Using Gene Ontology to Generate Biological Contexts for Augmenting Statistical Patterns of Molecular Data

This paper describes the research to reduce high false positive discovery rates when discovering possible molecular diagnostic patterns. This effort combines information from the gene ontology with multiple sets of discriminating patterns discovered in a publicly available gene expression dataset on breast cancer. Using a second validation dataset, we identify candidate patterns with good and poor validation performance, and then show that certain biological contexts appear to provide some ability to discriminate between them.