SurfPro – a curated database and predictive model of experimental properties of surfactants

Abstract

Despite great industrial interest, modeling the physical properties of surfactants in water based on their molecular structure remains a challenge. A significant part of this challenge is in obtaining sufficient amounts of high-quality data. Experimentally determined properties such the critical micelle concentration (CMC) and surface tension at CMC (γ_CMC) have been reported for many surfactants. However, surfactant data are scattered across many literature sources, and reported in a manner which is often unsuitable as input for predictive models. In this work, we address this limitation by compiling the SurfPro database of surfactant properties. SurfPro consists of 1624 surfactant entries curated from 223 literature sources, containing 1395 CMC values, 972 γ_CMC values and more than 657 values for Γ_max, C₂₀, π_CMC and A_min. However, only 647 structures have all reported properties, and for most surfactants multiple properties are missing. We trained a previously reported graph neural network architecture for single- and multi-property prediction on these incomplete data of all surfactant types in the database to accurately predict pCMC (−log₁₀(CMC)), γ_CMC, Γ_max and pC₂₀. We achieved state-of-the-art performance of these four properties using an ensemble of AttentiveFP models trained on ten different folds of the training data in the multi-property setting. Finally, we leveraged the predictions and uncertainties of the ensemble model to impute all missing properties for all 977 surfactants with an incomplete set of properties. We make our curated SurfPro database, proposed test split and training datasets, the imputed database, as well as our code publicly available.