低成本,高精度的反应性建模:将遗传算法和机器学习与多级 DFT 计算相结合
José A Pérez1,2, María M Zanardi2, Ariel M Sarotti1
1Instituto de Química Rosario (CONICET), Facultad de Ciencias Bioquímicas y Farmacéuticas, Universidad Nacional de Rosario, Suipacha 531, Rosario 2000, Argentina.
Journal of chemical information and modeling
|November 10, 2025
概括
预测迪尔斯-阿尔德反应能量是一项挑战. 一个新的遗传算法和机器学习 (GA-ML) 框架准确地预测这些能量,以较低的计算成本匹配高级方法.
科学领域:
- 计算化学计算化学
- 化学动力学 化学动力学
背景情况:
- 对迪尔斯-阿尔德 (DA) 反应来说,准确预测吉布斯激活能 (ΔG‡) 是至关重要的,但很困难.
- 传统的密度函数理论 (DFT) 方法往往缺乏所需的化学精度 (<1 kcal mol−1).
研究的目的:
- 系统评估720个用于预测DA反应能量的DFT方法.
- 利用机器学习开发一个具有成本效益,高可靠性框架,用于使用机器学习进行反应性预测.
主要方法:
- 开发了一种遗传算法和机器学习 (GA-ML) 框架,以选择最佳的多级 DFT 组合.
- 引入了动态泛化驱动转移学习 (DGDTL),用于自适应系数优化.
- 对24个DA反应的性能进行了评估,并与高级CCSD计算进行了比较.
主要成果:
- 优化的GA1模型确定了四种低成本的DFT组合,达到0.4 kcal mol-1.1的平均绝对误差 (MAE).
- 这种准确性与高级CCSD计算相匹配,但计算成本显著降低.
- 对于培训和外部验证集,DGDTL确保了可靠的预测,包括未见的反应.
结论:
- 集成的GA-ML和DGDTL框架提供了一个可扩展和准确的方法来预测化学反应性.
- 这种方法为计算化学提供了显著的进步,在催化,药物设计和材料科学中具有广泛的应用.
更多相关视频
05:57Author Spotlight: In Silico Creation and Impact of Carbonylated Amino Acids on Protein Structure and Function
Published on: April 26, 2024
821
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
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
271
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
271
Molecular Models
43.4K
Physical models representing molecular architectures of chemical compounds play essential roles in understanding chemistry. The use of molecular models makes it easier to visualize the structures and shapes of atoms and molecules.
43.4K
