Harnessing Deep Learning to Analyze Cryptic Morphological Variability ofMarchantia polymorpha

Characterizing phenotypes is a fundamental aspect of biological sciences, although it can be challenging due to various factors. For instance, the liverwort ( Marchantia polymorpha ), a model system for plant biology, exhibits morphological variability, making it difficult to identify and quantify distinct phenotypic features using objective measures. To address this issue, we utilized a deep learning-based image classifier that can handle plant images directly without manual extraction of phenotypic features, and analyzed bright-field images of M. polymorpha . This dioicous plant species exhibits morphological differences between male and female wild accessions at an early stage of gemmaling growth, although it remains elusive whether the differences are attributable to sexual dimorphism or autosomal genetic variation. To dissect the genomic factors, we established a male and female set of recombinant inbred lines (RILs) from a set of male and female wild accessions. We then trained deep-learning models to classify the sexes of the RILs and the wild accessions. Our results showed that the trained classifiers accurately classified male and female gemmalings of wild accessions in the first week of growth, confirming the intuition of plant researchers in a reproducible and objective manner. In contrast, the RILs were less distinguishable, indicating that the differences between the parental wild accessions arose from autosomal variations instead of sexual dimorphism. Furthermore, we validated our trained models by an “explainable AI” technique that highlights image regions relevant to the classification. Our findings demonstrate that the classifier-based approach provides a powerful tool for analyzing plant species that lack standardized phenotyping metrics.