piRNN: deep learning algorithm for piRNA prediction

PeerJ

article

Kai Wang¹  Joshua Hoeksema²  Chun Liang¹ 

[1] Department of Biology, Miami University;Department of Computer Science & Software Engineering, Miami University

关键词: piRNA;    Deep learning;    Convolution neural network;   

DOI  :  10.7717/peerj.5429

学科分类：社会科学、人文和艺术（综合）

来源: Inra

【 摘 要 】

Piwi-interacting RNAs (piRNAs) are the largest class of small non-coding RNAs discovered in germ cells. Identifying piRNAs from small RNA data is a challenging task due to the lack of conserved sequences and structural features of piRNAs. Many programs have been developed to identify piRNA from small RNA data. However, these programs have limitations. They either rely on extracting complicated features, or only demonstrate strong performance on transposon related piRNAs. Here we proposed a new program called piRNN for piRNA identification. For our software, we applied a convolutional neural network classifier that was trained on the datasets from four different species (Caenorhabditis elegans, Drosophila melanogaster, rat and human). A matrix of k-mer frequency values was used to represent each sequence. piRNN has great usability and shows better performance in comparison with other programs. It is freely available at https://github.com/bioinfolabmu/piRNN.

【 授权许可】

CC BY