MixtureMetrics: A comprehensive package to develop additive numerical features to describe complex materials for machine learning modeling

Multi-component materials/compounds and polymeric/composite systems pose structural complexity that challenges the conventional methods of molecular representation in cheminformatics, which have limited applicability in such cases. Therefore, we have introduced an innovative structural representation technique tailored for complex materials. We implemented different mixing rules based on linear and nonlinear relationships’ additive effect of different components in composites treating each multi-component material as a mixture system. We developed and improved mixture descriptors based on 12 different mixture functions grouped into three main categories: property-based descriptors, concentration-weighted descriptors, and deviation-combination descriptors. A python package was developed for this purpose, allowing users to compute 12 different mixture-descriptors to use as input for the generation of mixture-based Quantitative Structure-Activity/Property Relationship (mxb-QSAR/QSPR) machine learning models for predicting a range of chemical and physical properties across various complex systems.