ProtInteract: A deep learning framework for predicting protein-protein interactions

Farzan Soleymani; Eric Paquet; Herna Lydia Viktor; Wojtek Michalowski; Davide Spinello

doi:10.1016/j.csbj.2023.01.028

ProtInteract: A deep learning framework for predicting protein-protein interactions

Comput Struct Biotechnol J. 2023 Jan 25:21:1324-1348. doi: 10.1016/j.csbj.2023.01.028. eCollection 2023.

Authors

Farzan Soleymani¹, Eric Paquet², Herna Lydia Viktor³, Wojtek Michalowski⁴, Davide Spinello¹

Affiliations

¹ Department of Mechanical Engineering, University of Ottawa, Ottawa, ON K1N 6N5, Canada.
² National Research Council, 1200 Montreal Road, Ottawa, ON K1A 0R6, Canada.
³ School of Electrical Engineering and Computer Science, University of Ottawa, ON K1N 6N5, Canada.
⁴ Telfer School of Management, University of Ottawa, ON K1N 6N5, Canada.

Abstract

Proteins mainly perform their functions by interacting with other proteins. Protein-protein interactions underpin various biological activities such as metabolic cycles, signal transduction, and immune response. However, due to the sheer number of proteins, experimental methods for finding interacting and non-interacting protein pairs are time-consuming and costly. We therefore developed the ProtInteract framework to predict protein-protein interaction. ProtInteract comprises two components: first, a novel autoencoder architecture that encodes each protein's primary structure to a lower-dimensional vector while preserving its underlying sequence attributes. This leads to faster training of the second network, a deep convolutional neural network (CNN) that receives encoded proteins and predicts their interaction under three different scenarios. In each scenario, the deep CNN predicts the class of a given encoded protein pair. Each class indicates different ranges of confidence scores corresponding to the probability of whether a predicted interaction occurs or not. The proposed framework features significantly low computational complexity and relatively fast response. The contributions of this work are twofold. First, ProtInteract assimilates the protein's primary structure into a pseudo-time series. Therefore, we leverage the nature of the time series of proteins and their physicochemical properties to encode a protein's amino acid sequence into a lower-dimensional vector space. This approach enables extracting highly informative sequence attributes while reducing computational complexity. Second, the ProtInteract framework utilises this information to identify protein interactions with other proteins based on its amino acid configuration. Our results suggest that the proposed framework performs with high accuracy and efficiency in predicting protein-protein interactions.

Keywords: Autoencoder; Convolutional neural network; Feature selection; Long short-term memory; Protein–Protein interaction; Sequential pattern; Temporal convolutional, Network.