Applying omic data analytics with real world evidence to predict personalised drug response
09 Sept 2026
Drug Response Prediction
- How can multi-omic data — including genomics, transcriptomics, proteomics, single-cell data, and functional assay data — be used more effectively to uncover disease biology and identify actionable therapeutic hypotheses?
- What are the biggest challenges in connecting omic signatures to true drug response biology, rather than simply identifying statistical correlations?
- How can AI and machine learning help integrate omic data with real-world patient data to better understand disease heterogeneity and define patient subpopulations most likely to respond to a therapeutic mechanism？
- How should discovery teams build a learning loop between computational prediction, wet-lab experiments, translational biomarkers, and real-world evidence so that AI models continuously improve and remain biologically meaningful?
- How should biopharma organizations build the right data infrastructure, governance, and cross-functional collaboration model to turn omic analytics and RWE into actionable evidence for drug discovery and development?
