Poster
Yu Sugihara
Postdoctoral scientist
The Sainsbury Laboratory
NORWICH, England, United Kingdom
AmirAli Toghani (he/him/his)
PhD Student
The Sainsbury Laboratory
Norwich, England, United Kingdom
Raoul Frijters
Rijk Zwaan Breeding B.V., Department of Biotechnology
Fijnaart, Noord-Brabant, Netherlands
Tolga Bozkurt, PhD (he/him/his)
Reader
Imperial College London
London, England, United Kingdom
Ryohei Terauchi, PhD
Professor
Kyoto University
Muko, Kyoto, Kyoto, Japan
Sophien Kamoun
Group leader
The Sainsbury Laboratory
Norwich, England, United Kingdom
NLR proteins are intracellular immune receptors present across all kingdoms of life, with exceptional diversification in plants. In plant immunity, paired NLRs consist of sensors, which detect pathogens, and helpers, which execute immune responses. However, the classification of these paired NLRs has conventionally depended on the presence of non-canonical integrated domains, which are absent in helper NLRs. Here, we propose that the AI system AlphaFold 3 can classify paired NLR proteins into sensor or helper categories based on predicted structural characteristics. Helper NLRs showed higher AlphaFold 3 confidence scores than sensors when modelled in oligomeric configurations. Furthermore, funnel-shaped structures—essential for activating immune responses—were predicted in helpers but not in sensors. These approaches could overcome the limitations of sequence-based annotation methods and provide new insights into the structural and functional organization of immune receptors.