RESEARCH GROUPS
Alessandro Barberis
BSc, MSc, PhD
Senior Postdoctoral Researcher
Machine Learning, Cancer Biomarkers
RESEARCH SUMMARY
Alessandro's main research activity is related to the development and application of machine learning (ML) techniques to clinical cohorts. At the NDS, he studies the contribution of insulin-like growth factors (IGFs) to prostate cancer biology.
Alessandro's current projects include:
- Study the contribution of insulin-like growth factors (IGFs) to prostate cancer biology
- Derivation of multi-omic classifiers in different cancer types
- Identification of circulating biomarkers to improve radiotherapy effectiveness in glioblastoma
- Development of novel robust and reproducible computational methodologies
BIOGRAPHY
Alessandro graduated from University of Pavia (Italy) in Computer Science Engineering with a Thesis focusing on the identification of an order parameter in Monte Carlo simulations of dipolar systems on hexagonal lattices.
After completing his Master’s Degree, Alessandro started a PhD in Electronics, Computer Science and Electrical Engineering within the Custom Computing and Programmable Systems group at the same University. During his PhD, he specialised in High Performance Computing and Data Processing. In particular, he focused on Graphics Processing Units (GPUs) and Field Programmable Gate Arrays (FPGAs) technologies to develop real time solutions for image analysis. His main project was in collaboration with Professor Antonio Plaza, Head of the Hyperspectral Computing Laboratory, University of Extremadura.
Alessandro joined the Department of Oncology in 2014, working as a postdoc in the Computational Biology and Integrative Genomics group. He is now a senior postdoc in the IGF group at the Nuffield Department of Surgical Sciences.
Alessandro is a Lecturer for the MSc in Precision Cancer Medicine.
Recent publications
-
Identification and validation of a machine learning model of complete response to radiation in rectal cancer reveals immune infiltrate and TGFβ as key predictors.
Journal article
Domingo E. et al, (2024), EBioMedicine, 106
-
Robustness and reproducibility for AI learning in biomedical sciences: RENOIR.
Journal article
Barberis A. et al, (2024), Sci Rep, 14