Designing catalysts with deep generative models and computational data. A case study for Suzuki cross coupling reactions
Oliver Schilter, Alain C. Vaucher, Philippe Schwaller, Teodoro Laino
Abstract
Variational-autoencoders with an additional predictor neural-network and gradient-based optimization allow us to generate new Suzuki-catalysts and predict the binding energies.
Topics & Concepts
Generative grammarArtificial neural networkCoupling (piping)CatalysisComputer scienceDeep neural networksArtificial intelligenceComputational chemistryMachine learningChemistryBiological systemOrganic chemistryEngineeringMechanical engineeringBiologyMachine Learning in Materials ScienceScientific Computing and Data ManagementAdvanced Graph Neural Networks