Abstract

Gene expression datasets used for cancer analysis are frequently high- dimensional and complex, making accurate bracketing delicate. This work presents a harmonious machine learning technique for classification of cancer types using multiple reference gene expression datasets, including leukaemia, DLBCL, brain, breast cancer, Golub, and colon cancer. Originally, the datasets are pre-processed using standard point scaling to reduce variations in gene expression values. To address the dimensionality problem, KPCA with a RBF is employed to extract applicable nonlinear features. Latterly, the class markers are converted to a numerical format, and Min-Max normalization is used for enhancing learning effectiveness. The reused data is divided for training and testing the sets, and a feedforward deep neural network is trained for cancer prediction. The model’s performance is estimated using bracket delicacy. The experimental results demonstrate the proposed frame effectively handles high-dimensional gene expression data and achieves harmonious bracket performance across five cancer datasets.

References

• B. Schölkopf, A. Smola, and K.-R. Müller, “Nonlinear component analysis as a kernel eigenvalue problem,” Neural Computation, vol. 10, no. 5, pp. 1299–1319, 1998.
• S. Mika, G. Rätsch, J. Weston, B. Schölkopf, and K.-R. Müller, “Fisher discriminant analysis with kernels,” in Proc. IEEE Neural Networks for Signal Processing, 1999.
• C. M. Bishop, Pattern Recognition and Machine Learning. New York, NY, USA: Springer, 2006.
• T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning. New York, NY, USA: Springer, 2009.
• T. R. Golub et al., “Molecular classification of cancer: Class discovery and class prediction by gene expression monitoring,” Science, vol. 286, no. 5439, pp. 531–537, 1999.
• A. A. Alizadeh et al., “Distinct types of diffuse large B-cell lymphoma identified by gene expression profiling,” Nature, vol. 403, pp. 503–511, 2000.
• D. Singh et al., “Gene expression correlates of clinical prostate cancer behavior,” Cancer Cell, vol. 1, no. 2, pp. 203–209, 2002.
• S. Ramaswamy et al., “Multiclass cancer diagnosis using tumor gene expression signatures,” PNAS, vol. 98, no. 26, pp. 15149–15154, 2001.
• C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, no. 3, pp. 273–297, 1995.
• N. Cristianini and J. Shawe-Taylor, An Introduction to Support Vector Machines. Cambridge, U.K.: Cambridge Univ. Press, 2000.
• I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.
• S. Haykin, Neural Networks and Learning Machines, 3rd ed. Upper Saddle River, NJ, USA: Pearson, 2009.
• I. Guyon et al., “Gene selection for cancer classification using support vector machines,” Machine Learning, vol. 46, pp. 389–422, 2002.
• C. Ding and X. He, “K-means clustering via principal component analysis,” in Proc. ICML, 2004.
• I. T. Jolliffe, Principal Component Analysis. New York, NY, USA: Springer, 2002.
• M. P. S. Brown et al., “Knowledge-based analysis of microarray gene expression data,” PNAS, vol. 97, no. 1, pp. 262–267, 2000.
• D. K. Slonim, “From patterns to pathways: Gene expression data analysis comes of age,” Nature Genetics, vol. 32, pp. 502–508, 2002.
• J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques. Burlington, MA, USA: Morgan Kaufmann, 2011.
• P.-N. Tan, M. Steinbach, and V. Kumar, Introduction to Data Mining. Boston, MA, USA: Pearson, 2006.
• K. P. Murphy, Machine Learning: A Probabilistic Perspective. Cambridge, MA, USA: MIT Press, 2012.