CRIP: predicting circRNA-RBP interaction sites using a codon-based encoding and hybrid deep neural networks.

Researchers

Journal

Modalities

Models

Abstract

Circular RNAs (circRNAs), with their crucial roles in gene regulation and disease development, have become a rising star in the RNA world. Especially, a lot of studies focused on their interactions with RNA-binding proteins (RBPs), as the knowledge of circRNA-RBP association is very important for understanding circRNA functions. Recently, the abundant CLIP-Seq experimental data has enabled the large-scale identification and analysis of circRNA-RBP interactions, while no computational tool based on machine learning has been developed yet. We present a deep learning-based method, CRIP (\underline{C}irc\underline{R}NAs \underline{I}nteract with \underline{P}roteins), for the prediction of RBP binding sites on circRNAs, based on the RNA sequences alone. In order to fully exploit the sequence information, we propose a stacked codon-based encoding scheme and a hybrid deep learning architecture, in which a convolutional neural network (CNN) learns high-level abstract features and a recurrent neural network (RNN) learns long dependency in the sequences. We construct 37 datasets including sequence fragments of binding sites on circRNAs, and each set corresponds to one RBP. The experimental results show that the new encoding scheme is superior to the existing feature representation methods for RNA sequences, and the hybrid network outperforms conventional classifiers by a large margin, where both the CNN and RNN components contribute to the performance improvement. To the best of our knowledge, CRIP is the first machine learning-based tool specialized in the prediction of circRNA-RBP interactions, which can contribute to revealing the regulatory functions of circRNAs.
Published by Cold Spring Harbor Laboratory Press for the RNA Society.