Workshop Schedule

09:00 - 09:20          Opening : Prof Dr. Michel Dumontier  

09:30- 10:25 Keynote Speech 

Catia Pesquita 

Ciências, Universidade de Lisboa, Group Leader at LiSeDa Lab

Vice-Director, LASIGE Computer Science and Engineering Research Centre 

Knowledge Graphs for Explainable Scientific Discovery 

Artificial intelligence is increasingly integrated into scientific discovery, but two key challenges remain: the integration of domain knowledge into models and the generation of explainable outputs that are scientifically relevant.

This talk explores the role of knowledge graphs in addressing these challenges through the lens of biomedical research with a particular focus on protein-protein interaction prediction and drug repurposing.  It highlights the limitations of current knowledge graph embedding techniques, which, although able to integrate domain knowledge into models, often trade explainability for predictive performance, and examines recent advances in explainable approaches for semantic similarity, embeddings, and path-based reasoning.

It concludes with a vision of the future of scientific research, where artificial intelligence systems are able to generate scientifically meaningful outcomes grounded in domain knowledge, verifiable against existing evidence, and capable of advancing understanding.

Bio

Catia Pesquita is a Professor of Computer Science at the Faculty of Sciences of the University of Lisbon and a Senior Researcher at LASIGE where she leads the Research Line of Excellence in Biomedical and Health Informatics. She has a multidisciplinary background in Biology and Computer Science, and develops her research at the intersection between Semantic Web and Data Mining, focusing on applications in the life and health sciences. She is also involved in activities to promote computer science career paths to young women. 

10:30 – 11:00 Coffee Break

11:00 - 12:30

Session 1:  Artificial Intelligence and Large Language Models for Healthcare and Life Sciences 

• AI based chatbots vs. traditional search: A systematic comparison of response quality for dementia management information

Sourav Maiti, Qurratal Ain Fatimah, Syeda Mah E Fatima, Ali Hasnain

• Constructing CCEE an LLM evaluation dataset for Complex Context-aware Event Extraction for gene regulatory networks

Frederik Labonté and Lucie Flek

• Using clinical guidelines, domain ontology, and LLMs for Personalized Leukemia Treatment Recommendations

Xingru Xu, Michel Dumontier and Chang Sun

12:30 – 14:00 Lunch Break

14:00 - 14:30 Session 2: Healthcare and Life Sciences Data Similarity

• LISE: a Logic-based Interactive Similarity Explainer

Simona Colucci, Francesco Maria Donini and Verdiana Schena

14:30 - 15:00 Session 3: Text, Data and Ontologies in Healthcare and Life Sciences 

• Can Language Models Align Biomedical Ontologies?: Evaluating Retrieval-Augmented Prompt Strategies in Bio-ML.

Lucas Ferraz, Pedro Giesteira Cotovio and Catia Pesquita

15:00 – 15:30 Discussion and Closing  Prof Dr. Michel Dumontier  

15:40 – 16:00 Coffee Break