Research Article

Multiple approaches to data-mining of proteomic data based on statistical and pattern classification methods

  1. Jacob W. Tatay1,
  2. Xin Feng2,
  3. Nancy Sobczak3,*,
  4. Hao Jiang2,
  5. Chin-Fu Chen3,
  6. Roumyana Kirova2,
  7. Craig Struble2,
  8. Nan Jiang Wang3,
  9. Peter J. Tonellato3

Article first published online: 9 SEP 2003

DOI: 10.1002/pmic.200300512

Issue

PROTEOMICS

PROTEOMICS

Special Issue: Mining MALDI-TOF Data

Volume 3, Issue 9, pages 1704–1709, September 2003

Additional Information

How to Cite

Tatay, J. W., Feng, X., Sobczak, N., Jiang, H., Chen, C.-F., Kirova, R., Struble, C., Wang, N. J. and Tonellato, P. J. (2003), Multiple approaches to data-mining of proteomic data based on statistical and pattern classification methods. PROTEOMICS, 3: 1704–1709. doi: 10.1002/pmic.200300512

Author Information

  1. 1

    University of Wisconsin Parkside, Kenosha, WI, USA

  2. 2

    Marquette University, Milwaukee, WI, USA

  3. 3

    Bioinformatics Research Center, Medical College of Wisconsin, Wauwatosa, WI, USA

*Bioinformatics Research Center, Medical College of Wisconsin, 8701 W. Watertown Plank Road, Wauwatosa, WI 53226, USA Fax: +1-414-456-6593

Publication History

  1. Issue published online: 9 SEP 2003
  2. Article first published online: 9 SEP 2003
  3. Manuscript Received: 16 OCT 2002

SEARCH

SEARCH BY CITATION

ARTICLE TOOLS

Get PDF (118K)

Keywords:

  • Artificial neural networks;
  • Fuzzy logic;
  • Principle component analysis;
  • Support vector machines

Abstract

The data-mining challenge presented is composed of two fundamental problems. Problem one is the separation of forty-one subjects into two classifications based on the data produced by the mass spectrometry of protein samples from each subject. Problem two is to find the specific differences between protein expression data of two sets of subjects. In each problem, one group of subjects has a disease, while the other group is nondiseased. Each problem was approached with the intent to introduce a new and potentially useful tool to analyze protein expression from mass spectrometry data. A variety of methodologies, both conventional and nonconventional were used in the analysis of these problems. The results presented show both overlap and discrepancies. What is important is the breadth of the techniques and the future direction this analysis will create.

Get PDF (118K)