通过量子信息对小分子的CYP450结合进行深度学习
Shan Lu1, Nicholas J Huls1, Koushiki Basu1
1Industrial and Molecular Pharmaceutics, Purdue University, West Lafayette, Indiana 47907, United States.
Journal of chemical information and modeling
|January 27, 2025
概括
预测药物相互作用对于患者的安全至关重要. 使用分子电子特性的新型深度学习模型在识别与细胞P450酶相互作用时显示出更高的准确性.
科学领域:
- 药理学 药理学是指药理学的学科.
- 计算化学的计算化学
- 人工智能的人工智能
背景情况:
- 药物相互作用 (DDI) 存在重大风险,特别是在多药中,由于治疗效果或毒性发生变化.
- 细胞染色体P450酶在药物代谢中至关重要,处理大约90%的FDA批准的药物,并调解许多DDI.
- 传统的in-silico DDI预测模型通常依赖于结构描述符,可能缺少关键的电子相互作用.
研究的目的:
- 开发先进的in-silico模型来预测药物相互作用.
- 将分子的量子力学电子性质集成到预测模型中.
- 提高DDI预测的准确性,特别是对于细胞染色体P450介导的相互作用.
主要方法:
- 实施分子表面多重嵌入 (MEMS) 方法来捕获分子电子特征.
- 用于深度学习的MEMS生成的电子属性的特色化.
- 使用DeepSets架构构建预测模型.
主要成果:
- 开发的深度学习模型在预测DDI方面取得了很高的准确性.
- 具体来说,模型在细胞P450酶1A2 (CYP1A2) 相互作用方面表现强,F1得分为0.866.
- 该方法成功地集成了详细的电子属性,克服了传统描述符的局限性.
结论:
- 将详细的分子电子特性与深度学习相结合,为提高DDI预测准确性提供了一个强大的策略.
- 这种方法解决了传统分子描述器和机器学习技术在捕捉复杂药物相互作用方面的局限性.
- 这项研究强调了先进的计算方法在提高药物安全性和个性化医疗方面的潜力.
相关概念视频
02:40Ligand Binding Sites
12.7K
Proteins are dynamic macromolecules that carry out a wide variety of essential processes; however, the activities of most proteins depend on their interactions with other molecules or ions, known as ligands.
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
12.7K
02:18The Equilibrium Binding Constant and Binding Strength
12.8K
The equilibrium binding constant (Kb) quantifies the strength of a protein-ligand interaction. Kb can be calculated as follows when the reaction is at equilibrium:
12.8K