Thanks to integration with Basecamp Research’s EDEN models, scientists can now design potent antibiotics and quickly prioritize vaccine targets using Claude Science.
, /PRNewswire/ — Basecamp Research announced today that its EDEN models for antibiotic design and vaccine target prediction are now available through Claude Science, Anthropic’s life sciences research ecosystem. This allows researchers to generate and prioritize therapeutic candidates through a conversational interface in a matter of minutes.
By combining Claude’s reasoning with EDEN’s biological design capabilities, researchers can now go directly from a pathogen to a narrow list of high-performance antibiotic candidates. This capability is available in Claude.ai, Claude Desktop, Claude Mobile, Claude Code, Cowork and Claude Science via Anthropic Connector Directory.
The world needs new antibiotics
Drug-resistant infections contribute to nearly 5 million deaths a year, but the pharmaceutical industry has largely retreated from antibiotic development. New antibiotics are urgently needed, particularly for pathogens that spread more rapidly in low-income countries, where access to last-resort medicines is more difficult.
“Microbes have been producing antibiotics and developing resistance to each other for billions of years,” said Glen Gowers, co-founder and CEO of Basecamp Research. “EDEN learned from that story and now, through Claude, researchers around the world can design successful new antibiotics in minutes, not years.”
In collaboration with researchers at the University of Pennsylvania, Basecamp Research demonstrated that 97% of EDEN-designed antibiotic peptides are active against World Health Organization (WHO) priority pathogens when tested in the laboratory. Fleming Prize winner and Presidential Associate Professor César de la Fuente led the work of UPenn’s Automated Biology Group.
One candidate, EDEN-7, was tested in mice infected with Acinetobacter baumannii multidrug-resistant—a pathogen associated with hospital outbreaks around the world—and demonstrated efficacy similar to that of a next-generation antibiotic, despite having been generated through an initial optimization process (zeroshot), that is, without subsequent optimization or iterative engineering.
“This collaboration demonstrates how cutting-edge biological models can be combined with rigorous experimental validation to accelerate antibiotic discovery,” de la Fuente said. “Antimicrobial resistance is one of the biggest existential threats to humanity, and collaborations like this between academia and industry are crucial.”
Find vaccine targets in minutes
Developing a vaccine against an emerging pathogen is a race against time. Identifying which part of the pathogen to attack is usually determined empirically and can take months of laboratory work. This delay often costs lives.
EDEN’s vaccine design model identifies which proteins are most likely to trigger a protective immune response, outperforming comparable genomic models. By integrating it into Claude, researchers can describe a problem in plain language and have Claude run a prioritization workflow against the pathogen’s genetic sequence. This can reduce several weeks of research per pathogen to a single conversation.
A growing collaboration
“The antibiotic crisis and the need for new vaccines are two of the most important public health challenges of our time,” said Jonah Cool, director of Life Sciences Partnerships and Deployment at Anthropic. “Making EDEN available through Claude Science offers researchers a new way to explore and prioritize treatments for some of the most dangerous pathogens on the planet.”
Built on the world’s largest biological data set
Most biological AI models are trained with a limited set of well-studied organisms: those that scientists have already catalogued. Instead, EDEN is trained with BaseData, the largest, fastest growing, and most informative biological database on the planet.
To build it, Basecamp Research has conducted expeditions to more than 200 locations in more than 30 countries, sampling the places where life is strangest and least understood, including hot springs, deep-sea sediments, polar ice, and remote high-altitude plateaus. In the process, he has documented more than a million species new to science. The result is more than 10 billion new genes and approximately ten times the content of all public databases combined.
Basecamp Research aims to grow BaseData 100-fold over the next two years through the Trillion Gene Atlas, a collaboration with Anthropic, NVIDIA, PacBio and Ultima Genomics designed to generate trillion-gene scale genomic data for AI-powered drug discovery.
Diversity drives EDEN’s performance across a wide range of tasks. Each sample is collected under informed consent and benefit-sharing agreements, so the countries and communities that manage this biodiversity share in the value it generates, and each sequence is traceable to one of hundreds of country-specific permits. This allows a portion of the revenue to go back to the country and community where the data was originally sourced from, setting a standard for data provenance that the rest of the sector has yet to meet.
About Basecamp Research
Basecamp Research is dedicated to solving major challenges in healthcare and life sciences by exploring Beyond Known Biology™. The company trains cutting-edge AI models with BaseData, the world’s largest biological data set, collected through collaborations with more than 200 organizations in more than 30 countries. Basecamp Research is developing a portfolio of therapies and working with commercial and academic partners around the world to accelerate the discovery and development of treatments.
BaseData™, Beyond Known Biology™, EDEN-GLM™ and aiPGI™ are trademarks and technologies of Basecamp Research.
Logo – https://mma.prnewswire.com/media/3002092/Basecamp_Research_Logo.jpg