Evo 2 is a state of the art DNA language model for long context modeling and design. Evo 2 models DNA sequences at single-nucleotide resolution at up to 1 million base pair context length using the StripedHyena 2 architecture.

Evo is a genomic foundation model capable of generalist prediction and design tasks across DNA, RNA, and proteins. It uses a frontier deep learning architecture to enable modeling of biological sequences at single-nucleotide resolution, with a long context window of up to 1 million tokens.

Evo 2 is a genomic foundation model capable of generalist prediction and design tasks across DNA, RNA, and proteins. It uses a frontier deep learning architecture to enable modeling of biological sequences at single-nucleotide resolution with near-linear scaling of compute and memory relative to context length.

Evo 是第一个能够以单核苷酸分辨率预测和生成整个基因组规模的 DNA 序列的技术。 大规模 DNA 模型（如 Evo）带来的潜在能力也带来了很多挑战，还需要额外的工作来确保这些能力的安全部署，并造福于人类。

2025年2月21日 · We introduce Evo 2, a biological foundation model trained on 9.3 trillion DNA base pairs from a highly curated genomic atlas spanning all domains of life. We train Evo 2 with 7B and 40B parameters to have an unprecedented 1 million token context window with single-nucleotide resolution.

Evo 2 可以深入了解三种基本生物分子 (DNA、RNA 和蛋白质) 以及生命的所有三个领域：真核生物 (Eukarya)、原核生物 (Prokarya) 和古菌 (Archaea)。 此训练数据集基于来自 15,032 个真核基因组和 113,379 个原核基因组的 8.85T 核酸数据集进行训练，涵盖不同物种，与仅关注原核基因组的 Evo 相比，实现了前所未有的跨物种泛化，并显著拓宽了其范围。 Evo 2 使用经过改进的全新 StripedHyena 2 架构，该架构可将参数扩展至 40B 个，从而提高模型的训练效率，以及使用 …

2024年11月15日 · 美国 Arc 研究所（Arc Institute）和斯坦福大学的研究团队提出了一种机器学习模型「Evo」，其能够以无与伦比的准确性解码和设计从分子到基因组规模的 DNA、RNA 和蛋白质序列。

2025年2月19日 · Evo 2 is a biological foundation model that can interpret and generate DNA sequences across various biological scales: from individual molecules to entire genomes while retaining sensitivity to single-nucleotide changes, enabling zero-shot predictions and complex biological system designs.

2025年2月19日 · Run the NIM container with the following commands. You might need to adjust your GPU’s indices. This command will start the NIM container and expose port 8000 for the user to interact with the NIM. Open a new terminal, leaving …

2025年2月19日 · Genome modeling and design across all domains of life with Evo 2. Date posted: February 19, 2025 Click here to read the preprint on BioRxiv.