Home
This Title All WIREs
WIREs RSS Feed
How to cite this WIREs title:
WIREs RNA
Impact Factor: 4.928

Recent methodology progress of deep learning for RNA–protein interaction prediction

Full article on Wiley Online Library:   HTML PDF

Can't access this content? Tell your librarian.

Abstract Interactions between RNAs and proteins play essential roles in many important biological processes. Benefitting from the advances of next generation sequencing technologies, hundreds of RNA‐binding proteins (RBP) and their associated RNAs have been revealed, which enables the large‐scale prediction of RNA–protein interactions using machine learning methods. Till now, a wide range of computational tools and pipelines have been developed, including deep learning models, which have achieved remarkable performance on the identification of RNA–protein binding affinities and sites. In this review, we provide an overview of the successful implementation of various deep learning approaches for predicting RNA–protein interactions, mainly focusing on the prediction of RNA–protein interaction pairs and RBP‐binding sites on RNAs. Furthermore, we discuss the advantages and disadvantages of these approaches, and highlight future perspectives on how to design better deep learning models. Finally, we suggest some promising future directions of computational tasks in the study of RNA–protein interactions, especially the interactions between noncoding RNAs and proteins. This article is categorized under: RNA Interactions with Proteins and Other Molecules > Protein–RNA Interactions: Functional Implications RNA Evolution and Genomics > Computational Analyses of RNA RNA Interactions with Proteins and Other Molecules > Protein–RNA Recognition
Different encoding schemes for RNA sequences. Take the RNA sequence “ACCGUUCGA” as an example, (a) shows the one‐hot encoding, (b) shows the vector of k‐mer frequency, where k is set to 3, (c) shows the continuous distributed representation for the k‐mers, where k is also set to 3, and (d) shows the stacked codon‐based encoding
[ Normal View | Magnified View ]
The reported performance of different methods for predicting RBP‐binding sites on two benchmark datasets. (a) RBP‐24 dataset; (b) RBP‐31 dataset. Here the performance is directly collected from published papers, only those methods with reported performance on the corresponding dataset are shown. iDeep and CONCISE is evaluated on a subset of RBP‐31 dataset
[ Normal View | Magnified View ]
The reported performance of different methods for predicting RNA–protein interaction pairs on two benchmark datasets. (a) RPI2241 dataset; (b) RPI488 dataset. Here the AUC values are directly collected from published papers. Only those methods with reported performance on the corresponding dataset are shown
[ Normal View | Magnified View ]
The procedure of motif discovery using a convolutional neural network
[ Normal View | Magnified View ]
A diagram of CNN and RNN for RBP‐binding sites prediction. (a) CNN for RBP‐binding sites prediction, where the white rectangle is the region after convolution and max pooling. (b) The RNN for RBP‐binding sites prediction
[ Normal View | Magnified View ]

Browse by Topic

RNA Interactions with Proteins and Other Molecules > Protein–RNA Recognition
RNA Evolution and Genomics > Computational Analyses of RNA
RNA Interactions with Proteins and Other Molecules > Protein–RNA Interactions: Functional Implications

Access to this WIREs title is by subscription only.

Recommend to Your
Librarian Now!

The latest WIREs articles in your inbox

Sign Up for Article Alerts