BELIEF platform and biological expression language

BELIEF platform and biological expression language

The network models are encoded in Biological Expression Language (BEL) which represents scientific knowledge in human readable and computable format as semantic triples (subject, a predicate, and an object).

Here is a practical example:


Since neither purely manual nor automated literature curation yields satisfactory results, in terms of curation time and quality, we have developed the BEL Information Extraction workFlow (BELIEF)1-5. BELIEF is a semi-automated workflow for BEL network creation. It embeds an information extraction workflow with state-of-the-art named entity recognition and relation extraction methods. BELIEF is now routinely used to build biological network models.

The figure below describes the causal biological network construction pipeline. The workflow is divided in 3 steps:

  1. Literature review. Set of specific boundary criteria for the biological process of interest and selection of scientific articles
  2. Literature curation. Submission of the scientific articles to the text mining pipeline in the BELIEF platform. It automatically identifies causal relationships& proposes BEL statements. BELIEF platform also supports the user to check the validity of BEL statements and annotations.
  3. Network model review. The extracted causal relationships are then compiled into a causal network model. The nodes in the network model are connected by causally related edges.

 You can leverage the BELIEF platform for extending the networks and creating evidences.


Instructions on how to Use BELIEF to curate Network Models

If you are a new user of BELIEF, please have a look on this step-by-step tutorial.



  1. 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.
  2. 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.
  3. 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.
  4. Szostak J, Ansari S, Madan S, Fluck J, Talikka M, Iskandar A, et al. (2015) ”Construction of biological networks from unstructured information based on a semi-automated curation workflow”. Database : the journal of biological databases and curation.
  5. 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)

Share this page