AI ‘Writes’ DNA: New AI Tool Speeds Up Genetic Research and Breakthroughs

Researchers have introduced Evo 2, a cutting-edge generative artificial intelligence (AI) tool that marks a significant advancement in biological research.

Spiral DNA double helix structure on blue background.

Image Credit: Billion Photos/Shutterstock.com

Developed by a multi-institutional team led by Stanford’s Brian Hie, Evo 2 predicts protein structures and functions across all domains of life, accelerates genetic experimentation and generates novel DNA sequences. Trained on a dataset spanning both existing and extinct species, Evo 2 has the potential to drive breakthroughs in medicine, bioengineering, and environmental science by speeding up evolutionary processes and identifying disease-causing mutations.

Background

Biological research has traditionally relied on time-intensive laboratory experiments to decode the complexities of DNA, proteins, and genetic mutations. These conventional methods often take years—sometimes even centuries—to yield meaningful results, slowing the pace of scientific discovery. Evo 2 was designed to change that.

Developed in collaboration with researchers from Stanford, NVIDIA, and the Arc Institute, Evo 2 leverages advanced machine learning to analyze vast genomic datasets.

It can predict protein structures, simulate genetic interactions, and generate new DNA sequences within minutes or hours—tasks that would otherwise require years of research. This capability not only accelerates scientific progress but also opens up new possibilities for understanding diseases, designing novel therapies, and tackling environmental challenges.

Additionally, its open-source framework ensures accessibility to researchers worldwide, fostering collaboration and innovation across disciplines.

How Evo 2 Works and Its Capabilities

Evo 2 functions by analyzing DNA sequences, which consist of four nucleotides: adenine (A), cytosine (C), guanine (G), and thymine (T). These nucleotides form the genetic blueprint of all life. The human genome alone consists of approximately three billion of these building blocks. Evo 2 employs AI to detect patterns in DNA sequences and predict the next nucleotide in a chain, effectively enabling it to "write" new genetic code.

One of Evo 2’s key advantages is its ability to examine long-distance genetic interactions—relationships between genes that may not be physically adjacent on the DNA molecule. With a context window of up to one million nucleotides, Evo 2 can uncover connections that traditional methods might miss.

Beyond prediction, Evo 2 can generate entirely new genetic sequences. Some of these sequences replicate natural genes, while others introduce novel mutations with potentially beneficial functions.

For example, Evo 2 can design genes that could help combat diseases or address environmental issues. Once a sequence is generated, machine learning models evaluate its functionality and likelihood of existing in nature. Researchers can then synthesize the DNA and test it in living cells using tools like CRISPR (clustered regularly interspaced short palindromic repeats).

This process accelerates evolution, allowing scientists to explore genetic variations that would typically take millennia to develop naturally.

Applications and Future Potential

Evo 2’s applications span multiple fields, with particularly promising implications for medicine. It can distinguish harmful mutations—such as those leading to cancer—from benign genetic variations, paving the way for more precise diagnostics and personalized medicine.

Additionally, Evo 2’s ability to design novel genetic sequences offers potential breakthroughs in gene therapy and bioengineering. Scientists could use it to develop genes that produce therapeutic proteins, improve drug development, or enhance crop resilience in response to climate change.

The tool also holds promise for systems biology, where it can model interactions between multiple genes to better understand complex diseases. By integrating with other biological models, Evo 2 could provide new insights into genetic networks and their influence on health. Its open-source nature encourages global collaboration, ensuring that researchers worldwide can leverage and expand upon its capabilities.

Conclusion

Evo 2 represents a major step forward in biological research, providing exceptional capabilities to predict, generate, and test genetic sequences. By dramatically accelerating the pace of discovery, it holds immense potential for advancing medicine, bioengineering, and environmental science.

The collaborative effort behind Evo 2 highlights the power of interdisciplinary research in tackling some of the most complex scientific challenges. As it becomes more widely adopted, Evo 2 is poised to reshape our understanding of genetics and unlock new opportunities to improve human health and the environment.

Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of AZoM.com Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.

Source:

Stanford

Citations

Please use one of the following formats to cite this article in your essay, paper or report:

  • APA

    Nandi, Soham. (2025, March 11). AI ‘Writes’ DNA: New AI Tool Speeds Up Genetic Research and Breakthroughs. AZoRobotics. Retrieved on March 11, 2025 from https://www.azorobotics.com/News.aspx?newsID=15785.

  • MLA

    Nandi, Soham. "AI ‘Writes’ DNA: New AI Tool Speeds Up Genetic Research and Breakthroughs". AZoRobotics. 11 March 2025. <https://www.azorobotics.com/News.aspx?newsID=15785>.

  • Chicago

    Nandi, Soham. "AI ‘Writes’ DNA: New AI Tool Speeds Up Genetic Research and Breakthroughs". AZoRobotics. https://www.azorobotics.com/News.aspx?newsID=15785. (accessed March 11, 2025).

  • Harvard

    Nandi, Soham. 2025. AI ‘Writes’ DNA: New AI Tool Speeds Up Genetic Research and Breakthroughs. AZoRobotics, viewed 11 March 2025, https://www.azorobotics.com/News.aspx?newsID=15785.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.