Simone received his PhD from the Hong Kong University of Science and Technology in 2012. Before joining the University of Michigan, he has worked for the University of Pavia (Italy) and Kyoto University (Japan). Simone designes prediction models for medicine and molecular biology with machine learning. He is particularly interested in data integration, i.e. in developing models harvesting heterogeneous data from genomics, proteomics, medical literature, and ontologies. He has experience with supervised, unsupervised, semi-supervised, ensemble, and deep learning; SVMs, random forest, Bayesian networks, matrix factorization, and genetic algorithms. The application range of his models is broad, spanning from protein affinity prediction, to simulation of clinical trajectories in diabetic patients, to single-cell RNA-seq data analysis. He mainly works with R, Matlab/Octave, and Perl.
His personal website can be accessed through this link.