Multi-state Protein Design with DynamicMPNN
Alex Abrudan, Sebastian Pujalte Ojeda, Chaitanya K. Joshi, Matthew Greenig, Felipe Engelberger, Alena Khmelinskaia, Jens Meiler, Michele Vendruscolo
Abstract
Structural biology has long been dominated by the one sequence, one structure, one function paradigm, yet many critical biological processes—from enzyme catalysis to membrane transport—depend on proteins that adopt multiple conformational states. Existing multi-state design approaches rely on post-hoc aggregation of single-state predictions, achieving poor experimental success rates compared to single-state design. We introduce DynamicMPNN, an inverse folding model explicitly trained to generate sequences compatible with multiple conformations through joint learning across conformational ensembles. Trained on 46,033 conformational pairs covering 75\% of CATH superfamilies and evaluated using Alphafold 3, DynamicMPNN outperforms ProteinMPNN by up to 25% on decoy-normalized RMSD and by 12% on sequence recovery across our challenging multi-state protein benchmark.
BibTeX
@inproceedings{
abrudan2026multistate,
title={Multi-state Protein Design with Dynamic{MPNN}},
author={Alex Abrudan and Sebastian Pujalte Ojeda and Chaitanya K. Joshi and Matthew Greenig and Felipe Engelberger and Alena Khmelinskaia and Jens Meiler and Michele Vendruscolo and Tuomas Knowles},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=4ptHfbHG3D}
}