Biomedical knowledge engineering approaches driven by processing the primary experimental literature.

Abstract

Event Abstract Back to Event Biomedical knowledge engineering approaches driven by processing the primary experimental literature. Gully Burns1*, Eduard Hovy1 and Tommy Ingulfsen1 1 USC Information Sciences Institute, United States In general, there is a difference of scale between neuroinformatics and bioinformatics databases. For example, the CoCoMac system (a mature solution concerned with inter-area connections in the cerebral cortex of the Macaque) contained roughly 39,748 connection reports from 413 papers. By way of contrast, the Mouse Genome Informatics system contains 2,237,293 Mouse nucleotide sequences from 128,274 references. Why is this? Why are neuroscience databases not larger? It is not because of paucity of available data: the number of full-text articles available online is of the scale of millions. The absence of two key components prevents us from leveraging this abundance into large-scale, computationally-tractable resources. (A) Much of the information occurs as natural language text and (B) no general-purpose Knowledge Representation (KR) appropriately captures the semantics of experimental observations appropriately (i.e., in a mathematically tractable format that is also understandable to biologists). Bioinformatics systems use high-throughput methods of data acquisition and require only simple structures for data modeling. Here we present a strategy for the construction of knowledge bases from the biomedical literature based on a relatively-simple, generally-applicable knowledge representation for scientific observations called €˜Knowledge Engineering from Experimental Design€™ (€˜KE-f-ED€™). This approach is based on the experimental variables being studied and provides a way to represent data, significance relations and correlations in a generalized informatics framework. We describe the basic theory behind the model, and demonstrate a sample implementation in the domain of neuroendocrinology. We also illustrate how this approach can provide a substrate for semi-automated knowledge acquisition through text-mining. We performed information extraction work over the primary experimental research literature to locate and identify named brain regions. In collaboration with Elsevier Science, we downloaded 39,643 full-text articles as XML documents (and 117,602 as PDFs) multiple neuroanatomically-focused journals. We used Conditional Random Fields to analyze these texts and to annotate individual mentions of variables derived from generic tract-tracing experiments. Finally, we generalize these results ontologically to apply to other variables used in other experimental types. Conference: Neuroinformatics 2008, Stockholm, Sweden, 7 Sep - 9 Sep, 2008. Presentation Type: Poster Presentation Topic: General Neuroinformatics Citation: Burns G, Hovy E and Ingulfsen T (2008). Biomedical knowledge engineering approaches driven by processing the primary experimental literature.. Front. Neuroinform. Conference Abstract: Neuroinformatics 2008. doi: 10.3389/conf.neuro.11.2008.01.011 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 28 Jul 2008; Published Online: 28 Jul 2008. * Correspondence: Gully Burns, USC Information Sciences Institute, Marina del Rey, United States, burns@isi.edu Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Gully Burns Eduard Hovy Tommy Ingulfsen Google Gully Burns Eduard Hovy Tommy Ingulfsen Google Scholar Gully Burns Eduard Hovy Tommy Ingulfsen PubMed Gully Burns Eduard Hovy Tommy Ingulfsen Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.