AtbPpred is a web based two-layer prediction server for anti-tubercular peptides. In the first layer, we applied a two-step feature selection procedure and identified the optimal feature set individually for nine different feature encodings, whose corresponding models were developed using extremely randomized tree (ERT). In the second-layer, the predicted probability of AtbPs from the above nine models were considered as input features to ERT and developed the final predictor. For a given peptide, AtbPpred predicts its class and probability values.
We used the same positve dataset while constructing the two prediction models (AntiTB_MD and AntiTB_RD), but the negative dataset is different. AntitB_MD and AntiTB_RD respectively utilized anti-bacterial and random peptides.