Reliable Sequenced-Based Protein-Protein Interaction Prediction Using Lempel Ziv Complexity and Optimized Deep Learning Model

Abstract

In this study, a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) deep learning model was developed for sequence-based prediction of protein–protein interactions (PPIs). To address the limitations of experimental methods in terms of time and cost, computational approaches were employed. A novel method based on Lempel–Ziv (LZ) complexity was proposed to select reliable non-interacting protein pairs. Protein sequences were represented as feature vectors using the Conjoint Triad (CT) method, which encodes amino acid physicochemical properties. The hybrid CNN–LSTM architecture was then used to classify interacting and non-interacting protein pairs, where CNN layers captured local sequence motifs and LSTM layers modeled long-range dependencies. Furthermore, Genetic Algorithm (GA)–based hyperparameter optimization was applied to tune model hyperparameters. The novelty of this study lies in the combination of LZ complexity–based negative sample selection, CT feature representation, and GA-optimized CNN–LSTM architecture, providing a robust and biologically informed framework for PPI prediction. The proposed model achieved 91% training accuracy and 90% testing accuracy before optimization, which increased to 94% and 93%, respectively, after GA optimization. These results demonstrate that the integrated approach enhances predictive performance and enables reliable extraction of meaningful information from protein sequences.