Jump to main content
Jump to site search


Predicting binding affinity of compound-protein interaction by random forest using network topology features

Abstract

Identification of binding affinity between compound and protein is of extraordinary significance to modern pharmacology and drug discovery. Despite the advances in experiment technology, the determination of binding affinity at proteome scale is still expensive, laborious and time consuming. Therefore, there is strong desire for the development of a novel theoretical method to identify binding affinity of compound-protein. A comprehensive node- and edge-weighted network is constructed including three subnetworks of compound-compound similarity, protein-protein interaction and compound-protein interaction. Based on the graph theory, some novel network topological features are proposed to characterize compound-protein interaction and random forest is utilized to construct model for predicting binding affinity of interaction. The Spearman and Pearson correlation coefficient of 0.8547 and 0.8779 as well as root mean square error of 0.8638 are obtained, indicating the effectiveness of the developed method. The 2102 potential chemical-protein interactions are identified associated with diseases, such as aromatase excess syndrome and immunodeficiency autosomal recessive. It is anticipated that the proposed method may become a powerful high-throughput virtual screening tool for drug research and development.

Back to tab navigation

Supplementary files

Publication details

The article was received on 23 Jun 2018, accepted on 05 Aug 2018 and first published on 06 Aug 2018


Article type: Paper
DOI: 10.1039/C8AY01396A
Citation: Anal. Methods, 2018, Accepted Manuscript
  •   Request permissions

    Predicting binding affinity of compound-protein interaction by random forest using network topology features

    Z. Li, Y. Wang, Y. Xie, L. Zhang, Z. Dai and X. Zou, Anal. Methods, 2018, Accepted Manuscript , DOI: 10.1039/C8AY01396A

Search articles by author

Spotlight

Advertisements