CDPred Dataset

Dataset

Description

Positive

Negative

Main

Dataset contains 503 experimentally validated celiac disease associated peptides as positive peptides and 503 random negative peptides obtained from SWISSPROT

Alternate

Dataset contains 503 experimentally validated celiac disease associated peptides as positive peptides and 807 not associated with celiac disease but associated with other autoimmune diseases as negative peptides

Independent

Dataset contains 775 Independent dataset (data not used in training or testing) obtained from AllergenOnline database. This dataset contains 1040 unique experimentally validated celiac disease associated peptide sequences. In order to avoid any biasness, we removed 265 common peptides found in Main and Alternate datasets (used for developing CDpred) as well as in AllergenOnline. Finally, An independent dataset of 775 CD-associated peptides were created from AllergnOnline.