Advances in bridging computational and clinical outcomes in brain tumour therapy by leveraging artificial intelligence and machine learning

Brain tumours represent a significant therapeutic challenge due to their high complexity, aggressive nature, and protective obstacle posed by the blood-brain barrier (BBB). Among these, GBM emerges as the most aggressive and treatment-resistant variety of brain tumours. With current therapies, limitations arise while combating rapid progression and tumour heterogeneity coupled with poor drug delivery across the BBB. This review demonstrates how the confluence of drug discovery, together with the recent advancement of computer-aided drug design (CADD), artificial intelligence (AI), and machine learning (ML), is revolutionizing the discovery and therapeutic approach towards brain tumours, especially Glioblastoma Multiforme (GBM). Our work systematically examines CADD methodologies that enable accelerated discovery of therapeutic compounds, optimization of drug-target interactions, and enhanced BBB permeability. Particular focus in this review is placed on the AI and ML contributions to refining predictive models for drug efficacy and BBB penetration so that highly targeted, personalized therapies are developed. This review also covers a few unique challenges specific to GBM, how the tumour microenvironment influences resistance, how multi-targeted approaches would be critical, and the discussion of combination therapies. This review offers a comprehensive synthesis of recent advances integrating AI/ML, CADD, and network pharmacology for GBM therapy an interdisciplinary perspective that is still emerging in current literature. By highlighting recent successes and outlining promising directions, this review underscores the potential of CADD, AI, and ML to revolutionize brain tumour therapy, offering hope for improved outcomes in treating one of the most challenging cancers.