Use RFantibody

Official Neurosnap webserver for accessing RFantibody online.

Antibodies Protein Design

Overview

Generate de-novo antibodies and nanobodies (VHHs) with atomic accuracy using RFantibody. This pipeline targets user-defined epitopes by leveraging fine-tuned RFdiffusion for backbone and docking prediction, ProteinMPNN for sequence optimization, and a specialized RoseTTAFold2 oracle to ensure structural validity and specificity.

Neurosnap Overview

The RFantibody online webserver allows anybody with a Neurosnap account to run and access RFantibody, no downloads required. Information submitted through this webserver is kept confidential and never sold to third parties as detailed by our strong terms of service and privacy policy.

View Paper

Features

  • Epitope-guided de-novo CDR backbone generation and docking via fine-tuned RFdiffusion.
  • ProteinMPNN-based sequence optimization tailored to the designed backbones.
  • RoseTTAFold2 antibody oracle for structural self-consistency and off-target filtering.

Statistics

Neurosnap periodically calculates runtime statistics based on job execution data. These estimates provide a general guideline for how long your job may take, but actual runtimes can vary significantly depending on factors like input size or settings used.

Statistic Value
Credit Usage Rate loading...
Estimated Total Cost loading...
Runtime Mean loading...
Runtime Median loading...
Runtime Standard Deviation loading...
Runtime 90th Percentile loading...
Runtime Longest loading...

API Request

Access RFantibody using the Neurosnap API by sending a request using any programming language with HTTP support. To safely generate an API key, visit the API tab of your overview page.

Job Note

Provide a name or description for your job to help you organize and track its results. This input is solely for organizational purposes and does not impact the outcome of the job.

Configuration & Options

Service Inputs

Select the mode of the design.

Input framework template for the design. The expected type (Antibody or Nanobody) depends on the selected 'Mode'.

Input target protein for the design.

Specify key residues on the *target* protein to guide binding. Provide a comma-separated list (spaces ignored). Each item can be a single residue (e.g., 'A21') or a range (e.g., 'B14-21'). Uses 1-based numbering. Note: Attractive sites typically have >~3 hydrophobic residues. Binding to charged/polar sites or near glycans is challenging. Binding unstructured loops is possible but may have energetic costs due to ordering upon binding. Read more: https://www.nature.com/articles/s41586-023-06953-1

Number of distinct backbone structures to generate using RFdiffusion. The total number of final designs will be this value multiplied by the 'Number of ProteinMPNN Designs'. Note: Higher values significantly increase runtime and credit usage.

The number of ProteinMPNN sequences to generate for *each* RFdiffusion backbone. Note: Higher values significantly increase runtime and credit usage.

Advanced Settings

Specify which CDR loops (H1, H2, H3, L1, L2, L3) to design and optionally constrain their lengths. Provide a comma-separated list. Each item follows the format: 'LOOP:', 'LOOP:LENGTH', or 'LOOP:START-END'. Examples: 'H1:' (design H1 with framework length), 'L2:7' (design L2 with fixed length 7), 'H3:5-13' (design H3 with length between 5 and 13). If a loop is omitted, it remains fixed from the input framework. Leave empty to design all loops with their framework lengths.

Ready to submit your job?

Once you're done just hit the submit button below and let us do the rest.

To submit a job please login or register an account.