您好,欢迎访问安徽省农业科学院 机构知识库!

Unveiling Salt Tolerance Mechanisms in Plants: Integrating the KANMB Machine Learning Model With Metabolomic and Transcriptomic Analysis

文献类型: 外文期刊

作者: Chen, Shoukun 1 ; Zhang, Hao 1 ; Gao, Shuqiang 1 ; He, Kunhui 1 ; Yu, Tingxi 1 ; Gao, Shang 1 ; Wang, Jiankang 1 ; Li, Huihui 1 ;

作者机构: 1.Chinese Acad Agr Sci CAAS, Inst Crop Sci, State Key Lab Crop Gene Resources & Breeding, Beijing 100081, Peoples R China

2.CAAS, Nanfan Res Inst, Sanya 572024, Hainan, Peoples R China

3.Guangxi Acad Agr Sci, Rice Res Inst, Guangxi Key Lab Rice Genet & Breeding, Nanning 530007, Guangxi, Peoples R China

关键词: KANMB; metabolomic; salt tolerance; Spartina alterniflora; transcriptomic

期刊名称:ADVANCED SCIENCE ( 影响因子:14.1; 五年影响因子:15.6 )

ISSN:

年卷期: 2025 年 12 卷 23 期

页码:

收录情况: SCI

摘要: Salt stress presents a substantial threat to cereal crop productivity, especially in coastal agricultural regions where salinity levels are high. Addressing this challenge requires innovative approaches to uncover genetic resources that support molecular breeding of salt-tolerant crops. In this study, a novel machine learning model, KANMB is introduced, designed to analyze integrated multi-omics data from the natural halophyte Spartina alterniflora under various NaCl concentrations. Using KANMB, 226 metabolic biomarkers significantly linked to salt stress responses, grounded in metabolomic and transcriptomic profiles are identified. These biomarkers correlate with metabolic pathways associated with salt tolerance, providing insight into the underlying biochemical mechanisms. A co-expression analysis further highlights the MYB gene SaMYB35 as a pivotal regulator in the flavonoid biosynthesis pathway under salt stress. When overexpressed SaMYB35 in rice (ZH11) grown under high salinity, it triggers the upregulation of key flavonoid biosynthetic genes, elevates flavonoid content, and enhances salt tolerance compared to wild-type plants. The findings from this study offer a valuable genetic toolkit for breeding salt-tolerant cereal varieties and demonstrate the power of machine learning in accelerating biomarker discovery for stress resilience in non-model plant species.

  • 相关文献
作者其他论文 更多>>