Communications in Information and Systems

Volume 23 (2023)

Number 2

A review of computational models for predicting protein-protein interaction and non-interaction

Pages: 15 – 184

DOI: https://dx.doi.org/10.4310/CIS.2023.v23.n2.a1

Authors

Nan Zhao (Institute for Mathematical Sciences, Renmin University of China, Beijing, China)

Xinqi Gong (nstitute for Mathematical Sciences, Renmin University of China, Beijing, China; and Beijing Academy of Artificial Intelligence, Beijing, China)

Abstract

Predicting potential protein-protein interaction and non-interaction are vital to study the mechanism of protein function. Traditional experimental technologies show their disadvantages of being expensive, time-consuming and laborious. Numerous computational methods have been developed to detect potential interacting and non-interacting protein partners. This paper reviews recent advancements in effective computational models for protein‑protein interactions and non-interactions prediction.We classified the computational methods based on the protein information types into five different categories and introduced the main ideas, advantages and disadvantages of algorithms in each category. To obtain a highquality dataset, we analyzed the collection methods and composition of positive and negative samples in detail and described some applications of real non-interacting protein pairs. Finally, we summarized some challenges and open issues in the future.

Received 2 January 2023

Published 7 August 2023