CucurbitAgent: An AI agent for exploring cucurbit multi-omics resources
- 1National Engineering Research Center for Vegetables; State Key Laboratory of Vegetable Biobreeding, Beijing Vegetable Research Center, Beijing Academy of Agricu
Abstract
Functional genomics in crops increasingly depends on integrating information from an extensive literature and heterogeneous multi-omics datasets. Large language models (LLMs) offer a powerful approach to synthesizing these resources and revealing hidden connections across datasets; however, they frequently hallucinate, producing plausible but unsupported claims, when responding to gene-specific queries. Here, we present CucurbitAgent, an AI research agent for functional genomics in the Cucurbitaceae, a major family of horticultural crops. CucurbitAgent integrates multi-omics resources from nine cultivated cucurbit species and more than 18,000 publications, encompassing approximately 256,000 genes, tissue-resolved expression profiles, over 16 million natural genetic variants, and roughly 242,000 predicted protein structures with more than 14 million predicted binding-site residue annotations. Responses link retrieved evidence to source records, including gene entries, expression measurements, structural predictions, and literature passages. On a curated benchmark of 50 tasks assessed by domain experts under blinded conditions, CucurbitAgent achieved an overall pairwise win rate of 96.0% against nine general-purpose LLMs, based on weighted scores for factual accuracy, completeness, relevance, and traceability. The platform is freely available at https://cucurbitagent.com and supports queries in 37 languages collectively spoken by an estimated 70% or more of the world's population. CucurbitAgent not only unifies evidence retrieval and interpretation but also reveals latent associations across datasets, helping researchers formulate testable hypotheses and substantially accelerating candidate-gene research. Its framework is readily transferable to other crops and, more broadly, provides a blueprint for building specialized agents in any domain.
Related
- The bacterial pathogen causing cucurbit yellow vine disease associates with the specialized extrafascicular phloem unique to cucurbits
- Exploring Moringa‐Derived Phytosterol From East Nusa Tenggara, Indonesia, as Antialopecia Agent: 5α‐Reductase Inhibition and Topical Tonic for Sustainable Health Innovation and Development
- BrainAgent: A Large Language Model-Driven Multi-Agent Framework for Autonomous Brain Signal Understanding
- A closed-loop language-model agent for target-specific multi-objective hit-to-lead optimization
- Multi-agent game theory for precision psychiatry
BibTeX
@misc{zhang2026cucurbitagent,
title = {{CucurbitAgent: An AI agent for exploring cucurbit multi-omics resources}},
author = {R. Zhang and J. Zhang and Y. Zhang and X. Zhang and J. Yang and C. Xia and J. Zhang and H. Zhao and C. Wen},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.09.758138},
url = {https://www.biorxiv.org/content/10.64898/2026.10.09.758138v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - CucurbitAgent: An AI agent for exploring cucurbit multi-omics resources
AU - R. Zhang
AU - J. Zhang
AU - Y. Zhang
AU - X. Zhang
AU - J. Yang
AU - C. Xia
AU - J. Zhang
AU - H. Zhao
AU - C. Wen
PY - 2026
DA - 2026/10/09
PB - bioRxiv
DO - 10.64898/2026.10.09.758138
UR - https://www.biorxiv.org/content/10.64898/2026.10.09.758138v1
AB - Functional genomics in crops increasingly depends on integrating information from an extensive literature and heterogeneous multi-omics datasets. Large language models (LLMs) offer a powerful approach to synthesizing these resources and revealing hidden connections across datasets; however, they frequently hallucinate, producing plausible but unsupported claims, when responding to gene-specific queries. Here, we present CucurbitAgent, an AI research agent for functional genomics in the Cucurbitaceae, a major family of horticultural crops. CucurbitAgent integrates multi-omics resources from nine cultivated cucurbit species and more than 18,000 publications, encompassing approximately 256,000 genes, tissue-resolved expression profiles, over 16 million natural genetic variants, and roughly 242,000 predicted protein structures with more than 14 million predicted binding-site residue annotations. Responses link retrieved evidence to source records, including gene entries, expression measurements, structural predictions, and literature passages. On a curated benchmark of 50 tasks assessed by domain experts under blinded conditions, CucurbitAgent achieved an overall pairwise win rate of 96.0% against nine general-purpose LLMs, based on weighted scores for factual accuracy, completeness, relevance, and traceability. The platform is freely available at https://cucurbitagent.com and supports queries in 37 languages collectively spoken by an estimated 70% or more of the world's population. CucurbitAgent not only unifies evidence retrieval and interpretation but also reveals latent associations across datasets, helping researchers formulate testable hypotheses and substantially accelerating candidate-gene research. Its framework is readily transferable to other crops and, more broadly, provides a blueprint for building specialized agents in any domain.
ER -