MSc Thesis: AI against SARS-CoV-2
Viruses interact with cellular proteins to replicate and spread. We aim to gain functional insights into the mode of action of cellular proteins, enabling us to better understand how different viruses like SARS-CoV-2 cause disease.
We are using genetic ablation of cellular proteins and viruses that express a green fluorescent protein (GFP), allowing us to continuously follow the infection by live-cell fluorescent microscopy in a time-resolved manner. The resulting, very rich dataset (consisting of ~60.000 images per virus tested), will be used to search for patterns allowing to classify the function of the perturbed gene in relation to the infecting virus. For instance, the GFP intensity/area, the localization, and spatial proximity of a GFP signal over time contains information on virus replication and spread. This work aims to establish and apply unbiased machine learning algorithms to understand these functional links between the cell and the viruses and to identify the proteins and perturbations that contribute to virus growth and virus restriction. This algorithm will further be used to study the influence of inflammatory events and treatment with drug libraries.
We are looking for a highly motivated Master’s student who will establish a comprehensive bioinformatics pipeline to extract information from these images. You will be working together with computational scientists at the AI in Medicine Lab and wet-lab scientists (Prof. Andreas Pichlmair group, Virology). Importantly, your results will be functionally tested iteratively and used to further improve the predictive power of your model.
- Advanced programming skills in Python
- Strong background in deep learning and image analysis
- Strong interest in working in an interdisciplinary team
What we offer:
- An exciting research project with many possibilities to bring in your own ideas.
- Close supervision and access to state-of-the-art computer hardware.
- The chance to work in a team of experts in image processing, deep learning, biology and medicine.