Argonne National Laboratory

Rapid procedure for the exploration of chemical compound space

February 27, 2012

By combining quantum chemistry with artificial intelligence (machine learning), researchers at the Institute for Pure and Applied Mathematics at UCLA achieved a scientific breakthrough expected to aid in exploring chemical compound space, i.e., the virtual space populated by all possible chemical compounds. The interdisciplinary team from the Technische Universität Berlin, the Fritz-Haber Institute of the Max-Planck Society, and the Argonne Leadership Computing Facility dramatically increased the speed of calculating energies of small molecules with quantum chemical accuracy. 

Quantum chemical methods permit scientists to calculate molecular properties on a computer from first principles (i.e., without having to conduct any experiments) — they are necessary for many chemical applications such as catalysis, or the discovery of novel materials. Previously, such calculations demanded intensive computational resources. Machine learning, on the other hand, generates predictive models based on examples. When applied to quantum chemistry, thousands of quantum chemical reference energies have been calculated in order to "learn" a molecular model. The resulting machine permits the prediction of molecular properties with comparable accuracy within milliseconds, instead of hours. Such speed-up paves the way for highly accurate calculations of unprecedentedly many molecules.

Matthias Rupp, Alexandre Tkatchenko, Klaus-Robert Müller, and O. Anatole von Lilienfeld,  “Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning,” Phys. Rev. Lett. 108, 058301 (2012).