Abstract

Solenoid proteins are elongated tandem repeat proteins with diverse biological functions, making them attractive targets for protein design. Previously, we made synthetic solenoids drawing residues from consensus sequence distributions1. Advances in machine learning have transformed our understanding of sequence-structure relationships, enabling new approaches for de novo protein design. We made an in silico evolution platform that couples a solenoid discriminator neural network2 with AlphaFold2 as an oracle within a genetic algorithm. Starting from random sequences, we select α-, β-, and αβ-solenoid backbones, generating structures that span natural and novel solenoid space. We experimentally characterise 41 solenoid designs, with α-solenoids consistently folding as intended, including one structurally validated design that closely matches the design model3. All β-solenoids initially failed, reflecting the difficulty of designing β-strand majority proteins. By introducing terminal capping elements and refining designs based on earlier experimental screens, we generate two β-solenoids that have biophysical properties consistent with their designs. Our approach achieves fold-specific hallucination-based design without depending on explicit structural templates.

REFERENCES

1.    MacDonald, J. T. et al. Synthetic beta-solenoid proteins with the fragment-free computational design of a beta-hairpin extension. Proceedings of the National Academy of Sciences 113, 10346–10351 (2016). 2.    Nikov, G. I., Pretorius, D. & Murray, J. W. SOLeNNoID: a deep learning pipeline for solenoid residue detection in protein structures. Bioinformatics 41, btaf415 (2025). 3.    Pretorius, D. et al. Designing novel solenoid proteins with in silico evolution. Commun Chem 9, 10 (2026).