Cancer Subtype Prediction Model

Cancer continues to be one of the most life-threatening diseases worldwide, with diagnosis and treatment often depending on the accurate identification of specific cancer subtypes. Conventional diagnostic techniques such as histopathology, imaging, and laboratory testing provide valuable insights but remain limited in scalability, speed, and precision. In recent years, the advent of machine learning and high-throughput genomic technologies has opened new opportunities for precision oncology. This research presents a Cancer Subtype Prediction Model that leverages RNA-Seq gene expression data along with supervised machine learning algorithms to classify five major cancer subtypes: Breast Invasive Carcinoma (BRCA), Colon Adenocarcinoma (COAD), Kidney Renal Clear Cell Carcinoma (KIRC), Lung Adenocarcinoma (LUAD), and Prostate Adenocarcinoma (PRAD). The model integrates preprocessing, feature selection, and classification pipelines to handle high-dimensional data, supported by robust visualization and web deployment using Flask. Experimental evaluation demonstrates accuracy above 85%, highlighting its effectiveness in clinical and research contexts. The system represents a step forward in personalized medicine, providing an accessible and scalable platform for oncologists and researchers.