Use Chai-1 (AlphaFold3)

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

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.

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 Chai-1 (AlphaFold3) 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

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)

Specify inter-chain restraints to guide Chai-1 in folding complexes. These restraints define contacts between residues across sequences, influencing the folding process.

Each row should define one restraint, with values separated by commas (,). The format is:

SEQ_ID1, RES_ID1, SEQ_ID2, RES_ID2, MAX_DIST
  • SEQ_ID1 → ID of the first sequence containing the residue.
  • RES_ID1 → Residue index on SEQ_ID1. Use * to allow interaction with any residue on SEQ_ID1.
  • SEQ_ID2 → ID of the second sequence containing the interacting residue.
  • RES_ID2 → Residue index on SEQ_ID2.
  • MAX_DIST → Maximum allowed distance (in Å) for the restraint (recommended: 5.5 Å).


🔹 Example Input:

Protein_1,C55,Protein_2,C66,5.5
Protein_1,M24,DNA_seq1,*,3.2
Protein_1,*,Protein_2,D78,3.2
Protein_1,C55,DNA_seq1,G13,5.5


⚠️ Notes:

  • Sequence IDs match those in Input Sequences.
  • Residue numbering starts at 1.
  • Use * to indicate flexibility in residue selection.
  • The recommended MAX_DIST is 5.5 Å for close contacts but can be adjusted as needed.

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.