State of the Art and of Outlook of Data Science and Machine Learning in Organic Chemistry

The use of data science, artificial intelligence, and big data in the field of chemistry has recently grown to speed up the discovery of new materials, drugs, and synthetic substances and the identification of automated compounds. Machine learning and data science are commonly used in organic chemistry to predict biological and physicochemical properties of molecules and are referred to as quantitative structure active relationship (QSAR, for biological properties) and quantitative structure property relationship (QSPR, for nonbiological properties). In addition, data science and machine learning have advanced the optimization of molecular properties, synthetic pathways, and even the design of novel compounds. These models can learn the underlying patterns of molecular structures to generate new compounds with desirable properties. Hence, machine learning (ML) is extensively used in chemistry, and the field is rapidly adopting state-of-the-art ML algorithms and tools such as deep learning, tensors, and transformers to solve and model chemical problems. The application of data science and ML, particularly deep learning, plays a significant role in advancing research in organic chemistry.