{"id":20434,"date":"2006-04-28T05:55:00","date_gmt":"2006-04-28T05:55:00","guid":{"rendered":"http:\/\/weblogs.madrimasd.org\/\/bioinformatica\/archive\/2006\/04\/28\/20434.aspx"},"modified":"2006-04-28T05:55:00","modified_gmt":"2006-04-28T05:55:00","slug":"segunda-edicion-de-biocreative-la-competicion-de-text-mining","status":"publish","type":"post","link":"https:\/\/www.madrimasd.org\/blogs\/bioinformatica\/2006\/04\/28\/20434","title":{"rendered":"Segunda edici\u00f3n de BioCreAtIvE, la competici\u00f3n de text-mining"},"content":{"rendered":"

Una de las formas de comprobar las mejoras que se han producido en cualquier \u00e1rea de conocimiento es la celebraci\u00f3n de una competici\u00f3n en la que se comparen de forma objetiva las distintas alternativas disponibles. En el caso de la bioinform\u00e1tica hay algunas competiciones con mucha solera, como es el caso de CASP<\/a> (Critical Assessment of Techniques for Protein Structure Prediction<\/i>), que ya se encuentra en su s\u00e9ptima edici\u00f3n, CAPRI<\/a> (a Critical Assessment of PRedicted Interactions<\/i>) o GASP<\/a> (Genome Annotation aSsessment Project<\/i>). Incluso hay un art\u00edculo del a\u00f1o pasado que trata este tema, y que se llama \u00abPrices for Ingenuity<\/a>\u00ab<\/i>, disponible online<\/i> en PLoS Biology<\/a>:<\/p>\n

http:\/\/biology.plosjournals.org\/perlserv\/?request=get-document&doi=10.1371\/journal.pbio.0030288<\/a><\/p>\n

Pues bien, una de esas competiciones es BioCreAtIvE<\/a>, que adem\u00e1s est\u00e1 auspiciada en parte por el grupo de investigaci\u00f3n en el que trabajo. En este caso, la competici\u00f3n est\u00e1 enfocada en la evaluaci\u00f3n de las t\u00e9cnicas de miner\u00eda de textos y sistemas de extracci\u00f3n de informaci\u00f3n aplicados al dominio de la biolog\u00eda. Surgi\u00f3 de las necesidades de bi\u00f3logos, bioinform\u00e1ticos y curators<\/i><\/a> (cuidadores) de datos biol\u00f3gicos de acceder a informaci\u00f3n destacada e interesante disponible en la literatura cient\u00edfica, y que dicha informaci\u00f3n est\u00e9 enlazada a las fuentes de datos disponibles (princalmente, bases de datos y ontolog\u00edas).<\/p>\n

\u00a1A\u00fan estais a tiempo de participar! Os incluyo a continuaci\u00f3n el correo completo que anuncia la competici\u00f3n.
CALL FOR PARTICIPATION:
Second BioCreAtIvE Challenge Evaluation, 2006-2007 <\/p>\n

We are pleased to announce the second BioCreAtIvE
(Critical Assessment of Information Extraction
systems in Biology) challenge evaluation. <\/p>\n

The BioCreAtIvE website can be found at:
http:\/\/biocreative.sourceforge.net<\/a> <\/p>\n

If you are interested, please join our mailing list:
http:\/\/lists.sourceforge.net\/mailman\/listinfo\/biocreative-participant<\/a> <\/p>\n

BACKGROUND: <\/p>\n

BioCreAtIvE is a community-wide effort for evaluating text
mining and information extraction systems applied to the
biological domain. BioCreAtIvE arose out the needs of working
biologists, biological curators and bioinformaticians to access the
wealth of information in the literature, and to link this information to
biological databases and ontologies. BioCreAtIvE focuses on the
comparison of methods and community assessment of scientific
progress, rather than on the purely competitive aspects. The first
BioCreAtIvE challenge evaluation in 2003-2004 attracted broad
interest within the bioinformatics and biomedical text mining community,
with participation from 27 groups from 10 countries. BioCreAtIvE is
organized through collaborations between text mining groups,
biological database curators and bioinformatics researchers. <\/p>\n

BioCreAtIvE II Information <\/p>\n

BioCreAtIve II will be held during October of 2006, with the workshop
to be held in Spring 2007. It will consist of three tracks. The first
will focus on finding the mentions of genes and proteins in sentences
drawn from MEDLINE abstracts and is the same as Task 1A (Tanabe,
Xie et al. 2005) from BioCreAtIvE I. The second track will involve
producing a list of the EntrezGene identifiers for all the human
genes\/proteins mentioned in a collection of MEDLINE abstracts and is
similar to BioCreAtIvE I Task 1B (Hirschman, Colosimo et al. 2005). The
third track of BioCreAtIvE II is new and will involve identifying protein-
protein interactions from full text papers, including extraction of
excerpts from those papers that describe experimentally derived
interactions, for curation into one of two interaction databases:
IntAct (Hermjakob, Montecchi-Palazzi et al. 2004) and MINT
(Zanzoni, Montecchi-Palazzi et al. 2002). <\/p>\n

The approximate time line for BioCreAtIvE is as follows:
Jun 2006 Release of training data
Oct 2006 Release and evaluation of test data
Dec 2006 Results returned to participants
Feb 2007 Workshop papers submitted
Mar 2007 Workshop
Jun 2007 Journal articles submitted <\/p>\n

We encourage you to visit the web site and sign up
for further information. <\/p>\n

Thank you, <\/p>\n

Alfonso Valencia
Martin Krallinger
* CNIO – Spanish National Center for Oncology Research <\/p>\n

Lynette Hirschman
Alex Morgan
* The MITRE Corporation <\/p>\n

W. John Wilbur
Lorrie Tanabe
Larry Smith
* NCBI, NLM, NIH <\/p>\n

REFERENCES <\/p>\n

Hermjakob, H., L. Montecchi-Palazzi, et al. (2004). \u00abIntAct: an open
source molecular interaction database.\u00bb Nucleic Acids Res
32(Database issue): D452-5. <\/p>\n

Hirschman, L., M. Colosimo, et al. (2005). \u00abOverview of BioCreAtIvE
task 1B: normalized gene lists.\u00bb BMC Bioinformatics 6 Suppl 1: S11. <\/p>\n

Tanabe, L., N. Xie, et al. (2005). \u00abGENETAG: a tagged corpus for
gene\/protein named entity recognition.\u00bb BMC Bioinformatics 6
Suppl 1: S3. <\/p>\n

Zanzoni, A., L. Montecchi-Palazzi, et al. (2002). \u00abMINT: a Molecular
INTeraction database.\u00bb FEBS Lett 513(1): 135-40.<\/font> <\/p>\n","protected":false},"excerpt":{"rendered":"

Una de las formas de comprobar las mejoras que se han producido en cualquier \u00e1rea de conocimiento es la celebraci\u00f3n de una competici\u00f3n en la que se comparen de forma objetiva las distintas alternativas disponibles. En el caso de la bioinform\u00e1tica hay algunas competiciones con mucha solera, como es el caso de CASP (Critical Assessment of Techniques for Protein Structure Prediction), que ya se encuentra en su s\u00e9ptima edici\u00f3n, CAPRI (a Critical Assessment of PRedicted Interactions) o GASP (Genome Annotation aSsessment Project). Incluso hay un art\u00edculo del a\u00f1o pasado que trata este tema, y que se llama \u00abPrices for Ingenuity\u00ab,\u2026<\/p>\n","protected":false},"author":25,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"ngg_post_thumbnail":0},"categories":[186,31],"tags":[],"blocksy_meta":{"styles_descriptor":{"styles":{"desktop":"","tablet":"","mobile":""},"google_fonts":[],"version":4}},"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/www.madrimasd.org\/blogs\/bioinformatica\/wp-json\/wp\/v2\/posts\/20434"}],"collection":[{"href":"https:\/\/www.madrimasd.org\/blogs\/bioinformatica\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.madrimasd.org\/blogs\/bioinformatica\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.madrimasd.org\/blogs\/bioinformatica\/wp-json\/wp\/v2\/users\/25"}],"replies":[{"embeddable":true,"href":"https:\/\/www.madrimasd.org\/blogs\/bioinformatica\/wp-json\/wp\/v2\/comments?post=20434"}],"version-history":[{"count":0,"href":"https:\/\/www.madrimasd.org\/blogs\/bioinformatica\/wp-json\/wp\/v2\/posts\/20434\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.madrimasd.org\/blogs\/bioinformatica\/wp-json\/wp\/v2\/media?parent=20434"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.madrimasd.org\/blogs\/bioinformatica\/wp-json\/wp\/v2\/categories?post=20434"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.madrimasd.org\/blogs\/bioinformatica\/wp-json\/wp\/v2\/tags?post=20434"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}