English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The use of laboratory automation by all researchers may substantiallyaccelerate scientific activities by humans, including those in the lifesciences. However, computer programs to operate robots should be written toimplement laboratory automation, which requires technical knowledge and skillsthat may not be part of a researcher's training or expertise. In the last fewyears, there has been remarkable development in large language models (LLMs)such as GPT-4, which can generate computer codes based on natural languageinstructions. In this study, we used LLMs, including GPT-4, to generate scriptsfor robot operations in biological experiments based on ambiguous instructions.GPT-4 successfully generates scripts for OT-2, an automated liquid-handlingrobot, from simple instructions in natural language without specifying therobotic actions. Conventionally, translating the nuances of biologicalexperiments into low-level robot actions requires researchers to understandboth biology and robotics, imagine robot actions, and write robotic scripts.Our results showed that GPT-4 can connect the context of biological experimentswith robot operation through simple prompts with expert-level contextualunderstanding and inherent knowledge. Replacing robot script programming, whichis a tedious task for biological researchers, with natural-language LLMinstructions that do not consider robot behavior significantly increases thenumber of researchers who can benefit from automating biological experiments.

LLMs can generate robotic scripts from goal-oriented instructions in biological laboratory automation