Computational Immunobiology


Infectious diseases accounted for almost six million global deaths in 2019. Despite extensive public health interventions worldwide and expanded genomic surveillance, infectious diseases remain a major public health challenge. At the moment, there is a pressing need to develop point-of-care diagnostic tools that can be deployed in areas where the disease is more prevalent and where healthcare is scarce. These tools will aid with the early detection of the pathogen, monitoring disease progression, and evaluate treatment effectiveness on site. 

The latest developments in the field of artificial intelligence, such as graph neural networks and language models, have provided new strategies to extract knowledge and identify novel trends from large amounts of disparate datasets. These methods are perfectly suited to mine large collections of clinical (i.e: electronic health records), imaging (i.e: CT-scans, MRIs, X-Rays) and multiomic (i.e: RNA-Seq, scRNA-Seq, scCITE-Seq, scATAC-Seq) data, and help identifying biomarkers with the potential to be translated into novel clinical diagnostic tools.

The “Computational Infection Biology” group specialises in the study of the biological circuits involved in cellular communication during infection. We use and develop state-of-the-art machine learning methods and apply them to spatially-resolved single cell multiomics data generated from both pathogen and host cells. This strategy will allow us to understand how host - pathogen interactions shape the inflammatory response to clear infection and repair the damaged tissue, allowing for the identification of novel biomarkers that can be translated to the clinic to predict disease progression and to develop novel point-of-care diagnostic tools.