In our research, we develop and apply both theory- and data-driven methods to understand and predict chemical phenomena with as few resources as possible. Our main areas of focus are chemical reactivity, active learning, and drug design.
We are always looking for motivated students for bachelor and master theses as well as "hiwi" jobs (payed minijobs in research or teaching). Please write to me (j.proppe@tu-braunschweig.de) or contact me after a lecture or other event. We look forward to hearing from you!
Congratulations to Maike for successfully defending her Doctor thesis!
We warmly welcome our newest group members!
Maike's and Kerstin's publication Unveiling CO2 reactivity with data-driven methods is now available on Digit. Discov.!
Maike's and Liudmila's publication Predicting the stability of base-mediated C--H carboxylation adducts using data science tools is now available on ChemRxiv!
Kerrin's publication Predicting and Explaining Yields with Machine Learning for Carboxylated Azoles and Beyondis now available on J. Chem. Inf. Model.!
Liza's first publication regAL: Python Package for Active Learning of Regression Problems is now available on Arxiv!
