Accelerating cancer research and personalized medicine by tie-up with AI empowered genomics and proteomics.

BACKGROUND: Artificial intelligence (AI) driven novel technique in genomics and proteomics have revolutionized cancer research with comprehensive analysis of complex molecular datasets. However, multiple challenges linked to data heterogeneity and large-scale integration requires advanced computational frameworks. METHODS: AI-based advanced methodologies such as machine learning (ML) and deep learning (DL) models, are utilized to analyze multi-omics datasets enclosing gene expression patterns, chromosomal variants, protein expression profiles, post-translational modifications, and interaction in protein networks. Integrated analytical advances, including liquid biopsy analysis and transfer learning, are explored to enhance data interpretation and predictive modeling. RESULTS: AI models along with the patients specific digital framework enables dynamic prediction of cancer and its treatment helping real-time disease monitoring precisely and with better optimized clinical decision making. Recent advances such as digital twin model, multi-omics framework, Graph neural network (GNN) and generative AI helps in mechanistic insights of oncology along with AI driven modality such as whole genome sequence, RNA-seq, proteomic profile and liquid biopsy. Moreover the integration of single-cell and multi-omics data with digital pathology, radio genomic and adaptive longitudinal AI model jells the real time analysis of cancer and predict risk stratification with dynamic optimisation of treatment plans for cancer CONCLUSION: The integration of AI at the genomics and proteomics level provides a robust framework for linking molecular modification in specific cancers, advancing precision oncology. These innovations enable personalized treatment strategies, improved biomarker discovery, and a deeper understanding of cancer biology, ultimately contributing to enhanced patient outcomes.