Integrative analysis of RNA expression data unveils distinct cancer types through machine learning techniques - Saudi Journal of Biological Sciences article

Aug 3, 2026

Cancer is a complex, heterogeneous disease and conventional classification relying on histopathology often limits personalized prognosis and therapy planning. This study performs an integrative analysis of RNA sequencing data from five cancer types (BRCA, KIRC, COAD, LUAD, PRAD) using a machine learning pipeline: dataset identification, normalization, feature selection, dimensionality reduction, clustering, and classification. Unsupervised k-means clustering separates samples into five clusters that strongly correlate with known cancer types. It further reports high predictive accuracy with Wide Neural Network (99.834% validation; 99.995% testing), supporting machine-learning-driven molecular subtyping from transcriptomic signatures.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages20

Reading Time50 min

AccessFree to download

Introduction

Motivation and global cancer burden

Materials and methods

Integrative RNA-seq analysis pipeline

Clustering and classification strategy

Results

Cluster correspondence to known cancer types

Model performance and accuracy

Conclusion

[Short title + Author Name-P&H title] 31 (2024) 103918 Contents lists available at ScienceDirect Saudi Journal of Biological Sciences journal [homepage: www.sciencedirect.com](homepage: www.sciencedirect.com) | Original article
Integrative analysis of RNA expression data unveils distinct cancer types through machine learning techniques | | | | | --- | --- | --- | --- | | Saad Awadh Alanazia, *, Nasser Alshammaria, Maddalah Alruwailib, Kashaf Junaid c, Muhammad Rizwan Abidd, Fahad Ahmad e
a Department of Computer Science, College of Computer and Information Sciences, Jouf University, Sakaka, Aljouf 72341, Saudi Arabia b Department of Computer Engineering and Networks, College of Computer and Information Sciences, Jouf University, Sakaka 72341, Saudi Arabia c School of Biological and Behavioural Sciences, Queen Mary University of London, London E1 4NS, United Kingdom
d Department of Computer Science, Florida Polytechnic University, Lakeland, FL 33805, United States e Department of Basic Sciences, Common First Year, Jouf University, Sakaka 72341, Saudi Arabia | | | | | A R T I C L E I N F O | | A B S T R A C T | | | Keywords:
Gene
RNA expression, cancer Tumour, diagnosis Machine learning Clustering
Classification | | Cancer is a highly complex and heterogeneous disease. Traditional methods of cancer classification based on histopathology have limitations in guiding personalized prognosis and therapy. Gene expression profiling provides a powerful approach to unraveling molecular intricacies and better-stratifying cancer subtypes. In this study, we performed an integrative analysis of RNA sequencing data from five cancer types-BRCA, KIRC, COAD, LUAD, and PRAD. A machine learning workflow consisting of dataset identification, normalization, feature selection, dimensionality reduction, clustering, and classification was implemented. The k-means algorithm was applied to categorize samples into distinct clusters based solely on gene expression patterns. Five unique clusters emerged from the unsupervised machine learning based analysis, significantly correlating with the known cancer types. BRCA aligned predominantly with one cluster, while COAD spanned three clusters. KIRC was represented within two main clusters. LUAD is associated strongly with a single cluster and PRAD with another cluster. This demonstrates the ability of machine learning approaches to unravel complex signatures within transcriptomic profiles that can delineate cancer subtypes. The proposed study highlights the potential of integrative analytics to derive meaningful biological insights from high-dimensional omics datasets. Molecular subtyping through machine learning clustering enhances our understanding of the intrinsic heterogeneities and pathways dysregulated in different cancers. Overall, this study exemplifies a powerful computational framework to classify gene expressions of patients having different types of cancers and guide personalized therapeutic decisions. Finally, Wide Neural Network demonstrates a significantly higher accuracy, achieving 99.834% on the validation set and an even more impressive 99.995% on the test set. | | 1. Introduction Cancer is a highly prevalent and profoundly impactful global disease that affects people across the world. According to the World Health Organization Global Cancer Report, it is projected that the global incidence of cancer will increase by a significant 57 % over the next two decades. This disease, characterized by pathological disruptions in the natural process of cellular division, is responsible for a substantial global mortality rate. In 2020 alone, there were more than 19.3 million newly diagnosed cancer cases, resulting in an estimated 10 million fatalities, as reported by the Global Cancer Report (Arslan et al., 2022). Cancer imposes a significant healthcare burden, affecting not only individuals diagnosed with the disease but also their families and the healthcare sys

FAQs

What is the main goal of the study on RNA expression data?

The study aims to use machine learning to uncover distinct cancer types by analyzing transcriptomic (RNA sequencing) profiles and deriving molecular subtypes.

Which cancer types are included in the integrative analysis?

The analysis includes five cancer types: BRCA, KIRC, COAD, LUAD, and PRAD.

How does the study determine distinct cancer subtypes from gene expression?

It applies an unsupervised k-means approach to cluster samples based solely on gene expression patterns, producing five clusters that correlate with the known cancer types.

Aug 3, 2026

Upload by Theodore