What do we do?
In the SIB Text Mining Group, we carry out activities in semantic interoperability and text analytics applied to the health and life sciences. Previously hosted by the Radiology and Medical Informatics Department of the University Hospitals of Geneva, our group moved to the University of Applied Sciences Geneva (HES-SO – HEG Geneva) in 2008. We develop text mining solutions to support both the annotation of curated databases and the work of a wide range of biomedical professionals from drug designers to clinicians. We thus develop specific biomedical decision-support systems (hypothesis generators, search engines, classifiers, etc.).
Over the course of 2017, our team enhanced the nextA5 curation-support platform, which prioritizes the literature for specific curation requirements (with a focus on literature triage for Gene Ontology and Human Diseases annotation). This service has been shown to significantly improve the search effectiveness of curators along three important curation axes: diseases (+231%), molecular functions (+236%), and biological processes (+3,153%). In parallel, user-friendly interfaces powered with a set of JSON web services are currently being implemented into the neXtProt annotation pipeline. The group has been awarded two SPHN grants with the objective of supporting clinicians when interpreting somatic variants. Finally, in 2017, we co-organized the BioCreative Kinome curation track.
Main publications 2017
- Teodoro D et al. Improving average ranking precision in user searches for biomedical research datasets. Database (Oxford). 2017 Jan 1;2017.
- Mottin L et al. Triage by ranking to support the curation of protein interactions. Database (Oxford). 2017 Jan 1;2017.
- Venkatesan A et al. SciLite: a platform for displaying text-mined annotations as a means to link research articles with biological data. Wellcome Open Res. 2017 Jul 10;1:25. doi: 10.12688/wellcomeopenres.10210.2.