Chai Discovery applies frontier artificial intelligence to drug discovery, building foundation models that predict and reprogram biochemical molecular interactions. The company was founded by researchers who co-invented protein language modeling and developed state-of-the-art protein folding algorithms. Its backers include OpenAI, Thrive Capital, and General Catalyst, and it has established a partnership with Eli Lilly.
The company's core models, Chai-1 and Chai-2, are designed for the computational design of antibodies and small molecules. Together, they have achieved success rates above 85% for computationally designed molecules meeting drug-like properties. The broader Chai Discovery platform extends these capabilities to particularly difficult targets, including proteins traditionally considered undruggable, and claims to generate functional GPCR agonists with minimal screening and to design drug-like antibodies against challenging targets with atomic precision.
Chai Discovery's technical work spans several domains:
- Protein language modeling and folding algorithms
- Computational protein and molecular design
- Antibody and GPCR agonist design
- Biochemical interaction prediction and reprogramming
The company's stated mission is to turn biology from a science into an engineering discipline - shifting drug discovery away from the trial-and-error approach of screening millions or billions of sequences toward a more systematic, design-driven process.