FlashAffinity: Bridging the Accuracy-Speed Gap in Protein-Ligand Binding Affinity Prediction

Abstract

Accurate prediction of protein-ligand interactions is central to computational drug discovery. Recent foundation models such as Boltz-2 have achieved remarkable accuracy in binding affinity prediction, yet their prohibitive computational cost remains a major barrier to large-scale virtual screening. Here we introduce FlashBind, a lightweight structure-based model that achieves a 50x speedup over Boltz-2 at inference time by replacing expensive structure prediction with a fast docking model and substituting costly PairFormer modules with a streamlined EGNN architecture. FlashBind attains early enrichment competitive with Boltz-2 on standard virtual screening benchmarks and demonstrates strong generalization to enzyme-substrate specificity prediction. To evaluate real-world applicability, we apply FlashBind to target-based antibiotic screening against the essential bacterial proteins in E. coli and show that FlashBind substantially outperforms Boltz-2 and other virtual screening baselines. Notably, several top-ranked candidates exhibit potent inhibition of DnaG and effective bacterial growth inhibition against E. coli in wet-lab validation. Together, these results demonstrate that FlashBind bridges the gap between accuracy and efficiency, enabling ultra-fast and accurate screening of massive chemical libraries for drug discovery.