A strategy for predicting the chemosensitivity of human cancers and its application to drug discovery

Departments of *Public Health Sciences,
^†Molecular Physiology and Biological Physics,
^‡Urology, and
**Computer Science, University of Virginia, Charlottesville, VA 22908;
^¶Laboratory of Molecular Pharmacology, Genomics and Bioinformatics Group, Building 37, Room 5068, National Cancer Institute, National Institutes of Health, Bethesda, MD 20892;
^§Department of Statistics, Korea University, Seoul 136-701, Korea; and
^‖Gene Logic, Inc., 610 Professional Drive, Gaithersburg, MD 20879

Edited by Michael S. Waterman, University of Southern California, Los Angeles, CA, and approved April 3, 2007 (received for review November 21, 2006)

Abstract

The U.S. National Cancer Institute has used a panel of 60 diverse human cancer cell lines (the NCI-60) to screen >100,000 chemical compounds for anticancer activity. However, not all important cancer types are included in the panel, nor are drug responses of the panel predictive of clinical efficacy in patients. We asked, therefore, whether it would be possible to extrapolate from that rich database (or analogous ones from other drug screens) to predict activity in cell types not included or, for that matter, clinical responses in patients with tumors. We address that challenge by developing and applying an algorithm we term “coexpression extrapolation” (COXEN). COXEN uses expression microarray data as a Rosetta Stone for translating from drug activities in the NCI-60 to drug activities in any other cell panel or set of clinical tumors. Here, we show that COXEN can accurately predict drug sensitivity of bladder cancer cell lines and clinical responses of breast cancer patients treated with commonly used chemotherapeutic drugs. Furthermore, we used COXEN for in silico screening of 45,545 compounds and identify an agent with activity against human bladder cancer.

Footnotes

^††To whom correspondence should be addressed at:
Department of Molecular Physiology and Biological Physics, Box 800422, University of Virginia, Charlottesville, VA 22908.
E-mail: dt9d{at}virginia.edu
Author contributions: J.K.L. and D.T. designed research; J.K.L., D.M.H., H.C., and D.T. performed research; J.K.L., E.P.K., and D.T. contributed new reagents/analytic tools; J.K.L., J.N.W., J.K., A.G., and D.T. analyzed data; and J.K.L., J.N.W., and D.T. wrote the paper.
The authors declare no conflict of interest.
This article is a PNAS Direct Submission.
This article contains supporting information online at www.pnas.org/cgi/content/full/0610292104/DC1.
Abbreviations:

COXEN,

coexpression extrapolation;

DTP,

Developmental Therapeutics Program;

NCI,

National Cancer Institute;

MiPP,

misclassification-penalized posterior;

GI50,

50% growth inhibition;

ROC,

receiver operator characteristic.