Predicting the Surface Tension of Liquids: Comparison of Four Modeling Approaches and Application to Cosmetic Oils

Valentin Goussard (1) , Arthur Duprat (2) , Vincent Gerbaud (2) , Jean-Luc Ploix (2) , Gérard Dreyfus (2) , Véronique Nardello-Rataj (1) , Jean-Marie Aubry (1)

1 UCCS - Unité de Catalyse et Chimie du Solide - UMR 8181
2 LGC - Laboratoire de Génie Chimique

The efficiency of four modeling approaches, namely group contributions, corresponding-states principle, σ-moment-based neural networks, and graph machines, are compared for the estimation of the surface tension (ST) of 269 pure liquid compounds at 25 °C from their molecular structure. This study focuses on liquids containing only carbon, oxygen, hydrogen or silicon atoms since our purpose is to predict the surface tension of cosmetic oils. Neural network estimations are performed from σ-moment descriptors as defined in the COSMO-RS model, while methods based on group contributions, corresponding-states principle and graph machines use 2D molecular information (SMILES codes). The graph machine approach provides the best results, estimating the surface tensions of 23 cosmetic oils, such as hemisqualane, isopropyl myristate or decamethylcyclopentasiloxane (D5), with accuracy better than 1 mN.m–1. A demonstration of the graph machine model using the recent Docker technology is available for download in the Supplementary Information.

Mots clés: Surface tension; Ab initio modeling; Group contribution-based methods; COSMO-RS; Graph machines; Neural networks; QSAR; QSPR; Machine learning

Domaines: Génie chimique; Génie des procédés

Valentin Goussard, Arthur Duprat, Vincent Gerbaud, Jean-Luc Ploix, Gérard Dreyfus, et al.. Predicting the Surface Tension of Liquids: Comparison of Four Modeling Approaches and Application to Cosmetic Oils. Journal of Chemical Information and Modeling, 2017, 57 (12), pp.2986-2995. ⟨10.1021/acs.jcim.7b00512⟩. ⟨hal-03512685⟩