltz-2 and DrugFormDTA ranked highest overall among ML-based approaches, and GNINA did best among docking approaches, with notable variance across specific viral proteins. Fine-tuning DrugFormDTA on our custom cleaned antiviral dataset boosted performance from $r=0.5$ to $r=0.7$. As part of this work we also compiled a library of approved drugs and a comprehensive list of investigational and approved antiviral drugs that can be viewed at https://antivirals-database.radvac.org. Together, this work provides a foundation for future work towards new tools and platforms for rapid drug repurposing and rapid design of antiviral combinations.