GAP: towards almost 100 percent prediction for β-strand-mediated aggregating peptides with distinct morphologies

• Published in: Bioinformatics (Oxford, England) England), 2014-07, Vol.30 (14), p.1983-1990
• Main Authors: Thangakani, A Mary, Kumar, Sandeep, Nagarajan, R, Velmurugan, D, Gromiha, M Michael
• Format: Article
• Language: English
• Subjects: Algorithms; Amino Acids - chemistry; Amyloid - chemistry; Artificial Intelligence; Oligopeptides - chemistry; Peptides - chemistry; Sequence Analysis, Protein - methods
• ISSN: 1367-4803; 1367-4811
• DOI: 10.1093/bioinformatics/btu167

Distinguishing between amyloid fibril-forming and amorphous β-aggregating aggregation-prone regions (APRs) in proteins and peptides is crucial for designing novel biomaterials and improved aggregation inhibitors for biotechnological and therapeutic purposes. Adjacent and alternate position residue pairs in hexapeptides show distinct preferences for occurrence in amyloid fibrils and amorphous β-aggregates. These observations were converted into energy potentials that were, in turn, machine learned. The resulting tool, called Generalized Aggregation Proneness (GAP), could successfully distinguish between amyloid fibril-forming and amorphous β-aggregating hexapeptides with almost 100 percent accuracies in validation tests performed using non-redundant datasets. Accuracies of the predictions made by GAP are significantly improved compared with other methods capable of predicting either general β-aggregation or amyloid fibril-forming APRs. This work demonstrates that amino acid side chains play important roles in determining the morphological fate of β-mediated aggregates formed by short peptides. http://www.iitm.ac.in/bioinfo/GAP/.