基于几何深度学习的RNA-小分子配体结合亲和力的预测
Wentao Xia1, Jiasai Shu1, Chunjiang Sang1
1Department of Physics, Zhejiang University of Science and Technology, Hangzhou 310008, China.
Computational biology and chemistry
|February 4, 2025
概括
我们开发了RLASIF,这是一种新的深度学习方法,使用分子表面特征来预测RNA-接体结合亲和力. RLASIF显著优于现有的计算方法,推进药物发现和抑制剂设计.
科学领域:
- 计算生物学 计算生物学
- 药物发现 药物发现 药物发现
- 结构生物信息学 结构生物信息学
背景情况:
- 预测RNA-小分子相互作用对于药物发现至关重要.
- 当前的计算方法往往忽略了分子表面信息.
- 很少有方法可以准确地预测RNA和小分子的结合亲和关系.
研究的目的:
- 开发一种新的计算方法来预测RNA-小分子结合亲和力.
- 将分子表面特征纳入结合亲和力预测中.
- 解决现有的序列和基于结构的方法的局限性.
主要方法:
- 提出了一种几何深度学习方法,称为RNA-ligand表面交互指纹 (RLASIF).
- 从几何和化学表面特征创建了RNA - 连接体相互作用指纹.
- 使用PDBbind NL2020数据集进行培训和验证.
主要成果:
- 在PDBbind NL2020.2020的十个测试组中,RLASIF表现出卓越的性能.
- 在四个评估指标上,与现有的计算方法相比,实现了显著的性能改进.
- 有效地捕获了影响RNA-连接体结合强度的关键特征.
结论:
- RLASIF是一种高效的方法,用于预测RNA-小分子结合亲和力.
- 该方法的重点是分子表面特征,提高了预测的准确性.
- RLASIF显示了虚拟选和确定绑定站点的潜力.
相关概念视频
Ligand Binding Sites
12.7K
Proteins are dynamic macromolecules that carry out a wide variety of essential processes; however, the activities of most proteins depend on their interactions with other molecules or ions, known as ligands.
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...
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...
12.7K
Conserved Binding Sites
4.2K
Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...
4.2K


