Harnessing angular geometry in deep learning for protein–ligand binding affinity prediction
The angular features are effective, lightweight, and robust descriptors for binding affinity prediction. These results highlight angular geometry as a valuable direction for future structure-based drug discovery. The program and data of AAP are publicly available at https://github.com/juliacse06/AAP.
Authors
- Md Khaled Ben Islam (ORCID: https://orcid.org/0000-0003-4841-9604)
- Jiffriya Mohamed Abdul Cader
- Julia Rahman (ORCID: https://orcid.org/0000-0001-5005-9922)
- Mohammed Eunus Ali
- M.A. Hakim Newton
- Abdul Sattar
Institutions
- Griffith University (AU)
- Monash University (AU)
- University of Newcastle Australia (AU)
Publication Details
- Journal
- Computer Methods and Programs in Biomedicine
- Published
- 2026-02-12
- DOI
- https://doi.org/10.1016/j.cmpb.2026.109282
- Primary Topic
- Protein Structure and Dynamics
- Type
- article
- Field-Weighted Citation Impact
- 0.00