Recognition of a protein fold in the context of the SCOP classification

A computational method has been developed for the assignment of a protein s equence to a folding class in the Structural Classification of Proteins (SC OP). This method uses global descriptors of a primary protein sequence in t erms of the physical, chemical, and structural properties of the constituen t amino acids. Neural networks are utilized to combine these descriptors in a way to discriminate members of a given fold from members of all other fo lds. An extensive testing of the method has been performed to evaluate its prediction accuracy. The method is applicable for the fold assignment of an y protein sequence with or without significant sequence homology to known p roteins. A WWW page for predicting protein folds is available at URL http:/ /cbcg.lbl.gov/. Proteins 1999;35:401407, Published 1999 Wiley-Liss, Inc.dag ger.