Prediction of MoRFs in Protein Sequences with MLPs Based on Sequence Properties and Evolution Information.

Hao He,Guiling Sun,Jiaxiang Zhao

doi:10.3390/e21070635

Abstract

Molecular recognition features (MoRFs) are one important type of intrinsically disordered proteins functional regions that can undergo a disorder-to-order transition through binding to their interaction partners. Prediction of MoRFs is crucial, as the functions of MoRFs are associated with many diseases and can therefore become the potential drug targets. In this paper, a method of predicting MoRFs is developed based on the sequence properties and evolutionary information. To this end, we design two distinct multi-layer perceptron (MLP) neural networks and present a procedure to train them. We develop a preprocessing process which exploits different sizes of sliding windows to capture various properties related to MoRFs. We then use the Bayes rule together with the outputs of two trained MLP neural networks to predict MoRFs. In comparison to several state-of-the-art methods, the simulation results show that our method is competitive.

Highlights

Disordered proteins (IDPs) possess flexible and instable structures which make them play a crucial role in a variety of important biological functions [1]
Utilizing the probability distributions yielded from these two distinct multi-layer perceptron (MLP) neural networks, we follow the Bayes rule to predict molecular recognition features (MoRFs)
For comparison with other methods, we use the same datasets created by Disfani et al [9], which is from Protein Data Bank (PDB) [25]

Summary

Introduction

Disordered proteins (IDPs) possess flexible and instable structures which make them play a crucial role in a variety of important biological functions [1]. Being an important type of functional region in IDPs, molecular recognition features (MoRFs), generally consisting of 10–70 consecutive residues and are located in the long disordered regions, can undergo a disorder-to-order transition through binding to their interaction partners [2,3]. Many MoRFs, acting as molecular switches in molecular-interaction networks, play a role in the signaling and alternative splicing of cells [2]. It is observable that MoRFs are abundant in proteins with recognition functions [5]. Prediction of MoRFs is crucial, as the functions of MoRFs are associated with many diseases and may be potential drug targets [6]

Methods

Results

Conclusion