Towards the design of chemical reactions: Machine learning barriers of competing mechanisms in reactant space

Abstract

While sophisticated numerical methods for studying equilibrium states have well advanced, quantitative predictions of kinetic behaviour remain challenging. We introduce a reactant-to-barrier (R2B) machine learning model that rapidly and accurately infers activation energies and transition state geometries throughout chemical compound space. R2B enjoys improving accuracy as training sets grow, and requires as input solely molecular graph information of the reactant. We provide numerical evidence for the applicability of R2B for two competing text-book reactions relevant to organic synthesis, E2 and SN2, trained and tested on chemically diverse quantum data from literature. After training on 1k to 1.8k examples, R2B predicts activation energies on average within less than 2.5 kcal/mol with respect to Coupled-Cluster Singles Doubles (CCSD) reference within milliseconds. Principal component analysis of kernel matrices reveals the hierarchy of the multiple scales underpinning reactivity in chemical space: Nucleophiles and leaving groups, substituents, and pairwise substituent combinations correspond to systematic lowering of eigenvalues. Analysis of R2B based predictions of ~11.5k E2 and SN2 barriers in gas-phase for previously undocumented reactants indicates that on average E2 is favored in 75% of all cases and that SN2 becomes likely for nucleophile/leaving group corresponding to chlorine, and for substituents consisting of hydrogen or electron-withdrawing groups. Experimental reaction design from first principles is enabled thanks to R2B, which is demonstrated by the construction of decision trees. Numerical R2B based results for interatomic distances and angles of reactant and transition state geometries suggest that Hammond's postulate is applicable to SN2, but not to E2.

References in corpus (8)

• FCHL revisited: faster and more accurate quantum machine learning
• Autonomous discovery in the chemical sciences part I: Progress
• Machine learning based energy-free structure predictions of molecules (closed and open-shell), transition states, and solids
• Towards the design of chemical reactions: Machine learning barriers of competing mechanisms in reactant space
• Machine Learning of Free Energies in Chemical Compound Space Using Ensemble Representations: Reaching Experimental Uncertainty for Solvation
• An assessment of the structural resolution of various fingerprints commonly used in machine learning
• Machine Learning Quantum Reaction Rate Constants
• Ab initio machine learning in chemical compound space

Cited by in corpus (9)

• Quantum Machine Learning for Chemistry and Physics
• Quantum chemistry-augmented neural networks for reactivity prediction: Performance, generalizability and interpretability
• Towards the design of chemical reactions: Machine learning barriers of competing mechanisms in reactant space
• 3DReact: Geometric deep learning for chemical reactions
• Quantum chemical roots of machine-learning molecular similarity descriptors
• Ab initio machine learning of phase space averages
• Molecular Hessian matrices from a machine learning random forest regression algorithm
• Data-Driven Modeling of S0 -> S1 Excitation Energy in the BODIPY Chemical Space: High-Throughput Computation, Quantum Machine Learning, and Inverse Design
• Finding Pathways in Reaction Networks guided by Energy Barriers using Integer Linear Programming