IDPpred: a new sequence-based predictor for identification of intrinsically disordered protein with enhanced accuracy

Area of Science:

• Biochemistry and Molecular Biology
• Structural Biology
• Bioinformatics

Background:

• Intrinsically disordered proteins (IDPs) lack fixed structures but are crucial for biological processes and implicated in diseases.
• Experimental characterization of IDPs is challenging due to overexpression, purification difficulties, and limited residue-level resolution.
• Existing sequence-based prediction methods struggle with accuracy, particularly for short disordered regions and boundary residues.

Purpose of the Study:

• To develop an improved sequence-based prediction method for intrinsically disordered proteins (IDPs).
• To address the limitations of current predictors in identifying short disordered regions and residues near order-disorder boundaries.
• To enhance the accuracy of large-scale proteomic investigations of protein disorder.

Main Methods:

• Utilized profiles of random sequential appearance of amino acid physicochemical properties.
• Incorporated profiles of order and disorder promoting amino acids in protein sequences.
• Integrated existing CIDER features for sequence-based IDP prediction.

Main Results:

• The developed method demonstrated significantly superior performance compared to existing IDP predictors.
• The approach showed improved accuracy across various benchmark datasets.
• Outperformed current methods in predicting intrinsically disordered protein regions (IDPRs).

Conclusions:

• The novel sequence-based approach offers a more accurate and reliable tool for IDP prediction.
• This advancement aids in large-scale proteomic studies and understanding the roles of IDPs.
• The method provides a valuable strategy for identifying potential drug targets among IDPs.