{"title":"Deep learning with a small dataset predicts chromatin remodelling contribution to winter dormancy of apple axillary buds.","authors":"Takanori Saito, Shanshan Wang, Katsuya Ohkawa, Hitoshi Ohara, Satoru Kondo","doi":"10.1093/treephys/tpae072","DOIUrl":null,"url":null,"abstract":"<p><p>Epigenetic changes serve as a cellular memory for cumulative cold recognition in both herbaceous and tree species, including bud dormancy. However, most studies have discussed predicted chromatin structure with respect to histone marks. In the present study, we investigated the structural dynamics of bona fide chromatin to determine how plants recognize prolonged chilling during the initial stage of bud dormancy. The vegetative axillary buds of the 'Fuji' apple, which shows typical low temperature-dependent, but not photoperiod, dormancy induction, were used for the chromatin structure and transcriptional change analyses. The results were integrated using a deep-learning model and interpreted using statistical models, including Bayesian estimation. Although our model was constructed using a small dataset of two time points, chromatin remodelling due to random changes was excluded. The involvement of most nucleosome structural changes in transcriptional changes and the pivotal contribution of cold-driven circadian rhythm-dependent pathways regulated by the mobility of cis-regulatory elements were predicted. These findings may help to develop potential genetic targets for breeding species with less bud dormancy to overcome the effects of short winters during global warming. Our artificial intelligence concept can improve epigenetic analysis using a small dataset, especially in non-model plants with immature genome databases.</p>","PeriodicalId":23286,"journal":{"name":"Tree physiology","volume":" ","pages":""},"PeriodicalIF":3.5000,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11285188/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Tree physiology","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1093/treephys/tpae072","RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"FORESTRY","Score":null,"Total":0}
引用次数: 0
Abstract
Epigenetic changes serve as a cellular memory for cumulative cold recognition in both herbaceous and tree species, including bud dormancy. However, most studies have discussed predicted chromatin structure with respect to histone marks. In the present study, we investigated the structural dynamics of bona fide chromatin to determine how plants recognize prolonged chilling during the initial stage of bud dormancy. The vegetative axillary buds of the 'Fuji' apple, which shows typical low temperature-dependent, but not photoperiod, dormancy induction, were used for the chromatin structure and transcriptional change analyses. The results were integrated using a deep-learning model and interpreted using statistical models, including Bayesian estimation. Although our model was constructed using a small dataset of two time points, chromatin remodelling due to random changes was excluded. The involvement of most nucleosome structural changes in transcriptional changes and the pivotal contribution of cold-driven circadian rhythm-dependent pathways regulated by the mobility of cis-regulatory elements were predicted. These findings may help to develop potential genetic targets for breeding species with less bud dormancy to overcome the effects of short winters during global warming. Our artificial intelligence concept can improve epigenetic analysis using a small dataset, especially in non-model plants with immature genome databases.
期刊介绍:
Tree Physiology promotes research in a framework of hierarchically organized systems, measuring insight by the ability to link adjacent layers: thus, investigated tree physiology phenomenon should seek mechanistic explanation in finer-scale phenomena as well as seek significance in larger scale phenomena (Passioura 1979). A phenomenon not linked downscale is merely descriptive; an observation not linked upscale, might be trivial. Physiologists often refer qualitatively to processes at finer or coarser scale than the scale of their observation, and studies formally directed at three, or even two adjacent scales are rare. To emphasize the importance of relating mechanisms to coarser scale function, Tree Physiology will highlight papers doing so particularly well as feature papers.