Use Chai-1 (AlphaFold3)

Official Neurosnap webserver for accessing Chai-1 (AlphaFold3) online.

BETA - MAY CONTAIN BUGS Protein Folding Molecular Docking

Overview

Chai-1 is an advanced open-source model delivering AlphaFold3-level accuracy in predicting 3D structures of biomolecular complexes. The model integrates state-of-the-art innovations in architecture, MSA processing, and interaction confidence scoring. Chai-1 provides accessible tools for structural biology and drug discovery.

Neurosnap Overview

The Chai-1 (AlphaFold3) online webserver allows anybody with a Neurosnap account to run and access Chai-1 (AlphaFold3), 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

  • Delivers AlphaFold3-level accuracy for biomolecular structure prediction.
  • Handles diverse molecular systems: proteins, RNA/DNA, and small molecules.
  • Cutting-edge approaches for MSA pairing and structural conditioning.
  • Optimized for efficient, accurate confidence predictions in molecular interactions.
  • Demonstrates superior computational efficiency and speed over previous models.
  • Validated extensively on CASP15 and specialized benchmarking datasets.

Configuration & Options

Service Inputs

The amino acid, DNA, and RNA sequences corresponding to the molecules you want to predict. For complex prediction simply provide multiple sequences in this input and they will all be folded at the same time together. For DNA and RNA sequences enter them in the 5′-->3′ direction. To specify modified amino acids that already have an associated CCD code, include the modified residue's CCD code in parentheses directly in the sequence in place of its canonical residue, e.g., "RKDES(MSE)EES" to specify a selenomethionine at the 6th position.

Input small molecules to include in prediction. All inputs are converted to SMILES format, with SMILES strings being the preferred input for optimal results.

Restraints Instructions (Optional)

Chai-1 offers the ability to fold complexes with user-specified "restraints" as inputs. These restraints specify inter-chain contacts at various resolutions that are used to guide Chai-1 in folding the complex. For more information about restraints check out this documentation from the authors.

Specifying Restraints:

The format for restraints is the following per line SEQ_ID1,RES_ID1,SEQ_ID2,RES_ID2,MAX_DIST

SEQ_ID1: This is the ID of the first sequence that your residue is located on. Sequence IDs are assigned to the sequence within the Input Proteins input or the header of the nucleotide sequence within the Input Nucleotides input.

RES_ID1: This is the residue index / position to constrain on SEQ_ID1. Use a residue ID of 1 for the first residue in your sequence. Can also be set to * if you don’t care about which residues RES_ID2 interacts with on SEQ_ID1.

SEQ_ID2: This is the ID of the second sequence that your residue is located on.

RES_ID2: This is the residue index / position to constrain on SEQ_ID2.

MAX_DIST: The maximum distance in angstroms for a bond / constraint (recommended 5.5).

Example:

In the following toy example we want the Cysteines in Protein_1 and Protein_2 to be folded in very close proximity:


Protein_1,C55,Protein_2,C66,5.5

See above instructions for information on how to use this input.

Advanced Settings

Choose whether you want to use an MSA generated using mmseqs2 or if you want to use single sequence mode which leverages language model embeddings instead ("single_sequence"). The single sequence approach is much faster and achieves 90% of the accuracy of its MSA counterpart. Warning: We query a 3rd party service to perform sequence searches, if you do not wish to share your sequence set this to "single_sequence".

Increased recycling steps tend to produce more accurate predictions but will also greatly increases prediction time. For smaller proteins and monomers we recommend 6 recycles, for bigger proteins we recommend 10 recycles.

The number of diffusion steps to use for prediction.

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.