Resumen:
In this work, we developed a general Perturbation Theory and Machine Learning (PTML) method for data mining of proteomes in order to discover new B-cell epitopes useful for 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 method uses as input the sequence of the q-peptide. The method also uses as input information about the sequence and epitope activity εr(crj) of a peptide of reference (r-peptide) assayed on similar experimental conditions (crj). The model proposed here is able to classify 1,048,190 pairs of query and reference peptide sequences from the proteome of many organisms reported on IEDB database. These pairs have variations (perturbations) in sequence or assay conditions. The model has accuracy, sensitivity, and specificity between 71% and 80% for training and external validation series. The retrieved information contains structural changes in 83683 peptides sequences (Seq) determined in experimental assays with boundary conditions involving 1448 Epitope Organisms (Org), 323 Host Organisms (Host), 15 types of In vivo Process (Proc), 28 Experimental Techniques (Tech), and 505 Adjuvant additives (Adj). Afterwards, we reported the experimental sampling, isolation, and sequencing of 15 complete sequences of Bm86 gene from state of Colima, Mexico. Last, we used the model to predict the epitope immunogenic scores in different experimental conditions for the 26112 peptides obtained from these sequences. 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.