A Star Wars character beats Quantum Chemistry! A neural network accelerating molecular calculations
Adrian Roitberg, University of Florida
We will show that a neural network can learn to compute energies and forces for acting on small molecules, from a training set of quantum mechanical calculations. This allows us to perform very accurate calculations at roughly a 10^7 speedup versus conventional quantum calculations. This opens the door for many possible applications, where the speed versus accuracy bottleneck have made them unfeasible until now.
References:
”TorchANI: A Free and Open Source PyTorch Based Deep Learning Implementation of the ANI Neural Network Potentials” Xiang Gao, Farhad Ramezanghorbani, Olexander Isayev,Justin S. Smith, and Adrian E. Roitberg. Journal of Chemical Information and Modeling (2020) 60:3408–3415 https://doi.org/10.26434/chemrxiv.12218294.v1
“Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning”. Justin Smith , Benjamin Nebgen , Roman Zubatyuk , Nicholas Lubbers , Christian Devereux , Kipton Barros , Sergei Tretiak , Olexandr Isayev, Adrian Roitberg. Nature Communications 10: 2903 (2019) https://www.nature.com/articles/s41467-019-10827-4
"Less is more: sampling chemical space with active learning" Justin S. Smith, Ben Nebgen, Nicholas Lubbers, Olexandr Isayev, Adrian E. Roitberg. The Journal of Chemical Physics. 148:241733 (2018) https://doi.org/10.1063/1.5023802