Deep Learning-Based Phenotypic Analysis of Soybean Diseases and Assessment of Phylogenetic Signal

Abstract

Soybean diseases caused by fungal, bacterial, and viral pathogens represent a major constraint to global agricultural productivity. Although molecular phylogenetic analyses have advanced the understanding of pathogen evolution, the extent to which disease phenotypes reflect evolutionary relationships remains poorly understood. In this study, we developed an integrative framework combining deep learning-based phenotypic analysis with phylogenetic inference to investigate the relationship between soybean disease symptoms and pathogen evolution. An EfficientNet-B0 convolutional neural network (CNN) was trained to classify 10 soybean disease classes comprising 703 leaf images and achieved a mean cross-validation accuracy of 98.72 ± 1.17%, a weighted F1-score of 98.74 ± 1.16%, and a macro F1-score of 98.47 ± 1.74%. Evaluation on a held-out test set generated through image-level partitioning yielded an accuracy of 96.19%, a weighted F1-score of 96.28%, and a macro F1-score of 95.86%. Latent feature embeddings revealed a structured phenotypic space with clear separation among most disease classes and enabled quantitative analyses of phenotypic similarity. To provide biological context, taxonomy-derived distance matrices and sequence-based phylogenetic analyses of the fungal subset using 28S rRNA sequences were compared with CNN-derived phenotypic representations. A Mantel test identified a moderate and statistically significant association between phenotypic and phylogenetic distances (Spearman r = 0.3393, p = 0.0050), indicating that pathogen evolutionary history contributes to disease phenotype while explaining only part of the observed phenotypic variation. Overall, the results demonstrate that deep learning effectively captures biologically meaningful phenotypic information while highlighting that disease symptoms arise from the combined influence of pathogen evolution, host responses, and environmental conditions. This study provides an integrative framework for combining image-based phenotyping with phylogenetic analysis to support biologically informed interpretation of plant disease phenotypes.