Quantitative trait locus (QTL) analysis is a powerful approach for identifying variants associated with the phenotypic variation of complex traits. However, selecting optimal methods and pre-processing steps require considerable time and effort. In this study, we demonstrated applicability and replicability of machine learning (ML) models in QTL analysis by evaluating their performance in comparison with conventional QTL analysis methods using 142 recombinant inbred lines derived from two japonica rice cultivars, Koshihikari and Baegilmi. Random forest and gradient boosting models showed the highest predictive accuracy, and consistently identified three QTLs associated with heading date: qDTH3, qDTH6, and qDTH7. Moreover, ML-based QTL analysis detected minor-effect qDTH10, where Koshihikari allele promoted heading date when combined with Koshihikari alleles of qDTH6 and qDTH7. These results demonstrate the applicability of ML models in QTL analysis on bi-parental mapping population in rice.

Citations

Citations to this article as recorded by  

• Machine Learning Method to Select Single Nucleotide Polymorphism Markers for Protein Content, Grain Filling Rate, Height, and Panicle Length in Korean Rice
  Jeong-Gu Kim, Minwoo Kim, Gyu-Hwang Park, Jinhyun Kim, Jinho Jung, Tae-Ho Lee
  Korean Journal of Breeding Science.2025; 57(4): 403.     CrossRef

Understanding the genetics underlying heading date and yield-related traits is essential in wheat breeding for maximizing productivity under different environments. Using doubled haploid lines derived from two Korean wheat cultivars, we identified seven stable quantitative trait loci (QTLs) for yield-related traits, i.e., days to heading date (QDhd.jbnu-3B, QDhd.jbnu-6B, and QDhd.jbnu-7D), culm length (QCl.jbnu-6A), thousand kernel weight (QTkw.jbnu-6A), kernels per spike (QKps.jbnu-3B) and test weight (QTw.jbnu-1A). Compared to the lines carrying the allele for late heading, those carrying the allele for early heading at QDhd.jbnu-3B, QDhd.jbnu-6B, and QDhd.jbnu-7D headed 3.1, 2.0, and 1.7 days earlier, respectively. Interestingly, when the alleles for early heading at the three QTLs were accumulated, heading date was accelerated by approximately one week, indicating that these QTLs provide useful genetic resources to fine-tune heading date. However, as the alleles for early heading at all three QTLs were associated with decreased kernels per spike, caution is required when deploying them to minimize the negative impacts on yield. Our study provides useful information for developing wheat cultivars with optimal heading date and enhanced productivity.

Citations

Citations to this article as recorded by  

• Variations in Major Agronomic Traits of Durum Wheat Germplasm Under Different Nitrogen Fertilization Levels
  Hosun Cheon, Sun-Hwa Kwak, Sieun Choi, Sukyeung Lee, Jinhee Park, Kyung-Min Kim, Chul Soo Park, Youngjun Mo
  Korean Journal of Breeding Science.2024; 56(3): 281.     CrossRef