Background:

The global rise of infectious diseases underscores the need for universal and systemic infection models. This project aims to develop an alternative to traditional animal models by adapting pathogen-permissive human organoid cultures within an organ-on-a-chip system. Imaging techniques will capture viral replication data, which will be quantified through in silico analysis and modelled to deduce causal relationships.

Human lung organoids, derived from adult stem cells, were infected with recombinant vaccinia viruses (VACV-GFP). The GFP fluorescence signal from actively replicating viruses will enable the mathematical modelling of infection kinetics in live 3D cultures. The lung was chosen as the primary organ due to its role as the initial entry point for many human pathogens and its involvement in disease progression.

Aim/s:

This project aims to develop an unbiased, automated data analysis system that enables predictions about relevant aspects of viral replication kinetics. These insights will help design optimized experimental setups, reducing lab time and conserve resources.

AI methods:

Experimentally obtained 4D imaging data of infected organoids will be automatically quantified and converted into numerical data for statistical analysis and mathematical modelling. Deep learning techniques will identify and distinguish infected from non-infected cells.

Keywords:

Infectious diseases detection, organoids, 4D Imaging, deep learning