How to use SwitchCraft Online

Protein Design Allostery Proteins Small Molecules

Design ligand-responsive proteins with SwitchCraft online.

SwitchCraft optimizes one protein sequence against multiple structural states to propose ligand-responsive conformational changes. The available tasks are positive allostery, negative allostery, induced binding, ligand discrimination, and motif switching. These are computational hypotheses, rather than experimentally validated switches.

How SwitchCraft Works

SwitchCraft differentiates through a modified Boltz-1 model to optimize sequence logits across multiple states. Motif geometry, ligand contacts, conformational separation, and backbone contacts contribute task-specific objectives. The standard 240-step schedule proceeds through warmup, exploration, annealing, and discrete sequence optimization. Final diffusion predictions use three recycles and 200 diffusion steps.

Positive allostery favors motif geometry in the ligand-bound state; negative allostery favors it in the apo state. Induced binding discourages target contacts without an effector and promotes target and effector contacts together. Ligand discrimination favors distinct apo and two ligand-bound conformations; it does not estimate selective binding affinity. Motif switching alternates the preferred geometry of two non-overlapping motifs.

Outputs include CSV sequence and confidence tables, FASTA sequences, PDB/mmCIF structures, aligned-error matrices, optimization trajectories, and structural RMSDs. Confidence values range from zero to one. RMSDs compare matched scaffold atoms after optimal alignment and should be interpreted alongside confidence and variation among diffusion samples.

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 SwitchCraft on Neurosnap

Using SwitchCraft on Neurosnap could drastically accelerate multistate sequence optimization for ligand-responsive protein design.

Five task-oriented workflows share one multistate optimization engine.
User-defined motif placements preserve functional sequence context.
State-specific structures, confidence, and geometry measurements support downstream assessment.

How to Use SwitchCraft on Neurosnap

To harness the capabilities of SwitchCraft, researchers can follow this streamlined workflow within Neurosnap:

Access Neurosnap: Start by logging in to the Neurosnap website.
Select Tool: From the list of available tools, choose SwitchCraft.
Provide Inputs: Provide all the inputs specified within the submission panel and optionally configure the tool as desired.
Run Tool: Submit the SwitchCraft job and Neurosnap will execute it in the cloud, automatically notifying you as soon as your results are ready.
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 SwitchCraft in publications or research outputs.

Jing, B., Bafna, M., Parsan, A., Ni, H. M., Kwabi-Addo, D., Bryson, B., Klivans, A., and Berger, B. SwitchCraft: A Programmatic Framework for Designing State-Switching Proteins. ICML (2026). https://arxiv.org/abs/2605.31236

Wohlwend, J., et al. Boltz-1: Democratizing Biomolecular Interaction Modeling. bioRxiv (2024). https://doi.org/10.1101/2024.11.19.624167

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:

BoltzGen

DISCO

LigandMPNN

Proteina-Complexa

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