Carterra HT-SPR platforms used in large-scale validation of AI-designed protein binders
Carterra®, a provider of high-throughput surface plasmon resonance (HT-SPR) instrumentation for antibody and small-molecule characterisation, has featured in one of the largest published wet-lab validations of AI-generated proteins to date. In a study released on 18 August 2026, Anthropic reported that its Claude models had autonomously run de novo protein binder design campaigns against 15 targets, researching each target, selecting epitopes, running open-source design tools and producing ranked candidate designs without human input into any design decision. The resulting designs, 1,320 protein binders in total, were sent to Twist Bioscience and Adaptyv Bio for experimental analysis, both of which used Carterra HT-SPR platforms to generate binding kinetics and affinity data.
Autonomous design across 15 targets
According to the study, the Claude-led campaigns produced functional binders with hit rates exceeding those reported for prior methods, and did so within days rather than the weeks or months typically required by human specialists. Investigators noted that as design throughput increases, the ratelimiting step in such programmes moves from generating candidate molecules to validating them experimentally.
Scale shifts the bottleneck to analysis
Carterra’s array-based method allows a large number of binding interactions to be measured within a small number of unattended runs, using as little as one per cent of the antigen sample required by conventional SPR systems. This is intended to address the shift in bottleneck from design to measurement. “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, chief executive 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.”
Head-to-head comparison outperforms established binder
Among the reported findings, Claude’s best-performing binder against the target RBX1 was compared directly with the winning binder from an earlier open design competition, both measured on the same array under identical conditions. The Claude-designed binder recorded an affinity of 3.9 nM, compared with 45 nM for the earlier competition winner. Running human, mouse and cynomolgus versions of a target in parallel also yielded species cross-reactivity data, originally a secondary objective, as part of the primary dataset rather than requiring a separate follow-up study.
Julian Englert, chief executive and co-founder of Adaptyv Bio, said: “The bottleneck in AI drug discovery is the experimental validation of all those molecules that the AI models come up with. 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.”
The study follows a July 2026 report from Leerink Partners identifying Carterra as a core enabling technology within the approximately $7 billion “Lab-in-the-Loop” market for AI-driven antibody discovery, citing binding affinity measurement as a central element of that workflow. Carterra’s platforms combine proprietary flow-printing microfluidics with real-time array HT-SPR, offering up to 100 times the throughput of conventional label-free systems while using substantially less sample. The company has more than two decades of experience in label-free bio-sensor technology and its platforms are used by major pharmaceutical companies for biologics and small-molecule characterisation.
