[Paper Review] LLMs can generate robotic scripts from goal-oriented instructions in biological laboratory automation

Takashi Inagaki, Akari Kato+3 more|arXiv (Cornell University)|Apr 18, 2023

Machine Learning in Materials Science17 citations

TL;DR

The study shows GPT-4 can generate OT-2 robotic scripts from natural language goal-oriented instructions for biological experiments, reducing the need for writing low-level robot code.

ABSTRACT

The use of laboratory automation by all researchers may substantially accelerate scientific activities by humans, including those in the life sciences. However, computer programs to operate robots should be written to implement laboratory automation, which requires technical knowledge and skills that may not be part of a researcher's training or expertise. In the last few years, there has been remarkable development in large language models (LLMs) such as GPT-4, which can generate computer codes based on natural language instructions. In this study, we used LLMs, including GPT-4, to generate scripts for robot operations in biological experiments based on ambiguous instructions. GPT-4 successfully generates scripts for OT-2, an automated liquid-handling robot, from simple instructions in natural language without specifying the robotic actions. Conventionally, translating the nuances of biological experiments into low-level robot actions requires researchers to understand both biology and robotics, imagine robot actions, and write robotic scripts. Our results showed that GPT-4 can connect the context of biological experiments with robot operation through simple prompts with expert-level contextual understanding and inherent knowledge. Replacing robot script programming, which is a tedious task for biological researchers, with natural-language LLM instructions that do not consider robot behavior significantly increases the number of researchers who can benefit from automating biological experiments.

Motivation & Objective

• Motivate the potential of laboratory automation to accelerate life sciences research.
• Demonstrate that LLMs can convert ambiguous, natural language experimental goals into executable robotic scripts.
• Show that high-level prompts enable expert-like contextual understanding of biological workflows by LLMs.

Proposed method

• Use GPT-4 and related LLMs to generate scripts for OT-2 liquid-handling robots from natural language instructions.
• Evaluate whether the LLM can infer the necessary robotic actions without explicit low-level commands.
• Leverage simple prompts to connect biological experiment context with robot operation.
• Assess the feasibility of replacing traditional robot programming with natural-language prompts.

Experimental results

Research questions

• RQ1 Can GPT-4 produce functional OT-2 scripts from ambiguous biological experiment prompts?
• RQ2 To what extent can LLMs translate biological context into appropriate robot actions without detailed scripting knowledge?
• RQ3 Does simple prompting suffice to enable expert-level contextual understanding of lab workflows by LLMs?

Key findings

• GPT-4 successfully generates OT-2 scripts from natural language instructions without specifying robotic actions.
• LLMs connect biological experiment context with robot operation via concise prompts.
• Using natural-language prompts can significantly lower the barrier to automating biological experiments.