Mojmir Mutny

Experiment design, Bayesian optimization or Active learning -- all under one umbrella. The advent of self-driving labs is here. We need strategies to implement automatic information gathering! ML models are only as informed as the data they are trained on.

✨ Featured Speakers: Ditte Welner, Sílvia Osuna, Gustav Oberdorfer, Christian C. Gruber, Markus Jeschek, Juergen Pleiss, Adrian Bunzel, Mattia Gollub, Julian Englert 🔗 Register and submit your poster abstract now! 👉 mlbiocat.github.io/mlbiocat2025//

We’re excited to welcome registered participants from over 10 countries and 15 leading universities 🏫🎓 💡 Discover how ML & computational tools are advancing enzyme design and engage in meaningful discussions about the challenges at the interface of wet lab and dry lab.

🚨 Registration & Poster Submission Deadline Approaching! 🚨 Are you interested in how Machine Learning is shaping the future of Biocatalysis? 🧬🤖 Then don’t miss out on the ML for Biocatalysis Workshop in Zurich! Registration & submission deadline is March 3rd.

Sponsors: NCCR Molecular Systems Engineering, NCCR Catalysis, SNSF, Competence Center for Biocatalysis, Adaptyv Bio, Twist Bioscience, Innophore, and inSEIT. @arkrause @WardGroupBS @rebeccambuller @t_vornholt @JeschekLab

Featuring exciting talks by Ditte Hededam Welner, Silvia Osuna, Gustav Oberdorfer, Christian Gruber, Markus Jeschek, Jürgen Pleiss, Adrian Bunzel & Mattia Gollub. Register and submit your poster abstract now: mlbiocat.github.io/mlbiocat2025//

Are you interested in how machine learning will shape the future of biocatalysis? Then join us for the ML for Biocatalysis Workshop in Zurich! 🧬🤖 Discover how ML & computational tools are advancing enzyme design and discuss challenges at the interface of wet lab and dry lab.

Meet Heisenberg, the software agent that cloud controls chemputers to make molecules using our ChemputerAGI, safely, on demand, & reproducibly.

Our solution is provably converging to the algorithm optimally collecting information, and is practically tractable in discrete or continuous domains. We demonstrate the algorithms on sequence on problem from physical sciences such as reactor optimization!

We apply modern convex reinforcement learning and experiment design for the task of maximum identification with the caveat of transition constrains on the search space. This involves equilibration constrains and/or movement constraints.

#NeurIPS2024It is my pleasure to share that our work on Transition Constrained Bayesian Optimization has been accepted to NeurIPS2024. Amazing work by coauthors @ Imperial: @folch_pablo @RuthMisener @CalvinTsay ETH: @arkrause, Weronica Ormaniec, and amazing scientists from BASF.

Have you ever wondered how to address diversity and increase hit rate in your ML-driven sequential optimization (directed evolution) of enzymes? Small data? No problem, lets select the most informative one! Check out our work featured on front cover with Tobias (@t_vornholt)!

Navigating sequence-activity landscapes with AI and automation - great to have our article featured on the cover of @ACSCentSci

@romerolab1 @DukeUBME @DukeU Congrats!

Happy Monday and big news for the Romero lab: we are moving to Biomedical Engineering Dept. at Duke University (@DukeUBME) later this summer! We will miss our wonderful colleagues and friends at UW-Madison very much, but are thrilled for the new adventure ahead!

An Artificial Metalloenzyme for Atroposelective Metathesis by Thomas R. Ward, Christof Sparr, Markus Jeschek, and co-workers (@WardGroupBS, @christof_sparr, @JeschekLab) onlinelibrary.wiley.com/doi/10.1002/cc…

ML and automation can take protein engineering to a whole new level. In a really exciting collaboration, we have explored new strategies to navigate large sequence-activity landscapes in an efficient yet thorough manner. pubs.acs.org/doi/10.1021/ac…

🌟#ICLR2024 Spotlight🌟 How to learn a policy in an MDP with non-additive rewards, e.g., experiment design, exploration, etc?🤔 Excited to share our paper: Submodular RL for such challenging tasks; where standard RL fails P: openreview.net/pdf?id=loYSzjS… W: @mutny_ml, MZ, @arkrause

The commentary I wrote is now live at Nature Biotech: nature.com/articles/s4158… (free version rdcu.be/dwSSy).

I am at ICLR 2024. Happy to meet familiar and new faces! If you want to talk about AI, active learning, experiment design and self-driving labs, send me a msg. #AI4Science #ICLR2024