Abstract
The interactions between RNAs and RNA binding proteins (RBPs) are crucial for understanding post-transcriptional regulation mechanisms. A lot of computational tools have been developed to automatically predict the binding relationship between RNAs and RBPs. However, most of the methods can only predict the presence or absence of binding sites for a sequence fragment, without providing specific information on the position or length of the binding sites. Besides, the existing tools focus on the interaction between RBPs and linear RNAs, while the binding sites on circular RNAs (circRNAs) have been rarely studied. In this study, we model the prediction of binding sites on RNAs as a sequence labeling problem, and propose a new model called circSLNN to identify the specific location of RBP-binding sites on circRNAs. CircSLNN is driven by pretrained RNA embedding vectors and a composite labeling model. On our constructed circRNA datasets, our model has an average F 1 score of 0.790. We assess the performance on full-length RNA sequences, the proposed model outperforms previous classification-based models by a large margin.
Highlights
Benefitting from the rapid development of high-throughput experimental technologies, transcriptome, proteome, epigenome and other omics data have accumulated in an unprecedented speed
We propose a sequence labeling neural network model to predict circRNA–protein binding sites, called circSLNN, which is composed of a long-short-term memory (LSTM) network, a convolutional neural network (CNN) and a conditional random field (CRF) model
In circSLNN, the number of convolution kernels in the CNN layer is 128, the convolution window size is 10, the hidden layer size of the bi-directional long short-term memory (BiLSTM) layer is 256, and the activation function used by the middle layer is ReLU
Summary
Benefitting from the rapid development of high-throughput experimental technologies, transcriptome, proteome, epigenome and other omics data have accumulated in an unprecedented speed. The multi-omics data have enabled large-scale studies on gene regulation at different levels. The interactions between RNAs and RNA binding proteins (RBPs) are crucial for understanding post-transcriptional regulation mechanisms (Filipowicz et al, 2008). The RNA–RBPinteractions play important roles in protein synthesis, gene fusion, alternative mRNA processing, etc. The aberrant expression of RBPs and disruption of RNA–RBP-interactions are closely related to various diseases of human beings (Khalil and Rinn, 2011). In the early stage of RNA–RBP-interaction studies, the recognition of binding sites mainly relies on the analysis of RNA–protein complexes via biophysical methods. As the experimental process is costly and laborious, it is increasingly important to develop automatic tools to predict binding sites
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.
