Predicting the secondary structure (α-helices, α-sheets, coils) of proteins is an important step to-wards 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 of two or more disjoint regions. The exact nature of these long distance interactions remains unclear. Here we introduce two neural-network based methods for the prediction of amino acid partners in parallel as well as anti-parallel β-sheets. The neural architectures predict whether two residues located at the center of two distant windows are paired or not in a β-sheet structure. Variations on these architecture, including also profiles and ensembles, are trained and tested via five-fold cross validation using a large corpus of curated data. Prediction on both coupled and non-coupled residues currently approaches 84% accuracy, better than any previously reported method.
展开▼
