(Press-News.org) A new collaboration between EMBL’s European Bioinformatics Institute (EMBL-EBI), Google DeepMind, NVIDIA, and Seoul National University has made millions of AI-predicted protein complex structures openly available through the AlphaFold Database. To maximise global health impact, the dataset prioritises proteins important for understanding human health and disease. This is the largest dataset of protein complex predictions currently available.
Proteins are the building blocks of life. They interact to create protein complexes which fulfil biological functions. By visualising protein interactions, scientists can uncover the molecular mechanisms that drive cell behaviour, identify what goes wrong when someone gets sick, and develop new drugs and therapies. Predicting the structure of protein complexes is extremely challenging because, in nature, proteins change shape and interact in many different ways.
“Science thrives on collaboration,” said Jo McEntyre, Interim Director of EMBL-EBI. “By making this foundational protein complex dataset openly available to the world, we’re inviting researchers to test, refine, and build on it to drive the next wave of biological discoveries.”
Protein complexes for global health impact
The latest AlphaFold Database update spans millions of homodimers – protein complexes formed of two identical proteins. It focuses on 20 of the most studied species, including humans, as well as the World Health Organization’s bacterial priority pathogens list. This approach aims to bring significant and immediate value for global health challenges.
“By expanding the AlphaFold Database to include protein complexes, we are addressing a critical need expressed by the scientific community,” said Anna Koivuniemi, Head of the Google DeepMind Impact Accelerator. “We hope that by lowering the barrier to these complex predictions, we can empower researchers everywhere to pursue the next wave of discoveries that could ultimately improve human health on a global scale.”
Scientific expertise meets technical innovation
The collaboration builds on Google DeepMind’s AI system AlphaFold, which, since 2021, accurately predicted the structure of millions of proteins. To democratise access to AlphaFold predictions, Google DeepMind and EMBL-EBI developed the AlphaFold Database, an open resource that anyone can access. The database has over 3.4 million users from 190 countries.
Through ongoing dialogue with the scientific community, a clear need emerged to expand the AlphaFold database to include protein complexes. In response to this need, EMBL-EBI, Google DeepMind, NVIDIA, and Seoul National University teamed up, contributing specialist expertise and resources, to calculate and integrate millions of protein complexes into the AlphaFold Database.
The collaboration brought together deep biological expertise and technical innovations. NVIDIA and the Steinegger Lab at the Seoul National University developed the methodology, based on Google DeepMind’s AI system AlphaFold, including accelerations to multiple sequence alignment calculations and deep learning inference. NVIDIA provided cutting-edge AI infrastructure and scaled out inference pipelines to overcome limitations that historically made this scale of calculations challenging. EMBL-EBI enabled the collaboration by bringing the other parties together and contributing expertise in scientific and biodata management, as well as analysis. As a champion of open science, EMBL-EBI, together with Google DeepMind, integrated the new dataset into the AlphaFold Database.
"NVIDIA's ambition is to consistently contribute orders-of-magnitude accelerations for fundamental digital biology workloads, enabling what was not possible before,” said Anthony Costa, NVIDIA Director of Digital Biology. “This release is a great example of how AI infrastructure and software can uniquely enable new scales of biological understanding."
“By making predicted protein complexes accessible at an unprecedented scale, we are illuminating an unseen landscape of molecular interactions across the tree of life,” explained Martin Steinegger, Associate Professor at Seoul National University.
Open science at scale
It takes a blend of AI-scale infrastructure and deep technical knowledge in accelerating complex workflows to generate AI predictions for protein complexes at this scale. The collaboration is centrally hosting data that would otherwise require around 17 million hours of GPU (graphics processing unit) computing to recreate.
By making these calculations once and adding the information into the AlphaFold Database, this collaboration aims to help democratise access to protein complex predictions. It enables scientists everywhere to investigate how proteins interact in the vast protein universe, and accelerate discoveries that could lead to new medicines, new products, and a deeper understanding of life itself.
This is the first step in an ambition to add a wide range of protein complex structure predictions to the AlphaFold Database. The partnership has already calculated predictions for 30 million complexes. Of these, 1.7 million high-confidence homodimer predictions have been added to the AlphaFold Database. Another 18 million are lower-confidence homodimers, which are available as a list and for bulk download. The rest are heterodimers, currently being analysed and assessed. More protein complex predictions will be calculated and high-confidence predictions will be added to the AlphaFold Database in the coming months. The work is described in more detail in a preprint.
“The human genome has just over 20,000 different proteins. Despite this relatively small genome, human beings display incredibly complex pathways, processes and regulation. Much of this complexity arises from the intermolecular interactions between proteins, and with small molecule ligands and DNA. Adding predicted protein-protein homodimeric interactions to the AlphaFold Database is a first step towards a comprehensive description of the human interactome, the basis by which human biology will be described and understood. This has relevance for the design of new therapeutics, understanding host-pathogen interactions, and more. Making these structures accessible to all, allows every researcher around the world to build on these data, moving one step closer to predicting the biology of life,” said Dame Janet Thornton, Director Emeritus of EMBL-EBI.
EMBL’s European Bioinformatics Institute (EMBL-EBI)
EMBL’s European Bioinformatics Institute (EMBL-EBI) is a global leader in the storage, analysis, and dissemination of large biological datasets. We help scientists realise the potential of big data by enhancing their ability to exploit complex information, enabling responsible AI development, and making scientific outcomes available to the community, to make discoveries that benefit humankind.
We are at the forefront of computational biology research, with work spanning sequence analysis methods, multi-dimensional statistical analysis and data-driven biological discovery, from plant biology to mammalian development and disease.
We are part of the European Molecular Biology Laboratory (EMBL) and are located on the Wellcome Genome Campus, one of the world’s largest concentrations of scientific and technical expertise in genomics.
Google Deepmind
Google DeepMind is a world-leading AI research lab with British heritage and an international team, committed to building AI responsibly, delivering scientific breakthroughs, and creating products that improve billions of lives. The unit’s breakthroughs over the last decade include AlphaGo - the first computer program to defeat a Go world champion, Transformers - neural networks that underpin all modern language models, AlphaFold - an AI model that can accurately predict the structure and interactions of proteins, DNA, RNA, ligands and more, and Gemini, a family of versatile AI models built from the ground up for multimodality, seamlessly combining and understanding text, code, images, audio and video.
Seoul National University
Seoul National University is a leading research university in the Republic of Korea, dedicated to advancing knowledge through education, research, and public service.
With strengths across a broad range of disciplines, the University fosters interdisciplinary collaboration in fields including life sciences, engineering, and data-driven science.
Through global partnerships, Seoul National University contributes to scientific innovation and to addressing challenges that impact society worldwide.
END
Millions of protein complexes added to AlphaFold Database shed light on how proteins interact
2026-03-17
ELSE PRESS RELEASES FROM THIS DATE:
Researchers show dinos hatched eggs less efficiently than modern birds
2026-03-17
What do we really know about how oviraptors – bird-like but flightless dinosaurs – hatched their eggs? Did they use environmental heat, like crocodiles, or body heat from an adult, like birds? In a new Frontiers in Ecology and Evolution study, researchers in Taiwan examined the brooding behavior and hatching patterns of oviraptors. They also modelled heat transfer simulations of oviraptor clutches and compared hatching efficiency to modern birds. To do so, they experimented with a life-sized oviraptor incubator and eggs.
“We show the difference ...
Neuroscientist from US-Mexico border dismantles science’s class problem from the inside
2026-03-17
LA JOLLA, California, USA, 17 March 2026 — A first-generation college student who once needed research stipends to pay rent has spent the last decade building the infrastructure to ensure others do not face the same calculus. Dr. Christian Cazares, a postdoctoral fellow in the Department of Cognitive Science at the University of California, San Diego, grew up in Calexico, California, a border town where more than eighty percent of his schoolmates qualified for the free lunch program. In a new interview published today in the Genomic Press journal Brain Medicine, Dr. ...
What flocking birds can teach AI
2026-03-17
Among the primary concerns surrounding artificial intelligence is its tendency to yield erroneous information when summarizing long documents. These “hallucinations” are problematic not only because they convey falsehoods, but also because they reduce efficiency—sorting through content to search for mistakes of AI outputs is time-consuming.
To help address this challenge, a team of computer scientists has created an algorithmic framework that draws from a natural phenomenon—bird flocking—by mimicking how birds efficiently self-organize. The framework serves as a preprocessing step for large language models ...
The scientist who warned that profit, not science, decides which drugs reach patients
2026-03-17
MONTREAL, Quebec, CANADA, 17 March 2026 – Dr. Gabriella Gobbi, Professor of Psychiatry at McGill University, Canada Research Chair (Tier 1) in Therapeutics for Mental Health, Staff Psychiatrist at the McGill University Health Center (MUHC), and Senior Scientist, Brain Repair and Integrative Neuroscience Program at the Research Institute of the MUHC, and President-Elect of the Collegium Internationale of Neuropsychopharmacology (CINP), has issued an unambiguous challenge to the global drug-development system, ...
A sea slug taught her how the brain works, and she never looked back
2026-03-17
PITTSBURGH, Pennsylvania, USA, 17 March 2026 — The girl was maybe fourteen. In Nottingham, England, there was a state comprehensive school where egalitarianism was practiced the way religion is practiced in some households: fervently, and with suspicion toward anyone who broke ranks. In biology class, Mary Phillips stood up and said something that got her into trouble. She said the brain was superior to every other organ in the body. Her argument was precise: you could transplant a heart, a kidney, a liver. You could not transplant the brain. The teachers disapproved. Her classmates shifted ...
KIER cracks seawater electrolysis deposit problem with dual electrode system
2026-03-17
A research team led by Dr. Ji-Hyung Han from the Convergence Research Center of Sector Coupling & Integration at the Korea Institute of Energy Research (President Yi, Chang-Keun, hereinafter “KIER”) has developed a new seawater electrolysis system that overcomes the precipitate formation issue long blamed for performance degradation and process interruptions, while also presenting a new direction for further technology advancement.
Water electrolysis is a technology that produces hydrogen, an eco-friendly energy source, by splitting water. Recently, amid the global freshwater shortage, seawater electrolysis using seawater has been gaining attention as a promising ...
Automated intervention shows significant increase in smoking cessation behavior
2026-03-17
Philadelphia, March 17, 2026 – Researchers at Children’s Hospital of Philadelphia (CHOP) found that a new automated tobacco treatment system integrated into routine pediatric care helped drive a 3.9% absolute increase in smoking cessation among mothers – a population-level impact that could translate to tens of thousands of parents quitting each year and protect hundreds of thousands of children from harmful secondhand smoke exposure. The study, published today in Pediatrics, demonstrates how technology can scale ...
Top AI coding tools make mistakes one in four times
2026-03-17
New research from the University of Waterloo shows that artificial intelligence (AI) still struggles with some basic software development tasks, raising questions about how reliably AI systems can assist developers.
As Large Language Models (LLMs) are increasingly incorporated into software development, developers have struggled to ensure that AI-generated responses are accurate, consistent, and easy to integrate into larger development workflows.
Previously, LLMs ...
Hidden acid imbalance in kidney disease raises red flags
2026-03-17
Niigata Japan - A Japanese registry has identified a blind spot in the routine care of patients with chronic kidney disease (CKD). Serum bicarbonate levels are rarely measured, leaving metabolic acidosis largely undetected and hence, undertreated.
Metabolic acidosis is a common complication of CKD and is associated with muscle loss, bone disease, insulin resistance, accelerated kidney decline, and increased mortality. Clinical guidelines recommend treatment when the serum bicarbonate level falls below 22 mEq/L. However, real-world data from Asia have been limited.
To address this, Mai Tanaka and colleagues extracted nationwide data ...
No evidence to suggest medicinal cannabis is effective for depression, anxiety or PTSD: research
2026-03-17
Australian media release (see below for North American media release)
A landmark Lancet Psychiatry paper published today – the largest-ever review of the safety and efficacy of cannabinoids across a range of mental health conditions – found no evidence that medicinal cannabis is effective in treating anxiety, depression or post-traumatic stress disorder (PTSD).
The study comes amid more than one million prescription approvals and a tripling of sales of cannabinoid medications (including ...