Evaluation and improvement of multiple sequence methods for protein secondary structure prediction

We have developed an automatic algorithm STRIDE for protein secondary structure assignment from atomic coordinates based on the combined use of hydrogen bond energy and statistically derived backbone torsional angle information. Parameters of the pattern recognition procedure were optimized using designations provided by the crystallographers as a standard-of-truth. Comparison to the currently most widely used technique DSSP by Kabsch and Sander (Biopolymers 22:2577-2637, 1983) shows that STRIDE and DSSP assign secondary structural states in 58 and 31% of 226 protein chains in our data sample, respectively, in greater agreement with the specific residue-by-residue definitions provided by the discoverers of the structures while in 11% of the chains, the assignments are the same. STRIDE delineates every 11th helix and every 32nd strand more in accord with published assignments.

We have trained a two-layered feed-forward neural network on a non-redundant data base of 130 protein chains to predict the secondary structure of water-soluble proteins. A new key aspect is the use of evolutionary information in the form of multiple sequence alignments that are used as input in place of single sequences. The inclusion of protein family information in this form increases the prediction accuracy by six to eight percentage points. A combination of three levels of networks results in an overall three-state accuracy of 70.8% for globular proteins (sustained performance). If four membrane protein chains are included in the evaluation, the overall accuracy drops to 70.2%. The prediction is well balanced between alpha-helix, beta-strand and loop: 65% of the observed strand residues are predicted correctly. The accuracy in predicting the content of three secondary structure types is comparable to that of circular dichroism spectroscopy. The performance accuracy is verified by a sevenfold cross-validation test, and an additional test on 26 recently solved proteins. Of particular practical importance is the definition of a position-specific reliability index. For half of the residues predicted with a high level of reliability the overall accuracy increases to better than 82%. A further strength of the method is the more realistic prediction of segment length. The protein family prediction method is available for testing by academic researchers via an electronic mail server.