What we do

The BioMeXT group specializes in Information Extraction from the biomedical literature and other textual sources. Information extraction consists in automatically extracting structured information from textual documents. We specialize in the extraction of domain-specific entities (such as genes, drugs, diseases), and their semantic relationships (e.g. gene-disease associations). Our tools are often evaluated through participation in community-run evaluation challenges (e.g. BioCreAtIvE). We provide an environment for Assisted Curation (ODIN), which is used in the curation pipeline of the RegulonDB database, in an NIH-funded project.

Highlights 2017

In 2017 we continued our successful acquisition of new projects, which together with our existing projects, will keep us busy for the next couple of years. First, the Commission for Technology and Innovation will be funding a project with a major pharmaceutical company aimed at mining social media for mentions of adverse drug reactions. Second, the Federal Office for Veterinary and Food Safety will support a continuation of our successful collaboration with the Veterinary Faculty of the University of Bern. This project is aimed at mining pathology reports in the veterinary domain for epidemiological studies. The SNF-funded MelanoBase project, which began in 2016, performs large-scale extraction of information from the biomedical literature in order to build a disease-centric knowledge base of information relevant for biological and clinical purposes. The SwissMADE project (Swiss Monitoring of Adverse Drug Reactions), which began in 2017, mines ADRs in EHRs from five Swiss hospitals.

Find out more about the Group’s activities

Main publications 2017

  • Basaldella M et al. Entity Recognition in the Biomedical domain using a hybrid approach. J Biomed Semantics (2017), 8:51. doi:10.1186/s13326-017-0157-6
  • Balderas-Martínez YI et al. Improving biocuration of microRNAs in diseases: a case study in idiopathic pulmonary fibrosis. Database (Oxford) 2017; 2017 (1): bax030. doi:10.1093/database/bax030
  • Rinaldi Fabio et al. Strategies towards digital and semi-automated curation in RegulonDB. Database (Oxford) 2017; 2017 (1): bax012. doi:10.1093/database/bax012


University zurich

Fabio Rinaldi
BioMeXT: Biomedical Information Extraction
University of Zurich
Group Webpage

Domains of activity:

  • Text mining and machine learning
  • Database curation
  • Knowledgebase
  • Machine learning
  • Text mining

Domains of application:

  • Medicine and health
  • Basic research