Welcome to TorchANI’s documentation!

TorchANI is a PyTorch implementation of ANI, created and maintained by the Roitberg group. TorchANI contains classes like AEVComputer, ANIModel, and EnergyShifter that can be pipelined to compute molecular energies from the 3D coordinates of molecules. It also include tools to: deal with ANI datasets(e.g. ANI-1, ANI-1x, ANI-1ccx, ANI-2x) at torchani.data, import various file formats of NeuroChem at torchani.neurochem, and more at torchani.utils.

Getting Started

• Installation
• Tips

Examples

• Computing Energy and Force Using Models Inside Model Zoo
• Structure minimization and constant temperature MD using ASE interface
• Using TorchScript to serialize and deploy model
  • Scripting builtin model directly
  • Customize the model and script
• Computing Vibrational Frequencies Using Analytical Hessian
• Construct Model From NeuroChem Files
• Train Your Own Neural Network Potential
• Train Neural Network Potential To Both Energies and Forces
• Train Neural Network Potential From NeuroChem Input File

TorchANI's API

• TorchANI
• Model Zoo
• Datasets
• Utilities
• NeuroChem
• ASE Interface
• Units

Indices and tables

• Index
• Module Index
• Search Page