De novo design of flexible protein interactions with GuideFlip
- 1MRC Laboratory of Molecular Biology
Abstract
De novo design of protein binders requires a target structure. However, for flexible targets, such as intrinsically disordered proteins, this structure does not exist until the binder has stabilized the interaction. Such targets are therefore difficult for methods that separate structure generation from sequence design. We introduce GuideFlip, which co-designs structure and sequence through guided discrete flow matching: binder residues are assigned progressively while the complex is re-predicted at each step, allowing the evolving interface to affect the design process. GuideFlip reduces the hydrophobic bias of direct AlphaFold optimization and improves in silico success rates over existing approaches. We release a database of binder candidates for 177 human disordered proteins. Experimentally, we obtain de novo binders to the C-terminus of -synuclein and the disordered amino terminus of RBX1 with hit rates of 13.5% and 41.7%, respectively, and we confirm the epitopes of selected binders by NMR and mutagenesis. Applying GuideFlip to flexibility on the binder side, we design a nanobody that binds the agonist-bound {beta}1-adrenergic receptor in the active state, but not the receptor in its inactive state, with a 75% hit rate and cryo-EM structure confirming the design. GuideFlip enables protein design where bound structures emerge only upon binding.
Related
- De novo Rubisco design with protein language models
- Aptamers without SELEX: De novo design from protein structure in hours
- De novo design of functional RNAs through higher-order interactions
- De novo protein design in an expanded chemical space
- EquiDesign: a versatile computational framework for de novo protein sequence design.
BibTeX
@misc{yi2026novo,
title = {{De novo design of flexible protein interactions with GuideFlip}},
author = {K. Yi and Q. Chen and D. Zhang and P. Tian and J. L. Wagstaff and S. H. McLaughlin and C. G. Tate and K. Jamali and S. H. W. Scheres},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.27.754145},
url = {https://www.biorxiv.org/content/10.64898/2026.09.27.754145v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - De novo design of flexible protein interactions with GuideFlip
AU - K. Yi
AU - Q. Chen
AU - D. Zhang
AU - P. Tian
AU - J. L. Wagstaff
AU - S. H. McLaughlin
AU - C. G. Tate
AU - K. Jamali
AU - S. H. W. Scheres
PY - 2026
DA - 2026/09/27
PB - bioRxiv
DO - 10.64898/2026.09.27.754145
UR - https://www.biorxiv.org/content/10.64898/2026.09.27.754145v1
AB - De novo design of protein binders requires a target structure. However, for flexible targets, such as intrinsically disordered proteins, this structure does not exist until the binder has stabilized the interaction. Such targets are therefore difficult for methods that separate structure generation from sequence design. We introduce GuideFlip, which co-designs structure and sequence through guided discrete flow matching: binder residues are assigned progressively while the complex is re-predicted at each step, allowing the evolving interface to affect the design process. GuideFlip reduces the hydrophobic bias of direct AlphaFold optimization and improves in silico success rates over existing approaches. We release a database of binder candidates for 177 human disordered proteins. Experimentally, we obtain de novo binders to the C-terminus of -synuclein and the disordered amino terminus of RBX1 with hit rates of 13.5% and 41.7%, respectively, and we confirm the epitopes of selected binders by NMR and mutagenesis. Applying GuideFlip to flexibility on the binder side, we design a nanobody that binds the agonist-bound {beta}1-adrenergic receptor in the active state, but not the receptor in its inactive state, with a 75% hit rate and cryo-EM structure confirming the design. GuideFlip enables protein design where bound structures emerge only upon binding.
ER -