Dataset Information

Bio-Ontology and text: bridging the modeling gap.

ABSTRACT: 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.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).http://zellig.cpmc.columbia.edu/PGschema

SUBMITTER: Friedman C

PROVIDER: S-EPMC2879055 | biostudies-literature | 2006 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Bio-Ontology and text: bridging the modeling gap.

Friedman Carol C Borlawsky Tara T Shagina Lyudmila L Xing H Rosie HR Lussier Yves A YA

Bioinformatics (Oxford, England) 20060726 19

<h4>Motivation</h4>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 ...[more]

PMID: 16870928

Similar Datasets

Project description:Simple Summary Chemotherapy-induced peripheral neuropathy (CIPN) remains a clinical challenge with a considerable impact on the effective treatment of cancers and quality of life during and after concluding chemotherapy. Given the limited understanding of CIPN, there are no options for the treatment and prevention of CIPN. Decades of research with the unsuccessful translation of preclinical findings to clinical studies argue for the requirement of human model systems. This review focuses on the translational potential of human induced pluripotent stem cells (iPSCs) in CIPN research. We provide an overview of the current studies and discuss important aspects to improve the translation of in vitro findings. We identified distinct effects on the neurite network and cell viability upon exposure to different classes of chemotherapy. Our study revealed considerable variability between donors and between neurons of the central and peripheral nervous system. Translational success may be improved by including multiple iPSC donors with known clinical data and selecting clinically relevant concentrations. Abstract Chemotherapy-induced peripheral neuropathy (CIPN) is a common and potentially serious adverse effect of a wide range of chemotherapeutics. The lack of understanding of the molecular mechanisms underlying CIPN limits the efficacy of chemotherapy and development of therapeutics for treatment and prevention of CIPN. Human induced pluripotent stem cells (iPSCs) have become an important tool to generate the cell types associated with CIPN symptoms in cancer patients. We reviewed the literature for iPSC-derived models that assessed neurotoxicity among chemotherapeutics associated with CIPN. Furthermore, we discuss the gaps in our current knowledge and provide guidance for selecting clinically relevant concentrations of chemotherapy for in vitro studies. Studies in iPSC-derived neurons revealed differential sensitivity towards mechanistically diverse chemotherapeutics associated with CIPN. Additionally, the sensitivity to chemotherapy was determined by donor background and whether the neurons had a central or peripheral nervous system identity. We propose to utilize clinically relevant concentrations that reflect the free, unbound fraction of chemotherapeutics in plasma in future studies. In conclusion, iPSC-derived sensory neurons are a valuable model to assess CIPN; however, studies in Schwann cells and motor neurons are warranted. The inclusion of multiple iPSC donors and concentrations of chemotherapy known to be achievable in patients can potentially improve translational success.

Project description:BackgroundDetermining usefulness of biomedical text mining systems requires realistic task definition and data selection criteria without artificial constraints, measuring performance aspects that go beyond traditional metrics. The BioCreative III Protein-Protein Interaction (PPI) tasks were motivated by such considerations, trying to address aspects including how the end user would oversee the generated output, for instance by providing ranked results, textual evidence for human interpretation or measuring time savings by using automated systems. Detecting articles describing complex biological events like PPIs was addressed in the Article Classification Task (ACT), where participants were asked to implement tools for detecting PPI-describing abstracts. Therefore the BCIII-ACT corpus was provided, which includes a training, development and test set of over 12,000 PPI relevant and non-relevant PubMed abstracts labeled manually by domain experts and recording also the human classification times. The Interaction Method Task (IMT) went beyond abstracts and required mining for associations between more than 3,500 full text articles and interaction detection method ontology concepts that had been applied to detect the PPIs reported in them.ResultsA total of 11 teams participated in at least one of the two PPI tasks (10 in ACT and 8 in the IMT) and a total of 62 persons were involved either as participants or in preparing data sets/evaluating these tasks. Per task, each team was allowed to submit five runs offline and another five online via the BioCreative Meta-Server. From the 52 runs submitted for the ACT, the highest Matthew's Correlation Coefficient (MCC) score measured was 0.55 at an accuracy of 89% and the best AUC iP/R was 68%. Most ACT teams explored machine learning methods, some of them also used lexical resources like MeSH terms, PSI-MI concepts or particular lists of verbs and nouns, some integrated NER approaches. For the IMT, a total of 42 runs were evaluated by comparing systems against manually generated annotations done by curators from the BioGRID and MINT databases. The highest AUC iP/R achieved by any run was 53%, the best MCC score 0.55. In case of competitive systems with an acceptable recall (above 35%) the macro-averaged precision ranged between 50% and 80%, with a maximum F-Score of 55%.ConclusionsThe results of the ACT task of BioCreative III indicate that classification of large unbalanced article collections reflecting the real class imbalance is still challenging. Nevertheless, text-mining tools that report ranked lists of relevant articles for manual selection can potentially reduce the time needed to identify half of the relevant articles to less than 1/4 of the time when compared to unranked results. Detecting associations between full text articles and interaction detection method PSI-MI terms (IMT) is more difficult than might be anticipated. This is due to the variability of method term mentions, errors resulting from pre-processing of articles provided as PDF files, and the heterogeneity and different granularity of method term concepts encountered in the ontology. However, combining the sophisticated techniques developed by the participants with supporting evidence strings derived from the articles for human interpretation could result in practical modules for biological annotation workflows.

Dataset Information

Bio-Ontology and text: bridging the modeling gap.

Publications

Bio-Ontology and text: bridging the modeling gap.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets