Jennifer Zaino
SemanticWeb.com Contributor

The winner and runner-up of the Elsevier Grand Challenge: Knowledge Enhancement in the Life Sciences – a contest created to improve the way scientific information is communicated and used – were announced Tuesday.

Not surprisingly, semantic technologies were represented among the group of finalists, given the need to improve collaboration, research and development in the fast-moving and prolific life sciences research sector.

Taking second place in the contest was the team from DERI (Digital Enterprise Research Institute) at the National University of Ireland Galway, with a project titled CORAAL – Dive into Publications, Bathe in the Knowledge.

Finalists gave presentations at a scientific session at the Experimental Biology event in New Orleans and participated in an online webinar with judges and the general public.

During the webinar DERI team member Vit Novacek said CORAAL essentially is “about developing a new generation, a more intelligent search engine for life sciences publication data.”

It strives to enable more efficient search for and retrieval of life science publications based on the knowledge and meta-data that the team says is purely and automatically extracted from their text content. The knowledge implicitly contained in publication texts heretofore has been ignored in searches in favor of raw publication data and shallow meta-data such as authors, keywords, and citations, the team members posit.

The addition of the faceted browsing aspect means users get all the results displayed in an integral manner but filtered by facet, Novacek said-for example, returns can present information related not just to a particular type of leukemia but a particular gene involved in that type of leukemia.

“You can very quickly navigate to the relevant portion of the results that are of interest to you,” Novacek said.

Making a reality of the Semantic Web

Future plans could include combining artificial intelligence that extracts inferred knowledge with the wisdom of the crowds, “connecting the power of human intelligence with the possibility of processing huge amounts of data in CORAAL,” he said.

Contest chairman Eduard Hovy, director of the Natural Language Group, Information Sciences Institute, University of Southern California, praised the project for its high scores on innovation, and its potential to be a boon for search and knowledge discovery if and when it becomes operational. Hovy noted that many parts of the project had been done in isolation elsewhere, “but no one has taken it and put it in a framework that is extensible and articulates how it all fits together and is as nice and open as this one. They were daring in doing this and [they are] making a reality of some of the ideas of the semantic web.”

There was a time when experts could easily keep up with all the research in the Life Sciences sector, Elsevier notes, but with 4,100 journals in the space that’s nearly impossible today. The challenge was instituted in the hope of getting tools that can help scientists enhance their knowledge and get more out of the huge body of literature that is available today.

First place went to Reflect: Automated Annotation of Scientific Terms, which was developed and maintained at the European Molecular Biology Laboratory, Heidelberg, Germany. The tool enables molecular biologists and botanists to very quickly get a version of a research page returned that highlights the proteins and chemicals mentioned on it and shows via a pop-up the most important information about them, including links to related databases.

The dictionary behind it was created by merging many major gene and protein dictionaries in the field, said team member Sean I. O’Donoghue, and the user community has the power to correct the dictionary as needed, as “no automated tag service is 100 percent accurate.”

Hovy cited the project as being the most mature of all, “beautifully conceived and nicely executed. It runs fast, there are thousands of downloads already and there is an exciting vision for extending its capabilities and bringing in the user community.”

Semantic Tech & Business Conference Returns to San Francisco

Semantic Tech & Business Conference returns to San Francisco in June! Join us from June 3-7 for complete coverage of Big Data, Linked Data, Extreme Information Management, and Semantic Web. From breakthrough approaches to solving business problems to the big data implications of fast–evolving technologies, SemTechBiz provides you with an unparalleled interactive experience and delivers tangible business value. We're offering a special early rate when you register by February 17. Sign up now!