Predicting Solvent-Dependent Nucleophilicity Parameter with a Causal Structure Property Relationship

• Published in: Journal of chemical information and modeling 2021-10, Vol.61 (10), p.4890-4899
• Main Authors: Boobier, Samuel, Liu, Yufeng, Sharma, Krishna, Hose, David R. J, Blacker, A. John, Kapur, Nikil, Nguyen, Bao N
• Format: Article
• Language: English
• Subjects: Algorithms; Computing time; Machine learning; Machine Learning and Deep Learning; Mathematical models; Nucleophiles; Parameterization; Parameters; Prediction models; Predictions; Principal components analysis; Reactivity; Selectivity; Solvents
• ISSN: 1549-9596; 1549-960X
• DOI: 10.1021/acs.jcim.1c00610

Solvent-dependent reactivity is a key aspect of synthetic science, which controls reaction selectivity. The contemporary focus on new, sustainable solvents highlights a need for reactivity predictions in different solvents. Herein, we report the excellent machine learning prediction of the nucleophilicity parameter N in the four most-common solvents for nucleophiles in the Mayr’s reactivity parameter database (R 2 = 0.93 and 81.6% of predictions within ±2.0 of the experimental values with Extra Trees algorithm). A Causal Structure Property Relationship (CSPR) approach was utilized, with focus on the physicochemical relationships between the descriptors and the predicted parameters, and on rational improvements of the prediction models. The nucleophiles were represented with a series of electronic and steric descriptors and the solvents were represented with principal component analysis (PCA) descriptors based on the ACS Solvent Tool. The models indicated that steric factors do not contribute significantly, because of bias in the experimental database. The most important descriptors are solvent-dependent HOMO energy and Hirshfeld charge of the nucleophilic atom. Replacing DFT descriptors with Parameterization Method 6 (PM6) descriptors for the nucleophiles led to an 8.7-fold decrease in computational time, and an ∼10% decrease in the percentage of predictions within ±2.0 and ±1.0 of the experimental values.