Overview of STALLION methodology
|
In this study, we proposed an Stacking-based ensemble learning framework called STALLION for identifying species-specific KAce sites. To extract crucial patterns around Kace sites, we employed eleven different encodings representing three different characteristics. Subsequently, a systematic and rigorous feature selection approach was employed to identify the optimal feature independently set for five tree-based ensemble algorithms and built their respective baseline model for each species. Finally, the predicted values from baseline models were utilised and trained with an appropriate classifier using the stacking strategy to develop STALLION. Comparative benchmarking experiments showed that STALLION significantly outperformed existing predictors on independent tests.
|