GenShin:geometry-enhanced structural graph embodies binding pose can better predicting compound-protein interaction affinity
This work addresses a core challenge in AI-powered drug discovery by reducing dependency on expensive experimental or simulation data for binding poses, potentially making the process more practical and efficient.
The paper tackles the problem of predicting compound-protein interaction affinity without requiring accurate binding poses as input, which are typically costly to obtain. The GenShin model achieves accuracy on par with mainstream models that rely on such poses and outperforms other models that do not use them.
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.