SR4GN: A Species Recognition Software Tool for Gene Normalization

Wei, Chih Hsuan; Kao, Hung Yu; Lu, Zhiyong

doi:10.1371/journal.pone.0038460

Cited by 75 publications

(64 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Next, gene name normalization assigns a unique gene identifier for ambiguous gene mentions in text. This step is performed with GenNorm (Wei et al, 2012), which achieved state-of-the-art performance in the BioCreative III challenge (Arighi et al, 2011). Finally, relations or events are extracted between these genes and proteins, detecting a variety of different event types ranging from phosphorylation and ubiquitination to PPIs and regulatory associations.…”

Section: Text Mining Methodologymentioning

confidence: 99%

The Potential of Text Mining in Data Integration and Network Biology for Plant Research: A Case Study onArabidopsis

et al. 2013

View full text Add to dashboard Cite

Despite the availability of various data repositories for plant research, a wealth of information currently remains hidden within the biomolecular literature. Text mining provides the necessary means to retrieve these data through automated processing of texts. However, only recently has advanced text mining methodology been implemented with sufficient computational power to process texts at a large scale. In this study, we assess the potential of large-scale text mining for plant biology research in general and for network biology in particular using a state-of-the-art text mining system applied to all PubMed abstracts and PubMed Central full texts. We present extensive evaluation of the textual data for Arabidopsis thaliana, assessing the overall accuracy of this new resource for usage in plant network analyses. Furthermore, we combine text mining information with both protein-protein and regulatory interactions from experimental databases. Clusters of tightly connected genes are delineated from the resulting network, illustrating how such an integrative approach is essential to grasp the current knowledge available for Arabidopsis and to uncover gene information through guilt by association. All largescale data sets, as well as the manually curated textual data, are made publicly available, hereby stimulating the application of text mining data in future plant biology studies.

show abstract

Section: Text Mining Methodologymentioning

confidence: 99%

The Potential of Text Mining in Data Integration and Network Biology for Plant Research: A Case Study onArabidopsis

et al. 2013

View full text Add to dashboard Cite

show abstract

“…It is based on conditional random fields and identifies many types of mutations and sequence variants in protein, gene, DNA and RNA levels for biomedical curation. This tool was developed in Perl and uses the CRF++ module developed in C++. SR4GN (16) is a species recognition tool optimized for the gene normalization task. It is a rule-based system that identifies species from full-texts and pairs them with corresponding gene or protein mentions.…”

Section: Concept Recognition Toolsmentioning

confidence: 99%

tmBioC: improving interoperability of text-mining tools with BioC

et al. 2014

Self Cite

View full text Add to dashboard Cite

The lack of interoperability among biomedical text-mining tools is a major bottleneck in creating more complex applications. Despite the availability of numerous methods and techniques for various text-mining tasks, combining different tools requires substantial efforts and time owing to heterogeneity and variety in data formats. In response, BioC is a recent proposal that offers a minimalistic approach to tool interoperability by stipulating minimal changes to existing tools and applications. BioC is a family of XML formats that define how to present text documents and annotations, and also provides easy-to-use functions to read/write documents in the BioC format. In this study, we introduce our text-mining toolkit, which is designed to perform several challenging and significant tasks in the biomedical domain, and repackage the toolkit into BioC to enhance its interoperability.Our toolkit consists of six state-of-the-art tools for named-entity recognition, normalization and annotation (PubTator) of genes (GenNorm), diseases (DNorm), mutations (tmVar), species (SR4GN) and chemicals (tmChem). Although developed within the same group, each tool is designed to process input articles and output annotations in a different format. We modify these tools and enable them to read/write data in the proposed BioC format. We find that, using the BioC family of formats and functions, only minimal changes were required to build the newer versions of the tools. The resulting BioC wrapped toolkit, which we have named tmBioC, consists of our tools in BioC, an annotated full-text corpus in BioC, and a format detection and conversion tool.Furthermore, through participation in the 2013 BioCreative IV Interoperability Track, we empirically demonstrate that the tools in tmBioC can be more efficiently integrated with each other as well as with external tools: Our experimental results show that using BioC reduces >60% in lines of code for text-mining tool integration. The tmBioC toolkit is publicly available at http://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/tmTools/.Database URL: http://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/tmTools/

show abstract

“…Similar methods have been applied to disease names (Doğan & Lu, 2012b;Kang et al, 2012;Névéol et al, 2009) and species names (Gerner et al, 2010;Wei et al, 2012b), and the MetaMap program is used to locate and identify concepts from the UMLS MetaThesaurus (Aronson, 2001;Bodenreider, 2004).…”

Section: Introductionmentioning

confidence: 99%

Automated Disease Normalization with Low Rank Approximations

Leaman¹,

2014

Proceedings of BioNLP 2014

Self Cite

View full text Add to dashboard Cite

While machine learning methods for named entity recognition (mention-level detection) have become common, machine learning methods have rarely been applied to normalization (concept-level identification). Recent research introduced a machine learning method for normalization based on pairwise learning to rank. This method, DNorm, uses a linear model to score the similarity between mentions and concept names, and has several desirable properties, including learning term variation directly from training data. In this manuscript we employ a dimensionality reduction technique based on low-rank matrix approximation, similar to latent semantic indexing. We compare the performance of the low rank method to previous work, using disease name normalization in the NCBI Disease Corpus as the test case, and demonstrate increased performance as the matrix rank increases. We further demonstrate a significant reduction in the number of parameters to be learned and discuss the implications of this result in the context of algorithm scalability.

show abstract

SR4GN: A Species Recognition Software Tool for Gene Normalization

Cited by 75 publications

References 19 publications

The Potential of Text Mining in Data Integration and Network Biology for Plant Research: A Case Study onArabidopsis

The Potential of Text Mining in Data Integration and Network Biology for Plant Research: A Case Study onArabidopsis

tmBioC: improving interoperability of text-mining tools with BioC

Automated Disease Normalization with Low Rank Approximations

Contact Info

Product

Resources

About