Abstract
Long non-coding RNAs (lncRNAs) play crucial roles in diverse biological processes and human complex diseases. Distinguishing lncRNAs from protein-coding transcripts is a fundamental step for analyzing the lncRNA functional mechanism. However, the experimental identification of lncRNAs is expensive and time-consuming. In this study, we presented an alignment-free multimodal deep learning framework (namely lncRNA_Mdeep) to distinguish lncRNAs from protein-coding transcripts. LncRNA_Mdeep incorporated three different input modalities, then a multimodal deep learning framework was built for learning the high-level abstract representations and predicting the probability whether a transcript was lncRNA or not. LncRNA_Mdeep achieved 98.73% prediction accuracy in a 10-fold cross-validation test on humans. Compared with other eight state-of-the-art methods, lncRNA_Mdeep showed 93.12% prediction accuracy independent test on humans, which was 0.94%~15.41% higher than that of other eight methods. In addition, the results on 11 cross-species datasets showed that lncRNA_Mdeep was a powerful predictor for predicting lncRNAs.
Highlights
Long non-coding RNA are defined as non-protein-coding transcripts with a length of more than 200 nucleotides
LncRNA-MFDL [17] predicts Long non-coding RNAs (lncRNAs) by fusing multiple features and a deep stacking network, and Tripathi et al [18] proposed the DeepLNC method to predict lncRNAs by k-mer features and a deep neural network classifier. These two methods based on deep learning algorithms achieve a better performance than previous conventional machine learning algorithms to predict lncRNAs, they still depend on manually crafted features and fail to learn intrinsic features automatically from raw transcript sequences
We developed an alignment-free multimodal deep learning framework to distinguish lncRNAs from protein-coding transcripts (Figure 1, Materials and Methods)
Summary
Long non-coding RNA (lncRNAs) are defined as non-protein-coding transcripts with a length of more than 200 nucleotides. The alignment-based methods generally align the transcripts against a comprehensive reference protein database for predicting lncRNAs; for example, CPC (Coding Potential Calculator) [8] aligns transcripts against UniRef dataset [22] using BLSATX [23] tool; lncRNA-ID [11] and lncADeep [13] align the transcripts against Pfam dataset [24] using HMMER [25] tool. PLEK (Predictor of LncRNA and mEssenger RNAs based on an improved k-mer scheme) [16] proposes an improved k-mer feature These methods adopt different machine learning algorithms to build the classifiers for predicting lncRNAs. For example, CNCI and PLEK use a support vector machine (SVM), and CPAT uses logistic regression. LncRNAnet builds a convolutional neural network (CNN) for detecting the open reading frame (ORF) indicator and a recurrent neural network (RNN) for modeling RNA sequence to predict lncRNAs, not taking into consideration at all the manually crafted features
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
