Google DeepMind Unveils New AI Tool To Understand DNA Mutations

Google DeepMind has revealed a new artificial intelligence system, AlphaGenome, which, the researchers say, could help scientists better interpret the human genome and understand how genetic changes affect biology.

In a post on X, the team said the tool would help researchers “understand our DNA, predict the molecular impact of genetic changes, and drive new biological discoveries.”

AlphaGenome was unveiled on Wednesday, January 28, in the journal Nature.

Our breakthrough AI model AlphaGenome is helping scientists understand our DNA, predict the molecular impact of genetic changes, and drive new biological discoveries. ????

Find out more in @Nature ↓ https://t.co/jvBLRXYzdj pic.twitter.com/WEL4Ptdv06

— Google DeepMind (@GoogleDeepMind) January 28, 2026

How AlphaGenome Works

According to the abstract of the Nature study, deep learning models that can predict functional genomic measurements from DNA sequences have become valuable for interpreting the genetic regulatory code. But many existing tools either study long stretches of DNA or give very detailed results, and not both.

Researchers said AlphaGenome can analyse up to 1 Mb of DNA at a time and still make highly detailed predictions, down to a single DNA letter, across thousands of biological signals.

The Nature abstract adds, “Trained on human and mouse genomes, AlphaGenome matches or exceeds the strongest available external models in 25 of 26 evaluations of variant effect prediction.”

Why Gene Regulation Matters

AlphaGenome predicts how mutations can disrupt the way genes are controlled, including when they are switched on, which cells in the body are affected and whether biological volume controls are set to high or low. Most common inherited diseases, such as heart disease and autoimmune disorders, as well as mental health problems, have been linked to mutations that affect gene regulation, according to The Guardian. Many cancers have also been linked to such mutations, but identifying the exact changes responsible remains difficult.

What Researchers And Experts Are Saying

Natasha Latysheva, a DeepMind researcher, told The Guardian, “We see AlphaGenome as a tool for understanding what the functional elements in the genome do, which we hope will accelerate our fundamental understanding of the code of life.”

According to the English daily, the DeepMind team believes the tool could help identify which parts of the genetic code are most critical for the development of specific tissues, such as nerve and liver cells, and help pinpoint the most important mutations driving cancer and other diseases. It could also support new gene therapies by enabling researchers to design new DNA sequences.

Peter Koo, a computational biologist at Cold Spring Harbor Laboratory in New York who was not involved in the project, told The New York Times that AlphaGenome represented an important step forward in applying artificial intelligence to the genome. “It's an engineering marvel,” Koo added.

DeepMind researchers hoped that training the AI on existing results would help build a programme capable of making accurate predictions about DNA sequences it had never encountered. “It was the right target for us,” Ziga Avsec, a research scientist at Google DeepMind, told The NYT.