Prediction of piRNAs using transposon interaction and a support vector machine

Abstract

BackgroundPiwi-interacting RNAs (piRNAs) are a class of small non-coding RNA primarily expressed in germ cells that can silence transposons at the post-transcriptional level. Accurate prediction of piRNAs remains a significant challenge.ResultsWe developed a program for piRNA annotation (Piano) using piRNA-transposon interaction information. We downloaded 13,848 Drosophila piRNAs and 261,500 Drosophila transposons. The piRNAs were aligned to transposons with a maximum of three mismatches. Then, piRNA-transposon interactions were predicted by RNAplex. Triplet elements combining structure and sequence information were extracted from piRNA-transposon matching/pairing duplexes. A support vector machine (SVM) was used on these triplet elements to classify real and pseudo piRNAs, achieving 95.3 ± 0.33% accuracy and 96.0 ± 0.5% sensitivity. The SVM classifier can be used to correctly predict human, mouse and rat piRNAs, with overall accuracy of 90.6%. We used Piano to predict piRNAs for the rice stem borer, Chilo suppressalis, an important rice insect pest that causes huge yield loss. As a result, 82,639 piRNAs were predicted in C. suppressalis.ConclusionsPiano demonstrates excellent piRNA prediction performance by using both structure and sequence features of transposon-piRNAs interactions. Piano is freely available to the academic community at http://ento.njau.edu.cn/Piano.html.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-014-0419-6) contains supplementary material, which is available to authorized users.

PIWI Proteins and PIWI-Interacting RNA: Emerging Roles in Cancer

“…Brayet et al [133] integrated machine learning method based on multiple kernels and SVM classifier to identify the human and Drosophila piRNAs. Wang et al [134] performed transposon interaction and a SVM for piRNAs prediction to predict human, mouse and rat piRNAs with 90.6% accuracy. Seyeddokht et al [135] proposed a prediction method to identify piRNA in human and 48 heterogeneous features (sequence and structural features).…”

773 Piwi-interacting RNAs as novel prognostic markers in clear cell renal cell carcinomas

“…However, the recently reported comprehensive molecular characterization of ccRCC did not mention any relationships between typical RCC hot spots and piRNAs [46]. In addition, sophisticated search machines for target predictions of human piRNAs like for miRNAs are planned but are currently not available [18,47].…”

InsectBase: A resource for insect genomes and transcriptomes

“…For piRNA, 987 piRNAs of D. melanogaster were downloaded from the NCBI GenBank database (GI: 157361675-157362817) and 13 299 Drosophila piRNAs were from the NCBI Gene Expression Omnibus with the accession number GSE9138 (1). The piRNAs of Chilo suppressalis were obtained by Piano prediction (23). For long noncoding RNA (lncRNA), we developed a pipeline to find lncRNAs from 12 transcriptomes of N. lugens.…”

“…Triplet-SVM is a support vector machine (SVM)-based de novo classifier for miRNA identification (32). Piano is a SVM-based tool for piRNA annotation (23). We developed these tools and intend to provide additional Web-based services for entomologists in the future.…”