通过多任务学习解密孤儿GPCR药物发现
Wei-Cheng Huang1, Wei-Ting Lin1, Ming-Shiu Hung1
1Institute of Biotechnology and Pharmaceutical Research, National Health Research Institutes, Miaoli County, 35053, Taiwan.
Journal of cheminformatics
|January 23, 2024
概括
这项研究引入了多任务模型来预测G蛋白合受体 (GPCRs) 的药物疗效,通过利用蛋白质特征进行数据传输来加速对孤儿GPCRs的治疗方法的发现.
科学领域:
- 计算化学是一种计算化学.
- 药理学 药理学是指药理学的学科.
- 结构生物学是结构生物学.
背景情况:
- 对G蛋白结合受体 (GPCRs) 的药物发现受到有限的3D结构和生物活性数据的阻碍,特别是对于孤儿GPCRs.
- 由于数据稀缺,现有的计算模型在预测配体-GPCR相互作用方面面临挑战.
研究的目的:
- 开发和验证用于预测化学-GPCR对半最大有效度 (EC50) 的多任务模型.
- 通过利用蛋白序列和化学性质信息,使人类孤儿GPCRs的药物发现成为可能.
主要方法:
- 利用蛋白质多个序列对齐特征和化学物理化学特性/指纹进行编码.
- 根据特征相似性,雇佣多任务学习将已知GPCRs的数据传输到孤儿受体.
- 在200个GPCRs的agonist和antagonist数据上训练模型.
主要成果:
- 在验证数据集上获得了0.24的优异平均平方误差 (MSE).
- 在独立的孤儿数据集上显示了1.51的相当好的MSE,可通过基于特征的可转移性改进到0.53.
- 识别了信息特征,并将它们映射到3D结构中,以了解GPCR-配体相互作用.
结论:
- 拟议的多任务模型为GPCR超级家族中的联体生物活性学习提供了一种新的方法.
- 这种方法可以显著加速对孤儿GPCRs的治疗剂的发现.
- 通过分析信息特征和它们的结构映射,获得了对GPCR-连接物相互作用的洞察力.
相关概念视频
Drug Discovery: Overview
7.9K
Drug discovery is a multifaceted process involving extensive screening, testing, and optimization of lead compounds to identify potential new drugs for therapeutic use. It combines several approaches, including screening large numbers of natural products, chemical modification of known active molecules, identification of new drug targets, and rational design based on biological mechanisms and drug-receptor structure. These approaches are carried out in both academic research laboratories and...
7.9K
GPCR Desensitization
6.0K
G protein-coupled receptor (GPCR) signaling plays a crucial role in cell functioning. GPCR desensitization is an equally essential process. It allows cells to respond to changing environments and regain sensitivity to new stimuli while preventing unnecessary stimulation when no longer needed. Prolonged exposure to stimuli leads to GPCR desensitization. It involves blocking the receptors from binding and activating additional G proteins. This inhibits activation of downstream effectors, thereby...
6.0K


