Multiple Kernel Learning for Fold Recognition

摘要

Fold recognition is a key problem in computational biology that involves classifying protein sharing structural similarities into classes commonly known as "folds". Recently, researchers have developed several efficient kernel based discriminatory methods for fold classification using sequence information. These methods train one-versus-rest binary classifiers using well optimized kernels from different data sources and techniques. Integrating this vast amount of data in the form of kernel matrices is an interesting and challenging problem. The semidefinite positive property of the various kernel matrices makes it attractive to cast the task of learning an optimal weighting of several kernel matrices as a semi-definite programming optimization problem. We experiment with a previously introduced quadratically constrained quadratic optimization problem for kernel integration using 1-norm and 2-norm support vector machines. We integrate state-of-the-art profile-based direct kernels to learn an optimal kernel matrix K*. Our experimental results show a small significant improvement in terms of the classification accuracy across the different fold classes. Our analysis illustrates the strength of two dominating kernels across different fold classes, which suggests the redundant nature of the kernel matrices being combined.