How to Use FKSFold-Chai

Commercially Available Online Web Server

Try FKSFold-Chai View Paper
Structure Prediction & Folding Co-Folding Conformation Generation Nucleotides Protein Folding Proteins Protein–Ligand Docking Protein–Protein Docking Small Molecules

Use FKSFold-Chai online for Feynman-Kac-steered Chai-1 complex prediction.

FKSFold-Chai is a Chai-1 fork that adds Feynman-Kac steering to the diffusion stage for molecular-glue-induced ternary complex prediction. The Neurosnap wrapper exposes the FKSFold-compatible subset of Chai-style inputs: proteins, nucleic acids, glycans, small molecules, templates, contact restraints, and protein/glycan covalent restraints. Cyclic biopolymers are not exposed because this FKSFold path does not consume Chai-1's cyclic-chain option.

Researchers can tune FK steering with particle count, resampling interval, potential type, lambda weight, sigma threshold, and steering score. This makes the workflow useful for induced-proximity systems where the biologically relevant ternary pose can be difficult to recover from unconstrained sampling alone.

How FKSFold-Chai Works

The FKSFold paper frames ternary-complex modeling as a diffusion-time search problem: multiple particles are propagated through denoising, scored, and periodically resampled so that later diffusion steps concentrate on particles with more promising interface confidence. In this implementation, users can steer by mean interface pTM, interface pTM, protein mean interface pTM, pLDDT, or the default internal score.

Within Neurosnap, the primary inputs and restraint formats intentionally match Chai-1. MSA Mode, recycling, diffusion steps, and diffusion samples control the base folding run, while the FK-specific controls determine how strongly and how often particles are selected during diffusion. Outputs remain ranked structures with Chai confidence summaries, so candidates can be reviewed the same way as Chai-1 predictions.

What is Neurosnap?

Neurosnap is the leading platform for bioinformatics and computational science focused on expanding access to powerful modeling and simulation tools. Because many state-of-the-art machine learning systems remain complex to install, configure, and scale, Neurosnap offers a clean, browser-based workspace that removes the burden of infrastructure management, dependency conflicts, and command-line tooling.

Built for biologists, chemists, and cross-disciplinary scientists, the platform enables advanced computational workflows without requiring expertise in software engineering or cloud architecture. Researchers can launch analyses through an intuitive interface, connect programmatically through a comprehensive API, and rely on automated resource management to scale workloads efficiently. By taking care of the underlying compute and operational complexity, Neurosnap allows teams to devote their energy to scientific progress and faster iteration. Security and data protection remain foundational principles, with clear safeguards outlined in our Terms of Use and Privacy Policy to ensure your work stays protected.

Advancing Discovery with FKSFold-Chai on Neurosnap

Using FKSFold-Chai on Neurosnap could drastically accelerate Feynman-Kac-steered biomolecular complex prediction for molecular-glue and induced-proximity systems.

  • FKSFold-compatible Chai inputs: The service keeps familiar mixed biomolecular inputs without exposing unsupported cyclic-chain controls.
  • Steered diffusion search: Particle resampling can focus generation on higher-confidence interface arrangements in difficult ternary systems.
  • Tunable steering controls: Particle count, resampling interval, potential type, lambda weight, sigma threshold, and score choice let users balance search breadth against runtime.
  • Confidence-guided review: Ranked structures retain pTM, ipTM, pLDDT, PAE, PDE, and interface metrics for downstream triage.

How to Use FKSFold-Chai on Neurosnap

To harness the capabilities of FKSFold-Chai, researchers can follow this streamlined workflow within Neurosnap:

  1. Access Neurosnap: Start by logging in to the Neurosnap website.
  2. Select Tool: From the list of available tools, choose FKSFold-Chai.
  3. Provide Inputs: Provide all the inputs specified within the submission panel and optionally configure the tool as desired.
  4. Run Tool: Submit the FKSFold-Chai job and Neurosnap will execute it in the cloud, automatically notifying you as soon as your results are ready.
  5. Review Output: Explore your results through rich visualizations, including figures, plots, and interactive views designed to help you analyze findings with clarity and confidence.

Citations

Please cite the original work when using FKSFold-Chai in publications or research outputs.

Shen, J., Zhou, S., & Che, X. (2025). FKSFold: Improving AlphaFold3-Type Predictions of Molecular Glue-Induced Ternary Complexes with Feynman-Kac-Steered Diffusion. bioRxiv. https://doi.org/10.1101/2025.05.03.651455

Chai Discovery, Jacques Boitreaud, Jack Dent, Matthew McPartlon, Joshua Meier, Vinicius Reis, Alex Rogozhnikov, Kevin Wu bioRxiv 2024.10.10.615955; doi: https://doi.org/10.1101/2024.10.10.615955

Abramson, J., Adler, J., Dunger, J. et al. Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature 630, 493–500 (2024). https://doi.org/10.1038/s41586-024-07487-w

Neurosnap Inc. (2022). Neurosnap: An online platform for computational biology and chemistry. Available at: https://neurosnap.ai/

Similar Services

Explore related tools that support similar research workflows:

Boltz-1 (AlphaFold3)

Boltz-2 (AlphaFold3)

Chai-1 (AlphaFold3)

ESMFold2

Proudly supporting 50,000+ scientists worldwide, including 7,000+ leading biotech and global biopharma organizations.

Making Scientific Research
Faster & Easier

Register for free — upgrade anytime.

Interested in getting a license? Contact Sales.

Try Free