美国JURA Bio公司Elizabeth B. Wood小组取得一项新突破。他们的论文发现了制造感知的生成模型实现千万亿级DNA设计合成。2026年3月17日出版的《自然—生物技术》发表了这项成果。

介绍了一种从生成模型中高效合成DNA设计的方法。该方法集成了机器学习和湿实验室程序，通过以DNA寡合成为主题的受控随机化学反应物理地实现生成抽样算法。该研究组从人类抗体生成模型合成了约10¹⁶种设计，具有可与最先进的蛋白质语言模型相媲美的现实性和多样性，并通过测序验证设计的DNA。设计的抗体scFvs在人细胞系中的翻译和表达，结合对多重人白细胞抗原（HLA）呈递的细胞内蛋白的高通量筛选，产生潜在的治疗性嵌合抗原受体。该研究组进一步从Taq聚合酶模型和HLA呈现肽球模型合成了约10¹⁶个DNA设计，证实了该方法的通用性。

据了解，生成建模为设计功能性DNA、RNA和蛋白质序列提供了一个基本框架。然而，大规模的物理合成这些序列是非常昂贵的。

附：英文原文

Title: Manufacturing-aware generative models enable petascale synthesis of designed DNA

Author: Weinstein, Eli N., Gollub, Mattia G., Slabodkin, Andrei, Dobbs, Kerry, Cui, Xiao-Bing, Gardner, Cameron L., Grant, Ryan J., Gurung, Kristina, Bailey, Amira, Amin, Alan N., Church, George M., Wood, Elizabeth B.

Issue&Volume: 2026-03-17

Abstract: Generative modeling offers a robust framework for designing functional DNA, RNA and protein sequences. However, physical synthesis of these sequences at scale is prohibitively expensive. We introduce a method to efficiently synthesize DNA designs from generative models. The method integrates machine learning and wet lab procedures, implementing generative sampling algorithms physically through controlled stochastic chemical reactions using DNA oligosynthesis. We synthesize ~1016 designs from a generative model of human antibodies, with realism and diversity comparable to state-of-the-art protein language models, and verify the designed DNA by sequencing. Translation and expression of the designed antibody scFvs in human cell lines, combined with high-throughput screening against multiplexed human leukocyte antigen (HLA)-presented intracellular proteins, yields potential therapeutic chimeric antigen receptors. We further synthesize ~1016 DNA designs from models of Taq polymerase and the HLA-presented peptidome, confirming the method’s generalizability.

DOI: 10.1038/s41587-026-03020-8

Source: https://www.nature.com/articles/s41587-026-03020-8