Skip to yearly menu bar Skip to main content


Poster
in
Workshop: 2nd Generative AI for Biology Workshop

How Good is AlphaFold3 at Ranking Drug Binding Affinities?

Xin Hong · Bowen Gao · Yinjun Jia · Wenyu Zhu · Qixuan Chen · Xiaohe Tian · Zhenyi Zhong · Jianhui Wang · Yanyan Lan

Keywords: [ affinity prediction ] [ FEP+ ] [ AlphaRank ] [ ranking ] [ AlphaFold3 ] [ lead optimization ]


Abstract:

Accurate affinity ranking of small molecules is pivotal for drug discovery. We investigate whether structure prediction models like AlphaFold3, pretrained on protein-ligand interactions, can address this task. Zero-shot evaluation of Protenix (an AlphaFold3-like model) demonstrates superior prioritization of active compounds over conventional scoring functions and state-of-the-art deep learning models. By further fine-tuning Protenix on structure-agnostic protein-ligand bioactivity data from ChEMBL and BindingDB, we develop AlphaRank that predicts pairwise affinity relationships. AlphaRank achieves prediction accuracy comparable to computationally intensive free energy perturbation (FEP+) workflows on standard benchmarks, while requiring substantially less computational resources. Our findings highlight the emergent potential of AlphaFold3-derived models in affinity ranking tasks and emphasize the necessity for targeted methodological exploration to fully harness their capabilities in drug discovery applications.

Chat is not available.