United KingdomHealthcare and life sciences2026 – ongoingTangram Therapeutics
LLibra OS for drug-target assessment
Tangram reduced drug-target assessment from 1 quarter to a few hours using agentic AI
Problem
Tangram needed to evaluate disease-related targets for RNA interference medicines. Research depended on evidence scattered across biological datasets and documents.
Approach
Tangram and AWS Professional Services built LLibra OS for internal research. AI agents reviewed evidence, while graph neural networks scored target-indication pairs. Scientists contributed expertise to prompts and model design.
Results
Takeaway
Scientific expertise remained embedded in the prompts and scoring models used to assess potential targets.
Categories
- Size
- Small business
- Industry
- Healthcare and life sciences
- Business function
- IT and R&D
- Innovation type
- Process innovation
- AI technology
- Generative AIAI agentsPredictive analytics and ML
- Adoption
- Partner co-development
- Evidence
- Vendor case study
Sources
Source summaries
AWS described Tangram's internal AI research platform. It reported that assessing 4 to 5 target-indication propositions took a few hours instead of 1 quarter. The page carries no date; the Internet Archive first saved it on January 31, 2026.
Full details are in the original sources.
