Newshot 
Credit: Hiroshi Watanabe/Getty
In 2024, researchers found a new driver of inflammatory bowel disease (IBD): it was a gene called ETS2 that is overactive in immune cells due to a DNA variant that predisposes people to the condition. This variant had previously confounded researchers because it lies in a ‘gene desert’ nowhere near protein-coding sequences.
That discovery had involved gene-editing and other sophisticated molecular biology techniques and identified potential new IBD treatments. Now, researchers at Google DeepMind in London have replicated aspects of the finding using an AI model, and they have done this without lifting a pipette. Their model is called AlphaGenome 2.
“They’ve managed to figure out the answer in 30 minutes, and it took us a year and a half of experiments,” says James Lee, an immunologist and geneticist at the Francis Crick Institute in London who led the 2024 study. “It’s reassuring from our perspective.”
The AlphaGenome 2 model, which was announced today, is an update to an AI tool that predicts the molecular effects of ‘non-coding’ DNA sequences, such as on the expression of other genes. These sequences comprise 98% of the human genome, but they are among the hardest to decipher. The latest model makes these predictions in hundreds of different mouse and human cell types.
Two months ago, Google DeepMind released the AlphaGenome Atlas: these were predictions for every possible single-letter DNA change to the human genome – a total of 9 billion different variants.
These and other predictions were made with a tool called AlphaGenome 1 and came with a major caveat: they did not specify the precise kind of cell – be it antibody-making B cells or pancreatic beta-cells – in which a variant was likely to act. “Having something that cannot predict cell type specificity is a bit of a problem, which is why it hasn’t been hugely useful for us,” says Lee.
But researchers know that many non-coding DNA sequences – including the variant that Lee’s team mapped, which is part of a sequence called a gene enhancer – tend to be active in specific types of cells.
“If you want to understand variants associated with genetic diseases, then you have to ask yourself what are the cell types that are affected,” says Žiga Avsec, a Google DeepMind researcher who leads the AlphaGenome team.
100 million cells
To develop an AI model that could decipher variant effects in diverse cells, Avsec’s team trained AlphaGenome 2 on gene activity and other measurements made in more than 100 million individual cells, across 68 tissues. AlphaGenome 1, by contrast, was fed data collected in ‘bulk’ samples of heterogeneous cells.
The result is a richer, more fine-grained representation of the differences between cells, says Adam Gayoso, a Google DeepMind scientist and co-author of a preprint describing the model on the company’s website.
The model also isn’t limited to making predictions in the 637 types of human and 311 mouse cells it was trained with. Researchers can provide the model with new single-cell gene activity data – such as cells in a disease state – and generate gene variant predictions. This could help researchers more quickly identify variants underlying disease, says Gayoso.
Enjoying our latest content? Log in or create an account to continue
- Access the most recent journalism from Nature's award-winning team
- Explore the latest features & opinion covering groundbreaking research
doi: https://doi.org/10.1038/d41586-026-03673-0
Reprints and permissions
Subjects
- Molecular biology
Latest on:
- Molecular biology
- Human replisomes direct a dedicated leading-strand primase for fork restart Article 11 NOV 26
Human replisomes direct a dedicated leading-strand primase for fork restart
Article 11 NOV 26
- The molecular basis of replication fork restart via repriming by PRIMPOL Article 11 NOV 26
The molecular basis of replication fork restart via repriming by PRIMPOL
Article 11 NOV 26
- Domain-alteration chimeras rewire oncogenic complexes in prostate cancer Article 11 NOV 26
Domain-alteration chimeras rewire oncogenic complexes in prostate cancer
Article 11 NOV 26
- Move over BMI: new obesity definition is better for predicting your health News 11 NOV 26
Move over BMI: new obesity definition is better for predicting your health
News 11 NOV 26
- New culprit in early Alzheimer’s: Blood–brain barrier blocks protective proteins News 11 NOV 26
New culprit in early Alzheimer’s: Blood–brain barrier blocks protective proteins
News 11 NOV 26
- Validation of clinical and preclinical obesity across global cohorts Article 11 NOV 26
Validation of clinical and preclinical obesity across global cohorts
Article 11 NOV 26
Jobs
- Associate or Senior Editor, Communications AI & Computing Job Title: Associate or Senior Editor, Communications AI & Computing Locations: Shanghai, Beijing, Pune, New Delhi, Berlin or Madrid (hybrid) Appli... Shanghai, Beijing, Pune, New Delhi, Berlin or Madrid (hybrid) Springer Nature Ltd
Associate or Senior Editor, Communications AI & Computing
Job Title: Associate or Senior Editor, Communications AI & Computing Locations: Shanghai, Beijing, Pune, New Delhi, Berlin or Madrid (hybrid) Appli...
Shanghai, Beijing, Pune, New Delhi, Berlin or Madrid (hybrid)
Springer Nature Ltd
- Postdoctoral Fellow Postdoctoral Fellow focus on ferroic smart materials: shape-memory alloys, piezoelectric ceramics, and magnetostrictive materials, etc Ningbo, Zhejiang (CN) Center for Advanced Smart Materials (CASM), Yongjiang Laboratory (Y-Lab)
Postdoctoral Fellow
Postdoctoral Fellow focus on ferroic smart materials: shape-memory alloys, piezoelectric ceramics, and magnetostrictive materials, etc
Ningbo, Zhejiang (CN)
Center for Advanced Smart Materials (CASM), Yongjiang Laboratory (Y-Lab)
- Principal Investigator/ Associate Professor PI & Associate Professor class focus on innovative research about ferroic smart materials or technology transfer Ningbo, Zhejiang (CN) Center for Advanced Smart Materials (CASM), Yongjiang Laboratory (Y-Lab)
Principal Investigator/ Associate Professor
PI & Associate Professor class focus on innovative research about ferroic smart materials or technology transfer
Ningbo, Zhejiang (CN)
Center for Advanced Smart Materials (CASM), Yongjiang Laboratory (Y-Lab)
- Open-Rank Faculty Position in Basic Biomedical Research WashU Medicine’s Dept of Anesthesiology seeks applicants for a tenure-track or tenured faculty position in the Division of Basic Research. Saint Louis, Missouri WashU Medicine - Anesthesiology
Open-Rank Faculty Position in Basic Biomedical Research
WashU Medicine’s Dept of Anesthesiology seeks applicants for a tenure-track or tenured faculty position in the Division of Basic Research.
Saint Louis, Missouri
WashU Medicine - Anesthesiology
- Global Recruitment of Outstanding Young Talents We are seeking exceptional candidates who qualify for the National Science Fund for Excellent Young Scholars (Overseas) 1068 Xueyuan Avenue, Shenzhen 518055 P. R. China Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences（CAS)
Global Recruitment of Outstanding Young Talents
We are seeking exceptional candidates who qualify for the National Science Fund for Excellent Young Scholars (Overseas)
1068 Xueyuan Avenue, Shenzhen 518055 P. R. China
Shenzhen Institutes of Advanced Technology (SIAT), Chinese Academy of Sciences（CAS)