PRIME-3D2D is a 3D2D model to predict binding sites of protein\u2013RNA interaction

Juan Xie,Xu Hong,Shiyong Liu,Jinfang Zheng,Xiaoxue Tong

doi:10.1038/s42003-020-1114-y

Juan Xie, Xu Hong + Show 3 more

Open Access

https://doi.org/10.1038/s42003-020-1114-y

Copy DOI

Abstract

Protein-RNA interaction participates in many biological processes. So, studying protein–RNA interaction can help us to understand the function of protein and RNA. Although the protein–RNA 3D3D model, like PRIME, was useful in building 3D structural complexes, it can’t be used genome-wide, due to lacking RNA 3D structures. To take full advantage of RNA secondary structures revealed from high-throughput sequencing, we present PRIME-3D2D to predict binding sites of protein–RNA interaction. PRIME-3D2D is almost as good as PRIME at modeling protein–RNA complexes. PRIME-3D2D can be used to predict binding sites on PDB data (MCC = 0.75/0.70 for binding sites in protein/RNA) and transcription-wide (MCC = 0.285 for binding sites in RNA). Testing on PDB and yeast transcription-wide data show that PRIME-3D2D performs better than other binding sites predictor. So, PRIME-3D2D can be used to predict the binding sites both on PDB and genome-wide, and it’s freely available.

Highlights

Protein-RNA interaction participates in many biological processes
For investigating the effect of RNA secondary structure in RNA alignment, we developed RNA2dA, an RNA alignment approach combined RNA secondary structure and sequence
The small similarity value of two monomers (RNA and protein) was employed to measure the similarity of binary complexes on the previous studies[27,60]. This may be not the best way to describe the similarity of binary complexes, because we found that the success rate was not the highest after applying a cutoff in modeling[27]

Summary

Introduction

Protein-RNA interaction participates in many biological processes. So, studying protein–RNA interaction can help us to understand the function of protein and RNA. To take full advantage of RNA secondary structures revealed from high-throughput sequencing, we present PRIME-3D2D to predict binding sites of protein–RNA interaction. CLIP (Photoactivatable-Ribonucleoside-Enhanced Crosslinking and Immunoprecipitation)[9], iCLIP (individual-nucleotide resolution UV-Crosslinking and Immunoprecipitation)[10], and eCLIP (enhanced Crosslinking and Immunoprecipitation)[11], provide the protein–RNA interaction data on genome wide. The sequence features (such as physicochemical properties of protein and RNA, sequence composition features, motif information), RNA secondary information or RNA 3D structure features were applied to these methods[16,17,18,19] to predict the protein–RNA interaction. The co-evolution methods were introduced to predict the 3D protein–RNA complexes[24] or interaction[25] All these approaches do not take into account the RNA structurome data produced by NGS. We still lack the researches based on 3D information on genome wide because of the lack of a protein–RNA complexes[26,27]

Methods

Results

Conclusion