Related Experiment Video
Updated: Mar 15, 2026
07:12
High-Throughput, In-Field Screening of Photosynthetic Efficiency in Crop Plants Using an Autonomous Robot
Published on: January 9, 2026
500
Trait Association for Flowering Time in Lentil from Global Multi-Environment Data Using GWAS and Machine Learning.
Shriprabha R Upadhyaya1,2, Hawlader A Al-Mamun1,2,3, Monica F Danilevicz4
1Centre for Applied Bioinformatics, The University of Western Australia, Perth, WA 6009, Australia.
Plants (Basel, Switzerland)
|March 14, 2026
Summary
Machine learning models complement Genome-Wide Association Studies (GWAS) for identifying genetic markers linked to plant flowering time. These advanced methods improve trait prediction by capturing complex gene interactions and environmental influences.
Area of Science:
- Plant genetics
- Agricultural science
- Computational biology
Background:
- Flowering time is a crucial plant trait influenced by genes and environment.
- Genome-Wide Association Studies (GWAS) identify genetic markers but often miss complex interactions.
- Machine Learning (ML) can model these interactions and improve trait prediction.
Purpose of the Study:
- To identify genetic markers associated with flowering time in lentil (Lens culinaris Medik.).
- To compare the effectiveness of GWAS and ML approaches in detecting flowering time-associated loci.
- To leverage Explainable AI (XAI) for enhanced model interpretability.
Main Methods:
- Analysis of multi-environment lentil data using GWAS.
- Application of Random Forest and XGBoost machine learning models.
- Utilisation of SHapley Additive exPlanations (SHAP) for model interpretability.
Main Results:
- GWAS identified eight significant loci, with the top SNP at Chr2_530433205.
- ML approaches detected nine markers, with the top SNP at Chr7_523220088.
- Most identified markers were associated with known flowering time genes; ML also suggested potential epistasis.
Conclusions:
- Machine learning serves as a powerful complementary tool to GWAS for trait association studies.
- ML models enhance the discovery of genetic architecture underlying complex traits like flowering time.
- This study provides valuable genetic insights for developing improved lentil varieties.
