Leveraging Artificial Intelligence for Protein-Based Drug Target Prediction in Pseudomonas aeruginosa

Abstract

Protein-based drug target identification, as a novel approach, has found its importance in controlling the threat of emerging antimicrobial resistance, especially in opportunistic microorganisms such as Pseudomonas aeruginosa. Recent advancements in artificial intelligence (AI) and machine learning (ML) have enabled the investigation of large-scale protein data sets, facilitating protein identification and functional annotation. In this article, the authors have proposed a hybrid computational approach, combining unsupervised and supervised machine learning methods, which can be used to analyze the physicochemical properties of P. aeruginosa proteins. Unsupervised methods like K-Means clustering and Principal Component Analysis (PCA) have been integrated into the model to identify the internal patterns among proteins, and Support Vector Machines (SVMs) have been used to classify protein functions. The authors have proven the effectiveness of the AI model in obtaining biologically relevant results regarding protein virulence and resistance with the help of additional protein physicochemical properties, thereby establishing protein analysis as a viable approach in the field of drug discovery.