%0 Journal Article %J Decision Support Systems %D 2007 %T Large-scale regulatory network analysis from microarray data: Modified Bayesian network learning and association rule mining %A Huang,Zan %A Li,Jiexun %A Su,Hua %A Watts,George S. %A Chen,Hsinchun %K BIS %B Decision Support Systems %V 43 %P 1207-1225 %8 2007 %G eng %2 a %4 86818299904 %$ 86818299904 %0 Journal Article %J IEEE Transactions on Information Technology in Biomedicine %D 2007 %T Optimal search-based gene subset selection for gene array cancer classification %A Li,Jiexun %A Su,Hua %A Chen,Hsinchun %A Futscher,Bernard W. %K BIS %B IEEE Transactions on Information Technology in Biomedicine %V 11 %P 398-405 %8 2007 %G eng %N 4 %2 a %4 86818201600 %$ 86818201600 %0 Journal Article %J IEEE Transactions on Information Technology in Biomedicine %D 2007 %T User-Centered Evaluation of Arizona BioPathway: An Information Extraction, Integration, and Visualization System %A Quiñones,Karin D. %A Su,Hua %A Marshall,Byron %A Eggers,Shauna %A Chen,Hsinchun %K Accounting %K BIS %X Explosive growth in biomedical research has made automated information extraction, knowledge integration, and visualization increasingly important and critically needed. The Arizona BioPathway (ABP) system extracts and displays biological regulatory pathway information from the abstracts of journal articles. This study uses relations extracted from more than 200 PubMed abstracts presented in a tabular and graphical user interface with built-in search and aggregation functionality. This article presents a task-centered assessment of the usefulness and usability of the ABP system focusing on its relation aggregation and visualization functionalities. Results suggest that our graph-based visualization is more efficient in supporting pathway analysis tasks and is perceived as more useful and easier to use as compared to a text-based literature viewing method. Relation aggregation significantly contributes to knowledge acquisition efficiency. Together, the graphic and tabular views in the ABP Visualizer provide a flexible and effective interface for pathway relation browsing and analysis. Our study contributes to pathway-related research and biological information extraction by assessing the value of a multi-view, relation-based interface which supports user-controlled exploration of pathway information across multiple granularities. %B IEEE Transactions on Information Technology in Biomedicine %V 11 %P 527-536 %8 2007 %G eng %U http://ieeexplore.ieee.org/xpls/abs_all.jsp?isnumber=4300830&arnumber=4300844&count=17&index=5 %N 5 %2 a %4 648212480 %$ 648212480 %0 Journal Article %J IEEE Transactions on Information Technology in Biomedicine %D 2006 %T Aggregating Automatically Extracted Regulatory Pathway Relations %A Marshall,Byron %A Su,Hua %A McDonald,Daniel %A Eggers,Shauna %A Chen,Hsinchun %K Accounting %K BIS %X Automatic tools to extract information from biomedical texts are needed to help researchers leverage the vast and increasing body of biomedical literature. While several biomedical relation extraction systems have been created and tested, little work has been done to meaningfully organize the extracted relations. Organizational processes should consolidate multiple references to the same objects over various levels of granularity, connect those references to other resources, and capture contextual information. We propose a feature decomposition approach to relation aggregation to support a five-level aggregation framework. Our BioAggregate tagger uses this approach to identify key features in extracted relation name strings. We show encouraging feature assignment accuracy and report substantial consolidation in a network of extracted relations. %B IEEE Transactions on Information Technology in Biomedicine %V 10 %P 100- 108 %8 2006 %G eng %U http://people.oregonstate.edu/~marshaby/Papers/Marshall_IEEE_TITB_2005.pdf %N 1 %2 a %4 648208384 %$ 648208384 %0 Generic %D 2006 %T A Bayesian framework of integrating gene functional relations from heterogeneous data sources %A Li,Jiexun %A Li,Xin %A Su,Hua %A Chen,Hsinchun %K BIS %B American Medical Informatics Association (AMIA) Spring Congress %C Phoenix, AZ, USA %8 2006 %G eng %2 c %4 98584031232 %$ 98584031232 %0 Journal Article %J Bioinformatics %D 2006 %T A framework of integrating gene functional relations from heterogeneous data sources: An experiment on Arabidopsis thaliana %A Li,Jiexun %A Li,Xin %A Su,Hua %A Chen,Hsinchun %A Galbraith,David W. %K BIS %B Bioinformatics %V 22 %P 2037-2043 %8 2006 %G eng %N 16 %2 a %4 86818365440 %$ 86818365440 %0 Generic %D 2006 %T Optimal search-based gene subset selection for microarray cancer classification %A Li,Jiexun %A Su,Hua %A Chen,Hsinchun %A Futscher,Bernard W %K BIS %B American Medical Informatics Association (AMIA) Spring Congress %C Phoenix, AZ, USA %8 2006 %G eng %2 c %4 98584055808 %$ 98584055808 %0 Conference Paper %B Proceedings of the Pacific Symposium on Biocomputing, Jan 4-8, 2005, Big Island, Hawaii %D 2005 %T Linking Ontological Resources Using Aggregatable Substance Identifiers to Organize Extracted Relations %A Marshall,Byron %A Su,Hua %A McDonald,Dan %A Chen,Hsinchun %K Accounting %K BIS %X Systems that extract biological regulatory pathway relations from free-text sources are
intended to help researchers leverage vast and growing collections of research literature.
Several systems to extract such relations have been developed but little work has focused on
how those relations can be usefully organized (aggregated) to support visualization systems or
analysis algorithms. Ontological resources that enumerate name strings for different types of
biomedical objects should play a key role in the organization process. In this paper we
delineate five potentially useful levels of relational granularity and propose the use of
aggregatable substance identifiers to help reduce lexical ambiguity. An aggregatable
substance identifier applies to a gene and its products. We merged 4 extensive lexicons and
compared the extracted strings to the text of five million MEDLINE abstracts. We report on
the ambiguity within and between name strings and common English words. Our results show
an 89% reduction in ambiguity for the extracted human substance name strings when using an
aggregatable substance approach. %B Proceedings of the Pacific Symposium on Biocomputing, Jan 4-8, 2005, Big Island, Hawaii %8 2005 %G eng %U http://people.oregonstate.edu/~marshaby/Papers/marshall_PSB2005.pdf %2 b %4 2606753793 %$ 2606753793 %0 Generic %D 2005 %T Optimal search based gene selection for cancer prognosis %A Li,Jiexun %A Su,Hua %A Chen,Hsinchun %K BIS %B Americas Conference on Information Systems (AMCIS’05) %C Omaha, NE %8 2005 %G eng %2 c %4 98584080384 %$ 98584080384 %0 Conference Paper %B Proceedings of the 2005 Joint ACM/IEEE Conference on Digital Libraries (JCDL 2005), June 7-11, 2005 , Denver, CO %D 2005 %T Visualizing Aggregated Biological Pathway Relations %A Marshall,Byron %A Quiñones,Karin %A Su,Hua %A Eggers,Shauna %A Chen,Hsinchun %K Accounting %K BIS %X The Genescene development team has constructed an aggregation interface for automatically-extracted biomedical pathway
relations that is intended to help researchers identify and process relevant information from the vast digital library of abstracts found in the National Library of Medicine’s PubMed collection.
Users view extracted relations at various levels of relational granularity in an interactive and visual node-link interface. Anecdotal feedback reported here suggests that this multigranular visual paradigm aligns well with various research tasks,
helping users find relevant articles and discover new information. %B Proceedings of the 2005 Joint ACM/IEEE Conference on Digital Libraries (JCDL 2005), June 7-11, 2005 , Denver, CO %8 2005 %G eng %U http://people.oregonstate.edu/~marshaby/Papers/Marshall_JCDL_2005_Aggregation.pdf %2 b %4 2606727169 %$ 2606727169 %0 Journal Article %J Bioinformatics %D 2004 %T Extracting Gene Pathway Relations Using a Hybrid Grammar: The Arizona Relation Parser %A McDonald,Dan %A Chen,Hsinchun %A Su,Hua %A Marshall,Byron %K Accounting %K BIS %X Motivation: Text-mining research in the biomedical domain has been motivated by the rapid growth of new research findings. Improving the accessibility of findings has potential to speed hypothesis generation.Results: We present the Arizona Relation Parser that differs from other parsers in its use of a broad coverage syntax-semantic hybrid grammar. While syntax grammars have generally been tested over more documents, semantic grammars have outperformed them in precision and recall. We combined access to syntax and semantic information from a single grammar. The parser was trained using 40 PubMed abstracts and then tested using 100 unseen abstracts, half for precision and half for recall. Expert evaluation showed that the parser extracted biologically relevant relations with 89% precision. Recall of expert identified relations with semantic filtering was 35 and 61% before semantic filtering. Such results approach the higher-performing semantic parsers. However, the AZ parser was tested over a greater variety of writing styles and semantic content. %B Bioinformatics %V 20 %P 3370-8 %8 2004 %G eng %U http://people.oregonstate.edu/~marshaby/Papers/MCDONALD_BIOINFORMATICS.pdf %N 18 %2 a %4 648206336 %$ 648206336