Strand-loop-strand motifs: prediction of hairpins and diverging turns in proteins

TitleStrand-loop-strand motifs: prediction of hairpins and diverging turns in proteins
Publication TypeJournal Article
Year of Publication2004
AuthorsKuhn, M., Meiler J., & Baker D.
Date Published2004 Feb 1
KeywordsAlgorithms, Amino Acid Motifs, Computational Biology, Computer Simulation, Databases, Protein, Hydrogen Bonding, Internet, Models, Molecular, Neural Networks (Computer), Primary Publication, Protein Structure, Secondary, Proteins, Sensitivity and Specificity, Software

Beta-sheet proteins have been particularly challenging for de novo structure prediction methods, which tend to pair adjacent beta-strands into beta-hairpins and produce overly local topologies. To remedy this problem and facilitate de novo prediction of beta-sheet protein structures, we have developed a neural network that classifies strand-loop-strand motifs by local hairpins and nonlocal diverging turns by using the amino acid sequence as input. The neural network is trained with a representative subset of the Protein Data Bank and achieves a prediction accuracy of 75.9 +/- 4.4% compared to a baseline prediction rate of 59.1%. Hairpins are predicted with an accuracy of 77.3 +/- 6.1%, diverging turns with an accuracy of 73.9 +/- 6.0%. Incorporation of the beta-hairpin/diverging turn classification into the ROSETTA de novo structure prediction method led to higher contact order models and somewhat improved tertiary structure predictions for a test set of 11 all-beta-proteins and 3 alphabeta-proteins. The beta-hairpin/diverging turn classification from amino acid sequences is available online for academic use (Meiler and Kuhn, 2003;

Alternate JournalProteins
kuhn04A.pdf219.88 KB