- Identify underlying molecular characteristics and signature of genes linked to disease state.
- Learn from diverse data: multi-omics and/or clinical data to identify new pathways and markers that lead to new therapeutic targets.
- Assess druggability of targets by learning from existing and failed drug targets structure and property data.
- Use pathways data sources (GO, KEGG, Panther, MSigDB etc.) to uncover MOA and enriched terms.
- Networks to identify combination therapies.
- Predict patient's response to drug to distinguish responders and non-responders.
- Machine learning for clinical trial patient selection and stratification/classification.
AI & QSP
Identifying parameter regimes for virtual patients, combining network-based reasoning with quantitative models of biology.
Network analysis and ML/AI approaches on integrated biological, pharmalogical and clinical data to identify new therapeutic uses for a drug or target.