DIRECT: RNA contact predictions by integrating structural patterns

Yiren Jian,Jaidi Qiu,Zhichao Liu,Huiwen Wang,Chen Zeng,Yunjie Zhao,Xiaonan Wang

doi:10.1186/s12859-019-3099-4

Abstract

BackgroundIt is widely believed that tertiary nucleotide-nucleotide interactions are essential in determining RNA structure and function. Currently, direct coupling analysis (DCA) infers nucleotide contacts in a sequence from its homologous sequence alignment across different species. DCA and similar approaches that use sequence information alone typically yield a low accuracy, especially when the available homologous sequences are limited. Therefore, new methods for RNA structural contact inference are desirable because even a single correctly predicted tertiary contact can potentially make the difference between a correct and incorrectly predicted structure. Here we present a new method DIRECT (Direct Information REweighted by Contact Templates) that incorporates a Restricted Boltzmann Machine (RBM) to augment the information on sequence co-variations with structural features in contact inference.ResultsBenchmark tests demonstrate that DIRECT achieves better overall performance than DCA approaches. Compared to mfDCA and plmDCA, DIRECT produces a substantial increase of 41 and 18%, respectively, in accuracy on average for contact prediction. DIRECT improves predictions for long-range contacts and captures more tertiary structural features.ConclusionsWe developed a hybrid approach that incorporates a Restricted Boltzmann Machine (RBM) to augment the information on sequence co-variations with structural templates in contact inference. Our results demonstrate that DIRECT is able to improve the RNA contact prediction.

Highlights

It is widely believed that tertiary nucleotide-nucleotide interactions are essential in determining RNA structure and function
direct coupling analysis (DCA) requires a sufficient number of homologous sequences for accurate sequence co-evolution analysis, which may not be readily available
The results showed an average accuracy increase of 15 and 4% compared to mean-field formulation of DCA (mfDCA) and Direct Information REweighted by Contact Templates (DIRECT) achieves reliable prediction of conserved contacts The hypothesis of direct coupling analysis stipulates that co-evolving nucleotides in an RNA molecule may form intra-molecular contacts to support its structure and function

Summary

Introduction

It is widely believed that tertiary nucleotide-nucleotide interactions are essential in determining RNA structure and function. Many computational RNA tertiary structure prediction methods have been developed, including homology or fragments-based prediction (ModeRNA, Vfold, RNAComposer, 3dRNA) [10,11,12,13,14,15,16] and simulation-based prediction (SimRNA, Rosetta FARFAR, iFoldRNA, NAST) [17,18,19,20,21]. Using these strategies, sequence and secondary structure information can be used to predict RNA tertiary structures. The starting point for this approach is to determine the potential contacts themselves

Methods

Results

Discussion

Conclusion