Limits...
BioCreative V track 4: a shared task for the extraction of causal network information using the Biological Expression Language.

Rinaldi F, Ellendorff TR, Madan S, Clematide S, van der Lek A, Mevissen T, Fluck J - Database (Oxford) (2016)

Bottom Line: Given the complexity of the task, we designed an evaluation methodology which gives credit to partially correct statements.We identified various levels of information expressed by BEL statements, such as entities, functions, relations, and introduced an evaluation framework which rewards systems capable of delivering useful BEL fragments at each of these levels.The aim of this evaluation method is to help identify the characteristics of the systems which, if combined, would be most useful for achieving the overall goal of automatically constructing causal biological networks from text.

View Article: PubMed Central - PubMed

Affiliation: Institute of Computational Linguistics, University of Zurich, Zurich, Switzerland fabio.rinaldi@uzh.ch juliane.fluck@scai.fraunhofer.de.

No MeSH data available.


Visualization of the BEL statement ‘cat(p(HGNC:FAS)) increases p(HGNC:RB1,pmod(P))’ derived from the sentence ‘Fas stimulation of Jurkat cells is known to induce p38 kinase and we find a pronounced increase in Rb phosphorylation within 30 min of Fas stimulation’.
© Copyright Policy - creative-commons
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4940434&req=5

baw067-F3: Visualization of the BEL statement ‘cat(p(HGNC:FAS)) increases p(HGNC:RB1,pmod(P))’ derived from the sentence ‘Fas stimulation of Jurkat cells is known to induce p38 kinase and we find a pronounced increase in Rb phosphorylation within 30 min of Fas stimulation’.

Mentions: Further supporting resources included the BEL statements from the training and sample set in BioC format. These were generated automatically using a converter based on the official ruby-based BEL parser (http://www.openbel.org/tags/bel-parser-belrb) and an open-source BioC ruby module (https://github.com/dongseop/simple_bioc) (23). Furthermore, a tab-separated format containing all fragments of the BEL statements (terms, functions and relations) was generated from the sample and training set, using the same BEL parser mentioned above. Finally, graph visualizations representing the structure of the BEL statements were automatically derived from the BioC format. An example for such visualization can be seen in Figure 3.Figure 3


BioCreative V track 4: a shared task for the extraction of causal network information using the Biological Expression Language.

Rinaldi F, Ellendorff TR, Madan S, Clematide S, van der Lek A, Mevissen T, Fluck J - Database (Oxford) (2016)

Visualization of the BEL statement ‘cat(p(HGNC:FAS)) increases p(HGNC:RB1,pmod(P))’ derived from the sentence ‘Fas stimulation of Jurkat cells is known to induce p38 kinase and we find a pronounced increase in Rb phosphorylation within 30 min of Fas stimulation’.
© Copyright Policy - creative-commons
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4940434&req=5

baw067-F3: Visualization of the BEL statement ‘cat(p(HGNC:FAS)) increases p(HGNC:RB1,pmod(P))’ derived from the sentence ‘Fas stimulation of Jurkat cells is known to induce p38 kinase and we find a pronounced increase in Rb phosphorylation within 30 min of Fas stimulation’.
Mentions: Further supporting resources included the BEL statements from the training and sample set in BioC format. These were generated automatically using a converter based on the official ruby-based BEL parser (http://www.openbel.org/tags/bel-parser-belrb) and an open-source BioC ruby module (https://github.com/dongseop/simple_bioc) (23). Furthermore, a tab-separated format containing all fragments of the BEL statements (terms, functions and relations) was generated from the sample and training set, using the same BEL parser mentioned above. Finally, graph visualizations representing the structure of the BEL statements were automatically derived from the BioC format. An example for such visualization can be seen in Figure 3.Figure 3

Bottom Line: Given the complexity of the task, we designed an evaluation methodology which gives credit to partially correct statements.We identified various levels of information expressed by BEL statements, such as entities, functions, relations, and introduced an evaluation framework which rewards systems capable of delivering useful BEL fragments at each of these levels.The aim of this evaluation method is to help identify the characteristics of the systems which, if combined, would be most useful for achieving the overall goal of automatically constructing causal biological networks from text.

View Article: PubMed Central - PubMed

Affiliation: Institute of Computational Linguistics, University of Zurich, Zurich, Switzerland fabio.rinaldi@uzh.ch juliane.fluck@scai.fraunhofer.de.

No MeSH data available.