Construction of two mathematical models for prediction of bacterial sRNA targets.

Accurate prediction of sRNA targets plays a key role in determining sRNA functions. Here we introduced two mathematical models, sRNATargetNB and sRNATargetSVM, for prediction of sRNA targets using Nai ve Bayes method and support vector machines (SVM), respectively. The training dataset was composed of 46 positive samples (real sRNA-targets interaction) and 86 negative samples (no interaction between sRNA and targets). The leave-one-out cross-validation (LOOCV) classification accuracy was 91.67% for sRNATargetNB, and 100.00% for sRNATargetSVM. To evaluate the performance of the models, an independent test dataset was used, which contained 22 positive samples and 1700 randomly generated negative samples. The results showed that the classification accuracy, sensitivity, and specificity were 93.03%, 40.90%, and 93.71% for sRNATargetNB and 80.55%, 72.73%, and 80.65% for sRNATargetSVM, respectively. Therefore, the presented models provide support for experimental identification of sRNA targets. The related software and supplementary materials can be downloaded from webpage http://www.biosun.org.cn/srnatarget/.

[1]  Ivo L. Hofacker,et al.  Vienna RNA secondary structure server , 2003, Nucleic Acids Res..

[2]  Momiao Xiong,et al.  Tclass: tumor classification system based on gene expression profile , 2002, Bioinform..

[3]  Pascale Cossart,et al.  Identification of new noncoding RNAs in Listeria monocytogenes and prediction of mRNA targets , 2007, Nucleic acids research.

[4]  G. Storz,et al.  Target prediction for small, noncoding RNAs in bacteria , 2006, Nucleic acids research.

[5]  J. Vogel,et al.  Target identification of small noncoding RNAs in bacteria. , 2007, Current opinion in microbiology.

[6]  J. Vogel,et al.  The Small RNA IstR Inhibits Synthesis of an SOS-Induced Toxic Peptide , 2004, Current Biology.

[7]  C. Zaniolo,et al.  Letter , 1986, Experimental Gerontology.

[8]  Jörg Vogel,et al.  How to find small non-coding RNAs in bacteria , 2005, Biological chemistry.

[9]  Liyan Xu,et al.  Construction of mathematical model for high-level expression of foreign genes in pPIC9 vector and its verification. , 2007, Biochemical and biophysical research communications.

[10]  Changning Liu,et al.  Identifying Hfq-binding small RNA targets in Escherichia coli. , 2006, Biochemical and biophysical research communications.

[11]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[12]  G. Storz,et al.  MicC, a Second Small-RNA Regulator of Omp Protein Expression in Escherichia coli , 2004, Journal of bacteriology.

[13]  Alan Mitchell Durham,et al.  Computational methods in noncoding RNA research , 2008, Journal of mathematical biology.

[14]  B. Tjaden,et al.  Prediction of small, noncoding RNAs in bacteria using heterogeneous data , 2007, Journal of mathematical biology.

[15]  Kaitai Zhang,et al.  An Approach to Studying Lung Cancer-related Proteins in Human Blood*S , 2005, Molecular & Cellular Proteomics.

[16]  Byoung-Tak Zhang,et al.  miTarget: microRNA target gene prediction using a support vector machine , 2006, BMC Bioinformatics.

[17]  G. Storz,et al.  The Escherichia coli OxyS regulatory RNA represses fhlA translation by blocking ribosome binding , 1998, The EMBO journal.

[18]  N. Delihas,et al.  MicF: an antisense RNA gene involved in response of Escherichia coli to global stress factors. , 2001, Journal of molecular biology.

[19]  S. Gottesman,et al.  A small RNA regulates the expression of genes involved in iron metabolism in Escherichia coli , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[20]  M. Herbster,et al.  Identification of diagnostic markers for tuberculosis by proteomic fingerprinting of serum , 2006, The Lancet.

[21]  S. Gottesman,et al.  Effect of RyhB Small RNA on Global Iron Use in Escherichia coli , 2005, Journal of bacteriology.