Rice (Oryza sativa) is a staple food for billions of people globally, but it faces significant yield losses due to heat stress. However, rice responses to heat stress remain understudied as compared to other stress factors. In this study, we combined meta-transcriptomics, machine learning, functional validation, and proteomic analysis to identify the key genes involved in heat stress tolerance in rice. We identified 409 meta-differentially expressed genes (meta-DEGs) between heat-tolerant and susceptible genotypes, which were associated with detoxification, oxidative stress, protein folding, phenylpropanoid biosynthesis, glutathione metabolism, and plant hormone signal transduction. We trained five machine learning models, of which Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) outperformed the others. Using SHAP analysis, the top 14 genes for each model were identified, including the OsWOX13 gene, which was detected simultaneously across both models, indicating a positive regulator and a strong candidate for heat stress tolerance. Functional validation of OsWOX13 via CRISPR/Cas9-mediated knockout (KO) confirmed its positive role in heat stress, with a delay in flowering and survival rate of ~20% compared to ~60% for WT under heat stress. Physiological and antioxidant enzymatic activities showed a significant (p ≤ 0.05) reduction in ABA accumulation levels, increased MDA accumulation, and decreased SOD and POD activities in KO lines compared to WT. The proteomic analysis identified upregulated heat shock proteins (HSF8, BIP1, BIP5, and HSP81-1) and downregulated flowering-associated proteins (ROC6 and 4CL4) in mutant lines in response to heat stress. These results indicate that OsWOX13 enhances heat tolerance by regulating ABA signaling and antioxidant defense mechanisms. Taken together, this study highlights the efficiency of machine learning models in the identification of stress responsive genes and provides OsWOX13 as a strong positive candidate for heat stress tolerance and breeding climate-resilient rice varieties.
No takes yet. Share an insight, caveat, or question.
Ikram et al. (2025) studied this question.
Synapse has enriched 2 closely related papers on similar clinical questions. Consider them for comparative context: