Evaluating the Automatic Mapping of Human Gene and Protein Mentions to Unique Identifiers

Morgan, Alexander A.; Wellner, Benjamin; Colombe, Jeffrey B.; Arens, Robert; Colosimo, Marc E.; Hirschman, Lynette

doi:10.1142/9789812772435_0027

Cited by 8 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Testing set 2 was derived using the training and evaluation sets of the BioCreAtIvE II Gene Normalization (GN) task (Morgan 2007). The Bio-CreAtIvE II GN task involved mapping human gene mentions in MEDLINE abstracts to gene identifiers (Entrez Gene ID), which is a broader task than the GSD task.…”

Section: Document Set and Testing Setsmentioning

confidence: 99%

Combining multiple evidence for gene symbol disambiguation

Fan

Friedman

2007

Proceedings of the Workshop on BioNLP 2007 Biological, Translational, and Clinical Language Processing - BioNLP '07

View full text Add to dashboard Cite

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.

show abstract

Section: Document Set and Testing Setsmentioning

confidence: 99%

Combining multiple evidence for gene symbol disambiguation

Fan

Friedman

2007

Proceedings of the Workshop on BioNLP 2007 Biological, Translational, and Clinical Language Processing - BioNLP '07

View full text Add to dashboard Cite

show abstract

“…The test case for this more complex evaluation is a gene name normalization system [ 32 ] constructed for the 2006 BioCreative Gene Name Normalization task [ 33 ]. The GN system used in this example relies on gene annotations as input, and we will use many of the components generated for the gene tagger evaluation discussed in the previous section to produce these annotations.…”

Section: Methodsmentioning

confidence: 99%

An open-source framework for large-scale, flexible evaluation of biomedical text mining systems

Baumgartner

Cohen

Hunter

2008

J Biomed Discov Collaboration

View full text Add to dashboard Cite

Background: Improved evaluation methodologies have been identified as a necessary prerequisite to the improvement of text mining theory and practice. This paper presents a publicly available framework that facilitates thorough, structured, and large-scale evaluations of text mining technologies. The extensibility of this framework and its ability to uncover system-wide characteristics by analyzing component parts as well as its usefulness for facilitating third-party application integration are demonstrated through examples in the biomedical domain.

show abstract

“…To get new automatically labeled examples, we made use of the synonym lists provided by the organisers of the BioCreative II task [ 16 ] for the human task and the lists of extracted synonyms from the Entrez 'gene_info' file [ 3 ] for the mouse, fly and yeast tasks. These lists contain several aliases (synonyms) for each gene.…”

Section: Methodsmentioning

confidence: 99%

“…The GSD datasets for yeast, fly and mouse are generated using MedLine abstracts and the Entrez 'gene2pubmed' file [ 3 ], which is manually disambiguated [ 14 ]. The dataset for human genes was derived [ 15 ] from the training and evaluation sets of the BioCreative II GN task [ 16 ].…”

Section: Introductionmentioning

confidence: 99%

The strength of co-authorship in gene name disambiguation

Farkas

2008

BMC Bioinformatics

View full text Add to dashboard Cite

BackgroundA biomedical entity mention in articles and other free texts is often ambiguous. For example, 13% of the gene names (aliases) might refer to more than one gene. The task of Gene Symbol Disambiguation (GSD) – a special case of Word Sense Disambiguation (WSD) – is to assign a unique gene identifier for all identified gene name aliases in biology-related articles. Supervised and unsupervised machine learning WSD techniques have been applied in the biomedical field with promising results. We examine here the utilisation potential of the fact – one of the special features of biological articles – that the authors of the documents are known through graph-based semi-supervised methods for the GSD task.ResultsOur key hypothesis is that a biologist refers to each particular gene by a fixed gene alias and this holds for the co-authors as well. To make use of the co-authorship information we decided to build the inverse co-author graph on MedLine abstracts. The nodes of the inverse co-author graph are articles and there is an edge between two nodes if and only if the two articles have a mutual author. We introduce here two methods using distances (based on the graph) of abstracts for the GSD task. We found that a disambiguation decision can be made in 85% of cases with an extremely high (99.5%) precision rate just by using information obtained from the inverse co-author graph. We incorporated the co-authorship information into two GSD systems in order to attain full coverage and in experiments our procedure achieved precision of 94.3%, 98.85%, 96.05% and 99.63% on the human, mouse, fly and yeast GSD evaluation sets, respectively.ConclusionBased on the promising results obtained so far we suggest that the co-authorship information and the circumstances of the articles' release (like the title of the journal, the year of publication) can be a crucial building block of any sophisticated similarity measure among biological articles and hence the methods introduced here should be useful for other biomedical natural language processing tasks (like organism or target disease detection) as well.

show abstract

Evaluating the Automatic Mapping of Human Gene and Protein Mentions to Unique Identifiers

Cited by 8 publications

References 16 publications

Combining multiple evidence for gene symbol disambiguation

Combining multiple evidence for gene symbol disambiguation

An open-source framework for large-scale, flexible evaluation of biomedical text mining systems

The strength of co-authorship in gene name disambiguation

Contact Info

Product

Resources

About