The SCEC (Structural Class prediction based on Evolutionary Collocation based sequence representation) server is designed for the prediction of 4 types of structural classes (all-α,all-β,α/β, and α+β) based on a protein sequence.

all-α	all-β	α/β	α+β

The detailed description of the prediction method can be found here.

This prediction method was published in

Chen K, Kurgan LA, Ruan J, 2008. Prediction of Protein Structural Class Using Novel Evolutionary Collocation Based Sequence Representation. Journal of Computational Chemistry, 29(10):1596-1604

The prediction method was developed with the dataset of 640 twilight zone domains that can be downloaded from here.

This prediction server is provided by the Kurgan Lab.

Input protein sequence (EXAMPLE).