Use EvoBind2

Official Neurosnap webserver for accessing EvoBind2 online.

BETA - MAY CONTAIN BUGS Protein Design

Overview

EvoBind2 is a computational framework for designing high-affinity linear and cyclic peptide binders using target protein sequences. By integrating modified AlphaFold2 and AlphaFold-Multimer models, it performs in silico directed evolution to optimize peptide sequences and structures without requiring prior knowledge of binding sites or scaffold templates. The method employs adversarial checks to eliminate false positives and achieves success rates of 46% (linear) and 75% (cyclic) with affinities ranging from 0.26 nM to 7.9 µM. EvoBind2 enables cyclic peptide design for enhanced stability and membrane permeability.

Neurosnap Overview

The EvoBind2 online webserver allows anybody with a Neurosnap account to run and access EvoBind2, 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

  • Generates novel linear/cyclic peptide binders using only target protein sequences, requiring no structural or binding site information.
  • Integrates modified AlphaFold2 for structure prediction and AlphaFold-Multimer for adversarial validation, tripling success rates by eliminating false positives.
  • Achieves nanomolar affinities (0.26 nM best cyclic, 19 nM best linear) validated by surface plasmon resonance (SPR).
  • Cyclic peptide support enables membrane traversal and improved half-life while matching linear binder efficacy.

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 EvoBind2 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

Structure of the receptor to design a binder for.

Specify the receptor chain in the PDB file for binder design.

Specify the indices of the target residues in a comma-separated format like: 12, 14, 13. If left empty, EvoBind will pick a binding spot for you.

The length of the binder to design.

The starting sequence for the binder design. If left empty, a random sequence with the same length as the binder length will be used. Otherwise, the provided sequence will be used as the starting point for the optimisation.

The number of iterations for the binder design (repeated optimisation).

Number of recyles through the model.

Use a cyclic offset for the binder design.

Allowed Types: a3m
The Multiple Sequence Alignment (MSA) of the receptor chain's input sequence. If left blank, the MSA will be generated using the ColabFold API. If you are not confortable or authorized sharing your sequences with the third party API, please upload a sequence here.

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.