OntoMate: a text-mining tool aiding curation at the Rat Genome Database

Liu, Weisong; Laulederkind, Stanley J. F.; Wang, Shur-Jen; Nigam, Rajni; Smith, Jennifer; Pons, Jeff De; Dwinell, Melinda R.; Shimoyama, Mary

doi:10.1093/database/bau129

Cited by 22 publications

(15 citation statements)

References 18 publications

(10 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, PubMed abstracts are searched using the text mining software tool OntoMate ( 11 ) which has been integrated into the curation software ( 2 ). The search retrieves and ranks abstracts containing selected disease terms and the name and synonyms of selected genes ( Figure 1 ).…”

Section: Manual Disease Curation At Rgdmentioning

confidence: 99%

The Disease Portals, disease–gene annotation and the RGD disease ontology at the Rat Genome Database

et al. 2016

Self Cite

View full text Add to dashboard Cite

The Rat Genome Database (RGD; http://rgd.mcw.edu/) provides critical datasets and software tools to a diverse community of rat and non-rat researchers worldwide. To meet the needs of the many users whose research is disease oriented, RGD has created a series of Disease Portals and has prioritized its curation efforts on the datasets important to understanding the mechanisms of various diseases. Gene-disease relationships for three species, rat, human and mouse, are annotated to capture biomarkers, genetic associations, molecular mechanisms and therapeutic targets. To generate gene–disease annotations more effectively and in greater detail, RGD initially adopted the MEDIC disease vocabulary from the Comparative Toxicogenomics Database and adapted it for use by expanding this framework with the addition of over 1000 terms to create the RGD Disease Ontology (RDO). The RDO provides the foundation for, at present, 10 comprehensive disease area-related dataset and analysis platforms at RGD, the Disease Portals. Two major disease areas are the focus of data acquisition and curation efforts each year, leading to the release of the related Disease Portals. Collaborative efforts to realize a more robust disease ontology are underway.Database URL: http://rgd.mcw.edu

show abstract

Section: Manual Disease Curation At Rgdmentioning

confidence: 99%

The Disease Portals, disease–gene annotation and the RGD disease ontology at the Rat Genome Database

et al. 2016

Self Cite

View full text Add to dashboard Cite

show abstract

“…The focus in such studies is often to design a Graphic User Interfaces and to simplify the curation work by highlighting specifi c concepts in a dedicated tool [ 16 ]. While most of these systems seem exploratory studies, some seem deeply integrated in the curation workfl ow, as shown by the OntoMate tool designed by the Rat Genome Database [ 17 ], the STRING DB for protein-protein interactions or the BioEditor of neXtProt [ 18 ]. From an evaluation perspective, the idea is to detect the beginning and the end of an entity and to assign a semantic type to this string.…”

Section: Check Of Recordsmentioning

confidence: 99%

Text Mining to Support Gene Ontology Curation and Vice Versa

Ruch

2016

Methods in Molecular Biology

View full text Add to dashboard Cite

In this chapter, we explain how text mining can support the curation of molecular biology databases dealing with protein functions. We also show how curated data can play a disruptive role in the developments of text mining methods. We review a decade of efforts to improve the automatic assignment of Gene Ontology (GO) descriptors, the reference ontology for the characterization of genes and gene products. To illustrate the high potential of this approach, we compare the performances of an automatic text categorizer and show a large improvement of +225 % in both precision and recall on benchmarked data. We argue that automatic text categorization functions can ultimately be embedded into a Question-Answering (QA) system to answer questions related to protein functions. Because GO descriptors can be relatively long and specific, traditional QA systems cannot answer such questions. A new type of QA system, so-called Deep QA which uses machine learning methods trained with curated contents, is thus emerging. Finally, future advances of text mining instruments are directly dependent on the availability of high-quality annotated contents at every curation step. Databases workflows must start recording explicitly all the data they curate and ideally also some of the data they do not curate.

show abstract

“…OntoMate, for example, uses natural language processing to curate gene and phenotype ontology from the titles and abstracts of PubMed literature (LIU et al 2015). PubMatrix uses text mining to build a frequency matrix of term co-occurrence (BECKER et al 2003).…”

Section: Introductionmentioning

confidence: 99%

“…Nevertheless, many literature mining tools, often called “PubMed derivatives,” have been developed to facilitate the search of literature to address specific needs. OntoMate, for example, uses natural language processing to curate gene and phenotype ontology from the titles and abstracts of PubMed literature ( Liu et al 2015 ). PubMatrix uses text mining to build a frequency matrix of term co-occurrence ( Becker et al 2003 ).…”

mentioning

confidence: 99%

BioLitMine: Advanced Mining of Biomedical and Biological Literature About Human Genes and Genes from Major Model Organisms

Chung

Comjean

et al. 2020

G3 Genes|Genomes|Genetics

View full text Add to dashboard Cite

The accumulation of biological and biomedical literature outpaces the ability of most researchers and clinicians to stay abreast of their own immediate fields, let alone a broader range of topics. Although available search tools support identification of relevant literature, finding relevant and key publications is not always straightforward. For example, important publications might be missed in searches with an official gene name due to gene synonyms. Moreover, ambiguity of gene names can result in retrieval of a large number of irrelevant publications. To address these issues and help researchers and physicians quickly identify relevant publications, we developed BioLitMine, an advanced literature mining tool that takes advantage of the medical subject heading (MeSH) index and gene-to-publication annotations already available for PubMed literature. Using BioLitMine, a user can identify what MeSH terms are represented in the set of publications associated with a given gene of the interest, or start with a term and identify relevant publications. Users can also use the tool to find co-cited genes and a build a literature co-citation network. In addition, BioLitMine can help users build a gene list relevant to a MeSH terms, such as a list of genes relevant to "stem cells" or "breast neoplasms." Users can also start with a gene or pathway of interest and identify authors associated with that gene or pathway, a feature that makes it easier to identify experts who might serve as collaborators or reviewers. Altogether, BioLitMine extends the value of PubMed-indexed literature and its existing expert curation by providing a robust and gene-centric approach to retrieval of relevant information.

show abstract

OntoMate: a text-mining tool aiding curation at the Rat Genome Database

Cited by 22 publications

References 18 publications

The Disease Portals, disease–gene annotation and the RGD disease ontology at the Rat Genome Database

The Disease Portals, disease–gene annotation and the RGD disease ontology at the Rat Genome Database

Text Mining to Support Gene Ontology Curation and Vice Versa

BioLitMine: Advanced Mining of Biomedical and Biological Literature About Human Genes and Genes from Major Model Organisms

Contact Info

Product

Resources

About