Summary
The benefit of including both sequence- and structure-based features during Inverse folding is greater than the sum of each feature’s benefit in isolation (1).
Figures
| SPDesign¹ (distance only) | SPDesign² (+ pre-trained structure) | SPDesign³ (+ sequence profile) | SPDesign (all features) | |
|---|---|---|---|---|
| Backbone atoms distance | ✓ | ✓ | ✓ | ✓ |
| Pre-trained knowledge of structure | ✗ | ✓ | ✗ | ✓ |
| Structural sequence profile | ✗ | ✗ | ✓ | ✓ |
| Perplexity | 5.36 | 4.96 | 3.51 | 2.43 |
| Recovery (%) | 44.60 | 48.81 | 58.76 | 67.05 |
| Table 3 from (1) |
See also
1.
Wang H, Liu D, Zhao K, Wang Y, Zhang G. SPDesign: protein sequence designer based on structural sequence profile using ultrafast shape recognition. Briefings in Bioinformatics. 2024;25(3). Available from: https://doi.org/10.1093/bib/bbae146