Rapid prediction of conformationally-dependent DFT-level descriptors using graph neural networks for carboxylic acids and alkyl amines.

Autor:	Haas BC; Department of Chemistry, University of Utah Salt Lake City Utah 84112 USA matt.sigman@utah.edu., Hardy MA; Department of Chemistry, University of Utah Salt Lake City Utah 84112 USA matt.sigman@utah.edu., Sowndarya S V S; Department of Chemistry, Colorado State University Fort Collins Colorado 80523 USA robert.paton@colostate.edu., Adams K; Department of Chemical Engineering, Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA ccoley@mit.edu., Coley CW; Department of Chemical Engineering, Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA ccoley@mit.edu.; Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA., Paton RS; Department of Chemistry, Colorado State University Fort Collins Colorado 80523 USA robert.paton@colostate.edu., Sigman MS; Department of Chemistry, University of Utah Salt Lake City Utah 84112 USA matt.sigman@utah.edu.
Jazyk:	angličtina
Zdroj:	Digital discovery [Digit Discov] 2024 Nov 28. Date of Electronic Publication: 2024 Nov 28.
DOI:	10.1039/d4dd00284a
Abstrakt:	Data-driven reaction discovery and development is a growing field that relies on the use of molecular descriptors to capture key information about substrates, ligands, and targets. Broad adaptation of this strategy is hindered by the associated computational cost of descriptor calculation, especially when considering conformational flexibility. Descriptor libraries can be precomputed agnostic of application to reduce the computational burden of data-driven reaction development. However, as one often applies these models to evaluate novel hypothetical structures, it would be ideal to predict the descriptors of compounds on-the-fly. Herein, we report DFT-level descriptor libraries for conformational ensembles of 8528 carboxylic acids and 8172 alkyl amines towards this goal. Employing 2D and 3D graph neural network architectures trained on these libraries culminated in the development of predictive models for molecule-level descriptors, as well as the bond- and atom-level descriptors for the conserved reactive site (carboxylic acid or amine). The predictions were confirmed to be robust for an external validation set of medicinally-relevant carboxylic acids and alkyl amines. Additionally, a retrospective study correlating the rate of amide coupling reactions demonstrated the suitability of the predicted DFT-level descriptors for downstream applications. Ultimately, these models enable high-fidelity predictions for a vast number of potential substrates, greatly increasing accessibility to the field of data-driven reaction development. Competing Interests: There are no conflicts to declare. (This journal is © The Royal Society of Chemistry.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu