Identifying Acetylation Protein by Fusing Its PseAAC and Functional Domain Annotation

Area of Science:

• Biochemistry
• Bioinformatics
• Computational Biology

Background:

• Acetylation is a crucial post-translational modification (PTM) involved in biological processes.
• Accurate identification of acetylation sites is vital for understanding acetylation mechanisms.
• Existing high-throughput methods have identified many sites, but discovery remains ongoing.

Purpose of the Study:

• To develop a novel computational method for identifying acetylation proteins.
• To distinguish acetylated proteins from non-acetylated ones effectively.
• To reduce experimental costs and improve the efficiency of acetylation site discovery.

Main Methods:

• Feature extraction from sequence conservation information using a gray system model.
• KNN scores integration based on functional domain annotation and subcellular localization.
• 5-fold cross-validation on three datasets with Relief feature selection algorithm.

Main Results:

• Achieved satisfactory accuracy in identifying acetylation proteins.
• Mean performance metrics: 77.10% accuracy, 0.5457 Matthew's correlation coefficient, 0.8389 AUC value.
• The developed web-server 'iACetyP' is available for researchers.

Conclusions:

• The proposed computational method is effective for identifying acetylation proteins.
• Provides valuable insights for experimental validation and further PTM studies.
• The 'iACetyP' web-server facilitates access for the research community.