中文摘要：

microRNA（miRNA）是一类长度约为20—24个核苷酸保守的非编码小分子RNA，如何能准确预测miRNA一直是生物信息学的难点之一。文中提出一种新的预测方法一粒子群优化的前馈人工神经网络预测miRNA，从331（阴性数据168，阳性数据163）个样本组成的数据集中提取每个样本的36维特征向量训练人工神经网络模型，并用训练好的模型对不同的测试集进行测试，结果表明这种方法平均预测精度达到91．0％，高于传统的SVM预测方法，从而为miRNA预测提供了一个新的研究方向。

英文摘要：

microRNA（miRNA） is a class of 20 - 24 long nucleotides conserved non-coding small RNA. How to predict miRNA accurately is one of the difficulties in bioinformatics. A new predicting method has been proposed in this paper, that is, particle swarm opti- mized feedforward artificial neural network. Use 36 feature extracted from the data set comprised of 331 samples to train the neural network model,which used to test new data-sets get a prediction accuracy up to 91.0%. This indicates that the model can be used as a new direction to predict miRNA.