SVD Based Feature Selection and Sample Classification of Proteomic Data

  • Authors:

  • Annarita D'Addabbo;Massimo Papale;Salvatore Paolo;Simona Magaldi;Roberto Colella;Valentina D'Onofrio;Annamaria Palma;Elena Ranieri;Loreto Gesualdo;Nicola Ancona

  • Affiliations:

  • Istituto di Studi sui Sistemi Intelligenti per l'Automazione, CNR, Bari, Italy 70126;Molecular Medicine Center, Sect. of Nephrology, Dept. of Biomedical Sciences and Bioagromed, Faculty of Medicine, University of Foggia,;Division of Nephrology and Dialysis, Hospital "Dimiccoli", ASL BAT, Barletta,;Molecular Medicine Center, Sect. of Nephrology, Dept. of Biomedical Sciences and Bioagromed, Faculty of Medicine, University of Foggia,;Istituto di Studi sui Sistemi Intelligenti per l'Automazione, CNR, Bari, Italy 70126;Dept. of Surgical Sciences , Faculty of Medicine, University of Foggia, Italy;Molecular Medicine Center, Sect. of Nephrology, Dept. of Biomedical Sciences and Bioagromed, Faculty of Medicine, University of Foggia,;Dept. of Biomedical Sciences, Sect. of Clinical Pathology, Faculty of Medicine, University of Foggia, Italy;Molecular Medicine Center, Sect. of Nephrology, Dept. of Biomedical Sciences and Bioagromed, Faculty of Medicine, University of Foggia,;Istituto di Studi sui Sistemi Intelligenti per l'Automazione, CNR, Bari, Italy 70126

  • Venue:
  • KES '08 Proceedings of the 12th international conference on Knowledge-Based Intelligent Information and Engineering Systems, Part III
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

Feature selection becomes a central task when 'signature' profiles specific to a pathological status have to be extracted from high dimensional gene expression or proteomic data. In the present paper, we propose a feature selection method based on Singular Value Decomposition (SVD) and apply it to SELDI-TOF/MS proteomic data from a cohort of Type 2 Diabetics affected by Glomerulosclerosis and Membranous Nephropathy. We have selected a profile composed of 24 proteins that seems to be an effective signature for the pathology at hand, allowing to efficiently discriminate between the considered subtype of diabetes.