MENU

AutoDNA: AI-native autonomous biomolecular engineering laboratory

Nature
Overview
AutoDNA is an AI-native laboratory that autonomously orchestrates over 20 types of instruments across 11,000+ steps for biomolecular operations. The system achieves expert-level DNA synthesis yields and accelerates protocol execution by 3.2-fold, establishing a blueprint for “science-as-a-service.”
In Depth

Key Findings

AutoDNA has demonstrated the ability to execute complex biomolecular engineering tasks with minimal human intervention. In four representative applications, the system matched expert-optimized enzymatic DNA synthesis yields and accelerated concurrent protocol execution by 3.2-fold. Furthermore, it successfully completed an end-to-end DNA data storage cycle with exact recovery of original digital content and identified and validated a clinically detected KRAS G13D mutation.

Technical Details

Unlike traditional “add-on” architectures that use AI as a task-specific tool, AutoDNA utilizes an AI-native design based on the co-design of models, experiments, and instruments. This end-to-end multi-user framework allows for the co-evolution of the AI and the automation system. The laboratory autonomously manages more than 20 types of instruments to perform core nucleic acid operations, including:

  • Synthesis
  • Transcription
  • Amplification
  • Sequencing

The system executed over 11,000 steps autonomously, restricting human involvement solely to hardware maintenance tasks such as the replenishment of labware and reagents.

Background & Context

While autonomous experimental systems have emerged in materials science and chemical research, they have largely been limited to domains with simple instrumentation, well-defined workflows, and singular objectives. These limitations often stem from a lack of global understanding of experiments within the AI architecture, particularly in engineering-oriented contexts.

Significance & Outlook

By integrating AI natively into the laboratory infrastructure, AutoDNA provides a scalable model for autonomous scientific exploration. This approach establishes a blueprint for “science-as-a-service,” which is expected to accelerate biological discovery and advance practical applications in information storage and synthetic biology.

Source: https://www.nature.com/articles/s41586-026-11228-6

Get our weekly technology intelligence — free

Receive an infographic that lets you judge at a glance whether each field’s analysis report is worth reading.

Subscribe Free — Weekly Tech Intelligence

By subscribing, you’ll receive Troy-Technical’s weekly technology intelligence newsletter.

  • Your email and selected fields are used only to deliver the newsletter.
  • We never share your information with third parties.
  • You can unsubscribe anytime via the link in each email.

See our Privacy Policy for details.

Takes about a minute · Unsubscribe anytime

Published by Troy-Technical, an independent site run by one engineer with a career in materials development.
About the author / Contact info@troy-technical.jp
Let's share this post !

Author of this article

TOC