Toriumi Shinya, Shimokawa Komei, Yamamoto Munehiro, Uesawa Yoshihiro
Department of Medical Molecular Informatics, Meiji Pharmaceutical University, Kiyose 204-8588, Japan.
Department of Pharmacy, National Hospital Organization Kanagawa Hospital, Hadano 257-8585, Japan.
Pharmaceuticals (Basel). 2025 Mar 17;18(3):423. doi: 10.3390/ph18030423.
Medication-related osteonecrosis of the jaw (MRONJ) is a rare but serious adverse event. Herein, we conducted a quantitative structure-activity relationship analysis using the U.S. Food and Drug Administration Adverse Drug Reaction Database System (FAERS) and machine learning to construct a drug prediction model for MRONJ induction based solely on chemical structure information. A total of 4815 drugs from FAERS were evaluated, including 70 and 139 MRONJ-positive and MRONJ-negative drugs, respectively, identified based on reporting odds ratios, Fisher's exact tests, and ≥100 total adverse event reports. Then, we calculated 326 chemical structure descriptors for each drug and compared three supervised learning algorithms (random forest, gradient boosting, and artificial neural networks). We also compared the number of chemical structure descriptors (5, 6, 7, 8, 9, 10, 20, and 30 descriptors). We indicated that the MRONJ prediction model using an artificial neural network algorithm and eight descriptors achieved the highest validation receiver operating characteristic curve value of 0.778. Notably, the total polar surface area (ASA_P) was among the top-ranking descriptors, and MRONJ-positive drugs such as bisphosphonates and anticancer drugs showed high values. Our final model demonstrated a balanced accuracy of 0.693 and a specificity of 0.852. In this study, our MRONJ-inducing drug prediction model identified drugs with polar surface area properties as potential causes of MRONJ. This study demonstrates a promising approach for predicting MRONJ risk, which could enhance drug safety assessment and streamline drug screening in clinical and preclinical settings.
药物相关性颌骨坏死（MRONJ）是一种罕见但严重的不良事件。在此，我们使用美国食品药品监督管理局不良药物反应数据库系统（FAERS）并结合机器学习进行定量构效关系分析，以仅基于化学结构信息构建MRONJ诱导的药物预测模型。对FAERS中的4815种药物进行了评估，其中分别根据报告比值比、Fisher精确检验以及≥100份总不良事件报告确定了70种MRONJ阳性药物和139种MRONJ阴性药物。然后，我们为每种药物计算了326个化学结构描述符，并比较了三种监督学习算法（随机森林、梯度提升和人工神经网络）。我们还比较了化学结构描述符的数量（5、6、7、8、9、10、20和30个描述符）。我们指出，使用人工神经网络算法和八个描述符的MRONJ预测模型实现了最高的验证受试者工作特征曲线值0.778。值得注意的是，总极性表面积（ASA_P）在排名靠前的描述符之中，双膦酸盐和抗癌药物等MRONJ阳性药物显示出较高的值。我们的最终模型显示平衡准确率为0.693，特异性为0.852。在本研究中，我们的MRONJ诱导药物预测模型将具有极性表面积特性的药物确定为MRONJ的潜在原因。本研究展示了一种预测MRONJ风险的有前景的方法，这可以加强药物安全性评估并简化临床和临床前环境中的药物筛选。
