HSIC-H-FLapSVM: A Kernel Entropy Component Analysis and Multiple Kernel Learning-based Fuzzy Laplacian SVM Model for Identifying Exosomal Proteins

Exosomal proteins participate in many vital biological processes and have great application in clinical diagnosis and prognosis. However, because of the low sequence similarity within exosomal protein datasets. It becomes increasingly urgent to develop computational methods for accurately identifying proteins secreted by exosomes. Therefore, we propose an algorithmic model called HSIC-H-FLapSVM. We extract six feature types from protein sequences. Through experimentation, we determine to use PSSM-DWT, PSSM-AB, and PsePSSM. Subsequently, the features are integrated via multiple kernel learning method based on the Hilbert-Schmidt independence criterion (MKL-HSIC). Following this, fuzzy membership scores for the training samples are derived using kernel entropy component analysis (KECA). Ultimately, HSIC-H-FLapSVM achieves superior performance on testing set, outperforming all competing methods with an ACC of 0.8623 and an MCC of 0.6347. These results demonstrate that HSIC-H-FLapSVM is an effective tool for predicting exosomal proteins. The data.