id author title date pages extension mime words sentences flesch summary cache txt work_ho2ac3l4ivbnbkr2yq3m3ik4re Binti Solihah Enhancement of conformational B-cell epitope prediction using CluSMOTE 2020 17 .pdf application/pdf 7766 918 63 This study proposes CluSMOTE, which is a combination of a clusterbased undersampling method and Synthetic Minority Oversampling Technique. than other methods in the general protein antigen, though comparable with SEPPA 3 Keywords Cluster-based undersampling, SMOTE, Class imbalance, Hybrid sampling, Hierarchical DBSCAN, Vaccine design methods, including the structure and sequence-based approaches. discarded the negative class data that overlap the positive in a specific cluster based on the In this research, the cluster-based undersampling method is combined with SMOTE to Conformational B-cell epitope prediction method The number of clusters is less than the positive class data. A dataset used for conformational epitope prediction contains the class imbalance problem. An epitope is a small part of the exposed antigen that creates class imbalance problems in the prediction of learning-based conformational epitopes. Prediction of residues in discontinuous B-cell epitopes using protein 3D structures. A new performance measure for class imbalance learning. ./cache/work_ho2ac3l4ivbnbkr2yq3m3ik4re.pdf ./txt/work_ho2ac3l4ivbnbkr2yq3m3ik4re.txt