SESL

Overview

The SESL Pilot is a feasibility study for the extraction of disease related assertions from the full text scientific literature and the data resources provided by EMBL-EBI focusing on information related to Diabetes Type II. The project is geared to produce a prototype that delivers assertions from the scientific literature to researchers from the participating life science and food companies. Assertions will be extracted from the literature based on existing text mining solutions, will be integrated into a database and delivered through programmatic interfaces and Web interfaces to the sites of the participating partners.

Project Partners

Data Resources

The involved project partners from the publishing companies (Elsevier, Nature Publishing Group, Oxford University Press, Royal Society of Chemistry) contributed in total 638,088 scientific publications (minimum: 16,817; maximum: 548,134). An additional 232,665 documents from Biomed Central were added. All documents were processed, but only 20,168 publications from in total 870,753 publications contained information that was relevant for the project, since only those documents were kept that provided any reference to a gene-disease association for DmT2.

Access

For access to the demonstrator please use: http://Demo.pistoia-sesl.org

Acknowledgements

Special thanks to the Pistoia Alliance (http://www.pistoiaalliance.org/) who has funded the project and to the members of the publishing companies who have contributed to the project: David Hoole (Nature Publishing Group), Richard o’Beirne (Oxford University Press), Jabe Wilson (Elsevier Inc.), and Richard Kidd (Royal Society of Chemistry). Significant input for the development of the prototype and the shaping of the resources was received from Ian Harrow (Pfizer Inc. at that time).