提出通过String Kernel方法把负实例语法数据库中的负实例转化成核矩阵,再用Kernel Principal Component Analysis(KPCA)对转换的核矩阵进行特征提取,进而可将原始负实例数据库按照这些特征分成多个容量较小的特征表。通过构造负实例特...提出通过String Kernel方法把负实例语法数据库中的负实例转化成核矩阵,再用Kernel Principal Component Analysis(KPCA)对转换的核矩阵进行特征提取,进而可将原始负实例数据库按照这些特征分成多个容量较小的特征表。通过构造负实例特征索引表设计了一个分类器,待检查的句子通过此分类器被分配到某个负实例特征表里进行匹配搜索,而此特征表的特征属性数和记录数要远远小于原始负实例数据库中的相应数目,从而大大提高了检查的速度,同时不影响语法检查的精度。通过比较测试,可看出提出的方法在保证语法检查精确度的同时有更快的速度。展开更多
MicroRNAs （miRNAs） are one family of short （21-23 nt） regulatory non-coding RNAs processed from long （70-110 nt） miRNA precursors （pre-miRNAs）. Identifying true and false precursors plays an important role in ...MicroRNAs （miRNAs） are one family of short （21-23 nt） regulatory non-coding RNAs processed from long （70-110 nt） miRNA precursors （pre-miRNAs）. Identifying true and false precursors plays an important role in computational identification of miRNAs. Some numerical features have been extracted from precursor sequences and their secondary structures to suit some classification methods; however, they may lose some usefully discriminative information hidden in sequences and structures. In this study, pre-miRNA sequences and their secondary structures are directly used to construct an exponential kernel based on weighted Levenshtein distance between two sequences. This string kernel is then combined with support vector machine （SVM） for detecting true and false pre-miRNAs. Based on 331 training samples of true and false human pre-miRNAs, 2 key parameters in SVM are selected by 5-fold cross validation and grid search, and 5 realizations with different 5-fold partitions are executed. Among 16 independent test sets from 3 human, 8 animal, 2 plant, 1 virus, and 2 artificially false human pre-miRNAs, our method statistically outperforms the previous SVM-based technique on 11 sets, including 3 human, 7 animal, and 1 false human pre-miRNAs. In particular, premiRNAs with multiple loops that were usually excluded in the previous work are correctly identified in this study with an accuracy of 92.66%.展开更多
String kernels are popular tools for analyzing protein sequence data and they have been successfully applied to many computational biology problems. The traditional string kernels assume that different substrings are ...String kernels are popular tools for analyzing protein sequence data and they have been successfully applied to many computational biology problems. The traditional string kernels assume that different substrings are independent. However, substrings can be highly correlated due to their substructure relationship or common physico-chemical properties. This paper proposes two kinds of weighted spectrum kernels： The correlation spectrum kernel and the AA spectrum kernel. We evMuate their performances by predicting glycan-binding proteins of 12 glycans. The results show that the correlation spectrum kernel and the AA spectrum kernel perform significantly better than the spectrum kernel for nearly all the 12 glycans. By comparing the predictive power of AA spectrum kernels constructed by different physico-chemical properties, the authors can also identify the physico- chemical properties which contributes the most to the glycan-protein binding. The results indicate that physico-chemical properties of amino acids in proteins play an important role in the mechanism of glycamprotein binding.展开更多
文摘提出通过String Kernel方法把负实例语法数据库中的负实例转化成核矩阵,再用Kernel Principal Component Analysis(KPCA)对转换的核矩阵进行特征提取,进而可将原始负实例数据库按照这些特征分成多个容量较小的特征表。通过构造负实例特征索引表设计了一个分类器,待检查的句子通过此分类器被分配到某个负实例特征表里进行匹配搜索,而此特征表的特征属性数和记录数要远远小于原始负实例数据库中的相应数目,从而大大提高了检查的速度,同时不影响语法检查的精度。通过比较测试,可看出提出的方法在保证语法检查精确度的同时有更快的速度。
基金the National Nat-ural Science Foundation of China (No. 60405001 and 60875001)the Natural Science Foundationof Jiangsu Province, China (No. BK2004142).
文摘MicroRNAs （miRNAs） are one family of short （21-23 nt） regulatory non-coding RNAs processed from long （70-110 nt） miRNA precursors （pre-miRNAs）. Identifying true and false precursors plays an important role in computational identification of miRNAs. Some numerical features have been extracted from precursor sequences and their secondary structures to suit some classification methods; however, they may lose some usefully discriminative information hidden in sequences and structures. In this study, pre-miRNA sequences and their secondary structures are directly used to construct an exponential kernel based on weighted Levenshtein distance between two sequences. This string kernel is then combined with support vector machine （SVM） for detecting true and false pre-miRNAs. Based on 331 training samples of true and false human pre-miRNAs, 2 key parameters in SVM are selected by 5-fold cross validation and grid search, and 5 realizations with different 5-fold partitions are executed. Among 16 independent test sets from 3 human, 8 animal, 2 plant, 1 virus, and 2 artificially false human pre-miRNAs, our method statistically outperforms the previous SVM-based technique on 11 sets, including 3 human, 7 animal, and 1 false human pre-miRNAs. In particular, premiRNAs with multiple loops that were usually excluded in the previous work are correctly identified in this study with an accuracy of 92.66%.
基金supported in part by Research Grants Council of Hong Kong under Grant No.17301214HKU CERG Grants+2 种基金Hung Hing Ying Physical Research Grantthe Research Funds of Renmin University of Chinathe National Natural Science Foundation of China under Grant Nos.11271144,11101382,11471256,and S201201009985
文摘String kernels are popular tools for analyzing protein sequence data and they have been successfully applied to many computational biology problems. The traditional string kernels assume that different substrings are independent. However, substrings can be highly correlated due to their substructure relationship or common physico-chemical properties. This paper proposes two kinds of weighted spectrum kernels： The correlation spectrum kernel and the AA spectrum kernel. We evMuate their performances by predicting glycan-binding proteins of 12 glycans. The results show that the correlation spectrum kernel and the AA spectrum kernel perform significantly better than the spectrum kernel for nearly all the 12 glycans. By comparing the predictive power of AA spectrum kernels constructed by different physico-chemical properties, the authors can also identify the physico- chemical properties which contributes the most to the glycan-protein binding. The results indicate that physico-chemical properties of amino acids in proteins play an important role in the mechanism of glycamprotein binding.
