EVEX is a text mining resource built on top of PubMed abstracts and PubMed Central full text articles. It contains over 40 million bio-molecular events among more than 76 million automatically extracted gene/protein name mentions. The text mining data further has been enriched with gene identifiers and gene families from Ensembl and HomoloGene, providing homology-based event generalizations. EVEX presents both direct and indirect associations between genes and proteins, enabling explorative browsing of relevant literature.
The EVEX resource is made possible thanks to collaborative efforts within the BioNLP community, specifically by the BioNLP group at the University of Turku (Finland), the Tsujii lab at Tokyo University (Japan), the Bioinformatics group at Ghent University (Belgium), the NaCTeM text mining center at the University of Manchester (UK) and the Intelligent Knowledge Management Laboratory at the National Cheng Kung University of Tainan (Taiwan).
EVEX is primarily built upon the NER package BANNER, the TEES event extraction system and the NEN system GenNorm. Further, events are visualised on the website using the stav visualiser.
Support and funding:
The development of EVEX is possible thanks to funding granted by University of Turku, Turku Centre for Computer Science (TUCS), Academy of Finland, the Belgian Research Foundation Flanders (FWO-Vlaanderen), the Intramural Research Program of NIH, NLM and the UK Biotechnology and Biological Sciences Research Council (BBSRC). Computational resources are provided by CSC - IT Center for Science.
Sofie Van Landeghem