Hyperspectral trait selection helps identify GhST7 in cotton salt tolerance
Source check: Source checked. Not independent scientific confirmation.
Finding: Bowei Xu and colleagues at the Chinese Academy of Agricultural Sciences and collaborating institutions analyzed 419 upland cotton accessions using time-series hyperspectral traits, hierarchical filtering and GWAS. Random Forest, PLS-DA and LASSO consensus reduced 14,336 image-derived traits to 47 core traits used in the association analysis, which identified GhST7. The authors report functional support from gene-editing and overexpression experiments and associate promoter haplotypes with expression and salt-response differences. Work was performed in controlled seedling conditions; independent cotton populations and field-level breeding effects remain unestablished.
Technology: Random Forest, PLS-DA and LASSO consensus trait selection coupled to hyperspectral phenotyping and GWAS
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Machine-learning consensus feature selection reduces hyperspectral traits used as GWAS phenotypes; it supports prioritization of GhST7, while functional experiments test the candidate gene.
- Test and result
- In 419 upland cotton accessions, machine-learning consensus retained 47 core traits from 14,336 hyperspectral i-traits for GWAS, which identified GhST7. The paper reports CRISPR knockout, VIGS, haplotype-specific overexpression and promoter assays supporting a role in salt response.
- Limitation / still unknown
- Validation is controlled and focused on seedlings. Independent populations and field-level breeding performance were not established.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC13710715/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary source full text reviewed for title, authorship, Methods, Results, version date and stated limitations..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.