AIMNet2 Now Available on Rowan
two orders of magnitude faster than conventional DFT; glimpsing the future of computational chemistry
We’re excited to announce that you can now run AIMNet2 calculations through Rowan. AIMNet2 is the latest machine learning-based interatomic potential from Olexander Isayev’s group at Carnegie Mellon, released just a few months ago. While there have been lots of exciting developments in ML potentials recently, AIMNet2 is particularly suited for routine use by computational chemists:
AIMNet2 supports 14 elements (H, B–F, Si–Cl, As–Br, I), up from 4 elements in the original ANI release and 7 in ANI-2x; and while ANI is limited to neutral compounds, AIMNet2 can also handle charged molecules.
Unlike many machine learning-based methods, no system-specific training or external descriptors are required, making AIMNet2 a fast and simple way to accelerate chemical modeling.
On a variety of benchmarks (like GMTKN55), AIMNet2 is more accurate than semiempirical methods like GFN2-xtb and displays comparable accuracy to routine DFT methods. Of course, there are still limitations: metals and open-shell systems aren’t supported, and there’s no way to model solvent effects yet.
Perhaps most importantly, AIMNet2 is incredibly fast compared to conventional quantum chemical calculations—so fast that the entire experience of running a calculation is different. Rather than submitting a job and waiting hours or days, you can get your answers in the time it takes to check your email. Here’s how fast AIMNet2 is when run through Rowan:
Optimizing the geometry of maraviroc (78 atoms) takes 3.5 minutes.
Similarly, optimizing the geometry of azithromycin (124 atoms) takes 5 minutes. (The same optimization is reported to take 9 hours at the B3LYP/6-31G(d) level of theory, so AIMNet2 is about two orders of magnitude faster—and probably more accurate, since it’s trained to reproduce the ωB97M-D3/def2-TZVPP level of theory.)
Running an optimization and subsequent frequency calculation on a 108-atom hydrogen-bond-donor catalyst from my PhD takes only 4 minutes.
Optimizing 64 lisdexamfetamine conformers takes 10 minutes, including the time it takes to allocate the computers: the optimizations run in parallel, and the whole ensemble costs only 178 credits to run (about $3.50), while running the same ensemble with HF-3c costs 1166 credits.
Although AIMNet2 is open-source, there are many advantages to running AIMNet2 through Rowan. As a part of this release, we’ve written Peregrine, a library which uses energy and gradient calculations from ML potentials to run geometry optimizations, compute frequencies, analyze thermochemistry and molecular symmetry, and more. With Peregrine, you can run calculations with AIMNet2 just like you would for a conventional QM calculation—and Rowan’s autoscaling capabilities mean that even hundreds of jobs can all run within minutes.
Best of all, if you already have a Rowan account, you can start using AIMNet2 without having to install anything. Simply select “Peregrine” as the underlying engine, and we’ll handle the rest:
AIMNet2 is our first step into the world of ML-accelerated computational chemistry, but it won’t be our last. We plan to add more ML models to Rowan in the near future, so stay tuned! (And if you want us to add your model, reach out and we’ll get back to you.)