This consensus-based method is designed for in-silico prediction of per-residue protein disorder propensities. It combines four rationally selected input predictors: DISOclust, DISOPRED2, MD, and SPINE-D, using custom-designed features that aggregate their predictions and binomial deviance-based regression model.
Upon the usage the users are requested to use the following citations:
disCoP accepts either single or multiple protein sequences. The input is limited to 5 protein sequences at the time. The user should submit the protein sequence(s) in FASTA format.
The format of the input file is as follows (example):