DPROT is a PSSM based predictor for the prediction of disordered proteins. A simple two state prediction id done over the query protein. Here we utilize a SVM based algorithm to utilize evolutionary information of amino acid sequences in terms of their position specific scoring matrices (PSSMs) for the better prediction of disordered proteins. A five-fold cross-validation technique was used for the evaluation of various prediction strategies in the current work.
            The PSSM based classifier was able to achieve 78.0, 97.7, 95.1 and 0.78, corresponding to sensitivity, specificity, accuracy and MCC respectively.


Residues most prominent in disordered proteins