How Good is AlphaFold3 at Ranking Drug Binding Affinities?
Hong, X.; Gao, B.; Jia, Y.; Zhu, W.; Chen, Q.; Tian, X.; Zhong, Z.; Wang, J.; Lan, Y.
Show 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.
Matching journals
The top 2 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- DiffDock-Glide: a hybrid physics-based and data-driven approach to molecular docking 96%
- DENVIS: scalable and high-throughput virtual screening using graph neural networks with atomic and surface protein pocket features 96%
- Dataset Augmentation Allows Deep Learning-Based Virtual Screening To Better Generalize To Unseen Target Classes, And Highlight Important Binding Interactions 96%
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.