ProteinEngine: Empower LLM with Domain Knowledge for Protein Engineering

TL;DR

This work tackles the gap between general-purpose LLMs and the domain-specific needs of protein engineering by introducing ProteinEngine, a human-centered platform that integrates diverse protein-engineering tools via APIs and employs a three-role LLM framework: AI Project Manager, AI Domain Expert, and AI Presenter. The approach enables efficient task decomposition, domain-specific reasoning, and clear result presentation, with extensibility to incorporate new models and APIs. An extensive user study demonstrates that ProteinEngine improves task time, reduces attempts, and enhances usability across participants from AI and biology communities, while workload effects remain unchanged. These findings suggest that bridging disconnected protein-engineering tools with structured LLM roles can accelerate discovery and broaden accessibility, though the authors emphasize responsible use and robust validation as future priorities.

Abstract

Large language models (LLMs) have garnered considerable attention for their proficiency in tackling intricate tasks, particularly leveraging their capacities for zero-shot and in-context learning. However, their utility has been predominantly restricted to general tasks due to an absence of domain-specific knowledge. This constraint becomes particularly pertinent in the realm of protein engineering, where specialized expertise is required for tasks such as protein function prediction, protein evolution analysis, and protein design, with a level of specialization that existing LLMs cannot furnish. In response to this challenge, we introduce \textsc{ProteinEngine}, a human-centered platform aimed at amplifying the capabilities of LLMs in protein engineering by seamlessly integrating a comprehensive range of relevant tools, packages, and software via API calls. Uniquely, \textsc{ProteinEngine} assigns three distinct roles to LLMs, facilitating efficient task delegation, specialized task resolution, and effective communication of results. This design fosters high extensibility and promotes the smooth incorporation of new algorithms, models, and features for future development. Extensive user studies, involving participants from both the AI and protein engineering communities across academia and industry, consistently validate the superiority of \textsc{ProteinEngine} in augmenting the reliability and precision of deep learning in protein engineering tasks. Consequently, our findings highlight the potential of \textsc{ProteinEngine} to bride the disconnected tools for future research in the protein engineering domain.

Figures (4)

• Figure 1: The overall framework of the proposed ProteinEngine, which incorporates three distinct roles, each assigned to a separate LLM.
• Figure 2: Three representative use case examples of the ProteinEngine in user mode, where only the absence of mandatory parameters will be requested to the user.
• Figure 3: The overall flowchart of the user study. This includes preparation (participant recruitment and briefing), user participation operation (familiarization with the technology and random assignment to conditions), data collection (sequential tasks under different conditions with intermittent feedback). Each stage of the process is color-coded for ease of understanding.
• Figure 4: Boxplots for the four variables.