Integrated sequence-structure motifs suffice to identify microRNA precursors

About Mirident classifier

This program is developed for predicting a query sequence with hairpin structure as a real miRNA precursor or not. The Mirident classifier analyzes the ss-motifs of the query and predicts it using a SVM classifier. The SVM classifier is previously trained based on the ss-motif features of a set of real miRNA precursors and a set of non-premiRNA hairpins.

Mirident classifier was written by Xiuqin Liu and is free to all.

Install and Use

1. Download the package to anywhere in your computer
2. Uncompress the file: mirident soft and
3. Read Readme.txt before running the programs

Mirident classifier runs directly on Windows with Python compiler.

Note: this package need the third-party softwares, namely RNAfold and Libsvm packages.

RNAfold can be downloaded from
Libsvm can be downloaded from, the 2.86 version is used in our work and we recommend this version. (The homepage of Libsvm is

And both softwares should be compiled in local PC.


The package is free for all users but without any warranty.

Mirident classifier contains all source codes for predicting candidate hairpins.
train_test data


Please contact mail to: for any problem.