I study microbial adaptation using graph theory and AI—from developing algorithms to identifying antibiotic targets.
As a researcher, I am interested in understanding how the microbial world has adapted to be found (nearly) everywhere. To achieve this, I study microbial evolutionary dynamics and environmental adaptation using computational methods based on graph theory and artificial intelligence. My previous research focused on new methodological development for pangenomic analyses and comparisons, which led to the creation of graph-based algorithms and a bioinformatic software: PANORAMA.
My current research aims to identify new potential antibiotic targets as multi-resistant species emerge as a worldwide public health issue. The challenge lies in identifying essential pathogen proteins during infection as quantifying them is not possible with current methods. To bypass this limitation, we are developing AI models to predict protein levels in infected tissues based on single-cell RNA sequences from in vivo bacterial pathogen data. This approach will unlock access to new potential antibiotic targets that remain inaccessible through existing methods.
In my free time, I enjoy walking in nature, and when the weather does not cooperate, I find peaceful refuge in video games or reading fantasy books. Fair warning: I will keep talking until someone physically restrains me or I pass out from exhaustion, whichever comes first.