[BioNLP] BioCreative 2015: BEL track (causal networks), call for participation

Fabio Rinaldi fabio at ontogene.org
Fri Mar 27 03:29:11 PDT 2015

--- Call for Participation ---

BioCreative 2015: Extraction of causal network information in
Biological Expression Language (BEL)


--- Short synopsis ---

BEL (Biological Expression Language) is a formal language used to
represent biological knowledge, and in particular causal networks.
The goal of the BEL task at BioCreative 2015 is to test how far
biological network fragments represented in BEL language can be
constructed automatically from sentences selected from the scientific
literature. In particular we will verify the following:

- Given textual evidence for a BEL statement, generate the
  corresponding BEL statement.

- Given a BEL statement, provide additional evidence sentences from
  the biomedical literature.

The challenge is described in detail at the following URL, where you can
also find sample material and the training set (11000 BEL statements
with the sentences from which they are derived):


--- Important dates ---

May 27, 2015: Test data release
May 30, 2015: Submission of results deadline
June 30, 2015: Delivery of evaluation results
July 10, 2015: Paper submission
August 15, 2015: Camera-ready
September 9-11, 2015: Workshop (Sevilla, Spain)

--- Evaluation ---

Notice that the BEL statements might appear very complex at first
sight, and therefore difficult to construct automatically. However, in
the evaluation, we will introduce numerous simplifications, in order
to give credit to partially correct BEL statements. For details of the
evaluation procedure please see:


The task of constructing BEL statements, thanks to the simplifications
introduced in the evaluation procedure, can be see as a combination of
standard tasks performed in several previous biomedical text mining
challenges: entity recognition and disambiguation, relation
extraction, event extraction. As an illustration of the structural
similarity of BEL statements with BioNLP-style events, we have
converted the training data into BioC format, and provided a graphical
representation of the syntactic structure of the statements:


Since each of the levels of analysis (entities, relations, events) is
going to be evaluated separately, we hope that the challenge will
prove interesting for several text mining groups.

Feel free to contact us for additional information and suggestions,
either directly (fabio at ontogene.org) or by posting to our mailing list


To register a team go to:


--- Background ---

Biological networks with a structured syntax are a powerful way of
representing biological information and knowledge. Well-known examples
of methods to formally represent biological networks are the Systems
Biology Markup Language (SBML, Hucka et al., 2001) and the Biological
Expression Language (BEL, www.openbel.org). Both approaches are not
only designed for representation of biological events, but they are
also intended to support downstream computational applications.  In
particular, BEL is gaining ground as the de-facto standard for systems
biology applications, because it combines the power of a formalized
representation language with a relatively simple syntax that allows
easy interpretation of BEL statement by a trained domain expert.

As part of an on-going product assessment program, the sbvIMPROVER
initiative (https://sbvimprover.com/) is supporting the manual
curation and expansion of biological networks related to human lung
disease. A large-scale crowdsourcing verification approach for the
validation of these biological networks, called Network Verification
Challenge (NVC, https://sbvimprover.com/challenge-3/challenge),
was organized by them.

This initiative aims to provide a measure of quality control of
systems-based research, supporting the verification of methods and
concepts in this domain. The NVC supports community-based verification
and extension of biological relationships based on peer-reviewed
literature evidence. At present, 50 biological networks have been
curated, resulting in a total of more than 180'000 relationships, all
available in BEL format, with supporting evidence in form of a
sentence or section and a PubMed identifier.

Using the data provided and validated through the sbvIMPROVER NVC,
we invite members of the academic text mining community and providers
of text mining solutions to develop and test novel approaches aiming at
evaluating the usage of text mining for relation extraction and
automated construction of network elements. The goal is to assess the
utility of such tools either for the automated annotation and network
expansion, or their suitability as supporting tools for assisted curation.

--- Organizing Committee ---

Fabio Rinaldi (OntoGene, Switzerland)
Juliane Fluck (Fraunhofer SCAI, Germany)
Sam Ansari (sbvIMPROVER, Switzerland)
Dr. Julia Hoeng (sbvIMPROVER, Switzerland)
Prof. Dr. Martin Hofmann-Apitius (OpenBEL Consortium, Germany)
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.bionlp.org/pipermail/bionlp_bionlp.org/attachments/20150327/719bddb3/attachment.html>

More information about the BioNLP mailing list