DISCO
Joint protein sequence-structure co-design with ligand, RNA, and DNA conditioning in one diffusion workflow.
Overview
DISCO (Diffusion for Sequence-structure CO-design) is a multimodal generative model that simultaneously designs protein amino-acid sequences and three-dimensional atomic structures in a single diffusion pass. Unlike two-stage pipelines that first generate a backbone and then inverse-fold a sequence, DISCO learns a joint distribution over discrete sequence tokens and continuous coordinates, denoising both together while conditioning on and co-folding with arbitrary biomolecules. The model supports unconditional protein design, ligand-conditioned binder and enzyme design, and nucleic-acid-conditioned complexes without requiring pre-defined catalytic motifs or theozyme templates.
Run DISCO on Neurosnap
The DISCO online webserver allows anybody with a Neurosnap account to run and access DISCO, no downloads required. Information submitted through this webserver is kept confidential and never sold to third parties as detailed by our strong Terms of Use and Privacy Policy.
Features
- Co-designs protein sequence and 3D structure jointly, eliminating the backbone-to-inverse-folding handoff.
- Supports unconditional, ligand-conditioned, RNA-conditioned, and DNA-conditioned design modes.
- Conditions on and co-folds with small molecules, nucleic acids, and other biomolecular partners.
- Cross-modal recycling and self-correcting sequence inference improve co-designability.
- Configurable experiment presets and effort levels for designable versus diverse sampling campaigns.
- Exports co-designed sequences and structure files for downstream folding validation and experimental follow-up.
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 DISCO 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.
Similar Tools
Explore tools with similar features, categories, and use cases.
Citations
Please cite the original work when using DISCO in publications or research outputs.
|
Rector-Brooks, J., Lambert, T., Skreta, M., Roth, D., Long, Y., Li, Z.-Q., Zhang, X., Cretu, M., Li, F.-Z., Ganapathy, T., Jin, E., Bose, A. J., Neklyudov, K., Bengio, Y., Tong, A., Arnold, F. H., & Liu, C.-H. General Multimodal Protein Design Enables DNA-Encoding of Chemistry. arXiv (2026). https://arxiv.org/abs/2604.05181 |
|
Neurosnap Inc. (2022). Neurosnap: An online platform for computational biology and chemistry. Available at: https://neurosnap.ai/ |