Enhanced Cancer Subclassification Using Multi-Omics Clustering and Quantum Cat Swarm Optimization

Integrating multiple omics data can significantly improve the accuracy of cancer subclassification, achallenging task due to the high dimensionality and limited sample sizes. The integration of these data sets canenhance model performance. This study addresses these challenges by employing Quantum Cat SwarmOptimization (QCSO) for feature selection, along with K-means clustering and Support Vector Machine (SVM) forclassification. Using QCSO, the most significant features were identified, resulting in an increase in accuracy from81% to 100%. Performance was evaluated using accuracy, F1-score, precision, recall, ROC, and the silhouettemetric, all of which confirmed the effectiveness of the feature selection approach. Additionally, this methodenhances the classification of samples while making the models more interpretable, providing better insights intothe molecular mechanisms of cancer. This work contributes to advancing knowledge in the field of cancer researchand biology in general.