A biotech built a cross-species knowledge graph on Polly KG and prioritized five targets in six months.
Siloed, non-model datasets could not be unified or queried for cross-species insight. Elucidata built an ETL pipeline and a production-scale Polly Knowledge Graph with natural-language querying and a transparent target-ranking framework. The page reports a graph of about 31M nodes and 60M relationships in six months, five prioritized targets and a PDE4 inhibitor repurposing opportunity.
Elucidata is a biomedical data company whose Polly platform harmonizes and curates omics and clinical data for AI-driven target discovery.
This sits in the Data Providers stage of the AI use-case lifecycle: Named examples from the real-world-data, claims and competitive-intelligence providers pharma AI systems are trained on, benchmarked against, or run inside of.
Published by Elucidata on its own site — read the original case study on elucidata.io ↗
Related use cases
- 01A diagnostics company used Polly to harmonize EHR, imaging and omics data for hospital-acquired sepsis products.
- 02An AI biotech processed bulk RNA-seq on a custom STAR pipeline on Polly for ML training data.
- 03A therapeutics company assessed AML differentiation targets with Polly and its knowledge graph.
- 04A pharma company used curated single-cell data on Polly to speed target identification in inflammatory disease.
- 05A core facility automated spatial metabolomics analysis with a Polly pipeline.
- 06How Bioventus evolved their commercial strategy with real world data and intelligence