Chongqing Key Laboratory of Digitalization of Pharmaceutical Processes and Equipment, College of Chemistry and Chemical Engineering, Chongqing University of Science and Technology, No. 20, University City East Road, Chongqing, 401331, China.
AAPS PharmSciTech. 2024 Jun 11;25(5):133. doi: 10.1208/s12249-024-02846-2.
Nifedipine (NIF) is a dihydropyridine calcium channel blocker primarily used to treat conditions such as hypertension and angina. However, its low solubility and low bioavailability limit its effectiveness in clinical practice. Here, we developed a cocrystal prediction model based on Graph Neural Networks (CocrystalGNN) for the screening of cocrystals with NIF. And scoring 50 coformers using CocrystalGNN. To validate the reliability of the model, we used another prediction method, Molecular Electrostatic Potential Surface (MEPS), to verify the prediction results. Subsequently, we performed a second validation using experiments. The results indicate that our model achieved high performance. Ultimately, cocrystals of NIF were successfully obtained and all cocrystals exhibited better solubility and dissolution characteristics compared to the parent drug. This study lays a solid foundation for combining virtual prediction with experimental screening to discover novel water-insoluble drug cocrystals.
硝苯地平（NIF）是一种二氢吡啶钙通道阻滞剂，主要用于治疗高血压和心绞痛等疾病。然而，其低溶解度和低生物利用度限制了其在临床实践中的效果。在这里，我们开发了一种基于图神经网络（CocrystalGNN）的共晶预测模型，用于筛选与 NIF 的共晶。并使用 CocrystalGNN 对 50 个共晶物进行评分。为了验证模型的可靠性，我们使用另一种预测方法，分子静电势表面（MEPS），来验证预测结果。随后，我们进行了第二次实验验证。结果表明，我们的模型表现出了很高的性能。最终，成功获得了 NIF 的共晶，并且所有共晶都表现出了比母体药物更好的溶解度和溶解特性。这项研究为将虚拟预测与实验筛选相结合，发现新型水不溶性药物共晶奠定了坚实的基础。
