Streamlining Antibody Discovery: RFantibody is Now Available on Vecura

What is RFantibody?

RFantibody is an advanced de novo design pipeline specifically engineered for the creation of custom antibodies and nanobodies against target proteins from scratch. By integrating three state-of-the-art computational methods—RFdiffusion for backbone generation, ProteinMPNN for sequence design, and an antibody-finetuned RoseTTAFold2 for structure filtering—it automates the complex process of antibody discovery. It helps users bypass the need for traditional starting binders, allowing for the generation and screening of thousands of potential designs in a systematic, guided manner. It is especially useful for structural biologists and drug discovery researchers aiming to develop specific binders against complex or difficult-to-target epitopes.

What can users do with RFantibody on Vecura?

With RFantibody on Vecura, users can:

• Generate novel antibody or nanobody backbones docked to a specific antigen structure.
• Steer design processes toward targeted epitope hotspots for improved binding specificity.
• Design diverse CDR amino-acid sequences for optimized backbone geometries.
• Perform high-throughput in silico filtering using structural confidence scores to shortlist candidates for laboratory synthesis.

What the output means

The output provides structured PDB files of designed antibody-target complexes, FASTA sequences for experimental synthesis, and a comprehensive set of RF2 confidence metrics (pAE, pLDDT, and RMSD).

This output should be used to support scientific decision making. It does not replace experimental validation, as the pipeline focuses on structural feasibility rather than predicting binding affinity (Kd) directly.

Why this matters

The design of therapeutic antibodies has traditionally been a time-consuming, trial-and-error process heavily reliant on immunization or existing library screening. RFantibody represents a significant shift toward "rational design," enabling researchers to computationally explore the vast space of potential binders and prioritize only the most structurally sound candidates for wet-lab validation.

By lowering the barrier to de novo design, this technology accelerates the early stages of drug discovery, enabling the development of biologics against targets that were previously considered "undruggable." It provides a robust, reproducible workflow that helps researchers focus their laboratory resources on the designs with the highest predicted success rates.

• Developed by: Researchers at the University of Washington (Baker Lab) and contributors to the RosettaCommons.
• Source: Official GitHub Repository
• Reference: RFantibody: A de novo antibody and nanobody design pipeline (bioRxiv 2024)