基于对联结的比较网络计算连接体的相对结合亲和力
Jie Yu1,2,3, Zhaojun Li4,5, Geng Chen1,6,7
1Drug Discovery and Design Center, State Key Laboratory of Drug Research, Shanghai Institute of Materia Medica, Chinese Academy of Sciences, Shanghai, China.
我们开发了一种新的计算方法,即双向结合比较网络 (PBCNet),以准确排列连接体结合亲和力. PBCNet显著加速药物发现和优化,具有高预测准确性和效率.
科学领域:
- 计算化学是一种计算化学.
- 药物发现 药物发现
- 机器学习在化学中的应用
背景情况:
- 基于结构的优化仍然是药物发现的挑战.
- 目前的方法很大程度上依赖于假设和药物化学家的经验.
研究的目的:
- 引入一种新的计算方法,用于对同源配体的相对结合亲缘关系进行排名.
- 提高药物发现中的预测准确性和计算效率.
主要方法:
- 开发了一种对联结合的比较网络 (PBCNet).
- 使用了基于物理的图表注意力机制.
- 在施罗丁格和默克的持有数据集上对比PBCNet.
主要成果:
- PBCNet在预测准确性和计算效率方面展示了显著的优势.
- 通过微调,PBCNet的表现与施罗丁格的FEP+相匹配.
- 积极学习优化的PBCNet显示出加速领先优化的潜力473%.
结论:
- PBCNet提供了一种强大而高效的工具,用于预测相对结合亲和力.
- 提供PBCNet的网络服务,以促进其在药物发现中的使用.
- 该方法有可能显著加速领先优化活动.
更多相关视频
13:49Semi-automated Biopanning of Bacterial Display Libraries for Peptide Affinity Reagent Discovery and Analysis of Resulting Isolates
Published on: December 6, 2017
08:40An ELISA Based Binding and Competition Method to Rapidly Determine Ligand-receptor Interactions
Published on: March 14, 2016
相关概念视频
Ligand Binding and Linkage
The Equilibrium Binding Constant and Binding Strength
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...
Conserved Binding Sites
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...
The Two-State Receptor Model
The binding affinity of a drug determines its interaction with...
Drug-Receptor Bonds
In...
