Using a Classifier Fusion Strategy to Identify Anti-angiogenic Peptides.

ABSTRACT: Anti-angiogenic peptides perform distinct physiological functions and potential therapies for angiogenesis-related diseases. Accurate identification of anti-angiogenic peptides may provide significant clues to understand the essential angiogenic homeostasis within tissues and develop antineoplastic therapies. In this study, an ensemble predictor is proposed for anti-angiogenic peptide prediction by fusing an individual classifier with the best sensitivity and another individual one with the best specificity. We investigate predictive capabilities of various feature spaces with respect to the corresponding optimal individual classifiers and ensemble classifiers. The accuracy and Matthew's Correlation Coefficient (MCC) of the ensemble classifier trained by Bi-profile Bayes (BpB) features are

SUBMITTER: Zhang L 

PROVIDER: S-EPMC6138733 | biostudies-literature | 2018 Sep

REPOSITORIES: biostudies-literature