An Efficient High Dimensional Gene Expression BasedMulti-Class Cancer Prediction Model using EnsembleLearning
Keywords:
Tumor-Educated Platelets, Principal Component Analysis, Ensemble Learning, Non-invasive cancer detection, Cross ValidationAbstract
Cancer continues to be a predominant worldwide health concern, and early, non-invasive identification significantly improves survival rates and treatment results. Conventional diagnostic techniques, including tissue biopsies and imaging, are often invasive, costly, and time-consuming. Recent improvements in next-generation sequencing facilitate the examination of gene expression data at the molecular level. Nevertheless, this data is high-dimensional and noisy, making manual analysis impossible. This paper presents a machine learning framework for multi-class cancer categorization using Tumor-Educated Platelet (TEP) gene expression data. The dataset undergoes preprocessing using normalization, feature selection, and Principal Component Analysis (PCA) to reduce data dimensionality. Several supervised models, including Support Vector Machine (SVM), Random Forest, Logistic Regression, and XGBoost, were trained and refined by cross validation. The performance is assessed using accuracy, precision, recall, F1-score, and ROC-AUC metrics. Experimental findings demonstrate that ensemble models, notably
Random Forest and XGBoost, surpass other classifiers in managing high-dimensional biological data. The finished model is then deployed via a web-based application for real-time, user-friendly cancer prediction. This study presents a scalable and noninvasive method for precise cancer categorization that facilitates future clinical decision-making systems.
References
[1] Kourou, K., Exarchos, T.P., Exarchos, K.P., Karamouzis, M.V., Fotiadis, D.I.: Machine learning applications in cancer prognosis and prediction. Computational and Structural Biotechnology Journal 13, 8–17 (2015)
[2] Angermueller, M., P”arnamaa, T., Parts, L., Stegle, O.: Deep learning for computational biology. Molecular Systems Biology 12(7) (2016)
[3] Zhang, Z., Xiao, Y., Luo, L.: Deep neural networks for multi-class cancer classification using rna-seq data. Journal of Biomedical Informatics 89, 1–10 (2019)
[4] Best, M.G., Sol, N., Kooi, I., et al.: Rna-seq of tumor-educated platelets enables blood-based pan cancer, multiclass, and molecular pathway cancer diagnostics. Cancer Cell 28(5), 666–676 (2015)
[5] Nilsson, R.J.A., Balaj, L., Hulleman, M.N., et al.: Blood platelets contain tumor-derived rna biomarkers. Blood 118(13), 3680–3683 (2011)
[6] Hira, Z., Gillies, D.F.: A review of feature selection and feature extraction methods applied on microarray data. Advances in Bioinformatics 2015, 198363 (2015)
[7] Ahn, J., Lee, Y., Park, S.: Principal component analysis for rna-seq data classification. BMC Bioinformatics 14(Suppl. 5) (2013)
[8] Li, X., Wang, Y., Zhang, J.: Ensemble learning for multi-class cancer classification based on gene expression. Bioinformatics 34(21), 3755–3762 (2018)
[9] Lyu, B., Haque, A.: Deep learning based tumor type classification using gene expression data. Scientific Reports 8, 10301 (2018)
[10] Esteva, A., Kuprel, B., Novoa, R.A., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115–118 (2017)