Detection of cancer-specific markers amid massive mass spectral data
- *Department of Applied Mathematics and Statistics, and ¶Long Island Cancer Center, State University of New York, Stony Brook, NY 11794; and ‡Medical Department, and §Center for Data Intensive Computing, Brookhaven National Laboratory, Upton, NY 11973
-
Edited by Richard V. Kadison, University of Pennsylvania, Philadelphia, PA, and approved October 8, 2003 (received for review April 16, 2003)
Abstract
We propose a comprehensive pattern recognition procedure that will achieve best discrimination between two or more sets of subjects with data in the same coordinate system. Applying the procedure to MS data of proteomic analysis of serum from ovarian cancer patients and serum from cancer-free individuals in the Food and Drug Administration/National Cancer Institute Clinical Proteomics Database, we have achieved perfect discrimination (100% sensitivity, 100% specificity) of patients with ovarian cancer, including early-stage disease, from normal controls for two independent sets of data. Our procedure identifies the best subset of proteomic biomarkers for optimal discrimination between the groups and appears to have higher discriminatory power than other methods reported to date. For large-scale screening for diseases of relatively low prevalence such as ovarian cancer, almost perfect specificity and sensitivity of the detection system is critical to avoid unmanageably high numbers of false-positive cases.
Footnotes
-
↵ † To whom correspondence should be addressed. E-mail: zhu{at}ams.sunysb.edu.
-
This paper was submitted directly (Track II) to the PNAS office.
-
Abbreviation: FWHM, full width at half maximum.
- Copyright © 2003, The National Academy of Sciences
