Artificial intelligence and computational methods in human metabolism research: A comprehensive survey.

Area of Science:

• Biochemistry
• Pharmacology
• Computational Biology

Background:

• Understanding human metabolism is crucial for drug development and disease research.
• Metabolism research informs drug safety, efficacy, and disease mechanism elucidation.
• Traditional methods face challenges in predicting complex metabolic pathways.

Purpose of the Study:

• To highlight the role of artificial intelligence (AI) and machine learning (ML) in advancing human metabolism studies.
• To explore the application of AI/ML in predictive modeling for drug metabolism.
• To discuss the integration of AI-driven insights into genome-scale metabolic models (GEMs).

Main Methods:

• Utilizing machine learning (ML) and deep learning (DL) techniques for predictive modeling.
• Applying computational approaches to analyze metabolic pathways at the molecular and omics levels.
• Integrating AI-driven predictions into genome-scale metabolic models (GEMs).

Main Results:

• AI/ML significantly enhances the accuracy of predicting human metabolism.
• Computational methods facilitate molecular-level metabolism predictions.
• Integration with GEMs provides omics-level insights into metabolic processes.

Conclusions:

• AI and ML offer powerful tools for accelerating drug discovery and development.
• Overcoming challenges like data heterogeneity is key for further advancements.
• This research contributes to the progress of precision medicine through enhanced metabolism understanding.