Key points are not available for this paper at this time.
Plant diseases threaten global food security by causing 20–40% annual crop losses, with climate change accelerating pathogen evolution and expanding disease ranges. This review examines how the convergence of genomic technologies, artificial intelligence (AI), clustered regularly interspaced short palindromic repeats (CRISPR) gene editing, and high-throughput phenotyping (HTP) is revolutionizing disease resistance breeding. We analyze the progression from marker-assisted selection to current integrated platforms that combine pan-genome resources, multi-omics data, and single-cell sequencing to dissect resistance mechanisms at unprecedented resolution. Machine learning algorithms now predict disease resistance phenotypes, optimize CRISPR targeting strategies, and enable real-time disease detection through computer vision, while reducing breeding cycles from 8–10 years to 2–3 years. We evaluate successful applications including CRISPR-edited rice with broad-spectrum bacterial blight resistance, AI-guided discovery of novel resistance genes, and genomic selection programs achieving 2–3-fold higher genetic gains than conventional methods. Critical challenges remain, including transformation bottlenecks in recalcitrant crops, managing pathogen evolution, regulatory uncertainties, and ensuring equitable technological access. We propose a roadmap for next-generation resistance breeding incorporating quantum computing, synthetic biology, and microbiome engineering. The integration of these technologies offers unprecedented opportunities to develop climate-resilient varieties with durable, broad-spectrum disease resistance while maintaining yield potential, ultimately contributing to sustainable intensification of agriculture and global food security in an era of rapid environmental change.
Kamran et al. (Thu,) studied this question.