Deep-learning approaches integrated into the paradigms of systems biology to gain insights into autophagy role in backgrounds

The goal of this project is to contribute to the contextual understanding of autophagy in different pathological backgrounds using systems biology based approaches. A system view of the relevant physiological function is essential to uncover the molecular mechanisms underlying the function of autophagy in different pathological backgrounds and to identify any common patterns and crosstalk. The inescapable fact that biological pathways are highly interconnected represents one of the major motivations for adopting a system-level approach. Moreover, systems biology approaches provide an optimal framework for integrating and synthesizing diverse knowledge into a consistent and unified view. Analysis of data in the context of biological networks has the potential to reveal unexpected or under-appreciated biological connections.

The ESR will exploit and extend the capabilities of systems biology approaches developed by AX to contextualize findings of model organisms in a human background and optimize AX tools for the purpose. The molecular data on autophagy in pathological backgrounds, existing or newly generated within DRIVE by the different partners (initially Vici syndrome and ciliopathies) will be analysed in the context of human functional network using the updated tools. Different models for each of the pathological backgrounds will be generated and compared. In particular the PhD student will design, develop and validate new innovations in network data analysis and extend its application for autophagy research. This will include i) the evaluation of different deep learning approaches, ii) the acceleration of current data mining workflows using distributed GPU computation and iii) the evaluation of the incorporation of orthology-based network alignment to improve the systems-level knowledge translation between model organisms and human.