Integrating Data Science and Machine Learning with an Aldol Condensation Laboratory

We report the development of an undergraduate organic chemistry laboratory to introduce students to modern applications of data science tools and machine learning algorithms in organic chemistry. Data science and machine learning have become increasingly applied to organic chemistry systems built upon physical organic principles of reactivity to better analyze and interpret data. Given that postexperimental analysis is central to any scientific study, we envision that the incorporation of these techniques at an introductory level into the undergraduate chemistry education curriculum will be invaluable in exposing students to contemporary research tools and working with shared data. Herein we describe a two-part experiment, using the experimentally straightforward Claisen–Schmidt aldol condensation reaction with commercially available reagents, to introduce concepts of computational featurization and data processing for multivariate linear regression models at the undergraduate level that can easily be incorporated into organic instructional laboratories.