The LAIF Research Group is a junior research group at the Department of Life Science Informatics and Data Science (Uni Bonn and Lamarr Institute).Β
The group's research directions are in the field of artificial intelligence applied to the life sciences. The core research area is graph learning for bio- and chemoinformatics, with a special focus on generative models and explainable artificial intelligence.Β
Andrea Mastropietro
Andrea is interested in graph learning and explainable AI in the life sciences π€π§¬. He is a Junior Research Group Leader at Uni Bonn. When he is not in Bonn, he is probably in Japan at NAIST πΎ, where he is an Assistant Professor, or in Italy, drinking espresso β and eating pizza π.
Maria Julia Teja Urrutia
Julia is a Ph.D. student working on graph-based models, such as graph transformers, for targeted molecular generation βοΈ. She is particularly interested in how we can use these models to design molecules with specific properties in mind, while also trying to understand what they are actually learning along the way π‘. Outside the lab, she's usually trying to learn something else. She loves learning languages and picking up new skills (her latest adventure is ice skating βΈοΈ), she also enjoys knitting, going to the movies ποΈ, and getting lost in a good puzzle or word game (especially crosswords and NYT Connections) π§©.
Luca Song
Francesco Madeddu (Sapienza University of Rome)
Francesco is a Ph.D. student working on graph learning, with a particular interest in applying it to real-world problems in biology π§¬. Outside the lab, youβll usually find him hiking ποΈ, biking π΅, or baking and cooking something new π₯§π.
Madeddu, F., Testa, L., De Carlo, G., Pieroni, M., Mastropietro, A., Petti, M., Anagnostopoulos, A., Tieri, P., & Barbarossa, S. VitaGraph: building a knowledge graph for biologically relevant learning tasks. Scientific Data 13, 1045 (2026).
Teja Urrutia, M.J., Mastropietro, A. & Bajorath, J. Explainable artificial intelligence reveals divergent learning in pharmacophore-based hierarchical pooling graph neural networks. Scientific Reports 16, 19794, 2026.
Mastropietro, A., & Bajorath J. Explaining a molecular diffusion model, Cell Reports Physical Science, Cell Reports Physical Science 7, 103270 (2026).
Andrea Mastropietro, Georgios Markopoulos, Evangelos Evangelou, Aris Anagnostopoulos, A novel explainable deep-learning approach for network analysis of epistatic interactions, NAR Genomics and Bioinformatics, Volume 8, Issue 1, March 2026, lqag004, https://doi.org/10.1093/nargab/lqag004.Β
π‘ Stay tuned for futher updates from our group!