1,3-Asymmetric Induction in Diastereoselective Allylations of Chiral N-Tosyl Imines

Lewis-acid mediated allylations of β-alkoxy N-tosyl imines lead to 3-alkoxy homoallylic N-tosyl amines with anti diastereoselectivity. Diastereoselectivity and yields of reactions are comparable between two methods of Hosomi-Sakurai allylations. Observed selectivity trends and computational evidence suggest that 1,3 asymmetric induction occurs through the formation of a six- membered ring chelate which adopts a half-chair-like conformation. The product ratios of allylations to β-alkoxy N-tosyl imines are dependent on conformation preferences of the chelate and stereoelectronic interactions in the transition-state structures. Debenzylation and detosylation of these allylation products result in anti 1,3-amino alcohols, a privileged motif in synthetic and natural bioactive compounds.

TSNET: PREDICTING TRANSITION STATE STRUCTURES WITH TENSOR FIELD NETWORKS AND TRANSFER LEARNING

Transition states are among the most important molecular structures in chemistry, critical to a variety of fields such as reaction kinetics, catalyst design, and the study of protein function. However,...

Generating Transition States of Isomerization Reactions with Deep Learning

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.

Generating Transition States of Isomerization Reactions with Deep Learning

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.

Genereting Transition States of Isomerization Reactions with Deep Learning

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.