Tagging gene and protein names in biomedical text

By Lorraine K. Tanabe, W. John Wilbur. Bioinform., 2002

357 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/fdf8976d5e1c927ffffd87ab12132124c0938fa5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

Comparative experiments on learning information extractors for proteins and their interactions (2005, background): “The second system is ABGENE, introduced in [43].”
Mining knowledge from text using information extraction (2005, methodology): “Specifically, we evaluated Rapier, BWI, MBL, TBL, SVM, MaxEnt, HMM, and CRF by running 10-fold cross-validation on set of approximately 1,000 manuallyannotated Medline abstracts that discuss human proteins.”
Unsupervised biomedical named entity recognition: Experiments with clinical and biological texts (2013, methodology): “…information about drugs and genes relevant to cancer from the biomedical literature [34]; AbGene is one of the most successful NER systems for gene and protein [7]; MetaMap, developed by National Library of Medicine (NLM), is a tool discovering UMLS Metathesaurus concepts referred to in text [36].”
Overview of BioCreative II gene mention recognition (2008, methodology): “In 2003, as part of a project to improve on the AbGene tagger [6], a corpus of 20,000 sentences was selected and annotated for training and testing purposes [7].”
Overview of BioCreative II gene normalization (2008, methodology): “The systems were KeX [28], AbGene [29], the team's BioCreative I GM system [30], LingPipe [10], and ABNER (NLPBA and BioCreative models) [11].”
Literature mining for the biologist: from information retrieval to biological discovery (2006, methodology): “The early ER methods relied on manually devised rules that look for typical features of names — such as letters that are followed by numbers, or the ending '-ase' — as well as contextual information from nearby words such as 'gene' and 'receptor”
Term identification in the biomedical literature (2004, background): “Tanabe and Wilbur [ 39 ] presented a protein and gene name tagger, ABGENE, which has been trained on Medline abstracts by adapting Brill’s POS tagger [40].”