Computer based chemistry (modeling of molecules and reactions) is nothing new. It seems (although not clear from the site) that this is some sort of ML-based “reaction prediction” algorithm based on pattern matching of known reactions vs modeling the electrons in drawn molecules which would—-from a chemistry perspective—-be a much better way to approach the problem.
Is this just IBM throwing another “hey everybody look we did some machine learning” thing at the wall and hoping it sticks or is there real scientific advancement here in computational chemistry?
Indeed, we used machine learning to predict reactions. DFT and molecular dynamics are much more computationally expensive (magnitude of ~10^4s) whereas here you can predict a reaction in less than a sec.
Obviously we are not the only one working on this topic, but our approach is pretty flexible and general. Compared to other approaches, we handle stereochemistry (graph methods are struggling with that) and we don't require data with atom mapping for training.
Is this just IBM throwing another “hey everybody look we did some machine learning” thing at the wall and hoping it sticks or is there real scientific advancement here in computational chemistry?