Adding noise sometimes leads to greater diversity during inverse folding inference

Summary

For Inverse folding models, adding noise during inference sometimes leads to greater diversity (1). Perturbations in this case were carried using Rosetta.

Figures

Figure 3 from (1)

See also

• Adding noise while training non-Ab inverse folding models improves self-consistency while worsening sequence recovery

1.

Liu J, Guo Z, You H, Zhang C, Lai L. All‐Atom Protein Sequence Design Based on Geometric Deep Learning. Angewandte Chemie International Edition. 2024;63(50). Available from: https://doi.org/10.1002/anie.202411461