FBK > IT > Content

Roberto Visintainer

Roberto Visintainer

Junior Researcher
FBK - MPBA
Via Sommarive 18, I-38100 Povo (Trento), Italy
Ph: +39 0461 314 650
Fax: +39 0461 314 591
Skype: robeolo
Email: visintainer AT fbk DOT eu
Short CV Research Publication

Short CV

Nov09 - present Ph.D. Student at ICT - Information and Communication Technolgy Doctoral School in Trento Italy
Jun08 - present Junior Researcher at FBK - MPBA
Mar08 M.Sc. (Telecommunication Eng.) at University of Trento (Prof. L. Bruzzone)
Mar04

B.Sc. (Telecommunication Eng.) at University of Trento (Prof. L. Bruzzone)

Research

Distances and Stability in biological Network Theory

A major issue aff ecting network inference is indeed the high variability of network topology found for data perturbations,
diff erent parameter choices and alternative methods. Network stability can thus be used to measure reliability of inferred topology, also obtaining con dence intervals for the outcomes.

  • Investigation of (spectral) distances to analyse network structure improving over classic measures based on the confusion matrix.
  • Analysis of biological timevarying networks as a function of diff erent conditions with application to synthetic and real gene expression data.
  • Integration of stability measures with statistical machine learning classifi ers, in the attempt to combine feature selection and network inference.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

omputational Biology and Bioinformatics

Supervised discrimination and feature ranking are essential steps throughout any data analysis task. The high-throughput (and beyond) data for functional genomics we are dealing with and the need for a methodology warranting honest estimate of the performances require algorithms able to cope with the p>>n issue, adapting to very unbalanced problems and robustly detecting the relevant features: all this has also to be realized within reasonable time. To such aim, we are constantly considering state-of-art classifiers and ranking methods, finding possible improvements, implementing them in our library mply and benchmarking them against more standard choices.

Current projects:

  • Analysis/implementation/extensions of classifiers in the family of Discriminant Analysis
  • Analysis/implementation/extensions of feature ranking evolutionary algorithms: Genetic Algorithms, Particle Swarm Optimization, Ant Colony Optimization
  • Use of Discrete Wavelet Transform in feature ranking

Publications

2011

[JOURNAL] G. Jurman, R. Visintainer, C. Furlanello. An introduction to spectral distances in networks. Proc. WIRN2010, 227-234, 2011. (Full text PDF)

2010

[JOURNAL] The MicroArray Quality Control (MAQC) Consortium. The MAQC-II Project: A comprehensive study of common practices for the development and validation of microarray-based predictive models. Nature Biotechnology, 28(8):827-838, 2010. Full text (HTML) [IF 29.495 (09)]

[POSTER] R. Visintainer, G. Jurman, M. Grimaldi, Introduction to Spectral Metrics in Biological Network Theory Networks Across Disciplines: Theory and Applications NIPS 10 Workshop - Vancouver/Whistler, Canada. Poster (PDF) Spotlight (PDF) Abstract (PDF)

[POSTER] M. Grimaldi, R. Visintainer, G. Jurman, RegnANN: network inference using Artificial Neural Networks Networks Across Disciplines: Theory and Applications NIPS 10 Workshop - Vancouver/Whistler, Canada. Poster (PDF) Spotlight (PDF) Abstract(PDF)

[TALK] M. Filosi, G. Guzzetta, D. Albanese, G. Jurman, S. Riccadonna, R. Visintainer, C. Furlanello L1L2 regression in oncogenomics Fourth Bioinformatics Meeting on Machine Learning for the Microarray Studies of Disease, Burg Randeck, Germany, 2010. Presentation (PDF)

[TALK] D. Albanese, G. Jurman, R. Visintainer, S. Merler, S.Riccadonna, C. Furlanello mlpy, high-performance Python package for predictive modeling Fourth Bioinformatics Meeting on Machine Learning for the Microarray Studies of Disease, Burg Randeck, Germany, 2010. Presentation (PDF)

[TALK] G. Jurman, R. Visintainer, M. Grimaldi, C. Furlanello D(*,*) Distances and Variability in (Gene) Network Inference Fourth Bioinformatics Meeting on Machine Learning for the Microarray Studies of Disease, Burg Randeck, Germany, 2010. Presentation (PDF)

[POSTER] G. Jurman, S. Riccadonna, R. Visintainer, G.Guzzetta C. Furlanello. A ranking stability indicator in bioinformatics. Cancer Bioinformatics Workshop 2010 - Cambridge, UK. Poster (PDF)

[POSTER] C.Furlanello, G. Guzzetta, M. Filosi, S. Riccadonna, R. Visintainer, G. Jurman. High-throughput Profiling for Quantitative Phenotypes. MGED13 - Boston, USA. Poster (PDF)

[TALK] G. Jurman, R. Visintainer, C. Furlanello. An introduction to spectral distances in networks. WIRN 2010 - Vietri sul Mare, Italy. Presentation (PDF)

[PREPRINT] M. Grimaldi, G. Jurman, R. Visintainer. Reverse Engineering Gene Networks with ANN: Variability in Network Inference Algorithms arXiv:1009.4824 [q-bio.MN]

[PREPRINT] G. Jurman, S. Riccadonna, R. Visintainer, C. Furlanello. Algebraic Comparison of Partial Lists in Bioinformatics. arXiv:1004.1341v1 [stat.ML]

[PREPRINT] G. Jurman, R. Visintainer, C. Furlanello. An introduction to spectral distances in networks (extended version). arXiv:1005.0103v2 [q-bio.MN]

2009

[TALK] G. Jurman, S. Riccadonna, R. Visintainer, C. Furlanello. Canberra Distance on Ranked Lists. In Proceedings of Advances in Ranking NIPS 09 Workshop (eds. S. Agrawal, C. Burges, K. Crammer):  22-27, 2009. Full text (PDF) (available here)

[POSTER] G. Jurman, S. Riccadonna, R. Visintainer, C. Furlanello. Canberra Distance on Ranked Lists. Advances in Ranking NIPS 09 Workshop - Vancouver/Whistler, Canada. Poster (PDF)

 

2008

[POSTER] S. Riccadonna, D. Albanese, R. Visintainer, S. Paoli, G. Jurman, and C. Furlanello. The MLPY/BIODCV Machine Learning Environment for Reproducible Molecular Signature. MGED11, Riva del Garda, 2008

[TALK] D. Albanese, S. Merler, G. Jurman, R. Visintainer, S. Riccadonna, S. Paoli and C. Furlanello. mlpy - Machine Learning Py - A High-Performance Python/NumPy Based Package for Machine Learning. EuroSciPy 2008, Leipzig (D), 2008

FBK © 2008-12 Fondazione Bruno Kessler