ChatT2 builds an AI assistant for bacterial natural product research
ChatT2: An Adaptive Framework for Developing a Large Language Model-Based Agent for Natural Product Domain Research
Artificial Intelligence
Summary
Researching natural products made by bacteria is tricky because the biology and chemistry are complex and require special skills. The authors created ChatT2, an AI tool that talks with users to better understand their questions and then uses multiple expert agents to find and check detailed information about specific bacterial compounds. This tool combines text, biology, and chemistry knowledge to give accurate and rich answers, helping both beginners and experts learn about these compounds more easily. ChatT2 is available as a web service for people to try.
What this means in practice
- •For bioinformatics teams: Use ChatT2 to integrate biological and chemical data retrieval specific to bacterial polyketides with guided user interaction for natural product analyses.
- •For pharmaceutical developers: Leverage ChatT2 to assist in early-stage identification and characterization of therapeutic bacterial compounds through multimodal AI-powered information synthesis.
Authors
Yihan Wang, Qiandi Gao, Yihui Zhuang, Liangjun Ge, Heqian Zhang, Jiaquan Huang, Zhiwei Qin
Abstract
Scientific investigations into microbial natural products (NPs) present significant challenges for novices, largely due to the complexity of microbial systems, biochemical diversity, technical skill requirements, and the demands of bioinformatics and data analysis processes. To address these issues, we introduce ChatT2, a large language model (LLM)-based agent that is specifically tailored to the unique characteristics of bacterial type II polyketides. These polyketides form a structurally distinct and therapeutically important NP family. ChatT2 was developed within an autonomous multiagent framework composed of a mentor, an executor, and an evaluator, each with defined responsibilities. The mentor acts as an intermediary between ChatT2 and the user, utilizing chain-of-thought prompting to refine the intent of the user. Under the guidance of the mentor, the executor synthesizes multimodal information via retrieval-augmented generation techniques and seamlessly integrates bioinformatics and cheminformatics tools. The evaluator ultimately assesses the output of the executor to ensure the richness and accuracy of the retrieved information. Our research highlights how ChatT2, designed with this multiagent framework, addresses the challenges faced by general LLMs in terms of understanding limited, specialized corpora and complex biological information and provides both experts and novices with a valuable tool for exploring various NPs of interest. The ChatT2 webserver can be accessed at https://chatt2.site/#/chat.