iProtease-PseAAC(2L): A two-layer predictor for identifying proteases and their types using Chou's 5-step-rule and...

Area of Science:

• Biochemistry
• Bioinformatics
• Enzymology

Background:

• Proteases are essential enzymes catalyzing proteolysis, vital for cellular functions.
• Proteases play a significant role in therapeutic applications and drug development.
• Current methods for protease identification and classification are often time-consuming and operator-dependent.

Purpose of the Study:

• To develop a computational classifier, iProtease-PseAAC (2L), for identifying proteases.
• To classify proteases into their distinct types based on sequence information.
• To provide a rapid and reliable alternative to conventional protease identification methods.

Main Methods:

• Development of the iProtease-PseAAC (2L) classifier using a 5-step rule methodology.
• Utilized a benchmark dataset of protease and non-protease sequences.
• Employed rigorous verification and validation tests, including self-consistency, cross-validation, and jackknife estimation.

Main Results:

• The iProtease-PseAAC (2L) classifier achieved high accuracy in protease identification.
• Self-consistency validation yielded 98.32% accuracy.
• Cross-validation and jackknife tests demonstrated accuracies of 90.71% and 96.07%, respectively.
• The average accuracy for protease classification (level-2) was 95.77%.

Conclusions:

• iProtease-PseAAC (2L) is a highly effective tool for identifying proteases and their classes from protein sequences.
• The developed classifier offers a significant advancement over traditional, labor-intensive methods.
• This tool has strong potential for applications in drug discovery and biochemical research.