检索结果-南通市图书馆

Application of deep learning in genomics

在线全文

学校读者我要写书评

暂无评论

Science China(life Sciences) 2020年第12期63卷 1860-1878页

作者： Jianxiao liu jiying li Hai Wang Jianbing Yan National Key Laboratory of Crop Genetic Improvement Huazhong Agricultural UniversityWuhan 430070China College of Informatics Huazhong Agricultural UniversityWuhan 430070China Microsoft Corporation Redmond 98052USA National Maize Improvement Center Key Laboratory of Crop Heterosis and UtilizationJoint Laboratory for International Cooperation in Crop Molecular BreedingChina Agricultural UniversityBeijing 100193China

In recent years, deep learning has been widely used in diverse fields of research, such as speech recognition, image classification,autonomous driving and natural language processing. Deep learning has showcased dramatically improved performance in complex classification and regression problems, where the intricate structure in the high-dimensional data is difficult to discover using conventional machine learning algorithms. In biology, applications of deep learning are gaining increasing popularity in predicting the structure and function of genomic elements, such as promoters, enhancers, or gene expression levels. In this review paper, we described the basic concepts in machine learning and artificial neural network, followed by elaboration on the workflow of using convolutional neural network in genomics. Then we provided a concise introduction of deep learning applications in genomics and synthetic biology at the levels of DNA, RNA and protein. Finally, we discussed the current challenges and future perspectives of deep learning in genomics.

关键词： deep learning genomics convolutional neural network

Morphological and molecular identification of Xylocoris flavipes(Hemiptera:Anthocoridae)in southern China

在线全文

学校读者我要写书评

暂无评论

Grain & Oil Science and Technology 2021年第1期4卷 26-32页

作者： Zonglin Wu Shaohua Lu jiying li Shiyuan Miao Yujie Lu School of Food Science and Technology Henan University of TechnologyZhengzhou 450001China School of Grain Science and Technology Jiangsu University of Science and TechnologyZhenjiang 212003China

During the investigation of natural enemy insects in grain depots,we've found an Anthocoridae insect accounted for a high proportion of natural enemy *** identify the enemy insects from morphology and molecular biology,so as to realize more accurate and effective control of storage pests by using the enemy *** images of the insects under the ultra-depth microscope(VHX-5000)showed that the insect adults were black brown in colour;the antennas of both the female and male had four segments,which increase in length sequentially from the base to the end,and had a length of 756.2μm for the female and 741.1μm for the *** rostrums of both the female and the male insects were composed of three segments,the male's rostrum(596.8μm)were shorter than the female's(734.6μm),and the former two segments of the female's rostrum were significantly longer than the male'*** abdomen of the insect was bilaterally symmetrical,the female's abdomen was wider than the male,and the male insect had a dent between its eighth and ninth segments of the left abdomen,in which its male genitalia was *** addition,the nymphs as a whole were tangerine in colour,and the eggs were elliptic with creamy white gloss and gridding patterns on the *** cytochrome C oxidase I(COI)gene sequences of the insects were identified by DNA barcoding technique,and the determined COI sequences were then submitted to the Genbank database for Blast alignment,and the results showed that the COI gene sequences had a high degree of similarity(99%)with *** records in the Genbank ***,we could determine that the insect was *** addition,the neighbor joining(NJ)was used to construct the evolutionary tree,and 1,000 repeated tests were conducted on the confidence levels of each *** on the phylogenetic tree,we've found that *** belongs to Xylocoris *** on morphology and COI sequence identification,we confidentiy determined that the collected nat

关键词： Xylocoris flavipes Morphology DNA barcoding Stored products insects COI

Mathematical Model of Decarburization of Ultra Low Carbon Steel during RH Treatment

在线全文

学校读者我要写书评

暂无评论

International Journal of Minerals,Metallurgy and Materials 1997年第4期11卷 19-23页

作者： ZHANG lifeng JING Xuejing li jiying XU Thongbo CAI Kaike(Metallurgy Engineering School, USTB, Beijing 100083, China) USTB Beijing China

According to the balance of carbon and oxygen, a decarburization model for the RH treatment has been developed. in which the influence of the mass transfer of carbon and oxygen in the liquid steel and the stirring energy (ε) in the vacuum vessel on decarburization rate has been considered. The conclusion that the volumetric coefficients of the mass transfer of carbon is proportional to ε(1.5) is drawn. Industrical experiment proves this model is reliable. The influence of some factors on decarburization rate has been obtained. which can provide directions for RH treatment The decarburization behavior of steel with RH-OB treatment is also studied. The OB-or-not curve, the optimized OB time and OB amount are discussed.

关键词： RH treatment ultra-low carbon steel decarburization behavior mathematical model

DeepCBA:A deep learning framework for gene expression prediction in maize based on DNA sequences and chromatin interactions

在线全文

学校读者我要写书评

暂无评论

Plant Communications 2024年第9期5卷 38-53页

作者： Zhenye Wang Yong Peng Jie li jiying li Hao Yuan Shangpo Yang Xinru Ding Ao Xie Jiangling Zhang Shouzhe Wang Keqin li Jiaqi Shi Guangjie Xing Weihan Shi Jianbing Yan Jianxiao liu National Key Laboratory of Crop Genetic Improvement Huazhong Agricultural UniversityWuhan 430070China Hubei Key Laboratory of Agricultural Bioinformatics Huazhong Agricultural UniversityWuhan 430070China College of Informatics Huazhong Agricultural UniversityWuhan 430070China Hubei Hongshan Laboratory Wuhan 430070China Microsoft Corporation RedmondWA 98052USA WIMI Biotechnology Co. Ltd.Changzhou 213000China

Chromatin interactions create spatial proximity between distal regulatory elements and target genes in the genome,which has an important impact on gene expression,transcriptional regulation,and phenotypic *** date,several methods have been developed for predicting gene ***,existing methods do not take into consideration the effect of chromatin interactions on target gene expression,thus potentially reducing the accuracy of gene expression prediction and mining of important regulatory *** this study,we developed a highly accurate deep learning-based gene expression prediction model(DeepCBA)based on maize chromatin interaction *** with existing models,DeepCBA exhibits higher accuracy in expression classification and expression value *** average Pearson correlation coefficients(PCCs)for predicting gene expression using gene promoter proximal interactions,proximaldistal interactions,and both proximal and distal interactions were 0.818,0.625,and 0.929,respectively,representing an increase of 0.357,0.16,and 0.469 over the PCCs obtained with traditional methods that use only gene proximal *** important motifs were identified through DeepCBA;they were enriched in open chromatin regions and expression quantitative trait loci and showed clear tissue ***,experimental results for the maize flowering-related gene ZmRap2.7 and the tillering-related gene ZmTb1 demonstrated the feasibility of DeepCBA for exploration of regulatory elements that affect gene ***,promoter editing and verification of two reported genes(ZmCLE7 and ZmVTE4)demonstrated the utility of DeepCBA for the precise design of gene expression and even for future intelligent *** is available at http://***/or http://124.***.197.196/.

关键词： maize gene expression prediction chromatin interactions deep learning promoter editing regulatory elements and motifs

Strong Seedlings of Improved Varieties and High-efficiency Cultivation of Artificial Forests Promotes the Early Realization of"Carbon Neutrality"

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Agricultural Biotechnology 2022年第4期11卷 136-141页

作者： Menghong HU jiying li Man SUN Gansu Xiaolongshan Research Institute of Forest Science Tianshui 741022China Key Laboratory of Secondary Forest Cultivation Gansu Province Gansu Xiaolongshan Forest Ecosystem National Positioning Observation and Research StationTianshui 741022China

China is striving to achieve"carbon dioxide peaking"in 2030 and"carbon neutrality"in *** addition to optimizing and upgrading the industrial structure and increasing industrial emission reduction,afforestation is an important way to increase forest carbon sinks and achieve carbon dioxide peaking and carbon *** seedlings are significantly better than general seedlings in terms of afforestation adaptability,growth and stress *** use of improved varieties for afforestation can improve the quality of afforestation from the *** the growth cycle of economical tree species is short,and the carbon storage does not increase after directional cultivation,they significantly improve the quality and yield,and indirectly reduce carbon emissions compared with ordinary ***,in agricultural and forestry production,the transformation and utilization efficiency of improved varieties should be improved and the planting structure should be optimized to improve the quality and efficiency and significantly improve the yield and carbon storage,and the management of plantations should be strengthened to help achieve the goal of"carbon neutrality"as soon as *** paper analyzed the current situation of improved varieties and plantation management in China,and put forward corresponding countermeasures.

关键词： Improved seedlings Afforestation Afforestation quality Plantation management Carbon neutrality

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

基于优化蚁群算法的钢轨轮廓识别

中国铁道科学 2017年第4期38卷 8-14页

作者：旷文珍常峰许丽李积英兰州交通大学自动化与电气工程学院甘肃兰州730070 兰州交通大学光电技术与智能控制教育部重点实验室甘肃兰州730070 兰州交通大学电子与信息工程学院甘肃兰州730070

针对传统蚁群算法在钢轨图像识别中存在的问题,对蚁群算法进行4个方面的优化。初始化过程优化:采用一维Logistic混沌映射序列非线性迭代方程,使蚁群的初始化分布更加均匀,以避免大量的无关运算;搜索过程优化:在蚁群的搜索初期采用随机... 详细信息

针对传统蚁群算法在钢轨图像识别中存在的问题,对蚁群算法进行4个方面的优化。初始化过程优化:采用一维Logistic混沌映射序列非线性迭代方程,使蚁群的初始化分布更加均匀,以避免大量的无关运算;搜索过程优化:在蚁群的搜索初期采用随机搜索策略,根据图像灰度梯度值自动设置阈值,初步确定图像中钢轨边缘的像素点,然后建立区域搜索模型,以进行钢轨边缘的精确搜索和描绘;搜索步长优化:在搜索初期,采用大步长随机搜索策略识别钢轨边缘的像素点,然后利用小步长区域搜索策略对钢轨边缘像素点做更精确地识别,从而实现钢轨轮廓的精确识别,并减少了搜索时间和算法的收敛时间;信息素更新策略优化:每完成1次搜索,根据自动设置的信息素最大、最小浓度值更新信息素,防止陷入局部最优。对实际采集到的直线和曲线线路上的钢轨图像分别用Canny边缘检测算子、传统算法和优化算法进行钢轨轮廓识别的对比试验,结果表明:优化算法具有更好的健壮性和识别效率。

关键词：蚁群算法钢轨识别边缘检测混沌向量搜索策略信息素

公共图书馆弱势群体特色服务的实践与思索——以黔南州图书馆盲人特色服务为例

在线全文

学校读者我要写书评

暂无评论

国家图书馆学刊 2010年第1期19卷 80-81,92页

作者：李纪英贵州省都匀市黔南州图书馆

通过对黔南州图书馆为提高盲人特色服务实效性所进行的多方面探索总结,从四个方面阐述了公共图书馆怎样提高弱势群体特色服务实效性。参考文献4。

关键词：图书馆弱势群体特色服务

Solution for Smooth Evolution of CDMA2000 to3G

在线全文

学校读者我要写书评

暂无评论

ZTE Communications 2004年第1期2卷 28-29,33页

作者： Xiang jiying li Weidong (CDMA Division of ZTE Corporation,Shenzhen 518004,China)

Analysis on the evolution and developmenttrend of CDMA standards can be madeon the radio and network ***,ZTE’s solution for thesmooth evolution of CDMA2000 to 3G isproposed in the two aspects.

关键词： CDMA EV ZTE DV DO Solution for Smooth Evolution of CDMA2000 to3G

融合量子克隆进化与二维Tsallis熵的医学图像分割算法

在线全文

学校读者我要写书评

暂无评论

计算机辅助设计与图形学学报 2014年第3期26卷 465-471页

作者：李积英党建武王阳萍兰州交通大学电子与信息工程学院兰州730070

针对进化算法用于图像分割时收敛速度慢、易早熟的缺点,提出一种改进的量子克隆进化算法.首先利用量子空间的多样性丰富种群信息,在量子变异中根据适应度的不同对个体施以不同的混沌扰动,以克服量子门旋转方向单一、大小固定的缺陷,避... 详细信息

针对进化算法用于图像分割时收敛速度慢、易早熟的缺点,提出一种改进的量子克隆进化算法.首先利用量子空间的多样性丰富种群信息,在量子变异中根据适应度的不同对个体施以不同的混沌扰动,以克服量子门旋转方向单一、大小固定的缺陷,避免种群陷入局部早熟;然后利用克隆算子将最优个体信息扩充至下一代,以提高其局部寻优能力,加快收敛速度;最后将此算法用于寻找二维Tsallis熵的最佳阈值,实现了对图像的分割.实验结果表明,该算法有效地解决了进化算法收敛速度慢和容易陷入局部极值的问题,而且在分割速度和精度上得到了较大提高,分割效果良好,可以满足医学图像三维重建要求.

关键词：进化算法量子克隆二维Tsallis熵图像分割