A critical assessment of feature selection methods for biomarker discovery in clinical proteomics

Molecular and Cellular Proteomics

Volumn 12, Issue 1, 2013, Pages 263-276

  Christin, Christin ^a,c   Hoefsloot, Huub C J ^c,d   Smilde, Age K ^c,d   Hoekman, B ^a,c   Suits, Frank ^b   Bischoff, Rainer ^a,c   Horvatovich, Peter ^a,c  

^a UNIVERSITY OF GRONINGEN   (Netherlands)

^b NETHERLANDS BIOINFORMATICS CENTRE   (Netherlands)

^c UNIVERSITY OF AMSTERDAM   (Netherlands)

^d IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BIOLOGICAL MARKER; PEPTIDE;

ADULT; AGED; ANALYTIC METHOD; ANALYTICAL ERROR; ARTICLE; CEREBROSPINAL FLUID ANALYSIS; CLASSIFICATION; DISCRIMINANT ANALYSIS; FEATURE SELECTION METHOD; FEMALE; HUMAN; LINEAR SUPPORT VECTOR MACHINE RECURSIVE FEATURES ELIMINATION; LIQUID CHROMATOGRAPHY; MALE; MASS SPECTROMETRY; MEASUREMENT ACCURACY; METABOLOMICS; NEAREST SHRUNKEN CENTROID; NONHUMAN; NORMAL HUMAN; PARTIAL LEAST SQUARES DISCRIMINANT ANALYSIS; PEPTIDE ANALYSIS; PRINCIPAL COMPONENT ANALYSIS; PRINCIPAL COMPONENT DISCRIMINANT ANALYSIS; PRIORITY JOURNAL; PROTEOMICS; RANK SUM TEST; RELIABILITY; SAMPLE SIZE; SCORING SYSTEM; SENSITIVITY AND SPECIFICITY; STATISTICAL ANALYSIS; STUDENT T TEST; SWINE; URINALYSIS;

ANIMALS; BIOLOGICAL MARKERS; CHROMATOGRAPHY, LIQUID; COMPUTATIONAL BIOLOGY; DATA INTERPRETATION, STATISTICAL; GENE EXPRESSION PROFILING; HUMANS; MASS SPECTROMETRY; METABOLOMICS; OLIGONUCLEOTIDE ARRAY SEQUENCE ANALYSIS; PATTERN RECOGNITION, AUTOMATED; PEPTIDES; PRINCIPAL COMPONENT ANALYSIS; PROTEOMICS; SWINE;

SUS;

EID: 84871862591     PISSN: 15359476     EISSN: 15359484     Source Type: Journal    
DOI: 10.1074/mcp.M112.022566     Document Type: Article

References (49)

1. Mischak, H., Allmaier, G., Apweiler, R., Attwood, T., Baumann, M., Benigni, A., Bennett, S. E., Bischoff, R., Bongcam-Rudloff, E., Capasso, G., Coon, J. J., D'Haese, P., Dominiczak, A. F., Dakna, M., Dihazi, H., Ehrich, J. H., Fernandez-Llama, P., Fliser, D., Frokiaer, J., Garin, J., Girolami, M., Hancock, W. S., Haubitz, M., Hochstrasser, D., Holman, R. R., Ioannidis, J. P., Jankowski, J., Julian, B. A., Klein, J. B., Kolch, W., Luider, T., Massy, Z., Mattes, W. B., Molina, F., Monsarrat, B., Novak, J., Peter, K., Rossing, P., Sanchez-Carbayo, M., Schanstra, J. P., Semmes, O. J., Spasovski, G., Theodorescu, D., Thongboonkerd, V., Vanholder, R., Veenstra, T. D., Weissinger, E., Yamamoto, T., and Vlahou, A. (2010) Recommendations for biomarker identification and qualification in clinical proteomics. Sci. Transl. Med. 2, 46ps42
2. Puntmann, V. O. (2009) How-to guide on biomarkers: biomarker definitions, validation and applications with examples from cardiovascular disease. Postgrad. Med. J. 85, 538-545
3. Rifai, N., Gillette, M. A., and Carr, S. A. (2006) Protein biomarker discovery and validation: the long and uncertain path to clinical utility. Nat. Biotechnol. 24, 971-983
4. Hoekman, B., Breitling, R., Suits, F., Bischoff, R., and Horvatovich, P. (2012) msCompare: a framework for quantitative analysis of label-free LC-MS data for comparative candidate biomarker studies. Mol. Cell. Proteomics 11, M111.015974
5. Saeys, Y., Inza, I., and Larranaga, P. (2007) A review of feature selection techniques in bioinformatics. Bioinformatics 23, 2507-2517
6. Smit, S., Hoefsloot, H. C. J., and Smilde, A. K. (2008) Statistical data processing in clinical proteomics. J. Chromatogr. B Analyt. Technol. Biomed. Life Sci. 866, 77-88
7. Smit, S., van Breemen, M. J., Hoefsloot, H. C., Smilde, A. K., Aerts, J. M., and de Koster, C. G. (2007) Assessing the statistical validity of proteomics based biomarkers. Anal. Chim. Acta 592, 210-217
8. Kohavi, R., and John, G. H. (1997) Wrappers for feature subset selection. Artif. Intell. 97, 273-324
9. Hilario, M., and Kalousis, A. (2008) Approaches to dimensionality reduction in proteomic biomarker studies. Brief Bioinform. 9, 102-118
10. Baek, S., Tsai, C. A., and Chen, J. J. (2009) Development of biomarker classifiers from high-dimensional data. Brief Bioinform. 10, 537-546
11. Datta, S., and Pihur, V. (2010) Feature selection and machine learning with mass spectrometry data. Methods Mol. Biol. 593, 205-229
12. Van der Walt, C., and Barnard, E. (2006) Data characteristics that determine classifier performance. SAIEE Africa Research Journal, 98, 87-93
13. Rubingh, C., Bijlsma, S., Derks, E., Bobeldijk, I., Verheij, E., Kochhar, S., and Smilde, A. (2006) Assessing the performance of statistical validation tools for megavariate metabolomics data. Metabolomics 2, 53-61
14. Benjamini, Y., and Hochberg, Y. (1995) Controlling the false discovery rate: a practical and powerful approach to multiple testing. J. R. Stat. Soc. Ser. B 57, 289-300
15. Tibshirani, R., Hastie, T., Narasimhan, B., and Chu, G. (2002) Diagnosis of multiple cancer types by shrunken centroids of gene expression. Proc. Natl. Acad. Sci. U.S.A. 99, 6567-6572
16. Tibshirani, R., Hastie, T., Narasimhan, B., and Chu, G. (2003) Class prediction by nearest shrunken centroids, with applications to DNA microarrays. Stat. Sci. 18, 104-117
17. Guyon, I., Weston, J., Barnhill, S., and Vapnik, V. (2002) Gene selection for cancer classification using support vector machines. Mach. Learn. 46, 389-422
18. Barker, M., and Rayens, W. (2003) Partial least squares for discrimination. J. Chemom. 17, 166-173
19. Hoogerbrugge, R., Willig, S. J., and Kistemaker, P. G. (1983) Discriminant analysis by double stage principal component analysis. Anal. Chem. 55, 1710-1712
20. Breitling, R., Armengaud, P., Amtmann, A., and Herzyk, P. (2004) Rank products: a simple, yet powerful, new method to detect differentially regulated genes in replicated microarray experiments. FEBS Lett. 573, 83-92
21. Suits, F., Hoekman, B., Rosenling, T., Bischoff, R., and Horvatovich, P. (2011) Threshold-avoiding proteomics pipeline. Anal. Chem. 83, 7786-7794
22. Vapnik, V. (1998) Statistical Learning Theory, Wiley-Interscience
23. Anderson, D. C., Li, W., Payan, D. G., and Noble, W. S. (2003) A new algorithm for the evaluation of shotgun peptide sequencing in proteomics: support vector machine classification of peptide MS/MS spectra and SEQUEST scores. J. Proteome Res. 2, 137-146
24. Mao, Y., Zhou, X. B., Pi, D. Y., and Sun, Y. X. (2005) Constructing support vector machine ensembles for cancer classification based on proteomic profiling. Genomics Proteomics Bioinformatics 3, 238-241
25. Jiang, Z., Yamauchi, K., Yoshioka, K., Aoki, K., Kuroyanagi, S., Iwata, A., Yang, J., and Wang, K. (2006) Support vector machine-based feature selection for classification of liver fibrosis grade in chronic hepatitis C. J. Med. Syst. 30, 389-394
26. Guo, J., Deng, W., Zhang, L., Li, C., Wu, P., and Mao, P. (2007) Prediction of prostate cancer using hair trace element concentration and support vector machine method. Biol. Trace Elem. Res. 116, 257-272
27. Mao, Y., Zhao, X., Wang, S., and Cheng, Y. (2007) Urinary nucleosides based potential biomarker selection by support vector machine for bladder cancer recognition. Anal. Chim. Acta 598, 34-40
28. Lin, E., and Hwang, Y. (2008) A support vector machine approach to assess drug efficacy of interferon-alpha and ribavirin combination therapy. Mol. Diagn. Ther. 12, 219-223
29. Pham, T. V., van de Wiel, M. A., and Jimenez, C. R. (2008) Support vector machine approach to separate control and breast cancer serum samples. Stat. Appl. Genet. Mol. Biol. 7, Article 11
30. Webb-Robertson, B. J., Cannon, W. R., Oehmen, C. S., Shah, A. R., Gurumoorthi, V., Lipton, M. S., and Waters, K. M. (2008) A support vector machine model for the prediction of proteotypic peptides for accurate mass and time proteomics. Bioinformatics 24, 1503-1509
31. Henneges, C., Bullinger, D., Fux, R., Friese, N., Seeger, H., Neubauer, H., Laufer, S., Gleiter, C. H., Schwab, M., Zell, A., and Kammerer, B. (2009) Prediction of breast cancer by profiling of urinary RNA metabolites using support vector machine-based feature selection. BMC Cancer 9, 104
32. Zou, A. M., Wu, F. X., Ding, J. R., and Poirier, G. G. (2009) Quality assessment of tandem mass spectra using support vector machine (SVM). BMC Bioinformatics 10 Suppl 1, S49
33. Hermes, L., and Buhmann, J. M. (2000) Feature selection for support vector machines. Proceedings of the 15th International Conference on Pattern Recognition, 2000, Barcelona, Spain September 3-7 pp. 712-715
34. Weston, J., Mukherjee, S., Chapelle, O., Pontil, M., Poggio, T., and Vapnik, V. (2000) Advances in Neural Information Processing Systems 13, Papers from Neural Information Processing Systems (NIPS) 27 Nov- 2 Dec 2000, Denver, CO, MIT Press 2001 Feature selection for SVMs.
35. Hoefsloot, H. C., Smit, S., and Smilde, A. K. (2008) A classification model for the Leiden proteomics competition. Stat. Appl. Genet. Mol. Biol. 7, Article 8
36. Amato, U., Larobina, M., Antoniadis, A., and Alfano, B. (2003) Segmentation of magnetic resonance brain images through discriminant analysis. J. Neurosci. Meth. 131, 65-74
37. Lamers, R. J., DeGroot, J., Spies-Faber, E. J., Jellema, R. H., Kraus, V. B., Verzijl, N., TeKoppele, J. M., Spijksma, G. K., Vogels, J. T., van der Greef, J., and van Nesselrooij, J. H. (2003) Identification of disease- and nutrient-related metabolic fingerprints in osteoarthritic guinea pigs. J. Nutr. 133, 1776-1780
38. Ramadan, Z., Jacobs, D., Grigorov, M., and Kochhar, S. (2006) Metabolic profiling using principal component analysis, discriminant partial least squares, and genetic algorithms. Talanta 68, 1683-1691
39. Lv, Y., Liu, X., Yan, S., Liang, X., Yang, Y., Dai, W., and Zhang, W. (2010) Metabolomic study of myocardial ischemia and intervention effects of Compound Danshen Tablets in rats using ultra-performance liquid chromatography/quadrupole time-of-flight mass spectrometry. J. Pharm. Biomed. Anal. 52, 129-135
40. Liu, Y., Huang, R., Liu, L., Peng, J., Xiao, B., Yang, J., Miao, Z., and Huang, H. (2010) Metabonomics study of urine from Sprague-Dawley rats exposed to Huang-yao-zi using (1)H NMR spectroscopy. J. Pharm. Biomed. Anal. 52, 136-141
41. Lan, K., Zhang, Y., Yang, J., and Xu, L. (2010) Simple quality assessment approach for herbal extracts using high performance liquid chromatography-UV based metabolomics platform. J. Chromatogr. A 1217, 1414-1418
42. Kim, H. K., Saifullah Khan, S., Wilson, E. G., Kricun, S. D., Meissner, A., Goraler, S., Deelder, A. M., Choi, Y. H., and Verpoorte, R. (2010) Metabolic classification of South American Ilex species by NMR-based metabolomics. Phytochemistry 71, 773-784
43. Feng, B., Wu, S. M., Lv, S., Liu, F., Chen, H. S., Gao, Y., Dong, F. T., and Wei, L. (2009) A novel scoring system for prognostic prediction in dgalactosamine/lipopolysaccharide-induced fulminant hepatic failure BALB/c mice. BMC Gastroenterol. 9, 99
44. Barba, I., Garcia-Ramirez, M., Hernandez, C., Alonso, M. A., Masmiquel, L., Garcia-Dorado, D., and Simo, R. (2010) Metabolic fingerprints of proliferative diabetic retinopathy: an 1H-NMR-based metabonomic approach using vitreous humor. Invest. Ophthalmol. Vis. Sci. 51, 4416-4421
45. Boulesteix, A. L., and Strimmer, K. (2007) Partial least squares: a versatile tool for the analysis of high-dimensional genomic data. Brief Bioinform. 8, 32-44
46. Chevallier, S., Bertrand, D., Kohler, A., and Courcoux, P. (2006) Application of PLS-DA in multivariate image analysis. J. Chemom. 20, 221-229
47. Westerhuis, J., Hoefsloot, H., Smit, S., Vis, D., Smilde, A., van Velzen, E., van Duijnhoven, J., and van Dorsten, F. (2008) Assessment of PLSDA cross validation. Metabolomics 4, 81-89
48. Westerhuis, J., van Velzen, E., Hoefsloot, H., and Smilde, A. (2008) Discriminant Q2 (DQ2) for improved discrimination in PLSDA models. Metabolomics 4, 293-296
49. Westerhuis, J. A., van Velzen, E. J., Hoefsloot, H. C., and Smilde, A. K. (2010) Multivariate paired data analysis: multilevel PLSDA versus OPLSDA. Metabolomics 6, 119-128