A principal component regression model for predicting phytochemical binding to the H. pylori CagA protein

College

College of Science

Department/Unit

Biology

Document Type

Article

Source Title

Network Modeling Analysis in Health Informatics and Bioinformatics

Volume

9

Issue

1

Publication Date

12-1-2020

Abstract

Helicobater pylori is an important causative factor in the pathogenesis of multiple gastrointestinal diseases. One of the factors responsible for the virulence of H. pylori is the cagA protein, which can interfere with a number of cellular signaling processes once this protein is transferred inside the host cell. Thus, inhibiting the interaction of the cagA protein with the host cell membrane using small molecular inhibitors appears to be a promising pharmacological strategy. In this study, a predictive model for the binding free energy of natural compounds towards the cagA protein is presented. The formulated model which is built on principal component—multiple linear regression demonstrates reliable accuracy (r2test = 0.92, RMSEtest = 0.483), while only requiring five independent variables for the prediction. It was further noted that topological descriptors had the greatest influence on the generated principal components which served as the predictors. The created regression model can help promote and accelerate the discovery of natural compounds as cagA binders for the development of anti-H. pylori agents. © 2020, Springer-Verlag GmbH Austria, part of Springer Nature.

html

Digitial Object Identifier (DOI)

10.1007/s13721-020-00252-9

Disciplines

Biology | Chemistry

Keywords

Molecules—Computer-aided design; Machine learning; Binding energy; Linear free energy relationship

Upload File

wf_no

This document is currently not available here.

Share

COinS