Panahi Bahman, Hassani Mahdi, Hosseinzaeh Gharajeh Nahid
Department of Genomics, Branch for Northwest & West Region, Agricultural Biotechnology Research Institute of Iran (ABRII), Agricultural Research, Education and Extension Organization (AREEO), Tabriz, 5156915-598, Iran.
Sugar Beet Seed Institute (SBSI), Agricultural Research, Education and Extension Organization (AREEO), Karaj, Iran.
Biochem Biophys Rep. 2025 Jan 19;41:101920. doi: 10.1016/j.bbrep.2025.101920. eCollection 2025 Mar.
Rhizoctonia solani is a significant pathogen that causes crown and root rot in sugar beet (Beta vulgaris), leading to considerable yield losses. To develop resilient cultivars, it is crucial to understand the molecular mechanisms underlying both resistance and susceptibility. In this study, we employed RNA-Seq analysis alongside machine learning techniques to identify key biomarkers associated with resistance to R. solani. We ranked differentially expressed genes (DEGs) using feature-weighting algorithms, such as Relief and kernel-based methods, to model expression patterns between sensitive and tolerant cultivars. Our integrative approach identified several candidate genes, including Bv5g001004 (encoding Ethylene-responsive transcription factor 1A), Bv8g000842 (encoding 5'-adenylylsulfate reductase 1), and Bv7g000949 (encoding Heavy metal-associated isoprenylated plant protein 5). These genes are involved in stress signal transduction, sulfur metabolism, and disease resistance pathways. Graphical visualizations of the Random Forest and Decision Tree models illustrated the decision-making processes and gene interactions, enhancing our understanding of the complex relationships between sensitive and tolerant genotypes. This study demonstrates the effectiveness of integrating RNA-Seq and machine learning techniques for biomarker discovery and highlights potential targets for developing R. solani-resistant sugar beet cultivars. The findings provide a robust framework for improving crop enhancement strategies and contribute to sustainable agricultural practices by increasing stress resilience in economically important crops.
立枯丝核菌是一种重要的病原菌，可导致甜菜（Beta vulgaris）的根腐病和冠腐病，造成可观的产量损失。为了培育具有抗性的品种，了解抗性和易感性的分子机制至关重要。在本研究中，我们采用RNA测序分析和机器学习技术来鉴定与对立枯丝核菌抗性相关的关键生物标志物。我们使用特征加权算法（如Relief和基于核的方法）对差异表达基因（DEG）进行排名，并对敏感和耐受品种之间的表达模式进行建模。我们的综合方法鉴定出了几个候选基因，包括Bv5g001004（编码乙烯响应转录因子1A）、Bv8g000842（编码5'-腺苷硫酸还原酶1）和Bv7g000949（编码重金属相关异戊烯化植物蛋白5）。这些基因参与应激信号转导、硫代谢和抗病途径。随机森林和决策树模型的图形可视化展示了决策过程和基因相互作用，加深了我们对敏感和耐受基因型之间复杂关系的理解。本研究证明了整合RNA测序和机器学习技术用于生物标志物发现的有效性，并突出了培育抗立枯丝核菌甜菜品种的潜在靶点。这些发现为改进作物改良策略提供了一个强大的框架，并通过提高经济作物的胁迫恢复力为可持续农业实践做出了贡献。
