Please login first
Alignment-Free Model for Prediction of B-cell Epitopes  
* 1 , 1 , 1 , 2 , 1
1  Molecular Biology Laboratory, CIESA, FMVZ, Autonomous University of The State of Mexico (UAEM), 50200 Mexico State, Mexico.
2  Wellcome Trust Centre for Molecular Parasitology, University of Glasgow, University Place, Glasgow G12 8TA, United Kingdom.


In this work, we developed a general Perturbation Theory model for prediction of B-cell epitopes in vaccine design. The method predicts the epitope activity εq(cqj) of one query peptide (q-peptide) in a set of experimental query conditions (cqj). The model proposed here is able to classify 1,048,190 pairs of query and reference peptide sequences reported on IEDB database with perturbations in sequence or assay conditions. The model has accuracy, sensitivity, and specificity between 71% and 80% for training and external validation series. The model may become a useful tool for epitope selection towards vaccine design. The theoretic-experimental results on Bm86 protein may help on the future design of a new vaccine based on this protein. Ref: J Proteome Res. 2017 Sep 18. doi: 10.1021/acs.jproteome.7b00477

Keywords: Proteome mining; Epitope prediction; B-cell epitope; PCR; Bm86 protein; Machine Learning; Perturbation Theory.