TeroSeek: An AI-Powered Knowledge Base and Retrieval Generation Platform for Terpenoid Research

TL;DR

TeroSeek is a specialized AI platform that integrates a curated terpenoid knowledge base with retrieval-augmented generation to enhance multidisciplinary research and outperform general LLMs in terpenoid queries.

Contribution

The paper introduces TeroSeek, a novel domain-specific knowledge base and AI tool that combines curated literature with RAG to improve terpenoid research capabilities.

Findings

TeroSeek outperforms general-purpose LLMs in terpenoid question-answering.

The platform provides structured, high-quality information tailored for multidisciplinary research.

Publicly available at http://teroseek.qmclab.com for community use.

Abstract

Terpenoids are a crucial class of natural products that have been studied for over 150 years, but their interdisciplinary nature (spanning chemistry, pharmacology, and biology) complicates knowledge integration. To address this, the authors developed TeroSeek, a curated knowledge base (KB) built from two decades of terpenoid literature, coupled with an AI-powered question-answering chatbot and web service. Leveraging a retrieval-augmented generation (RAG) framework, TeroSeek provides structured, high-quality information and outperforms general-purpose large language models (LLMs) in terpenoid-related queries. It serves as a domain-specific expert tool for multidisciplinary research and is publicly available at http://teroseek.qmclab.com.