BELIEF (Biological Expression Language Information Extraction WorkFlow) is a semi-automated workflow for BEL network creation. It embeds an information extraction workflow with state-of-the-art named entity recognition (NER) and relation extraction (RE) methods. This dashboard provides an interface to the BELIEF system.
If you are a new user of BELIEF, please have a look on the provided step-by-step tutorial: Quick Tours -> How to use BELIEF.
A short introduction to BEL can be find on the page Quick Tours -> Introduction to BEL.
BELIEF provides the user with pre-annotations to speed up the extraction of causal relationships from scientific texts.
Causal relationships can be molecular between genes, proteins (partly in a modified form or in a complex) and chemicals. On the other hand causal relationships can link proteins or chemicals to biological processes or diseases. BEL networks can cover all these relationships and use defined namespaces to describe the different entities. Additional annotations such as anatomy, cell or disease describe the context of the causal relationship.
BELIEF provides the user with entity annotations containing the corresponding BEL namespace. BELIEF suggests BEL statements (directly converted from automatic extraction procedures). The user can edit the statements, add annotations and select the statements to be exported.
BELIEF supports the user to check the validity of BEL statements and annotations.
BELIEF gives you warnings and errors about BEL syntax, semantic errors and unknown name spaces/annotations.
BELIEF embeds the BEL statements directly in valid BEL documents. These documents can be added into a BEL knowledgebase to be used for network visualisation, reasoning and large scale data analysis.
Regarding questions and other issues you can contact us at bio-support@scai.fraunhofer.de.
Madan, S., Hodapp, S., Senger, P., Ansari, S., Szostak, J., Hoeng, J., Peitsch, M., & Fluck, J. (2016). The BEL Information Extraction Workflow (BELIEF): Evaluation in the BioCreative V BEL and IAT track. The Journal of Biological Databases and Curation (DATABASE)
Madan, S., Hodapp, S., & Fluck, J.; (2015). BELIEF Dashboard - a Web-based Curation Interface to Support Generation of BEL Networks. In Proceedings of the Fifth BioCreative Challenge Evaluation Workshop (pp. 409–417). Sevilla, Spain.
Ansari, S.; Szostak, J.; Madan, S.; Fluck, J.; Talikka, M.; Iskandar, A.; De Leon, H.; Hofmann-Apitius, M.; Peitsch, M.; Hoeng, J.; (2015) A semi-automated curation workflow to construct biological networks from unstructured information. The Journal of Biological Databases and Curation (DATABASE)
Fluck, J.; Madan, S.; Ansari, S.; Szostak J.; Hoeng, J.; Zimmermann, M.; Hofmann-Apitius, M.; Peitsch, M.; (2014) BELIEF - A semiautomatic workflow for BEL network creation. 6th International Symposium on Semantic Mining in Biomedicine (SMBM 2014), Aveiro, Portugal.
Fluck, J.; Klenner, A.; Madan, S.; Ansari, S.; Bobic, T.; Hoeng, J.; Hofmann-Apitius, M.; Peitsch, M.; (2013) BEL networks derived from qualitative translations of BioNLP Shared Task annotations. The Association for Computational Linguistics (ACL) Sofia 2013.