SchNetPack 2.0: A neural network toolbox for atomistic machine learning

Abstract

SchNetPack is a versatile neural networks toolbox that addresses both the requirements of method development and application of atomistic machine learning. Version 2.0 comes with an improved data pipeline, modules for equivariant neural networks as well as a PyTorch implementation of molecular dynamics. An optional integration with PyTorch Lightning and the Hydra configuration framework powers a flexible command-line interface. This makes SchNetPack 2.0 easily extendable with custom code and ready for complex training task such as generation of 3d molecular structures.

References in corpus (10)

• Machine learning for molecular simulation
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• Accurate sampling using Langevin dynamics
• Efficient stochastic thermostatting of path integral molecular dynamics
• How to remove the spurious resonances from ring polymer molecular dynamics
• Colored-noise thermostats à la carte
• Unsupervised machine learning in atomistic simulations, between predictions and understanding
• Equivariant Flows: sampling configurations for multi-body systems with symmetric energies
• SE(3)-equivariant prediction of molecular wavefunctions and electronic densities
• Accurate Machine Learned Quantum-Mechanical Force Fields for Biomolecular Simulations

Cited by in corpus (21)

• DeePMD-kit v2: A software package for Deep Potential models
• DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials
• MLatom 3: Platform for machine learning-enhanced computational chemistry simulations and workflows
• The Evolution of Machine Learning Potentials for Molecules, Reactions and Materials
• TorchMD-Net 2.0: Fast Neural Network Potentials for Molecular Simulations
• Generative diffusion model for surface structure discovery
• Neural Network Potential with Multi-Resolution Approach Enables Accurate Prediction of Reaction Free Energies in Solution
• chemtrain: Learning Deep Potential Models via Automatic Differentiation and Statistical Physics
• MGNN: Moment Graph Neural Network for Universal Molecular Potentials
• Stress and heat flux via automatic differentiation
• Analyzing Atomic Interactions in Molecules as Learned by Neural Networks
• FeNNol: an Efficient and Flexible Library for Building Force-field-enhanced Neural Network Potentials
• Metatensor and metatomic: foundational libraries for interoperable atomistic machine learning
• Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features
• A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors
• Reconstructions and Dynamics of $\beta$-Lithium Thiophosphate Surfaces
• EOSnet: Embedded Overlap Structures for Graph Neural Networks in Predicting Material Properties
• Molecular relaxation by reverse diffusion with time step prediction
• Guest Editorial: Special Topic on Software for Atomistic Machine Learning
• Anharmonic infrared spectra of cationic pyrene and superhydrogenated derivatives
• Faster Molecular Dynamics with Neural Network Potentials via Distilled Multiple Time-Stepping and Non-Conservative Forces