Synergies Between Quantum Mechanics and Machine Learning in Reaction Prediction

Abstract

Machine learning (ML) and quantum mechanical (QM) methods can be used in two-way synergy to build chemical reaction expert systems. The proposed ML approach identifies electron sources and sinks among reactants and then ranks all source-sink pairs. This addresses a bottleneck of QM calculations by providing a prioritized list of mechanistic reaction steps. QM modeling can then be used to compute the transition states and activation energies of the top-ranked reactions, providing additional or improved examples of ranked source-sink pairs. Retraining the ML model closes the loop, producing more accurate predictions from a larger training set. The approach is demonstrated in detail using a small set of organic radical reactions.

Modelling Chemical Reasoning to Predict and Invent Reactions

“…Preliminary work in our laboratory indicates that these can be solved be an extension of the model, for example, by augmenting the graph with abstract, hierarchical knowledge about molecules and reactions, similar to the hierarchical representations that human experts develop . In forthcoming work, we will further examine how our ansatz can be combined with machine learning and quantum mechanics . Finally, we anticipate that our work will take up the pioneering work on computer‐assisted reaction discovery by Ugi and Herges, and will be employed as an inspirational tool that provides ideas for unprecedented reactions.…”

“…[3] In forthcoming work, we will further examine how our ansatz can be combined with machine learning [17][18][19][20][21][22][23] andq uantum mechanics. [49,50] Finally,w ea nticipate that our work will take up the pioneering work on computer-assisted reaction discovery by Ugi and Herges, and will be employed as an inspirational tool that providesi deas for unprecedented reactions.…”

Machine learning dihydrogen activation in the chemical space surrounding Vaska's complex

“…The catalysis of a particular reaction is typically proven for only a few tens (or less) of metal complexes. The possibility of learning from synthetic data generated in silico [99][100][101] is appealing, but in practice accurate QC calculations are expensive. In this context, optimizing the ratio between accuracy and the size of the training data is imperative.…”

Deep Learning for Deep Chemistry: Optimizing the Prediction of Chemical Patterns

“…Also, recent progresses have enabled the acceleration of MD simulations (atomistic and coarse-grained), contributing to increase knowledge on the interactions within quantum manybody systems and efficiency of DFT-based quantum mechanical modeling methods (Bartók et al, 2010(Bartók et al, , 2013Behler, 2011aBehler, ,b, 2016Rupp et al, 2012Rupp et al, , 2015Snyder et al, 2012;Hansen et al, 2013Hansen et al, , 2015Montavon et al, 2013;Schütt et al, 2014;Alipanahi et al, 2015;Botu and Ramprasad, 2015b;De et al, 2016;Faber et al, 2016;Sadowski et al, 2016;Wei et al, 2016;Brockherde et al, 2017;Chmiela et al, 2017Chmiela et al, , 2018Smith et al, 2017;Wu et al, 2017;Gómez-Bombarelli et al, 2018). This field is still in its infancy and have offered invaluable opportunities for dealing with a wide range of challenges and unsolved questions, including but not limited to model accuracy, interpretability, and causality.…”