A machine learning-guided adaptive parameterization method was proposed for developing a mixed atomic and coarse-grained (CG)
model through a multi-objective optimization strategy. Our model incorporates the united-atom (UA) model for diphenylalanine
(P) and the polarizable electrostatic-variable coarse-grained (VaCG) model for aqueous ionic liquids [BMIM]+[BF4]- solution.
In this mixed model, the coupling van der Waals (vdW) interaction is addressed by introducing virtual sites (VS) in UA model
to interact with solvent CG beads. The coupling parameters, including the electrostatic parameter and vdW parameters,
are automatically optimized through ML-guided adaptive parameterization. The performance of this model was tested by some
microstructural properties, e.g., the average number of inter-P hydrogen bond (HB) and radius distribution functions (RDF)
between P and different fragments of IL, in comparison with all-atom (AA) simulations. The computational cost is significantly
reduced using such a parameterization scheme, which could search tens of thousands of force field parameter sets,
while needing only a small fraction of them to be assessed with molecular dynamic (MD) simulations.
To cite this algorithm, please reference: Yang Ge, Xueping Wang, Qiang Zhu, Yuqin Yang, Hao Dong, Jing Ma*, Machine Learning-Guided Adaptive Parameterization for Coupling Terms in a Mixed United-atom/Coarse-Grained Model for Diphenylalanine Self-assembly in Aqueous Ionic Liquids. J. Chem. Theory Comput. 2023, 19, 6718–6732.
To request the code and data, please complete the LICENSE FORM,
scan and email it to majing@nju.edu.cn.