CombinatorixPy: Advancing mixture descriptors for computational chemistry
Rahil Ashtari Mahini, Gerardo M. Casañola‐Martín, Stephen Szwiec, Simone A. Ludwig, Bakhtiyor Rasulev · SoftwareX · 2025
Quantitative Structure-Activity/Property Relationship (QSAR/QSPR) is a machine learning approach to predict chemical and physical properties of pure compounds; however, it has limited application in multi-component compounds. The complex and layered nature of multi-component materials presents challenges in computing molecular representation, thus limiting the application of QSAR and QSPR. In this study, a new method has been proposed to derive numerical representation based on a combinatorial approach. It calculates all the possible interactions between different components in reaction using the Cartesian product over sets of descriptors of constituents, considering each multi-component material as a mixture system. A Python package was developed to calculate mixture descriptors based on this arithmetic equation, which can be used in machine learning-based QSAR and QSPR models. • Molecular representation of multi-component materials and polymers. • Simplified structure by modeling materials as mixture systems. • Method applies combinatorial mixing rule, assuming intermolecular interactions in mixture. • Developed Python code to compute Cartesian product for combinatorial mixture descriptor. • Combinatorial descriptors applied in mixture-based QSAR and machine learning models.