Lipoxygenases（LOXs） are a group of non-heme,iron-containing enzymes and extensively involved in plant growth and development,ripening and senescence,stress responses,biosynthesis of regulatory molecules and defense ...Lipoxygenases（LOXs） are a group of non-heme,iron-containing enzymes and extensively involved in plant growth and development,ripening and senescence,stress responses,biosynthesis of regulatory molecules and defense reaction.In our previous study,18 LOXs in melon genome were screened and identified,and five 13-LOX genes（CmLOX08,CmLOX10,CmLOX12,CmLOX13 and CmLOX18） were predicted to locate in chloroplast.Phylogenetic analysis result showed that the five genes have high homology with jasmonic acid（JA） biosynthesis-related LOXs from other plants.In addition,promoter analysis revealed that motifs of the five genes participate in gene expression regulated by hormones and stresses.Therefore,we analyzed the expressions of the five genes and LOX activity in leaves of four-leaf stage seedlings of oriental melon cultivar Yumeiren under abiotic stress：wounding,cold,high temperature and hydrogen peroxide（H_2O_2）,and signal molecule treatments：methyl jasmonate（MeJA）,abscisic acid（ABA） and salicylic acid（SA）.Real time qPCR revealed that wounding and H_2O_2 induced the expressions of all the five genes.Only CmLOX08 was induced by cold while only CmLOX13 was suppressed by high temperature.ABA induced the expressions of CmLOXIO and CmLOX12 while inhibited CmLOX13 and CmLOX18.MeJA increased the 3 genes expressions except CmLOX08 and CmLOX13,whereas SA decreased the effect,apart from CmLOX12.All the abiotic stresses and signal molecules treatments increased the LOX activity in leaves of oriental melon.In summary,the results suggest that the five genes have diverse functions in abiotic stress and hormone responses,and might participate in defense response.The data generated in this study will be helpful in subcellular localization and transgenic experiment to understand their precise roles in plant defense response.展开更多
目的通过深度残差神经网络(ResNet38)对腹部立位平片进行学习,从中检出小肠梗阻。方法本研究使用的训练集和测试集数据来源于西安交通大学第一附属医院及陕西省核工业二一五医院,独立验证集数据来源于陕西省核工业二一五医院。由2名经...目的通过深度残差神经网络(ResNet38)对腹部立位平片进行学习,从中检出小肠梗阻。方法本研究使用的训练集和测试集数据来源于西安交通大学第一附属医院及陕西省核工业二一五医院,独立验证集数据来源于陕西省核工业二一五医院。由2名经验丰富的影像科诊断医师依据腹部立位平片小肠梗阻的4种征象分别对来源于2家医院的3298张腹部立位平片进行分类,意见不一致时讨论达到共识,其中小肠梗阻569例(17.3%),非小肠梗阻2729例(82.7%)。对2组数据采用完全随机分组的方法组成训练集2305张和测试集993张(训练集∶测试集=2.3∶1),其中训练集小肠梗阻405例(17.6%),非小肠梗阻1900例(82.4%);测试集小肠梗阻164例(16.5%),非小肠梗阻829例(83.5%)。训练集和测试集小肠梗阻的诊断均以有丰富经验的影像科医师的评判为标准。验证集共861张腹部立位平片,其中小肠梗阻99例(11.5%),非小肠梗阻762例(88.5%),以手术结果及临床诊断为金标准。本研究使用ImageNet 2012年大规模视觉识别挑战赛数据集(ILSVRC2012)对深度残差神经网络(ResNet38)进行预训练;用训练集数据对深度残差神经网络(ResNet38)再训练建立诊断模型;测试集主要用于学习算法过程中,调整算法的参数来修正网络,从而使得网络模型效能更优。结果本研究开发的小肠梗阻诊断模型在测试集上敏感性为84.1%,特异性为65.0%,受试者工作特征曲线(receiver operating characteristic,ROC)曲线下面积(area under the curve,AUC)为0.83(95%CI为0.82~0.92);在验证集上的敏感性为89.9%,特异性为68.0%,ROC曲线下面积为0.87(95%CI为0.82~0.92),AUC为0.87。结论对深度残差神经网络进行有限的数据训练,可以获得一个有效的用于在腹部立位平片上检出小肠梗阻的诊断模型。展开更多
基金financially supported by the National Natural Science Foundation of China(31272154)
文摘Lipoxygenases（LOXs） are a group of non-heme,iron-containing enzymes and extensively involved in plant growth and development,ripening and senescence,stress responses,biosynthesis of regulatory molecules and defense reaction.In our previous study,18 LOXs in melon genome were screened and identified,and five 13-LOX genes（CmLOX08,CmLOX10,CmLOX12,CmLOX13 and CmLOX18） were predicted to locate in chloroplast.Phylogenetic analysis result showed that the five genes have high homology with jasmonic acid（JA） biosynthesis-related LOXs from other plants.In addition,promoter analysis revealed that motifs of the five genes participate in gene expression regulated by hormones and stresses.Therefore,we analyzed the expressions of the five genes and LOX activity in leaves of four-leaf stage seedlings of oriental melon cultivar Yumeiren under abiotic stress：wounding,cold,high temperature and hydrogen peroxide（H_2O_2）,and signal molecule treatments：methyl jasmonate（MeJA）,abscisic acid（ABA） and salicylic acid（SA）.Real time qPCR revealed that wounding and H_2O_2 induced the expressions of all the five genes.Only CmLOX08 was induced by cold while only CmLOX13 was suppressed by high temperature.ABA induced the expressions of CmLOXIO and CmLOX12 while inhibited CmLOX13 and CmLOX18.MeJA increased the 3 genes expressions except CmLOX08 and CmLOX13,whereas SA decreased the effect,apart from CmLOX12.All the abiotic stresses and signal molecules treatments increased the LOX activity in leaves of oriental melon.In summary,the results suggest that the five genes have diverse functions in abiotic stress and hormone responses,and might participate in defense response.The data generated in this study will be helpful in subcellular localization and transgenic experiment to understand their precise roles in plant defense response.
文摘目的通过深度残差神经网络(ResNet38)对腹部立位平片进行学习,从中检出小肠梗阻。方法本研究使用的训练集和测试集数据来源于西安交通大学第一附属医院及陕西省核工业二一五医院,独立验证集数据来源于陕西省核工业二一五医院。由2名经验丰富的影像科诊断医师依据腹部立位平片小肠梗阻的4种征象分别对来源于2家医院的3298张腹部立位平片进行分类,意见不一致时讨论达到共识,其中小肠梗阻569例(17.3%),非小肠梗阻2729例(82.7%)。对2组数据采用完全随机分组的方法组成训练集2305张和测试集993张(训练集∶测试集=2.3∶1),其中训练集小肠梗阻405例(17.6%),非小肠梗阻1900例(82.4%);测试集小肠梗阻164例(16.5%),非小肠梗阻829例(83.5%)。训练集和测试集小肠梗阻的诊断均以有丰富经验的影像科医师的评判为标准。验证集共861张腹部立位平片,其中小肠梗阻99例(11.5%),非小肠梗阻762例(88.5%),以手术结果及临床诊断为金标准。本研究使用ImageNet 2012年大规模视觉识别挑战赛数据集(ILSVRC2012)对深度残差神经网络(ResNet38)进行预训练;用训练集数据对深度残差神经网络(ResNet38)再训练建立诊断模型;测试集主要用于学习算法过程中,调整算法的参数来修正网络,从而使得网络模型效能更优。结果本研究开发的小肠梗阻诊断模型在测试集上敏感性为84.1%,特异性为65.0%,受试者工作特征曲线(receiver operating characteristic,ROC)曲线下面积(area under the curve,AUC)为0.83(95%CI为0.82~0.92);在验证集上的敏感性为89.9%,特异性为68.0%,ROC曲线下面积为0.87(95%CI为0.82~0.92),AUC为0.87。结论对深度残差神经网络进行有限的数据训练,可以获得一个有效的用于在腹部立位平片上检出小肠梗阻的诊断模型。
