DiANNA 1.1: an extension of the DiANNA web server for ternary cysteine classification

摘要: DiANNA is a recent state-of-the-art artificial neural network and web server, which determines the 10 cysteine oxidation state disulfide connectivity of protein, given only its amino acid sequence. Version 1.0 uses feed-forward to determine cysteines are involved in bond, employs novel architec15 ture predict half-cystines covalently bound other half-cystines. In version 1.1 DiANNA, described here, we extend functionality by applying support vector machine with spectrum kernel for clas20 sification problem—to whether reduced (free sulfhydryl state), halfcystine (involved bond) or metallic ligand. latter case, predicts ligand among iron, zinc, cadmium carbon. 25 Available at: http://bioinformatics.bc.edu/clotelab/ DiANNA/.