Mission
Axiom provides frontier intelligence for human drug toxicity, helping scientists reduce unexpected toxicity earlier and develop safer medicines with less animal testing.
Mission
90% of drug candidates fail in clinical development because preclinical tests do not reliably predict human outcomes.
Mission
Reducing failure rates by helping scientists and drug hunters develop safer, better medicines.
Mission
Who we serve
Dominique Bonafoux
VP of Small Molecule Chemistry
Novo Nordisk
"I want to develop medicines safe enough that I would give them to my own family without hesitation. That, to me, is the standard we should hold ourselves to in drug discovery: not simply advancing compounds that show promise, but building the evidence and confidence that they are truly safe for patients in the real world. This remains an immense challenges which existing approaches have been unable to solve."
LinkedIn
Nicholas Meanwell
VP of Medicinal Chemistry
BMS
"Despite advances in screening methods, biochemical understanding and a broader awareness of toxicophores, toxicity persists as one of the main causes of drug attrition both preclinically and clinically with hepatotoxicity a particularly difficult challenge. There remains a pressing need for better tools to predict toxicity and a deeper understanding of the underlying mechanisms."
LinkedIn
Yvonne Will
Founder
SCIENTIA Consultants
"Early safety decisions often fail not due to lack of data, but lack of decision-ready insight. Platforms like Axiom shift the focus from binary hazard flags to mechanistic, exposure-aware risk understanding. This enables teams to distinguish manageable signals from true liabilities—earlier in discovery, when it matters most. The result: better compound selection, fewer late-stage surprises, and more confident decisions."
LinkedInAxiom's Digest
Learn more about our work
03/2026 Technical Summary
03/2026 Technical Report
A Better Proxy Than the Rat and Dog
Using AI to Combine Exposure, Metabolism, and Liver Function to Model DILI in Modern Molecules
Cell Painting for cytotoxicity and mode-of-action analysis in primary human hepatocytes
Counting cells can accurately predict small-molecule bioactivity benchmarks
Modeling and Interpreting Multiple Readouts for Clinical Liver Toxicity Risk Assessment