--- title: How Open Science Can Help Researchers Prepare for the... description: NVIDIA, Google DeepMind, and EMBL-EBI have released an open dataset of predicted 3D protein structures for over 2,800 viruses through the AlphaFold Database,... canonical: https://daily.dev/posts/how-open-science-can-help-researchers-prepare-for-the-next-pandemic-j2nxjuah9 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How Open Science Can Help Researchers Prepare for the Next Pandemic | daily.dev og:description: NVIDIA, Google DeepMind, and EMBL-EBI have released an open dataset of predicted 3D protein structures for over 2,800 viruses through the AlphaFold Database,... og:url: https://daily.dev/posts/how-open-science-can-help-researchers-prepare-for-the-next-pandemic-j2nxjuah9 og:image: https://api.daily.dev/og/posts/J2NXjUah9.png og:image:alt: How Open Science Can Help Researchers Prepare for the Next Pandemic og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # How Open Science Can Help Researchers Prepare for the Next Pandemic **[NVIDIA](https://daily.dev/sources/nvidia)** · 5 min read · 0 upvotes · 0 comments ## Summary NVIDIA, Google DeepMind, and EMBL-EBI have released an open dataset of predicted 3D protein structures for over 2,800 viruses through the AlphaFold Database, aiming to give scientists a head start against future pandemics. The structures were generated using AlphaFold2 optimized with NVIDIA's BioNeMo Inference Runtime, allowing bulk prediction of viral protein complexes in minutes instead of the years traditional X-ray crystallography requires. About 30% of the protein interactions in the dataset are entirely new to science. NVIDIA is also open-sourcing the BioNeMo Structure Prediction Pipeline used to generate the data, and the collaboration includes CEPI, Seoul National University, Sungkyunkwan University, the Swiss Institute of Bioinformatics, and the University of Glasgow. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What new viral protein structure dataset did NVIDIA and Google DeepMind release for pandemic research? NVIDIA, Google DeepMind, and EMBL-EBI released predicted 3D structures for protein complexes of more than 2,800 viruses through the AlphaFold Database. The structures were inferred using AlphaFold2 optimized with NVIDIA's BioNeMo Inference Runtime, scaling inference to thousands of viral proteomes. About 30% of the protein interactions are entirely new to science, not previously documented in the Protein Data Bank. _Researchers tracking new structural biology datasets can follow developments like this one on daily.dev._ ### How does using AlphaFold2 with NVIDIA BioNeMo compare to traditional X-ray crystallography for determining protein structures? AlphaFold2 optimized with NVIDIA BioNeMo predicts a protein structure in minutes and can run in bulk across thousands of proteins, while traditional crystallization and X-ray methods can take years and cost thousands of dollars per structure. High-confidence AI predictions can then be verified experimentally, dramatically accelerating structural biology research. _Developers evaluating AI-accelerated scientific pipelines can weigh trade-offs like these on daily.dev._ ### Where can I access the BioNeMo Structure Prediction Pipeline to predict protein structures for my own targets? NVIDIA openly released the BioNeMo Structure Prediction Pipeline, the GPU-accelerated workflow used to generate the viral protein complex dataset, allowing researchers to go from a protein sequence to a predicted 3D structure for their own targets. It is available on GitHub under NVIDIA-BioNeMo alongside the broader BioNeMo toolkit. _Biology-focused developers building on open GPU pipelines can track releases like this on daily.dev._ ## Similar posts on daily.dev - [How to Predict Biomolecular Structures Using the OpenFold3 NIM](https://daily.dev/posts/how-to-predict-biomolecular-structures-using-the-openfold3-nim-ygqkqxkos) · NVIDIA Developer · 1 upvotes · 0 comments - [What’s next for AlphaFold: A conversation with a Google DeepMind Nobel laureate](https://daily.dev/posts/what-s-next-for-alphafold-a-conversation-with-a-google-deepmind-nobel-laureate-bka0wcmlt) · MIT Technology Review · 0 upvotes · 0 comments - [AlphaFold: Five years of impact](https://daily.dev/posts/alphafold-five-years-of-impact-tqbavrueh) · DeepMind · 0 upvotes · 0 comments - [Predicting Molecular Structures with AlphaFold 2 and 3](https://daily.dev/posts/predicting-molecular-structures-with-alphafold-2-and-3-qhqe8pzbn) · DigitalOcean Community · 0 upvotes · 0 comments - [How to Accelerate Protein Structure Prediction at Proteome-Scale](https://daily.dev/posts/how-to-accelerate-protein-structure-prediction-at-proteome-scale-nqxd3k5yj) · NVIDIA Developer · 0 upvotes · 0 comments --- Tags: [#nvidia](https://daily.dev/tags/nvidia) [View this post on daily.dev](https://daily.dev/posts/how-open-science-can-help-researchers-prepare-for-the-next-pandemic-j2nxjuah9) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"How Open Science Can Help Researchers Prepare for the Next Pandemic","url":"https://daily.dev/posts/how-open-science-can-help-researchers-prepare-for-the-next-pandemic-j2nxjuah9","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-open-science-can-help-researchers-prepare-for-the-next-pandemic-j2nxjuah9"},"datePublished":"2026-09-24T17:40:42.869Z","dateModified":"2026-09-24T17:41:06.265Z","description":"NVIDIA, Google DeepMind, and EMBL-EBI have released an open dataset of predicted 3D protein structures for over 2,800 viruses through the AlphaFold Database,...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/30ba53f78211db77f02b1f0043299b8f?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/30ba53f78211db77f02b1f0043299b8f?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"NVIDIA","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"NVIDIA","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/236a5c1f410e450b8d696cf3a4bbe374","url":"https://daily.dev/sources/nvidia"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-open-science-can-help-researchers-prepare-for-the-next-pandemic-j2nxjuah9","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"nvidia","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"NVIDIA","item":"https://daily.dev/sources/nvidia"},{"@type":"ListItem","position":3,"name":"How Open Science Can Help Researchers Prepare for the Next Pandemic"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/how-open-science-can-help-researchers-prepare-for-the-next-pandemic-j2nxjuah9#faq","mainEntity":[{"@type":"Question","name":"What new viral protein structure dataset did NVIDIA and Google DeepMind release for pandemic research?","acceptedAnswer":{"@type":"Answer","text":"NVIDIA, Google DeepMind, and EMBL-EBI released predicted 3D structures for protein complexes of more than 2,800 viruses through the AlphaFold Database. The structures were inferred using AlphaFold2 optimized with NVIDIA's BioNeMo Inference Runtime, scaling inference to thousands of viral proteomes. About 30% of the protein interactions are entirely new to science, not previously documented in the Protein Data Bank. Researchers tracking new structural biology datasets can follow developments like this one on daily.dev."}},{"@type":"Question","name":"How does using AlphaFold2 with NVIDIA BioNeMo compare to traditional X-ray crystallography for determining protein structures?","acceptedAnswer":{"@type":"Answer","text":"AlphaFold2 optimized with NVIDIA BioNeMo predicts a protein structure in minutes and can run in bulk across thousands of proteins, while traditional crystallization and X-ray methods can take years and cost thousands of dollars per structure. High-confidence AI predictions can then be verified experimentally, dramatically accelerating structural biology research. Developers evaluating AI-accelerated scientific pipelines can weigh trade-offs like these on daily.dev."}},{"@type":"Question","name":"Where can I access the BioNeMo Structure Prediction Pipeline to predict protein structures for my own targets?","acceptedAnswer":{"@type":"Answer","text":"NVIDIA openly released the BioNeMo Structure Prediction Pipeline, the GPU-accelerated workflow used to generate the viral protein complex dataset, allowing researchers to go from a protein sequence to a predicted 3D structure for their own targets. It is available on GitHub under NVIDIA-BioNeMo alongside the broader BioNeMo toolkit. Biology-focused developers building on open GPU pipelines can track releases like this on daily.dev."}}]} ```