Evedesign: Accessible Biosequence Design Framework
Summary
NIST has published guidance on 'Evedesign,' a new open-source framework for biosequence design. The framework aims to make machine learning methods for protein engineering more accessible and interoperable for researchers, with an interactive web interface available.
What changed
NIST has released a publication detailing 'Evedesign,' a unified open-source framework designed to address the interoperability and accessibility challenges in machine learning for protein engineering. The framework formalizes conditional biosequence design in a method-agnostic way, supporting complex multi-objective workflows and iterative experimental integration. It is demonstrated for applications in antibody engineering, enzyme design, and natural enzyme discovery, with an invitation for community contributions.
This guidance is relevant to researchers and developers in the biotechnology and pharmaceutical sectors. While not imposing direct regulatory obligations, it offers a new tool to enhance research capabilities. The publication highlights an interactive web interface for end-to-end design, encouraging adoption and contribution to the open-source project. No specific compliance deadlines or penalties are associated with this publication, as it serves as informational guidance and a software framework release.
What to do next
- Review the Evedesign framework documentation and interactive web interface.
- Evaluate the potential application of Evedesign for protein engineering and biosequence design workflows.
- Consider contributing to the open-source Evedesign project.
Source document (simplified)
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock () or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
evedesign: accessible biosequence design with a unified framework
Published
March 9, 2026
Author(s)
David Ross, Thomas Hopf, Artem Gazizov, Sergio Garcia Busto, Ethan Eschbach, SunJae Lee, Milot Mirdita, Ian Ross, Rose Orenbuch, Khaoula Belahsen, Anthony Gitter, Chris Sander, Martin Steinegger, Simon d'Oelsnitz, Debora Marks
Abstract
Machine learning methods for protein engineering are rarely interoperable, require bespoke workflows, and remain inaccessible to non-experts. Yet the design problems that matter most - conditional design subject to real-world constraints, multi-objective optimization, and iterative lab-in-the-loop workflows where experimental data continuously refines successive design rounds - demand exactly the kind of flexible, composable infrastructure that no single tool provides. We present evedesign, a unified open-source framework that formalizes conditional biosequence design in a method-agnostic way, enabling complex multiobjective workflows combining supervised and unsupervised models from standardized specifications, and built from the outset to support iterative experimental integration. An interactive web interface facilitates end-to-end design for a broad scientific audience at https://evedesign.bio. We demonstrate evedesign's utility in antibody engineering, enzyme design, and natural enzyme discovery, and invite open-source community contributions. Citation Nature Methods Pub Type Journals
Keywords
AixBio, protein engineering Protein engineering
Citation
Ross, D.
, Hopf, T.
, Gazizov, A.
, Busto, S.
, Eschbach, E.
, Lee, S.
, Mirdita, M.
, Ross, I.
, Orenbuch, R.
, Belahsen, K.
, Gitter, A.
, Sander, C.
, Steinegger, M.
, d'Oelsnitz, S.
and Marks, D.
(2026),
evedesign: accessible biosequence design with a unified framework, Nature Methods
(Accessed March 10, 2026)
Additional citation formats
Issues
If you have any questions about this publication or are having problems accessing it, please contact [email protected].
Created March 9, 2026
Related changes
Source
Classification
Who this affects
Taxonomy
Browse Categories
Get Cybersecurity alerts
Weekly digest. AI-summarized, no noise.
Free. Unsubscribe anytime.
Get alerts for this source
We'll email you when NIST Publications publishes new changes.