We belong to the Institute of Bioengineering at EPFL and are also part of the Ludwig Institute for Cancer Research (LICR) in Lausanne. While EPFL provides a world class environment for basic science and engineering, the LICR fosters translational applications of basic discoveries to cancer medicine at the highest level. Our laboratory benefits from this dual exciting environment and interdisciplinary approaches are essential to our research. We welcome highly motivated students and postdocs with computational and experimental backgrounds to continue fostering a very collaborative end enjoyable environment in the lab. We design projects so lab members can not only continue to develop their main skills but also learn novel techniques and acquire fundamental knowledge on membrane protein signaling and design.
On the computational side, we are looking for highly motivated and experienced scientists in the areas of computational biophysics, chemistry and biology with strong programming skills. Projects involve computational developments, protein modeling and design applications in collaborations with experimentalists as well as database mining and analysis. Computational experts who wish to also acquire wet lab skills are welcome to apply.
On the experimental side, we are looking for highly motivated and experienced scientists in the areas of protein engineering, biophysics, biochemistry, structures, protein-protein interactions and protein/cellular signaling with particular emphasis on membrane receptors. Projects involve protein modeling and design applications in collaborations with computational experts in the lab, directed evolution of receptor functions as well as investigations of native receptor systems. Experimentalists who wish to receive training in computational and quantitative approaches are welcome to apply.
If you are interested, feel free to email the lab directly with your CV, research interests, and the names and contact information of three professional references.
Expanding the universe of protein functions for synthetic biology and biomedicine
Our lab is developing and applying hybrid AI-based computational/experimental approaches for engineering classes of proteins with novel functions for cell engineering, synthetic biology and therapeutic applications. Through our bottom up design approach, we also strive to better understand the molecular and physical principles that underlie the emergence, evolution and robustness of the complex functions encoded by proteins and their associated networks.
We are part of RosettaCommons (https://rosettacommons.org/), a collaborative network of academic laboratories that develop the software platform Rosetta and AI-based approaches for macromolecular modeling and design. Ultimately, we aim to develop a versatile tool for designing novel potent, selective therapeutic molecules, synthetic proteins, receptor biosensors, networks and pathways for reprogramming cellular functions. We are also affiliated to the Ludwig Institute for Cancer Research in Lausanne.
Projects in the lab are often multidisciplinary and involve the development of novel methods (e.g. Feng, Nat Chem Biol 2016; Nat Chem Biol 2017; Paradis, Nat Comm 2022; Dumas, biorxiv 2023) and their application involving experimental studies (e.g. Young, PNAS 2018; Chen, Nat Chem Biol 2020; Yin, Nature 2020; Keri et al., biorxiv 2023; Jefferson, Nat Comm 2023). Projects involving external collaborations with other research groups around the world or internal collaborations between computational biologists, physicists and experimentalists in the lab are frequent. We also actively translate our findings to the clinic in collaboration with physicians (e.g. Dr. Arber, Coukos from the Ludwig Institute for Cancer Research). Specific research topics include: 1. The design of protein biosensors, mechanosensors and signaling receptors for reprogramming cell (e.g. CAR T cell) functions and enhance cell-based therapies; 2. The design of highly selective and potent protein and peptide-based therapeutics towards challenging targets such as GPCRs or ion channels; 3. The study, prediction and design of protein dynamics and allostery using AI and classic computational approaches; 4. The development of novel AI-based algorithms for modeling & design of protein structures, interactions and motions.
Dry lab candidates should have strong programming skills in python/C/C++ and expertise in the development of deep learning methods. Knowledge in structural biology, bioinformatics, computational biomolecular modeling including molecular dynamics simulations is a plus. Candidates more oriented towards the wet lab should have strong skills in molecular and cell biology including experience in protein biochemistry, mammalian cell culture, microscopy, and structural biology. Hybrid computational / experimental projects are also possible.
We have always several opportunities for semester, Master’s and Bachelor Projects in the Laboratory. Please email the Laboratory directly with your CV, grades and research interests.
AI-based approaches are revolutionizing structural biology and hold great promises for accelerating the discovery of therapeutics. However, despite tremendous advances, these methods have yet to generate de novo proteins for specific biomedical applications. To address these limitations, we are currently developing diffusion generative models to design de novo proteins with precise functions. We are seeking a masters student to work at the intersection of bioengineering and artificial intelligence. In this cutting-edge project, you will help develop and interrogate deep-learning models to design proteins with specific biomedical applications, with the ultimate goal of revolutionizing diagnostics and therapeutics.
Your primary mission will be to help curate a comprehensive protein structural training dataset and assist in refining our existing deep learning models based on this dataset to generalize de novo protein design across the vast protein structure-sequence space, ultimately working towards solving one of synthetic biology’s greatest challenges. Working closely with the model’s author, you’ll receive one-on-one mentorship, and have the opportunity to improve your skills in biophysics, bioinformatics, AI and big data.
Keywords: Protein design, deep learning, diffusion generative models, bioengineering, proteomics, personalized medicine
Requirements: Proficiency in Python and bash is essential, while experience with protein structures and the PDB, along with knowledge of PyTorch and working on supercomputing clusters is highly relevant.
Supervisor: Patrick Barth
Contact: [email protected]