RaptorX-Angle: real-value prediction of protein backbone dihedral angles through a hybrid method of clustering and deep learning

Yujuan Gao,Jinbo Xu,Minghua Deng,Sheng Wang

doi:10.1186/s12859-018-2065-x

Abstract

BackgroundProtein dihedral angles provide a detailed description of protein local conformation. Predicted dihedral angles can be used to narrow down the conformational space of the whole polypeptide chain significantly, thus aiding protein tertiary structure prediction. However, direct angle prediction from sequence alone is challenging.ResultsIn this article, we present a novel method (named RaptorX-Angle) to predict real-valued angles by combining clustering and deep learning. Tested on a subset of PDB25 and the targets in the latest two Critical Assessment of protein Structure Prediction (CASP), our method outperforms the existing state-of-art method SPIDER2 in terms of Pearson Correlation Coefficient (PCC) and Mean Absolute Error (MAE). Our result also shows approximately linear relationship between the real prediction errors and our estimated bounds. That is, the real prediction error can be well approximated by our estimated bounds.ConclusionsOur study provides an alternative and more accurate prediction of dihedral angles, which may facilitate protein structure prediction and functional study.

Highlights

Protein dihedral angles provide a detailed description of protein local conformation
We evaluate the performance by Pearson Correlation Coefficient (PCC) and Mean Absolute Error (MAE) as described by [48], for assessing the prediction of φ/ψ angles
We test on 85 CASP11 targets and the latest 40 CASP12 targets with publicly released native structures

Summary

Introduction

Protein dihedral angles provide a detailed description of protein local conformation. Predicted dihedral angles can be used to narrow down the conformational space of the whole polypeptide chain significantly, aiding protein tertiary structure prediction. It has been shown that sequences contain rich information for protein tertiary structure prediction as well as functional study [1, 2]. It is challenging to directly predict tertiary structure from primary sequence, so the hierarchical approach has been widely accepted as one of the most efficient methods. Dihedral angle prediction may act as substitute or supplement for secondary structure prediction [4,5,6]. It can be used in generation of sequence/structure alignment.

Methods

Results

Discussion

Conclusion