AI-guided discovery of atypical protein assemblies
-
1.
Sainsbury Laboratory
- 2. The Sainsbury Laboratory
-
3.
Wageningen University & Research
-
4.
Norwich BioScience Institutes
-
5.
Imperial College London
Description
Artificial intelligence (AI) systems such as AlphaFold have transformed structural biology by enabling accurate prediction of protein structures. However, their capacity to uncover new classes of macromolecular assemblies remains largely untapped. We developed the Structural Novelty Index (SNI), a quantitative framework that combines structural modeling with prior knowledge to identify protein complexes that diverge from canonical architectures at scale. As one implementation, we applied SNI to nucleotide-binding, leucine-rich repeat immune receptors (NLRs) to identify unconventional resistosome assemblies. Our analysis led to the discovery of several atypical NLR resistosome complexes, including the undecameric (11-mer) NRC7 resistosome. Our results establish SNI as a scalable approach for discovering atypical protein complexes.
Files
BSPP2026_toghani_v1.pdf
Files
(2.8 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:8e01e38249503a7133a24925f540ec11
|
2.8 MB | Preview Download |
Additional details
Related works
- Is published in
- Preprint: 10.64898/2026.05.03.722499 (DOI)