Dissertation/Thesis Abstract

Accurate prediction of protein function using GOstruct
by Sokolov, Artem, Ph.D., Colorado State University, 2011, 90; 3489918
Abstract (Summary)

With the growing number of sequenced genomes, automatic prediction of protein function is one of the central problems in computational biology. Traditional methods employ transfer of functional annotation on the basis of sequence or structural similarity and are unable to effectively deal with today's noisy high-throughput biological data. Most of the approaches based on machine learning, on the other hand, break the problem up into a collection of binary classification problems, effectively asking the question “does this protein perform this particular function?”; such methods often produce a set of predictions that are inconsistent with each other.

In this work, we present GOstruct, a structured-output framework that answers the question “what function does this protein perform?” in the context of hierarchical multilabel classification. We show that GOstruct is able to effectively deal with a large number of disparate data sources from multiple species. Our empirical results demonstrate that the framework achieves state-of-the-art accuracy in two of the recent challenges in automatic function prediction: Mousefunc and CAFA.

Indexing (document details)
Advisor: Ben-Hur, Asa
Commitee: Anderson, Chuck, McConnell, Ross M., Wang, Haonan
School: Colorado State University
Department: Computer Science
School Location: United States -- Colorado
Source: DAI-B 73/04, Dissertation Abstracts International
Subjects: Bioinformatics, Computer science
Keywords: Computational biology, Gene sequencing, Machine learning, Protein function prediction
Publication Number: 3489918
ISBN: 9781267097811