Lack of quality data and difficulty generating these data hinder quantitative understanding of reaction kinetics. Specifically, conventional methods to generate transition state structures are deficient in speed, accuracy, or scope. We describe a novel method to generate three-dimensional transition state structures for isomerization reactions using reactant and product geometries. Our approach relies on a graph neural network to predict the transition state distance matrix and a least squares optimization to reconstruct the coordinates based on which entries of the distance matrix the model perceives to be important. We feed the structures generated by our algorithm through a rigorous quantum mechanics workflow to ensure the predicted transition state corresponds to the ground truth reactant and product. In both generating viable geometries and predicting accurate transition states, our method achieves excellent results. We envision workflows like this, which combine neural networks and quantum chemistry calculations, will become the preferred methods for computing chemical reactions.

/pdf/generating-transition-states-of-isomerization-reactions-with-3nw9n4pnc0.pdf

Molecular Force Fields with Gradient-Domain Machine Learning: Dynamics of Small Molecules with Coupled Cluster Forces

Citations

Generating transition states of isomerization reactions with deep learning

Related Papers (5)

Constrained langevin dynamics method for simulating molecular conformations

Force distribution in a semiflexible loop

Conformational Analysis of Single DNA Molecules Undergoing Entropically Induced Motion in Nanochannels.

Force-Clamp Experiments Reveal the Free Energy Profile and Diffusion Coefficient of the Collapse of Proteins

Dissipative particle dynamics simulation of field-dependent DNA mobility in nanoslits