Automatic derivation of substructures yields novel structural building blocks in globular proteins

Because the general problem of predicting the ter-tiary structure of a globular protein from its se-quence is so difficult, researchers have tried to predict regular substructures, known as secondary structures, of proteins. Knowledge of the posi-tion of these structures in the sequence can signif-icantly constrain the possible conformations of the protein. Traditional protein secondary structures are a-helices, ~sheets, and coil. Secondary struc-ture prediction programs have been developed, based upon several different algorithms. Such systems, despite their varied natures, are noted for their universal limit on prediction accuracy of about 65%. A possible cause for this limit is that traditional secondary structure classes are only a coarse characterization of local structure in pro-teins. This work presents the results of an alterna-tive approach where local structure classes in pro-teins are derived using neural network and clus-tering techniques. These give a set of local struc-ture categories, which we call Structural Building Blocks (SBBs), based upon the data itself, rather than a pr/or/categories imposed upon the data. Analysis of SBBs shows that these categories are general classifications, and that they account for recognized helical and strand regions, as well as novel categories such as N- and C-caps of helices and strands