普罗斯塔网:一种新的几何向量感知子-图形神经网络算法,用于预测单点和多点突变中的蛋白质稳定性,并进行实验验证
Tianjian Liang1, Ze-Yu Sun1, Rieko Ishima2
1Department of Pharmaceutical Sciences, Computational Chemical Genomics Screening Center, and Pharmacometrics and System Pharmacology PharmacoAnalytics, School of Pharmacy, National Center of Excellence for Computational Drug Abuse Research, University of Pittsburgh, Pittsburgh, PA 15261, USA.
深度学习框架ProstaNet准确预测突变导致的蛋白质稳定性变化. 它在单点和多点突变方面表现优于现有的方法,有助于蛋白质工程和药物开发.
科学领域:
- 计算生物学 计算生物学
- 生物物理学的生物物理.
- 机器学习 机器学习
背景情况:
- 蛋白质稳定性预测对于生物学和生物制药至关重要,但在实验上具有挑战性.
- 深度学习提供了一种高效的计算方法来预测突变对蛋白质稳定性的影响.
研究的目的:
- 介绍ProstaNet,这是一个深度学习框架,用于预测由单点和多点突变引起的蛋白质稳定性变化.
- 开发一个全面的数据集 (ProstaDB) 和创新的方法来训练和验证深度学习模型.
主要方法:
- 在ProstaNet.Net中使用几何向量感知子-图形神经网络进行3D特征处理.
- 创建了ProstaDB,具有3,784个单点和1,642个多点突变,使用热力学循环和集群来增强和测试数据.
- 识别了残留评分作为蛋白质性质预测的关键编码方法.
主要成果:
- 在单点突变预测中,ProstaNet获得了0.75的准确性,超过了ThermoMPNN (0.63),PoPMuSiCsym (0.66),MUPRO (0.52) 和FoldX (0.71).
- 对于多点突变预测,ProstaNet的准确性比FoldX提高了1.3倍.
- 实验验证显示,HuJ3突变体中单点突变的准确性为80%,多点突变的准确性为100%.
结论:
- 普罗斯塔网准确地预测了单点和多点突变的热稳定性变化,没有偏差.
- 该框架显示了通过准确的突变效应预测来推进蛋白质工程和药物开发的巨大潜力.
更多相关视频
07:08Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues
Published on: July 14, 2015
10:21Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
Published on: February 23, 2024
相关概念视频
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...
Covalently Linked Protein Regulators
These groups modify specific amino acids in a protein....
Mutations
Protein Networks
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,...
Conservation of Protein Domains Over Different Proteins
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to...
Protein-protein Interfaces
