一种混合自下而上和数据驱动的机器学习方法,用于准确地粗大分子复合体的粗粒度
Korbinian Liebl1, Gregory A Voth1
1Department of Chemistry, Chicago Center for Theoretical Chemistry, Institute for Biophysical Dynamics, and James Franck Institute, The University of Chicago, Chicago, Illinois 60637, United States.
Journal of chemical theory and computation
|April 17, 2025
概括
本研究介绍了一种使用机器学习改进分子模拟的混合粗粒度方法. 新方法准确地预测了结合亲和力和复杂结构,克服了传统方法的局限性.
科学领域:
- 计算化学是一种计算化学.
- 分子动力学分子动力学
- 生物物理学的生物物理.
背景情况:
- "自下而上粗粒化"从原子模拟中开发出低分辨率模型.
- 力量匹配和相对最小化是常见的,但可以过度适应有限的原子数据.
- 对大型分子复合体来说,过度装配是有问题的,影响着结合亲和力预测.
研究的目的:
- 开发一种数据驱动的机器学习混合粗粒度方法.
- 调整相对最小化方法以提高模型准确性.
- 创建粗粒度模型,准确预测结合亲和力和复杂结构.
主要方法:
- 一个基于规范化相对最小化的新型混合粗粒度概念.
- 利用机器学习用于数据驱动的模型开发.
- 对分子复合体的原子模拟数据进行验证.
主要成果:
- 开发的模型准确地复制了目标的结合亲和关系.
- 这些模型以高准确度描述了底层的复杂结构.
- 训练有素的模型表现出多样化的行为,包括频繁的绑定/解绑事件.
结论:
- 混合粗粒度方法克服了传统方法的局限性.
- 这种方法可以准确模拟分子复杂相互作用和结构.
- 这些模型可用于模拟较大的系统,如蛋白质格子和病毒囊.
相关概念视频
02:00Molecular Models
37.6K
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.
37.6K
01:29Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
30
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...
30