来自机器学习的力场参数的凝结预测了高通量虚拟选应用程序的分布
Domenico Bonanni1,2, Yuedong Zhang3, Davide Gadioli3
1Department of Physical and Chemical Sciences, University of L'Aquila, 67100 Coppito, Italy.
Journal of chemical information and modeling
|November 22, 2025
概括
一种新的机器学习方法缩小了力场参数,在生物分子模拟中显著提高了30倍的计算效率. 这种方法保持了高精度,使复杂的分子建模更容易获得.
科学领域:
- 计算化学计算化学
- 分子动力学分子动力学
- 机器学习 机器学习
背景情况:
- 传统的可转移生物分子力场很难与新数据更新.
- 机器学习力场 (MLFF) 提供了准确性和适应性,但对于高通量虚拟选 (HTVS) 来说,它们在计算上昂贵.
研究的目的:
- 为MLFF参数开发一种新的凝结方法,以提高计算效率.
- 与现有方法相比,评估缩MLFF的准确性和性能.
主要方法:
- 利用机器学习算法来预测和缩小力场参数.
- 开发了一种统计方法,在缩小的参数中表示化学变异性.
- 在OpenFF行业基准数据集上评估了缩的MLFF.
主要成果:
- 在计算效率方面实现了30倍的改进.
- 与分子特异性参数相比,只观察到精度 (RMSD和TFD) 略有下降.
- 缩MLFF显示了与已建立的可转移力场相比具有竞争力的性能.
结论:
- 拟议的凝结方法显著提高了MLFF的计算效率,而不会大幅降低准确度.
- 这种方法为将MLFF集成到HTVS和大型生物分子模拟中提供了可行的解决方案.
更多相关视频
05:37Rapid in-silico Battery Electrolyte Electrochemical Reaction Generation using 3T-VASP Multi-Scale Energy Minimization
Published on: August 22, 2025
583
10:52Multiscale Sampling of a Heterogeneous Water/Metal Catalyst Interface using Density Functional Theory and Force-Field Molecular Dynamics
Published on: April 12, 2019
13.3K
相关概念视频
02:27Predicting Molecular Geometry
44.5K
VSEPR Theory for Determination of Electron Pair Geometries
44.5K
01:20Maxwell-Boltzmann Distribution: Problem Solving
2.8K
Individual molecules in a gas move in random directions, but a gas containing numerous molecules has a predictable distribution of molecular speeds, which is known as the Maxwell-Boltzmann distribution, f(v).
This distribution function f(v) is defined by saying that the expected number N (v1,v2) of particles with speeds between v1 and v2 is given by
This distribution function f(v) is defined by saying that the expected number N (v1,v2) of particles with speeds between v1 and v2 is given by
2.8K
01:06Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
226
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
226