Supervised Selective Kernel Fusion for Membrane Protein Prediction

Abstract

Abstract. Membrane protein prediction is a significant classification problem, requiring the integration of data derived from different sources such as protein sequences, gene expression, protein interactions etc. A generalized probabilistic approach for combining different data sources via supervised selective kernel fusion was proposed in our previous papers. It includes, as particular cases, SVM, Lasso SVM, Elastic Net SVM and others. In this paper we apply a further instantiation of this approach, the Supervised Selective Support Kernel SVM and demonstrate that the proposed approach achieves the top-rank position among the selective kernel fusion variants on benchmark data for membrane protein prediction. The method differs from the previous approaches in that it naturally derives a subset of "support kernels" (analogous to support objects within SVMs), thereby allowing the memory-efficient exclusion of significant numbers of irrelevant kernel matrixes from a decision rule in a manner particularly suited to membrane protein prediction.

High-performance DTW-based signals comparison for the brain electroencephalograms analysis

“…Modern methods of machine learning in the construction of decision rules are based on measures of object comparison and allow us to automatically choose the most suitable ones in the training process, improving the quality of the solution of the problem [10]. The great complexity of training is due to the necessity of multiple comparison of long signals in the calculation of a whole series of matrices of their pairwise dissimilarity (for different electrodes, different types of preprocessing, different values of the parameters of the comparison algorithm), choosing the most suitable of which is not possible a priori.…”