Uxía Veleiro
Currently, I am a postdoctoral researcher at MBZUAI in the Integrative Computational Network Biology Lab, working on multi-omics data integration and network science for precision medicine.
Previously, I completed my Ph.D. within the Machine Learning in Biomedicine research group at CIMA University of Navarra, developing computational methods for drug repurposing.
Beyond research, I’m interested in how new technologies move from scientific discovery to real-world adoption, and the decisions that shape that process.
Feel free to reach out if you’d like to connect or discuss potential collaborations. 📩
my doctoral research
During my Ph.D., I focused on applying AI to drug discovery, particularly on predicting interactions between drugs and their biological targets. Understanding these interactions is an important step in identifying potential new uses for existing drugs.
My research explored how Graph Neural Networks (GNNs) can address this challenge. In collaboration with other researchers, we evaluated state-of-the-art prediction models, identified their strengths and limitations, and proposed guidelines for future developments. This work was published in Nature Machine Intelligence (2025) and presented at the AI4D3 Workshop at NeurIPS 2023. I also led the development of GeNNius, a GNN model that predicts drug–target interactions several orders of magnitude faster than existing approaches, published in Bioinformatics (2024).
During these years, I had the opportunity to travel to international conferences, meet inspiring people from different backgrounds, and exchange ideas that broadened my perspective beyond my own research.
news
| Jun 04, 2026 | I recently joined Pržulj Lab at MBZUAI! |
|---|---|
| Apr 01, 2026 | I defended my thesis! 💐 |
| Sep 02, 2025 | Our work is going to be presented at JBI 2025 in Madrid. |
selected publications
- Towards a more inductive world for drug repurposing approachesNature Machine Intelligence, 2025
- GeNNius: an ultrafast drug–target interaction inference method based on graph neural networksBioinformatics, Dec 2023