Artificial Intelligence Powers Protein Functional Annotation.

Area of Science:

• Bioinformatics
• Computational Biology
• Genomics

Background:

• Protein functional annotation is crucial for understanding biological processes and diseases.
• Experimental methods for protein function validation are expensive and slow.
• Artificial Intelligence (AI) offers promising computational solutions for protein function inference.

Purpose of the Study:

• To systematically review computational methods for annotating Gene Ontology (GO) terms and Enzyme Commission (EC) numbers.
• To synthesize existing AI-driven approaches into a structured framework of six modeling paradigms.
• To outline future opportunities for enhanced protein functional annotation.

Main Methods:

• Categorization of existing computational methods into six general modeling paradigms.
• Parallel introduction of Gene Ontology (GO) and Enzyme Commission (EC) systems.
• Analysis of representative methods, evaluation metrics, prediction scenarios, and challenges for GO and EC annotation.

Main Results:

• A structured framework synthesizing various AI-based protein functional annotation approaches.
• Detailed overview of methods, metrics, and challenges specific to GO and EC annotation.
• Identification of emerging trends and future research directions in the field.

Conclusions:

• Computational methods, particularly AI-driven ones, are vital for efficient protein functional annotation.
• A structured understanding of existing methods is key to advancing the field.
• Future research should focus on accuracy, context-dependency, and high-resolution protein function prediction.