Deep neural network (DNN) techniques, as an advanced machine learning framework, have allowed various image diagnoses in plants, which often achieve better prediction performance than human experts in each specific field. Notwithstanding, in plant biology, application of deep neural networks is still mostly limited to rapid and effective phenotyping. Recent development of explainable DNN frameworks has allowed visualization of the features in the prediction by DNN, which potentially contributes to the understanding of physiological mechanisms in objective phenotypes. In this study, we propose an integration of explainable DNN and transcriptomic approach to make a physiological interpretation on occurrence of a fruit internal disorder in persimmon, rapid over-softening. We constructed convolutional neural network (CNN) models to highly predict the fate to be rapid softening in persimmon cv. Soshu, only with photo images. Grad-CAM and Guided Grad-CAM visualized specific featured regions relevant to the prediction of rapid-softening, which would correspond the premonitory symptoms in a fruit. Transcriptomic analyses to compare the featured regions of predicted rapid-softening and control fruits suggested that rapid softening is triggered by precocious ethylene signal-dependent cell wall modification, despite exhibiting no direct phenotypic changes. Further transcriptomic comparison between the featured and non-featured regions in predicted rapid-softening fruit suggested that premonitory symptoms in a fruit reflected hypoxia and the related stress signals finally to induce ethylene signals. These results would provide a good example for collaboration of AI and omics approach in plant physiology, which uncovered a novel aspect of fruit premonitory reactions in the rapid softening fate.