RESUMEN
[This corrects the article DOI: 10.1371/journal.pone.0258679.].
RESUMEN
Plant stomata are essential structures (pores) that control the exchange of gases between plant leaves and the atmosphere, and also they influence plant adaptation to climate through photosynthesis and transpiration stream. Many works in literature aim for a better understanding of these structures and their role in the evolution process and the behavior of plants. Although stomata studies in dicots species have advanced considerably in the past years, even there is not much knowledge about the stomata of cereal grasses. Due to the high morphological variation of stomata traits intra- and inter-species, detecting and classifying stomata automatically becomes challenging. For this reason, in this work, we propose a new system for automatic stomata classification and detection in microscope images for maize cultivars based on transfer learning strategy of different deep convolution neural netwoks (DCNN). Our performed experiments show that our system achieves an approximated accuracy of 97.1% in identifying stomata regions using classifiers based on deep learning features, which figures out as a nearly perfect classification system. As the stomata are responsible for several plant functionalities, this work represents an important advance for maize research, providing an accurate system in replacing the current manual task of categorizing these pores on microscope images. Furthermore, this system can also be a reference for studies using images from different cereal grasses.
Asunto(s)
Procesamiento de Imagen Asistido por Computador/métodos , Microscopía/métodos , Fotosíntesis , Fenómenos Fisiológicos de las Plantas , Estomas de Plantas/clasificación , Transpiración de Plantas , Zea mays/fisiología , Hojas de la Planta/anatomía & histología , Hojas de la Planta/fisiología , Estomas de Plantas/anatomía & histología , Estomas de Plantas/fisiología , Zea mays/anatomía & histologíaRESUMEN
UNLABELLED: ⢠PREMISE OF THE STUDY: Whole genome duplication (WGD) and specific polyploidy events marked turning points for angiosperm genome structure and evolution. Therefore, cytogenetic studies of polyploidy-prone groups such as the tropical Malvaceae and plant formations such as as the Brazilian Cerrado have gained further importance. We present new chromosome counts for Cerrado Bombacoideae and revised chromosome numbers for the Malvaceae s.l., compare these between subfamilies, and relate them to phylogenetic signal.⢠METHODS: We studied the chromosome number of Eriotheca candolleana, E. gracilipes, E. pubescens, Pachira glabra, Pseudobombax longiflorum, and P. tomentosum. We also compared Eriotheca species ploidy levels using flow cytometry. We compiled chromosome numbers for 557 species of Malvaceae s.l., including 37 Bombacoideae species. We included this information in a phylogenetic reconstruction based on chloroplast matK-trnK DNA to evaluate chromosome evolution of the Malvaceae s.l. and the Bombacoideae in particular.⢠KEY RESULTS: The Cerrado Bombacoideae presented consistently high chromosome numbers. Numbers for Eriotheca species were among the highest and varied among populations. Flow cytometry analyses showed similar 1Cx DNA for all cytotypes and indicated neopolyploidy. Chromosome numbers differed between subfamilies, with the lowest numbers in the Malvoideae and Byttnerioideae and the highest in Tilioideae. Chromosome numbers had significant phylogenetic signal for Bombacoideae but not for Malvoideae or Malvaceae s.l.⢠CONCLUSIONS: Clearly distinct chromosome numbers allied to monophyly provide some support for a circumscription of the Bombacoideae and distinction within the Malvaceae. The phylogenetic signal for chromosome number supports the idea of an ancient WGD and further neopolyploidy events as important evolutionary trends for the Bombacoideae.