Unveiling Salt Tolerance Mechanisms in Plants: Integrating the KANMB Machine Learning Model With Metabolomic and Transcriptomic Analysis
Abstract 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...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-06-01
|
| Series: | Advanced Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/advs.202417560 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract 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. |
|---|---|
| ISSN: | 2198-3844 |