Using of Machine Learning Capabilities to Predict Double Phosphate Structures for Biomedical Applications

Abstract

In the rapidly developing field of biomedical research, the search for new materials with improved properties is crucial to moving the entire field forward. Double phosphates have generated significant interest in a wide range of applications, ranging from drug delivery systems to catalysts for biomedical reactions, and the fields of biomedicine and tissue engineering are no exception. In this article, we propose a method for finding new double phosphate materials, which is based on machine learning, screening, and applying data from structural databases, and use this methodology combined with chemical knowledge to propose several promising materials for bone tissue engineering. For the selected candidates, we develop a solid-phase synthesis procedure and apply their physical characteristics to confirm the results. In addition, the role of morphology, that is, the porosity of frameworks based on these materials, is discussed from a biomedical point of view, and several synthetic ways to adjust this parameter are proposed and investigated.