Protein β-Sheet Partner Prediction by Neural Networks

Abstract

Predicting the secondary structure (α-helices, β-sheets, coils) of proteins is an important step towards understanding their three dimensional conformations. Unlike α-helices that are built up from one contiguous region of the polypeptide chain, β-sheets are more complex resulting from a combination several disjoint regions. The exact nature of these long distance interactions remains unclear. Here we introduce a neural-network based method for the prediction of amino acid partners in parallel as well as anti-parallel β-sheets. The neural architecture predicts whether two residues located at the center of two distant windows are paired or not in a β-sheet structure. The distance between the windows is a third essential input into the architecture. Variations on this architecture are trained using a large corpus of curated data. Prediction on both coupled and non-coupled residues currently exceeds 83% accuracy, well above any previously reported method. Unlike standard secondary structure prediction methods, the use of multiple alignment (profiles) in our case seems to degrade the performance, probably as a result of intra-chain correlation effects.