TY  - EJOU
AU  - Albaradei, Somayah 

TI  - AI-Driven Approaches to Utilization of Multi-Omics Data for Personalized Diagnosis and Treatment of Cancer: A Comprehensive Review
T2  - Computer Modeling in Engineering \& Sciences

PY  - 2025
VL  - 145
IS  - 3
SN  - 1526-1506

AB  - Cancer deaths and new cases worldwide are projected to rise by 47% by 2040, with transitioning countries experiencing an even higher increase of up to 95%. Tumor severity is profoundly influenced by the timing, accuracy, and stage of diagnosis, which directly impacts clinical decision-making. Various biological entities, including genes, proteins, mRNAs, miRNAs, and metabolites, contribute to cancer development. The emergence of multi-omics technologies has transformed cancer research by revealing molecular alterations across multiple biological layers. This integrative approach supports the notion that cancer is fundamentally driven by such alterations, enabling the discovery of molecular signatures for precision oncology. This review explores the role of AI-driven multi-omics analyses in cancer medicine, emphasizing their potential to identify novel biomarkers and therapeutic targets, enhance understanding of Tumor biology, and address integration challenges in clinical workflows. Network biology analyzes identified ERBB2, KRAS, and TP53 as top hub genes in lung cancer based on Maximal Clique Centrality (MCC) scores. In contrast, TP53, ERBB2, ESR1, MYC, and BRCA1 emerged as central regulators in breast cancer, linked to cell proliferation, hormonal signaling, and genomic stability. The review also discusses how specific Artificial Intelligence (AI) algorithms can streamline the integration of heterogeneous datasets, facilitate the interpretation of the tumor microenvironment, and support data-driven clinical strategies.
KW  - Artificial intelligence (AI); machine learning algorithms; multi-omics approaches; protein-protein interactions (PPIs) networking

DO  - 10.32604/cmes.2025.072584