通过自我训练提高化合物-蛋白相互作用预测,增加负样本
Takuto Koyama1, Shigeyuki Matsumoto1, Hiroaki Iwata1
1Graduate School of Medicine, Kyoto University, Sakyo-ku 606-8507 Kyoto, Japan.
Journal of chemical information and modeling
|July 17, 2023
概括
本研究引入了一种自我训练方法,通过生成信息性的负样本来改善化合物-蛋白相互作用 (CPI) 预测. 这种方法提高了模型性能和通用性,这对于加速药物发现至关重要.
科学领域:
- 计算化学是一种计算化学.
- 生物信息学是一种生物信息学.
- 机器学习 机器学习
背景情况:
- 确定化合物-蛋白相互作用 (CPI) 对药物发现至关重要.
- 对CPI的实验验证是昂贵且耗时的.
- 计算方法,特别是机器学习,用于CPI预测,但由于缺乏负样本,数据失衡.
研究的目的:
- 开发一种自我训练方法,以增加可信和有信息的负面样本.
- 提高用于CPI预测的机器学习模型的性能和通用性,特别是在外部数据集上.
- 用现实数据提供指导方针,以提高CPI预测.
主要方法:
- 开发了一种自我培训方法,用于为不平衡的CPI数据集生成负样本.
- 评估模型性能与解决数据不平衡的传统方法相比.
- 分析了伪标签值对模型通用性的影响.
主要成果:
- 与传统方法相比,提出的自我训练方法显著改善了模型性能.
- 在对外部数据集进行测试时,性能增长尤其显著,这表明增强了概括性.
- 在自我训练期间增加具有模两可的预测分数的样本,证明对模型通用性有益.
结论:
- 开发的自我训练方法有效地解决了CPI预测中的数据不平衡.
- 这种方法提高了模型的通用性,这对于现实世界药物发现应用至关重要.
- 该研究提供了改善计算CPI预测准确性和效率的实用指南.
更多相关视频
10:21Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
Published on: February 23, 2024
2.7K
07:08Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues
Published on: July 14, 2015
7.3K
相关概念视频
Protein-protein Interfaces
12.6K
Many proteins form complexes to carry out their functions, making protein-protein interactions (PPIs) essential for an organism's survival. Most PPIs are stabilized by numerous weak noncovalent chemical forces. The physical shape of the interfaces determines the way two proteins interact. Many globular proteins have closely-matching shapes on their surfaces, which form a large number of weak bonds. Additionally, many PPIs occur between two helices or between a surface cleft and a...
12.6K
Protein 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
Protein Complex Assembly
2.1K
2.1K
Protein-Protein Interfaces
3.8K
3.8K
Protein Complexes with Interchangeable Parts
1.9K
1.9K
Proteins: From Genes to Degradation
3.6K
3.6K
