Query：
学者姓名：温永仙
Refining：
Year
Type
Indexed by
Source
Complex
Co-Author
Language
Clean All
Abstract ：
【目的】全基因组选择(genomic selection,GS)是一种通过全基因组标记信息预测个体表型或遗传值的核心技术,在农业育种和遗传研究中具有重要的理论价值和实践意义。然而,高维特征冗余和非线性关系建模是全基因组选择中的关键挑战。提出一种从基因型到表型的堆叠集成模型(genotype to phenotype stacking ensemble,G2PSE),旨在提高预测精度和泛化能力,为高维基因组数据分析提供高效的解决方案。【方法】构建G2PSE堆叠集成模型框架,综合应用十折交叉验证、集成学习、特征选择(LAR算法)和特征增强策略。模型采用随机森林(RF)、支持向量回归(SVR)和梯度提升回归(GBR)作为基学习器,并以普通最小二乘回归(OLSR)作为元学习器,同时,评估随机森林、支持向量回归和神经网络等元学习器对模型性能的影响。G2PSE模型包含3种核心子模型:(1)全特征堆叠集成(AFSE),充分利用所有SNP特征;(2)LAR特征堆叠集成(LFSE),通过特征选择减少冗余信息,提升泛化能力;(3)LAR特征增强堆叠集成(LFESE),结合特征选择与增强策略,在高维数据环境中优化预测能力。探讨3种特征增强变体(AFESE、HFESE Ⅰ、HFESE Ⅱ)的性能。最终,模型在小麦、大豆、罗非鱼3个物种的多性状数据集上进行试验评估,并进一步利用Pepper203数据集进行独立测试集评估,验证模型的鲁棒性。【结果】G2PSE模型在皮尔逊相关系数(PCC)和平均绝对误差(MAE)2项指标上显著优于传统方法和单一机器学习模型。3种核心子模型中,LFESE通过结合特征选择与增强策略表现最佳,LFSE通过特征选择减少了冗余信息并增强了泛化能力,而AFSE在全面捕获基因型全局信息方面具有显著优势。此外,3种特征增强变体模型进一步验证了特征质量相较于特征数量对提升预测性能的重要性。试验还表明,在元学习器选择中,线性回归模型的表现最佳,而在计算效率上,LFESE和LFSE子模型展示了较为均衡的性能。且合理的特征选择阈值对模型性能至关重要,其中,低维数据集的最优阈值为10%—20%,而高维数据集的最优阈值为1%。最后,在独立测试集上的评估证明LFESE子模型具有最佳的泛化能力。【结论】G2PSE模型通过集成学习、特征选择与增强策略显著提升了全基因组选择的预测性能。
Keyword ：
全基因组选择 全基因组选择 农业育种 农业育种 堆叠集成 堆叠集成 特征增强 特征增强 特征选择 特征选择
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 庄润杰 , 刘慧铭 , 王诗雨 et al. 基于G2PSE堆叠集成的全基因组选择方法 [J]. | 中国农业科学 , 2025 , 58 (15) : 2960-2979 . |
| MLA | 庄润杰 et al. "基于G2PSE堆叠集成的全基因组选择方法" . | 中国农业科学 58 . 15 (2025) : 2960-2979 . |
| APA | 庄润杰 , 刘慧铭 , 王诗雨 , 吕婉萍 , 温永仙 . 基于G2PSE堆叠集成的全基因组选择方法 . | 中国农业科学 , 2025 , 58 (15) , 2960-2979 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Disentangling the phylogenetic relationship of polyploid species is essential for understanding how such polyploid species evolved following their origin. To investigate the speciation and evolutionary history of Eremopyrum, we analyzed 36 transcriptomes from 9 polyploid accessions of Eremopyrum and 27 diploid taxa representing 12 basic genomes in Triticeae. Phylogenetic reconstruction, divergence time, and introgression event demonstrated that (1) Eremopyrum and Agropyron shared a common ancestor; (2) Eremopyrum has undergone ongoing evolutionary diversification since its origin in Late Miocene; (3) the diploid E. triticeum and E. distans were the genome donors of the tetraploid species of Eremopyrum; (4) both Eremopyrum and Agropyron contribute to the nonmonophyletic origin of tetraploid E. orientale via introgression events. Our results shed new light on our understanding of the diversity and ecological adaptation of the species in Eremopyrum.
Keyword ：
Eremopyrum Eremopyrum hybridization hybridization introgression introgression polyploid polyploid speciation speciation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Fan, Shu-Qi , Yan, Hao , Zhang, Yue et al. Phylotranscriptomic Analyses Resolve Evolutionary History of Eremopyrum (Triticeae; Poaceae) [J]. | ECOLOGY AND EVOLUTION , 2025 , 15 (2) . |
| MLA | Fan, Shu-Qi et al. "Phylotranscriptomic Analyses Resolve Evolutionary History of Eremopyrum (Triticeae; Poaceae)" . | ECOLOGY AND EVOLUTION 15 . 2 (2025) . |
| APA | Fan, Shu-Qi , Yan, Hao , Zhang, Yue , Ma, Xiao , Zhao, Jun-Ming , Zhang, Hai-Qin et al. Phylotranscriptomic Analyses Resolve Evolutionary History of Eremopyrum (Triticeae; Poaceae) . | ECOLOGY AND EVOLUTION , 2025 , 15 (2) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Flue-cured tobacco is the most important raw material for cigarette production, and efficient and accurate intelligent grading of flue-cured tobacco leaves is of great significance to the acquisition and correct use of tobacco. Currently, there are few studies on the classification of flue-cured tobacco by using both front and back images of tobacco leaves, while the back image of flue-cured tobacco leaves has enriched information. To harness the back information of these leaves and enhance grading accuracy, a revolution ResNet network model, Evo-ResNet, was proposed in this study based on front and back images of flue-cured tobacco leaves. Evo-ResNet had six channel with added Squeeze-and-Excitation (SE) attention mechanism. Six grades pictures of Cuibi 1 and Yunyan 87 tobacco species were collected using mobile phone, respectively. Evo-ResNet was compared with three-channel models of ResNet, GoogLeNet, VGGNet, and AlexNet with only front images of flue-cured tobacco leaves and both front and back images of flue-cured tobacco leaves. The results showed that the loss of train set and the accuracy of validation set had better results while the front and back pictures of flue-cured tobacco leaves were used meantime. For the test set, the accuracy, recall, precision, and F1-score of Evo-ResNet were better than that of other three-channel network models, expect for GoogleNet. The accuracy, recall, precision, and F1-score value of Cuibi 1 were 95.83%, 95.83%, 96.16%, and 95.78%, respectively, while those of Yunyan 87 were 99.07%, 99.07%, 99.10% and 99.08%, respectively. There was better generalization ability for Evo-ResNet. Because of the convenience for obtaining image of flue-cured tobacco by mobile phone, the proposed Evo-ResNet network model had better applicability in practice, which provided a new idea for the application of intelligent classification of flue-cured tobacco leaves in purchasing practice of flue-cured tobacco. © (2025), (Bio Tech System). All rights reserved.
Keyword ：
Flues Flues
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, Shiyu , Zhuang, Runjie , Lv, Wanping et al. Intelligent classification of flue-cured tobacco based on improved network model of six channel ResNet [J]. | Journal of Biotech Research , 2025 , 20 : 98-110 . |
| MLA | Wang, Shiyu et al. "Intelligent classification of flue-cured tobacco based on improved network model of six channel ResNet" . | Journal of Biotech Research 20 (2025) : 98-110 . |
| APA | Wang, Shiyu , Zhuang, Runjie , Lv, Wanping , Lin, Tianzhen , Wen, Yongxian . Intelligent classification of flue-cured tobacco based on improved network model of six channel ResNet . | Journal of Biotech Research , 2025 , 20 , 98-110 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Introduction Rice is one of the world's leading food crops, with nearly half of the world's population eating rice as their staple food. Rice yield is directly related to varieties, and the most intuitive agronomic trait of varietal yield is the number of grains per panicle.Methods In this study, rice panicles are taken as the research object, and images of the panicles are captured using a smartphone. The CSRNet counting model based on deep learning is then improved and applied to the problem of counting the number of grains per panicle in rice.Results and discussion The results show that the method of this study has a mean error value of 3.83% on the final validation set. On this basis, the development of rice per panicle counting APP based on Android terminal and batch counting software RiceGrainCounter based on PC terminal realizes real-time counting on Android terminal and batch counting on PC terminal, which can provide theoretical basis and technical support for rice per panicle counting.
Keyword ：
automatic counting automatic counting CSRNet CSRNet deep learning deep learning rice panicle counting rice panicle counting yield estimation yield estimation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhu, Junyan , Huang, Jiaxing , Wang, Yiyuan et al. A method of rice panicle number counting based on improved CSRNet model [J]. | FRONTIERS IN PLANT SCIENCE , 2025 , 16 . |
| MLA | Zhu, Junyan et al. "A method of rice panicle number counting based on improved CSRNet model" . | FRONTIERS IN PLANT SCIENCE 16 (2025) . |
| APA | Zhu, Junyan , Huang, Jiaxing , Wang, Yiyuan , Wang, Jingyu , Wen, Yongxian . A method of rice panicle number counting based on improved CSRNet model . | FRONTIERS IN PLANT SCIENCE , 2025 , 16 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Introduction Purple eggplant (Solanum melongena L.) is valued for its high anthocyanin content, yet the regulatory mechanisms driving anthocyanin biosynthesis during fruit development remain poorly understood. This study aimed to elucidate the dynamics of anthocyanin accumulation and identify key regulatory genes across three developmental stages of eggplant fruit peel (S1: white, S2: light purple, S3: dark purple).Methods Integrated metabolomic and transcriptomic analyses were conducted to investigate anthocyanin profiles and gene expression patterns during fruit development. Metabolomic profiling identified anthocyanin types, while transcriptomic data highlighted differentially expressed genes. Transient overexpression assays of candidate MYB transcription factors (TFs) were performed to validate their regulatory roles in anthocyanin biosynthesis.Results Total anthocyanin content significantly increased as the fruit peel color deepened from S1 to S3. Metabolomic analysis detected 11 distinct anthocyanins, with concentrations rising progressively across stages. Transcriptomics revealed 8 structural genes and 11 MYB TFs enriched in the anthocyanin pathway. Transient overexpression of SmMYB32 and SmMYB67 upregulated key biosynthetic genes (e.g., CHS, DFR, ANS), confirming their role in enhancing anthocyanin production.Discussion This study demonstrates that anthocyanin accumulation in eggplant fruit peels is tightly linked to the upregulation of biosynthetic genes and MYB TFs during development. The functional validation of SmMYB32 and SmMYB67 highlights their potential as targets for breeding high-anthocyanin cultivars. These findings advance our understanding of anthocyanin regulation in eggplant and provide actionable strategies for improving nutritional quality through molecular breeding.
Keyword ：
anthocyanin anthocyanin metabolomic metabolomic MYB MYB solanum melongena L solanum melongena L transcriptomic transcriptomic
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yang, Ting , Lv, Wanping , Zhuang, Runjie et al. Transcriptomic and metabolomic analyses for the mechanism underlying anthocyanin synthesis during the growth and development of purple eggplant (Solanum melongena L) [J]. | FRONTIERS IN PLANT SCIENCE , 2025 , 16 . |
| MLA | Yang, Ting et al. "Transcriptomic and metabolomic analyses for the mechanism underlying anthocyanin synthesis during the growth and development of purple eggplant (Solanum melongena L)" . | FRONTIERS IN PLANT SCIENCE 16 (2025) . |
| APA | Yang, Ting , Lv, Wanping , Zhuang, Runjie , Wang, Shiyu , Fan, Shuqi , Wen, Yongxian . Transcriptomic and metabolomic analyses for the mechanism underlying anthocyanin synthesis during the growth and development of purple eggplant (Solanum melongena L) . | FRONTIERS IN PLANT SCIENCE , 2025 , 16 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
茄子是重要的园艺作物，也是茄科植物中种植最广泛的蔬菜之一。茄子果实相关农艺性状是一种复杂的数量性状，传统育种选育效率低、周期长。高通量测序技术与生物信息学技术的快速发展，使得全基因组关联分析(genome-wide association study,GWAS)在解析茄子果实相关复杂农艺性状的遗传规律方面展现出巨大的应用前景。本文对全基因组关联分析在茄子的果形、果色等果实相关农艺性状中的研究进展进行了综述；针对茄子数量性状遗传研究中普遍存在的“丢失遗传力”(missing heritability)问题，从4个GWAS策略在茄子果实相关农艺性状研究中的应用热点出发，提出了未来茄子GWAS的发展对策；并结合当前茄子遗传改良的实践需求，展望了GWAS策略在茄子分子育种领域的广阔应用前景。本文为今后利用GWAS解析各种茄子果实相关性状的遗传基础以及选育符合消费者需求的果实材料提供了理论依据和参考。
Keyword ：
丢失遗传力 丢失遗传力 全基因组关联分析 全基因组关联分析 分子育种 分子育种 系统遗传学 系统遗传学 遗传结构 遗传结构
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 黎成 , 杨婷 , 庄彬贤 et al. 茄子果实相关农艺性状全基因组关联分析研究进展与展望 [J]. | 生物工程学报 , 2024 , 40 (01) : 94-103 . |
| MLA | 黎成 et al. "茄子果实相关农艺性状全基因组关联分析研究进展与展望" . | 生物工程学报 40 . 01 (2024) : 94-103 . |
| APA | 黎成 , 杨婷 , 庄彬贤 , 温永仙 . 茄子果实相关农艺性状全基因组关联分析研究进展与展望 . | 生物工程学报 , 2024 , 40 (01) , 94-103 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
为实现烤烟烟叶等级快速、准确的智能化识别，本研究基于手机拍摄的不同品种烤烟烟叶正、反面图像，构建了VGG16与DenseNet组合的新网络模型VGG16-Dense，并应用手机拍摄的翠碧1号、云烟87烤烟烟叶6个等级正反面图片，总共24类，验证该模型的有效性，同时与5个网络模型DenseNet121、ResNet50、AlexNet、VGG16和GoogLeNet进行比较。研究表明：VGG16-Dense网络模型在验证集的各评估指标（准确率、精确率、召回率、F1分数和平均损失值）均达到优秀值，在测试集的各评估指标较其他模型是最优的，准确率为92.71%，精确率为93.07%，召回率为92.71%,F1分数为92.72%，平均损失值为0.22，有较好的泛化能力，错判较少。VGG16-Dense网络模型能同时智能判别烤烟烟叶等级及其正反面，甄别不同品种，这为初级烤烟收购中的定级实现智能化提供理论指导。
Keyword ：
SE模块 SE模块 深度学习 深度学习 烤烟智能分级 烤烟智能分级 组合网络模型 组合网络模型
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 黄本荣 , 范兆烽 , 王飞 et al. 基于VGG16-DenseNet集成模型的烤烟智能分级 [J]. | 中国烟草科学 , 2024 , 45 (03) : 102-112 . |
| MLA | 黄本荣 et al. "基于VGG16-DenseNet集成模型的烤烟智能分级" . | 中国烟草科学 45 . 03 (2024) : 102-112 . |
| APA | 黄本荣 , 范兆烽 , 王飞 , 江逸昕 , 马祥根 , 肖光林 et al. 基于VGG16-DenseNet集成模型的烤烟智能分级 . | 中国烟草科学 , 2024 , 45 (03) , 102-112 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
BackgroundIn plants, Cytochrome P450 (CYP450) constitutes the largest family of metabolic enzymes and plays a crucial role in various physiological processes, including plant growth and development. Eggplants are well-known for their peel's high concentration of anthocyanin compounds that provide significant health benefits to humans. The accumulation of anthocyanins in eggplant peels is an important process during growth and development. Therefore, it is essential to identify the CYP450 genes in eggplant (SmCYPs) and analyze their expression profiles during the period of anthocyanin accumulation in the peel.ResultsA total of 180 SmCYPs were identified in the eggplant genome and classified into eight subfamilies based on phylogenetic analysis. These SmCYPs exhibited highly conserved gene structure (exon/intron) and protein motifs, especially within their respective subgroup. Sixteen pairs of genes with collinearity were identified through gene duplication analysis. Promoter cis-acting element analysis revealed that SmCYPs are involved in various responses, including growth and development, stress responsiveness, and light responsiveness. Transcriptome data analysis revealed that all SmCYPs were expressed in various eggplant tissues, such as roots, stems, leaves, flowers, and fruits; with diverse expression patterns among members. The expression patterns of SmCYPs in eggplant peel also exhibited diversity during different stages of anthocyanin accumulation. qRT-PCR analysis demonstrated similar expression patterns for 15 selected SmCYPs as observed in the transcriptome data. Metabolomics analysis further suggested that SmCYPs are involved in the biosynthesis of secondary metabolites and metabolic pathways related to flavonoid and flavone/flavonol biosynthesis. Notably, three specific SmCYPs (SmCYP73A1/75A/98A1) play a significant role in flavonoid biosynthesis, particularly in anthocyanin synthesis in eggplant.ConclusionGenome-wide identification, phylogenetic analysis, expression profile analysis, and exploration of metabolic pathways related to SmCYPs provide valuable insights into the roles of these genes in anthocyanin accumulation in various tissues and organs, including eggplant peel. The findings from this study lay a foundation for the functional analysis of SmCYPs involvement in anthocyanin accumulation in eggplant peel, providing a molecular basis for breeders to cultivate novel varieties of eggplants with high levels of anthocyanin content.
Keyword ：
Anthocyanin process Anthocyanin process Cytochrome P450 (CYP450) Cytochrome P450 (CYP450) Gene expression Gene expression Phylogenetic analysis Phylogenetic analysis Solanum melongena L Solanum melongena L
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yang, Ting , Zhuang, Ruijie , Wang, Shiyu et al. Genome-wide identification and functional analysis of CYP450 genes in eggplant (Solanum melongena L.) with a focus on anthocyanin accumlation [J]. | BMC GENOMICS , 2024 , 25 (1) . |
| MLA | Yang, Ting et al. "Genome-wide identification and functional analysis of CYP450 genes in eggplant (Solanum melongena L.) with a focus on anthocyanin accumlation" . | BMC GENOMICS 25 . 1 (2024) . |
| APA | Yang, Ting , Zhuang, Ruijie , Wang, Shiyu , Lv, Wanping , Wen, Yongxian . Genome-wide identification and functional analysis of CYP450 genes in eggplant (Solanum melongena L.) with a focus on anthocyanin accumlation . | BMC GENOMICS , 2024 , 25 (1) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
本文得到复系数有理分式函数的共轭极点的留数在一定条件下具有相应的对称性，并给出一类特殊的复系数有理分式函数在共轭极点的留数的实部、虚部的特性.
Keyword ：
共轭极点 共轭极点 复系数有理分式函数 复系数有理分式函数 极点 极点 留数 留数
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 丁明玲 , 温永仙 , 张慾 . 复系数有理分式函数共轭极点的留数 [J]. | 高等数学研究 , 2024 , 27 (03) : 70-74 . |
| MLA | 丁明玲 et al. "复系数有理分式函数共轭极点的留数" . | 高等数学研究 27 . 03 (2024) : 70-74 . |
| APA | 丁明玲 , 温永仙 , 张慾 . 复系数有理分式函数共轭极点的留数 . | 高等数学研究 , 2024 , 27 (03) , 70-74 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
气温的准确预测对人类生产生活、农业等方面至关重要。针对传统气温预测方法难以捕捉数据的动态变化、预测精度差等问题，提出了一种融合离散小波变换（Discrete Wavelet Transformation, DWT）、卷积神经网络（Convolutional Neural Network, CNN）和长短期记忆网络（Long Short-Term Memory, LSTM）的组合气温预测模型。首先，利用DWT对原始气温观测数据进行分解与重构；其次，使用CNN进行特征提取，使用LSTM对提取的特征信息进行处理，以实现气温预测。同时采用均方根误差、平均绝对值误差和决定系数作为评价指标；最后，使用气温观测数据验证所提模型的有效性，并分别与LSTM模型、CNN-LSTM模型和DWTLSTM模型进行对比分析。实验结果表明，与LSTM模型、CNN-LSTM模型和基于离散小波变换的LSTM模型相比，DWT-CNN-LSTM模型分别将RMSE降低了1.009 24,1.002 74,0.100 23,MAE降低了0.918 36,0.862 65,0.144 89,R
Keyword ：
卷积神经网络 卷积神经网络 时间序列 时间序列 气温预测 气温预测 离散小波变换 离散小波变换 长短期记忆网络 长短期记忆网络
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 樊姝琪 , 刘慧铭 , 庄润杰 et al. 基于DWT-CNN-LSTM逐日气温预测模型研究 [J]. | 热带气象学报 , 2024 , 40 (06) : 1063-1073 . |
| MLA | 樊姝琪 et al. "基于DWT-CNN-LSTM逐日气温预测模型研究" . | 热带气象学报 40 . 06 (2024) : 1063-1073 . |
| APA | 樊姝琪 , 刘慧铭 , 庄润杰 , 王诗雨 , 温永仙 . 基于DWT-CNN-LSTM逐日气温预测模型研究 . | 热带气象学报 , 2024 , 40 (06) , 1063-1073 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
