Sorry, you need Javascript on to email me.

My Research

My main research focus is the application of deep learning to biomedical data for precision medicine, with a secondary focus on interpretability and explainability.

One of the greatest innovations that deep learning brought to the field of data science is the capability to seamlessly integrate different sources of information in a unified framework that can be used to make new predictions. During my PhD project at the Max-Planck Institute for Intelligent Systems in Tübingen, I have worked to apply cutting-edge machine learning to several fields of biomedicine, including epigenomics, proteomics, graph analysis of molecular networks, and patients clinical data. This experience gave me a robust multidisciplinary background that allows me to collaborate with domain experts in medicine and biology, as well as machine learning experts. I enjoy working at the intersection of the two disciplines, where the challenges inherent to the analysis of biomedical data can be tackled with state-of-the-art models and robust statistical methodologies.

My primary research passion is the application of modeling methods, data mining and analysis to the medical field. While earning my Physics bachelor’s and master’s degrees from the Universities of Turin and Trent, I focused on the field of medical physics. My works in this field, which ranged from simulations of contrast media for radiotherapy, to the applications of nanomaterials for drug delivery, left me with a deep fascination for multidisciplinary approaches to tackle medical problems. I further explored my interest in the field of machine learning and data science at the University of Edinburgh, where I successfully completed the Artificial Intelligence MSc. In December 2019, I joined MPI-IS in Tübingen, as part of the Epi-Logos group led by Gabriele Schweikert and the Empirical Inference department under the supervision of Bernhard Schölkopf.

Additional topics in which I am interested include Bayesian models, robust statistical methodologies, and best practices for open science.