AI Application in Pharmaceutical Industries Being Beneficial to Material Science
Abstract The application of AI will develop further in the area of material technology similarly to how the application has advanced in the pharmaceutical industry. In this article, we explain how AI is applied in the pharmaceutical industry and in the material sciences. First, we show the trends of AI in data analysis for the different areas of the pharmaceutical industry. Second, we explain how the new machine learning platform (AutoML), in particular, benefits this type of data analysis by describing supervised machine learning. If the target value is available to define, executing the supervised machine learning is feasible to solve the problem. In this case, Implementing an AutoML process is the simple solution to look for insight. Third, we provide and discuss an example of an output from analysis done using unsupervised machine learning such as topological data analysis (TDA) as a new approach. Finally, we explain that these successful examples of AI applications in pharma provide a potential roadmap of how they may be applied to the science of material informatics. Adding new data to the current data is almost always required. Achievements are observed in the area of life science because many databases are consolidated into one database. Thus, creating new data with appropriate definitions and expanding the amount of applicable data will help materials informatics evolve into a field with both higher quality and more robust analyses in the future.