Assess the utility of multi-omics (Cell Painting, transcriptomics, proteomics) for DILI prediction

Determine whether multi-omics datasets—including Cell Painting morphological profiles, gene expression measurements (e.g., L1000 or RNA-Seq), and proteomics profiles—can be used to predict drug-induced liver injury (DILI).

Background

Drug-induced liver injury (DILI) remains a critical challenge in drug safety assessment. Prior work combining proxy-DILI labels with chemical and pharmacokinetic features has improved detection accuracy and differentiated animal versus human DILI sensitivity, suggesting value in integrating diverse data modalities.

The authors specifically point out that it remains unresolved whether -omics datasets such as Cell Painting morphology, gene expression, and proteomics can be applied effectively for DILI prediction, highlighting this as a goal of the OASIS consortium and an important open question for future research.

References

Previously, combining proxy-DILI labels with chemical and pharmacokinetic features, achieving improved detection accuracy and differentiation between animal and human DILI sensitivity and it remains to be seen if -omics datasets such as Cell Painting, gene expression and proteomics data can be used for DILI prediction, which is one of the aims of the recently established OASIS consortium.119,120.

— A Decade in a Systematic Review: The Evolution and Impact of Cell Painting  (2405.02767 - Seal et al., 2024) in Section 5.9, Integrating Cell Painting, Transcriptomics, and Proteomics Data