Molecular Foundation Models for Predicting Self-Assembly in Aqueous Mixtures

Pretrained foundation models offer new representations for molecular structures but have predominantly been applied to single-component property prediction. Here, we develop a concentration-weighted average of the latent representations of graph neural network and transformer-based molecular foundation models to predict the critical micelle concentrations of single surfactant, biphasic separation of binary mixtures, and liposome formation in 7-component amphiphile mixtures. Simple random forest and feed-forward neural network models trained with these representations are comparable to or exceed prior work using bespoke graph neural network methods, physicochemical features, and binary fingerprinting. High-throughput automated experiments validate the ability of our models to extrapolate to novel surfactant mixtures and to guide the iterative exploration of liposome design.