Carterra enables Anthropic's autonomous AI Protein Design Study via its HT-SPR Binding Platforms

Carterra^® has highlighted the role of Carterra HT-SPR in one of the largest published wet-lab validations of AI-designed proteins to date. In a study¹ Anthropic reported that its Claude models autonomously ran de novo protein binder design campaigns against 15 challenging targets — researching each target, selecting epitopes, running open-source design tools, and delivering ranked designs per target with no human input into any design decision.

Anthropic sent the protein designs to Twist Bioscience and Adaptyv Bio to be analyzed. Both use Carterra HT-SPR platforms to generate binding kinetics and affinity data at scale.

Protein design is a key step in the early stages of a drug discovery campaign. Anthropic generated functional binders — with hit rates exceeding prior methods — in a matter of days rather than the weeks or months it would take a human specialist.

This creates enormous opportunity for drug developers, but it also moves the bottleneck from protein design to wet lab experimental analysis. Carterra’s HT-SPR technologies overcome this bottleneck, enabling large scale affinity and kinetics binding data to be generated in days instead of the months required historically.

"This study shows the enormous potential of AI and Lab-in-a-Loop automation to accelerate drug discovery, when paired with high-throughput analysis platforms," said Josh Eckman, CEO and co-founder of Carterra. "An AI system generated thousands of novel binders in a matter of days. Two independent labs experimentally validated the protein designs in a few weeks. Carterra was built for this moment, when measurement has to keep up with design."

Scale is the story

The ability to measure tens of thousands of binding interactions in a short period of time has changed the specter of drug development. If done a few at a time on legacy SPR platforms, a campaign this size would consume many months of instrument time and far more purified antigen than a design program typically has on hand.

Carterra's array-based approach compresses these complex experiments into a small number of unattended runs which consume as little as 1% of the sample required by traditional systems.

Collecting data on multiple targets and multiple designs on a single Carterra array unlocks scale never before possible. When Anthropic wanted to know how Claude's best RBX1 binder compared to the winner of an earlier open design competition, the investigators put both on the same array.

Claude's design measured 3.9 nM versus 45 nM for the previous winner, head-to-head, under identical conditions. And because human, mouse, and cynomolgus versions of a target were run in parallel, Anthropic got species cross-reactivity — a preclinical-relevance question it had treated as a secondary objective — as part of the primary dataset instead of requiring a follow-up study.

"The bottleneck in AI drug discovery is the experimental validation of all those molecules that the AI models come up with,” added Julian Englert, CEO and co-founder of Adaptyv Bio." For large campaigns like this one, high-throughput SPR is the best method to get real binding kinetics data, which is why we're using Carterra SPR in our automated lab. That's what generates the data to train the AI models and improve the next round of designs."

References

1. Anthropic, How Claude is accelerating protein design and analytical chemistry. Aug 18, 2026.

Want the latest science news straight to your inbox? Become a SelectScience member for free today>>