My current interest is on sparsity-enforcing regularization methods, exploiting different penalties to achieve sparse models depending only on few and relevant variables, with the main goal of modelling complex biological systems. Such methods should possibly allow for the integration of different data types and be flexible enough to incorporate all the available biological prior knowledge.
machine learning, regularization methods, high-dimensional data, biomedical data analysis, computational biology
I graduated in Physics in 2001 at the University of Genoa, with a thesis on Data Representation in Machine Learning.
During my PhD years I focused on supervised machine learning methods, especially Support Vector Machines for binary and one-class classification and kernel methods tailored on the specific representation of the data at hand. An internship on medical imaging in the Integrated Data Systems Department headed by Dr. Comaniciu, at Siemens Corporate Research (Princeton, NJ, USA) led me to develop an interest in evidence-based medicine. After my PhD graduation (2005, Computer Science, University of Genoa) I became a post-doc in MPBA (Dr. Furlanello's Lab) at ITC-IRST, now Fondazione Bruno Kessler (Trento, Italy), where I started my research in computational biology, acquiring the expertise needed for a careful design of selection-bias aware data analysis frameworks [G. Jurman et al. Bioinformatics, 2008] applied to -omics data (DNA microarray, Mass spectrometry proteomics data) [M. Cannataro et al. IEEE Trans. on Nanobiosciences, 2007; Barla et al Briefings in Bioinformatics, 2008].
With the FP6 Integrated Project Health-e-Child IST-2004-02774919 I joined (2007) the Statistical Learning and Image Processing group, starting a research line in computational biology. Since January 2012, I am Assistant Professor at the Department of Computer Science, Bioengineering, Robotics and Systems Engineering at the University of Genoa. I authored more than 40 peer-reviewed papers on international journals and conference proceedings.
My research is placed at the intersection of statistical learning and computational biology. In particular, I am interested in developing regularization methods that guarantee robust and unbiased results and possibly exploit the available knowledge on the given problem.