Predicting experimental electrophilicities from quantum and topological descriptors: A machine learning approach. Issue 24 (21st July 2020)

• Record Type: Journal Article
• Authors: Hoffmann, Guillaume; Balcilar, Muhammet; Tognetti, Vincent; Héroux, Pierre; Gaüzère, Benoît; Adam, Sébastien; Joubert, Laurent
• Is Part Of: Journal of computational chemistry. Volume 41:Issue 24(2020)
• Page Start: 2124
• Page End: 2136
• Publication Date: 2020-07-21
• Subjects: conceptual density functional theory -- decision trees -- electrophilicity -- machine learning -- nonlinear approaches -- reactivity descriptors; Chemistry -- Data processing -- Periodicals; 542.85
• DOI: 10.1002/jcc.26376
• Languages: English
• ISSNs: 0192-8651

Abstract

Abstract: In this paper, we assess the ability of various machine learning methods, either linear or non‐linear, to efficiently predict Mayr's experimental scale for electrophilicity. To this aim, molecular and atomic descriptors rooted in conceptual density functional theory and in the quantum theory of atoms‐in‐molecules as well as topological features defined within graph theory were evaluated for a large set of molecules widely used in organic chemistry. State‐of‐the‐art regression tools belonging to the support vector machines family and decision tree models were in particular considered and implemented. They afforded a promising predictive model, validating the use of such methodologies for the study of chemical reactivity. Abstract : Quantum chemistry and topological descriptors are used to predict experimental electrophilicity by means of state‐of‐the‐art machine learning techniques.