Prediction of RNA-protein sequence and structure binding preferences using deep convolutional and recurrent neural networks

Abstract

Background: RNA regulation is significantly dependent on its binding protein partner, known as the RNA-binding proteins (RBPs). Unfortunately, the binding preferences for most RBPs are still not well characterized. Interdependencies between sequence and secondary structure specificities is challenging for both predicting RBP binding sites and accurate sequence and structure motifs detection.

Results: In this study, we propose a deep learning-based method, iDeepS, to simultaneously identify the binding sequence and structure motifs from RNA sequences using convolutional neural networks (CNNs) and a bidirectional long short term memory network (BLSTM). We first perform one-hot encoding for both the sequence and predicted secondary structure, to enable subsequent convolution operations. To reveal the hidden binding knowledge from the observed sequences, the CNNs are applied to learn the abstract features. Considering the close relationship between sequence and predicted structures, we use the BLSTM to capture possible long range dependencies between binding sequence and structure motifs identified by the CNNs. Finally, the learned weighted representations are fed into a classification layer to predict the RBP binding sites. We evaluated iDeepS on verified RBP binding sites derived from large-scale representative CLIP-seq datasets. The results demonstrate that iDeepS can reliably predict the RBP binding sites on RNAs, and outperforms the state-of-the-art methods. An important advantage compared to other methods is that iDeepS can automatically extract both binding sequence and structure motifs, which will improve our understanding of the mechanisms of binding specificities of RBPs.

Conclusion: Our study shows that the iDeepS method identifies the sequence and structure motifs to accurately predict RBP binding sites. iDeepS is available at https://github.com/xypan1232/iDeepS .

Keywords: Bidirectional long short term memory network; Convolutional neural network; RNA-binding protein; Sequence motifs; Structure motifs.

Fig. 1

The flowchart of proposed iDeepS. For each experiment, iDeepS integrates two CNNs (one is for sequences, the other is for structures predicted by RNAshape from sequences) to predict RBP interaction sites and identify binding sequence and structure motifs, followed by the bidirectional LSTM, which learns the long range dependencies between learned sequence and structure motifs. Finally, the outputs from bidirectional LSTM are fed into a sigmoid classifier to predict the probability of being RBP binding sites

Fig. 2

The AUCs of iDeepS, DeepBind, Oli and GraphProt across 31 experiments. The performances are evaluated on the same training and independent testing set across 31 experiments (x-axis) for iDeepS,DeepBind, DeeperBind, Oli and GraphProt. For Oli, DeepBind and DeeperBind, only sequences are used. For iDeepS and GraphProt, sequences and predicted structures are used

Fig. 3

iDeepS captures known sequence motifs and structure motifs. The predicted sequence motifs are compared them against known motifs in study [48] from CISBP-RNA database and literature. E-value is the expected number of false positives for the predicted motifs against known motifs using TOMTOM. The Adjusted p-value is estimated for the corresponding structure motif using enrichment analysis tool AME in MEME Suite. The structure motifs are labelled as follows: stems (S), multiloops (M), hairpins (H), internal loops (I), dangling end (T) and dangling start (F). Note that these listed logos do not represent the full extent of the matched motifs

Fig. 4

The identified novel binding sequence and structure motifs by iDeepS for RBPs. a protein FUS. b protein MOV10. c protein IGF2BP1-3. d protein Ago2. e protein EIF4A3. f protein NSUN2. In the structure motif logos, they are labelled as follows: stems (S), multiloops (M), hairpins (H), internal loops (I), dangling end (T) and dangling start (F)

Fig. 5

The difference of predictive performance using CNN + BLSTM and only CNN. On the y-axis the performance of the full model with CNNs and BLSTM is shown. The x-axis shows the performance of the model using only the CNNs without BLSTM. The two red lines indicate the 2 times standard deviation of the difference between only using CNN and using CNN + BLSTM