Multiple kernel support vector regression for siRNA efficacy prediction

The cell defense mechanism of RNA interference has applications in gene function analysis and human disease therapy. To effectively silence a target gene, it is desirable to select the initiator siRNA molecules having satisfactory silencing capabilities. Computational prediction for silencing efficacy of siRNAs can assist this screening process before using them in biological experiments. String kernel functions, which operate directly on the string objects representing siRNAs and target mRNAs, have been applied to support vector regression for the prediction and improved accuracy over numerical kernels in multidimensional vector spaces constructed from descriptors of siRNA design rules. To fully utilize information provided by string and numerical kernels, we propose to unify the two in the kernel feature space by devising a multiple kernel regression framework where a linear combination of the kernels are used. We formulate the multiple kernel learning into a quadratically constrained quadratic programming (QCQP) problem, which although yields global optimal solution, is computationally inefficient and requires a commercial solver package. We further propose three heuristics based on the principle of kernel-target alignment and predictive accuracy. Empirical results on real biological data demonstrate that multiple kernel regression can improve accuracy and decrease model complexity by reducing the number of support vectors. In addition, multiple kernel regression gives insights into the kernel combination, which, for siRNA efficacy prediction, evaluates the relative significance of the design rules.