Premium
Strand‐loop‐strand motifs: Prediction of hairpins and diverging turns in proteins
Author(s) -
Kuhn Michael,
Meiler Jens,
Baker David
Publication year - 2003
Publication title -
proteins: structure, function, and bioinformatics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.699
H-Index - 191
eISSN - 1097-0134
pISSN - 0887-3585
DOI - 10.1002/prot.10589
Subject(s) - loop (graph theory) , artificial neural network , computational biology , amino acid , set (abstract data type) , deep neural networks , test set , turn (biochemistry) , computer science , biology , artificial intelligence , algorithm , mathematics , genetics , biochemistry , combinatorics , programming language
β‐sheet proteins have been particularly challenging for de novo structure prediction methods, which tend to pair adjacent β‐strands into β‐hairpins and produce overly local topologies. To remedy this problem and facilitate de novo prediction of β‐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 β‐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‐β‐proteins and 3 αβ‐proteins. The β‐hairpin/diverging turn classification from amino acid sequences is available online for academic use (Meiler and Kuhn, 2003; www.jens‐meiler.de/turnpred.html ). Proteins 2004;54:000–000. © 2003 Wiley‐Liss, Inc.