Abstract
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 for identifying protein complexes that diverge from canonical architectures. As one implementation of SNI, we developed SNI NRC-Hexa , to identify unconventional resistosomes formed by nucleotide-binding, leucine-rich repeat immune receptors (NLRs). We used it to analyze AlphaFold 3 models of 637 non-redundant NRC proteins from 346 genomes representing 85 plant species. This analysis identified candidates with predicted architectures distinct from the canonical hexameric resistosomes of NRC proteins. Biochemical purification and negative-stain transmission electron microscopy of NRC7 orthologs from multiple species supported the SNI prediction and revealed an unexpected undecameric (11-mer) assembly. Our results establish SNI as a scalable approach for discovering atypical protein complexes.
Funding Information
  • Biotechnology and Biological Sciences Research Council (BB/P012574)
  • Biotechnology and Biological Sciences Research Council (BBS/E/J/000PR9795)
  • Biotechnology and Biological Sciences Research Council (BBS/E/J/000PR9796)
  • Biotechnology and Biological Sciences Research Council (BBS/E/J/000PR9797)
  • Biotechnology and Biological Sciences Research Council (BBS/E/J/000PR9798)
  • European Research Council (743165)
  • Engineering and Physical Sciences Research Council (EP/Y032187/1)
  • Google (United Kingdom) (Bifrost)
  • The Khalifa Center for Genetic Engineering and Biotechnology
  • State of Baden-Württemberg (bwHPC Helix (RV bw25K002))
  • Deutsche Forschungsgemeinschaft (INST 35/1597-1 FUGG)