Google DeepMind has announced AlphaGenome 2, a DNA sequence model that predicts how genetic variants affect hundreds of human cell types to help researchers uncover the cellular drivers of disease.
By Hermes Vector
Google DeepMind has announced AlphaGenome 2, a next-generation DNA sequence model that predicts how DNA sequences and their variations impact specific human cell types, giving scientists a tool to uncover the cellular drivers of disease.
AlphaGenome 2 predicts how genetic variants affect hundreds of human cell types. It is the successor to AlphaGenome, which DeepMind launched last year to predict how DNA variants affect molecular activity across broad tissues. The company also previously released AlphaGenome Atlas, a platform containing predictions for all 9 billion possible single-letter changes in the human genome.
By zooming in from broad tissue averages to individual cell types and cell states, and redesigning the model’s architecture, AlphaGenome 2 represents what DeepMind describes as a step-change improvement in variant predictive performance. It allows researchers to predict variant effects in disease-relevant cells that would be missed in broad-tissue models, as well as predictions for cell and disease states that the model hasn’t seen before.
AlphaGenome 2 identifies nearly twice as many variants that change gene expression in cells, compared to DeepMind’s previous state-of-the-art model. Trained on more than 100 million individual cell profiles across 68 tissues, the model turns static cell atlases into a predictive engine for human genetics, according to DeepMind.
The first AlphaGenome model took a million-letter DNA sequence and predicted properties across thousands of experiments from many tissues all at once. DeepMind says this parallel approach spread the model’s capacity thin and made it hard to capture subtle differences between closely related cell types.
AlphaGenome 2 is a conditional model that predicts DNA effects for one condition—defined as a tissue, cell type or state—at a time. Alongside the million-letter DNA sequence, it uses the target biological condition as input at every stage of its architecture. This allows it to learn how the same stretch of DNA is read differently across cell types.
The model can take a specific biological condition chosen from a reference catalog of cell types or generated on the fly from a scientist’s own single-cell experiment via DeepMind’s cell encoder. It also allows cross-modality imputation, enabling AlphaGenome 2 to predict missing experimental data. If a scientist inputs just one measurement, like single-cell gene activity, AlphaGenome 2 can then predict unmeasured properties, such as chromatin accessibility.
AlphaGenome 2 was trained on both bulk and single-cell data from human and mouse samples, including over 107 million individual cell profiles. It predicts the same core experimental readouts of DNA function as AlphaGenome—such as gene expression, histone modifications and chromatin accessibility—but also DNA methylation, a widely requested readout.
On the TenK10K dataset, a large single-cell map of 28 primary immune cell types, AlphaGenome 2 reliably identified nearly twice as many causal variants (30% vs. 16%) and directional gene effects (43% vs. 23%) as the original AlphaGenome fine-tuned on single-cell data and other specialized tools.
DeepMind says AlphaGenome 2 reproduced a finding from a recent landmark study showing that a variant in a distant regulatory switch drives IBD by overactivating the ETS2 gene in gut immune cells (macrophages). Making predictions across various immune cell types in the gut, AlphaGenome 2 singled out the causal variant and showed that it selectively boosts the ETS2 gene in gut macrophages, leaving other cell types and genes largely unaffected.
The model can also generalize to entirely new single-cell experiments without needing to be retrained. Scientists can upload a single-cell RNA-seq snapshot of gene activity from just a few dozen cells. For example, given unseen single-cell data from a COVID-19 mRNA vaccine study, AlphaGenome 2 distinguished vaccine-activated immune T cells from resting ones. It also revealed that a variant linked to severe COVID-19 disrupts gene activity more strongly when cells are in this activated state—an effect that would be missed in unactivated cells.
AlphaGenome 2 is available today for non-commercial research via the AlphaGenome API, and in private preview for commercial research. DeepMind says it will soon release AlphaGenome 2 Skills in Google Antigravity, its agentic development platform.
DeepMind notes that AlphaGenome and AlphaGenome 2 are intended for research use only and have not been validated or approved for clinical or diagnostic purposes.
Sources
This article was drafted with AI assistance and checked against the sources above. Company claims are reported as claims. Cover image is AI-generated.
The day's checked news, by email
One short email a day with the top stories. Free, and you can unsubscribe in one click.
Or follow for the latest news:
No comments yet. Start the discussion.
University of Oklahoma paleontologists found a 450-million-year-old crinoid fossil with preserved tube feet, only the second known example of soft tissue in crinoids.
UC San Francisco researchers identified a slow dopamine pathway linking the gut and brain that helps explain how flavors become enjoyable over time, based on mouse experiments and small human imaging studies.