HIERARCHICAL CLASSIFICATION OF GENEONTOLOGY TERMS USING THE GOstruct METHOD

摘要

Protein function prediction is an active area of research in bioinformatics. Yet, thetransfer of annotation on the basis of sequence or structural similarity remains widelyused as an annotation method. Most of today's machine learning approaches reduce theproblem to a collection of binary classification problems: whether a protein performsa particular function, sometimes with a post-processing step to combine the binaryoutputs. We propose a method that directly predicts a full functional annotation of aprotein by modeling the structure of the Gene Ontology hierarchy in the frameworkof kernel methods for structured-output spaces. Our empirical results show improvedperformance over a BLAST nearest-neighbor method, and over algorithms that employa collection of binary classifiers as measured on the Mousefunc benchmark dataset.