YOLO-based high-throughput phenotyping pipeline for soybean nodulation traits in genomic research

). Accurate quantification of nodule traits is essential for understanding host-microbe interactions and genetic determinants of nodulation. However, traditional manual or semi-quantitative approaches are labor-intensive, subjective, and unsuitable for large-scale studies. Here, we present a high-throughput phenotyping pipeline based on the YOLO deep learning architecture for the automated detection and extraction of soybean root traits. The pipeline quantifies nodule count, dimensions, and spatial distribution, enabling measurement of 24 distinct nodulation-related traits. Using root images from 21-day-old hydroponically grown soybean plants, the model achieved a precision of 0.94, a recall of 0.95, and an F1 score of 0.94 for nodule detection, maintaining accuracy across count ranges. It processes 50 root images in 37 seconds on a single GPU (45 GB memory), representing a ~227-fold improvement in efficiency compared to manual scoring (~2 h 20 min). As proof of concept, we applied this pipeline in a genome-wide association study (GWAS) using the FarmCPU approach and identified 50 significant SNPs associated with multiple nodulation traits, including novel ones. Several candidate genes linked to these loci suggest potential new regulators of nodulation. This YOLO-based phenotyping framework provides a robust, scalable, and reproducible tool for trait discovery and genetic analysis, advancing research in legume genomics and crop improvement. To promote the adoption of this user-friendly nodulation phenotyping pipeline and to support its further development, we have made all essential resources publicly available at: https://github.com/Salk-Harnessing-Plants-Initiative/soybean-nodule-detection.