Protein Structure and Function: Application of Bioinformatics Methods - John Rigden 2014

Bioinformatics Methods for Studying the Structure and Function of Disordered Proteins
Disorder Prediction
A reduced alphabet is sufficient for disorder prediction

To highlight the key aspects of the physical principles underlying disorder, it has been demonstrated that ordered and disordered Proteins can be distinguished using a reduced alphabet, i.e., by clustering the 20 Amino Acids into a smaller number of groups (Weathers et al. 2004). It was found that a support vector machine-based algorithm analyzing Amino Acid Composition achieves a prediction accuracy of 87±2%. This indicates that amino acid composition is the primary feature determining disorder. However, a successive significant reduction in the parameter space through the clustering of physically/chemically similar amino acids had no effect on prediction accuracy down to 4 vectors describing the 20 amino acids (84±2%). In agreement with the principles described earlier, the composition and relative weights of the vectors indicate that the primary determinants of structural disorder are not specific amino acids, but rather the general PHYSICOCHEMICAL PROPERTIES OF the protein.



Last update: 06/08/2026

Editorial and Educational Adaptation: This material has been compiled based on the primary/original source text. The project team performed an editorial review, corrected technical inaccuracies, structured sections, and adapted the content for an educational format.

What was processed:

  • elimination of formatting defects (OCR errors, structural breaks, corrupted characters);
  • editorial organization of content;
  • standardization of terminology in accordance with academic sources;
  • verification of factual statements against the original source text.

All mentions of the author, publication year, and origin of the primary text have been preserved in accordance with the source.