[Elsnet-list] Presenting BeCAS
tiago.nunes at ua.pt
Wed Jun 5 12:44:49 CEST 2013
Dear ELSNET-List members,
We are pleased to announce BeCAS, a web application, API and widget
for biomedical concept identification. BeCAS identifies and
annotates species, anatomical concepts, microRNAs, enzymes, genes,
proteins, chemicals, drugs, diseases, metabolic pathways,
cellular components, biological processes and molecular functions.
BeCAS provides annotations for isolated, nested and intersected
entities. It identifies concepts from multiple semantic groups,
providing preferred names and enriching them with references to
public knowledge resources. Users can choose the types of entities
for identification and highlighting in real-time.
To facilitate annotation of PubMed abstracts, BeCAS automatically
fetches publications from NCBI servers and renders them with
identified concepts highlighted.
BeCAS was validated against CRAFT, AnEM and the NCBI Diseases corpora,
achieving f-measure results for overlap matching of 76% for genes
and proteins, 95% for species, 65% for chemicals, 83% for cellular
components, 92% for cells, 63% for molecular functions and biological
processes, 83% for anatomical entities, and 85% for diseases.
In addition to the web frontend, BeCAS is also accessible
through an HTTP API, producing results in multiple formats, such as
JSON, XML, A1 (GENIA/Brat) and CoNLL. The API can also be easily used
through a Python client and CLI tool.
Concept identification and highlighting capabilities can be embedded
You can read more about BeCAS in the following manuscript:
* Web Application: http://bioinformatics.ua.pt/becas/
* API Documentation: http://bioinformatics.ua.pt/becas/api
* Widget Documentation: http://bioinformatics.ua.pt/becas/widget
* Python client and CLI tool:
We welcome all feedback and comments (contact at
http://bioinformatics.ua.pt/becas/contact) on any aspect of the system.
Thank you for your time.
IEETA, University of Aveiro
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Elsnet-list