Potato functional genomics lags due to unsystematic gene information curation, gene identifier inconsistencies across reference genome versions, and the increasing volume of research publications. To address these limitations, we developed the Potato Knowledge Hub (http://www.potato-ai.top), leveraging Large Language Models (LLMs) and a systematically curated collection of over 3,200 high-quality potato research papers spanning over 120 years. This platform integrates two key modules: a functional gene database containing 2,571 literature-reported genes, meticulously mapped to the latest DMv8.1 reference genome with resolved nomenclature discrepancies and links to original publications; and a potato knowledge base. The knowledge base, built using a Retrieval-Augmented Generation (RAG) architecture, accurately answers research queries with literature citations, mitigating LLM "hallucination." Users can interact with the hub via a natural language AI agent, "Potato Research Assistant," for querying specialized knowledge, retrieving gene information, and extracting sequences. The continuously updated Potato Knowledge Hub aims to be a comprehensive resource, fostering advancements in potato functional genomics and supporting breeding programs.
Cite
@article{arxiv.2506.00082,
title = {An AI-powered Knowledge Hub for Potato Functional Genomics},
author = {Jia Yuxin and Li Jinye and Jia Yudong and Li Futing and Su Xiaoqi and Luo Jilin and Dong Yarui and Sun Chunyan and Cui Qinghan and Wang Li and Li Axiu and Shang Yi and Zhu Yujuan and Huang Sanwen},
journal= {arXiv preprint arXiv:2506.00082},
year = {2025}
}