Uxía Veleiro

I am pursuing a Ph.D. in Graph Neural Networks for Drug Repurposing in the In the Machine Learning in Biomedicine research group at Cima University of Navarra . II am currently a Visiting Researcher at the Department of Mathematics and Computer Science, University of Basel, in the SADA Group.

Before joining Cima, I did a Master’s in Quantitative Biotechnology at BIFI, University of Zaragoza (2021). I also hold a Degree in Physics from the University of Santiago de Compostela (2020), including a year of ERASMUS Scholarship at Heidelberg University (academic course 2018-2019).

You can check my 2-pages CV here.

More in-depth on the focus of my doctoral research

In the Machine Learning in Biomedicine research group, I specialize in drug repositioning, particularly exploring the potential of Graph Neural Networks (GNNs) as effective models for this task. My dedication lies in bridging computational techniques with biological insights to contribute innovative solutions in drug repurposing.

In this context, we have evaluated models for predicting drug-target interaction (DTI), leading to a work accepted as an oral communication at the AI4D3 Workshop of Neurips 2023. You can read it in OpenReview here. In this work, we compare the current state-of-the-art models for DTI prediction, focusing on their advantages and disadvantages, and propose guidelines for their development.

Simultaneously, I have developed GeNNius, a Graph Neural Network (GNN) model designed for predicting drug-protein interactions. This approach formulates the problem as a link prediction task. In our paper, we also studied both its prediction and generalization capabilities. This research has been published in Bioinformatics, and you can access the full article here.

If you want to know more about it or are interested in possible collaborations, let me know! 📩