非編碼小片段核糖核酸 (sRNAs) 在許多細胞中扮演著重要調控功能的角色,由於非編碼小片段核糖核酸所具有特性使然: 非編碼小片段核糖核酸長度較短、 不會轉譯成蛋白質，以及穩定性會隨著不同條件而改變，因此現今以實驗及計算方法預測非編碼小片段核糖核酸皆相當困難。而目前大多數已知的非編碼小片段核糖核酸是在大腸桿菌上被發現，且高度保留於相近物種的基因體中。 因此我們發展出一項整合方法，藉由分析已知的非編碼小片段核糖核酸具有特徵，進而搜尋相近物種基因體上位於基因之間非編碼區內的高度保留區域，再以支持向量機(SVM)判定，以求發現新的非編碼小片段核糖核酸基因。 Small non-coding RNA genes have been shown to play important regulatory roles in a variety of cellular processes, but prediction of non-coding RNA genes is a great challenge to both experimental and computational approach due to the characteristics of sRNAs: small size, not translated into proteins, and varied stability under different conditions. Most known sRNAs have been identified in Escherichia coli and conserved in closely related organisms. We hope to develop an integrative approach to search highly conserved intergenic regions among related bacterial genomes for combination of various characteristics extracting from known sRNAs genes on Escherichia coli using support vector machines (SVM) to predict novel sRNA genes.
