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 between71% 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.

中文翻译：

---

B细胞表位蛋白质组挖掘的PTML模型和墨西哥科利马州Bm86蛋白序列的理论实验研究

在这项工作中，我们开发了蛋白质组数据挖掘的通用扰动理论和机器学习（PTML）方法，以发现可用于疫苗设计的新B细胞表位。该方法在一组实验查询条件（cqj）中预测一个查询肽（q-peptide）的表位活性εq（cqj）。该方法使用q-肽的序列作为输入。该方法还使用有关在相似实验条件（crj）上测定的参考肽（r-肽）的序列和表位活性εr（crj）的信息作为输入。此处提出的模型能够根据IEDB数据库中报告的许多生物的蛋白质组对1,048,190对查询和参考肽序列进行分类。这些对在序列或测定条件上具有变化（扰动）。该模型具有准确性，敏感性，培训和外部验证系列的特异性在71％至80％之间。检索到的信息包含在实验测定中确定的83683个肽序列（Seq）的结构变化，涉及1448个表位生物（Org），323个宿主生物（Host），15种体内过程（Proc），28种实验技术（Technology）的边界条件）和505助剂（Adj）。之后，我们报道了来自墨西哥科利马州的Bm86基因的15个完整序列的实验采样，分离和测序。最后，我们使用该模型预测了从这些序列获得的26112肽在不同实验条件下的表位免疫原性评分。该模型可能会成为针对疫苗设计进行表位选择的有用工具。