Advances in multimodal data integration for drug efficacy prediction: Methodological evolution and clinical translation.

M²DDI: A Unified Framework for Dynamic Multimodal Fusion in Drug-Drug Interaction Prediction

Empirical evaluation and robustness experiments show that M2DDI maintains high predictive accuracy even when modality-specific information is partially missing, outperforming existing methods under similar conditions and establish M2DDI as an effective and mechanism-aware solution for comprehensive DDI prediction.

Optimizing Cancer Drug Treatments Using Big Data Integration of Genomic and Clinical Data for Personalized Medicine.

Personalized cancer care depends on the seamless integration of genetic profiles, medical histories, and continuous patient monitoring to optimize therapeutic outcomes. Current clinical strategies struggle to combine these disparate, highly heterogeneous data streams, frequently resulting in incomplete diagnostic evaluations and suboptimal treatment selections. Factors such as poor cross-platform compatibility, low prediction precision, and the omission of real-time clinical parameters limit the practical deployment of precision medicine. To address these limitations, this study introduces BigCancerNet (BCN), a robust big data framework that merges multi-source information and uses a Graph Neural Network for Cancer Treatment Optimization (GNN-CTO) to accurately forecast individual drug responses and patient survival trajectories. This initiative is driven by the aspiration to boost treatment success, reduce toxic side effects, and permit flexible, patient-centric therapeutic adaptations. The processing pipeline comprises collecting genomic, clinical, and real-time biometric data from numerous repositories, including The Cancer Genome Atlas (TCGA), Gene Expression Omnibus (GEO), Cancer Dependency Map (DepMap), and hospital Electronic Health Records (EHRs). Data preprocessing applies Deep Embedding Networks (D2EN) to regularize genomic sequences, handle missing values, and standardize clinical features. The Hybrid Multi-Omics Fusion Algorithm (HMOFA) integrates these diverse datasets, harmonizing genomic, clinical, and wearable information while minimizing batch effects. The GNN-CTO model captures complex, nonlinear relationships among mutations, clinical factors, and drug responses, while Real-Time Model Adaptation with Dynamic Feedback Loop (RT-MADFL) continuously updates predictions. Results demonstrate reduced RMSE (0.160-0.245) and MAE (0.110-0.180), high stability with fold accuracy variance below 0.3%, fast training (12-15s per epoch), and prediction metrics exceeding 91%. Future work includes expanding to multi-cancer cohorts and integrating explainable AI to support transparent clinical decision-making.

AI-driven drug discovery and personalized medicine: integrating quantum computing and next-generation technologies

Advances in Multimodal Deep Learning for Drug Repurposing

Computational drug repurposing increasingly integrates chemical, biological, omics, network, text, and clinical data through deep learning. This structured narrative review examines how such modalities are encoded, aligned, and fused. We organize representative studies into four mechanism-centered families: heterogeneous-graph neural networks, multimodal knowledge-graph embeddings, pretrained language/sequence model-based cross-modal alignment, and multi-view or reconstruction-based fusion. Direct drug–disease association and repurposing studies form the core evidence; drug–target interaction, drug–drug interaction, target-identification, molecular-pretraining, and drug–microbe studies are treated as adjacent methodological evidence. We compare architectures, evaluation settings, failure modes, and evidence levels across oncology, neurology, infectious, and rare diseases. Practical guidance covers leakage-aware random, cold-start, temporal, and cluster-based evaluation; an actionable reproducibility checklist; and a scenario-based model-selection framework. We distinguish computational prioritization, docking, preclinical, retrospective clinical, and prospective evidence, and examine data sparsity, uncertain negatives, missing or noisy modalities, interpretability, and translational limitations. Future priorities include temporal and causal evaluation, external and multi-center validation, federated learning, and emerging therapeutic modalities. Multimodal fusion can improve complementary representation, but its value depends on task definition, data quality, evaluation design, and independent validation.

Digital Twins in Oncology: From Multimodal Data Integration to Precision Clinical Practice

Abstract Oncology digital twins are patient-specific computational models that are built by combining electronic health records, multiomics genomic data, and diagnostic imaging to simulate individual tumor biology and predict multiple treatment-related outcomes. Conceptually originated from aerospace engineering, it has matured clinically through convergent advances in radiomics, mechanistic tumor modeling, pharmacokinetic- pharmacodynamic systems, federated machine learning, and, most recently, large language model (LLM)-based clinical interfaces and agentic artificial intelligence (AI). For a practicing radiologist, digital twins offer a transformative role: imaging-derived quantitative features serve as the primary data, positioning diagnostic imaging at the center of these personalized oncology workflows. Key clinical applications especially in oncology span from chemotherapy response prediction, immunotherapy patient selection, personalized radiation planning, tumor progression modeling, and treatment toxicity forecasting. Several of these applications are achievable with current technology without any significant infrastructure investment. Substantial challenges include imaging data standards, absence of prospective validation, algorithmic bias in underrepresented populations, and regulatory uncertainty for continuously self-updating AI. This narrative review provides radiologists with a balanced, comprehensive overview of digital twin architecture, advanced enabling technologies, current clinical evidence, a practical roadmap for implementation, and a candid appraisal of barriers to adoption.

Artificial intelligence (AI) as a catalyst for mechanistic target discovery: Integrating systems pharmacology and multimodal data.

It is demonstrated that this AI-driven paradigm is essential for advancing precision medicine, as it systematically translates vast and heterogeneous datasets into testable mechanistic hypotheses, and accelerates the development of safer, more effective and patient-specific therapies.