Prediction of presynaptic and postsynaptic neurotoxins by combining various Chou\u2019s pseudo components

Yongchun Zuo,Yingli Lv,Shiyuan Wang,Haiyan Huo,Lei Yang,Tao Li

doi:10.1038/s41598-017-06195-y

Abstract

Presynaptic and postsynaptic neurotoxins are two groups of neurotoxins. Identification of presynaptic and postsynaptic neurotoxins is an important work for numerous newly found toxins. It is both costly and time consuming to determine these two neurotoxins by experimental methods. As a complement, using computational methods for predicting presynaptic and postsynaptic neurotoxins could provide some useful information in a timely manner. In this study, we described four algorithms for predicting presynaptic and postsynaptic neurotoxins from sequence driven features by using Increment of Diversity (ID), Multinomial Naive Bayes Classifier (MNBC), Random Forest (RF), and K-nearest Neighbours Classifier (IBK). Each protein sequence was encoded by pseudo amino acid (PseAA) compositions and three biological motif features, including MEME, Prosite and InterPro motif features. The Maximum Relevance Minimum Redundancy (MRMR) feature selection method was used to rank the PseAA compositions and the 50 top ranked features were selected to improve the prediction accuracy. The PseAA compositions and three kinds of biological motif features were combined and 12 different parameters that defined as P1-P12 were selected as the input parameters of ID, MNBC, RF, and IBK. The prediction results obtained in this study were significantly better than those of previously developed methods.

Highlights

Neurotoxins can be divided into presynaptic and postsynaptic neurotoxins based on their mechanism of action[1]
Evolutionary Genetics Analysis (MEGA) software[45] was used to provide the phylogenetic trees of presynaptic and postsynaptic neurotoxins, only the neurotoxins that had the signal peptides were uploaded to the MEGA software for generating phylogenetic trees
PS00118 is a pattern of phospholipase A2 histidine active site which is centered on the active site histidine and PS00119 is a pattern of phospholipase A2 aspartic acid active site which is centered on the active site aspartic acid

Summary

Introduction

Neurotoxins can be divided into presynaptic and postsynaptic neurotoxins based on their mechanism of action[1]. Due to postsynaptic neurotoxins have similarity action to the reversible acetylcholine receptor antagonist curare with curare-mimetic toxins, there are often referred to as “curare-mimetic toxins”[5] These two neurotoxins contribute to the understanding of the molecular steps of neurotransmission, and have potential use in cell biology and neuroscience research as well as therapeutics in some human neurological disorders. The Maximum Relevance Minimum Redundancy (MRMR)[34, 35] was used to rank the features for improving the performance of the predictors When these algorithms were applied to the neurotoxin dataset with 78 presynaptic neurotoxins and 69 postsynaptic neurotoxins, the overall success rates obtained by the jackknife test were significantly higher than those of existing classifier on the same dataset. We are to describe how to deal with these steps one-by-one

Methods

Results

Conclusion