Abstract

The theses examine the complementary roles of artificial intelligence and cheminformatics in modern chemistry. The applications of machine learning in predicting chemical properties, planning organic synthesis, forecasting chemical reactions, drug discovery, and experimental optimization are discussed. The advantages and limitations of AI-based approaches are analyzed, including data quality, model interpretability, prediction uncertainty, and the need for experimental validation. Future perspectives involving autonomous laboratories, materials discovery, quantum chemistry, and the development of digitally skilled chemists are considered.