NVIDIA Joins Coalition to Release Open Dataset of Viral Protein Structures

NVIDIA is collaborating with organizations including Google DeepMind and the European Molecular Biology Laboratory’s European Bioinformatics Institute (EMBL-EBI) to release an open dataset of viral protein structures. This initiative aims to give scientists a head start against diseases by providing predicted 3D structures for the protein complexes of more than 2,800 viruses. The dataset is openly available to any scientist through the AlphaFold Database, contributing to the existing repository of over 260 million protein and protein complex predictions.

The collaboration also involves the Coalition for Epidemic Preparedness Innovations, Seoul National University, Sungkyunkwan University, the Swiss Institute of Bioinformatics, and the University of Glasgow. The release coincides with a United Nations General Assembly meeting on pandemic prevention, preparedness, and response.

NVIDIA is also releasing the BioNeMo Structure Prediction Pipeline, a GPU-accelerated workflow used to generate the dataset, allowing researchers to predict 3D structures for their own protein targets. Approximately 30% of the protein interactions in the database are new to science, offering new insights for the biological community to explore and harness.

Joe Grove, professor of molecular virology at the Medical Research Council-University of Glasgow Centre for Virus Research, emphasized the importance of stockpiling knowledge ahead of time to prepare for future pandemics. Jo McEntyre, interim director of EMBL-EBI, highlighted the critical role of open data in understanding viral diagnostics and developing treatments and vaccines.

Source: nvidia-newsroom