Gene selection in microarray data: The elephant, the blind men and our algorithms

Current Opinion in Structural Biology

Volumn 13, Issue 3, 2003, Pages 370-376

  Stolovitzky, Gustavo ^a  

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

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHM; ANALYTIC METHOD; BLINDNESS; CELL ACTIVITY; CELL STRUCTURE; CLASSIFICATION; DATA ANALYSIS; DNA MICROARRAY; ELEPHANT; EXPERIMENT; GENE CLUSTER; GENE EXPRESSION; GENETIC ANALYSIS; GENETIC SELECTION; GENETIC TRANSCRIPTION; INFORMATION PROCESSING; LITERATURE; MULTIVARIATE ANALYSIS; PRIORITY JOURNAL; REVIEW; STATISTICAL ANALYSIS; STRUCTURE ANALYSIS; TECHNOLOGY; VALIDATION PROCESS;

ELEPHANT;

EID: 0037494667     PISSN: 0959440X     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0959-440X(03)00078-2     Document Type: Review

References (41)

1. Bibliography on Microarray Data Analysis on World Wide Web URL: http://www.nslij-genetics.org/microarray/.
2. ArrayExpress database on World Wide Web URL: http://www.ebi.ac.uk/arrayexpress/.
3. Stanford Microarray Database on World Wide Web URL: http://genome-www5.stanford.edu/MicroArray/SMD/.
4. GenomeWeb Gene Expression and Microarrays on World Wide Web URL: http://www.hgmp.mrc.ac.uk/GenomeWeb/nuc-genexp.html.
5. YF Leung's Microarray Links on World Wide Web URL: http://ihome.cuhk.edu.hk/%7Eb400559/array.html.
6. Slonim D.K. From patterns to pathways: gene expression data analysis comes of age. Nat. Genet. 32:2002;502-508.
7. Quackenbush J. Microarray data normalization and transformation. Nat. Genet. 32:2002;496-501.
8. Pan W. A comparative review of statistical methods for discovering differentially expressed genes in replicated microarray experiments. Bioinformatics. 18:2002;546-554 This paper unifies three apparently different methods under the umbrella of t-type statistics. It shows that, even though the scores are very similar, different ways of sampling its distribution can lead to different rejection regions for the null hypotheses, thus yielding different lists of selected genes.
9. Troyanskaya O.G., Garber M.E., Brown P.O., Botstein D., Altman R.B. Nonparametric methods for identifying differentially expressed genes in microarray data. Bioinformatics. 18:2002;1454-1461 This paper considers three nonparametric methods of gene selection. (One of these methods, the ideal discriminator method, could be mapped to a t-type score, a property not discussed in the paper.) One of the important features of this paper is the use of synthetic data. This allowed the authors to evaluate the performance of their algorithms not only in terms of their false positives rate (which is usually controlled by the p-value from randomized experiments), but also in terms of their false negatives rate.
10. Liu H., Li J., Wong L. A comparative study on feature selection and classification methods using gene expression profiles and proteomics patterns. Genome Inform. 13:2002;51-60.
11. Golub T.R., Slonim D.K., Tamayo P., Huard C., Gaasenbeek M., Mesirov J.P., Coller H., Loh M.L., Downing J.R., Caligiuri M.A.et al. Molecular classification of cancer: class discovery and class prediction by gene expression monitoring. Science. 286:1999;531-537.
12. Pan W., Lin J., Le C.T. How many replicates of arrays are required to detect gene expression changes in microarray experiments? A mixture model approach. Genome Biol. 3:2002;22.
13. Bijlani R., Cheng Y., Pearce D.A., Brooks A.I., Ogihara M. Prediction of biologically significant components from microarray data: independently consistent expression discriminator (ICED). Bioinformatics. 19:2003;62-70.
14. Li J., Liu H., Downing J.R., Yeoh A.E., Wong L. Simple rules underlying gene expression profiles of more than six subtypes of acute lymphoblastic leukemia (ALL) patients. Bioinformatics. 19:2003;71-78.
15. Fayyad U, Irani K: Multi-interval discretization of continuous-valued attributes for classification learning. Proc 13th Int Joint Conf Artif Intel 1993:1022-1029.
16. Li W., Yang Y. Zipf's law in importance of genes for cancer classification using microarray data. J. Theor. Biol. 219:2002;539-551 This paper introduces the use of Zipf's plots in gene expression analysis. Zipf's plots could reveal an intrinsic separation between important and irrelevant genes. In their Zipf's plot analysis using a maximum likelihood algorithm, the authors did not find such intrinsic separation. But it may be possible that Zipf's plots based on different scores reveal such a threshold.
17. Lee K.E., Sha N., Dougherty E.R., Vannucci M., Mallick B.K. Gene selection: a Bayesian variable selection approach. Bioinformatics. 19:2003;90-97.
18. Tu Y., Stolovitzky G., Klein U. Quantitative noise analysis for gene expression microarray experiments. Proc. Natl. Acad Sci. USA. 99:2002;14031-14036.
19. Holter N.S., Mitra M., Maritan A., Cieplak M., Banavar J.R., Fedoroff N.V. Fundamental patterns underlying gene expression profiles: simplicity from complexity. Proc. Natl. Acad Sci. USA. 97:2000;8409-8414.
20. Alter O., Brown P.O., Botstein D. Singular value decomposition for genome-wide expression data processing and modeling. Proc. Natl. Acad Sci. USA. 97:2000;10101-10106.
21. Alter O., Brown P.O. Botstein D, Generalized singular value decomposition for comparative analysis of genome-scale expression data sets of two different organisms. Proc. Natl. Acad Sci. USA. 100:2003;3351-3356.
22. Kluger Y., Basri R., Chang J.T., Gerstein M. Spectral biclustering of microarray data: coclustering genes and conditions. Genome Res. 13:2003;703-716 The importance of normalization in classification using SVD was clearly emphasized and studied in this paper. It also suggests a method of selecting eigenmodes based on the piecewise constant nature of the eigengenes to highlight the checkerboard structure of the gene expression matrix.
23. Lazzeroni L., Owen A. Plaid models for gene expression data. Statistica Sinica. 12:2002;61-86.
24. Cheng Y., Church G.M. Biclustering of expression data. Proc. Int. Conf. Intell Syst. Mol. Biol. 8:2000;93-103.
25. Getz G., Levine E., Domany E. Coupled two-way clustering analysis of gene microarray data. Proc. Natl. Acad Sci. USA. 97:2000;12079-12084.
26. Califano A., Stolovitzky G., Tu Y. Analysis of gene expression microarrays for phenotype classification. Proc. Int. Conf. Intell Syst. Mol. Biol. 8:2000;75-85.
27. Nielsen T.O., West R.B., Linn S.C., Alter O., Knowling M.A., O'Connell J.X., Zhu S., Fero M., Sherlock G., Pollack J.R.et al. Molecular characterisation of soft tissue tumours: a gene expression study. Lancet. 359:2002;1301-1307.
28. Misra J., Schmitt W., Hwang D., Hsiao L.L., Gullans S., Stephanopoulos G. Interactive exploration of microarray gene expression patterns in a reduced dimensional space. Genome Res. 12:2002;1112-1120 An investigation into the use of SVD for gene selection. By filtering out genes with small loadings in the two dominant eigenmodes and keeping only those genes that keep the structure of the scores plot minimally distorted, these authors identified tissue-specific genes.
29. Liebermeister W. Linear modes of gene expression determined by independent component analysis. Bioinformatics. 18:2002;51-60.
30. Antoniadis A., Lambert-Lacroix S., Leblanc F. Effective dimension reduction methods for tumor classification using gene expression data. Bioinformatics. 19:2003;563-570.
31. Bicciato S., Luchini A., Di Bello C. PCA disjoint models for multiclass cancer analysis using gene expression data. Bioinformatics. 19:2003;571-578.
32. Dettling M., Buhlmann P. Supervised clustering of genes. Genome Biol. 3:2002;69.
33. Deutsch J.M. Evolutionary algorithms for finding optimal gene sets in microarray prediction. Bioinformatics. 19:2003;45-52.
34. Kim S., Dougherty E.R., Barrera J., Chen Y., Bittner M.L., Trent J.M. Strong feature sets from small samples. J. Comput. Biol. 9:2002;127-146 This paper exhaustively evaluates the ability of all groups of d genes (d≤3) to classify between two tissue types. The large computational burden of exploring all possible gene groups is compensated by an analytical linear classifier whose predictive power can be assessed by an elegant method in which the mass of the sample points is spread to make classification more difficult, while maintaining the sample geometry, without doing a leave-one-out cross-validation.
35. Klein U., Tu Y., Stolovitzky G.A., Keller J.L., Haddad J. Jr., Miljkovic V., Cattoretti G., Califano A., Dalla-Favera R. Transcriptional analysis of the B cell germinal center reaction. Proc. Natl. Acad Sci. USA. 100:2003;2639-2644.
36. Kuppers R., Klein U., Schwering I., Distler V., Brauninger A., Cattoretti G., Tu Y., Stolovitzky G.A., Califano A., Hansmann M.L.et al. Identification of Hodgkin and Reed-Sternberg cell-specific genes by gene expression profiling. J. Clin. Invest. 111:2003;529-537.
37. Jelinek D.F., Tschumper R.C., Stolovitzky G.A., Iturria S.J., Tu Y., Lepre J., Shah N., Kay N.E. Identification of a global gene expression signature of B-chronic lymphocytic leukemia. Mol. Cancer Res. 1:2003;346-361 An example of merging together the results of a battery of univariate and multivariate techniques to find differentially expressing genes between cancer and control samples. The genes resulting from the combination of algorithms were validated by classification in a completely independent data set generated in a different laboratory.
38. Shipp M.A., Ross K.N., Tamayo P., Weng A.P., Kutok J.L., Aguiar R.C., Gaasenbeek M., Angelo M., Reich M., Pinkus G.S.et al. Diffuse large B-cell lymphoma outcome prediction by gene-expression profiling and supervised machine learning. Nat. Med. 8:2002;68-74.
39. Chaussabel D., Sher A. Mining microarray expression data by literature profiling. Genome Biol. 3:2002;55.
40. Khatri P., Draghici S., Ostermeier G.C., Krawetz S.A. Profiling gene expression using onto-express. Genomics. 79:2002;266-270.
41. Klein U., Tu Y., Stolovitzky G.A., Mattioli M., Cattoretti G., Husson H., Freedman A., Inghirami G., Cro L., Baldini L.et al. Gene expression profiling of B cell chronic lymphocytic leukemia reveals a homogeneous phenotype related to memory B cells. J. Exp. Med. 194:2001;1625-1638.