To predict sRNA targets, we developed two models, sRNATargetNB and sRNATargetSVM, using Naive Bayes method and support vector machines, respectively. In view that the running time for sRNATargetSVM is relatively longer  and the prediction accuracy on the test dataset is less than that from the sRNATargetNB, here we only provide usage information for sRNATargetNB as follows. The software was written in Perl language.  If readers are interested in the model sRNATargetSVM, please contact us.

The steps to use and


Download the related program: Four pieces of program and related demo files are compressed in a file sRNATargetNB.rar, which should be downloaded and put them in the same directory. Four pieces of program are rnafold.exe, b2shapiro.exe,, and, respectively.


Prepare sRNA file: All sRNA sequences should be stored in a FastA format file. Here is an example of sRNA sequence file ecolisrna1.fa.


Prepare mRNA file: All related mRNA sequence names should be stored in a file. Here is an example file ecolimrna.txt. During target prediction, the related sequences will be automatically extracted from the files *.fna and *.ptt, which are downloaded from NCBI webpage. Take the E.coli as an example, the related two files are NC_000913.fna and NC_000913.ptt, respectively. Here we want to emphasize that the program was used to evaluate whether the n-th mRNA sequence in ecolimrna.txt is the target of the n-th sRNA sequence in ecolisrna1.fa.


Predict sRNA-mRNA interaction using  In dos window, type the command as " ecolisrna1.fa ecolimrna.txt NC_000913.fna NC_000913.ptt result1.txt" . The prediction results will be saved in the file result1.txt.


Predict genome-scale sRNA-mRNA interaction using In dos window, type the command as " ecolisrna2.fa NC_000913.fna NC_000913.ptt result2.txt". Here ecolisrna2.fa contains all sRNA sequences used to predict their targets. The prediction results will be saved in the file result2.txt.


Explain prediction results: Here is an example file, result2.txt, from the genome-scale prediction of sRNA-mRNA interaction. There are three columns in the file. The first column stands for the sRNA sequence name. The secondary column represents the mRNA sequence name. The third column stands for the probability for sRNA-mRNA interaction in the same row. The bigger the probability, the more possible the sRNA-mRNA interaction.