通过机器学习来预测阿克尼德-利甘德复合的稳定常数.
Junhong Li1, Junqing Li1, Ziyi Liu1,2
1State Key Laboratory of Fine Chemicals, Liaoning Key Laboratory for Catalytic Conversion of Carbon Resources, School of Chemistry, Dalian University of Technology, Dalian 116024, China.
机器学习准确地预测了活性化物-配体结合亲缘关系,加速了用于核能应用的新型配体的设计. 这种方法确定了关键性质,改进了封存策略并减少了实验努力.
科学领域:
- 核化学和材料科学 核化学和材料科学
- 计算化学和机器学习.
背景情况:
- 有效地对动因化物进行隔离对于可持续的核能至关重要.
- 目前的连接体设计依赖于缓慢,劳动密集型的试错方法,受动因子毒性和放射性阻碍.
- 机器学习为加速连接体发现提供了一个有希望的替代方案.
研究的目的:
- 开发精确的机器学习模型,用于预测动因酸-连接物结合亲缘关系 (Log K1).
- 确定影响这些相互作用的关键物理化学描述因素.
- 为了证明机器学习在设计新型乙烯酸的配体中的实用性.
主要方法:
- 训练了14个机器学习算法,使用结合平衡常数 (log K1) 作为目标属性.
- 从一组282个描述符中确定了15个最相关的描述符,涵盖连接物,金属和溶剂.
- 使用梯度提升模型进行预测,使用SISSO模型进行定量相关性.
主要成果:
- 梯度增强模型实现了高精度,在训练组中R2值为0.98,在测试组中为0.93.
- 确定了影响动因化物-配体相互作用的关键物理化学性质.
- 成功地预测了与实验一致的新配体的结合亲缘关系.
结论:
- 机器学习模型,特别是渐变增强,可以准确地预测动因酸-连接物结合亲和力.
- 这项研究提供了基本的洞察力,对actinide-ligand相互作用及其治理性质.
- 机器学习辅助的设计加速了发现有效的连接体的发现,以对动因化物进行隔离.
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
06:50Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions
Published on: January 26, 2024
相关概念视频
Complexation Equilibria: Factors Influencing Stability of Complexes
The Equilibrium Binding Constant and Binding Strength
Complexometric Titration: Ligands
Ladder Diagrams: Complexation Equilibria
The formation constant, K1, for the formation of Cd(NH3)2+ complex from cadmium and ammonia is 3.55 × 102. Log K1 (i.e. pNH3) is 2.55, and...
Complexation Equilibria: Overview
The equilibrium constant of the complexation reaction is represented as the formation constant...
Ligand Binding Sites
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...
