Briefs

NewsFactor Network (01/27/04); Martin, Mike

The job of sifting through journals and scientific literature to unearth information relevant to studies could become less burdensome--and expensive--for researchers with the help of Iridescent, a software program developed by bioinformatics scientists at the University of Texas Southwest Medical Center.

"This work is about teaching computers to 'read' the literature and make relevant associations so they can be summarized and scored for their potential relevance," explains Iridescent co-developer Dr. Jonathan Wren at the University of Oklahoma, who adds that humans would have to read tens of thousands of documents to accomplish the same task. UT professor Dr. Harold Garner, who also contributed to Iridescent's development, says the program mimics the scientific thought process. Iridescent builds a network of related objects by identifying shared statistical relationships between object sets in the National Library of Medicine's Medline bibliographic database, an exponentially expanding archive.

"Having assimilated all of Medline, Iridescent can compile diverse facts to present a list of 'hypotheses' to the user for finding hidden knowledge in the data," Garner comments. The UT professor says Etexx Biopharmaceuticals employs Iridescent to devise new ways to apply existing FDA-approved drugs to cardiac diseases that otherwise have no therapeutics. Garner adds that the program dramatically lowers investments in time and money for high-throughput screening, toxicology testing, and manufacturing qualifications.

Here is the rest of the story.