ACCURACY OF SECONDARY STRUCTURE AND SOLVENT ACCESSIBILITY PREDICTIONSFOR A CLOSTRIDIAL NEUROTOXIN C-FRAGMENT

Earlier studies used Rest and Sander's artificial neural network [(199 3a), J. Mol. Biol. 232, 584-599] to predict the secondary structures [ Lebeda and Olson (1994), Proteins 20, 293-300] and residue solvent acc essibilities [Lebeda and Olson (1997), J. Protein Chem, 16, 607-618] o f the clostridial neurotoxins. Because the X-ray crystal structure of the 50-kDa C-terminal half of the heavy chain of tetanus toxin was rec ently determined, this report evaluates the accuracy of these network- derived predictions. For this predominantly P-strand-containing fragme nt, predictions, on a per-residue basis, for both secondary structure and solvent accessibility were about 70% accurate. A more flexible and realistic analysis based on overlapping segments yielded accuracies o f over 80% for the three-state secondary structure and for the two-sta te accessibility predictions. Because the accuracies of these predicti ons are comparable to those made by Rest and Sander using a dataset of 126 nonhomologous globular proteins, our predictions provide a quanti tative foundation for gauging the results when building by homology th e structures of related proteins.