Computational science

Deep neural networks

Open source

Applied mathematics

Computation

Computer science

Hessian matrix

Software

Computer architecture

Source code

Mathematics

Inference

Computer engineering

Artificial intelligence

Programming language

Deep learning

Artificial neural network

Machine learning

Journal of Chemical Information and Modeling

This paper presents TorchANI, a PyTorch-based program for training/inference of ANI (ANAKIN-ME) deep learning models to obtain potential energy surfaces and other physical properties of molecular systems. ANI is an accurate neural network potential originally implemented using C++/CUDA in a program called NeuroChem. Compared with NeuroChem, TorchANI has a design emphasis on being lightweight, user friendly, cross platform, and easy to read and modify for fast prototyping, while allowing acceptable sacrifice on running performance. Because the computation of atomic environmental vectors and atomic neural networks are all implemented using PyTorch operators, TorchANI is able to use PyTorch's autograd engine to automatically compute analytical forces and Hessian matrices, as well as do force training without requiring any additional codes. TorchANI is open-source and freely available on GitHub: https://github.com/aiqm/torchani.

TorchANI: A Free and Open Source PyTorch-Based Deep Learning Implementation of the ANI Neural Network Potentials