Publications

Nature Genetics published the following article on datamining:

"A literature network of human genes for high-throughput
gene-expression analysis", Tor-Kristian Jenssen, Astrid L�greid, Jan
Komorowski & Eivind Hovig, NTNU (Norwegian University of Science and
Technology), Trondheim, and Radium Hospitalet, Oslo, Norway.

Abstract. We have carried out automated extraction of explicit and
implicit biomedical knowledge from publicly available gene and text
databases to create a gene-to-gene co-citation network for 13,712
named human genes by automated analysis of titles and abstracts in
over 10 million MEDLINE records.  The associations between genes have
been annotated by linking genes to terms from the medical subject
headings (MeSH) index and terms from the gene ontology (GO).  The
extracted database and accompanying web-tools for gene-expression
analysis have collectively been named "PubGene".  We validated the
extracted networks by three large-scale experiments showing that
co-occurrence reflects biologically meaningful relationships, thus
providing an approach to extract and structure known biology.  We
validated the applicability of the tools by analyzing two publicly
available microarray data sets.

Reference: Nature Genetics, Vol 28, pp. 21--28, 2001.

The publicly available tool: http://www.PubGene.org/

GPS: Same work was also profiled in New Scientist Online (04/30/01),
which reports that the relationships predicted by PubGene are seven
times more likely to be correct than
those predicted by random selection--in a few cases, correctly
predicted relationships were not previously known to scientists. "It
is an exploratory tool," says University of California at San Diego
geneticist Daniel Masys. "They don't promise to give all possible
insights, but it is an aid to trying to digest and condense these huge
amounts of information."

See ACM Technews, May 7, 2001