FBK-irst (The Fondazione Bruno Kessler)

Number of employees: 350

The Fondazione Bruno Kessler (FBK) is a non-profit body with a public interest mission having private-law status and inheriting the history of Istituto Trentino di Cultura. FBK-irst is the FBK Centre for Scientific and Technological Research. Its applied and basic research activities aim at resolving real-world problems and transferring technology to companies and public entities, also by founding 11 spin-off companies. The research staff at FBK-irst consists of about 80 people on a permanent basis, and about 150 people on soft money. Half of FBK-irst direct costs are covered by industrial contracts and European and National contracts. So far over 70 European contracts have been carried on by FBK-irst in many successful Third, Fourth, Fifth and Sixth Framework projects (since 2000: 39 projects, 8 as coordinator).

Statistical machine learning, bioinformatics, geoinformatics, and Grid computing are the main research aims of the Predictive Models for Environmental and Biological Data (MPBA) Research Unit, acting in this consortium as the coordinating node and method integrator. MPBA has about 11 years of research experience in interdisciplinary research and in the development of novel open source software for data collection, management and distribution of the resulting models. Several MPBA systems are now data management infrastructures for public agencies. Since 2002, MPBA has started a research initiative in functional genomics, developing mathematical methods and a complete machine learning platform for predictive profiling on high-throughput data, in collaborations with national and international centres of excellence in molecular oncology.
The unit is coordinated by senior researcher Cesare Furlanello. His main research interests are in the applications of machine learning methods to medical and environmental data. He designed and managed many studies and projects involving interdisciplinary collaboration with life science researchers. He has contributed to the development of predictive classification models and gene selection procedures for molecular diagnostics. He is an investigator in two projects of AIRC, the national charity for cancer research, including the development of the Italian integrated platform for bioinformatics, with the IFOM-FIRC institute. In 2006, he was scientific organizer of the workshop “Biobanks for functional genomics: integrating data, integrating models”.

Other scientists in this project: Giuseppe Jurman Post-doc fellow at FBK-IRST, after a two-year staff position at CMA Australian Natl Univ. in Canberra. He is an expert in the study of various mathematical aspects of machine learning and bioinformatics, with focus on predictive classification on microarray and proteomics data. Stefano Merler is FBK-irst researcher, previously at CEA-Trento. He has contributed to research on kernel-based machine learning, model combination, cost-sensitive classification, feature selection with applications to molecular profiling, gene ranking with application to epidemiology and bioinformatics. Samantha Riccadonna. After 2 years as research fellow in medical informatics, she is now a PhD student in ICT with a thesis in integrative functional genomics. Silvano Paoli joined MPBA for the development of Grid algorithmic solutions in collaboration with the international EGEE grid project. He is now a PhD student in ICT. Davide Albanese is a programmer, actively developing software (C, Python, R) for machine learning and bioinformatics since 2004.

Relevant Publications

C. Furlanello, S. Merler, and G. Jurman. Combining feature selection and DTW for time-varying functional genomics. IEEE Transactions on Nanobioscience, in press, 2007.

C. Furlanello, M. Serafini, S. Merler, and G. Jurman. Semi-supervised learning for molecular profiling. IEEE Transactions on Computational Biology and Bioinformatics, 2(2):110-118, 2005. 2005.

C. Furlanello, M. Serafini, S. Merler, and G. Jurman. An accelerated procedure for recursive feature ranking on microarray data. Neural Networks, volume 16(5-6) pp. 641-648, 2003.

Barla, B. Irler, S. Merler, G. Jurman, S. Paoli, and C. Furlanello. Proteome profiling without selection bias. In Proc. of IEEE-CMBS 2006, 2006.

S.Paoli, G. Jurman, D. Albanese, S. Merler and C. Furlanello Integrating gene expression profiling and clinical data Int. J. of Approx. Reasoning, in press 2007


Copyright © 2011 HiPerDART. All rights reserved.