Abstract
). 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.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 9
Claim · model-written summary
The pipeline measures 24 nodulation traits.
- Taxon
- soybean
Glycine maxe1 - Outcome
- nodulation-related traitse0
- Value
- 24 distinct nodulation-related traitse0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“The pipeline quantifies nodule count, dimensions, and spatial distribution, enabling measurement of 24 distinct nodulation-related traits.”
e1“soybean root traits”
Claim · model-written summary
Nodule detection precision was 0.94.
- Taxon
- soybeanGlycine maxe1
- Outcome
- precisione0
- Value
- 0.94e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“the model achieved a precision of 0.94, a recall of 0.95, and an F1 score of 0.94 for nodule detection”
e1“soybean plants”
Claim · model-written summary
Nodule detection recall was 0.95.
- Taxon
- soybeanGlycine maxe1
- Outcome
- recalle0
- Value
- 0.95e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“the model achieved a precision of 0.94, a recall of 0.95, and an F1 score of 0.94 for nodule detection”
e1“soybean plants”
Claim · model-written summary
Nodule detection F1 was 0.94.
- Taxon
- soybeanGlycine maxe1
- Outcome
- F1 scoree0
- Value
- 0.94e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“the model achieved a precision of 0.94, a recall of 0.95, and an F1 score of 0.94 for nodule detection”
e1“soybean plants”
Claim · model-written summary
The pipeline processed 50 root images in 37 seconds.
- Taxon
- soybeanGlycine maxe1
- Outcome
- root imagese0
- Value
- 50 root images in 37 secondse0
- Qualifier
- single GPU (45 GB memory)e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“It processes 50 root images in 37 seconds on a single GPU (45 GB memory)”
e1“soybean plants”
Claim · model-written summary
The pipeline was about 227 times more efficient than manual scoring.
- Taxon
- soybeanGlycine maxe1
- Outcome
- efficiencye0
- Direction
- improvemente0
- Value
- ~227-folde0
- Comparator
- manual scoringe0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“representing a ~227-fold improvement in efficiency compared to manual scoring (~2 h 20 min)”
e1“soybean plants”
Claim · model-written summary
GWAS identified 50 significant SNPs for nodulation traits.
- Taxon
- soybeanGlycine maxe1
- Outcome
- SNPs associated with multiple nodulation traitse0
- Value
- 50e0
Not reportedDirection
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“identified 50 significant SNPs associated with multiple nodulation traits, including novel ones”
e1“soybean plants”
Claim · model-written summary
Several candidate genes may regulate nodulation.
- Taxon
- soybeanGlycine maxe1
- Gene
- candidate genese0
- Outcome
- nodulatione0
Not reportedDirection
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Several candidate genes linked to these loci suggest potential new regulators of nodulation.”
e1“soybean plants”
Claim · model-written summary
Resources for the pipeline were made publicly available.
- Taxon
- soybeanGlycine maxe1
- Outcome
- essential resourcese0
Not reportedComparatorValue
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“we have made all essential resources publicly available at: https://github.com/Salk-Harnessing-Plants-Initiative/soybean-nodule-detection”
e1“soybean plants”