Journal article

The gene normalization task in BioCreative III

Zhiyong Lu, Hung-Yu Kao, Chih-Hsuan Wei, Minlie Huang, Jingchen Liu, Cheng-Ju Kuo, Chun-Nan Hsu, Richard Tzong-Han Tsai, Hong-Jie Dai, Naoaki Okazaki, Han-Cheol Cho, Martin Gerner, Illes Solt, Shashank Agarwal, Feifan Liu, Dina Vishnyakova, Patrick Ruch, Martin Romacker, Fabio Rinaldi, Sanmitra Bhattacharya Show all

BMC Bioinformatics | BIOMED CENTRAL LTD | Published : 2011

Abstract

BACKGROUND: We report the Gene Normalization (GN) challenge in BioCreative III where participating teams were asked to return a ranked list of identifiers of the genes detected in full-text articles. For training, 32 fully and 500 partially annotated articles were prepared. A total of 507 articles were selected as the test set. Due to the high annotation cost, it was not feasible to obtain gold-standard human annotations for all test articles. Instead, we developed an Expectation Maximization (EM) algorithm approach for choosing a small number of test articles for manual annotation that were most capable of differentiating team performance. Moreover, the same algorithm was subsequently used ..

View full abstract

Grants

Awarded by National Library of Medicine


Awarded by European Union


Awarded by Swiss National Science Foundation


Awarded by NIH


Awarded by NSF


Awarded by Portuguese Foundation for Science and Technology


Awarded by NATIONAL INSTITUTE OF GENERAL MEDICAL SCIENCES


Awarded by NATIONAL LIBRARY OF MEDICINE


Funding Acknowledgements

The organizers would like to thank Lynette Hirschman for her helpful discussion and feedback on the earlier version of this paper. Zhiyong Lu and W. John Wilbur were supported by the Intramural Research Program of the NIH, National Library of Medicine. For team 93, this was a collaborative work with Rune Saetre, Sampo Pyysalo, Tomoko Ohta, and Jun'ichi Tsujii, supported by Grants-in-Aid for Scientific Research on Priority Areas (MEXT) and for Solution-Oriented Research for Science and Technology (JST), Japan. The work of team 68 was performed in collaboration with Jorg Hakenberg, and was funded by the University of Manchester (for MG) and the Alexander-von-Humboldt Stiftung (for IS). Team 89 would like to thank Zuofeng Li for developing the genetic sequence based gene normalizer and acknowledge the support from the National Library of Medicine, grant numbers 5R01LM009836 to Hong Yu and 5R01LM010125 to Isaac Kohane. The Bibliomics and Text Mining (BiTeM, http://eagl.unige.ch/bitem/) group (Team 80) was supported by the European Union's FP7 (Grant DebugIT # 217139). Additional contributors to the work of Team 80: Julien Gobeill, Emilie Pasche, Douglas Teodoro, Anne-Lise Veuthey and Arnaud Gaudinat. The OntoGene group (Team 65) was partially supported by the Swiss National Science Foundation (grants 100014-118396/1 and 105315-130558/1) and by NITAS/TMS, Text Mining Services, Novartis Pharma AG, Basel, Switzerland. Additional contributors to the work of Team 65: Gerold Schneider, Simon Clematide, and Therese Vachon. Team 97 was supported by NIH 1-R01-LM009959-01A1 and NSF CAREER 0845523. Team 78 would like to thank Aditya K. Sehgal for his valuable guidance with this work. Team 70 was partially supported by the Portuguese Foundation for Science and Technology (research project PTDC/EIA-CCO/100541/2008). Team 65 would like to thank William A. Baumgartner Jr., Kevin Bretonnel Cohen, Helen L. Johnson, Christophe Roeder, Lawrence E. Hunter, and all the members of the Center for Computational Pharmacology at the University of Colorado Denver, supported by NIH grants 3T15 LM009451-03S1 to K. L., 5R01 LM010120-02 to K. V., and 5R01 LM008111-05 and 5R01 GM083649-03 to L. H. All the authors would like to thank all the annotators who produced the gold-standard annotations.