Research Article

Ovarian cancer detection by logical analysis of proteomic data

  1. Gabriela Alexe1,
  2. Sorin Alexe1,
  3. Lance A. Liotta2,
  4. Emanuel Petricoin3,
  5. Michael Reiss4,
  6. Peter L. Hammer1,*

Article first published online: 22 AUG 2003

DOI: 10.1002/pmic.200300574

Issue

PROTEOMICS

PROTEOMICS

Volume 4, Issue 3, pages 766–783, March 2004

Additional Information

How to Cite

Alexe, G., Alexe, S., Liotta, L. A., Petricoin, E., Reiss, M. and Hammer, P. L. (2004), Ovarian cancer detection by logical analysis of proteomic data. PROTEOMICS, 4: 766–783. doi: 10.1002/pmic.200300574

Author Information

  1. 1

    RUTCOR, Rutgers Center for Operations Research, Rutgers University, Piscataway, NJ, USA

  2. 2

    Laboratory of Pathology, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA

  3. 3

    Food and Drug Administration/National Institutes of Health, Clinical Proteomics Program, Department of Therapeutic Proteins/Center for Biologics Evaluation and Research, Food and Drug Administration, Bethesda, MD, USA

  4. 4

    University of Medicine and Dentistry of New Jersey, and Robert Wood Johnson Medical School, Department of Medicine, The Cancer Institute of New Jersey, New Brunswick, NJ, USA

*RUTCOR, Rutgers Center for Operations Research, Rutgers University, 640 Bartholomew Road, Piscataway, NJ 08854, USA Fax: +1-732-445-5472

Publication History

  1. Issue published online: 19 FEB 2004
  2. Article first published online: 22 AUG 2003
  3. Manuscript Received: 1 APR 2003

SEARCH

SEARCH BY CITATION

ARTICLE TOOLS

Get PDF (212K)

Keywords:

  • Logical analysis of data;
  • Ovarian cancer

Abstract

A new type of efficient and accurate proteomic ovarian cancer diagnosis systems is proposed. The system is developed using the combinatorics and optimization-based methodology of logical analysis of data (LAD) to the Ovarian Dataset 8-7-02 (http://clinicalproteomics.steem.com), which updates the one used by Petricoin et al. in The Lancet 2002, 359, 572–577. This mass spectroscopy-generated dataset contains expression profiles of 15 154 peptides defined by their mass/charge ratios (m/z) in serum of 162 ovarian cancer and 91 control cases. Several fully reproducible models using only 7–9 of the 15 154 peptides were constructed, and shown in multiple cross-validation tests (k-folding and leave-one-out) to provide sensitivities and specificities of up to 100%. A special diagnostic system for stage I ovarian cancer patients is shown to have similarly high accuracy. Other results: (i) expressions of peptides with relatively low m/z values in the dataset are shown to be better at distinguishing ovarian cancer cases from controls than those with higher m/z values; (ii) two large groups of patients with a high degree of similarities among their formal (mathematical) profiles are detected; (iii) several peptides with a blocking or promoting effect on ovarian cancer are identified.

Get PDF (212K)