PRISM: Protocol Refinement through Intelligent Simulation Modeling
🤖 AI Summary
This work addresses the core challenge of end-to-end generation and execution of automated experimental protocols in self-driving laboratories. We propose a multi-agent collaborative framework that seamlessly integrates large language model (LLM) agents, NVIDIA Omniverse digital twin simulations, and a multi-robotic platform—including Opentrons OT-2, PF400, and Azenta systems—to automatically extract experimental procedures from web-based textual descriptions. Through an iterative loop of planning, critique, and validation, the system generates structured, executable protocols compiled into unified robot instructions. Leveraging the Argonne MADSci protocol format, our approach successfully produces high-fidelity protocols for Luna qPCR and Cell Painting assays. The integration of digital twin simulation effectively resolves physical and temporal constraint conflicts, enabling a fully closed-loop pipeline from natural language descriptions to hands-free experimental execution.
Application Category
📝 Abstract
Automating experimental protocol design and execution remains as a fundamental bottleneck in realizing self-driving laboratories. We introduce PRISM (Protocol Refinement through Intelligent Simulation Modeling), a framework that automates the design, validation, and execution of experimental protocols on a laboratory platform composed of off-the-shelf robotic instruments. PRISM uses a set of language-model-based agents that work together to generate and refine experimental steps. The process begins with automatically gathering relevant procedures from web-based sources describing experimental workflows. These are converted into structured experimental steps (e.g., liquid handling steps, deck layout and other related operations) through a planning, critique, and validation loop. The finalized steps are translated into the Argonne MADSci protocol format, which provides a unified interface for coordinating multiple robotic instruments (Opentrons OT-2 liquid handler, PF400 arm, Azenta plate sealer and peeler) without requiring human intervention between steps. To evaluate protocol-generation performance, we benchmarked both single reasoning models and multi-agent workflow across constrained and open-ended prompting paradigms. The resulting protocols were validated in a digital-twin environment built in NVIDIA Omniverse to detect physical or sequencing errors before execution. Using Luna qPCR amplification and Cell Painting as case studies, we demonstrate PRISM as a practical end-to-end workflow that bridges language-based protocol generation, simulation-based validation, and automated robotic execution.
Problem
Research questions and friction points this paper is trying to address.
automated protocol design
self-driving laboratories
experimental workflow automation
robotic execution
protocol validation
Innovation
Methods, ideas, or system contributions that make the work stand out.
PRISM
multi-agent language models
digital twin simulation
autonomous laboratory
protocol automation
🔎 Similar Papers
No similar papers found.
