Combining multiple evidence for gene symbol disambiguation

Hua Xu; Jung Wei Fan; Carol Friedman

doi:10.3115/1572392.1572400

Combining multiple evidence for gene symbol disambiguation

Hua Xu, Jung Wei Fan, Carol Friedman

Digital Health Sciences

Research output: Contribution to conference › Paper › peer-review

6 Scopus citations

Abstract

Gene names and symbols are important biomedical entities, but are highly ambiguous. This ambiguity affects the performance of both information extraction and information retrieval systems in the biomedical domain. Existing knowledge sources contain different types of information about genes and could be used to disambiguate gene symbols. In this paper, we applied an information retrieval (IR) based method for human gene symbol disambiguation and studied different methods to combine various types of information from available knowledge sources. Results showed that a combination of evidence usually improved performance. The combination method using coefficients obtained from a logistic regression model reached the highest precision of 92.2% on a testing set of ambiguous human gene symbols.

Original language	English (US)
Pages	41-48
Number of pages	8
DOIs	https://doi.org/10.3115/1572392.1572400
State	Published - 2007
Event	ACL 2007 Workshop on Biological, Translational, and Clinical Language Processing, BioNLP 2007 - Prague, Czech Republic Duration: Jun 29 2007 → …

Other

Other	ACL 2007 Workshop on Biological, Translational, and Clinical Language Processing, BioNLP 2007
Country/Territory	Czech Republic
City	Prague
Period	6/29/07 → …

ASJC Scopus subject areas

Language and Linguistics
Information Systems
Software
Health Informatics
Computer Science Applications
Biomedical Engineering

Access to Document

10.3115/1572392.1572400

Cite this

@conference{2d7598b14cd54c44891ff6b1ef69b75e,

title = "Combining multiple evidence for gene symbol disambiguation",

abstract = "Gene names and symbols are important biomedical entities, but are highly ambiguous. This ambiguity affects the performance of both information extraction and information retrieval systems in the biomedical domain. Existing knowledge sources contain different types of information about genes and could be used to disambiguate gene symbols. In this paper, we applied an information retrieval (IR) based method for human gene symbol disambiguation and studied different methods to combine various types of information from available knowledge sources. Results showed that a combination of evidence usually improved performance. The combination method using coefficients obtained from a logistic regression model reached the highest precision of 92.2% on a testing set of ambiguous human gene symbols.",

author = "Hua Xu and Fan, {Jung Wei} and Carol Friedman",

note = "Publisher Copyright: {\textcopyright} 2007 Association for Computational Linguistics.; ACL 2007 Workshop on Biological, Translational, and Clinical Language Processing, BioNLP 2007 ; Conference date: 29-06-2007",

year = "2007",

doi = "10.3115/1572392.1572400",

language = "English (US)",

pages = "41--48",

}

TY - CONF

T1 - Combining multiple evidence for gene symbol disambiguation

AU - Xu, Hua

AU - Fan, Jung Wei

AU - Friedman, Carol

PY - 2007

Y1 - 2007

N2 - Gene names and symbols are important biomedical entities, but are highly ambiguous. This ambiguity affects the performance of both information extraction and information retrieval systems in the biomedical domain. Existing knowledge sources contain different types of information about genes and could be used to disambiguate gene symbols. In this paper, we applied an information retrieval (IR) based method for human gene symbol disambiguation and studied different methods to combine various types of information from available knowledge sources. Results showed that a combination of evidence usually improved performance. The combination method using coefficients obtained from a logistic regression model reached the highest precision of 92.2% on a testing set of ambiguous human gene symbols.

AB - Gene names and symbols are important biomedical entities, but are highly ambiguous. This ambiguity affects the performance of both information extraction and information retrieval systems in the biomedical domain. Existing knowledge sources contain different types of information about genes and could be used to disambiguate gene symbols. In this paper, we applied an information retrieval (IR) based method for human gene symbol disambiguation and studied different methods to combine various types of information from available knowledge sources. Results showed that a combination of evidence usually improved performance. The combination method using coefficients obtained from a logistic regression model reached the highest precision of 92.2% on a testing set of ambiguous human gene symbols.

UR - http://www.scopus.com/inward/record.url?scp=51049110217&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51049110217&partnerID=8YFLogxK

U2 - 10.3115/1572392.1572400

DO - 10.3115/1572392.1572400

M3 - Paper

AN - SCOPUS:51049110217

SP - 41

EP - 48

T2 - ACL 2007 Workshop on Biological, Translational, and Clinical Language Processing, BioNLP 2007

Y2 - 29 June 2007

ER -

Combining multiple evidence for gene symbol disambiguation

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this