Faculty of Science, Technology and Medicine
Faculty of Law, Economics and Finance
Faculty of Humanities, Education and Social Sciences
Interdisciplinary Centre for Security, Reliability and Trust
Luxembourg Centre for Systems Biomedicine
Luxembourg Centre for Contemporary and Digital History
Luxembourg Centre for European Law
Luxembourg Centre for Socio-Environmental Systems
This is a hybrid event. Join in person at the LCSB, or tune in via Webex here.
Knowledge Graphs for Explainable AI in Biomedical Research
Artificial intelligence has become increasingly prevalent in biomedical and clinical applications, yet concerns about bias, lack of explainability, and trustworthiness continue to limit its adoption in practice. This lecture explores how knowledge graphs serve as a powerful framework for developing explainable and trustworthy AI methods in life sciences. The presentation will demonstrate how integrating structured biological knowledge with machine learning approaches can enhance both the interpretability and reliability of AI-driven discoveries. Through examples spanning protein-protein interaction prediction, gene-disease association discovery, and drug repurposing, the talk will illustrate how knowledge graphs enable researchers to trace the reasoning behind AI predictions and assess the validity of computational findings. The presentation will also address current challenges in building and maintaining biomedical knowledge graphs, including ontology alignment, semantic similarity measurement, and the integration of multi-modal data sources. Finally, the lecture will discuss future directions for knowledge science in supporting responsible AI development for biomedical applications.
About the speaker
Cátia Pesquita is an Associate Professor in Computer Science at the Faculty of Sciences of the University of Lisbon and Vice-Director of LASIGE, where she leads the Health and Biomedical Informatics Research Line. She has a multidisciplinary background in Biology and Computer Science, conducting research at the intersection of Artificial Intelligence and Data Science with a particular focus on AI for Science. Her work centers on integrating knowledge graphs with machine learning and advancing explainable and trustworthy AI methods for applications in the life and health sciences. She has made internationally recognized contributions to ontology-based semantic similarity and ontology alignment.
The Causal Analysis of Biomedical Data Lecture Series is supported by the Luxembourg National Research Fund (FNR) RESCOM Program.
