Browsing by Author "Mao, Yuezhi"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Free Energy Profile Decomposition Analysis for QM/MM Simulations of Enzymatic Reactions
    (American Chemical Society, 2023) Pan, Xiaoliang; Van, Richard; Pu, Jingzhi; Nam, Kwangho; Mao, Yuezhi; Shao, Yihan; Chemistry and Chemical Biology, School of Science
    In enzyme mechanistic studies and mutant design, it is highly desirable to know the individual residue contributions to the reaction free energy and barrier. In this work, we show that such free energy contributions from each residue can be readily obtained by postprocessing ab initio quantum mechanical molecular mechanical (ai-QM/MM) free energy simulation trajectories. Specifically, through a mean force integration along the minimum free energy pathway, one can obtain the electrostatic, polarization, and van der Waals contributions from each residue to the free energy barrier. Separately, a similar analysis procedure allows us to assess the contribution from different collective variables along the reaction coordinate. The chorismate mutase reaction is used to demonstrate the utilization of these two trajectory analysis tools.
  • Thumbnail Image
    Item
    Machine learning based implicit solvent model for aqueous-solution alanine dipeptide molecular dynamics simulations
    (Royal Society of Chemistry, 2023-02-03) Yao, Songyuan; Van, Richard; Pan, Xiaoliang; Park, Ji Hwan; Mao, Yuezhi; Pu, Jingzhi; Mei, Ye; Shao, Yihan; Chemistry and Chemical Biology, School of Science
    Inspired by the recent work from Noé and coworkers on the development of machine learning based implicit solvent model for the simulation of solvated peptides [Chen et al., J. Chem. Phys., 2021, 155, 084101], here we report another investigation of the possibility of using machine learning (ML) techniques to "derive" an implicit solvent model directly from explicit solvent molecular dynamics (MD) simulations. For alanine dipeptide, a machine learning potential (MLP) based on the DeepPot-SE representation of the molecule was trained to capture its interactions with its average solvent environment configuration (ASEC). The predicted forces on the solute deviated only by an RMSD of 0.4 kcal mol-1 Å-1 from the reference values, and the MLP-based free energy surface differed from that obtained from explicit solvent MD simulations by an RMSD of less than 0.9 kcal mol-1. Our MLP training protocol could also accurately reproduce combined quantum mechanical molecular mechanical (QM/MM) forces on the quantum mechanical (QM) solute in ASEC environment, thus enabling the development of accurate ML-based implicit solvent models for ab initio-QM MD simulations. Such ML-based implicit solvent models for QM calculations are cost-effective in both the training stage, where the use of ASEC reduces the number of data points to be labelled, and the inference stage, where the MLP can be evaluated at a relatively small additional cost on top of the QM calculation of the solute.
  • Thumbnail Image
    Item
    Machine learning based implicit solvent model for aqueous-solution alanine dipeptide molecular dynamics simulations
    (RSC, 2023) Yao, Songyuan; Van, Richard; Pan, Xiaoliang; Park, Ji Hwan; Mao, Yuezhi; Pu, Jingzhi; Mei, Ye; Shao, Yihan; Chemistry and Chemical Biology, School of Science
    Inspired by the recent work from Noé and coworkers on the development of machine learning based implicit solvent model for the simulation of solvated peptides [Chen et al., J. Chem. Phys., 2021, 155, 084101], here we report another investigation of the possibility of using machine learning (ML) techniques to “derive” an implicit solvent model directly from explicit solvent molecular dynamics (MD) simulations. For alanine dipeptide, a machine learning potential (MLP) based on the DeepPot-SE representation of the molecule was trained to capture its interactions with its average solvent environment configuration (ASEC). The predicted forces on the solute deviated only by an RMSD of 0.4 kcal mol−1 Å−1 from the reference values, and the MLP-based free energy surface differed from that obtained from explicit solvent MD simulations by an RMSD of less than 0.9 kcal mol−1. Our MLP training protocol could also accurately reproduce combined quantum mechanical molecular mechanical (QM/MM) forces on the quantum mechanical (QM) solute in ASEC environment, thus enabling the development of accurate ML-based implicit solvent models for ab initio-QM MD simulations. Such ML-based implicit solvent models for QM calculations are cost-effective in both the training stage, where the use of ASEC reduces the number of data points to be labelled, and the inference stage, where the MLP can be evaluated at a relatively small additional cost on top of the QM calculation of the solute.
  • Thumbnail Image
    Item
    Training Machine Learning Potentials for Reactive Systems: A Colab Tutorial on Basic Models
    (Wiley, 2024) Pan, Xiaoliang; Snyder, Ryan; Wang, Jia-Ning; Lander, Chance; Wickizer, Carly; Van, Richard; Chesney, Andrew; Xue, Yuanfei; Mao, Yuezhi; Mei, Ye; Pu, Jingzhi; Shao, Yihan; Chemistry and Chemical Biology, School of Science
    In the last several years, there has been a surge in the development of machine learning potential (MLP) models for describing molecular systems. We are interested in a particular area of this field - the training of system-specific MLPs for reactive systems - with the goal of using these MLPs to accelerate free energy simulations of chemical and enzyme reactions. To help new members in our labs become familiar with the basic techniques, we have put together a self-guided Colab tutorial (https://cc-ats.github.io/mlp_tutorial/), which we expect to be also useful to other young researchers in the community. Our tutorial begins with the introduction of simple feedforward neural network (FNN) and kernel-based (using Gaussian process regression, GPR) models by fitting the two-dimensional Müller-Brown potential. Subsequently, two simple descriptors are presented for extracting features of molecular systems: symmetry functions (including the ANI variant) and embedding neural networks (such as DeepPot-SE). Lastly, these features will be fed into FNN and GPR models to reproduce the energies and forces for the molecular configurations in a Claisen rearrangement reaction.