Decoding the blueprint of receptor binding by filoviruses through large-scale binding assays and machine learning

SUMMARYEvidence suggests that bats are important hosts of filoviruses, yet the specific species involved remain largely unidentified. Niemann-Pick C1 (NPC1) is an essential entry receptor, with amino acid variations influencing viral susceptibility and species-specific tropism. Herein, we conducted combinatorial binding studies with seven filovirus glycoproteins (GPs) and NPC1 orthologs from 81 bat species. We found that GP-NPC1 binding correlated poorly with phylogeny. By integrating binding assays with machine learning, we identified genetic factors influencing virus-receptor binding and predicted GP-NPC1 binding avidity for additional filoviruses and bats. Moreover, combining receptor binding avidities with bat geographic distribution and the locations of previous Ebola outbreaks allowed us to rank bats by their potential as Ebola virus hosts. This study represents a comprehensive investigation of filovirus receptor binding in bats (1,484 GP-NPC1 pairs, 11 filoviruses and 135 bats), and describes a multidisciplinary approach to predict susceptible species and guide filovirus host surveillance.Graphical AbstracteTOC BlurbLasso et al. combine large-scale binding assays and machine learning to uncover molecular rules of filovirus-receptor binding, predict receptor binding strength, and identify bats with the potential to act as filovirus hosts. These findings offer actionable data to design targeted surveillance strategies and anticipate potential animal-to-human transmission events.