New challenges for text mining: mapping between text and manually curated pathways.

@article{citeulike:2784632, abstract = {BACKGROUND: Associating literature with pathways poses new challenges to the Text Mining (TM) community. There are three main challenges to this task: (1) the identification of the mapping position of a specific entity or reaction in a given pathway, (2) the recognition of the causal relationships among multiple reactions, and (3) the formulation and implementation of required inferences based on biological domain knowledge. RESULTS: To address these challenges, we constructed new resources to link the text with a model pathway; they are: the GENIA pathway corpus with event annotation and NF-kB pathway. Through their detailed analysis, we address the untapped resource, 'bio-inference,' as well as the differences between text and pathway representation. Here, we show the precise comparisons of their representations and the nine classes of 'bio-inference' schemes observed in the pathway corpus. CONCLUSIONS: We believe that the creation of such rich resources and their detailed analysis is the significant first step for accelerating the research of the automatic construction of pathway from text.}, address = {Department of Computer Science, Graduate School of Information Science and Technology, University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan. k.oda@is.s.u-tokyo.ac.jp}, author = {Oda, K. and Kim, J. D. and Ohta, T. and Okanohara, D. and Matsuzaki, T. and Tateisi, Y. and Tsujii, J. }, citeulike-article-id = {2784632}, doi = {10.1186/1471-2105-9-S3-S5}, issn = {1471-2105}, journal = {BMC bioinformatics}, keywords = {pathway, text\_mining}, posted-at = {2008-05-12 13:08:51}, priority = {2}, title = {New challenges for text mining: mapping between text and manually curated pathways.}, url = {http://dx.doi.org/10.1186/1471-2105-9-S3-S5}, volume = {9 Suppl 3}, year = {2008} }

TY - JOUR ID - citeulike:2784632 L3 - citeulike-article-id:2784632 TI - New challenges for text mining: mapping between text and manually curated pathways. JF - BMC bioinformatics VL - 9 Suppl 3 AD - Department of Computer Science, Graduate School of Information Science and Technology, University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo, Japan. k.oda@is.s.u-tokyo.ac.jp SN - 1471-2105 N2 - BACKGROUND: Associating literature with pathways poses new challenges to the Text Mining (TM) community. There are three main challenges to this task: (1) the identification of the mapping position of a specific entity or reaction in a given pathway, (2) the recognition of the causal relationships among multiple reactions, and (3) the formulation and implementation of required inferences based on biological domain knowledge. RESULTS: To address these challenges, we constructed new resources to link the text with a model pathway; they are: the GENIA pathway corpus with event annotation and NF-kB pathway. Through their detailed analysis, we address the untapped resource, 'bio-inference,' as well as the differences between text and pathway representation. Here, we show the precise comparisons of their representations and the nine classes of 'bio-inference' schemes observed in the pathway corpus. CONCLUSIONS: We believe that the creation of such rich resources and their detailed analysis is the significant first step for accelerating the research of the automatic construction of pathway from text. KW - pathway KW - text_mining AU - Oda, K AU - Kim, JD AU - Ohta, T AU - Okanohara, D AU - Matsuzaki, T AU - Tateisi, Y AU - Tsujii, J PY - 2008/// UR - http://dx.doi.org/10.1186/1471-2105-9-S3-S5 ER -