Home › AI › NVIDIA and DeepMind Release 3D Structu
AI

NVIDIA and DeepMind Release 3D Structures for 2,800 Viruses

A global research coalition has added predicted protein complexes for over 2,800 viruses to the open-access AlphaFold Database.

WHAT YOU NEED TO KNOW
  • The dataset covers predicted 3D structures for protein complexes across more than 2,800 viruses.
  • Roughly 30 percent of the added interactions represent shapes never previously recorded in the Protein Data Bank.
  • NVIDIA released the BioNeMo Structure Prediction Pipeline as an open GPU-accelerated workflow.
  • The AlphaFold Database now holds over 260 million protein and protein complex predictions.

NVIDIA has joined a global research coalition to publish predicted 3D protein complex structures for more than 2,800 viruses, making the data openly accessible through the AlphaFold Database.

The coalition includes Google DeepMind, the European Molecular Biology Laboratory’s European Bioinformatics Institute (EMBL-EBI), the Coalition for Epidemic Preparedness Innovations, Seoul National University, Sungkyunkwan University, the Swiss Institute of Bioinformatics, and the University of Glasgow. Researchers generated the dataset using AlphaFold2, an artificial intelligence model developed by Google DeepMind, running with optimizations from the NVIDIA BioNeMo Inference Runtime.

About 30 percent of the protein interactions included in the release have never been documented in the Protein Data Bank, the primary public archive for experimentally determined protein structures. Alongside the viral dataset, NVIDIA released the BioNeMo Structure Prediction Pipeline, the GPU-accelerated software workflow used to predict 3D structures directly from amino acid sequences.

Accelerating Structural Biology

Traditional structural biology techniques, such as protein crystallization and X-ray diffraction, can take years and cost thousands of dollars per structure. AlphaFold2 running on NVIDIA graphics processors predicts those shapes in minutes, allowing scientists to generate bulk models that can later be verified experimentally.

The project mapped viral families that infect humans, spanning common-cold pathogens to emerging threats such as Mpox. Because most viral proteins operate as multi-protein complexes rather than isolated units, mapping these interacting groups provides structural targets for future vaccine and therapeutic research.

With this release, the AlphaFold Database now contains more than 260 million protein and protein complex predictions, covering nearly every cataloged protein known to science. The release coincided with a United Nations General Assembly meeting on pandemic prevention, preparedness, and response convened by the World Economic Forum in New York City.

Xentir Media
Xentir Media NewsroomSource-backed AI and technology coverage, drafted by Xentir's automated editorial system under fixed human-set rules. See our editorial policy and AI usage policy.
J
Jomon · Founder & EditorFounder and editor of Xentir Media. Sets the editorial rules the newsroom system runs under, and is accountable for its corrections. About Jomon · [email protected]
The Xentir Brief
The developments worth knowing — one useful email.
Get the Brief →