A Comparative Analysis of Machine Learning Models for Cancer Types Classification Using RNA-Seq Gene Expression Data

Abstract

Cancer is a significant global health concern, and scientists must set the right tumor identifier for accurate diagnosis and personalized treatment plans. While RNA-Seq gene expression data provides critical molecular information, it has two major challenges that can affect ML systems and hinder their performance: its large dimensionality and a propensity for class imbalance. This study offers a comprehensive and data-driven comparison of five machine learning classifiers that demonstrate superior performances in multi-class cancer diagnosis using the RNA-Seq-based TCGA dataset with Random Forest, Support Vector Machine (SVM), and Gradient Boosting k-Nearest Neighbors (k-NN) and Multilayer Perceptron (MLP). Mutual information was used to select important features that reduce the dimensions of the data, and then sensitivity analysis showed the successful performance of the method. To overcome these class imbalance problems, the Synthetic Minority Over-sampling Technique (SMOTE) method was used. The model performance was evaluated using a comprehensive testing framework that integrated 5-fold cross-validation with several evaluation metrics such as balanced accuracy, precision, recall, and F1-score, and confusion matrices and ROC curves. The research group performed ablation studies to better understand the individual effects of correct feature selection and SMOTE on their process. These outcomes show that the MLP classifier reached the highest balanced accuracy (0.9917) after resolving methodological avarice. The assessment demonstrates that SMOTE has a significant impact on improving classification results of minority classes due to its positive effects on recall and F1 score metrics. This study provides insights into selected gene features associated with known oncogenic pathways and, therefore, advanced biological interpretations per se of the obtained results. The work develops a framework that is reproducible and allows multi-metric evaluation of ML-based cancer classification, but exposes two key issues leading to data leakage and validation failures. Our research shows how the promise of AI-driven precision medicine can help build approaches to automated and accurate cancer typing.