使用图形卷积神经网络模型来识别胆汁盐出口抑制剂
Mohamed Diwan M AbdulHameed1,2, Ruifeng Liu1,2, Anders Wallqvist1
1Department of Defense Biotechnology High Performance Computing Software Applications Institute, Telemedicine and Advanced Technology Research Center, U.S. Army Medical Research and Development Command, Fort Detrick 21702, Maryland, United States.
ACS omega
|June 26, 2023
概括
我们开发了一个机器学习模型来预测胆汁盐出口 (BSEP) 抑制剂,帮助药物安全性评估. 这种图形卷积神经网络方法为识别潜在的BSEP抑制剂提供了有效的替代实验方法.
科学领域:
- 药理学 药理学是指药理学的学科.
- 计算化学计算化学
- 毒理学 毒理学 毒理学
背景情况:
- 胆盐出口 (BSEP) 对于从肝细胞中清除胆盐至关重要.
- 抑制BSEP可以导致胆汁盐的积累,导致胆固醇和药物诱导的肝损伤.
- 识别BSEP抑制剂对于评估化学安全和了解药物负担至关重要.
研究的目的:
- 开发预测机器学习模型,使用公共数据识别潜在的BSEP抑制剂.
- 评估图形卷积神经网络 (GCNN) 方法与多任务学习相结合用于BSEP抑制预测的有效性.
- 为了比较基于GCNN的单任务和多任务模型的性能,特别是在生物活性数据有限的场景中.
主要方法:
- 利用公开可用的数据来训练和验证机器学习模型.
- 使用图形卷积神经网络 (GCNN) 架构进行预测建模.
- 实施多任务学习以提高模型性能和解决数据限制.
主要成果:
- 开发的GCNN模型在0.86的曲线下实现了交叉验证接收器操作特征面积,优于其他机器学习方法.
- 与单一任务模型相比,多任务GCNN模型表现出更高的性能.
- 多任务学习有效地解决了与生物活性建模中的有限数据可用性相关的挑战.
结论:
- 基于多任务 GCNN 的 BSEP 模型是在早期药物发现中优先考虑潜在的 BSEP 抑制剂的宝贵工具.
- 这种计算方法有助于评估化学品的风险,因为它可以预测它们有抑制BSEP的潜力.
- 该研究强调了多任务学习在为数据稀缺的目标开发强大的预测模型的有用性.
相关概念视频
Bile
1.0K
Bile is a crucial bodily fluid, characterized by its yellow-green color and alkaline nature. Produced in the liver, it is transported through the common hepatic duct into either the cystic duct, leading to the gallbladder, or directly into the common bile duct. The flow of bile is regulated by the sphincter of Oddi located at the entrance of the duodenum. When this sphincter is closed, bile is redirected to the gallbladder for storage and concentration.
Bile is released when dietary fats enter...
Bile is released when dietary fats enter...
1.0K
Multi-pass Transmembrane Proteins and β-barrels
5.4K
In multi-pass transmembrane proteins, the polypeptide chain crosses the membrane more than once. The transmembrane polypeptide chain either forms an α-helix or β-strand structure. α-Helix containing multi-pass transmembrane proteins are ubiquitous, whereas β-strand containing ones are mainly found in gram-negative bacteria, mitochondria, and chloroplasts.
α-Helix containing multi-pass transmembrane proteins
Multi-pass transmembrane proteins such as...
α-Helix containing multi-pass transmembrane proteins
Multi-pass transmembrane proteins such as...
5.4K


