Machine learning models outperform deep learning models, provide interpretation and facilitate feature selection for soybean trait prediction.

Journal: BMC plant biology
Published Date:

Abstract

Recent growth in crop genomic and trait data have opened opportunities for the application of novel approaches to accelerate crop improvement. Machine learning and deep learning are at the forefront of prediction-based data analysis. However, few approaches for genotype to phenotype prediction compare machine learning with deep learning and further interpret the models that support the predictions. This study uses genome wide molecular markers and traits across 1110 soybean individuals to develop accurate prediction models. For 13/14 sets of predictions, XGBoost or random forest outperformed deep learning models in prediction performance. Top ranked SNPs by F-score were identified from XGBoost, and with further investigation found overlap with significantly associated loci identified from GWAS and previous literature. Feature importance rankings were used to reduce marker input by up to 90%, and subsequent models maintained or improved their prediction performance. These findings support interpretable machine learning as an approach for genomic based prediction of traits in soybean and other crops.

Authors

  • Mitchell Gill
    School of Biological Sciences, University of Western Australia, Australia.
  • Robyn Anderson
    School of Biological Sciences and Institute of Agriculture, University of Western Australia, Perth, WA, Australia.
  • Haifei Hu
    School of Biological Sciences and Institute of Agriculture, University of Western Australia, Perth, WA, Australia.
  • Mohammed Bennamoun
    School of Physics, Mathematics and Computing, University of Western Australia, Australia.
  • Jakob Petereit
    School of Biological Sciences, University of Western Australia, Australia.
  • Babu Valliyodan
    Division of Plant Sciences and National Center for Soybean Biotechnology, University of Missouri, Columbia, MO, 65211, USA.
  • Henry T Nguyen
    Division of Plant Sciences and National Center for Soybean Biotechnology, University of Missouri, Columbia, MO, 65211, USA.
  • Jacqueline Batley
    School of Biological Sciences, University of Western Australia, Australia.
  • Philipp E Bayer
    School of Biological Sciences, University of Western Australia, Australia.
  • David Edwards
    School of Biological Sciences, University of Western Australia, Australia.