Bio-Ontology and text: bridging the modeling gap

@article{citeulike:1107778, abstract = {Motivation: Natural language processing (NLP) techniques are increasingly being used in biology to automate the capture of new biological discoveries in text, which are being reported at a rapid rate. Yet, information represented in NLP data structures is classically very different from information organized with ontologies as found in model organisms or genetic databases. To facilitate the computational reuse and integration of information buried in unstructured text with that of genetic databases, we propose and evaluate a translational schema that represents a comprehensive set of phenotypic and genetic entities, as well as their closely related biomedical entities and relations as expressed in natural language. In addition, the schema connects different scales of biological information, and provides mappings from the textual information to existing ontologies, which are essential in biology for integration, organization, dissemination and knowledge management of heterogeneous phenotypic information. A common comprehensive representation for otherwise heterogeneous phenotypic and genetic datasets, such as the one proposed, is critical for advancing systems biology because it enables acquisition and reuse of unprecedented volumes of diverse types of knowledge and information from text. Results: A novel representational schema, PGschema, was developed that enables translation of phenotypic, genetic and their closely related information found in textual narratives to a well-defined data structure comprising phenotypic and genetic concepts from established ontologies along with modifiers and relationships. Evaluation for coverage of a selected set of entities showed that 90\% of the information could be represented (95\% confidence interval: 86-93\%; n = 268). Moreover, PGschema can be expressed automatically in an XML format using natural language techniques to process the text. To our knowledge, we are providing the first evaluation of a translational schema for NLP that contains declarative knowledge about genes and their associated biomedical data (e.g. phenotypes). Availability: http://zellig.cpmc.columbia.edu/PGschema Contact: Friedman@dbmi.columbia.edu or Lussier@uchicago.edu 10.1093/bioinformatics/btl405}, author = {Friedman, Carol and Borlawsky, Tara and Shagina, Lyudmila and Xing, Rosie H. and Lussier, Yves A. }, citeulike-article-id = {1107778}, doi = {http://dx.doi.org/10.1093/bioinformatics/btl405}, journal = {Bioinformatics}, keywords = {bioinformatics, nlp, ontology, text}, month = {October}, number = {19}, pages = {2421--2429}, posted-at = {2007-03-22 21:49:40}, priority = {2}, title = {Bio-Ontology and text: bridging the modeling gap}, url = {http://dx.doi.org/10.1093/bioinformatics/btl405}, volume = {22}, year = {2006} }

TY - JOUR ID - citeulike:1107778 L3 - citeulike-article-id:1107778 N2 - Motivation: Natural language processing (NLP) techniques are increasingly being used in biology to automate the capture of new biological discoveries in text, which are being reported at a rapid rate. Yet, information represented in NLP data structures is classically very different from information organized with ontologies as found in model organisms or genetic databases. To facilitate the computational reuse and integration of information buried in unstructured text with that of genetic databases, we propose and evaluate a translational schema that represents a comprehensive set of phenotypic and genetic entities, as well as their closely related biomedical entities and relations as expressed in natural language. In addition, the schema connects different scales of biological information, and provides mappings from the textual information to existing ontologies, which are essential in biology for integration, organization, dissemination and knowledge management of heterogeneous phenotypic information. A common comprehensive representation for otherwise heterogeneous phenotypic and genetic datasets, such as the one proposed, is critical for advancing systems biology because it enables acquisition and reuse of unprecedented volumes of diverse types of knowledge and information from text. Results: A novel representational schema, PGschema, was developed that enables translation of phenotypic, genetic and their closely related information found in textual narratives to a well-defined data structure comprising phenotypic and genetic concepts from established ontologies along with modifiers and relationships. Evaluation for coverage of a selected set of entities showed that 90% of the information could be represented (95% confidence interval: 86-93%; n = 268). Moreover, PGschema can be expressed automatically in an XML format using natural language techniques to process the text. To our knowledge, we are providing the first evaluation of a translational schema for NLP that contains declarative knowledge about genes and their associated biomedical data (e.g. phenotypes). Availability: http://zellig.cpmc.columbia.edu/PGschema Contact: Friedman@dbmi.columbia.edu or Lussier@uchicago.edu 10.1093/bioinformatics/btl405 IS - 19 JF - Bioinformatics EP - 2429 TI - Bio-Ontology and text: bridging the modeling gap VL - 22 SP - 2421 KW - bioinformatics KW - nlp KW - ontology KW - text AU - Friedman, Carol AU - Borlawsky, Tara AU - Shagina, Lyudmila AU - Xing, Rosie AU - Lussier, Yves PY - 2006/10/01/ UR - http://dx.doi.org/10.1093/bioinformatics/btl405 ER -