Identification of gene function using prediction by partial matching (PPM) language models

ABSTRACT

In this paper, we describe the utilization of text encoding and prediction by partial matching language modeling to identify gene functions within abstracts of biomedical papers. The National Center for Biotechnology Information has "GeneRIF" - a collection of the best possible functional representations for a subset of abstracts from PubMed. We use GeneRIF to test the efficiency of our technique. We discuss the methodology adopted to construct models necessary to enable the Text Mining Toolkit to distinguish between gene functions and the rest of the abstract (non gene functions). We also describe the similarity based approach we deploy on the list of automatically annotated functions to generate the most likely gene function representative of the paper. The results indicate that our combined approach to identify gene functions in scientific abstracts performs very well on both precision and recall, and therefore presents exciting opportunities for use in extracting other entities embedded in scientific text.

REFERENCES

• 1: PubMed; http://www.ncbi.nlm.nih.gov/entrez/ (2008).
• 2: Ken Ichiro Fukuda , Toshihisa Takagi, A pathway editor for literature-based knowledge curation, Proceedings of the second conference on Asia-Pacific bioinformatics, p.339-344, January 01, 2004, Dunedin, New Zealand
• 3: Bickel, S. , Brefeld, U., Faulstich, L., Jörg , et al. (2004) "Support Vector Machine Classifier for Gene Name Recognition". EMBO Workshop: A critical assessment of text mining methods in molecular biology. Granada, Spain, March.
• 4: Ono T, Hishigaki H, Tanigami A, Takagi T. (2001) "Automated extraction of information on protein-protein interactions from the biological literature". Bioinformatics, Feb;17(2):155--61.
• 5: Sven Mika , Burkhard Rost, Protein names precisely peeled off free text, Bioinformatics, v.20 n.1, p.241-247, January 2004 [doi>10.1093/bioinformatics/bth904]
• 6: Hanisch, D., Fluck, J., Mevissen, H. and Zimmer,R. (2003) Playing Biology's name game: identifying protein names in scientific text. Pacific Symposium on Biocomputing.,403--414.
• 7: Kaoru Yamamoto , Taku Kudo , Akihiko Konagaya , Yuji Matsumoto, Protein name tagging for biomedical annotation in text, Proceedings of the ACL 2003 workshop on Natural language processing in biomedicine, p.65-72, July 11-11, 2003, Sapporo, Japan [doi>10.3115/1118958.1118967]
• 8: Jeffrey T. Chang , Hinrich Schütze , Russ B. Altman, GAPSCORE: finding gene and protein names one word at a time, Bioinformatics, v.20 n.2, p.216-225, January 2004 [doi>10.1093/bioinformatics/btg393]
• 9: Asako Koike , Yoshiki Niwa , Toshihisa Takagi, Automatic extraction of gene/protein biological functions from biomedical text, Bioinformatics, v.21 n.7, p.1227-1236, April 2005 [doi>10.1093/bioinformatics/bti084]
• 10: Chiang, J.H., Yu, H.C. (2003) "MeKE: Discovering the functions of gene products from biomedical literature using sentence alignment". Bioinformatics, Vol. 19 no. 11 2003, pages 1417-- 1422.
• 11: Raychaudhuri S., Chang J.T., Sutphin P.D., Altman R.B. (2002) "Associating genes with gene ontology codes using a maximum entropy analysis of biomedical literature". Genome Research. Jan;12(1):203--14.
• 12: Seki, K., Mostafa, J. (2003) "Towards database curation in biology automated gene function identification from text", Tech. report, Indiana University, http://lair.slis.indiana.edu/research/capris/papers.html.
• 13: Gene ontology. (2007) http://www.geneontology.org/ .
• 14: NCBI. (2008) http://www.ncbi.nlm.nih.gov/.
• 15: GeneRIF.(2007) http://www.ncbi.nlm.nih.gov/projects/GeneRIF/GeneRIFhelp.html.
• 16: Teahan, W.J. (2006) The Text Mining Toolkit. http://www.cs.bangor.ac.uk/~wjt.
• 17: Cleary, J and Witten, I. (1984) "Data compression using adaptive coding and partial string matching." IEEE Transactions on Communications,32(4),396--402.
• 18: Moffat, A. (1990) "Implementing the PPM data compression scheme." IEE Transactions on Communications, 38(11): 1917--1921.
• 19: Teahan, W. J., & Harper, D. J. (2003) "Using compression-based language models for text categorization". Language Modeling for Information Retrieval, edited by W. B. Croft, & J. Lafferty, Kluwer. page(s) 141--166.
• 20: Teahan, W.J. (1998) "Modelling English Text", Ph.D. thesis, Dept. of Computer Science, The University of Waikato.
• 21: Timothy C. Bell , John G. Cleary , Ian H. Witten, Text compression, Prentice-Hall, Inc., Upper Saddle River, NJ, 1990
• 22: Paul Glor Howard, The design and analysis of efficient lossless data compression systems, Brown University, Providence, RI, 1993
• 23: Ian H. Witten , Zane Bray , Malika Mahoui , Bill Teahan, Text Mining: A New Frontier for Lossless Compression, Proceedings of the Conference on Data Compression, p.198, March 29-31, 1999
• 24: Kevin Knight, Mining online text, Communications of the ACM, v.42 n.11, p.58-61, Nov. 1999 [doi>10.1145/319382.319394]
• 25: Jelinek, F. (1985) "Self-organized Language Modeling for Speech Recognition," IBM Report.
• 26: Shannon, C.E. (1948) "A mathematical theory of communication." Bell SystemTechnical Journal 27: 379--423, 623--656.
• 27: Viterbi, A.J. (1967) "Error bounds for convolutional codes and an asymptotically optimal decoding algorithm." IEE Trans. on Information Theory. 13, 260--269.
• 28: Yeates, S. and Witten, I.H. (2000) "On tag insertion and its complexity." Proc. PRICAI'2000 Workshop on Text and Data Mining, pages. 52--63, Melbourne, Aus.
• 29: Stuart Yeates , David Bainbridge , Ian H. Witten, Using Compression to Identify Acronyms in Text, Proceedings of the Conference on Data Compression, p.582, March 28-30, 2000
• 30: W. J. Teahan , David J. Harper, Combining PPM Models Using A Text Mining Approach, Proceedings of the Data Compression Conference (DCC '01), p.153, March 27-29, 2001
• 31: Teahan, W. (2000) "Text Classification and Segmentation Using Minimum Cross-Entropy". Proceedings of the International Conference on Content-based Multimedia Information Access (RIAO 2000), pages 943--961.
• 32: GeneRIF help. (2007) http://www.ncbi.nlm.nih.gov/projects/GeneRIF/GeneRIFhelp.html.
• 33: John G. Cleary , W. J. Teahan, An Open Interface for Probabilistic Models of Text, Proceedings of the Conference on Data Compression, p.522, March 29-31, 1999

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.7 Natural Language Processing
          Subjects: Language generation

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.7 Natural Language Processing
          Subjects: Language parsing and understanding; Machine translation; Language models; Text analysis

General Terms:
Algorithms, Design, Documentation, Experimentation, Languages, Measurement, Performance, Theory, Verification

Keywords:
entropy, gene function identification, prediction by partial matching (PPM), text mining