Extraction of regulatory gene/protein networks from Medline. Saric, J., Jensen, L., J., Ouzounova, R., Rojas, I., & Bork, P. Bioinformatics, 22(6):645-650, Oxford Univ Press, 2006.
![Extraction of regulatory gene/protein networks from Medline. [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper ![Extraction of regulatory gene/protein networks from Medline. [link]](https://bibbase.org/img/filetypes/link.svg "link")
Website abstract bibtex
Paper Website abstract bibtex MOTIVATION: We have previously developed a rule-based approach for extracting information on the regulation of gene expression in yeast. The biomedical literature, however, contains information on several other equally important regulatory mechanisms, in particular phosphorylation, which we now expanded for our rule-based system also to extract. RESULTS: This paper presents new results for extraction of relational information from biomedical text. We have improved our system, STRING-IE, to capture both new types of linguistic constructs as well as new types of biological information i.e. (de-)phosphorylation. The precision remains stable with a slight increase in recall. From almost one million PubMed abstracts related to four model organisms, we manage to extract regulatory networks and binary phosphorylations comprising 3,319 relation chunks. The accuracy is 83-90% and 86-95% for gene expression and (de-)phosphorylation relations, respectively. To achieve this, we made use of an organism-specific resource of gene/protein names considerably larger than those used in most other biology related information extraction approaches. These names were included in the lexicon when retraining the part-of-speech (POS) tagger on the GENIA corpus. For the domain in question, an accuracy of 96.4% was attained on POS tags. It should be noted that the rules were developed for yeast and successfully applied to both abstracts and full-text articles related to other organisms with comparable accuracy. AVAILABILITY: The revised GENIA corpus, the POS tagger, the extraction rules and the full sets of extracted relations are available from http://www.bork.embl.de/Docu/STRING-IE
@article{
title = {Extraction of regulatory gene/protein networks from Medline.},
type = {article},
year = {2006},
identifiers = {[object Object]},
keywords = {abstracting indexing topic,abstracting indexing topic methods,gene expression regulation,gene expression regulation physiology,information storage retrieval,information storage retrieval methods,medline,natural language processing,periodicals topic,saccharomyces cerevisiae proteins,saccharomyces cerevisiae proteins classification,saccharomyces cerevisiae proteins genetics,saccharomyces cerevisiae proteins metabolism,signal transduction,signal transduction physiology},
pages = {645-650},
volume = {22},
websites = {http://www.ncbi.nlm.nih.gov/pubmed/16046493},
publisher = {Oxford Univ Press},
institution = {EML Research gGmbH D-69118 Heidelberg, Germany. saric@eml-r.org},
id = {3015db0c-1080-36a5-bc8f-ef66ce134628},
created = {2011-12-29T19:53:53.000Z},
file_attached = {true},
profile_id = {5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6},
group_id = {066b42c8-f712-3fc3-abb2-225c158d2704},
last_modified = {2017-03-14T14:36:19.698Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
citation_key = {Saric2006},
private_publication = {false},
abstract = {MOTIVATION: We have previously developed a rule-based approach for extracting information on the regulation of gene expression in yeast. The biomedical literature, however, contains information on several other equally important regulatory mechanisms, in particular phosphorylation, which we now expanded for our rule-based system also to extract. RESULTS: This paper presents new results for extraction of relational information from biomedical text. We have improved our system, STRING-IE, to capture both new types of linguistic constructs as well as new types of biological information i.e. (de-)phosphorylation. The precision remains stable with a slight increase in recall. From almost one million PubMed abstracts related to four model organisms, we manage to extract regulatory networks and binary phosphorylations comprising 3,319 relation chunks. The accuracy is 83-90% and 86-95% for gene expression and (de-)phosphorylation relations, respectively. To achieve this, we made use of an organism-specific resource of gene/protein names considerably larger than those used in most other biology related information extraction approaches. These names were included in the lexicon when retraining the part-of-speech (POS) tagger on the GENIA corpus. For the domain in question, an accuracy of 96.4% was attained on POS tags. It should be noted that the rules were developed for yeast and successfully applied to both abstracts and full-text articles related to other organisms with comparable accuracy. AVAILABILITY: The revised GENIA corpus, the POS tagger, the extraction rules and the full sets of extracted relations are available from http://www.bork.embl.de/Docu/STRING-IE},
bibtype = {article},
author = {Saric, Jasmin and Jensen, Lars Juhl and Ouzounova, Rossitza and Rojas, Isabel and Bork, Peer},
journal = {Bioinformatics},
number = {6}
}Downloads: 0
{"_id":"t7yWHtJxYpbGmRGJm","bibbaseid":"saric-jensen-ouzounova-rojas-bork-extractionofregulatorygeneproteinnetworksfrommedline-2006","authorIDs":[],"author_short":["Saric, J.","Jensen, L., J.","Ouzounova, R.","Rojas, I.","Bork, P."],"bibdata":{"title":"Extraction of regulatory gene/protein networks from Medline.","type":"article","year":"2006","identifiers":"[object Object]","keywords":"abstracting indexing topic,abstracting indexing topic methods,gene expression regulation,gene expression regulation physiology,information storage retrieval,information storage retrieval methods,medline,natural language processing,periodicals topic,saccharomyces cerevisiae proteins,saccharomyces cerevisiae proteins classification,saccharomyces cerevisiae proteins genetics,saccharomyces cerevisiae proteins metabolism,signal transduction,signal transduction physiology","pages":"645-650","volume":"22","websites":"http://www.ncbi.nlm.nih.gov/pubmed/16046493","publisher":"Oxford Univ Press","institution":"EML Research gGmbH D-69118 Heidelberg, Germany. saric@eml-r.org","id":"3015db0c-1080-36a5-bc8f-ef66ce134628","created":"2011-12-29T19:53:53.000Z","file_attached":"true","profile_id":"5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6","group_id":"066b42c8-f712-3fc3-abb2-225c158d2704","last_modified":"2017-03-14T14:36:19.698Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"Saric2006","private_publication":false,"abstract":"MOTIVATION: We have previously developed a rule-based approach for extracting information on the regulation of gene expression in yeast. The biomedical literature, however, contains information on several other equally important regulatory mechanisms, in particular phosphorylation, which we now expanded for our rule-based system also to extract. RESULTS: This paper presents new results for extraction of relational information from biomedical text. We have improved our system, STRING-IE, to capture both new types of linguistic constructs as well as new types of biological information i.e. (de-)phosphorylation. The precision remains stable with a slight increase in recall. From almost one million PubMed abstracts related to four model organisms, we manage to extract regulatory networks and binary phosphorylations comprising 3,319 relation chunks. The accuracy is 83-90% and 86-95% for gene expression and (de-)phosphorylation relations, respectively. To achieve this, we made use of an organism-specific resource of gene/protein names considerably larger than those used in most other biology related information extraction approaches. These names were included in the lexicon when retraining the part-of-speech (POS) tagger on the GENIA corpus. For the domain in question, an accuracy of 96.4% was attained on POS tags. It should be noted that the rules were developed for yeast and successfully applied to both abstracts and full-text articles related to other organisms with comparable accuracy. AVAILABILITY: The revised GENIA corpus, the POS tagger, the extraction rules and the full sets of extracted relations are available from http://www.bork.embl.de/Docu/STRING-IE","bibtype":"article","author":"Saric, Jasmin and Jensen, Lars Juhl and Ouzounova, Rossitza and Rojas, Isabel and Bork, Peer","journal":"Bioinformatics","number":"6","bibtex":"@article{\n title = {Extraction of regulatory gene/protein networks from Medline.},\n type = {article},\n year = {2006},\n identifiers = {[object Object]},\n keywords = {abstracting indexing topic,abstracting indexing topic methods,gene expression regulation,gene expression regulation physiology,information storage retrieval,information storage retrieval methods,medline,natural language processing,periodicals topic,saccharomyces cerevisiae proteins,saccharomyces cerevisiae proteins classification,saccharomyces cerevisiae proteins genetics,saccharomyces cerevisiae proteins metabolism,signal transduction,signal transduction physiology},\n pages = {645-650},\n volume = {22},\n websites = {http://www.ncbi.nlm.nih.gov/pubmed/16046493},\n publisher = {Oxford Univ Press},\n institution = {EML Research gGmbH D-69118 Heidelberg, Germany. saric@eml-r.org},\n id = {3015db0c-1080-36a5-bc8f-ef66ce134628},\n created = {2011-12-29T19:53:53.000Z},\n file_attached = {true},\n profile_id = {5284e6aa-156c-3ce5-bc0e-b80cf09f3ef6},\n group_id = {066b42c8-f712-3fc3-abb2-225c158d2704},\n last_modified = {2017-03-14T14:36:19.698Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {Saric2006},\n private_publication = {false},\n abstract = {MOTIVATION: We have previously developed a rule-based approach for extracting information on the regulation of gene expression in yeast. The biomedical literature, however, contains information on several other equally important regulatory mechanisms, in particular phosphorylation, which we now expanded for our rule-based system also to extract. RESULTS: This paper presents new results for extraction of relational information from biomedical text. We have improved our system, STRING-IE, to capture both new types of linguistic constructs as well as new types of biological information i.e. (de-)phosphorylation. The precision remains stable with a slight increase in recall. From almost one million PubMed abstracts related to four model organisms, we manage to extract regulatory networks and binary phosphorylations comprising 3,319 relation chunks. The accuracy is 83-90% and 86-95% for gene expression and (de-)phosphorylation relations, respectively. To achieve this, we made use of an organism-specific resource of gene/protein names considerably larger than those used in most other biology related information extraction approaches. These names were included in the lexicon when retraining the part-of-speech (POS) tagger on the GENIA corpus. For the domain in question, an accuracy of 96.4% was attained on POS tags. It should be noted that the rules were developed for yeast and successfully applied to both abstracts and full-text articles related to other organisms with comparable accuracy. AVAILABILITY: The revised GENIA corpus, the POS tagger, the extraction rules and the full sets of extracted relations are available from http://www.bork.embl.de/Docu/STRING-IE},\n bibtype = {article},\n author = {Saric, Jasmin and Jensen, Lars Juhl and Ouzounova, Rossitza and Rojas, Isabel and Bork, Peer},\n journal = {Bioinformatics},\n number = {6}\n}","author_short":["Saric, J.","Jensen, L., J.","Ouzounova, R.","Rojas, I.","Bork, P."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfdabac2-d7f2-3c5b-aa7a-06431c0ae35e/file/39c70265-7f3a-3c15-0c0e-a6674a2e48db/2006-Extraction_of_regulatory_geneprotein_networks_from_Medline..pdf.pdf","Website":"http://www.ncbi.nlm.nih.gov/pubmed/16046493"},"bibbaseid":"saric-jensen-ouzounova-rojas-bork-extractionofregulatorygeneproteinnetworksfrommedline-2006","role":"author","keyword":["abstracting indexing topic","abstracting indexing topic methods","gene expression regulation","gene expression regulation physiology","information storage retrieval","information storage retrieval methods","medline","natural language processing","periodicals topic","saccharomyces cerevisiae proteins","saccharomyces cerevisiae proteins classification","saccharomyces cerevisiae proteins genetics","saccharomyces cerevisiae proteins metabolism","signal transduction","signal transduction physiology"],"downloads":0,"html":""},"bibtype":"article","creationDate":"2020-02-06T23:48:11.856Z","downloads":0,"keywords":["abstracting indexing topic","abstracting indexing topic methods","gene expression regulation","gene expression regulation physiology","information storage retrieval","information storage retrieval methods","medline","natural language processing","periodicals topic","saccharomyces cerevisiae proteins","saccharomyces cerevisiae proteins classification","saccharomyces cerevisiae proteins genetics","saccharomyces cerevisiae proteins metabolism","signal transduction","signal transduction physiology"],"search_terms":["extraction","regulatory","gene","protein","networks","medline","saric","jensen","ouzounova","rojas","bork"],"title":"Extraction of regulatory gene/protein networks from Medline.","year":2006}