Scalable Hybrid Deep Neural Networks/Polarizable Potentials Biomolecular Simulations including Long-range Effects
| Autor: | Théo Jaffrelot Inizan, Thomas Plé, Olivier Adjoua, Pengyu Ren, Hatice Gökcan, Olexandr Isayev, Louis Lagardère, Jean-Philip Piquemal |
|---|---|
| Přispěvatelé: | Laboratoire de chimie théorique (LCT), Institut de Chimie du CNRS (INC)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Biomedical Engineering [Austin], University of Texas at Austin [Austin], Carnegie Mellon University [Pittsburgh] (CMU), Institut Parisien de Chimie Physique et Théorique (IP2CT), Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), European Project: 810367,EMC2(2019) |
| Jazyk: | angličtina |
| Rok vydání: | 2023 |
| Předmět: |
Chemical Physics (physics.chem-ph)
Binding free energy prediction Machine learning and deep learning Binding free energy Machine learning applications Molecular dynamics simulations Neural network models Long-range Interactions Tinker-HP FOS: Physical sciences Multiple time stepping Force field molecular dynamics General Chemistry Molecular dynamics Neural network [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] [CHIM.THEO]Chemical Sciences/Theoretical and/or physical chemistry AMOEBA polarizable force field Solvation free energy Physics - Chemical Physics ANI neural network Deep-HP Machine learning Force field Quantum chemistry |
| Zdroj: | Chemical Science Chemical Science, 2023, ⟨10.1039/D2SC04815A⟩ |
| ISSN: | 2041-6520 2041-6539 |
| DOI: | 10.1039/D2SC04815A⟩ |
| Popis: | International audience; Deep-HP is a scalable extension of the Tinker-HP multi-GPUs molecular dynamics (MD) package enabling the use of Pytorch/TensorFlow Deep Neural Networks (DNNs) 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 to introduce 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 DNNs/PFFs partition can be user-defined allowing for hybrid simulations to include biosimulation key ingredients such as polarizable solvents, polarizable counter ions, etc... ANI-2X/AMOEBA is accelerated using a multiple-timestep strategy focusing on the models 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 ligands solvation free energies in 4 solvents, and absolute binding free energies of host-guest complexes from SAMPL challenges. ANI-2X/AMOEBA average errors are within chemical accuracy opening the path towards large-scale hybrid DNNs simulations, at force-field cost, in biophysics and drug discovery. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|