Evolution is an all-purpose problem solver, which researchers mimic in the laboratory to engineer tailor-made (bio)molecules that aid us in combating diseases and in realizing a sustainable economy. While effective, such directed evolution campaigns are not only laborious and time-consuming, but also cover only a miniscule fraction of the unimaginably large sequence space available. As a result, means to guide evolutionary trajectories along a biomolecule’s fitness landscape are sought-after, as they could greatly accelerate evolutionary searches.
Within the framework of the recently funded ML-GUIDE project, we will make directed evolution guidable and, ultimately, predictable by machine learning. Specifically, you will build a first-in-class framework to expedite the design of high-affinity binders that engage with therapeutic targets or efficient (bio)catalysts for synthetic applications. By seamlessly merging cutting-edge directed evolution, next-generation sequencing, and deep learning approaches, you will establish accelerated Design-Build-Test-Learn cycles to continuously improve models via active learning and guide evolutionary trajectories toward promising but otherwise inaccessible sequence spaces.
You will be embedded in one of the three research groups involved in the ML-GUIDE project and focus your efforts on guiding engineering efforts for one particular biomolecule and its associated function.
(1) Dr. Robert Pollice (https://pollicegroup.web.rug.nl/) leads the Artificial Organic Chemistry Lab at the University of Groningen and will supervise a project focusing on developing efficient peptide catalysts for powerful C-C-bond forming reactions.
(2) Prof. Francesca Grisoni (https://molecularmachinelearning.com/) leads the Molecular Machine Learning Group at the Technical University Eindhoven and will lead a project on designing potent cyclic-peptide drugs for therapeutic intervention.
(3) Prof. Clemens Mayer (https://mayerlab.nl/) leads the Molecular Evolution Group at the University of Groningen and will tackle a project on making the directed evolution of biocatalysts predictable by machine learning.
As part of the ML-GUIDE team, you will closely collaborate with researchers to identify commonalities and distinct aspects of engineering biomolecules for diverse applications!
The preferred starting date is between 01-11-2026 and 01-03-2026.
