SECONDARY STRUCTURE PREDICTION QUALITY FOR NATURALLY-OCCURRING AMINO-ACIDS IN SOLUBLE-PROTEINS

To judge the performance of protein secondary structure prediction it is common to use performance measures that can report the prediction a ccuracy for each conformation of the three-state model (ct-helix, P-sh eet and loop). Much more specific performance quality factors can be a ssociated with each amino acid type found in each conformation. Such m easures are introduced in this work and used to test both weak and str ong features of secondary structure prediction with neural network alg orithms. Proline in the loop conformation is the best predicted amino acid conformation. At the same time proline is the worst predicted ami no acid in regular secondary structures. Other helix cap residues: gly cine, serine, asparagine, aspartate and histidine are also poorly pred icted in regular secondary structures. The overall percentage of corre ct predictions ranges from 77 for methionine to 65 for cysteine. Based on these results the prediction accuracy profile can be reported as a sequence of numbers along a polypeptide sequence for each protein tes ted with the chosen prediction scheme. Sequence segments associated wi th a low prediction accuracy will indicate that a training database of proteins was not adequate for the task of predicting such segments ev en by using the best available pattern recognition scheme.