Integrative AI, Machine Learning and Deep Learning frameworksfor drug target discovery in Chlamydia pneumoniae

The identification of novel therapeutic targets in bacterial pathogens remains a major challenge in antimicrobial research. Advances in artificial intelligence (AI), machine learning (ML), and deep learning (DL) have significantly enhanced computational strategies for protein characterization and drug discovery. In the present study, an integrated computational framework combining genome mining, AI-based functional annotation, deep learning structural prediction, molecular dynamics simulations, and machine learning–assisted trajectory analysis was employed to identify potential drug targets in Chlamydia pneumoniae . Genome analysis identified several conserved hypothetical proteins with unknown functions. Functional classification using machine learning algorithms revealed potential roles in metabolic processes, virulence mechanisms, and cellular regulation. Structural models were predicted using deep learning–based approaches and validated through stereochemical analysis. Molecular dynamics simulations were performed to evaluate structural stability and conformational dynamics. Simulation trajectories were further analyzed using AI-assisted approaches including principal component analysis, t-distributed stochastic neighbor embedding, and clustering algorithms to identify metastable conformational states. The results demonstrated stable structural conformations and distinct dynamic profiles for selected proteins. Integration of AI-driven structural prediction and molecular simulation analysis enabled identification of structurally stable proteins with potential functional relevance. These findings highlight the effectiveness of AI-assisted computational pipelines for identifying promising drug targets and provide valuable insights for future antimicrobial drug development.