Personalized Information Modeling for Personalized Medicine

Abstract

Personalized modeling offers a new and effective approach for the study of pattern recognition and knowledge discovery, especially for biomedical applications. The created models are very useful and informative for analyzing and evaluating an individual data object for a given problem. Such models are also expected to achieve a higher degree of accuracy of prediction of outcome or classification than conventional systems and methodologies. Motivated by the concept of personalized medicine and utilizing transductive reasoning, personalized modeling was recently proposed as a new method for knowledge discovery in biomedical applications. Personalized modeling aims to create a unique computational diagnostic or prognostic model for an individual. Here we introduce an integrated method for personalized modeling that applies global optimization of variables (features) and an appropriate neighborhood size to create an accurate personalized model for an individual. This method creates an integrated computational system that combines different information processing techniques, applied at different stages of data analysis, e.g., feature selection, classification, discovering the interaction of genes, outcome prediction, personalized profiling and visualization, etc. It allows for adaptation, monitoring, and improvement of an individualʼs model and leads to improved accuracy and unique personalized profiling that could be used for personalized treatment and personalized drug design.

Abbreviations

3-D

three-dimensional

AE

absolute error

AUC

area under curve

BRCA

breast cancer-associated gene

DNA

deoxyribonucleic acid

ECF

evolving classification function

ES

evolutionary strategy

GA

genetic algorithm

GWAS

genome-wide association scan

IMPM

integrated method for personalized modeling

ISPM

integrated optimization system for personalized modeling

KNN

K nearest neighbor

LOOCV

leave-one-out cross validation

MLP

multilayer perceptron

MLR

multiple linear regression

PMF

personalized modeling framework

PMS

personalized modeling system

RBF

radial basis function

RMSE

root mean squared error

RNA

ribonucleic acid

SNP

single-nucleotide polymorphism

SNR

signal-to-noise ratio

SOM

self-organizing map

SVM

support vector machine

TWNFI

transductive weighted neuro-fuzzy inference engine

TWRBF

transductive inference based radial basis function

WKNN

weighted nearest neighbor

WWKNN

weighted distance and weighted variables K nearest neighbor

cEAP

coevolutionary based algorithm for personalized modeling

mRNA

messenger RNA

References

  1. 33.1.
    J. Anderson, L.L. Hansen, F.C. Mooren, M. Post, H. Hug, A. Zuse, M. Los: Methods and biomarkers for the diagnosis and prognosis of cancer and other diseases: Towards personalized medicine, Drug Resist. Updates 9(4/5), 198–210 (2006)CrossRefGoogle Scholar
  2. 33.2.
    A.S. Levey, J.P. Bosch, J.B. Lewis, T. Greene, N. Rogers, D. Roth: A more accurate method to estimate glomerular filtration rate from serum creatinine: a new prediction equation. Modification of diet in renal disease study group, Ann. Intern. Med. 130, 461–470 (1999)CrossRefGoogle Scholar
  3. 33.3.
    A. Shabo: Health record banks: Integrating clinical and genomic data into patient-centric longitudinal and cross-institutional health records, Pers. Med. 4(4), 453–455 (2007)CrossRefGoogle Scholar
  4. 33.4.
    J.R. Nevins, E.S. Huang, H. Dressman, J. Pittman, A.T. Huang, M. West: Towards integrated clinico-genomic models for personalized medicine: Combining gene expression signatures and clinical factors in breast cancer outcomes prediction, Human Mol. Genet. 12(2), R153–R157 (2003)CrossRefGoogle Scholar
  5. 33.5.
    M.I. McCarthy, J.N. Hirschhorn: Genome-wide association studies: Potential next steps on a genetic journey, Human Mol. Genet. 17(R2), R156–R165 (2008)CrossRefGoogle Scholar
  6. 33.6.
    L.A. Hindorff, P. Sethupathy, H.A. Junkins, E.M. Ramos, J.P. Mehta, F.S. Collins, T.A. Manolio: Potential etiologic and functional implications of genome-wide association loci for human diseases and traits, Proc. Natl. Acad. Sci. USA 106(23), 9362–9367 (2009)CrossRefGoogle Scholar
  7. 33.7.
    The Congress of United States: S. 976 (110th): Genomics and Personalized Medicine Act of 2007 (2007)Google Scholar
  8. 33.8.
    V.N. Vapnik: Statistical Learning Theory (Wiley, New York 1998)MATHGoogle Scholar
  9. 33.9.
    N. Kasabov: Global, local and personalized modelling and pattern discovery in bioinformatics: An integrated approach, Pattern Recognit. Lett. 28(6), 673–685 (2007)CrossRefGoogle Scholar
  10. 33.10.
    T.J. Jorgensen: From blockbuster medicine to personalized medicine, Pers. Med. 5(1), 55–64 (2008)CrossRefGoogle Scholar
  11. 33.11.
    Q. Song, N. Kasabov: TWNFI – a transductive neuro-fuzzy inference system with weighted data normalization for personalized modeling, Neural Netw. 19(10), 1591–1596 (2006)MATHCrossRefGoogle Scholar
  12. 33.12.
    R. Solomonoff: A formal theory of inductive inference, part I, Inf. Control 7(1), 1–22 (1964)MATHMathSciNetCrossRefGoogle Scholar
  13. 33.13.
    R. Solomonoff: A formal theory of inductive inference, part II, Inf. Control 7(2), 224–254 (1964)MATHMathSciNetCrossRefGoogle Scholar
  14. 33.14.
    C. Bishop: Neural Networks for Pattern Recognition (Oxford Univ. Press, Cambridge 1995)MATHGoogle Scholar
  15. 33.15.
    D. Wu, K.P. Bennett, N. Cristianini, J. Shawe-Taylor: Large margin trees for induction and transduction, Proc. Sixteenth Int. Conf. Mach. Learn. (ICML) (Morgan Kaufmann, San Francisco 1999) pp. 474–483Google Scholar
  16. 33.16.
    N. Kasabov, S. Pang: Transductive support vector machines and applications in bioinformatics for promoter recognition, Proc. Int. Conf. Neural Netw. Signal Process. (IEEE Press, Bellingham 2004)Google Scholar
  17. 33.17.
    M. West, C. Blanchette, H. Dressman, E. Huang, S. Ishida, R. Spang, H. Zuzan, J.A. Olson, J.R. Marks, J.R. Nevins: Predicting the clinical status of human breast cancer by using gene expression profiles, Proc. Natl. Acad. Sci. USA 98(20), 11462–11467 (2001)CrossRefGoogle Scholar
  18. 33.18.
    Z. Bosnic, I. Kononenko, M. Robnik-Sikonja, M. Kukar: Evaluation of prediction reliability in regression using the transduction principle, EUROCON 2003. The IEEE Region 8, Vol. 2 (2003) pp. 99–103Google Scholar
  19. 33.19.
    M. Kukar: Transductive reliability estimation for medical diagnosis, Artif. Intell. Med. 29, 2003 (2002)Google Scholar
  20. 33.20.
    S. Pang, N. Kasabov: Inductive vs. transductive inference, global vs. local models: SVM, TSVM, and SVMT for gene expression classification problems, Neural Netw. 2004 IEEE Int. Joint Conf., Vol. 2 (2004) pp. 1197–1202Google Scholar
  21. 33.21.
    Q. Song, N. Kasabov: TWRBF: Transductive RBF neural network with weighted data normalization. In: Neural Information Processing, Lecture Notes in Computer Science, Vol. 3316, ed. by N. Pal, N. Kasabov, R. Mudi, S. Pal, S. Parui (Springer, Berlin, Heidelberg 2004) pp. 633–640CrossRefGoogle Scholar
  22. 33.22.
    N. Kasabov: Soft computing methods for global, local and personalised modeling and applications in bioinformatics. In: Soft Computing Based Modeling in Intelligent Systems, ed. by V.E. Balas, J. Fodor, A. Varkonyi-Koczy (Springer, Berlin, Heidelberg 2009) pp. 1–17CrossRefGoogle Scholar
  23. 33.23.
    U. Alon, N. Barkai, D.A. Notterman, K. Gish, S. Ybarra, D. Mack, A.J. Levine: Broad patterns of gene expression revealed by clustering analysis of tumor and normal colon tissues probed by oligonucleotide arrays, Proc. Natl. Acad. Sci. USA 96, 6745–6750 (1999)CrossRefGoogle Scholar
  24. 33.24.
    T. Furey, N. Cristianini, N. Duffy, D. Bednarski, M. Schummer, D. Haussler: Support vector machine classification and validation of cancer tissue samples using microarray expression data, Bioinformatics 16(10), 906–914 (2000)CrossRefGoogle Scholar
  25. 33.25.
    P. Dʼhaeseleer, S. Liang, R. Somogyi: Genetic network inference: from co-expression clustering to reverse engineering, Bioinformatics 16(8), 707–726 (2000)CrossRefGoogle Scholar
  26. 33.26.
    S. Lloyd: Least squares quantization in PCM, IEEE Trans. Inf. Theory 28(2), 129–137 (1982)MATHMathSciNetCrossRefGoogle Scholar
  27. 33.27.
    T. Kohonen: Self-organized formation of topologically correct feature maps, Biol. Cybern. 43, 59–69 (1982)MATHMathSciNetCrossRefGoogle Scholar
  28. 33.28.
    T. Graepel, M. Burger, K. Obermayer: Self-organizing maps: Generalizations and new optimization techniques, Neurocomputing 21, 173–190 (1998)MATHCrossRefGoogle Scholar
  29. 33.29.
    J.C. Bezdek: Pattern Recognition with Fuzzy Objective Function Algorithms (Kluwer Academic, Norwell 1982)MATHGoogle Scholar
  30. 33.30.
    A.V. Lukashin, R. Fuchs: Analysis of temporal gene expression profiles: clustering by simulated annealing and determining the optimal number of clusters, Bioinformatics 17(5), 405–414 (2001)CrossRefGoogle Scholar
  31. 33.31.
    N. Kasabov: Evolving connectionist systems. In: Methods and Applications in Bioinformatics, Brain Study and Intelligent Machines (Springer, London 2002)Google Scholar
  32. 33.32.
    N. Kasabov, Q. Song: Denfis: Dynamic evolving neural-fuzzy inference system and its application for time-series prediction, IEEE Trans. Fuzzy Syst. 10(2), 144–154 (2002)CrossRefGoogle Scholar
  33. 33.33.
    T. Mitchell, R. Keller, S. Kedar-Cabelli: Explanation-based generalization: A unifying view, Mach. Learn. 1(1), 47–80 (1986)Google Scholar
  34. 33.34.
    N. Kasabov, Y. Hu: Integrated optimisation method for personalised modelling and case studies for medical decision support, Int. J. Funct. Inform. Pers. Med. 3(3), 236–256 (2010)Google Scholar
  35. 33.35.
    L.J. vanʼt Veer, H. Dai, M.J. van de Vijver, Y.D. He, A.A.M. Hart, M. Mao, H.L. Peterse, K. van der Kooy, M.J. Marton, A.T. Witteveen, G.J. Schreiber, R.M. Kerkhoven, C. Roberts, P.S. Linsley, R. Bernards, S.H. Friend: Gene expression profiling predicts clinical outcome of breast cancer, Nature 415(6871), 530–536 (2002)CrossRefGoogle Scholar
  36. 33.36.
    Y. Hu, N. Kasabov: Coevolutionary method for gene selection and parameter optimization in microarray data analysis. In: Neural Information Processing, ed. by C.S. Leung, M. Lee, J.H. Chan (Springer, Berlin, Heidelberg 2009) pp. 483–492CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2014

Authors and Affiliations

  1. 1.Knowledge Engineering and Discovery Research InstituteAuckland University of TechnologyAucklandNew Zealand
  2. 2.KEDRI – Knowledge Engineering and Discovery Research InstituteAuckland University of TechnologyAucklandNew Zealand
  3. 3.School of Computing and Mathematical ScienceAuckland University of TechnologyAucklandNew Zealand

Personalised recommendations