How to cite item

Harnessing deep statistical potential for biophysical scoring of protein-peptide interactions

   
@article{APS11461,
	author = {De-jun Jiang and Hui-feng Zhao and Hong-yan Du and Yu Kang and Pei-chen Pan and Zhen-xing Wu and Yun-dian Zeng and O-din Zhang and Xiao-rui Wang and Ji-ke Wang and Yuan-sheng Huang and Yi-hao Zhao and Chang-Yu Hsieh and Dong-sheng Cao and Hui-yong Sun and Ting-jun Hou},
	title = {Harnessing deep statistical potential for biophysical scoring of protein-peptide interactions},
	journal = {Acta Pharmacologica Sinica},
	volume = {47},
	number = {2},
	year = {2026},
	keywords = {},
	abstract = {Protein-peptide interactions (PpIs) play a critical role in major cellular processes. Recently, a number of machine learning (ML)-based methods have been developed to predict PpIs, but most of them rely heavily on sequence data, limiting their ability to capture the generalized molecular interactions in three-dimensional (3D) space, which is crucial for understanding protein-peptide binding mechanisms and advancing peptide therapeutics. Protein-peptide docking approaches provide a feasible way to generate the 3D models of PpIs, but they often suffer from low-precision scoring functions (SFs). To address this, we developed DeepPpIScore, a novel SF for PpIs that employs unsupervised geometric deep learning coupled with a physics-inspired statistical potential. Trained solely on curated experimental structures without binding affinity data or classification labels, DeepPpIScore exhibits broad generalization across multiple tasks. Our comprehensive evaluations in bound and unbound peptide bioactive conformation prediction, binding affinity prediction, and binding pair identification reveal that DeepPpIScore outperforms or matches state-of-the-art baselines, including popular protein-protein SFs, ML-based methods, and AlphaFold-Multimer 2.3 (AF-M 2.3). Notably, DeepPpIScore achieves superior results in peptide binding mode prediction compared to AF-M 2.3. More importantly, DeepPpIScore offers interpretability in terms of hotspot preferences at protein interfaces, physics-informed noncovalent interactions, and protein-peptide binding energies.},
	issn = {1745-7254},	url = {http://www.chinaphar.com/article/view/11461}
}