PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 11262959

Event extraction from biomedical papers using a full parser.

A Yakushiji·Y Tateisi·Y Miyao·J Tsujii
View original source ↗Export metadata ↓

Abstract

We have designed and implemented an information extraction system using a full parser to investigate the plausibility of full analysis of text using general-purpose parser and grammar applied to biomedical domain. We partially solved the problems of full parsing of inefficiency, ambiguity, and low coverage by introducing the preprocessors, and proposed the use of modules that handles partial results of parsing for further improvement. Our approach makes it possible to modularize the system, so that the IE system as a whole becomes easy to be tuned to specific domains, and easy to be maintained and improved by incorporating various techniques of disambiguation, speed up, etc. In preliminary experiment, from 133 argument structures that should be extracted from 97 sentences, we obtained 23% uniquely and 24% with ambiguity. And 20% are extractable from not complete but partial results of full parsing.

Explore related subjects

Databases, FactualElectronic Data ProcessingNatural Language ProcessingJournal Article

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

A Yakushiji, Y Tateisi, Y Miyao, J Tsujii. 2001. Event extraction from biomedical papers using a full parser.. https://doi.org/10.1142/9789814447362_0040

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2003

Using a geographical information system to plan a malaria control programme in South Africa.

INTRODUCTION: Sustainable control of malaria in sub-Saharan Africa is jeopardized by dwindling public health resources resulting from competing health priorities that include an overwhelming acquired immunodeficiency syndrome (AIDS) epidemic. In Mpumalanga province, South Africa, rational planning has historically been hampered by a case surveillance system for malaria that only provided estimates of risk at the magisterial district level (a subdivision of a province). METHODS: To better map control programme activities to their geographical location, the malaria notification system was overhauled and a geographical information system implemented. The introduction of a simplified notification form used only for malaria and a carefully monitored notification system provided the good quality data necessary to support an effective geographical information system. RESULTS: The geographical information system displays data on malaria cases at a village or town level and has proved valuable in stratifying malaria risk within those magisterial districts at highest risk, Barberton and Nkomazi. The conspicuous west-to-east gradient, in which the risk rises sharply towards the Mozambican border (relative risk = 4.12, 95% confidence interval = 3.88-4.46 when the malaria risk within 5 km of the border was compared with the remaining areas in these two districts), allowed development of a targeted approach to control. DISCUSSION: The geographical information system for malaria was enormously valuable in enabling malaria risk at town and village level to be shown. Matching malaria control measures to specific strata of endemic malaria has provided the opportunity for more efficient malaria control in Mpumalanga province.

Databases, Factual↗
PubMed2002

OpenRIMS: an open architecture radiology informatics management system.

The benefits of an integrated picture archiving and communication system/radiology information system (PACS/RIS) archive built with open source tools and methods are 2-fold. Open source permits an inexpensive development model where interfaces can be updated as needed, and the code is peer reviewed by many eyes (analogous to the scientific model). Integration of PACS/RIS functionality reduces the risk of inconsistent data by reducing interfaces among databases that contain largely redundant information. Also, wide adoption would promote standard data mining tools--reducing user needs to learn multiple methods to perform the same task. A model has been constructed capable of accepting HL7 orders, performing examination and resource scheduling, providing digital imaging and communications in medicine (DICOM) worklist information to modalities, archiving studies, and supporting DICOM query/retrieve from third party viewing software. The multitiered architecture uses a single database communicating via an ODBC bridge to a Linux server with HL7, DICOM, and HTTP connections. Human interaction is supported via a web browser, whereas automated informatics services communicate over the HL7 and DICOM links. The system is still under development, but the primary database schema is complete as well as key pieces of the web user interface. Additional work is needed on the DICOM/HL7 interface broker and completion of the base DICOM service classes.

Databases, Factual↗
PubMed2002

DrugScore meets CoMFA: adaptation of fields for molecular comparison (AFMoC) or how to tailor knowledge-based pair-potentials to a particular protein.

The development of a new tailor-made scoring function to predict binding affinities of protein-ligand complexes is described. Knowledge-based pair-potentials are specifically adapted to a particular protein by considering additional ligand-based information. The formalism applied to derive the new function is similar to the well-known CoMFA approach, however, the fields used in the approach originate from the protein environment (and not from the aligned ligands as in CoMFA, thus, a "reverse" CoMFA (= AFMoC) named Adaptation of Fields for Molecular Comparison is performed). A regular-spaced grid is placed into the binding site and knowledge-based pair-potentials between protein atoms and ligand atom probes are mapped onto the grid intersections resulting in "potential fields". By multiplying distance-dependent atom-type properties of actual ligands docked into the binding site with the neighboring grid values, "interaction fields" are produced from the original "potential fields". In a PLS analysis, these atom-type specific interaction fields are correlated to the actual binding affinities of the embedded ligands, resulting in individual weighting factors for each field value. As in CoMFA, the results of the analysis can be interpreted in graphical terms by contribution maps, and binding affinities of novel ligands are predicted by applying the derived 3D QSAR equation. The scope of the new method is demonstrated using thermolysin and glycogen phosphorylase b as test examples. Impressive improvements of the predictive power for affinity prediction can be achieved compared to the application of the original knowledge-based potentials by considering a sample set of only 15 known training ligands. Thus, with growing information about the drug target studied, the new method allows one to move gradually from generally valid to protein-specifically adapted pair-potentials, depending on the amount of training information available and its degree of structural diversity. In addition, convincing predictive power is also achieved for ligand poses generated by automatic docking tools.

Databases, Factual↗