| Bringing next-generation binder design models into production discovery
Basel, Switzerland — Genedata, a Danaher company, and the leading provider of enterprise software solutions for biopharmaceutical R&D, today announced the addition of the new RFD4-Proteina binder design model into Genedata’s AI-enabled discovery workflows, following the model’s introduction at NVIDIA GTC Berlin. As an early ecosystem partner, Genedata is among the first companies to make RFD4-Proteina available within its production discovery workflows. By connecting AI-generated molecular designs, scientific data, and laboratory results, Genedata helps researchers transform AI predictions into continuous learning cycles that accelerate biologics discovery.
The workflow begins with scientists defining target characteristics and required properties using Genedata’s AI co-scientist. NVIDIA’s open protein design models then generate and evaluate candidate binders within Genedata. As candidates move into laboratory testing, results are captured and linked back to the original designs, helping scientists refine and rank the next round.
“Advances in AI are creating unprecedented opportunities for protein and antibody discovery, but unlocking their full value requires more than access to powerful models alone,” said Othmar Pfannes, Ph.D., President of Genedata. “Researchers need a way to connect molecular design, experimental execution, and scientific data into a continuous learning process. Genedata serves as the digital backbone that brings these elements together, helping scientists evaluate more candidates before testing, preserve the scientific context behind each outcome, and build knowledge from one discovery cycle to the next.”
While advances in generative AI are rapidly expanding what scientists can design, many organizations still struggle to operationalize these models within production scientific research workflows. Genedata provides the orchestration, governance, and scientific data foundation needed to deploy NVIDIA BioNeMo open models, including RFD4-Proteina, directly within the discovery workflows scientists use every day. Researchers can apply AI-generated designs within established processes while maintaining lineage, traceability, and scientific context across the discovery lifecycle.
Within Danaher’s autonomous laboratory initiative, these capabilities connect AI, automation, and scientific data in a closed-loop discovery framework where each experimental outcome informs the next design cycle, creating a continuous learn-and-improve process that advances science while keeping scientists in control. |
