Reaction kernels: structured output prediction approaches for novel enzyme function
Katja Astikainen, Esa Pitkänen, Juho Rousu, Liisa Holm and Sandor Szedmak
In: Bioinformatics 2010, 19-23 Jan 2010, Valencia, Spain.
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.
|EPrint Type:||Conference or Workshop Item (Paper)|
|Additional Information:||This paper received the Best Student Paper Award|
|Project Keyword:||Project Keyword UNSPECIFIED|
|Subjects:||Learning/Statistics & Optimisation|
|Deposited By:||Juho Rousu|
|Deposited On:||08 March 2010|