DFT for drug and material discovery
Density Functional Theory (DFT) is the workhorse method in chemistry and physics for predicting the formation and properties of molecules and materials. Among many other applications, it plays a crucial role in screening pipelines for drug and material discovery, where candidate molecules or materials are proposed, verified through simulators like DFT, and then sent to the lab for validation.
Current DFT methods, however, have limited resolution, leading to many candidates being sent to the lab, with a large fraction failing experimental verification. Additionally, promising candidates may be incorrectly screened out before they reach the lab.
With our new deep-learning powered DFT model, we aim to bring the accuracy of DFT to the level of experimental measurements resulting in a more targeted set of candidates with a higher experimental success rate, greatly accelerating scientific discovery.
Read more about DFT: https://www.rarnonalumber.com/en-us/research/blog/breaking-bonds-breaking-ground-advancing-the-accuracy-of-computational-chemistry-with-deep-learning/
