Scalable hybrid deep neural networks/polarizable potentials biomolecular simulations including long-range effects
Open Access
- 4 April 2023
- journal article
- research article
- Published by Royal Society of Chemistry (RSC) in Chemical Science
- Vol. 14 (20) , 5438-5452
Abstract
Deep-HP is a scalable extension of the Tinker-HP multi-GPU molecular dynamics (MD) package enabling the use of Pytorch/TensorFlow Deep Neural Network (DNN) models. Deep-HP increases DNNs' MD capabilities by orders of magnitude offering access to ns simulations for 100k-atom biosystems while offering the possibility of coupling DNNs to any classical (FFs) and many-body polarizable (PFFs) force fields. It allows therefore the introduction of the ANI-2X/AMOEBA hybrid polarizable potential designed for ligand binding studies where solvent–solvent and solvent–solute interactions are computed with the AMOEBA PFF while solute–solute ones are computed by the ANI-2X DNN. ANI-2X/AMOEBA explicitly includes AMOEBA's physical long-range interactions via an efficient Particle Mesh Ewald implementation while preserving ANI-2X's solute short-range quantum mechanical accuracy. The DNN/PFF partition can be user-defined allowing for hybrid simulations to include key ingredients of biosimulation such as polarizable solvents, polarizable counter ions, etc.… ANI-2X/AMOEBA is accelerated using a multiple-timestep strategy focusing on the model's contributions to low-frequency modes of nuclear forces. It primarily evaluates AMOEBA forces while including ANI-2X ones only via correction-steps resulting in an order of magnitude acceleration over standard Velocity Verlet integration. Simulating more than 10 μs, we compute charged/uncharged ligand solvation free energies in 4 solvents, and absolute binding free energies of host–guest complexes from SAMPL challenges. ANI-2X/AMOEBA average errors are discussed in terms of statistical uncertainty and appear in the range of chemical accuracy compared to experiment. The availability of the Deep-HP computational platform opens the path towards large-scale hybrid DNN simulations, at force-field cost, in biophysics and drug discovery.Keywords
All Related Versions
Funding Information
- H2020 European Research Council (810367, project EMC2)
- National Science Foundation (OAC-1818253)
This publication has 81 references indexed in Scilit:
- Polarizable Atomic Multipole-Based AMOEBA Force Field for ProteinsJournal of Chemical Theory and Computation, 2013
- Automation of AMOEBA polarizable force field parameterization for small moleculesTheoretical Chemistry Accounts, 2012
- Polarizable Molecular Dynamics Simulation of Zn(II) in Water Using the AMOEBA Force FieldJournal of Chemical Theory and Computation, 2010
- Current Status of the AMOEBA Polarizable Force FieldThe Journal of Physical Chemistry B, 2010
- Anisotropic, Polarizable Molecular Mechanics Studies of Inter- and Intramolecular Interactions and Ligand−Macromolecule Complexes. A Bottom-Up StrategyJournal of Chemical Theory and Computation, 2007
- Generalized Neural-Network Representation of High-Dimensional Potential-Energy SurfacesPhysical Review Letters, 2007
- Canonical sampling through velocity rescalingThe Journal of Chemical Physics, 2007
- Ion Solvation Thermodynamics from Simulation with a Polarizable Force FieldJournal of the American Chemical Society, 2003
- Reversible multiple time scale molecular dynamicsThe Journal of Chemical Physics, 1992
- Molecular mechanics. The MM3 force field for hydrocarbons. 1Journal of the American Chemical Society, 1989