The Community for Technology Leaders
Green Image
Issue No. 03 - May-June (2012 vol. 9)
ISSN: 1545-5963
pp: 934-939
Marco Antoniotti , Università degli Studi di Milano-Bicocca, Milan
Massimiliano Borsani , Università degli Studi di Milano-Bicocca, Monza
Barbara Borroni , Università degli Studi di Brescia, Brescia
Veronica Mainini , Università degli Studi di Milano-Bicocca, Monza
Carlo Ferrarese , Ospedale San Gerardo, Monza
Clizia Chinello , Università degli Studi di Milano-Bicocca, Monza
Fulvio Magni , Università degli Studi di Milano-Bicocca, Monza
Erica Gianazza , Università degli Studi di Milano-Bicocca, Monza
Gloria Galimberti , Ospedale San Gerardo, Monza
Carmen Galbusera , Università degli Studi di Milano-Bicocca, Monza
Giancarlo Mauri , Università degli Studi di Milano-Bicocca, Milan
Italo Zoppis , Università degli Studi di Milano-Bicocca, Milan
Sandro Sorbi , Università degli Studi di Firenze, Florence
ABSTRACT
"Signal” alignments play critical roles in many clinical setting. This is the case of mass spectrometry (MS) data, an important component of many types of proteomic analysis. A central problem occurs when one needs to integrate (MS) data produced by different sources, e.g., different equipment and/or laboratories. In these cases, some form of "data integration” or "data fusion” may be necessary in order to discard some source-specific aspects and improve the ability to perform a classification task such as inferring the "disease classes” of patients. The need for new high-performance data alignments methods is therefore particularly important in these contexts. In this paper, we propose an approach based both on an information theory perspective, generally used in a feature construction problem, and the application of a mathematical programming task (i.e., the weighted bipartite matching problem). We present the results of a competitive analysis of our method against other approaches. The analysis was conducted on data from plasma/ethylenediaminetetraacetic acid of "control” and Alzheimer patients collected from three different hospitals. The results point to a significant performance advantage of our method with respect to the competing ones tested.
INDEX TERMS
Optimization, information theory, medicine, medical informatics, proteomics, data integration, graph algorithms.
CITATION
Marco Antoniotti, Massimiliano Borsani, Barbara Borroni, Veronica Mainini, Carlo Ferrarese, Clizia Chinello, Fulvio Magni, Erica Gianazza, Gloria Galimberti, Carmen Galbusera, Giancarlo Mauri, Italo Zoppis, Sandro Sorbi, "Mutual Information Optimization for Mass Spectra Data Alignment", IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 9, no. , pp. 934-939, May-June 2012, doi:10.1109/TCBB.2011.80
191 ms
(Ver 3.1 (10032016))