Synthetic Protein Sequence Oversampling Method for Classification and Remote Homology Detection in Imbalanced Protein Data


Many classifiers are designed with the assumption of wellbalanced datasets. But in real problems, like protein classification and remote homology detection, when using binary classifiers like support vector machine (SVM) and kernel methods, we are facing imbalanced data in which we have a low number of protein sequences as positive data (minor class… (More)
DOI: 10.1007/978-3-540-71233-6_21


9 Figures and Tables