A text-mining system for extracting metabolic reactions from full-text articles
<p>Abstract</p> <p>Background</p> <p>Increasingly biological text mining research is focusing on the extraction of complex relationships relevant to the construction and curation of biological networks and pathways. However, one important category of pathway — metabolic...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2012-07-01
|
Series: | BMC Bioinformatics |
Online Access: | http://www.biomedcentral.com/1471-2105/13/172 |
id |
doaj-a3facb1ed0cc4db6803783eb225b8a75 |
---|---|
record_format |
Article |
spelling |
doaj-a3facb1ed0cc4db6803783eb225b8a752020-11-24T21:39:30ZengBMCBMC Bioinformatics1471-21052012-07-0113117210.1186/1471-2105-13-172A text-mining system for extracting metabolic reactions from full-text articlesCzarnecki JanNobeli IreneSmith Adrian MShepherd Adrian J<p>Abstract</p> <p>Background</p> <p>Increasingly biological text mining research is focusing on the extraction of complex relationships relevant to the construction and curation of biological networks and pathways. However, one important category of pathway — metabolic pathways — has been largely neglected.</p> <p>Here we present a relatively simple method for extracting metabolic reaction information from free text that scores different permutations of assigned entities (enzymes and metabolites) within a given sentence based on the presence and location of stemmed keywords. This method extends an approach that has proved effective in the context of the extraction of protein–protein interactions.</p> <p>Results</p> <p>When evaluated on a set of manually-curated metabolic pathways using standard performance criteria, our method performs surprisingly well. Precision and recall rates are comparable to those previously achieved for the well-known protein-protein interaction extraction task.</p> <p>Conclusions</p> <p>We conclude that automated metabolic pathway construction is more tractable than has often been assumed, and that (as in the case of protein–protein interaction extraction) relatively simple text-mining approaches can prove surprisingly effective. It is hoped that these results will provide an impetus to further research and act as a useful benchmark for judging the performance of more sophisticated methods that are yet to be developed.</p> http://www.biomedcentral.com/1471-2105/13/172 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Czarnecki Jan Nobeli Irene Smith Adrian M Shepherd Adrian J |
spellingShingle |
Czarnecki Jan Nobeli Irene Smith Adrian M Shepherd Adrian J A text-mining system for extracting metabolic reactions from full-text articles BMC Bioinformatics |
author_facet |
Czarnecki Jan Nobeli Irene Smith Adrian M Shepherd Adrian J |
author_sort |
Czarnecki Jan |
title |
A text-mining system for extracting metabolic reactions from full-text articles |
title_short |
A text-mining system for extracting metabolic reactions from full-text articles |
title_full |
A text-mining system for extracting metabolic reactions from full-text articles |
title_fullStr |
A text-mining system for extracting metabolic reactions from full-text articles |
title_full_unstemmed |
A text-mining system for extracting metabolic reactions from full-text articles |
title_sort |
text-mining system for extracting metabolic reactions from full-text articles |
publisher |
BMC |
series |
BMC Bioinformatics |
issn |
1471-2105 |
publishDate |
2012-07-01 |
description |
<p>Abstract</p> <p>Background</p> <p>Increasingly biological text mining research is focusing on the extraction of complex relationships relevant to the construction and curation of biological networks and pathways. However, one important category of pathway — metabolic pathways — has been largely neglected.</p> <p>Here we present a relatively simple method for extracting metabolic reaction information from free text that scores different permutations of assigned entities (enzymes and metabolites) within a given sentence based on the presence and location of stemmed keywords. This method extends an approach that has proved effective in the context of the extraction of protein–protein interactions.</p> <p>Results</p> <p>When evaluated on a set of manually-curated metabolic pathways using standard performance criteria, our method performs surprisingly well. Precision and recall rates are comparable to those previously achieved for the well-known protein-protein interaction extraction task.</p> <p>Conclusions</p> <p>We conclude that automated metabolic pathway construction is more tractable than has often been assumed, and that (as in the case of protein–protein interaction extraction) relatively simple text-mining approaches can prove surprisingly effective. It is hoped that these results will provide an impetus to further research and act as a useful benchmark for judging the performance of more sophisticated methods that are yet to be developed.</p> |
url |
http://www.biomedcentral.com/1471-2105/13/172 |
work_keys_str_mv |
AT czarneckijan atextminingsystemforextractingmetabolicreactionsfromfulltextarticles AT nobeliirene atextminingsystemforextractingmetabolicreactionsfromfulltextarticles AT smithadrianm atextminingsystemforextractingmetabolicreactionsfromfulltextarticles AT shepherdadrianj atextminingsystemforextractingmetabolicreactionsfromfulltextarticles AT czarneckijan textminingsystemforextractingmetabolicreactionsfromfulltextarticles AT nobeliirene textminingsystemforextractingmetabolicreactionsfromfulltextarticles AT smithadrianm textminingsystemforextractingmetabolicreactionsfromfulltextarticles AT shepherdadrianj textminingsystemforextractingmetabolicreactionsfromfulltextarticles |
_version_ |
1725930950022397952 |