PyAPX: python toolkit for atomic configuration pattern exploration

In materials discovery, the integration of first-principles calculations with machine learning techniques has been actively studied for two key tasks: crystal structure prediction, which searches for stable structures given a chemical composition, and elemental substitution, which explores chemical compositions that yield desirable properties in a given crystal structure. However, even when both the crystal structure and chemical composition are fixed, material properties can still vary depending on the atomic arrangements (configurations) at crystallographic sites. To support detailed material design, we present PyAPX, a Python toolkit that performs Bayesian searches of stable atomic configurations. A distinctive feature of this initial release is the introduction of encoding methods suitable for configuration search, and we evaluate their performance using the h-BCN system. As a result, the modified neighbor-atom (NAmod) encoding was confirmed to yield superior convergence compared to commonly used one-hot encoding in this system. In addition, the applicability of the toolkit and the proposed encoding beyond the two-dimensional test case is demonstrated for a three-dimensional c-BC 2 N system, using a universal machine-learning interatomic potential as the energy evaluator. The system dependence of the encoding performance is also discussed. PyAPX is broadly applicable to crystalline materials and is expected to further advance materials discovery.