1. PhD in AI Technology for plant-microbiome interactions.
   In this project you will develop methodology to understand the interactions between plant root systems and their associated microbiome. The project aims to investigate the fundamental principles underlying complex microbial community assembly on plant roots and therefore provide knowledge that can be used to improve growth and stress resilience of our crops. Your work will involve analysing complex synthetic communities with diverse microorganisms sourced from different plants. These communities exhibit various functional properties, influencing plant phenotypic outcomes. You will evaluate the contribution of specific functional properties, such as catabolic pathways, and community network properties like microbial cross-feeding and competition to the establishment of the root-associated microbiome and ultimately plant productivity. The objective is to develop methodology to understand and predict community assembly outcomes and plant productivity in both simulated and real-world environments. You will work closely together with experimental plant groups at the Biology department.  Your predictions and findings will inspire subsequent experiments, creating a feedback loop that enriches the project's outcomes.
2. PhD in Explainable AI for Multi-Modal Life Science Data.
   In this project, you will develop explainable AI methodologies for data in the Life Sciences. This project will focus on building generalizable and inherently interpretable models, generating explanations alongside predictions. Deep representation learning strategies will be developed to find the best and most interpretable semantic space combining imaging and tabular/multi-omics information. The methodology will be applied to medical data (images, and clinical information) and/or plants.
3. PhD in explainable AI in a multi-task setting.
   You will develop AI methodology to derive explanations for multi-task prediction models. In other words, there will be multi-modal learning objectives. You will further develop a multi-task deep learning model that can handle this type of data, and develop methodology that can explain predictions through related tasks. The applications are in the biomedical domain in neurodegenerative disease and/or in an oncology setting, using protein sequence, function and structure and/or multi-omics data.

You will become part of the vibrant interdisciplinary research group “AI Technology for Life”, a new interdepartmental research group between the Department of Information and Computing Sciences and the Department of Biology. The group is created as a result of the great importance attached by the Faculty of Science to stimulate research and teaching between departments. Together with the members of the group you work at the interface between the Life Sciences and AI.