Chemists are not only producers of chemicals but also of large amounts of data. In this talk, we will give some examples of the different types of information available and how they are already put to use with machine learning. Applications include the prediction of reaction yields [1] or computer simulations of molecules [2]. However, the bigger part of chemical data is probably left unused in such approaches and the opportunities and challenges for its utilization shall be discussed.

References:

[1]  B. Maryasin, P. Marquetand, N. Maulide, Machine Learning for Organic Synthesis: Robots Replacing Chemists?, Angew. Chem. Int. Ed., 57, 6978-6980 (2018).

[2]   M. Gastegger, J. Behler, P. Marquetand, Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra, Chem. Sci., 8, 6924-6935 (2017).

Nuno Maulide, Institute of Organic Chemistry    
Philipp Marquetand, Institute of Theoretical Chemistry
Boris Maryasin, Institute of Organic Chemistry, Institute of Theoretical Chemistry