GenShin:geometry-enhanced structural graph embodies binding pose can better predicting compound-protein interaction affinity

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhu, Pingfei, Zhao, Chenyang, Zhao, Haishi, Yang, Bo
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910914259714048
author Zhu, Pingfei
Zhao, Chenyang
Zhao, Haishi
Yang, Bo
author_facet Zhu, Pingfei
Zhao, Chenyang
Zhao, Haishi
Yang, Bo
contents AI-powered drug discovery typically relies on the successful prediction of compound-protein interactions, which are pivotal for the evaluation of designed compound molecules in structure-based drug design and represent a core challenge in the field. However, accurately predicting compound-protein affinity via regression models usually requires adequate-binding pose, which are derived from costly and complex experimental methods or time-consuming simulations with docking software. In response, we have introduced the GenShin model, which constructs a geometry-enhanced structural graph module that separately extracts additional features from proteins and compounds. Consequently, it attains an accuracy on par with mainstream models in predicting compound-protein affinities, while eliminating the need for adequate-binding pose as input. Our experimental findings demonstrate that the GenShin model vastly outperforms other models that rely on non-input docking conformations, achieving, or in some cases even exceeding, the performance of those requiring adequate-binding pose. Further experiments indicate that our GenShin model is more robust to inadequate-binding pose, affirming its higher suitability for real-world drug discovery scenarios. We hope our work will inspire more endeavors to bridge the gap between AI models and practical drug discovery challenges.
format Preprint
id arxiv_https___arxiv_org_abs_2504_13853
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GenShin:geometry-enhanced structural graph embodies binding pose can better predicting compound-protein interaction affinity
Zhu, Pingfei
Zhao, Chenyang
Zhao, Haishi
Yang, Bo
Biomolecules
Artificial Intelligence
AI-powered drug discovery typically relies on the successful prediction of compound-protein interactions, which are pivotal for the evaluation of designed compound molecules in structure-based drug design and represent a core challenge in the field. However, accurately predicting compound-protein affinity via regression models usually requires adequate-binding pose, which are derived from costly and complex experimental methods or time-consuming simulations with docking software. In response, we have introduced the GenShin model, which constructs a geometry-enhanced structural graph module that separately extracts additional features from proteins and compounds. Consequently, it attains an accuracy on par with mainstream models in predicting compound-protein affinities, while eliminating the need for adequate-binding pose as input. Our experimental findings demonstrate that the GenShin model vastly outperforms other models that rely on non-input docking conformations, achieving, or in some cases even exceeding, the performance of those requiring adequate-binding pose. Further experiments indicate that our GenShin model is more robust to inadequate-binding pose, affirming its higher suitability for real-world drug discovery scenarios. We hope our work will inspire more endeavors to bridge the gap between AI models and practical drug discovery challenges.
title GenShin:geometry-enhanced structural graph embodies binding pose can better predicting compound-protein interaction affinity
topic Biomolecules
Artificial Intelligence
url https://arxiv.org/abs/2504.13853