evedesign: accessible biosequence design with a unified framework

Thomas A. Hopf, Artem Gazizov, Sergio Garcia Busto, Ethan Eschbach, SunJae Lee, Milot Mirdita, Rose Orenbuch, Khaoula Belahsen, David J. Ross, Chris Sander, Martin Steinegger, Simon d'Oelsnitz, Debora Marks2026 · DOI

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.
BibTeX
@misc{hopf2026evedesign,
  author = {Thomas A. Hopf and Artem Gazizov and Sergio Garcia Busto and Ethan Eschbach and SunJae Lee and Milot Mirdita and Rose Orenbuch and Khaoula Belahsen and David J. Ross and Chris Sander and Martin Steinegger and Simon d'Oelsnitz and Debora Marks},
  title = {{evedesign: accessible biosequence design with a unified framework}},
  year = {2026},
  doi = {10.64898/2026.03.17.712115},
}
Figure