Researchers from the Arc Institute and Stanford University have developed Evo, a genomic foundation model capable of predicting and designing DNA, RNA, and protein sequences. Using a novel architecture called StripedHyena, the model can process genomic-scale data to understand the complex relationships within genetic code.
TLDR: Scientists have unveiled Evo, an AI foundation model trained on millions of microbial genomes. Capable of processing sequences over 100,000 characters long, Evo can predict the impact of mutations and design novel biological systems, marking a major step toward the era of programmable biology.
A collaborative team from the Arc Institute, Stanford University, and Together AI has introduced Evo, a genomic foundation model that represents a significant leap in the application of artificial intelligence to the biological sciences. While previous AI models in biology were often specialized for narrow tasks—such as predicting protein structures or identifying gene boundaries—Evo is designed as a general-purpose foundation model. It possesses the unique ability to understand and generate DNA, RNA, and protein sequences simultaneously at a genomic scale. This breakthrough allows scientists to predict the effects of mutations across entire biological systems and even design novel synthetic sequences with specific functions from scratch.
At the heart of Evo is the StripedHyena architecture, a sophisticated evolution of the Transformer models that power modern large language models like GPT-4. Traditional Transformers often struggle with the extremely long sequences found in genetic code because their computational requirements grow quadratically with sequence length. StripedHyena utilizes advancements in signal processing and efficient attention mechanisms to handle sequences spanning hundreds of thousands of base pairs. By training on a massive dataset of 2.7 million prokaryotic and phage genomes, the model has learned the complex, multi-layered grammar of life. It can identify the intricate relationships between distant genetic elements, understanding how a change in a non-coding regulatory region might affect the function of a protein encoded thousands of base pairs away.
One of the most impressive capabilities demonstrated by Evo is its ability to perform zero-shot prediction of mutation effects. Without being explicitly trained on a specific gene or organism, the model can accurately predict how a single nucleotide change will impact the fitness of a microbe. This has profound implications for medicine and public health, as it could allow researchers to identify potentially pathogenic variants or predict how bacteria might evolve resistance to new antibiotics. Furthermore, the model’s generative capabilities enable the design of entirely new biological components. In their research, the team used Evo to design functional CRISPR-Cas systems and transposable elements—complex molecular machines that are essential tools in modern biotechnology.
The development of Evo highlights the power of international and interdisciplinary collaboration, combining expertise in deep learning, computational biology, and large-scale computing infrastructure. By making the model and its weights publicly available, the researchers have provided the global scientific community with a powerful tool for exploring the frontiers of synthetic biology. This open-science approach is intended to accelerate the pace of discovery and ensure that the benefits of genomic AI are accessible to researchers worldwide, rather than being confined to a few well-funded institutions.
The scale at which Evo operates is truly unprecedented in the field of bioinformatics. While previous models were often limited to sequences of a few thousand characters, Evo can process and generate sequences of up to 131,000 tokens. This expanded context window allows it to capture the full context of entire operons and small genomes, providing a holistic view of biological function that was previously impossible to model. In rigorous testing, the model successfully designed functional synthetic sequences that were validated in laboratory settings, proving that its theoretical predictions translate into real-world biological activity.
As the field of genomic AI continues to evolve, models like Evo will play a central role in the transition toward “programmable biology.” The ability to read, interpret, and write genetic code with the same ease as computer code could revolutionize fields ranging from drug discovery to environmental remediation and sustainable manufacturing. Future iterations of the model are expected to incorporate eukaryotic data, potentially unlocking the ability to model more complex organisms, including humans. This research paves the way for a future where biological systems can be engineered with precision to solve some of the world’s most pressing challenges, from curing genetic diseases to creating carbon-sequestering plants.
Mason Reed serves as a Staff Writer for Just Right News, where he spearheads the Future Frontiers & Special Projects desk. In an era defined by rapid technological shifts and evolving social landscapes, Mason provides a steady, principled voice, examining the innovations of tomorrow through the lens of traditional American values. His work is most prominently featured in his signature series, “The Next Horizon,” where he explores the intersection of emerging technology, national sovereignty, and the preservation of individual liberty.
A native of San Diego, California, Mason’s worldview was shaped by the unique culture of his hometown. Growing up in a region defined by its strong military presence and its history of maritime industry, he developed a deep-seated respect for the institutions that provide national stability and the entrepreneurial spirit that drives the American economy. This upbringing instilled in him a belief that true progress is not found in discarding the past, but in building upon a foundation of proven principles. His reporting often reflects this San Diego influence, emphasizing the importance of a robust national defense and the necessity of maintaining a competitive edge in the global marketplace.
Now based in San Francisco, Mason operates from the heart of the world’s technological engine. Living and working in the Bay Area provides him with a front-row seat to the advancements—and the ideological challenges—emanating from Silicon Valley. While many in the region embrace a “move fast and break things” mentality, Mason’s reporting serves as a vital counterweight. He offers Just Right News readers a “boots on the ground” perspective, documenting how radical local policies and the concentration of tech power impact the everyday lives of citizens. His proximity to the industry allows him to cut through the marketing jargon of big tech to uncover the real-world implications for privacy, free speech, and the nuclear family.
In his “Future Frontiers” beat, Mason tackles complex subjects ranging from the ethics of artificial intelligence to the burgeoning private space race. He approaches these topics with a healthy skepticism toward centralized bureaucracy, championing instead the decentralized innovations that empower individuals. Through “The Next Horizon,” he highlights the pioneers and thinkers who are working to ensure that the future remains a place where human dignity and constitutional rights are protected. He believes that the rapid pace of change requires more than just technical expertise; it requires a moral compass rooted in the Western tradition.
Throughout his tenure at Just Right News, Mason has remained committed to the idea that the future is something to be shaped, not merely accepted. His writing is characterized by a rigorous defense of American exceptionalism and a belief that the country’s best days lie ahead, provided it remains true to its founding ideals. Whether he is investigating the impact of automation on the American workforce or profiling the next generation of aerospace engineers, Mason Reed ensures that his readers are equipped with the insights they need to navigate a changing world with confidence and clarity.