Construction of A Knowledge Graph for Selection and Breeding Research of New Potato Varieties in China Based on GraphRAG

Potato is the world’s fourth largest staple crop with high yield potential, and selection of early-maturing and high-yielding potato varieties with stable disease resistance is needed to meet future food security challenges. In this study, in order to assist the selection and breeding of new potato varieties and to clarify the current status of potato selection and breeding in China, 227 potato selection and breeding literatures in the China Knowledge Network (CNKI) database were used as the research object, and a knowledge map was constructed by using GraphRAG and Qwen2-70B-instruct and visualized by using Gephi. Based on the constructed knowledge graph, we analyzed the genealogy, resistance and fertility period of new potato varieties selected and bred in China in 2004-2024, and the results showed that the parents used more in the selection and breeding of new potato varieties in recent years were Ji Zhang Yam 8, Svante, Feiuretta, and Early Large White, etc. Most of the potato selections were resistant to late blight, and most of them were of medium-late maturity and late ripeness in their fertility period. In summary, this study explored the realization path of using a large language model to rapidly construct a knowledge graph for potato new variety selection and breeding research, and analyzed 227 potato selections to provide a reference for the future discovery and utilization of potato germplasm resources.

Recommended citation: Wei Yijin, Ren Youqiang, Zhao Hui, Fan Jingchao, Fang Wei & Yan Shen. (2025). Construction of a Knowledge Graph for New Potato Varieties in China Based on GraphRAG. Journal of Plant Genetic Resources, 26(06), 1229−1241. doi:10.13430/j.cnki.jpgr.20240919001.
Download Paper