Developing Machine-Learned Potentials for Coarse-Grained Molecular Simulations: Challenges and Pitfalls

被引:5
|
作者
Ricci, Eleonora [1 ,2 ]
Giannakopoulos, George [1 ,3 ]
Karkaletsis, Vangelis [1 ]
Theodorou, Doros N. [4 ]
Vergadou, Niki [2 ]
机构
[1] Natl Ctr Sci Res Demokritos, Inst Informat & Telecommun, Athens, Greece
[2] Natl Ctr Sci Res Demokritos, Inst Nanosci & Nanotechnol, Athens, Greece
[3] SciFY P N P C, Athens, Greece
[4] Natl Tech Univ Athens, Sch Chem Engn, Athens, Greece
关键词
Coarse-graining; Molecular Simulations; Machine Learning; Neural Network Potential; Hierarchical Modelling;
D O I
10.1145/3549737.3549793
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Coarse graining (CG) enables the investigation of molecular properties for larger systems and at longer timescales than the ones attainable at the atomistic resolution. Machine learning techniques have been recently proposed to learn CG particle interactions, i.e. develop CG force fields. Graph representations of molecules and supervised training of a graph convolutional neural network architecture are used to learn the potential of mean force through a force matching scheme. In this work, the force acting on each CG particle is correlated to a learned representation of its local environment that goes under the name of SchNet, constructed via continuous filter convolutions. We explore the application of SchNet models to obtain a CG potential for liquid benzene, investigating the effect of model architecture and hyperparameters on the thermodynamic, dynamical, and structural properties of the simulated CG systems, reporting and discussing challenges encountered and future directions envisioned.
引用
收藏
页数:6
相关论文
共 50 条
  • [1] Machine-Learned Coarse-Grained Models
    Bejagam, Karteek K.
    Singh, Samrendra
    An, Yaxin
    Deshmukh, Sanket A.
    [J]. JOURNAL OF PHYSICAL CHEMISTRY LETTERS, 2018, 9 (16): : 4667 - 4672
  • [2] Machine-learned coarse-grained potentials for particles with anisotropic shapes and interactions
    Campos-Villalobos, Gerardo
    Subert, Rodolfo
    Giunta, Giuliana
    Dijkstra, Marjolein
    [J]. NPJ COMPUTATIONAL MATERIALS, 2024, 10 (01)
  • [3] Improved Angle Potentials for Coarse-Grained Molecular Dynamics Simulations
    Bulacu, Monica
    Goga, Nicolae
    Zhao, Wei
    Rossi, Giulia
    Monticelli, Luca
    Periole, Xavier
    Tieleman, D. Peter
    Marrink, Siewert J.
    [J]. JOURNAL OF CHEMICAL THEORY AND COMPUTATION, 2013, 9 (08) : 3282 - 3292
  • [4] Coarse-Grained Many-Body Potentials of Ligand-Stabilized Nanoparticles from Machine-Learned Mean Forces
    Giunta, Giuliana
    Campos-Villalobos, Gerardo
    Dijkstra, Marjolein
    [J]. ACS NANO, 2023, 17 (23) : 23391 - 23404
  • [5] Representation of coarse-grained potentials for polymer simulations
    Briels, WJ
    Akkermans, RLC
    [J]. MOLECULAR SIMULATION, 2002, 28 (1-2) : 145 - 152
  • [6] Electrostatic-Consistent Coarse-Grained Potentials for Molecular Simulations of Proteins
    Spiga, Enrico
    Alemani, Davide
    Degiacomi, Matteo T.
    Cascella, Michele
    Dal Peraro, Matteo
    [J]. JOURNAL OF CHEMICAL THEORY AND COMPUTATION, 2013, 9 (08) : 3515 - 3526
  • [7] Stability and Metastability of Liquid Water in a Machine-Learned Coarse-Grained Model with Short-Range Interactions
    Dhabal, Debdas
    Sankaranarayanan, Subramanian K. R. S.
    Molinero, Valeria
    [J]. JOURNAL OF PHYSICAL CHEMISTRY B, 2022, 126 (47): : 9881 - 9892
  • [8] Introducing Memory in Coarse-Grained Molecular Simulations
    Klippenstein, Viktor
    Tripathy, Madhusmita
    Jung, Gerhard
    Schmid, Friederike
    van der Vegt, Nico F. A.
    [J]. JOURNAL OF PHYSICAL CHEMISTRY B, 2021, 125 (19): : 4931 - 4954
  • [9] Coarse-grained molecular simulations of allosteric cooperativity
    Nandigrami, Prithviraj
    Portman, John J.
    [J]. JOURNAL OF CHEMICAL PHYSICS, 2016, 144 (10):
  • [10] Coarse-grained molecular dynamics simulations of biomolecules
    Takahashi, Ken
    Oda, Takayuki
    Naruse, Keiji
    [J]. AIMS BIOPHYSICS, 2014, 1 (01): : 1 - 15