Prediction of acid radical ion binding residues by K-nearest neighbors classifier

Liu Liu,Xiuzhen Hu,Zhenxing Feng,Xiaojin Zhang,Kai Sun,Shan Wang,Shuang Xu

doi:10.1186/s12860-019-0238-8

Liu Liu, Xiuzhen Hu + Show 5 more

Open Access

https://doi.org/10.1186/s12860-019-0238-8

Copy DOI

Abstract

BackgroundProteins perform their functions by interacting with acid radical ions. Recently, it was a challenging work to precisely predict the binding residues of acid radical ion ligands in the research field of molecular drug design.ResultsIn this study, we proposed an improved method to predict the acid radical ion binding residues by using K-nearest Neighbors classifier. Meanwhile, we constructed datasets of four acid radical ion ligand (NO2−, CO32−, SO42−, PO43−) binding residues from BioLip database. Then, based on the optimal window length for each acid radical ion ligand, we refined composition information and position conservative information and extracted them as feature parameters for K-nearest Neighbors classifier. In the results of 5-fold cross-validation, the Matthew’s correlation coefficient was higher than 0.45, the values of accuracy, sensitivity and specificity were all higher than 69.2%, and the false positive rate was lower than 30.8%. Further, we also performed an independent test to test the practicability of the proposed method. In the obtained results, the sensitivity was higher than 40.9%, the values of accuracy and specificity were higher than 84.2%, the Matthew’s correlation coefficient was higher than 0.116, and the false positive rate was lower than 15.4%. Finally, we identified binding residues of the six metal ion ligands. In the predicted results, the values of accuracy, sensitivity and specificity were all higher than 77.6%, the Matthew’s correlation coefficient was higher than 0.6, and the false positive rate was lower than 19.6%.ConclusionsTaken together, the good results of our prediction method added new insights in the prediction of the binding residues of acid radical ion ligands.

Highlights

The protein is the foundation of life and participates in almost all life processes, such as heredity, growth and development
Hu et al developed the model (IonSeq) for predicting four acid radical ion (NO2−, CO32−, SO42−, PO43−) binding residues that were taken from the BioLip database and achieved an accuracy of nearly 98% for all ions in 2016 [17]
In 2016, Hu et al predicted binding residues of SO42− and PO43− in the BioLip database by the ensemble classifier, and obtained Matthew’s correlation coefficient was higher than 0.23 and overall accuracy was higher than 97% [18]

Summary

Introduction

The protein is the foundation of life and participates in almost all life processes, such as heredity, growth and development. Some researchers have studied acid radical ion binding residues by the experimental methods. Some researchers have studied acid radical ion binding residues by the theoretical methods. Hu et al developed the model (IonSeq) for predicting four acid radical ion (NO2−, CO32−, SO42−, PO43−) binding residues that were taken from the BioLip database and achieved an accuracy of nearly 98% for all ions in 2016 [17]. In 2016, Hu et al predicted binding residues of SO42− and PO43− in the BioLip database by the ensemble classifier, and obtained Matthew’s correlation coefficient was higher than 0.23 and overall accuracy was higher than 97% [18]. 2018, Peyton et al used an interpretable confidence-rated boosting algorithm to predict protein-ligand interactions with high accuracy from ligand chemical substructures and protein sequence motifs [21] Proteins perform their functions by interacting with acid radical ions. It was a challenging work to precisely predict the binding residues of acid radical ion ligands in the research field of molecular drug design

Objectives

Methods

Results