2015 | OriginalPaper | Buchkapitel
Discriminative Prediction of Enhancers with Word Combinations as Features
verfasst von : Pham Viet Hung, Tu Minh Phuong
Erschienen in: Knowledge and Systems Engineering
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Identification of enhancer regions is important for understanding the regulation mechanism of gene expression. Recent studies show that it is possible to predict enhancers using discriminative classifiers with generic sequence features such as k-mers or words. The accuracy of such discriminative prediction largely depends on the ability of the models to capture not only the presence of predictive k-mers (words), but also spatial constraints on clusters of such k-mers. In this paper, we propose a method that first selects the most important word features and then use combinations of such words, which satisfy certain spatial constraints, as additional features. Experiments with real data sets show that the proposed method compares favorably with a state-of-the-art enhancer prediction method in terms of prediction accuracy.