Caoili Salvador Eugenio C
Department of Biochemistry and Molecular Biology, College of Medicine, University of the Philippines Manila, Room 101, Medical Annex Building, 547 Pedro Gil Street, Ermita, 1000 Manila, Philippines.
Biomed Res Int. 2014;2014:867905. doi: 10.1155/2014/867905. Epub 2014 May 11.
B-cell epitope prediction can enable novel pharmaceutical product development. However, a mechanistically framed consensus has yet to emerge on benchmarking such prediction, thus presenting an opportunity to establish standards of practice that circumvent epistemic inconsistencies of casting the epitope prediction task as a binary-classification problem. As an alternative to conventional dichotomous qualitative benchmark data, quantitative dose-response data on antibody-mediated biological effects are more meaningful from an information-theoretic perspective in the sense that such effects may be expressed as probabilities (e.g., of functional inhibition by antibody) for which the Shannon information entropy (SIE) can be evaluated as a measure of informativeness. Accordingly, half-maximal biological effects (e.g., at median inhibitory concentrations of antibody) correspond to maximally informative data while undetectable and maximal biological effects correspond to minimally informative data. This applies to benchmarking B-cell epitope prediction for the design of peptide-based immunogens that elicit antipeptide antibodies with functionally relevant cross-reactivity. Presently, the Immune Epitope Database (IEDB) contains relatively few quantitative dose-response data on such cross-reactivity. Only a small fraction of these IEDB data is maximally informative, and many more of them are minimally informative (i.e., with zero SIE). Nevertheless, the numerous qualitative data in IEDB suggest how to overcome the paucity of informative benchmark data.
B细胞表位预测有助于新型药物产品的开发。然而，对于此类预测的基准测试，尚未形成一个基于机制的共识，因此有机会建立实践标准，以规避将表位预测任务视为二元分类问题时的认知不一致。作为传统二分法定性基准数据的替代，抗体介导的生物学效应的定量剂量反应数据从信息论的角度来看更有意义，因为此类效应可以表示为概率（例如，抗体功能抑制的概率），香农信息熵（SIE）可作为信息量的一种度量进行评估。因此，半数最大生物学效应（例如，在抗体的半数抑制浓度时）对应于信息量最大的数据，而未检测到的和最大生物学效应对应于信息量最小的数据。这适用于基于肽的免疫原设计的B细胞表位预测基准测试，此类免疫原可引发具有功能相关交叉反应性的抗肽抗体。目前，免疫表位数据库（IEDB）中关于此类交叉反应性的定量剂量反应数据相对较少。这些IEDB数据中只有一小部分信息量最大，更多的数据信息量最小（即SIE为零）。尽管如此，IEDB中的大量定性数据表明了如何克服信息量丰富的基准数据的匮乏。
