稀疏蛋白激酶活动数据的大规模建模
Sohvi Luukkonen1, Erik Meijer1, Giovanni A Tricarico2
1Leiden Academic Centre of Drug Research, Leiden University, Einsteinweg 55, 2333 CC Leiden, The Netherlands.
Journal of chemical information and modeling
|June 9, 2023
概括
多任务深度学习模型显示出从稀疏数据预测蛋白激酶活性的前景. 这项研究开发了一个基准数据集来评估模型的概括性,并发现数据归算没有提高性能.
科学领域:
- 生物化学和化学信息学
- 计算生物学 计算生物学
- 药物发现 药物发现 药物发现
背景情况:
- 蛋白激酶在癌症等复杂疾病中至关重要,具有保留的ATP结合位,使多向药物开发成为可能.
- 为了平衡药物的有效性和最小化毒性,需要了解酶抑制剂的选择性.
- 公共可用的蛋白激酶活性数据为先进的计算建模提供了潜力.
研究的目的:
- 为蛋白质激酶活性预测模型构建一个强大的基准数据集.
- 用稀疏的数据解决多任务学习的挑战,特别是数据泄露和缺失的值.
- 评估与其他机器学习方法相比,多任务深度学习模型的性能.
主要方法:
- 开发一个蛋白质激酶基因酶基准数据集,使用随机和不相似性驱动的基于集群的抽样采用两个平衡的分割.
- 实现和比较多任务深度学习,单任务深度学习和基于树的模型.
- 在构建的基准集上评估模型性能和概括性.
- 对数据归算对模型性能影响的评估.
主要成果:
- 由不相似性驱动的基于集群的分割表明模型性能低于随机分割,这表明概括性存在挑战.
- 多任务深度学习模型在稀疏的基准数据集上表现优于单任务深度学习和基于树的模型.
- 数据归算策略对于单任务或多任务模型都没有产生性能改善.
结论:
- 开发的基准数据集对于评估和推进蛋白激酶活性预测模型非常有价值.
- 多任务深度学习模型显示了有效建模稀疏蛋白激酶活性数据的潜力.
- 仔细考虑数据集分割和模型概括性对于可靠的激酶抑制剂药物发现至关重要.
相关概念视频
02:26Protein Networks
4.0K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.0K
02:54Protein Kinases and Phosphatases
13.2K
Proteins undergo chemical modifications that trigger changes in the charge, structure, and conformation of the proteins. Phosphorylation, acetylation, glycosylation, nitrosylation, ubiquitination, lipidation, methylation, and proteolysis are various protein modifications that regulate protein activity. Such modifications are usually enzyme-driven.
Protein kinases
Many proteins in the cell are regulated by phosphorylation, the addition of a phosphate group. A family of enzymes called kinases...
Protein kinases
Many proteins in the cell are regulated by phosphorylation, the addition of a phosphate group. A family of enzymes called kinases...
13.2K