A robust meta-classification strategy for cancer detection from MS data

被引:37
作者
Bhanot, G
Alexe, G [1 ]
Venkataraghavan, B
Levine, AJ
机构
[1] Thomas J Watson IBM Res, Computat Biol Ctr, Yorktown Hts, NY 10598 USA
[2] Canc Inst New Jersey, Robert Wood Johnson Med Sch & Dent, New Brunswick, NJ USA
[3] Inst Adv Study, Ctr Syst Biol, Princeton, NJ 08540 USA
关键词
biomarker; diagnosis; meta-classifier; pattern extraction; prostate cancer;
D O I
10.1002/pmic.200500192
中图分类号
Q5 [生物化学];
学科分类号
071010 ; 081704 ;
摘要
We propose a novel method for phenotype identification involving a stringent noise analysis and filtering procedure followed by combining the results of several machine learning tools to produce a robust predictor. We illustrate our method on SELDI-TOF MS prostate cancer data (http:// home.ccr.cancer.gov/ncifdaproteomics/ppatterns.asp). Our method identified 11 proteomic biomarkers and gave significantly improved predictions over previous analyses with these data. We were able to distinguish cancer from non-cancer cases with a sensitivity of 90.31% and a specificity of 98.81%. The proposed method can be generalized to multi-phenotype prediction and other types of data (e.g., microarray data).
引用
收藏
页码:592 / 604
页数:13
相关论文
共 61 条
[1]   Ovarian cancer detection by logical analysis of proteomic data [J].
Alexe, G ;
Alexe, S ;
Liotta, LA ;
Petricoin, E ;
Reiss, M ;
Hammer, PL .
PROTEOMICS, 2004, 4 (03) :766-783
[2]  
ALEXE G, IN PRESS DISCR APPL
[3]  
ALEXE G, 2003, RUTCOR RES REPORT, V7, P1
[4]  
ALEXE G, IN PRESS SOFT COMPUT
[5]   Proteomic analysis of lung biopsies:: Differential protein expression profile between peritumoral and tumoral tissue [J].
Alfonso, P ;
Catalá, M ;
Rico-Morales, ML ;
Durante-Rodríguez, G ;
Moro-Rodríguez, E ;
Fernández-García, H ;
Escribano, JM ;
Alvarez-Fernández, E ;
García-Poblete, E .
PROTEOMICS, 2004, 4 (02) :442-447
[6]   Quantifying reproducibility for differential proteomics: noise analysis for protein liquid chromatography-mass spectrometry of human serum [J].
Anderle, M ;
Roy, S ;
Lin, H ;
Becker, C ;
Joho, K .
BIOINFORMATICS, 2004, 20 (18) :3575-3582
[7]  
[Anonymous], 1983, Statistical methods
[8]   Signal in noise: Evaluating reported reproducibility of serum proteomic tests for ovarian cancer [J].
Baggerly, KA ;
Morris, JS ;
Edmonson, SR ;
Coombes, KR .
JNCI-JOURNAL OF THE NATIONAL CANCER INSTITUTE, 2005, 97 (04) :307-309
[9]   Generation of oscillations by the p53-Mdm2 feedback loop: A theoretical and experimental study [J].
Bar-Or, RL ;
Maya, R ;
Segel, LA ;
Alon, U ;
Levine, AJ ;
Oren, M .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2000, 97 (21) :11250-11255
[10]   CONTROLLING THE FALSE DISCOVERY RATE - A PRACTICAL AND POWERFUL APPROACH TO MULTIPLE TESTING [J].
BENJAMINI, Y ;
HOCHBERG, Y .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 1995, 57 (01) :289-300