The SIB team behind PDN’s ViralZone resource co-selected the viruses covered by the modelling, supplied unique, high-quality training data on polyproteins from 699 viruses, and quality-controlled predicted interactions for these proteins. The data on polyproteins – complex precursor proteins produced by 47% of human-infecting viruses, including Zika, dengue and poliovirus – were generated in a PDN project that started in January this year.
The protein modelling by AlphaFold was an international collaboration that includes the European Bioinformatics Institute of the European Molecular Biology Laboratory (EMBL-EBI), NVIDIA, Google DeepMind, Seoul National University, the University of Glasgow, Coalition for Epidemic Preparedness Innovations, Sungkyunkwan University and SIB.
The new data are openly available in the AlphaFold Protein Database, NVIDIA dataset. They give researchers a head start on understanding currently understudied viruses and developing responses long before any new outbreak.