Profiling of Mass Spectrometry Data for Ovarian Cancer Detection Using Negative Correlation Learning

This paper proposes a novel Mass Spectrometry data profiling method for ovarian cancer detection based on negative correlation learning (NCL). A modified Smoothed Nonlinear Energy Operator (SNEO) and correlation-based peak selection were applied to detected informative peaks for NCL to build a prediction model. In order to evaluate the performance of this novel method without bias, we employed randomization techniques by dividing the data set into testing set and training set to test the whole procedure for many times over. The classification performance of the proposed approach compared favorably with six machine learning algorithms.

[1]  Xuewu Zhang,et al.  Mass spectrometry-based "omics" technologies in cancer diagnostics. , 2007, Mass spectrometry reviews.

[2]  E. Petricoin,et al.  Use of proteomic patterns in serum to identify ovarian Cancer , 2002 .

[3]  Mark A. Hall,et al.  Correlation-based Feature Selection for Machine Learning , 2003 .

[4]  Xiaoli Li,et al.  Profiling of High-Throughput Mass Spectrometry Data for Ovarian Cancer Detection , 2007, IDEAL.

[5]  R. Tibshirani,et al.  Diagnosis of multiple cancer types by shrunken centroids of gene expression , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[6]  Claudio Cobelli,et al.  Ovarian cancer identification based on dimensionality reduction for high-throughput mass spectrometry data , 2005, Bioinform..

[7]  Huanhuan Chen,et al.  Evolutionary random neural ensembles based on negative correlation learning , 2007, 2007 IEEE Congress on Evolutionary Computation.

[8]  V. Zurawski,et al.  Elevated serum CA 125 levels prior to diagnosis of ovarian neoplasia: Relevance for early detection of ovarian cancer , 1988, International journal of cancer.

[9]  Xin Yao,et al.  Ensemble learning via negative correlation , 1999, Neural Networks.

[10]  S. Mukhopadhyay,et al.  A new interpretation of nonlinear energy operator and its efficacy in spike detection , 1998, IEEE Transactions on Biomedical Engineering.

[11]  Lars Kai Hansen,et al.  Neural Network Ensembles , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  E. Petricoin,et al.  High-resolution serum proteomic features for ovarian cancer detection. , 2004, Endocrine-related cancer.

[13]  Neal O. Jeffries,et al.  Performance of a genetic algorithm for mass spectrometry proteomics , 2004, BMC Bioinformatics.

[14]  Xin Yao,et al.  Evolutionary ensembles with negative correlation learning , 2000, IEEE Trans. Evol. Comput..

[15]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[16]  Peter Tiño,et al.  Managing Diversity in Regression Ensembles , 2005, J. Mach. Learn. Res..

[17]  Yang Li,et al.  Analysis of Tiling Microarray Data by Learning Vector Quantization and Relevance Learning , 2007, IDEAL.

[18]  Xin Yao,et al.  Simultaneous training of negatively correlated neural networks in an ensemble , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[19]  Xin Yao,et al.  A constructive algorithm for training cooperative neural network ensembles , 2003, IEEE Trans. Neural Networks.

[20]  César Hervás-Martínez,et al.  Cooperative coevolution of artificial neural network ensembles for pattern classification , 2005, IEEE Transactions on Evolutionary Computation.

[21]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.