机器学习是蛋白质热力学的粗粒度潜力
Maciej Majewski1,2, Adrià Pérez1,2, Philipp Thölke1
1Computational Science Laboratory, Universitat Pompeu Fabra, Barcelona Biomedical Research Park (PRBB), Carrer Dr. Aiguader 88, 08003, Barcelona, Spain.
Nature communications
|September 15, 2023
概括
研究人员开发了用于蛋白质动力学模拟的机器学习模型. 这些人工神经网络的潜力加速了模拟的1000倍以上,保持了基本的热力学和捕捉蛋白质的行为.
科学领域:
- 计算生物学是一种计算生物学.
- 生物物理学的生物物理.
- 结构生物学中的机器学习
背景情况:
- 了解蛋白质动态对于解释生物过程中的结构功能关系至关重要.
- 准确高效地模拟蛋白质动态仍然是一个重大的科学挑战.
研究的目的:
- 开发一种新的方法来模拟蛋白质动态,使用基于机器学习的粗粒度潜力.
- 为了加快分子动力学模拟,同时保持热力学精度.
主要方法:
- 使用基于统计力学的人工神经网络构建粗粒度分子潜力.
- 在一个大约9毫秒的数据集上训练模型,对12种不同的蛋白质进行无偏的全原子分子动力学模拟.
- 与全原子模拟和实验数据对比,验证了粗粒度模型.
主要成果:
- 粗粒度模型在动力学模拟速度中实现了超过三倍的加速.
- 这些模型保留了模拟系统的热力学.
- 确定了相关的结构状态及其能量,可与全原子模拟进行比较.
- 一个单一的粗粒子潜能成功地整合了所有十二种蛋白质,并预测了突变蛋白质的实验特征.
结论:
- 基于机器学习的粗粒度潜能为模拟蛋白质动态提供了一种可行且有效的方法.
- 这种方法可以帮助理解蛋白质结构-功能关系和基本的生物过程.
- 开发的潜力显示了整合多种蛋白质系统和预测突变影响的前景.
相关概念视频
01:26Thermodynamic Potentials
873
Thermodynamic potentials are state functions that are extremely useful in analyzing a thermodynamic system. They have dimensions of energy. The four important thermodynamic potentials are internal energy, enthalpy, Helmholtz free energy, and Gibbs free energy. These thermodynamic potentials can be expressed using two of the following variables: pressure, volume, temperature, and entropy. These two variables are expressed as the rate of change of the thermodynamic potential with respect to other...
873
01:10Thermodynamics: Chemical Potential and Activity
1.0K
The effective concentration of a species in a solution can be expressed precisely in terms of its activity. Activity considers the effect of electrolytes present in the vicinity of the species of interest and depends on the ionic strength of the solution. The activity of a species is expressed as the product of molar concentration and the activity coefficient of the species.
The thermodynamic equilibrium constant is more accurately defined in terms of activity rather than concentration.
The thermodynamic equilibrium constant is more accurately defined in terms of activity rather than concentration.
1.0K
01:58Mechanical Protein Function
2.0K
2.0K
01:58Mechanical Protein Functions
5.0K
Proteins perform many mechanical functions in a cell. These proteins can be classified into two general categories- proteins that generate mechanical forces and proteins that are subjected to mechanical forces. Proteins providing mechanical support to the structure of the cell, such as keratin, are subjected to mechanical force, whereas proteins involved in cell movement and transport of molecules across cell membranes, such as an ion pump, are examples of generating mechanical force.
5.0K
01:19Graded Potential
4.0K
Graded potentials are localized fluctuations in the cell membrane's electrical charge, commonly found in the dendrites of neurons. The magnitude of these potential changes depends on the strength of the initiating stimulus. In a membrane at its resting potential, a graded potential signifies a voltage shift either above -70 mV or below -70 mV.
Graded potentials fall into two categories: depolarizing and hyperpolarizing. Depolarizing graded potentials typically occur when sodium (Na+) or...
Graded potentials fall into two categories: depolarizing and hyperpolarizing. Depolarizing graded potentials typically occur when sodium (Na+) or...
4.0K
02:23Gibbs Free Energy and Thermodynamic Favorability
6.8K
The spontaneity of a process depends upon the temperature of the system. Phase transitions, for example, will proceed spontaneously in one direction or the other depending upon the temperature of the substance in question. Likewise, some chemical reactions can also exhibit temperature-dependent spontaneities. To illustrate this concept, the equation relating free energy change to the enthalpy and entropy changes for the process is considered:
6.8K