A graph-search framework for associating gene identifiers with documents.

A graph-search framework for associating gene identifiers with documents. Research Abstract Details 

Research Abstract Table of Contents

Jump to the:

A graph-search framework for associating gene identifiers with documents. Abstract Text:

William W Cohen,Einat Minkov,

BACKGROUND: One step in the model organism database curation process is to find, for each article, the identifier of every gene discussed in the article. We consider a relaxation of this problem suitable for semi-automated systems, in which each article is associated with a ranked list of possible gene identifiers, and experimentally compare methods for solving this geneId ranking problem. In addition to baseline approaches based on combining named entity recognition (NER) systems with a "soft dictionary" of gene synonyms, we evaluate a graph-based method which combines the outputs of multiple NER systems, as well as other sources of information, and a learning method for reranking the output of the graph-based method. RESULTS: We show that named entity recognition (NER) systems with similar F-measure performance can have significantly different performance when used with a soft dictionary for geneId-ranking. The graph-based approach can outperform any of its component NER systems, even without learning, and learning can further improve the performance of the graph-based ranking approach. CONCLUSION: The utility of a named entity recognition (NER) system for geneId-finding may not be accurately predicted by its entity-level F1 performance, the most common performance measure. GeneId-ranking systems are best implemented by combining several NER systems. With appropriate combination methods, usefully accurate geneId-ranking systems can be constructed based on easily-available resources, without resorting to problem-specific, engineered components.

A graph-search framework for associating gene identifiers with documents. Publishing Authors By Initials

WW Cohen,E Minkov,

For similar information science: pattern recognition, automated research abstracts see: information science: pattern recognition, automated research

PUBMED ID PMID:

MEDLINE DATE:

A graph-search framework for associating gene identifiers with documents. Journal Published:

PUBLICATION TYPE: Research Support, Non-U.S. Gov

Journal: BMC bioinformatics

VOLUME: 7

Page Numbers: 440

Journal Abbreviation: BMC Bioinformatics

ISSN: 1471-2105

DAY: 10

MONTH: 10

YEAR: 2006

A graph-search framework for associating gene identifiers with documents. Information

Number of References:

LANGUAGE: eng

NlmUniqueID: 100965194

A graph-search framework for associating gene identifiers with documents. Keywords Mesh Terms:

KEYWORDS: Pattern Recognition, Automated

MESH TERMS: methods

Chemical & Substance for Abstract: A graph-search framework for associating gene identifiers with documents. Information

Substance Name:

Registry Number:

Grant and Affiliation Information for A graph-search framework for associating gene identifiers with documents.

AFFILIATION: Department of Machine Learning, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA. wcohen@cs.cmu.edu

Country: England

AGENCY: United States NIDA

GRANT: K25 DA017357-01

ACRONYM: DA

MEDLINETA: BMC Bioinformatics

REFSOURCE:

DATABASENAME:

ACCESSION NUMBER:

Number Hits: 0

A graph-search framework for associating gene identifiers with documents Related Publications

• A graph-search framework for associating gene identifiers with documents.
• [Allergic rhinitis]
• [Effect of alpha-tocopherol and its derivatives on ATPase activity and oxidative phosphorylation in rat liver mitochondria]
• [Medical gymnastics for bronchial asthma and pollinosis patients]
• [Myxomas of the heart.]
• [Transfemoral renovasography by the Zel'dinger method.]