针对代谢疾病的三重激素治疗药物的机器学习引导优化
Anthony Wong1, Sanskruthi Guduri1, TsungYen Chen1,2
1Carle Illinois College of Medicine, Urbana, IL, United States.
Frontiers in bioinformatics
|December 3, 2025
概括
针对 GCGR,GLP1R 和 GIPR 的三重激素对糖尿病和肥胖有希望. 图形注意网络 (GAT) 为设计这些复杂的疗法提供了一种强大的计算方法.
科学领域:
- 类疗法设计 类疗法设计
- 计算化学是一种计算化学.
- 受体的药理学受体的药理学
背景情况:
- 针对糖尿病和肥胖症的多目标类疗法,准葡萄糖受体 (GCGR),葡萄糖类-1受体 (GLP1R) 和依赖葡萄糖的胰岛素型多受体 (GIPR),具有显著的潜力.
- 由于复杂的序列结构活动关系,三重激动蛋白质的理性设计在计算上具有挑战性.
- 像卷积神经网络 (CNN) 这样的现有方法在处理可变长度和分子拓学方面存在局限性.
研究的目的:
- 开发和评估基于图表注意力网络 (GAT) 的计算框架,用于设计多目标疗法.
- 将GAT与CNN的性能进行比较,以预测对GCGR,GLP1R和GIPR的结亲和力.
- 使用遗传算法 (GA) 来优化GAT框架识别的序列.
主要方法:
- 编制了234个具有实验确定结合亲和性的序列的数据集.
- 酸被表现为具有物理化学和位置节点特征的分子图形.
- 采用了一个具有共享编码器和任务特定头部的GAT架构,使用有限的GIPR数据的转移学习.
- 通过5倍交叉验证和独立验证来评估性能.
- 基于预测的结合亲和力,生物可信性和新性,开发了一个GA框架来优化序列.
主要成果:
- 在所有受体上,GAT框架表现出强大的性能:GCGR (AUC ROC: 0.915 ± 0.050),GLP1R (AUC-ROC: 0.853 ± 0.059) 和GIPR (AUC-ROC: 0.907 ± 0.083).
- 在GCGR预测方面,GAT显著超过CNN (RMSE:0.942对1.209,p=0.0013),而CNN显示出优越的GLP1R性能 (RMSE:0.552对0.723).
- GA优化导致了4.0%的健身增强,并生成了20个候选序列,所有目标的平均结合概率>0.5.
结论:
- 基于GAT的框架为合理的设计提供了有效的计算方法,展示了受体特异性的优势.
- 整合GA优化允许系统地探索序列空间,同时保持生物约束.
- 这种方法促进了对糖尿病和肥胖症治疗中三重激素开发的实验验证的优先考虑.
更多相关视频
07:08Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues
Published on: July 14, 2015
7.6K
08:48Development of a Backbone Cyclic Peptide Library as Potential Antiparasitic Therapeutics Using Microwave Irradiation
Published on: January 26, 2016
12.3K
相关概念视频
Drug Discovery: Overview
10.9K
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...
10.9K
Transducer Mechanism: Enzyme-Linked Receptors
3.8K
Enzyme-linked receptors are cell-surface receptors acting as an enzyme or associating with an enzyme intracellularly. They make excellent drug targets. Drugs can bind to the extracellular ligand-binding domain or directly affect their enzymatic domain and alter their activity.
Major types that are helpful drug targets include:
Major types that are helpful drug targets include:
3.8K
