ORIGINAL RESEARCH published: 04 August 2020 doi: 10.3389/fceng.2020.00005 Artificial Intelligence for Computer-Aided Synthesis In Flow: Analysis and Selection of Reaction Components Pieter P. Plehiers 1,2, Connor W. Coley 1, Hanyu Gao 1, Florence H. Vermeire 1, Maarten R. Dobbelaere 2, Christian V. Stevens 3, Kevin M. Van Geem 2* and William H. Green 1* 1 Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA, United States, 2 Laboratory for Chemical Technology, Department of Materials, Textiles and Chemical Engineering, Ghent University, Ghent, Belgium, 3 SynBioC Research Group, Department of Green Chemistry and Technology, Faculty of Bioscience Engineering, Ghent Edited by: University, Ghent, Belgium René Schenkendorf, Technische Universitat Braunschweig, Germany Computer-aided synthesis has received much attention in recent years. It is a challenging Reviewed by: topic in itself, due to the high dimensionality of chemical and reaction space. It becomes Richard Anthony Bourne, even more challenging when the aim is to suggest syntheses that can be performed in University of Leeds, United Kingdom Alexei Lapkin, continuous flow. Though continuous flow offers many potential benefits, not all reactions University of Cambridge, are suited to be operated continuously. In this work, three machine learning models United Kingdom have been developed to provide an assessment of whether a given reaction may benefit *Correspondence: from continuous operation, what the likelihood of success in continuous flow is for a Kevin M. Van Geem
[email protected] certain set of reaction components (i.e., reactants, reagents, solvents, catalysts, and William H. Green products) and, if the likelihood of success is low, which alternative reaction components
[email protected] can be considered.