通过不确定性引导的积极学习获得的凝聚有机系统的双切机器学习潜力
Leonid Kahle1, Benoit Minisini1, Tai Bui2
1Materials Design SARL, 42 avenue Verdier, 92120 Montrouge, France. lkahle@materialsdesign.com.
机器学习潜力 (MLP) 为有机化合物提供了高效而准确的预测. 一个新的双重描述器有效地模拟了短距离和长距离相互作用,并通过实验数据验证.
科学领域:
- 计算化学计算化学
- 材料科学 材料科学 材料科学
- 机器学习 机器学习
背景情况:
- 机器学习潜力 (MLP) 弥合了古典和第一原则方法之间的差距.
- 精确建模有机化合物在凝结阶段仍然是一个挑战.
研究的目的:
- 开发和培训一个MLP,以准确地预测有机分子的潜在能量表面和性质.
- 为分子内和分子间相互作用创建一个多功能描述符.
主要方法:
- 基于原子集群膨胀 (ACE) 的新型双重描述器的实施和培训.
- 以不确定性为导向的积极学习,以实现高效的培训集生成.
- 适用于分子和凝结相中的酒精,和酸盐.
主要成果:
- MLP准确地预测密度与实验差异<4%.
- 与DFT相比,振动频率显示<1 THz的RMSE.
- 凝结系统的热容量在实验值的11%以内.
结论:
- 双重描述器准确地捕捉了短距离的分子内相互作用和长距离的分子间相互作用.
- 用这种方法培训的MLP为有机材料提供了计算效率高,准确的工具.
- 该方法对各种有机化合物具有广泛的适用性.
更多相关视频
09:17Structure-Based Simulation and Sampling of Transcription Factor Protein Movements along DNA from Atomic-Scale Stepping to Coarse-Grained Diffusion
Published on: March 1, 2022
11:18Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
Published on: March 2, 2015
相关概念视频
Cooperative Allosteric Transitions
Predicting Molecular Geometry
Predicting Reaction Outcomes
Thermodynamics: Chemical Potential and Activity
The thermodynamic equilibrium constant is more accurately defined in terms of activity rather than concentration.
Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model
When a drug is administered through a constant intravenous infusion and eliminated via nonlinear pharmacokinetics, it follows zero-order input. For example, oral drugs undergo first-order absorption upon administration and are eliminated through nonlinear pharmacokinetics.
In the case of subcutaneously administered drugs,...
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
