检索结果-南通市图书馆

Using the Support Vector Machine Algorithm to Predict β-Turn Types in Proteins

Engineering（科研） 2013年第10期5卷 386-390页

作者： Xiaobo Shi xiuzhen hu College of Sciences Inner Mongolia University of Technology Hohhot China

The structure and function of proteins are closely related, and protein structure decides its function, therefore protein structure prediction is quite important.β-turns are important components of protein secondary structure. So development of an accurate prediction method ofβ-turn types is very necessary. In this paper, we used the composite vector with position conservation scoring function, increment of diversity and predictive secondary structure information as the input parameter of support vector machine algorithm for predicting theβ-turn types in the database of 426 protein chains, obtained the overall prediction accuracy of 95.6%, 97.8%, 97.0%, 98.9%, 99.2%, 91.8%, 99.4% and 83.9% with the Matthews Correlation Coefficient values of 0.74, 0.68, 0.20, 0.49, 0.23, 0.47, 0.49 and 0.53 for types I, II, VIII, I’, II’, IV, VI and nonturn respectively, which is better than other prediction.

关键词： Support Vector Machine Algorithm Increment of Diversity Value Position Conservation Scoring Function Value Secondary Structure Information

来源：

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

The Comparison between Random Forest and Support Vector Machine Algorithm for Predicting β-Hairpin Motifs in Proteins

引用

Engineering（科研） 2013年第10期5卷 391-395页

作者： Shaochun Jia xiuzhen hu Lixia Sun Department of Physics College of Sciences Inner Mongolia University of Technology Huhhot China

Based on the research of predictingβ-hairpin motifs in proteins, we apply Random Forest and Support Vector Machine algorithm to predictβ-hairpin motifs in ArchDB40 dataset. The motifs with the loop length of 2 to 8 amino acid residues are extracted as research object and thefixed-length pattern of 12 amino acids are selected. When using the same characteristic parameters and the same test method, Random Forest algorithm is more effective than Support Vector Machine. In addition, because of Random Forest algorithm doesn’t produce overfitting phenomenon while the dimension of characteristic parameters is higher, we use Random Forest based on higher dimension characteristic parameters to predictβ-hairpin motifs. The better prediction results are obtained;the overall accuracy and Matthew’s correlation coefficient of 5-fold cross-validation achieve 83.3% and 0.59, respectively.

关键词： Random Forest Algorithm Support Vector Machine Algorithm β-Hairpin Motif Increment of Diversity Scoring Function Predicted Secondary Structure Information

来源：

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

PredictingβαβMotifs Based on SVM Algorithm by Using the ID and MS values

PredictingβαβMotifs Based on SVM Algorithm by Using the I...

引用

第五届全国生物信息学与系统生物学学术大会暨国际生物信息学前沿研讨会高通量时代的生物信息学与系统生物学

作者： Lixia Sun xiuzhen hu College of Sciences Inner Mongolia University of Technology

Background:βαβmotif is an important super secondary structure in *** strand- loop-helix-loop-strand structures,if two parallelβ-strands are connected by a a-helix,and there are one or more hydrogen bonds between two adjacent strands,then the structure is called asβαβmotifs,otherwise it is considered as non-βαβ*** function of proteins is closely related with their structure,thus study of protein structure is very important to understand its *** the high-throughput era,by using the theoretical method to predict protein structure has become one of the important ways in biology *** is very difficult to directly predict the tertiary structure from *** secondary structure, especiallyβαβmotif,is a bridge between secondary structure and tertiary structure.βαβmotifs often appear in the bacillus subtilis protease,and many function sites occur in theβαβmotifs,therefore,prediction ofβαβmotif has very important *** provides theoretical direction for drug molecules design. Methods:We constructed a new dataset,which contains 4277βαβmotifs and 3366 nonβαβmotifs with sequence identity <25%and resolution < 3.0 *** Vector Machine (SVM) algorithm is used to predictβαβmotif by using increment of diversity(ID) values, matrix scoring(MS) values and amino acids component as parameters. Results:In this paper,by using the ID values,MS values and amino acids component to express the sequence information,then we combined these parameters as SVM input. The predictive performance is *** overall accuracy and Matthew’s correlation coefficient of 5-fold cross-validation achieve 77.7%and 0.527,the sensitivity ofβαβmotifs and non-βαβmotifs achieve respectively 83.6%and 68.4%,the specificity ofβαβmotifs and non-βαβmotifs achieve respectively 79.1%and 74.4%. Conclusions:The MS values can reflect the conservatism of the amino acids sequence, and ID value is the sequence information’s secondary *** SVM algorithm is a convex quadrati

关键词： βαβmotifs amino acids component increment of diversity scoring matrix Support Vector Machine algorithm

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Prediction of the ATP-binding site in Proteins Based on Improved Feature Parameter

Prediction of the ATP-binding site in Proteins Based on Impr...

引用

第五届全国生物信息学与系统生物学学术大会暨国际生物信息学前沿研讨会高通量时代的生物信息学与系统生物学

作者： Shaobo Li xiuzhen hu College of Sciences Inner Mongolia University of Technology

Background:In the protein research field one of the major challenges is identification of function of *** function of many proteins depends on their interaction with ligands, for example,ATP ligand is one of such important ***-binding site play a key role in the coenzyme *** the experimental method to identify ATP-binding site in protein is costly and time consuming,thus with the development of technology,in the high throughput times,there is need to use computational technique to identify ATP-binding site in proteins. Methods:Based on an ATP-binding site database used by previous which contains 168 non-redundant protein *** have generated 3104 ATP-binding patterns by using sliding window *** window size is 17 amino *** we fully consider characteristics of ATP-binding site amino *** improved feature parameters which contain amino acid components,dipeptide composition,physical and chemical features.A Support Vector Machine(SVM) algorithm based on improved feature parameter for predicting ATP-binding site is proposed. Results:In order to compare predictive *** we respectively used the amino acid components,dipeptide composition,physical and chemical features as SVM input,maximum overall accuracy(ACC) of 5-fold cross-validation achieve 70.15%with Matthew’s correlation coefficient(MCC) *** we used combined vector which contains above three kinds of feature parameters as SVM input,ACC of 5-fold cross-validation achieve 76.10%with MCC *** sensitivity of ATP-binding site and nonATP-binding site achieve respectively 75.3%and 73.3%,the specificity of ATP-binding site and nonATP-binding site achieve respectively 73.4%and 73.5%.This prediction results are better than previous results. Conclusions:This results shows that the amino acid components,dipeptide composition, physical and chemical feature are all important for the predicting of ATP-binding *** we use combined vector which contain three kin

关键词： ATP-binding site Support Vector Machine combined vector ligand

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

《敦煌石窟全集》第一卷洞窟测绘图的绘制

引用

敦煌研究 2021年第5期 61-66页

作者：胡秀珍敦煌研究院考古研究所甘肃敦煌736200

《敦煌石窟全集》第一卷《莫高窟第266~275窟考古报告》于2011年8月出版,洞窟测绘图的绘制,运用了当时的三维激光扫描技术结合电脑绘图软件绘制。通过第一卷洞窟测绘图的绘制,反映出了敦煌石窟考古测绘图绘制方法、技术不断探索、创新... 详细信息

《敦煌石窟全集》第一卷《莫高窟第266~275窟考古报告》于2011年8月出版,洞窟测绘图的绘制,运用了当时的三维激光扫描技术结合电脑绘图软件绘制。通过第一卷洞窟测绘图的绘制,反映出了敦煌石窟考古测绘图绘制方法、技术不断探索、创新、发展的历程。

关键词：《敦煌石窟全集》第一卷洞窟测绘图绘制方法

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

基于DEA方法的我国中小企业融资效率评价

引用

系统工程理论与实践 2017年第4期37卷 865-874页

作者：王秀贞丁慧平胡毅北京交通大学经济管理学院北京100044 中国科学院大学经济与管理学院北京100190 中国科学院大学创新创业学院北京100190 中国科学院大数据挖掘与知识管理重点实验室北京100190

利用中国工业企业数据库中的中小企业样本,构建了我国中小企业融资效率的评价指标体系,包括反映中小企业融资效率的投入指标和产出指标,采用数据包络分析方法,对我国中小企业的融资效率进行测算和评价,并分省份、行业、所有制对计算出... 详细信息

利用中国工业企业数据库中的中小企业样本,构建了我国中小企业融资效率的评价指标体系,包括反映中小企业融资效率的投入指标和产出指标,采用数据包络分析方法,对我国中小企业的融资效率进行测算和评价,并分省份、行业、所有制对计算出的效率值进行分析.研究结果表明:样本期内,我国中小企业的整体融资效率不高,仅为0.445;有一半的企业融资效率在0.429以下,低于平均值0.445;95%的企业的融资效率低于0.643;融资效率前1%的企业中,个人控股企业数目最多,国有和外商企业数目最少.

关键词：中小企业融资效率数据包络分析中国工业企业数据库

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

基于水平集的作物病叶图像分割方法

引用

农业工程学报 2011年第2期27卷 208-212页

作者：袁媛李淼梁青胡秀珍张伟安徽农业大学农学院合肥230036 中科院合肥智能机械研究所合肥230031 大同电力高级技工学校大同037039 中国科学技术大学信息科学技术学院合肥230026

针对具有复杂背景的作物病叶图像中的叶片提取问题,提出了一种基于先验信息的水平集模型。首先,在LBF模型中引入纹理信息——结构张量,构造新的水平集模型;其次,采用水平集方法表示目标叶片形状,并将先验形状信息以能量泛函的表达形式... 详细信息

针对具有复杂背景的作物病叶图像中的叶片提取问题,提出了一种基于先验信息的水平集模型。首先,在LBF模型中引入纹理信息——结构张量,构造新的水平集模型;其次,采用水平集方法表示目标叶片形状,并将先验形状信息以能量泛函的表达形式引入到上述新的水平集模型中,得到新的基于先验信息的水平集模型;最后,利用该模型对具有复杂背景的黄瓜病叶图像进行分割。结果表明,该方法能准确地提取具有复杂背景黄瓜病叶图像中的病叶,为后续的病斑提取、识别和诊断奠定前期基础。

关键词：图像分割水平集方法结构张量先验形状复杂背景

来源：

维普期刊数据库

同方期刊数据库评论