LncRNAnet: long non-coding RNA identification using deep learning

Motivation: Long non-coding RNAs (IncRNAs) are important regulatory elements in biological processes. LncRNAs share similar sequence characteristics with messenger RNAs, but they play completely different roles, thus providing novel insights for biological studies. The development of next-generation sequencing has helped in the discovery of IncRNA transcripts. However, the experimental verification of numerous transcriptomes is time consuming and costly. To alleviate these issues, a computational approach is needed to distinguish IncRNAs from the transcriptomes. Results: We present a deep learning-based approach, IncRNAnet, to identify IncRNAs that incorporates recurrent neural networks for RNA sequence modeling and convolutional neural networks for detecting stop codons to obtain an open reading frame indicator. IncRNAnet performed clearly better than the other tools for sequences of short lengths, on which most IncRNAs are distributed. In addition, IncRNAnet successfully learned features and showed 7.83%, 5.76%, 5.30% and 3.78% improvements over the alternatives on a human test set in terms of specificity, accuracy, Fl-score and area under the curve, respectively.