What is a positive epitope fragment? I found one paper on the subject:


The group tries to predict possible epitope sequences for the generation of antibodies. This includes also non-linear epitopes where not all amino acids of the epitope are line up behind each other, but come in close contact due to a 3D-structure. To train their algorithm, they use data, where the boundaries of the epitopes and the non-epitopes are known and clearly mapped.

The "Dataset and Preparation" section in this paper contains the following:

In this article, we used several different datasets to train and benchmark COBEpro. These datasets were derived from several different previously published sources: BciPep (Saha et al., 2005), Pellequer (Pellequer et al., 1993) and HIV (Korber et al., 2003). The BciPep datasets consist of epitope/non-epitope sequence fragments. The Pellequer and HIV datasets consist of whole antigen proteins annotated with precise epitope boundaries.

The "positive epitope fragments" are known and verified ("positive") epitopes from these datasets in the training database. The fragment refers to restriction of length to 20 amino acids which they choose to apply. Shorter epitopes got amino acids added so they get 20 aa long, longer got truncated.

  • $\begingroup$ so basically what this means is that epitope fragments which has been verified as epitopes are called positive epitopes?? $\endgroup$ – girl101 Feb 2 '15 at 6:18
  • $\begingroup$ For this paper: Yes. I haven't seen this term anywhere else, though. $\endgroup$ – Chris Feb 3 '15 at 7:22

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.