%0 Conference Paper %1 Spangler:2014:AHG:2623330.2623667 %A Spangler, Scott %A Wilkins, Angela D. %A Bachman, Benjamin J. %A Nagarajan, Meena %A Dayaram, Tajhal %A Haas, Peter %A Regenbogen, Sam %A Pickering, Curtis R. %A Comer, Austin %A Myers, Jeffrey N. %A Stanoi, Ioana %A Kato, Linda %A Lelescu, Ana %A Labrie, Jacques J. %A Parikh, Neha %A Lisewski, Andreas Martin %A Donehower, Lawrence %A Chen, Ying %A Lichtarge, Olivier %B Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining %C New York, NY, USA %D 2014 %E kdd2014, %I ACM %K P53 Protein literature-based-discovery %P 1877--1886 %R 10.1145/2623330.2623667 %T Automated Hypothesis Generation Based on Mining Scientific Literature %U http://doi.acm.org/10.1145/2623330.2623667 %X Keeping up with the ever-expanding flow of data and publications is untenable and poses a fundamental bottleneck to scientific progress. Current search technologies typically find many relevant documents, but they do not extract and organize the information content of these documents or suggest new scientific hypotheses based on this organized content. We present an initial case study on KnIT, a prototype system that mines the information contained in the scientific literature, represents it explicitly in a queriable network, and then further reasons upon these data to generate novel and experimentally testable hypotheses. KnIT combines entity detection with neighbor-text feature analysis and with graph-based diffusion of information to identify potential new properties of entities that are strongly implied by existing relationships. We discuss a successful application of our approach that mines the published literature to identify new protein kinases that phosphorylate the protein tumor suppressor p53. Retrospective analysis demonstrates the accuracy of this approach and ongoing laboratory experiments suggest that kinases identified by our system may indeed phosphorylate p53. These results establish proof of principle for automated hypothesis generation and discovery based on text mining of the scientific literature. %@ 978-1-4503-2956-9

@inproceedings{Spangler:2014:AHG:2623330.2623667, abstract = {Keeping up with the ever-expanding flow of data and publications is untenable and poses a fundamental bottleneck to scientific progress. Current search technologies typically find many relevant documents, but they do not extract and organize the information content of these documents or suggest new scientific hypotheses based on this organized content. We present an initial case study on KnIT, a prototype system that mines the information contained in the scientific literature, represents it explicitly in a queriable network, and then further reasons upon these data to generate novel and experimentally testable hypotheses. KnIT combines entity detection with neighbor-text feature analysis and with graph-based diffusion of information to identify potential new properties of entities that are strongly implied by existing relationships. We discuss a successful application of our approach that mines the published literature to identify new protein kinases that phosphorylate the protein tumor suppressor p53. Retrospective analysis demonstrates the accuracy of this approach and ongoing laboratory experiments suggest that kinases identified by our system may indeed phosphorylate p53. These results establish proof of principle for automated hypothesis generation and discovery based on text mining of the scientific literature.}, acmid = {2623667}, added-at = {2014-08-27T21:06:51.000+0200}, address = {New York, NY, USA}, author = {Spangler, Scott and Wilkins, Angela D. and Bachman, Benjamin J. and Nagarajan, Meena and Dayaram, Tajhal and Haas, Peter and Regenbogen, Sam and Pickering, Curtis R. and Comer, Austin and Myers, Jeffrey N. and Stanoi, Ioana and Kato, Linda and Lelescu, Ana and Labrie, Jacques J. and Parikh, Neha and Lisewski, Andreas Martin and Donehower, Lawrence and Chen, Ying and Lichtarge, Olivier}, biburl = {https://www.bibsonomy.org/bibtex/26e8114fc99eb334b540285185bf19ae4/huiyangsfsu}, booktitle = {Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining}, doi = {10.1145/2623330.2623667}, editor = {kdd2014}, interhash = {7eff94e4d85ead5eef86c9b4f0e414ad}, intrahash = {6e8114fc99eb334b540285185bf19ae4}, isbn = {978-1-4503-2956-9}, keywords = {P53 Protein literature-based-discovery}, location = {New York, New York, USA}, numpages = {10}, pages = {1877--1886}, publisher = {ACM}, series = {KDD '14}, timestamp = {2014-08-27T21:06:51.000+0200}, title = {Automated Hypothesis Generation Based on Mining Scientific Literature}, url = {http://doi.acm.org/10.1145/2623330.2623667}, year = 2014 }