REACTION KERNELS: Structured Output Prediction Approaches for Novel Enzyme Function

摘要

Enzyme function prediction problem is usually solved using annotation transfer methods. These methods are suitable in cases where the function of the new protein is previously characterized and included in the taxonomy such as EC hierarchy. However, given a new function that is not previously described, these approaches arguably do not offer adequate support for the human expert. In this paper, we explore a structured output learning approach, where enzyme function - an enzymatic reaction - is described in fine-grained fashion with so called reaction kernels which allow interpolation and extrapolation in the output (reaction) space. Two structured output models are learned via Kernel Density Estimation and Maximum Margin Regression to predict enzymatic reactions from sequence motifs. We bring forward two choices for constructing reaction kernels and experiment with them in the remote homology case where the functions in the test set have not been seen in the training phase. Our experiments demonstrate the viability of our approach.