Background: The exponential increase of published biomedical literature prompts the use of text mining tools to manage the information overload automatically. One of the most common applications is to mine protein-protein interactions (PPIs) from PubMed abstracts. Currently, most tools in mining PPIs from literature are using co-occurrence-based approaches or rule-based approaches. Hybrid methods (frame-based approaches) by combining these two methods may have better performance in predicting PPIs. However, the predicted PPIs from these methods are rarely evaluated by known PPI databases and co-occurred terms in Gene Ontology (GO) database.
Methodology/Principal Findings: We here developed a web-based tool, PPI Finder, to mine human PPIs from PubMed abstracts based on their co-occurrences and interaction words, followed by evidences in human PPI databases and shared terms in GO database. Only 28% of the co-occurred pairs in PubMed abstracts appeared in any of the commonly used human PPI databases (HPRD, BioGRID and BIND). On the other hand, of the known PPIs in HPRD, 69% showed co- occurrences in the literature, and 65% shared GO terms.
Conclusions: PPI Finder provides a useful tool for biologists to uncover potential novel PPIs. It is freely accessible at http:// liweilab.genetics.ac.cn/tm/.
%0 Journal Article
%1 PPIFinder.2009
%A He, Min
%A Wang, Yi
%A Li, Wei
%D 2009
%J PLoS one
%K CAT CAT-ONLINE-SW CAT-REL-COOR CAT-REL-DBS CAT-REL-VERB PPIFinder extraction interaction relation words
%N 2
%P e4554
%T PPI Finder: A Mining Tool for Human Protein-Protein Interactions
%U http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2641004/pdf/pone.0004554.pdf
%V 4
%X Background: The exponential increase of published biomedical literature prompts the use of text mining tools to manage the information overload automatically. One of the most common applications is to mine protein-protein interactions (PPIs) from PubMed abstracts. Currently, most tools in mining PPIs from literature are using co-occurrence-based approaches or rule-based approaches. Hybrid methods (frame-based approaches) by combining these two methods may have better performance in predicting PPIs. However, the predicted PPIs from these methods are rarely evaluated by known PPI databases and co-occurred terms in Gene Ontology (GO) database.
Methodology/Principal Findings: We here developed a web-based tool, PPI Finder, to mine human PPIs from PubMed abstracts based on their co-occurrences and interaction words, followed by evidences in human PPI databases and shared terms in GO database. Only 28% of the co-occurred pairs in PubMed abstracts appeared in any of the commonly used human PPI databases (HPRD, BioGRID and BIND). On the other hand, of the known PPIs in HPRD, 69% showed co- occurrences in the literature, and 65% shared GO terms.
Conclusions: PPI Finder provides a useful tool for biologists to uncover potential novel PPIs. It is freely accessible at http:// liweilab.genetics.ac.cn/tm/.
@article{PPIFinder.2009,
abstract = {Background: The exponential increase of published biomedical literature prompts the use of text mining tools to manage the information overload automatically. One of the most common applications is to mine protein-protein interactions (PPIs) from PubMed abstracts. Currently, most tools in mining PPIs from literature are using co-occurrence-based approaches or rule-based approaches. Hybrid methods (frame-based approaches) by combining these two methods may have better performance in predicting PPIs. However, the predicted PPIs from these methods are rarely evaluated by known PPI databases and co-occurred terms in Gene Ontology (GO) database.
Methodology/Principal Findings: We here developed a web-based tool, PPI Finder, to mine human PPIs from PubMed abstracts based on their co-occurrences and interaction words, followed by evidences in human PPI databases and shared terms in GO database. Only 28% of the co-occurred pairs in PubMed abstracts appeared in any of the commonly used human PPI databases (HPRD, BioGRID and BIND). On the other hand, of the known PPIs in HPRD, 69% showed co- occurrences in the literature, and 65% shared GO terms.
Conclusions: PPI Finder provides a useful tool for biologists to uncover potential novel PPIs. It is freely accessible at http:// liweilab.genetics.ac.cn/tm/.},
added-at = {2010-09-20T08:41:15.000+0200},
author = {He, Min and Wang, Yi and Li, Wei},
biburl = {https://www.bibsonomy.org/bibtex/2dc1ec03144c492ff61f8df1ef9d6f25d/huiyangsfsu},
interhash = {62376984b8d169e4665f52406599bf36},
intrahash = {dc1ec03144c492ff61f8df1ef9d6f25d},
journal = {PLoS one},
keywords = {CAT CAT-ONLINE-SW CAT-REL-COOR CAT-REL-DBS CAT-REL-VERB PPIFinder extraction interaction relation words},
month = feb,
number = 2,
pages = {e4554},
timestamp = {2010-11-12T02:20:23.000+0100},
title = {PPI Finder: A Mining Tool for Human Protein-Protein Interactions},
url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2641004/pdf/pone.0004554.pdf},
volume = 4,
year = 2009
}