AI models cut drug discovery time and cost for Citrini
Citrini Therapeutics used Anthropic models to identify molecules for scorpion stings in 48 hours, bypassing traditional antivenom methods. The project cost $200,000 and was completed by a team with no biotech background.
Citrini Therapeutics, a research institute, used Anthropic's models to identify molecules for treating toxic scorpion stings. The team, consisting of five people with no biotech background, spent $200,000 and six months on the project. The AI reduced 120 candidate molecules to 18 in 48 hours, identifying binders that neutralize the venom for four types of poisoning. This approach bypasses the traditional method of injecting venom into horses to produce antivenom.
Anthropic also acquired a one-person startup in July where a scientist used AI to manage research for a rare muscle disease, completing mouse tests in 80 days instead of years. These cases illustrate AI's potential to drastically reduce the time and cost of drug discovery and scientific research. "It took 48 hours to narrow it down from 120 molecules to 18," the team noted. AI models are beginning to provide tangible, significant efficiency gains in biotech research, potentially creating new value chains in drug discovery.