Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

BioCreative V a new challenge in text mining for biocuration

 
: Arighi, Cecilia N.; Chatraryamontri, Andrew; Kevin, Cohen B.; Comeau, Donald; Fluck, Juliane; Dogan, Rezarta Islamaj; Hirschman, Lynette; Kim, Sun; Krallinger, Martin; Leitner, Florian; Lu, Zhiyong; Oyarzabal, Julen; Rabal, Obdulia; Rinaldi, Fabio; Tudor, Catalina O.; Valencia, Alfonso; Wiegers, Thomas; Wilbur, John; Wu, Cathy H.

International Society for Biocuration -ISB-:
Biocuration 2015, 8th International Biocuration Conference. Abstract Booklet : From Big Data to Big Discofery, April 23-26, 2015, Beijing, China
Beijing, 2015
Poster Abstract 94
International Biocuration Conference (IBC) <8, 2015, Beijing>
Englisch
Abstract
Fraunhofer SCAI ()

Abstract
BioCreative: Critical Assessment of Information Extraction in Biology is a community-wide effort for evaluating text mining and information extraction systems applied to the biological domain. For the past ten years BioCreative challenges have spanned a number of tasks particularly important to biocuration. BioCreative V is underway and consists of five tracks: 1-Collaborative Biocurator Assistant Task for development of BioC-compatible modules which complement each other for an integrated system that assists BioGRID curators. This will be a non-competitive, cooperative task in which participants work together to build a better system; 2-CHEMDNER patents to address the automatic extraction of chemical and biological data from medicinal chemistry patents. Currently, the identification and integration of all information contained in these patents is an extremely hard task not only for database curators, but also for life sciences researches and biomedical text mining experts; 3-Chemical-disease relation task for automatic detection of mechanistic and biomarker chemical-disease relations from the biomedical literature, in support of biocuration, new drug discovery and drug safety surveillance; 4-Extraction of causal network information in Biological Expression Language for text mining solutions to develop and test novel approaches for relation extraction in the context of pathway networks. The goal is to assess the utility of such tools for the automated annotation and network expansion, and their suitability as supporting tools for assisted curation; 5-Interactive Curation for the demonstration and evaluation of web-based systems addressing user-defined tasks, evaluated by curators on performance and usability. BioCreative tracks are aimed to advance text-mining research and provide practical benefits to biocuration, therefore many tracks rely on curator’s participation. We will describe past and current efforts. Information is available at www.biocreative.org.

: http://publica.fraunhofer.de/dokumente/N-375298.html