Introducing of an integrated artificial neural network and Chou's pseudo amino acid composition approach for computational epitope-mapping of Crimean-Congo haemorrhagic fever virus antigens.

This study was aimed to introduce a novel algorithm for determining linear B- and T-cell epitopes from Crimean-Congo haemorrhagic fever virus (CCHFV) antigens. To this end, 387 approved B- and T-cell epitopes, as well as 331 non-epitope peptides from different serotypes of the virus were collected from IEDB database for generating of the train datasets. After that, the physicochemical properties of the epitopes were expressed as the numeric vectors using Chou's pseudo amino acid composition method. The vectors then were used for training of four machine learning algorithms including artificial neural network (ANN), k-nearest neighbors (kNN), support vector machine (SVM) and Random forest (RF). The results confirmed that ANN was the most accurate algorithm for discriminating between the epitopes and non-epitopes with the accuracy of 0.90. Furthermore, for evaluating the performance of the ANN algorithm, an epitope prediction challenge was performed to a random peptide library from envelopment polyprotein of CCHFV. Moreover, the efficiency of the predicted epitopes in term of antigenicity and affinity to MHC-II were compared to the predicted epitope by standard epitope prediction tools based on their VaxiJen 2.0 score and molecular docking outputs. Finally, the ability of the screened epitopes to stimulation of humoral and cellular responses was evaluated by an in silico immune simulation process thought C-Immsim 10.1 server. The results confirmed that this method has more accuracy for epitope-mapping than the standard tools and could considered as an effective algorithm to develop a serotype independent one-click automated epitope based vaccine design tool.