Dimitra Alexopoulou, Michael R. Alvers, Bill Andreopoulos, Liliana Barrio-Alvers, Gihan Dawelbait, Heiko Dietze, Andreas Doms, Cecilia Eyre, Jörg Hakenberg, Jan Mönnich, Laura Pickersgill, Conrad Plake, Andreas Reischuck, Loïc Royer, Michael Schroeder, Thomas Wächter, Matthias Zschunke:
Gihan Dawelbait, Heiko Dietze (editors):
GoPubMed: ontology-based literature search for the life sciences.

Complete Text [
.pdf, 2.17MB]
In: (A2-D7)

With the ever increasing size of scientific literature, finding relevant documents and answering questions has become even more of a challenge. Recently, ontologies - hierarchical, controlled vocabularies - have been introduced to annotate genomic data. They can also improve the question answering and the selection of relevant documents in the literature search. Search engines such as use ontological background knowledge to give an overview over large query results and to answer questions. Here we give an overview over GoPubMed. We show how it can answer questions using the GeneOntology and the Medical subject Headings as background knowledge. We also demonstrate that GoPubMed is general by applying it to the problem of associating genes, tissues, and developmental stages, as described in the Edinburgh Mouse Atlas. GoPubMed builds on background knowledge in the form of ontologies, which are given for the previous two applications. We describe a method to automatically generate the vocabulary for ontologies and compare our method to 3 other approaches in the context of a lipid metabolism ontology. The deliverable comprises three sections. GoPubMed is described in Section 1, MousePubMed in Section 2 and ontology generation in Section 3.



	url = {}