Cross-validation strategies in QSPR modelling of chemical reactions. Issue 3 (4th March 2021)

• Record Type: Journal Article
• Authors: Rakhimbekova, A.; Akhmetshin, T.N.; Minibaeva, G.I.; Nugmanov, R.I.; Gimadiev, T.R.; Madzhidov, T.I.; Baskin, I.I.; Varnek, A.
• Is Part Of: SAR and QSAR in environmental research. Volume 32:Issue 3(2021)
• Page Start: 207
• Page End: 219
• Publication Date: 2021-03-04
• Subjects: Validation -- QSPR -- chemical reactions -- rate constant prediction -- reaction rate -- structure-reactivity modelling; Structure-activity relationships (Biochemistry) -- Periodicals; QSAR (Biochemistry) -- Periodicals; 572.4
• DOI: 10.1080/1062936X.2021.1883107
• Languages: English
• ISSNs: 1062-936X

Abstract

ABSTRACT: In this article, we consider cross-validation of the quantitative structure-property relationship models for reactions and show that the conventional k-fold cross-validation (CV) procedure gives an 'optimistically' biased assessment of prediction performance. To address this issue, we suggest two strategies of model cross-validation, 'transformation-out' CV, and 'solvent-out' CV. Unlike the conventional k-fold cross-validation approach that does not consider the nature of objects, the proposed procedures provide an unbiased estimation of the predictive performance of the models for novel types of structural transformations in chemical reactions and reactions going under new conditions. Both the suggested strategies have been applied to predict the rate constants of bimolecular elimination and nucleophilic substitution reactions, and Diels-Alder cycloaddition. All suggested cross-validation methodologies and tutorial are implemented in the open-source software package CIMtools (https://github.com/cimm-kzn/CIMtools ).