My research focuses on understanding high-throughput biological data using computational methods, including machine learning, statistical modeling, and systems biology. I aim both to support medical and biological teams as a computational resource, and to develop new tools that reveal disease-driven intracellular changes. A particular interest of mine is projecting insights from well-characterized healthy systems, where data are typically abundant, onto human diseases where material is often limited.
My research path began in 2014, when I was introduced to mechanistic modeling and systems biology as a student visiting IMT. After completing my MSc, this interest led me to pursue a PhD in bioinformatics at the Department of Physics, Chemistry and Biology, where I focused on predicting high-confidence gene regulatory networks from RNA-seq data. Following my thesis defense, I continued as a postdoctoral researcher at the University of Skövde in collaboration with pharmaceutical companies. There, I also initiated my first project as a senior research leader, where I led the development of variational autoencoders, which are artificial neural networks designed to extract disease-specific groups of interconnected genes.
Now back at IMT, my work emphasizes continued method development and the application of computational approaches to real-world biomedical data. My long-term goal is to establish a hub that supports the interpretation of diverse high-throughput datasets across the life sciences.
My research path began in 2014, when I was introduced to mechanistic modeling and systems biology as a student visiting IMT. After completing my MSc, this interest led me to pursue a PhD in bioinformatics at the Department of Physics, Chemistry and Biology, where I focused on predicting high-confidence gene regulatory networks from RNA-seq data. Following my thesis defense, I continued as a postdoctoral researcher at the University of Skövde in collaboration with pharmaceutical companies. There, I also initiated my first project as a senior research leader, where I led the development of variational autoencoders, which are artificial neural networks designed to extract disease-specific groups of interconnected genes.
Now back at IMT, my work emphasizes continued method development and the application of computational approaches to real-world biomedical data. My long-term goal is to establish a hub that supports the interpretation of diverse high-throughput datasets across the life sciences.
