Machine-Learning-Assisted Free Energy Simulation of Solution-Phase and Enzyme Reactions

2021 ◽  
Vol 17 (9) ◽  
pp. 5745-5758 ◽  
Author(s):  
Xiaoliang Pan ◽  
Junjie Yang ◽  
Richard Van ◽  
Evgeny Epifanovsky ◽  
Junming Ho ◽  
...  
Keyword(s):  
Machine Learning ◽  
Free Energy ◽  
Energy Simulation ◽  
Solution Phase ◽  
Enzyme Reactions

scholarly journals Machine Learning Assisted Free Energy Simulation of Solution–Phase and Enzyme Reactions

2021 ◽  
Author(s):  
Xiaoliang Pan ◽  
junjie yang ◽  
Richard Van ◽  
Evgeny Epifanovsky ◽  
Junming Ho ◽  
...  
Keyword(s):  
Machine Learning ◽  
Free Energy ◽  
Reaction Pathway ◽  
Molecular System ◽  
Computational Cost ◽  
Energy Simulation ◽  
Solution Phase ◽  
Chorismate Mutase ◽  
Enzymatic Reactions ◽  
Enzyme Reactions

Despite recent advances in the development of machine learning potentials (MLPs) for biomolecular simulations, there has been limited effort in developing stable and accurate MLPs for enzymatic reactions. Here, we report a protocol for performing machine learning assisted free energy simulation of solution-phase and enzyme reactions at an ab initio quantum mechanical and molecular mechanical (ai-QM/MM) level of accuracy. Within our protocol, the MLP is built to reproduce the ai-QM/MM energy as well as forces on both QM (reactive) and MM (solvent/enzyme) atoms. As an alternative strategy, a delta machine learning potential (DMLP) is trained to reproduce the differences between ai-QM/MM and semiempirical (se) QM/MM energy and forces. To account for the effect of the condensed–phase environment in both MLP and DMLP, the DeePMD representation of a molecular system is extended to incorporate external electrostatic potential and field on each QM atom. Using the Menshutkin and chorismate mutase reactions as examples, we show that the developed MLP and DMLP reproduce the ai-QM/MM energy and forces with an error on average less than 1.0 kcal/mol and 1.0 kcal/mol/Å for representative configurations along the reaction pathway. For both reactions, MLP/DMLP-based simulations yielded free energy profiles that differed by less than 1.0 kcal/mol from the reference ai-QM/MM results, but only at a fractional computational cost.<br>

scholarly journals Machine Learning Assisted Free Energy Simulation of Solution–Phase and Enzyme Reactions

2021 ◽  
Author(s):  
Xiaoliang Pan ◽  
junjie yang ◽  
Richard Van ◽  
Evgeny Epifanovsky ◽  
Junming Ho ◽  
...  
Keyword(s):  
Machine Learning ◽  
Free Energy ◽  
Reaction Pathway ◽  
Molecular System ◽  
Computational Cost ◽  
Energy Simulation ◽  
Solution Phase ◽  
Chorismate Mutase ◽  
Enzymatic Reactions ◽  
Enzyme Reactions

Despite recent advances in the development of machine learning potentials (MLPs) for biomolecular simulations, there has been limited effort in developing stable and accurate MLPs for enzymatic reactions. Here, we report a protocol for performing machine learning assisted free energy simulation of solution-phase and enzyme reactions at an ab initio quantum mechanical and molecular mechanical (ai-QM/MM) level of accuracy. Within our protocol, the MLP is built to reproduce the ai-QM/MM energy as well as forces on both QM (reactive) and MM (solvent/enzyme) atoms. As an alternative strategy, a delta machine learning potential (DMLP) is trained to reproduce the differences between ai-QM/MM and semiempirical (se) QM/MM energy and forces. To account for the effect of the condensed–phase environment in both MLP and DMLP, the DeePMD representation of a molecular system is extended to incorporate external electrostatic potential and field on each QM atom. Using the Menshutkin and chorismate mutase reactions as examples, we show that the developed MLP and DMLP reproduce the ai-QM/MM energy and forces with an error on average less than 1.0 kcal/mol and 1.0 kcal/mol/Å for representative configurations along the reaction pathway. For both reactions, MLP/DMLP-based simulations yielded free energy profiles that differed by less than 1.0 kcal/mol from the reference ai-QM/MM results, but only at a fractional computational cost.<br>

Determination of Base Flipping Free Energy Landscapes from Nonequilibrium Stratification

2019 ◽  
Author(s):  
Xiaohui Wang ◽  
Zhaoxi Sun
Keyword(s):  
Free Energy ◽  
Energy Landscape ◽  
Sampling Technique ◽  
Umbrella Sampling ◽  
Energy Simulation ◽  
Nonlinear Dependence ◽  
Free Energy Landscape ◽  
Convergence Criterion ◽  
Base Flipping ◽  
Convergence Behavior

<p>Correct calculation of the variation of free energy upon base flipping is crucial in understanding the dynamics of DNA systems. The free energy landscape along the flipping pathway gives the thermodynamic stability and the flexibility of base-paired states. Although numerous free energy simulations are performed in the base flipping cases, no theoretically rigorous nonequilibrium techniques are devised and employed to investigate the thermodynamics of base flipping. In the current work, we report a general nonequilibrium stratification scheme for efficient calculation of the free energy landscape of base flipping in DNA duplex. We carefully monitor the convergence behavior of the equilibrium sampling based free energy simulation and the nonequilibrium stratification and determine the empirical length of time blocks required for converged sampling. Comparison between the performances of equilibrium umbrella sampling and nonequilibrium stratification is given. The results show that nonequilibrium free energy simulation is able to give similar accuracy and efficiency compared with the equilibrium enhanced sampling technique in the base flipping cases. We further test a convergence criterion we previously proposed and it comes out that the convergence behavior determined by this criterion agrees with those given by the time-invariant behavior of PMF and the nonlinear dependence of standard deviation on the sample size. </p>

Solution Phase DNA-Compatible Pictet-Spengler Reaction Aided by Machine Learning Building Block Filtering

2020 ◽  
Author(s):  
Ke Li ◽  
Xiaohong Liu ◽  
Sixiu Liu ◽  
Yulong An ◽  
Yanfang Shen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Building Block ◽  
Solution Phase

scholarly journals A Hybrid Alchemical Free Energy and Machine Learning Methodology for the Calculation of Absolute Hydration Free Energies of Small Molecules

2020 ◽  
Author(s):  
Jenke Scheen ◽  
Wilson Wu ◽  
Antonia S. J. S. Mey ◽  
Paolo Tosco ◽  
Mark Mackey ◽  
...  
Keyword(s):  
Machine Learning ◽  
Free Energy ◽  
Free Energy Calculations ◽  
Learning Approaches ◽  
Free Energies ◽  
Training Set ◽  
Set Size ◽  
Correction Terms ◽  
Alchemical Free Energy ◽  
Alchemical Free Energy Calculations

A methodology that combines alchemical free energy calculations (FEP) with machine learning (ML) has been developed to compute accurate absolute hydration free energies. The hybrid FEP/ML methodology was trained on a subset of the FreeSolv database, and retrospectively shown to outperform most submissions from the SAMPL4 competition. Compared to pure machine-learning approaches, FEP/ML yields more precise estimates of free energies of hydration, and requires a fraction of the training set size to outperform standalone FEP calculations. The ML-derived correction terms are further shown to be transferable to a range of related FEP simulation protocols. The approach may be used to inexpensively improve the accuracy of FEP calculations, and to flag molecules which will benefit the most from bespoke forcefield parameterisation efforts.

Quantum Chemical and Free Energy Simulation Analysis of Retinal Conformational Energetics

1997 ◽  
Vol 37 (6) ◽  
pp. 1018-1024 ◽  
Author(s):  
Jérôme Baudry ◽  
Serge Crouzy ◽  
Benoît Roux ◽  
Jeremy C. Smith
Keyword(s):  
Free Energy ◽  
Quantum Chemical ◽  
Simulation Analysis ◽  
Energy Simulation
Sign in / Sign up

Export Citation Format

Share Document