Jean-Baptiste Lugagne
Post-doctoral researcher, Dunlop lab, Boston University
Developing and using interfaces between cells and machines to accelerate research and engineering in the life sciences.
I've studied signal processing engineering at Grenoble INP before discovering synthetic biology thanks to the iGEM competition in 2011. Following this I decided to re-orient myself and finished my Master's working on noise in metabolic feedback loops with Guy-Bart Stan and Diego Oyarzún at Imperial College. I then started a PhD with Pascal Hersen and Grégory Batt at Université Sorbonne Paris Cité in 2012 during which I worked on real-time control of a genetic toggle switch. After graduating, I joined the lab of Mary Dunlop at Boston University as a post-doc in 2018 and have been working on a range of projects from control of gene expression to label-free Raman imaging, image analysis, and antibiotic resistance.
My research interests are broad, but can be grouped together as quantitative approaches for the study and control of the dynamics of cellular processes. I have applied techniques from control theory, machine learning, optics, and synthetic biology to the study of antibiotic resistance or biofuel production in single bacteria. In the last few years I have been following the sustained progress in deep learning as I find it particularly well-suited to identify patterns in complex and noisy biological datasets, especially as experimental methods keep increasing in throughput. In particular deep reinforcement learning, which lies at the intersection of machine learning and control theory, is a promising avenue of research for AI in biology, as these methods can navigate complex landscapes efficiently. Currently, I'm developing interfaces bridging cells and machines to harness these advanced algorithms, while exploring the unique challenges that they face in biological contexts.
During my PhD I used real-time control to maintain a genetic toggle switch around its unstable equilibrium point. More recently, I have leveraged modern deep learning-based control algorithms to control thousands of single cells in parallel with optogenetics, and applied this method to drive and study the dynamics of antibiotics resistance. Since then I have been working on transfering methods from deep reinforcement learning to gene expression control problems, in particular to drive cell growth in real time.
Lugagne et al. 2022 Klumpe, Lugagne, et al. 2023 Lugagne, et al. 2017
In 2019 I created DeLTA, a software suite that uses deep learning to rapidly and robustly segment, track, and reconstruct lineages in microscopy time-lapse movies. Since then DeLTA has been adopted by many and others have joined me in my effort to keep improving it.
Single-cell gene expression dynamics are critical to understanding bet-hedging strategies in cell response. With my expertise in microfluidics, single-cell microscopy, and advanced data analysis I have been collaborating on projects to interpret the impact of gene expression dynamics and cell-to-cell heterogeneity on antibiotic resistance in bacteria.
I have been collaborating with the Cheng lab at Boston University to develop stimulated Raman spectro-microscopy methodologies for label-free imaging of potential biofuels such as fatty acids or terpenes in single cells. We have been able to quantify not only concentrations and the spatial organization of bioproduction, but also the chemical composition of the products for differently optimized strains.
†: co-corresponding author
*: co-first author
See my Google Scholar page for the complete list.
I co-organize the Biocontrol seminars series, a series of monthly online seminars at the intersection of control theory and biology. Feel free to reach out if you would like to speak!
For questions regarding DeLTA check our GitLab repository, in particular the issues system. See also the online documentation.
jlugagne [at] bu [dot] edu