MedlineRanker: flexible ranking of biomedical literature

Publication type:
Journal article
Metadata:
Autoren
  • Jean-Fred Fontaine
  • Adriano Barbosa-Silva
  • Martin Schaefer
  • Matthew R Huska
  • Enrique M Muro
  • Miguel A Andrade-Navarro
Autoren-URL
https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=fis-test-1&SrcAuth=WosAPI&KeyUT=WOS:000267889100026&DestLinkType=FullRecord&DestApp=WOS_CPL
DOI
10.1093/nar/gkp353
eISSN
1362-4962
Externe Identifier
  • Clarivate Analytics Document Solution ID: 469IG
  • PubMed Identifier: 19429696
ISSN
0305-1048
Zeitschrift
NUCLEIC ACIDS RESEARCH
Paginierung
W141 - W146
Datum der Veröffentlichung
2009
Status
Published
Titel
MedlineRanker: flexible ranking of biomedical literature
Sub types
  • Article
Ausgabe der Zeitschrift
37

Data source: Web of Science (Lite)

Other metadata sources:
Autoren
  • Jean-Fred Fontaine
  • Adriano Barbosa-Silva
  • Martin Schaefer
  • Matthew R Huska
  • Enrique M Muro
  • Miguel A Andrade-Navarro
DOI
10.1093/nar/gkp353
eISSN
1362-4962
ISSN
0305-1048
Ausgabe der Veröffentlichung
suppl_2
Zeitschrift
Nucleic Acids Research
Sprache
en
Online publication date
2009
Paginierung
W141 - W146
Datum der Veröffentlichung
2009
Status
Published
Herausgeber
Oxford University Press (OUP)
Herausgeber URL
http://dx.doi.org/10.1093/nar/gkp353
Datum der Datenerfassung
2018
Titel
MedlineRanker: flexible ranking of biomedical literature
Ausgabe der Zeitschrift
37

Data source: Crossref

Abstract
The biomedical literature is represented by millions of abstracts available in the Medline database. These abstracts can be queried with the PubMed interface, which provides a keyword-based Boolean search engine. This approach shows limitations in the retrieval of abstracts related to very specific topics, as it is difficult for a non-expert user to find all of the most relevant keywords related to a biomedical topic. Additionally, when searching for more general topics, the same approach may return hundreds of unranked references. To address these issues, text mining tools have been developed to help scientists focus on relevant abstracts. We have implemented the MedlineRanker webserver, which allows a flexible ranking of Medline for a topic of interest without expert knowledge. Given some abstracts related to a topic, the program deduces automatically the most discriminative words in comparison to a random selection. These words are used to score other abstracts, including those from not yet annotated recent publications, which can be then ranked by relevance. We show that our tool can be highly accurate and that it is able to process millions of abstracts in a practical amount of time. MedlineRanker is free for use and is available at http://cbdm.mdc-berlin.de/tools/medlineranker.
Addresses
  • Computational Biology and Data Mining Group, Max Delbrück Center for Molecular Medicine, Robert-Rössle-Strasse. 10, D-13125, Berlin, Germany. jean-fred.fontaine@mdc-berlin.de
Autoren
  • Jean-Fred Fontaine
  • Adriano Barbosa-Silva
  • Martin Schaefer
  • Matthew R Huska
  • Enrique M Muro
  • Miguel A Andrade-Navarro
DOI
10.1093/nar/gkp353
eISSN
1362-4962
Externe Identifier
  • PubMed Identifier: 19429696
  • PubMed Central ID: PMC2703945
Open access
true
ISSN
0305-1048
Ausgabe der Veröffentlichung
Web Server issue
Zeitschrift
Nucleic acids research
Schlüsselwörter
  • Software
  • User-Computer Interface
  • Information Storage and Retrieval
  • MEDLINE
Sprache
eng
Medium
Print-Electronic
Online publication date
2009
Open access status
Open Access
Paginierung
W141 - W146
Datum der Veröffentlichung
2009
Status
Published
Publisher licence
CC BY-NC
Datum der Datenerfassung
2009
Titel
MedlineRanker: flexible ranking of biomedical literature.
Sub types
  • Research Support, Non-U.S. Gov't
  • research-article
  • Journal Article
Ausgabe der Zeitschrift
37

Files

https://academic.oup.com/nar/article-pdf/37/suppl_2/W141/16758323/gkp353.pdf http://nar.oxfordjournals.org/cgi/reprint/37/suppl_2/W141.pdf https://www.ncbi.nlm.nih.gov/pmc/articles/pmid/19429696/pdf/?tool=EBI https://europepmc.org/articles/PMC2703945?pdf=render

Data source: Europe PubMed Central

Abstract
The biomedical literature is represented by millions of abstracts available in the Medline database. These abstracts can be queried with the PubMed interface, which provides a keyword-based Boolean search engine. This approach shows limitations in the retrieval of abstracts related to very specific topics, as it is difficult for a non-expert user to find all of the most relevant keywords related to a biomedical topic. Additionally, when searching for more general topics, the same approach may return hundreds of unranked references. To address these issues, text mining tools have been developed to help scientists focus on relevant abstracts. We have implemented the MedlineRanker webserver, which allows a flexible ranking of Medline for a topic of interest without expert knowledge. Given some abstracts related to a topic, the program deduces automatically the most discriminative words in comparison to a random selection. These words are used to score other abstracts, including those from not yet annotated recent publications, which can be then ranked by relevance. We show that our tool can be highly accurate and that it is able to process millions of abstracts in a practical amount of time. MedlineRanker is free for use and is available at http://cbdm.mdc-berlin.de/tools/medlineranker.
Autoren
  • Jean-Fred Fontaine
  • Adriano Barbosa-Silva
  • Martin Schaefer
  • Matthew R Huska
  • Enrique M Muro
  • Miguel A Andrade-Navarro
Autoren-URL
https://www.ncbi.nlm.nih.gov/pubmed/19429696
DOI
10.1093/nar/gkp353
eISSN
1362-4962
Externe Identifier
  • PubMed Central ID: PMC2703945
Ausgabe der Veröffentlichung
Web Server issue
Zeitschrift
Nucleic Acids Res
Schlüsselwörter
  • Information Storage and Retrieval
  • MEDLINE
  • Software
  • User-Computer Interface
Sprache
eng
Country
England
Paginierung
W141 - W146
PII
gkp353
Datum der Veröffentlichung
2009
Status
Published
Datum, an dem der Datensatz öffentlich gemacht wurde
2009
Titel
MedlineRanker: flexible ranking of biomedical literature.
Sub types
  • Journal Article
  • Research Support, Non-U.S. Gov't
Ausgabe der Zeitschrift
37

Data source: PubMed

Beziehungen:
Property of

Tools