Google DeepMind's AlphaGenome AI tackles the 98% of human genome that doesn't code for proteins
14 Sources
[1]
How DeepMind's genome AI could help solve rare disease mysteries
When more than 100 researchers voluntarily locked themselves in a room last year to tackle some of the hardest conditions in medicine, they turned to artificial intelligence. As part of an effort, called the Undiagnosed Hackathon, to crack 29 undiagnosed conditions researchers deployed AlphaGenome
[2]
How AlphaGenome Is Changing the Genomic Research Landscape
The team at Google DeepMind behind that Nobel Prize-winning platform then turned their lens from from the structure of proteins to how these molecules function in the body. Applying similar machine-learning methods, they first developed AlphaMissense, an AI tool for predicting which changes in
[3]
Google DeepMind unleashes new AI AlphaGenome to investigate DNA's 'dark matter'
DeepMind's AlphaGenome AI model could help solve the problem of predicting how variations in noncoding DNA shape gene expression DNA is the blueprint for life, influencing everything about us -- including our health. We know that our genes, the genetic "words" that encode proteins, play a major
[4]
AI tool AlphaGenome predicts how one typo can change a genetic story
The model can predict changes in 11 biological activities across 1 million DNA letters A new deep-learning AI model may help scientists better decipher the plot of the genetic instruction book and learn how typos alter the story. AlphaGenome, created by Google DeepMind, is the latest in an
[5]
Google's AlphaGenome wants to do for DNA what AlphaFold did for ...
Google's new deep learning model can predict the effect of small changes to DNA sequences up to one million base pairs in length and is particularly good with non-coding DNA, which has proven especially difficult to understand. The artificial intelligence (AI) tool - called AlphaGenome - offers
[6]
Even Tech Skeptics Can Cheer AI's Promise in Decoding the 'Dark Genome'
The platform's progress is limited by the lack of experimental data for it to train on, and its advancement depends on humans in the lab cataloging critical data to improve the models. Google DeepMind, the artificial intelligence subsidiary of Alphabet, has made another leap in its efforts to
[7]
AI model from Google DeepMind reads recipe for life in our DNA
An AI model developed by Google's DeepMind could transform our understanding of DNA - the complete recipe for building and running the human body - and its impact on disease and medicine discovery, according to researchers. Called AlphaGenome, the model could help scientists discover why subtle
[8]
DeepMind's New AI Can Read a Million DNA Letters at Once -- and Actually Understand Them
AlphaGenome is reportedly the most comprehensive and accurate DNA sequence model developed to date. Artificial intelligence has gotten a bad reputation lately, and often for good reason. But a team of scientists at Google's DeepMind now claims to have found a revolutionary use case for AI: helping
[9]
Google DeepMind launches AI tool to help identify genetic drivers of disease
AlphaGenome can analyse up to 1m letters of DNA code at once and could pave way for new treatments Researchers at Google DeepMind have unveiled their latest artificial intelligence tool and claimed it will help scientists identify the genetic drivers of disease and ultimately pave the way for new
[10]
Google's new AI tool decodes DNA mutations. Here's how it works
A new AI model by Google DeepMind can decipher DNA and predict mutations, opening new doors for disease research. Our DNA is made of millions of combinations of the genomes that create the human body. Even the smallest changes in these sequences, or in how they act, can change the functioning of
[11]
Google unveils AI tool probing mysteries of human genome
Paris (France) (AFP) - Google unveiled an artificial intelligence tool Wednesday that its scientists said would help unravel the mysteries of the human genome -- and could one day lead to new treatments for diseases. The deep learning model AlphaGenome was hailed by outside researchers as a
[12]
Google DeepMind open-sources AlphaGenome medical research model
Google DeepMind open-sources AlphaGenome medical research model Google DeepMind today open-sourced AlphaGenome, an artificial intelligence model that researchers can use to study biological processes. The Alphabet Inc. unit first debuted the algorithm in June. Until now, it was only accessible
[13]
DeepMind's AlphaGenome: How AI Is Reading DNA's Code of Life
Scientists have traditionally referred to DNA as the blueprint to life. Another potent new artificial intelligence (AI) application, the AlphaGenome created by DeepMind, a division of Google, is enabling researchers to perceive that recipe in a brand-new approach. This model is published in the
[14]
AlphaGenome explained: How Google DeepMind is using AI to rewrite genomics research
The history of genomics has long been a story of reading a book where only every fiftieth page made sense. While the Human Genome Project gave us the full sequence of human DNA over two decades ago, we were largely illiterate in the language of the "non-coding" genome - the 98% of our genetic code
Share
Copy Link
Google DeepMind unveiled AlphaGenome, a deep-learning AI model that predicts how mutations in non-coding DNA affect gene expression across sequences up to one million base pairs long. The tool outperforms existing models in 25 out of 26 tasks and is already being used by nearly 3,000 scientists worldwide to investigate rare diseases, cancer mutations, and design new gene therapies.
AlphaGenome Addresses Biology's Grand Challenge
Google DeepMind has released AlphaGenome, a deep-learning AI model designed to decode the 98% of the human genome that doesn't produce proteins
1
. Described in Nature on January 28, this research tool can analyze DNA sequences up to one million base pairs in length and predict how mutations in non-coding DNA affect gene expression and other biological processes4
. The model represents what researchers call a "Swiss Army knife for exploring non-coding DNA," offering unprecedented precision in modeling intricate genomic processes2
.
Source: Digit
Deciphering non-coding regions has long been one of biology's most stubborn challenges. Once dismissed as "junk DNA," these sequences are now understood to be crucial for determining when, where, and how genes are turned on and off
3
. Mutations in these areas are especially vexing to researchers seeking to uncover the genetic basis for rare, often fatal genetic diseases. "These are variants that, to be quite honest, often get triaged," says Eric Klee, a bioinformatician at the Mayo Clinic who tested AlphaGenome at the Undiagnosed Hackathon in September 20251
.How AlphaGenome Predicts Genetic Changes Across Multiple Tasks
AlphaGenome takes a DNA sequence as input and predicts 11 types of biological signals that help determine how genes function inside cells
2
. These include whether a gene is activated or silenced, where gene activity begins, how genetic messages are edited, how tightly DNA is packed, which regulatory proteins bind to it, and how distant regions of the genome interact. The model can pinpoint biologically important spots down to single base resolution, a significant improvement over its predecessor Borzoi, which identified points of biological interest in 32 base-pair bins4
.
Source: ET
The tool matched or outperformed other state-of-the-art models in 25 out of 26 tasks predicting the effects of genetic variations
5
. For example, AlphaGenome identified gene activity changes in certain cell types 14.7 percent better than Borzoi24
. The team also successfully simulated known DNA mutations responsible for a type of leukemia, predicting the same results observed in laboratory experiments5
.From AlphaFold to AlphaGenome: Building a Molecular Prediction Platform
AlphaGenome extends Google DeepMind's growing stable of biological models, which includes the Nobel Prize-winning AlphaFold for protein structure prediction, AlphaMissense for analyzing mutations in protein-coding regions, and AlphaProteo for designing proteins that bind to specific molecular targets
2
. "The genome is the recipe and understanding the effect of changing any part of the recipe is what AlphaGenome looks at," explains Pushmeet Kohli, vice president of science at Google DeepMind5
.
Source: IEEE
While AlphaMissense focused on the small fraction of the genome that codes for proteins, AlphaGenome tackles the far larger regulatory landscape
3
. This vertical integration across genomics creates a comprehensive platform for molecular prediction that could unlock new diagnostic capabilities and therapeutic strategies. "All these different models are solving key problems that are relevant for understanding biology," Kohli notes2
.Related Stories
Real-World Applications in Rare Disease Diagnosis
Nearly 3,000 scientists in 160 countries have already used AlphaGenome since Google DeepMind released a preview for non-commercial research in June last year, submitting around one million requests daily
5
. At the Undiagnosed Hackathon, where more than 100 researchers tackled 29 undiagnosed conditions, AlphaGenome was deployed to investigate several cases1
. The event, organized by the Wilhelm Foundation—a charity founded by parents who lost three of their four children to an undiagnosed disease—aims to help the approximately 350 million people worldwide living with undiagnosed rare conditions.Klee tested AlphaGenome's predictions on a variant his team had linked to an individual's diagnosis before the hackathon. Experimental work showed the mutation altered gene expression in cardiac cells but not neural cells, aligning with the patient's symptoms. AlphaGenome's predictions supported this conclusion
1
. While none of the AlphaGenome predictions at the September 2025 hackathon led directly to a diagnosis, six of the 29 conditions were diagnosed using other approaches, demonstrating how AI tools complement traditional methods.Limitations and Future Directions in Genomics Research
Despite its advances, AlphaGenome faces notable constraints. The model's training data draw largely from bulk tissue datasets, limiting reliability in rare cell types or specific developmental stages. "Generalization to new cell types is a huge limitation," notes Christina Leslie, a computational biologist at Memorial Sloan Kettering Cancer Center
2
. The tool also struggles to capture distant effects when regulatory regions are hundreds of thousands to millions of DNA letters away from their target genes.Additionally, while the model makes accurate predictions, it doesn't always directly inform researchers of the underlying biological processes, explains Jian Zhou, a genomics machine learning researcher at the University of Chicago
5
. Robert Goldstone, head of genomics at the Francis Crick Institute, describes AlphaGenome as "a foundational, high-quality tool that turns the static code of the genome into a decipherable language for discovery," but cautions it "is not a magic bullet for all biological questions"5
. Researchers suggest the next leap will come from generating new types of data for the model to analyze, as AlphaGenome has "maxed out" what this type of architecture can achieve4
.References
Summarized by
Navi
[3]
[5]
Related Stories
DeepMind's AlphaGenome: Decoding the 'Dark Matter' of DNA with AI
26 Jun 2025•Science and Research
Google DeepMind Maps All 9 Billion Possible Human Gene Mutations in New AlphaGenome Atlas
08 Sept 2026•Science and Research
AI Model Predicts Gene Activity in Human Cells, Transforming Biological Research
09 Jan 2025•Science and Research
Recent Highlights
1
AI Hallucination Nearly Sparked US Military Confrontation With Chinese Ship in Middle East
Technology
2
OpenAI AI Agent Hacks Australian Government Healthcare Website in First-of-Its-Kind Breach
Technology
3
AI leaders warn UN Security Council of existential risks to humanity, call for global safeguards
Policy and Regulation
Recent Highlights
Today's Top Stories
Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Follow topics that matter to you and stay ahead.
