Skip to main content
SpringerLink
Log in

On the Identification of Correlated Differential Features for Supervised Classification of High-Dimensional Data

  • Conference paper
  • First Online:
Data Science

Abstract

Many real problems in supervised classification involve high-dimensional feature data measured for individuals of known origin from two or more classes. When the dimension of the feature vector is very large relative to the number of individuals, it presents formidable challenges to construct a discriminant rule (classifier) for assigning an unclassified individual to one of the known classes. One way to handle this high-dimensional problem is to identify highly relevant differential features for constructing a classifier. Here a new approach is considered, where a mixture model with random effects is used firstly to partition the features into clusters and then the relevance of each feature variable for differentiating the classes is formally tested and ranked using cluster-specific contrasts of mixed effects. Finally, a non-parametric clustering approach is adopted to identify networks of differential features that are highly correlated. The method is illustrated using a publicly available data set in cancer research for the discovery of correlated biomarkers relevant to the cancer diagnosis and prognosis.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 109.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 139.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Benjamini, Y., Hochberg, Y.: Controlling the false discovery rate: a practical and powerful approach to multiple testing. J. R. Stat. Soc. B 57, 259–300 (1995)

    MathSciNet  MATH  Google Scholar 

  2. Bickel, P.J., Levina, E.: Some theory for Fisher’s linear discriminant function, ‘naive Bayes’, and some alternatives when there are many more variables than observations. Bernoulli 10, 989–1010 (2004)

    Article  MathSciNet  MATH  Google Scholar 

  3. Borgatti, S.P., Everett, M.G., Freeman, L.C.: Ucinet for Windows: Software for Social Network Analysis. Analytic Technologies, Harvard, MA (2002). Available via http://www.analytictech.com/. Accessed 8 Dec 2015

  4. Cai, T., Liu, W.: A direct estimation approach to sparse linear discriminant analysis. J. Am. Stat. Assoc. 106, 1566–1577 (2011)

    Article  MathSciNet  MATH  Google Scholar 

  5. Collado, M., Garcia, V., Garcia, J.M., Alonso, I., Lombardia, L., et al.: Genomic profiling of circulating plasma RNA for the analysis of cancer. Clin. Chem. 53, 1860–1863 (2007)

    Article  Google Scholar 

  6. Dahl, D.B., Newton, M.A.: Multiple hypothesis testing by clustering treatment effects. J. Am. Stat. Assoc. 102, 517–526 (2007)

    Article  MathSciNet  MATH  Google Scholar 

  7. Donoho, D., Jin, J.: Higher criticism for large-scale inference, especially for rare and weak effects. Stat. Sci. 30, 1–25 (2015)

    Article  MathSciNet  MATH  Google Scholar 

  8. Fan, J., Lv, J.: A selective review of variable selection in high dimensional feature space. Stat. Sin. 20, 101–148 (2010)

    MATH  Google Scholar 

  9. Fan, J., Feng, Y., Tong, X.: A road to classification in high dimensional space: the regularized optimal affine discriminant. J. R. Stat. Soc. B 74, 745–771 (2012)

    Article  MathSciNet  Google Scholar 

  10. Hall, P., Pittelkow, Y., Ghosh, M.: Theoretic measures of relative performance of classifiers for high-dimensional data with small sample sizes. J. R. Stat. Soc. B 70, 158–173 (2008)

    MATH  Google Scholar 

  11. Hall, P., Jin, J., Miller, H.: Feature selection when there are many influential features. Bernoulli 20, 1647–1671 (2014)

    Article  MathSciNet  MATH  Google Scholar 

  12. He, Y., Pan, W., Lin, J.: Cluster analysis using multivariate normal mixture models to detect differential gene expression with microarray data. Comput. Stat. Data Anal. 51, 641–658 (2006)

    Article  MathSciNet  MATH  Google Scholar 

  13. Kersten, J.: Simultaneous feature selection and Gaussian mixture model estimation for supervised classification problems. Pattern Recogn. 47, 2582–2595 (2014)

    Article  MATH  Google Scholar 

  14. Matsui, S., Noma, H.: Estimating effect sizes of differentially expressed genes for power and sample-size assessments in microarray experiments. Biometrics 67, 1225–1235 (2011)

    Article  MathSciNet  MATH  Google Scholar 

  15. McLachlan, G.J.: Discriminant analysis. WIREs Comput. Stat. 4, 421–431 (2012)

    Article  Google Scholar 

  16. McLachlan, G.J., Peel, D.: Finite Mixture Models. Wiley, New York (2000)

    Book  MATH  Google Scholar 

  17. McLachlan, G.J., Do, K.A., Ambroise, C.: Analyzing Microarray Gene Expression Data. Wiley, New York (2004)

    Book  MATH  Google Scholar 

  18. Ng, S.K.: A two-way clustering framework to identify disparities in multimorbidity patterns of mental and physical health conditions among Australians. Stat. Med. 34, 3444–3460 (2015)

    Article  MathSciNet  Google Scholar 

  19. Ng, S.K., McLachlan, G.J.: Mixture models for clustering multilevel growth trajectories. Comput. Stat. Data Anal. 71, 43–51 (2014)

    Article  MathSciNet  Google Scholar 

  20. Ng, S.K., McLachlan, G.J., Wang, K., Ben-Tovim, L., Ng, S.-W.: A mixture model with random-effects components for clustering correlated gene-expression profiles. Bioinformatics 22, 1745–1752 (2006)

    Article  Google Scholar 

  21. Ng, S.K., Holden, L., Sun, J.: Identifying comorbidity patterns of health conditions via cluster analysis of pairwise concordance statistics. Stat. Med. 31, 3393–3405 (2012)

    Article  MathSciNet  Google Scholar 

  22. Ng, S.K., McLachlan, G.J., Wang, K., Nagymanyoki, Z., Liu, S., Ng, S.-W.: Inference on differences between classes using cluster-specific contrasts of mixed effects. Biostatistics 16, 98–112 (2015)

    Article  MathSciNet  Google Scholar 

  23. Pan, W., Lin, J., Le, C.T.: Model-based cluster analysis of microarray gene-expression data. Genome Biol. 3, 0009.1–0009.8 (2002)

    Google Scholar 

  24. Pyne, S., Lee, S.X., Wang, K., Irish, J., Tamayo, P., et al.: Joint modeling and registration of cell populations in cohorts of high-dimensional flow cytometric data. PLoS One 9, e100334 (2014)

    Article  Google Scholar 

  25. Qi, Y., Sun, H., Sun, Q., Pan, L.: Ranking analysis for identifying differentially expressed genes. Genomics 97, 326–329 (2011)

    Article  Google Scholar 

  26. Qiu, W., He, W., Wang, X., Lazarus, R.: A marginal mixture model for selecting differentially expressed genes across two types of tissue samples. Int. J. Biostat. 4, Article 20 (2008)

    Article  MathSciNet  Google Scholar 

  27. Smyth, G.: Linear models and empirical Bayes methods for assessing differential expression in microarray experiments. Stat. Appl. Genet. Mol. Biol. 3, Article 3 (2004)

    Article  MathSciNet  MATH  Google Scholar 

  28. Storey, J.D.: The optimal discovery procedure: a new approach to simultaneous significance testing. J. R. Stat. Soc. B 69, 347–368 (2007)

    Article  MathSciNet  Google Scholar 

  29. Zhao, Y.: Posterior probability of discovery and expected rate of discovery for multiple hypothesis testing and high throughput assays. J. Am. Stat. Assoc. 106, 984–996 (2011)

    Article  MathSciNet  MATH  Google Scholar 

Download references

Acknowledgements

Part of this work has been presented in the Conference of the International Federation of Classification Societies, Bologna, July 2015. This work was supported by a grant from the Australian Research Council.

Author information

Authors and Affiliations

  1. School of Medicine and Menzies Health Institute Queensland, Griffith University, Nathan, QLD, 4111, Australia

    Shu Kay Ng

  2. Department of Mathematics, University of Queensland, St Lucia, QLD, 4072, Australia

    Geoffrey J. McLachlan

Authors
  1. Shu Kay Ng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Geoffrey J. McLachlan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shu Kay Ng .

Editor information

Editors and Affiliations

  1. Department of Political Sciences, University of Naples Federico II, Napoli, Italy

    Francesco Palumbo

  2. Department of Statistical Sciences Paolo Fortunati, Alma Mater Studiorum, University of Bologna, Bologna, Italy

    Angela Montanari

  3. Department of Statistical Sciences, Sapienza University of Rome, Rome, Italy

    Maurizio Vichi

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Cite this paper

Ng, S.K., McLachlan, G.J. (2017). On the Identification of Correlated Differential Features for Supervised Classification of High-Dimensional Data. In: Palumbo, F., Montanari, A., Vichi, M. (eds) Data Science . Studies in Classification, Data Analysis, and Knowledge Organization. Springer, Cham. https://doi.org/10.1007/978-3-319-55723-6_4

Download citation

Publish with us

Policies and ethics

Search

Navigation