Bastion6 is a two-layer SVM-based ensemble model with fine-grain optimized parameters, to identify potential T6SEs. We extracted a wide range of features (divided into 3 groups) from T6SE protein sequences and thus generated a set of single feature based models. For each group of features, the prediction scores of single feature based models are averaged to obtain a one-layer ensemble model. Lastly, prediction scores of these one-layer ensemble models (corresponding to different feature groups) are averaged to form an integrative two-layer ensemble model for the final prediction.

An example of amino acid sequences in the FASTA format is presented by clicking the following "Example" button.

Visitor Map