ChemFlow:A Hierarchical Neural Network for Multiscale Representation Learning in Chemical Mixtures

TL;DR

ChemFlow introduces a hierarchical neural network that effectively models multiscale interactions in chemical mixtures, improving prediction accuracy of their physicochemical properties by capturing complex, composition-dependent interactions across atomic, functional, and molecular levels.

Contribution

The paper presents ChemFlow, a novel hierarchical framework with dynamic information exchange mechanisms that better emulate realistic chemical environments compared to prior models.

Findings

ChemFlow outperforms existing models in predicting mixture properties.

It accurately captures concentration-dependent behaviors.

The framework demonstrates superior efficiency in complex mixture modeling.

Abstract

Accurate prediction of the physicochemical properties of molecular mixtures using graph neural networks remains a significant challenge, as it requires simultaneous embedding of intramolecular interactions while accounting for mixture composition (i.e., concentrations and ratios). Existing approaches are ill-equipped to emulate realistic mixture environments, where densely coupled interactions propagate across hierarchical levels - from atoms and functional groups to entire molecules - and where cross-level information exchange is continuously modulated by composition. To bridge the gap between isolated molecules and realistic chemical environments, we present ChemFlow, a novel hierarchical framework that integrates atomic, functional group, and molecular-level features, facilitating information flow across these levels to predict the behavior of complex chemical mixtures. ChemFlow employs an atomic-level feature fusion module, Chem-embed, to generate context-aware atomic representations influenced by the mixture state and atomic characteristics. Next, bidirectional group-to-molecule and molecule-to-group attention mechanisms enable ChemFlow to capture functional group interactions both within and across molecules in the mixture. By dynamically adjusting representations based on concentration and composition, ChemFlow excels at predicting concentration-dependent properties and significantly outperforms state-of-the-art models in both concentration-sensitive and concentration-independent systems. Extensive experiments demonstrate ChemFlow's superior accuracy and efficiency in modeling complex chemical mixtures.