Introducing AlphaGenome: an AI model to help scientists better understand our DNA – the instruction manual for life 🧬
Researchers can now quickly predict what impact genetic changes could have – helping to generate new hypotheses and drive biological discoveries. ↓ pic.twitter.com/K441deSBgl
— Google DeepMind (@GoogleDeepMind) June 25, 2025
Google’s AI research company, DeepMind, has launched AlphaGenome, a new artificial intelligence model that predicts how DNA sequences regulate genes. This development marks a significant advancement in the field of genomics and could have major implications for therapeutic development. AlphaGenome takes a long DNA sequence of up to 1 million letters as input and predicts thousands of molecular properties that characterize its regulatory activity.
AI NEWS: Google DeepMind just dropped AlphaGenome, an AI for genomics — and it could change our understanding of disease
Plus, more news from Google, Anthropic, ElevenLabs, OpenAI, Higgsfield, and OpenRouter AI.
Here's everything you need to know:
— Rowan Cheung (@rowancheung) June 26, 2025
It can also score the effects of genetic variants or mutations by comparing predictions of mutated sequences with unmutated ones. The model offers several distinctive features compared to existing DNA sequence models. It can analyze long sequences at high resolution, covering regions that regulate genes from far away.
AlphaGenome also provides comprehensive multimodal prediction, giving scientists more insights into gene regulation and variant effects.
Google DeepMind's AlphaGenome
Alongside Gemini-cli, Google has unveiled DeepMind AlphaGenome, an AI model from DeepMind that can simultaneously predict multiple biological functions from long DNA sequences – in particular, how genes are regulated and how genetic variants affect… pic.twitter.com/t1NIuYL0VQ
— Chubby♨️ (@kimmonismus) June 25, 2025
DeepMind, already known for its protein-folding model AlphaFold, is now tackling the complex challenge of understanding how DNA encodes gene regulation. This process is crucial for comprehending gene expression and its implications for health and disease.
Pushmeet Kohli, a vice president for research at DeepMind, said, “We have, for the first time, created a single model that unifies many different challenges that come with understanding the genome.
Caleb Lareau, a computational biologist at Memorial Sloan Kettering Cancer Center, describes AlphaGenome as the most powerful tool to date for modeling genetic differences.
AlphaGenome predicts DNA sequence regulation
“We have these 3 billion letters of DNA that make up a human genome, but every person is slightly different, and we don’t fully understand what those differences do,” he said.
Google plans to make AlphaGenome available for noncommercial users and intends to release detailed information about the model in the near future. The company is also exploring ways to make the model available to commercial entities, such as biotech companies. AlphaGenome has the potential to significantly reduce the time required for certain types of genetic experiments.
It can make predictions about how genetic variants function at a molecular level, which would traditionally require extensive laboratory work. This could be particularly valuable in research on genetic diseases. Julien Gagneur, a professor of computational medicine at the Technical University of Munich, believes that tools like AlphaGenome are essential for understanding and diagnosing genetic causes of diseases.
“A hallmark of cancer is that specific mutations in DNA make the wrong genes express in the wrong context,” he said. “This type of tool is instrumental in narrowing down which ones mess up proper gene expression.”
DeepMind hopes AlphaGenome will provide a foundational tool for future research and therapeutic innovations. The model represents the company’s continued commitment to pushing the boundaries of artificial intelligence in life sciences.
A seasoned technology executive with a proven record of developing and executing innovative strategies to scale high-growth SaaS platforms and enterprise solutions. As a hands-on CTO and systems architect, he combines technical excellence with visionary leadership to drive organizational success.
