Using ABC Algorithm with Shrinkage Estimator to Identify Biomarkers of Ovarian Cancer from Mass Spectrometry Analysis
Biomarker discovery through mass spectrometry analysis has continuously intrigued researchers from various fields such as analytical researchers, computer scientists and mathematicians. The uniqueness of this study relies on the ability of the proteomic patterns to detect particular disease especially at the early stage. However, identification through high-throughput mass spectrometry analysis raises some challenges. Typically, it suffers from high dimensionality of data with tens of thousands attributes and high level of redundancy and noises. Hence this study will focus on two stages of mass spectrometry pipelines; firstly we propose shrinkage estimation of covariance to evaluate the discriminant characteristics among peaks of mass spectrometry data for feature extraction; secondly a sophisticated computational technique that mimic survival and natural processing which is called as Artificial Bee Colony (ABC) as feature selection is integrated with linear SVM classifier for this biomarker discovery analysis. The proposed method is tested with real-world ovarian cancer dataset to evaluate the discrimination power, accuracy, sensitivity and also specificity.
Keywordsmetaheuristic feature selection swarm algorithm bio-inspired algorithm classification feature extraction
Unable to display preview. Download preview PDF.
- 1.Armananzas, R., Saeys, Y., Inza, I., Garcia-Torres, M., Bielza, C., Van de Peer, Y., Larranaga, P.: Peakbin selection in mass spectrometry data using a consensus approach with estimation of distribution algorithms. IEEE/ACM Transactions on Computational Biology and Bioinformatics 8(3), 760–774 (2011)CrossRefGoogle Scholar
- 2.Celik, M., Karaboga, D., Koylu, F.: Artificial bee colony data miner (abc-miner). pp. 96–100. IEEE (2011)Google Scholar
- 4.Coombes, K.R., Tsavachidis, S., Morris, J.S., Baggerly, K.A., Hung, M.C., Kuerer, H.M.: Improved peak detection and quantification of mass spectrometry data acquired from surface-enhanced laser desorption and ionization by denoising spectra with the undecimated discrete wavelet transform. Proteomics 5(16), 4107–4117 (2005)CrossRefGoogle Scholar
- 6.He, Z., Yu, W.: Stable feature selection for biomarker discovery. arXiv preprint arXiv:1001.0887 (2010)Google Scholar
- 7.James, W., Stein, C.: Estimation with quadratic loss. In: Proceedings of the Fourth Berkeley Symposium on Mathematical Statistics and Probability, vol. 1, pp. 361–379 (1961)Google Scholar
- 8.Karaboga, D.: An idea based on honey bee swarm for numerical optimization. Techn. Rep. TR06, Erciyes Univ. Press, Erciyes (2005)Google Scholar
- 13.Massart, D.L., Smeyers-Verbeke, A.J.: Practical Data Handling Visual Presentation of Data by Means of Box Plots (2005)Google Scholar
- 16.Sanavia, T., Aiolli, F., Da San Martino, G., Bisognin, A., Di Camillo, B.: Improving biomarker list stability by integration of biological knowledge in the learning process. BMC Bioinformatics 13(suppl. 4), S22 (2012)Google Scholar
- 18.SyarifahAdilah, M., Abdullah, R., Venkat, I.: Abc algorithm as feature selection for biomarker discovery in mass spectrometry analysis. In: 2012 4th Conference on Data Mining and Optimization (DMO), pp. 67–72. IEEE (2012)Google Scholar