Artificial Intelligence-Driven Multi-Omics Approaches in Glioblastoma

Abstract

Glioblastoma (GBM) is the most common and aggressive primary brain tumor in adults. It is characterized by a high degree of heterogeneity, meaning that although these tumors may appear morphologically similar, they often exhibit distinct clinical outcomes. By associating specific molecular fingerprints with different clinical behaviors, high-throughput omics technologies (e.g., genomics, transcriptomics, and epigenomics) have significantly advanced our understanding of GBM, particularly of its extensive heterogeneity, by proposing a molecular classification for the implementation of precision medicine. However, due to the vast volume and complexity of data, the integrative analysis of omics data demands substantial computational power for processing, analyzing and interpreting GBM-related data. Artificial intelligence (AI), which mainly includes machine learning (ML) and deep learning (DL) computational approaches, now presents a unique opportunity to infer valuable biological insights from omics data and enhance the clinical management of GBM. In this review, we explored the potential of integrating multi-omics, imaging radiomics and clinical data with AI to uncover different aspects of GBM (molecular profiling, prognosis, and treatment) and improve its clinical management.

Keywords: artificial intelligence; deep learning; glioblastoma; machine learning; molecular classification; omics data; personalized medicine.

Figure 1

Applications of multi-modal data integration strategies and artificial intelligence for GBM precision medicine. This figure illustrates an AI-driven pipeline for personalized GBM interventions that leverages individual patient data to molecularly characterize and subtype GBM samples, predict clinical evolution and treatment sensitivity, and support personalized therapeutic strategies. AI-based data integration tools can combine multiple omics layers (such as genomics, epigenomics, transcriptomics) with clinical, histopathology and medical imaging data, allowing platforms to present a unified view of biological processes, evaluate interrelationships, identify patterns, and detect significant molecular changes across conditions. Beyond providing biological insights, these computational frameworks demonstrate high accuracy and sensitivity in predicting disease outcomes, identifying biomarkers, and supporting tailored treatment strategies through the integration of large-scale omics data.

Figure 2

A hierarchical representation of the most representative artificial intelligence, machine and deep learning algorithms. Machine Learning (ML) is a main subset of Artificial Intelligence (AI), and its diverse methodologies can be classified into four principal branches: Supervised Learning, Unsupervised Learning, Semi-supervised Learning and Reinforcement Learning. The image above provides a schematic representation of these branches and their associated sub-branches, offering a concise overview of the landscape of ML. Supervised Learning involves classification and regression, where models are trained with labeled data. Unsupervised Learning focuses on clustering, association and dimensionality reduction to find patterns in unlabeled data. Semi-supervised algorithms utilize a combination of both labeled and unlabeled data to enhance ML task performance, as well as reinforcement learning, which improves model performance through interaction with the environment. Deep Learning (DL) is a specific type of ML that uses complex Artificial Neural Networks (ANNs). Each of these branches employs various techniques and algorithms tailored to specific types of data and problem domains.