Medstract: creating large-scale information servers for biomedical libraries
BioMed '02 Proceedings of the ACL-02 workshop on Natural language processing in the biomedical domain - Volume 3
A GO-Based method for assessing the biological plausibility of regulatory hypotheses
ICCS'06 Proceedings of the 6th international conference on Computational Science - Volume Part II
| Hi-index | 0.00 |
Microarray gene expression data provide a unique information resource for learning biological networks using "reverse engineering" methods. However, there are a variety of cases in which we know which genes are involved in a given pathology of interest, but we do not have enough experimental evidence to support the use of fully-supervised/reverse-engineering learning methods. Moreover, corroboration of the reverse engineered networks through independent means such as evidence from the biomedical literature is always desirable. In this paper, we explore a novel semi-supervised approach in which biological networks are learned from a reference list of genes and a partial set of links for these genes extracted automatically from PubMed abstracts, using a knowledge-driven bootstrapping algorithm. We show how new relevant links between genes can be iteratively derived using a gene similarity measure based on the Gene Ontology that is optimized on the input network at each iteration. An initial evaluation indicates the viability of the approach as an alternate or complementary technique to fully supervised methods.