Data-Driven Insights into Porphyrin Geometry: Interpretable AI for Non-Planarity and Aromaticity Analyses

Porphyrins are involved in numerous and very different chemical and biological processes, due to the sensitivity of their application-relevant properties to subtle structural changes. Applying modern machine learning methodology is very appealing for discovering structure-activity relationships that can be used for design of tailor-made porphyrins for specific purposes. For achieving this goal, a high-quality set consisting of 425 metal porphyrins was established via curation of 7590 porphyrin structures from the Cambridge crystallographic database. Using data-driven techniques for analyzing nonplanarity and "structural aromaticity" allowed for validation of common knowledge in the field as well as discovery of new relations. Aromaticity was found to be influenced differently by distinct nonplanar distortions. Nonplanarity is more sensitive to macrocycle substitutions than to metal or axial ligand effects, while ruffled distortions are dominated by axial ligand size and metal properties. These findings offer new insights into structure-property relationships in porphyrins, providing a data-driven foundation for targeted synthesis to tune aromaticity and nonplanarity. Despite data set limitations, this work demonstrates the value of machine learning in uncovering complex chemical trends.